/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/322e194ff797/Qwen3.8-27B-UD-Q4_K_M.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 999 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.094.609 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.094.661 I srv llama_server: initializing ... 0.00.094.667 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.094.747 I srv init_listene: The UI is disabled 0.00.094.749 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.094.782 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.096.452 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/322e194ff797/Qwen3.8-27B-UD-Q4_K_M.gguf' 0.00.621.415 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.621.423 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.621.430 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.621.432 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.621.435 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.621.443 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.621.445 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.621.447 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.621.449 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.621.451 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.621.453 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.621.456 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.621.459 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.621.461 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.621.468 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.436.795 I cmn init: llama threadpool init, n_threads = 8 0.01.843.301 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.01.846.871 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.846.885 I srv llama_server: model loaded 0.01.846.887 I srv llama_server: listening on http://127.0.0.1:8091 0.32.574.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.574.541 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.32.574.542 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.574.561 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.32.574.562 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.32.574.581 I slot launch_slot_: id 2 | task 2 | processing task, is_child = 0 0.36.636.044 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.36.636.096 I slot launch_slot_: id 3 | task 4 | processing task, is_child = 0 0.36.636.103 I slot print_timing: id 0 | task 1 | prompt processing, n_tokens = 111, progress = 0.97, t = 4.06 s / 27.33 tokens per second 0.36.950.704 I slot print_timing: id 1 | task 0 | prompt processing, n_tokens = 111, progress = 0.97, t = 4.06 s / 27.33 tokens per second 0.36.962.244 I slot print_timing: id 2 | task 2 | prompt processing, n_tokens = 126, progress = 0.97, t = 4.06 s / 31.02 tokens per second 0.39.354.540 I slot print_timing: id 0 | task 1 | prompt eval time = 6381.19 ms / 115 tokens ( 55.49 ms per token, 18.02 tokens per second) 0.39.354.542 I slot print_timing: id 0 | task 1 | eval time = 398.76 ms / 2 tokens ( 398.76 ms per token, 2.51 tokens per second) 0.39.354.543 I slot print_timing: id 0 | task 1 | total time = 6779.95 ms / 117 tokens 0.39.354.543 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.39.354.544 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.354.565 I slot release: id 0 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.39.354.718 I slot print_timing: id 1 | task 0 | prompt eval time = 6381.50 ms / 115 tokens ( 55.49 ms per token, 18.02 tokens per second) 0.39.354.720 I slot print_timing: id 1 | task 0 | eval time = 398.62 ms / 2 tokens ( 398.62 ms per token, 2.51 tokens per second) 0.39.354.721 I slot print_timing: id 1 | task 0 | total time = 6780.12 ms / 117 tokens 0.39.354.721 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.39.354.721 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.354.732 I slot release: id 1 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.39.354.890 I slot print_timing: id 2 | task 2 | prompt eval time = 6381.81 ms / 130 tokens ( 49.09 ms per token, 20.37 tokens per second) 0.39.354.892 I slot print_timing: id 2 | task 2 | eval time = 398.48 ms / 2 tokens ( 398.48 ms per token, 2.51 tokens per second) 0.39.354.893 I slot print_timing: id 2 | task 2 | total time = 6780.28 ms / 132 tokens 0.39.354.893 I slot print_timing: id 2 | task 2 | graphs reused = 1 0.39.354.894 I slot print_timing: id 2 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.354.904 I slot release: id 2 | task 2 | stop processing: n_tokens = 131, truncated = 0 0.39.464.054 I slot print_timing: id 3 | task 4 | prompt eval time = 2381.50 ms / 122 tokens ( 19.52 ms per token, 51.23 tokens per second) 0.39.464.059 I slot print_timing: id 3 | task 4 | eval time = 108.79 ms / 2 tokens ( 108.79 ms per token, 9.19 tokens per second) 0.39.464.059 I slot print_timing: id 3 | task 4 | total time = 2490.30 ms / 124 tokens 0.39.464.060 I slot print_timing: id 3 | task 4 | graphs reused = 1 0.39.464.060 I slot print_timing: id 3 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.464.078 I slot release: id 3 | task 4 | stop processing: n_tokens = 123, truncated = 0 0.39.464.083 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.250 0.39.487.473 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.39.556.086 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.39.556.168 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 0.39.556.204 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.214 0.39.556.247 I slot launch_slot_: id 2 | task 10 | processing task, is_child = 0 0.39.556.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.236 0.39.556.306 I slot launch_slot_: id 3 | task 11 | processing task, is_child = 0 0.46.340.491 I slot print_timing: id 0 | task 9 | prompt processing, n_tokens = 156, progress = 0.97, t = 6.78 s / 22.99 tokens per second 0.47.114.489 I slot print_timing: id 1 | task 8 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.78 s / 21.82 tokens per second 0.47.118.920 I slot print_timing: id 2 | task 10 | prompt processing, n_tokens = 196, progress = 0.98, t = 6.78 s / 28.89 tokens per second 0.47.123.347 I slot print_timing: id 3 | task 11 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.78 s / 15.33 tokens per second 0.47.713.574 I slot print_timing: id 0 | task 9 | prompt eval time = 7947.42 ms / 160 tokens ( 49.67 ms per token, 20.13 tokens per second) 0.47.713.576 I slot print_timing: id 0 | task 9 | eval time = 209.83 ms / 2 tokens ( 209.83 ms per token, 4.77 tokens per second) 0.47.713.577 I slot print_timing: id 0 | task 9 | total time = 8157.25 ms / 162 tokens 0.47.713.577 I slot print_timing: id 0 | task 9 | graphs reused = 1 0.47.713.578 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.713.600 I slot release: id 0 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.47.713.751 I slot print_timing: id 1 | task 8 | prompt eval time = 7947.56 ms / 152 tokens ( 52.29 ms per token, 19.13 tokens per second) 0.47.713.755 I slot print_timing: id 1 | task 8 | eval time = 209.85 ms / 2 tokens ( 209.85 ms per token, 4.77 tokens per second) 0.47.713.755 I slot print_timing: id 1 | task 8 | total time = 8157.42 ms / 154 tokens 0.47.713.756 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.47.713.756 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.713.773 I slot release: id 1 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.47.713.940 I slot print_timing: id 2 | task 10 | prompt eval time = 7947.71 ms / 200 tokens ( 39.74 ms per token, 25.16 tokens per second) 0.47.713.945 I slot print_timing: id 2 | task 10 | eval time = 209.88 ms / 2 tokens ( 209.88 ms per token, 4.76 tokens per second) 0.47.713.945 I slot print_timing: id 2 | task 10 | total time = 8157.59 ms / 202 tokens 0.47.713.945 I slot print_timing: id 2 | task 10 | graphs reused = 1 0.47.713.946 I slot print_timing: id 2 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.713.957 I slot release: id 2 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.47.714.120 I slot print_timing: id 3 | task 11 | prompt eval time = 7947.86 ms / 108 tokens ( 73.59 ms per token, 13.59 tokens per second) 0.47.714.122 I slot print_timing: id 3 | task 11 | eval time = 209.90 ms / 2 tokens ( 209.90 ms per token, 4.76 tokens per second) 0.47.714.122 I slot print_timing: id 3 | task 11 | total time = 8157.76 ms / 110 tokens 0.47.714.123 I slot print_timing: id 3 | task 11 | graphs reused = 1 0.47.714.123 I slot print_timing: id 3 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.714.130 I slot release: id 3 | task 11 | stop processing: n_tokens = 109, truncated = 0 0.47.720.338 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.174 0.47.745.147 I slot launch_slot_: id 0 | task 15 | processing task, is_child = 0 0.47.817.850 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.190 0.47.817.937 I slot launch_slot_: id 1 | task 16 | processing task, is_child = 0 0.47.817.977 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.47.818.020 I slot launch_slot_: id 2 | task 17 | processing task, is_child = 0 0.47.818.038 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.257 0.47.818.069 I slot launch_slot_: id 3 | task 18 | processing task, is_child = 0 0.53.838.407 I slot print_timing: id 0 | task 15 | prompt processing, n_tokens = 113, progress = 0.97, t = 6.02 s / 18.77 tokens per second 0.54.270.665 I slot print_timing: id 1 | task 16 | prompt processing, n_tokens = 114, progress = 0.97, t = 6.02 s / 18.94 tokens per second 0.54.275.115 I slot print_timing: id 2 | task 17 | prompt processing, n_tokens = 146, progress = 0.97, t = 6.02 s / 24.25 tokens per second 0.54.279.526 I slot print_timing: id 3 | task 18 | prompt processing, n_tokens = 121, progress = 0.97, t = 6.02 s / 20.10 tokens per second 0.54.869.672 I slot print_timing: id 0 | task 15 | prompt eval time = 6841.34 ms / 117 tokens ( 58.47 ms per token, 17.10 tokens per second) 0.54.869.677 I slot print_timing: id 0 | task 15 | eval time = 210.26 ms / 2 tokens ( 210.26 ms per token, 4.76 tokens per second) 0.54.869.678 I slot print_timing: id 0 | task 15 | total time = 7051.60 ms / 119 tokens 0.54.869.679 I slot print_timing: id 0 | task 15 | graphs reused = 1 0.54.869.679 I slot print_timing: id 0 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.869.700 I slot release: id 0 | task 15 | stop processing: n_tokens = 118, truncated = 0 0.54.869.851 I slot print_timing: id 1 | task 16 | prompt eval time = 6841.48 ms / 118 tokens ( 57.98 ms per token, 17.25 tokens per second) 0.54.869.856 I slot print_timing: id 1 | task 16 | eval time = 210.28 ms / 2 tokens ( 210.28 ms per token, 4.76 tokens per second) 0.54.869.856 I slot print_timing: id 1 | task 16 | total time = 7051.76 ms / 120 tokens 0.54.869.857 I slot print_timing: id 1 | task 16 | graphs reused = 1 0.54.869.857 I slot print_timing: id 1 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.869.866 I slot release: id 1 | task 16 | stop processing: n_tokens = 119, truncated = 0 0.54.870.039 I slot print_timing: id 2 | task 17 | prompt eval time = 6841.62 ms / 150 tokens ( 45.61 ms per token, 21.92 tokens per second) 0.54.870.043 I slot print_timing: id 2 | task 17 | eval time = 210.31 ms / 2 tokens ( 210.31 ms per token, 4.75 tokens per second) 0.54.870.043 I slot print_timing: id 2 | task 17 | total time = 7051.93 ms / 152 tokens 0.54.870.044 I slot print_timing: id 2 | task 17 | graphs reused = 1 0.54.870.044 I slot print_timing: id 2 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.870.055 I slot release: id 2 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.54.870.235 I slot print_timing: id 3 | task 18 | prompt eval time = 6841.84 ms / 125 tokens ( 54.73 ms per token, 18.27 tokens per second) 0.54.870.238 I slot print_timing: id 3 | task 18 | eval time = 210.28 ms / 2 tokens ( 210.28 ms per token, 4.76 tokens per second) 0.54.870.239 I slot print_timing: id 3 | task 18 | total time = 7052.11 ms / 127 tokens 0.54.870.239 I slot print_timing: id 3 | task 18 | graphs reused = 1 0.54.870.239 I slot print_timing: id 3 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.870.248 I slot release: id 3 | task 18 | stop processing: n_tokens = 126, truncated = 0 0.54.876.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.237 0.54.902.592 I slot launch_slot_: id 0 | task 24 | processing task, is_child = 0 0.54.977.959 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.235 0.54.978.061 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.54.978.101 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.185 0.54.978.137 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.54.978.155 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.222 0.54.978.188 I slot launch_slot_: id 3 | task 25 | processing task, is_child = 0 1.01.401.764 I slot print_timing: id 0 | task 24 | prompt processing, n_tokens = 132, progress = 0.97, t = 6.42 s / 20.55 tokens per second 1.02.191.188 I slot print_timing: id 1 | task 22 | prompt processing, n_tokens = 139, progress = 0.97, t = 6.42 s / 21.64 tokens per second 1.02.195.657 I slot print_timing: id 2 | task 23 | prompt processing, n_tokens = 115, progress = 0.97, t = 6.42 s / 17.90 tokens per second 1.02.200.097 I slot print_timing: id 3 | task 25 | prompt processing, n_tokens = 177, progress = 0.98, t = 6.42 s / 27.56 tokens per second 1.02.791.498 I slot print_timing: id 0 | task 24 | prompt eval time = 7602.58 ms / 136 tokens ( 55.90 ms per token, 17.89 tokens per second) 1.02.791.504 I slot print_timing: id 0 | task 24 | eval time = 210.72 ms / 2 tokens ( 210.72 ms per token, 4.75 tokens per second) 1.02.791.504 I slot print_timing: id 0 | task 24 | total time = 7813.30 ms / 138 tokens 1.02.791.505 I slot print_timing: id 0 | task 24 | graphs reused = 1 1.02.791.505 I slot print_timing: id 0 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.791.529 I slot release: id 0 | task 24 | stop processing: n_tokens = 137, truncated = 0 1.02.791.682 I slot print_timing: id 1 | task 22 | prompt eval time = 7602.77 ms / 143 tokens ( 53.17 ms per token, 18.81 tokens per second) 1.02.791.684 I slot print_timing: id 1 | task 22 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 1.02.791.684 I slot print_timing: id 1 | task 22 | total time = 7813.47 ms / 145 tokens 1.02.791.684 I slot print_timing: id 1 | task 22 | graphs reused = 1 1.02.791.685 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.791.697 I slot release: id 1 | task 22 | stop processing: n_tokens = 144, truncated = 0 1.02.791.863 I slot print_timing: id 2 | task 23 | prompt eval time = 7602.97 ms / 119 tokens ( 63.89 ms per token, 15.65 tokens per second) 1.02.791.865 I slot print_timing: id 2 | task 23 | eval time = 210.67 ms / 2 tokens ( 210.67 ms per token, 4.75 tokens per second) 1.02.791.865 I slot print_timing: id 2 | task 23 | total time = 7813.64 ms / 121 tokens 1.02.791.865 I slot print_timing: id 2 | task 23 | graphs reused = 1 1.02.791.866 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.791.875 I slot release: id 2 | task 23 | stop processing: n_tokens = 120, truncated = 0 1.02.792.047 I slot print_timing: id 3 | task 25 | prompt eval time = 7603.18 ms / 181 tokens ( 42.01 ms per token, 23.81 tokens per second) 1.02.792.049 I slot print_timing: id 3 | task 25 | eval time = 210.64 ms / 2 tokens ( 210.64 ms per token, 4.75 tokens per second) 1.02.792.050 I slot print_timing: id 3 | task 25 | total time = 7813.81 ms / 183 tokens 1.02.792.050 I slot print_timing: id 3 | task 25 | graphs reused = 1 1.02.792.051 I slot print_timing: id 3 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.792.061 I slot release: id 3 | task 25 | stop processing: n_tokens = 182, truncated = 0 1.02.798.070 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.204 1.02.826.633 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 1.02.886.975 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.194 1.02.897.501 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 1.02.897.544 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.233 1.02.897.584 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 1.02.897.603 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.154 1.02.897.635 I slot launch_slot_: id 3 | task 32 | processing task, is_child = 0 1.09.294.178 I slot print_timing: id 0 | task 29 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.40 s / 18.45 tokens per second 1.10.059.052 I slot print_timing: id 1 | task 30 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.40 s / 19.85 tokens per second 1.10.063.985 I slot print_timing: id 2 | task 31 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.40 s / 21.89 tokens per second 1.10.074.155 I slot print_timing: id 3 | task 32 | prompt processing, n_tokens = 174, progress = 0.98, t = 6.40 s / 27.20 tokens per second 1.10.665.961 I slot print_timing: id 0 | task 29 | prompt eval time = 7557.59 ms / 122 tokens ( 61.95 ms per token, 16.14 tokens per second) 1.10.665.963 I slot print_timing: id 0 | task 29 | eval time = 210.72 ms / 2 tokens ( 210.72 ms per token, 4.75 tokens per second) 1.10.665.964 I slot print_timing: id 0 | task 29 | total time = 7768.31 ms / 124 tokens 1.10.665.964 I slot print_timing: id 0 | task 29 | graphs reused = 1 1.10.665.964 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.665.983 I slot release: id 0 | task 29 | stop processing: n_tokens = 123, truncated = 0 1.10.666.140 I slot print_timing: id 1 | task 30 | prompt eval time = 7557.80 ms / 131 tokens ( 57.69 ms per token, 17.33 tokens per second) 1.10.666.145 I slot print_timing: id 1 | task 30 | eval time = 210.69 ms / 2 tokens ( 210.69 ms per token, 4.75 tokens per second) 1.10.666.145 I slot print_timing: id 1 | task 30 | total time = 7768.48 ms / 133 tokens 1.10.666.146 I slot print_timing: id 1 | task 30 | graphs reused = 1 1.10.666.146 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.666.160 I slot release: id 1 | task 30 | stop processing: n_tokens = 132, truncated = 0 1.10.666.329 I slot print_timing: id 2 | task 31 | prompt eval time = 7558.00 ms / 144 tokens ( 52.49 ms per token, 19.05 tokens per second) 1.10.666.332 I slot print_timing: id 2 | task 31 | eval time = 210.66 ms / 2 tokens ( 210.66 ms per token, 4.75 tokens per second) 1.10.666.332 I slot print_timing: id 2 | task 31 | total time = 7768.65 ms / 146 tokens 1.10.666.332 I slot print_timing: id 2 | task 31 | graphs reused = 1 1.10.666.333 I slot print_timing: id 2 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.666.344 I slot release: id 2 | task 31 | stop processing: n_tokens = 145, truncated = 0 1.10.666.518 I slot print_timing: id 3 | task 32 | prompt eval time = 7558.19 ms / 178 tokens ( 42.46 ms per token, 23.55 tokens per second) 1.10.666.520 I slot print_timing: id 3 | task 32 | eval time = 210.64 ms / 2 tokens ( 210.64 ms per token, 4.75 tokens per second) 1.10.666.520 I slot print_timing: id 3 | task 32 | total time = 7768.83 ms / 180 tokens 1.10.666.520 I slot print_timing: id 3 | task 32 | graphs reused = 1 1.10.666.521 I slot print_timing: id 3 | task 32 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.666.531 I slot release: id 3 | task 32 | stop processing: n_tokens = 179, truncated = 0 1.10.672.678 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 1.10.690.383 I slot launch_slot_: id 0 | task 37 | processing task, is_child = 0 1.10.770.644 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.212 1.10.770.744 I slot launch_slot_: id 1 | task 36 | processing task, is_child = 0 1.10.770.784 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 1.10.770.825 I slot launch_slot_: id 3 | task 38 | processing task, is_child = 0 1.10.770.845 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.193 1.10.770.885 I slot launch_slot_: id 2 | task 39 | processing task, is_child = 0 1.16.868.407 I slot print_timing: id 0 | task 37 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.10 s / 19.02 tokens per second 1.17.034.783 I slot print_timing: id 1 | task 36 | prompt processing, n_tokens = 109, progress = 0.96, t = 6.10 s / 17.88 tokens per second 1.17.040.022 I slot print_timing: id 2 | task 39 | prompt processing, n_tokens = 138, progress = 0.97, t = 6.10 s / 22.63 tokens per second 1.17.044.993 I slot print_timing: id 3 | task 38 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.10 s / 22.96 tokens per second 1.17.635.626 I slot print_timing: id 0 | task 37 | prompt eval time = 6654.51 ms / 120 tokens ( 55.45 ms per token, 18.03 tokens per second) 1.17.635.632 I slot print_timing: id 0 | task 37 | eval time = 210.23 ms / 2 tokens ( 210.23 ms per token, 4.76 tokens per second) 1.17.635.632 I slot print_timing: id 0 | task 37 | total time = 6864.73 ms / 122 tokens 1.17.635.633 I slot print_timing: id 0 | task 37 | graphs reused = 1 1.17.635.633 I slot print_timing: id 0 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.635.656 I slot release: id 0 | task 37 | stop processing: n_tokens = 121, truncated = 0 1.17.635.812 I slot print_timing: id 1 | task 36 | prompt eval time = 6654.68 ms / 113 tokens ( 58.89 ms per token, 16.98 tokens per second) 1.17.635.814 I slot print_timing: id 1 | task 36 | eval time = 210.22 ms / 2 tokens ( 210.22 ms per token, 4.76 tokens per second) 1.17.635.814 I slot print_timing: id 1 | task 36 | total time = 6864.90 ms / 115 tokens 1.17.635.814 I slot print_timing: id 1 | task 36 | graphs reused = 1 1.17.635.815 I slot print_timing: id 1 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.635.831 I slot release: id 1 | task 36 | stop processing: n_tokens = 114, truncated = 0 1.17.635.994 I slot print_timing: id 2 | task 39 | prompt eval time = 6654.86 ms / 142 tokens ( 46.87 ms per token, 21.34 tokens per second) 1.17.635.996 I slot print_timing: id 2 | task 39 | eval time = 210.21 ms / 2 tokens ( 210.21 ms per token, 4.76 tokens per second) 1.17.635.996 I slot print_timing: id 2 | task 39 | total time = 6865.07 ms / 144 tokens 1.17.635.996 I slot print_timing: id 2 | task 39 | graphs reused = 1 1.17.635.996 I slot print_timing: id 2 | task 39 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.636.009 I slot release: id 2 | task 39 | stop processing: n_tokens = 143, truncated = 0 1.17.636.170 I slot print_timing: id 3 | task 38 | prompt eval time = 6655.08 ms / 144 tokens ( 46.22 ms per token, 21.64 tokens per second) 1.17.636.172 I slot print_timing: id 3 | task 38 | eval time = 210.16 ms / 2 tokens ( 210.16 ms per token, 4.76 tokens per second) 1.17.636.172 I slot print_timing: id 3 | task 38 | total time = 6865.24 ms / 146 tokens 1.17.636.172 I slot print_timing: id 3 | task 38 | graphs reused = 1 1.17.636.173 I slot print_timing: id 3 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.636.186 I slot release: id 3 | task 38 | stop processing: n_tokens = 145, truncated = 0 1.17.641.874 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.231 1.17.680.143 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 1.17.828.279 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.246 1.17.828.375 I slot launch_slot_: id 1 | task 45 | processing task, is_child = 0 1.17.828.420 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.196 1.17.828.463 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 1.17.828.484 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.193 1.17.828.522 I slot launch_slot_: id 3 | task 46 | processing task, is_child = 0 1.23.764.530 I slot print_timing: id 0 | task 43 | prompt processing, n_tokens = 105, progress = 0.96, t = 5.94 s / 17.69 tokens per second 1.24.195.415 I slot print_timing: id 1 | task 45 | prompt processing, n_tokens = 108, progress = 0.96, t = 5.94 s / 18.19 tokens per second 1.24.200.344 I slot print_timing: id 2 | task 44 | prompt processing, n_tokens = 139, progress = 0.97, t = 5.94 s / 23.42 tokens per second 1.24.205.006 I slot print_timing: id 3 | task 46 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.94 s / 20.05 tokens per second 1.24.796.446 I slot print_timing: id 0 | task 43 | prompt eval time = 6757.27 ms / 109 tokens ( 61.99 ms per token, 16.13 tokens per second) 1.24.796.448 I slot print_timing: id 0 | task 43 | eval time = 210.65 ms / 2 tokens ( 210.65 ms per token, 4.75 tokens per second) 1.24.796.449 I slot print_timing: id 0 | task 43 | total time = 6967.92 ms / 111 tokens 1.24.796.449 I slot print_timing: id 0 | task 43 | graphs reused = 1 1.24.796.449 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.796.466 I slot release: id 0 | task 43 | stop processing: n_tokens = 110, truncated = 0 1.24.796.628 I slot print_timing: id 1 | task 45 | prompt eval time = 6757.46 ms / 112 tokens ( 60.33 ms per token, 16.57 tokens per second) 1.24.796.630 I slot print_timing: id 1 | task 45 | eval time = 210.62 ms / 2 tokens ( 210.62 ms per token, 4.75 tokens per second) 1.24.796.630 I slot print_timing: id 1 | task 45 | total time = 6968.08 ms / 114 tokens 1.24.796.631 I slot print_timing: id 1 | task 45 | graphs reused = 1 1.24.796.631 I slot print_timing: id 1 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.796.642 I slot release: id 1 | task 45 | stop processing: n_tokens = 113, truncated = 0 1.24.796.808 I slot print_timing: id 2 | task 44 | prompt eval time = 6757.64 ms / 143 tokens ( 47.26 ms per token, 21.16 tokens per second) 1.24.796.810 I slot print_timing: id 2 | task 44 | eval time = 210.61 ms / 2 tokens ( 210.61 ms per token, 4.75 tokens per second) 1.24.796.810 I slot print_timing: id 2 | task 44 | total time = 6968.25 ms / 145 tokens 1.24.796.810 I slot print_timing: id 2 | task 44 | graphs reused = 1 1.24.796.811 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.796.823 I slot release: id 2 | task 44 | stop processing: n_tokens = 144, truncated = 0 1.24.796.997 I slot print_timing: id 3 | task 46 | prompt eval time = 6757.87 ms / 123 tokens ( 54.94 ms per token, 18.20 tokens per second) 1.24.796.999 I slot print_timing: id 3 | task 46 | eval time = 210.56 ms / 2 tokens ( 210.56 ms per token, 4.75 tokens per second) 1.24.797.000 I slot print_timing: id 3 | task 46 | total time = 6968.43 ms / 125 tokens 1.24.797.000 I slot print_timing: id 3 | task 46 | graphs reused = 1 1.24.797.000 I slot print_timing: id 3 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.797.008 I slot release: id 3 | task 46 | stop processing: n_tokens = 124, truncated = 0 1.24.802.773 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.257 1.24.853.328 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 1.25.953.447 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.255 1.25.986.472 I slot launch_slot_: id 0 | task 52 | processing task, is_child = 0 1.25.986.525 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.194 1.25.986.575 I slot launch_slot_: id 2 | task 50 | processing task, is_child = 0 1.25.986.594 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 1.25.986.627 I slot launch_slot_: id 3 | task 53 | processing task, is_child = 0 1.31.664.523 I slot print_timing: id 0 | task 52 | prompt processing, n_tokens = 125, progress = 0.97, t = 5.68 s / 22.02 tokens per second 1.32.427.616 I slot print_timing: id 1 | task 51 | prompt processing, n_tokens = 108, progress = 0.96, t = 5.68 s / 19.02 tokens per second 1.32.453.643 I slot print_timing: id 2 | task 50 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.68 s / 17.26 tokens per second 1.32.468.174 I slot print_timing: id 3 | task 53 | prompt processing, n_tokens = 132, progress = 0.97, t = 5.68 s / 23.25 tokens per second 1.33.070.174 I slot print_timing: id 0 | task 52 | prompt eval time = 6872.26 ms / 129 tokens ( 53.27 ms per token, 18.77 tokens per second) 1.33.070.176 I slot print_timing: id 0 | task 52 | eval time = 211.27 ms / 2 tokens ( 211.27 ms per token, 4.73 tokens per second) 1.33.070.177 I slot print_timing: id 0 | task 52 | total time = 7083.53 ms / 131 tokens 1.33.070.177 I slot print_timing: id 0 | task 52 | graphs reused = 1 1.33.070.177 I slot print_timing: id 0 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.070.269 I slot release: id 0 | task 52 | stop processing: n_tokens = 130, truncated = 0 1.33.070.455 I slot print_timing: id 1 | task 51 | prompt eval time = 6872.64 ms / 112 tokens ( 61.36 ms per token, 16.30 tokens per second) 1.33.070.457 I slot print_timing: id 1 | task 51 | eval time = 211.14 ms / 2 tokens ( 211.14 ms per token, 4.74 tokens per second) 1.33.070.457 I slot print_timing: id 1 | task 51 | total time = 7083.78 ms / 114 tokens 1.33.070.457 I slot print_timing: id 1 | task 51 | graphs reused = 1 1.33.070.458 I slot print_timing: id 1 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.070.492 I slot release: id 1 | task 51 | stop processing: n_tokens = 113, truncated = 0 1.33.070.783 I slot print_timing: id 2 | task 50 | prompt eval time = 6873.34 ms / 102 tokens ( 67.39 ms per token, 14.84 tokens per second) 1.33.070.786 I slot print_timing: id 2 | task 50 | eval time = 210.75 ms / 2 tokens ( 210.75 ms per token, 4.74 tokens per second) 1.33.070.786 I slot print_timing: id 2 | task 50 | total time = 7084.10 ms / 104 tokens 1.33.070.787 I slot print_timing: id 2 | task 50 | graphs reused = 1 1.33.070.787 I slot print_timing: id 2 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.070.817 I slot release: id 2 | task 50 | stop processing: n_tokens = 103, truncated = 0 1.33.070.992 I slot print_timing: id 3 | task 53 | prompt eval time = 6873.99 ms / 136 tokens ( 50.54 ms per token, 19.78 tokens per second) 1.33.070.996 I slot print_timing: id 3 | task 53 | eval time = 210.31 ms / 2 tokens ( 210.31 ms per token, 4.75 tokens per second) 1.33.070.997 I slot print_timing: id 3 | task 53 | total time = 7084.29 ms / 138 tokens 1.33.070.997 I slot print_timing: id 3 | task 53 | graphs reused = 1 1.33.070.997 I slot print_timing: id 3 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.071.032 I slot release: id 3 | task 53 | stop processing: n_tokens = 137, truncated = 0 1.33.079.067 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.215 1.33.106.839 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 1.33.106.863 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 1.33.162.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 1.33.214.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 1.33.275.639 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.248 1.33.275.735 I slot launch_slot_: id 1 | task 59 | processing task, is_child = 0 1.33.275.776 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.272 1.33.275.817 I slot launch_slot_: id 2 | task 60 | processing task, is_child = 0 1.33.275.839 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 1.33.275.873 I slot launch_slot_: id 3 | task 58 | processing task, is_child = 0 1.41.025.514 I slot print_timing: id 0 | task 57 | prompt processing, n_tokens = 128, progress = 0.97, t = 7.75 s / 16.52 tokens per second 1.41.197.424 I slot print_timing: id 1 | task 59 | prompt processing, n_tokens = 178, progress = 0.98, t = 7.75 s / 22.97 tokens per second 1.41.201.844 I slot print_timing: id 2 | task 60 | prompt processing, n_tokens = 173, progress = 0.98, t = 7.75 s / 22.32 tokens per second 1.41.206.307 I slot print_timing: id 3 | task 58 | prompt processing, n_tokens = 162, progress = 0.98, t = 7.75 s / 20.90 tokens per second 1.41.797.955 I slot print_timing: id 0 | task 57 | prompt eval time = 8311.62 ms / 132 tokens ( 62.97 ms per token, 15.88 tokens per second) 1.41.797.960 I slot print_timing: id 0 | task 57 | eval time = 210.45 ms / 2 tokens ( 210.45 ms per token, 4.75 tokens per second) 1.41.797.960 I slot print_timing: id 0 | task 57 | total time = 8522.07 ms / 134 tokens 1.41.797.961 I slot print_timing: id 0 | task 57 | graphs reused = 1 1.41.797.961 I slot print_timing: id 0 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.797.992 I slot release: id 0 | task 57 | stop processing: n_tokens = 133, truncated = 0 1.41.798.141 I slot print_timing: id 1 | task 59 | prompt eval time = 8311.76 ms / 182 tokens ( 45.67 ms per token, 21.90 tokens per second) 1.41.798.145 I slot print_timing: id 1 | task 59 | eval time = 210.48 ms / 2 tokens ( 210.48 ms per token, 4.75 tokens per second) 1.41.798.146 I slot print_timing: id 1 | task 59 | total time = 8522.24 ms / 184 tokens 1.41.798.146 I slot print_timing: id 1 | task 59 | graphs reused = 1 1.41.798.146 I slot print_timing: id 1 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.798.181 I slot release: id 1 | task 59 | stop processing: n_tokens = 183, truncated = 0 1.41.798.341 I slot print_timing: id 2 | task 60 | prompt eval time = 8311.91 ms / 177 tokens ( 46.96 ms per token, 21.29 tokens per second) 1.41.798.343 I slot print_timing: id 2 | task 60 | eval time = 210.52 ms / 2 tokens ( 210.52 ms per token, 4.75 tokens per second) 1.41.798.344 I slot print_timing: id 2 | task 60 | total time = 8522.43 ms / 179 tokens 1.41.798.344 I slot print_timing: id 2 | task 60 | graphs reused = 1 1.41.798.344 I slot print_timing: id 2 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.798.376 I slot release: id 2 | task 60 | stop processing: n_tokens = 178, truncated = 0 1.41.798.543 I slot print_timing: id 3 | task 58 | prompt eval time = 8312.08 ms / 166 tokens ( 50.07 ms per token, 19.97 tokens per second) 1.41.798.546 I slot print_timing: id 3 | task 58 | eval time = 210.54 ms / 2 tokens ( 210.54 ms per token, 4.75 tokens per second) 1.41.798.547 I slot print_timing: id 3 | task 58 | total time = 8522.62 ms / 168 tokens 1.41.798.547 I slot print_timing: id 3 | task 58 | graphs reused = 1 1.41.798.547 I slot print_timing: id 3 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.798.566 I slot release: id 3 | task 58 | stop processing: n_tokens = 167, truncated = 0 1.41.804.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.211 1.41.804.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 1.41.851.556 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 1.41.851.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 1.41.912.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.820 MiB) 1.41.960.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.630 MiB) 1.42.185.476 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.153 1.42.185.579 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 1.42.185.619 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.157 1.42.185.660 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 1.42.185.680 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.168 1.42.204.947 I slot launch_slot_: id 3 | task 67 | processing task, is_child = 0 1.48.970.690 I slot print_timing: id 0 | task 64 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.77 s / 17.59 tokens per second 1.49.399.685 I slot print_timing: id 1 | task 65 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.77 s / 21.43 tokens per second 1.49.414.894 I slot print_timing: id 2 | task 66 | prompt processing, n_tokens = 165, progress = 0.98, t = 6.77 s / 24.39 tokens per second 1.49.419.497 I slot print_timing: id 3 | task 67 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.77 s / 20.10 tokens per second 1.50.016.104 I slot print_timing: id 0 | task 64 | prompt eval time = 7599.33 ms / 123 tokens ( 61.78 ms per token, 16.19 tokens per second) 1.50.016.106 I slot print_timing: id 0 | task 64 | eval time = 211.81 ms / 2 tokens ( 211.81 ms per token, 4.72 tokens per second) 1.50.016.106 I slot print_timing: id 0 | task 64 | total time = 7811.14 ms / 125 tokens 1.50.016.107 I slot print_timing: id 0 | task 64 | graphs reused = 1 1.50.016.107 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.016.137 I slot release: id 0 | task 64 | stop processing: n_tokens = 124, truncated = 0 1.50.016.298 I slot print_timing: id 1 | task 65 | prompt eval time = 7599.84 ms / 149 tokens ( 51.01 ms per token, 19.61 tokens per second) 1.50.016.300 I slot print_timing: id 1 | task 65 | eval time = 211.49 ms / 2 tokens ( 211.49 ms per token, 4.73 tokens per second) 1.50.016.301 I slot print_timing: id 1 | task 65 | total time = 7811.32 ms / 151 tokens 1.50.016.301 I slot print_timing: id 1 | task 65 | graphs reused = 1 1.50.016.302 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.016.322 I slot release: id 1 | task 65 | stop processing: n_tokens = 150, truncated = 0 1.50.016.540 I slot print_timing: id 2 | task 66 | prompt eval time = 7600.60 ms / 169 tokens ( 44.97 ms per token, 22.24 tokens per second) 1.50.016.542 I slot print_timing: id 2 | task 66 | eval time = 210.95 ms / 2 tokens ( 210.95 ms per token, 4.74 tokens per second) 1.50.016.542 I slot print_timing: id 2 | task 66 | total time = 7811.55 ms / 171 tokens 1.50.016.543 I slot print_timing: id 2 | task 66 | graphs reused = 1 1.50.016.543 I slot print_timing: id 2 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.016.560 I slot release: id 2 | task 66 | stop processing: n_tokens = 170, truncated = 0 1.50.016.722 I slot print_timing: id 3 | task 67 | prompt eval time = 7601.28 ms / 140 tokens ( 54.29 ms per token, 18.42 tokens per second) 1.50.016.726 I slot print_timing: id 3 | task 67 | eval time = 210.44 ms / 2 tokens ( 210.44 ms per token, 4.75 tokens per second) 1.50.016.726 I slot print_timing: id 3 | task 67 | total time = 7811.72 ms / 142 tokens 1.50.016.726 I slot print_timing: id 3 | task 67 | graphs reused = 1 1.50.016.726 I slot print_timing: id 3 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.016.747 I slot release: id 3 | task 67 | stop processing: n_tokens = 141, truncated = 0 1.50.022.482 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 1.50.060.168 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 1.50.060.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 1.50.101.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 1.50.141.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 1.50.189.394 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 1.50.189.470 I slot launch_slot_: id 3 | task 72 | processing task, is_child = 0 1.50.189.510 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.172 (> 0.100 thold), f_keep = 0.187 1.50.189.544 I slot launch_slot_: id 1 | task 73 | processing task, is_child = 0 1.50.189.565 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.165 1.50.189.601 I slot launch_slot_: id 2 | task 74 | processing task, is_child = 0 1.57.314.998 I slot print_timing: id 0 | task 71 | prompt processing, n_tokens = 124, progress = 0.97, t = 7.13 s / 17.40 tokens per second 1.57.481.341 I slot print_timing: id 1 | task 73 | prompt processing, n_tokens = 159, progress = 0.98, t = 7.13 s / 22.31 tokens per second 1.57.485.893 I slot print_timing: id 2 | task 74 | prompt processing, n_tokens = 157, progress = 0.98, t = 7.13 s / 22.03 tokens per second 1.57.490.463 I slot print_timing: id 3 | task 72 | prompt processing, n_tokens = 107, progress = 0.96, t = 7.13 s / 15.02 tokens per second 1.58.082.640 I slot print_timing: id 0 | task 71 | prompt eval time = 7682.08 ms / 128 tokens ( 60.02 ms per token, 16.66 tokens per second) 1.58.082.643 I slot print_timing: id 0 | task 71 | eval time = 210.94 ms / 2 tokens ( 210.94 ms per token, 4.74 tokens per second) 1.58.082.643 I slot print_timing: id 0 | task 71 | total time = 7893.02 ms / 130 tokens 1.58.082.644 I slot print_timing: id 0 | task 71 | graphs reused = 1 1.58.082.644 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.082.688 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 1.58.082.837 I slot print_timing: id 1 | task 73 | prompt eval time = 7682.26 ms / 163 tokens ( 47.13 ms per token, 21.22 tokens per second) 1.58.082.840 I slot print_timing: id 1 | task 73 | eval time = 210.95 ms / 2 tokens ( 210.95 ms per token, 4.74 tokens per second) 1.58.082.841 I slot print_timing: id 1 | task 73 | total time = 7893.22 ms / 165 tokens 1.58.082.841 I slot print_timing: id 1 | task 73 | graphs reused = 1 1.58.082.842 I slot print_timing: id 1 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.082.866 I slot release: id 1 | task 73 | stop processing: n_tokens = 164, truncated = 0 1.58.083.030 I slot print_timing: id 2 | task 74 | prompt eval time = 7682.50 ms / 161 tokens ( 47.72 ms per token, 20.96 tokens per second) 1.58.083.042 I slot print_timing: id 2 | task 74 | eval time = 210.89 ms / 2 tokens ( 210.89 ms per token, 4.74 tokens per second) 1.58.083.044 I slot print_timing: id 2 | task 74 | total time = 7893.40 ms / 163 tokens 1.58.083.044 I slot print_timing: id 2 | task 74 | graphs reused = 1 1.58.083.045 I slot print_timing: id 2 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.083.087 I slot release: id 2 | task 74 | stop processing: n_tokens = 162, truncated = 0 1.58.083.245 I slot print_timing: id 3 | task 72 | prompt eval time = 7682.72 ms / 111 tokens ( 69.21 ms per token, 14.45 tokens per second) 1.58.083.246 I slot print_timing: id 3 | task 72 | eval time = 210.87 ms / 2 tokens ( 210.87 ms per token, 4.74 tokens per second) 1.58.083.246 I slot print_timing: id 3 | task 72 | total time = 7893.59 ms / 113 tokens 1.58.083.247 I slot print_timing: id 3 | task 72 | graphs reused = 1 1.58.083.247 I slot print_timing: id 3 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.083.279 I slot release: id 3 | task 72 | stop processing: n_tokens = 112, truncated = 0 1.58.089.224 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.177 1.58.089.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 1.58.158.317 I slot launch_slot_: id 1 | task 78 | processing task, is_child = 0 1.58.158.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 1.58.246.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.755 MiB) 1.58.429.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.632 MiB) 1.58.530.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.217 1.58.530.796 I slot launch_slot_: id 0 | task 79 | processing task, is_child = 0 1.58.530.839 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.179 1.58.530.875 I slot launch_slot_: id 2 | task 80 | processing task, is_child = 0 1.58.530.893 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.250 1.58.530.937 I slot launch_slot_: id 3 | task 81 | processing task, is_child = 0 2.05.310.052 I slot print_timing: id 0 | task 79 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.78 s / 15.93 tokens per second 2.05.478.754 I slot print_timing: id 1 | task 78 | prompt processing, n_tokens = 105, progress = 0.96, t = 6.78 s / 15.49 tokens per second 2.05.501.556 I slot print_timing: id 2 | task 80 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.78 s / 23.60 tokens per second 2.05.530.605 I slot print_timing: id 3 | task 81 | prompt processing, n_tokens = 163, progress = 0.98, t = 6.78 s / 24.04 tokens per second 2.06.132.482 I slot print_timing: id 0 | task 79 | prompt eval time = 7390.20 ms / 112 tokens ( 65.98 ms per token, 15.16 tokens per second) 2.06.132.487 I slot print_timing: id 0 | task 79 | eval time = 211.34 ms / 2 tokens ( 211.34 ms per token, 4.73 tokens per second) 2.06.132.487 I slot print_timing: id 0 | task 79 | total time = 7601.53 ms / 114 tokens 2.06.132.488 I slot print_timing: id 0 | task 79 | graphs reused = 1 2.06.132.488 I slot print_timing: id 0 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.132.531 I slot release: id 0 | task 79 | stop processing: n_tokens = 113, truncated = 0 2.06.132.690 I slot print_timing: id 1 | task 78 | prompt eval time = 7390.54 ms / 109 tokens ( 67.80 ms per token, 14.75 tokens per second) 2.06.132.695 I slot print_timing: id 1 | task 78 | eval time = 211.19 ms / 2 tokens ( 211.19 ms per token, 4.74 tokens per second) 2.06.132.695 I slot print_timing: id 1 | task 78 | total time = 7601.73 ms / 111 tokens 2.06.132.695 I slot print_timing: id 1 | task 78 | graphs reused = 1 2.06.132.696 I slot print_timing: id 1 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.132.730 I slot release: id 1 | task 78 | stop processing: n_tokens = 110, truncated = 0 2.06.133.042 I slot print_timing: id 2 | task 80 | prompt eval time = 7391.11 ms / 164 tokens ( 45.07 ms per token, 22.19 tokens per second) 2.06.133.045 I slot print_timing: id 2 | task 80 | eval time = 210.96 ms / 2 tokens ( 210.96 ms per token, 4.74 tokens per second) 2.06.133.045 I slot print_timing: id 2 | task 80 | total time = 7602.07 ms / 166 tokens 2.06.133.045 I slot print_timing: id 2 | task 80 | graphs reused = 1 2.06.133.045 I slot print_timing: id 2 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.133.069 I slot release: id 2 | task 80 | stop processing: n_tokens = 165, truncated = 0 2.06.133.238 I slot print_timing: id 3 | task 81 | prompt eval time = 7391.73 ms / 167 tokens ( 44.26 ms per token, 22.59 tokens per second) 2.06.133.240 I slot print_timing: id 3 | task 81 | eval time = 210.52 ms / 2 tokens ( 210.52 ms per token, 4.75 tokens per second) 2.06.133.240 I slot print_timing: id 3 | task 81 | total time = 7602.25 ms / 169 tokens 2.06.133.241 I slot print_timing: id 3 | task 81 | graphs reused = 1 2.06.133.241 I slot print_timing: id 3 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.133.266 I slot release: id 3 | task 81 | stop processing: n_tokens = 168, truncated = 0 2.06.139.522 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.248 2.06.139.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 2.06.195.842 I slot launch_slot_: id 0 | task 85 | processing task, is_child = 0 2.06.195.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 2.06.231.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.06.271.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.444 MiB) 2.06.326.765 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.255 2.06.326.850 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 2.06.326.891 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.170 2.06.330.233 I slot launch_slot_: id 2 | task 87 | processing task, is_child = 0 2.06.330.270 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.167 2.06.330.302 I slot launch_slot_: id 3 | task 88 | processing task, is_child = 0 2.12.458.797 I slot print_timing: id 0 | task 85 | prompt processing, n_tokens = 143, progress = 0.97, t = 6.13 s / 23.33 tokens per second 2.12.779.347 I slot print_timing: id 1 | task 86 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.13 s / 20.72 tokens per second 2.12.791.301 I slot print_timing: id 2 | task 87 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.13 s / 19.25 tokens per second 2.12.796.259 I slot print_timing: id 3 | task 88 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.13 s / 18.93 tokens per second 2.13.388.443 I slot print_timing: id 0 | task 85 | prompt eval time = 6847.15 ms / 147 tokens ( 46.58 ms per token, 21.47 tokens per second) 2.13.388.446 I slot print_timing: id 0 | task 85 | eval time = 210.98 ms / 2 tokens ( 210.98 ms per token, 4.74 tokens per second) 2.13.388.446 I slot print_timing: id 0 | task 85 | total time = 7058.13 ms / 149 tokens 2.13.388.447 I slot print_timing: id 0 | task 85 | graphs reused = 1 2.13.388.447 I slot print_timing: id 0 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.388.474 I slot release: id 0 | task 85 | stop processing: n_tokens = 148, truncated = 0 2.13.388.626 I slot print_timing: id 1 | task 86 | prompt eval time = 6847.37 ms / 131 tokens ( 52.27 ms per token, 19.13 tokens per second) 2.13.388.631 I slot print_timing: id 1 | task 86 | eval time = 210.94 ms / 2 tokens ( 210.94 ms per token, 4.74 tokens per second) 2.13.388.632 I slot print_timing: id 1 | task 86 | total time = 7058.30 ms / 133 tokens 2.13.388.633 I slot print_timing: id 1 | task 86 | graphs reused = 1 2.13.388.633 I slot print_timing: id 1 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.388.677 I slot release: id 1 | task 86 | stop processing: n_tokens = 132, truncated = 0 2.13.388.845 I slot print_timing: id 2 | task 87 | prompt eval time = 6847.57 ms / 122 tokens ( 56.13 ms per token, 17.82 tokens per second) 2.13.388.847 I slot print_timing: id 2 | task 87 | eval time = 210.94 ms / 2 tokens ( 210.94 ms per token, 4.74 tokens per second) 2.13.388.847 I slot print_timing: id 2 | task 87 | total time = 7058.51 ms / 124 tokens 2.13.388.848 I slot print_timing: id 2 | task 87 | graphs reused = 1 2.13.388.848 I slot print_timing: id 2 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.388.891 I slot release: id 2 | task 87 | stop processing: n_tokens = 123, truncated = 0 2.13.389.067 I slot print_timing: id 3 | task 88 | prompt eval time = 6847.78 ms / 120 tokens ( 57.06 ms per token, 17.52 tokens per second) 2.13.389.069 I slot print_timing: id 3 | task 88 | eval time = 210.95 ms / 2 tokens ( 210.95 ms per token, 4.74 tokens per second) 2.13.389.070 I slot print_timing: id 3 | task 88 | total time = 7058.73 ms / 122 tokens 2.13.389.070 I slot print_timing: id 3 | task 88 | graphs reused = 1 2.13.389.070 I slot print_timing: id 3 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.389.084 I slot release: id 3 | task 88 | stop processing: n_tokens = 121, truncated = 0 2.13.394.877 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 2.13.427.803 I slot launch_slot_: id 2 | task 92 | processing task, is_child = 0 2.13.427.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 2.13.460.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.380 MiB) 2.13.500.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 2.13.555.354 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.189 2.13.555.444 I slot launch_slot_: id 0 | task 93 | processing task, is_child = 0 2.13.555.484 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.212 2.13.555.520 I slot launch_slot_: id 1 | task 94 | processing task, is_child = 0 2.13.555.538 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.231 2.13.558.874 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 2.19.741.551 I slot print_timing: id 0 | task 93 | prompt processing, n_tokens = 120, progress = 0.97, t = 6.18 s / 19.41 tokens per second 2.20.048.429 I slot print_timing: id 1 | task 94 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.18 s / 22.64 tokens per second 2.20.053.194 I slot print_timing: id 2 | task 92 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.18 s / 20.54 tokens per second 2.20.057.951 I slot print_timing: id 3 | task 95 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.18 s / 22.16 tokens per second 2.20.650.353 I slot print_timing: id 0 | task 93 | prompt eval time = 6880.79 ms / 124 tokens ( 55.49 ms per token, 18.02 tokens per second) 2.20.650.355 I slot print_timing: id 0 | task 93 | eval time = 210.68 ms / 2 tokens ( 210.68 ms per token, 4.75 tokens per second) 2.20.650.356 I slot print_timing: id 0 | task 93 | total time = 7091.46 ms / 126 tokens 2.20.650.356 I slot print_timing: id 0 | task 93 | graphs reused = 1 2.20.650.357 I slot print_timing: id 0 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.650.407 I slot release: id 0 | task 93 | stop processing: n_tokens = 125, truncated = 0 2.20.650.559 I slot print_timing: id 1 | task 94 | prompt eval time = 6880.97 ms / 144 tokens ( 47.78 ms per token, 20.93 tokens per second) 2.20.650.565 I slot print_timing: id 1 | task 94 | eval time = 210.69 ms / 2 tokens ( 210.69 ms per token, 4.75 tokens per second) 2.20.650.565 I slot print_timing: id 1 | task 94 | total time = 7091.66 ms / 146 tokens 2.20.650.565 I slot print_timing: id 1 | task 94 | graphs reused = 1 2.20.650.566 I slot print_timing: id 1 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.650.606 I slot release: id 1 | task 94 | stop processing: n_tokens = 145, truncated = 0 2.20.650.773 I slot print_timing: id 2 | task 92 | prompt eval time = 6881.16 ms / 131 tokens ( 52.53 ms per token, 19.04 tokens per second) 2.20.650.778 I slot print_timing: id 2 | task 92 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 2.20.650.778 I slot print_timing: id 2 | task 92 | total time = 7091.86 ms / 133 tokens 2.20.650.778 I slot print_timing: id 2 | task 92 | graphs reused = 1 2.20.650.778 I slot print_timing: id 2 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.650.804 I slot release: id 2 | task 92 | stop processing: n_tokens = 132, truncated = 0 2.20.650.961 I slot print_timing: id 3 | task 95 | prompt eval time = 6881.36 ms / 141 tokens ( 48.80 ms per token, 20.49 tokens per second) 2.20.650.963 I slot print_timing: id 3 | task 95 | eval time = 210.68 ms / 2 tokens ( 210.68 ms per token, 4.75 tokens per second) 2.20.650.964 I slot print_timing: id 3 | task 95 | total time = 7092.04 ms / 143 tokens 2.20.650.964 I slot print_timing: id 3 | task 95 | graphs reused = 1 2.20.650.964 I slot print_timing: id 3 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.650.984 I slot release: id 3 | task 95 | stop processing: n_tokens = 142, truncated = 0 2.20.657.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.224 2.20.691.513 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 2.20.691.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.20.751.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.130 MiB) 2.20.809.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 2.20.860.382 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 2.20.860.470 I slot launch_slot_: id 1 | task 100 | processing task, is_child = 0 2.20.860.512 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 2.20.860.550 I slot launch_slot_: id 2 | task 101 | processing task, is_child = 0 2.20.860.571 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 2.20.860.609 I slot launch_slot_: id 3 | task 102 | processing task, is_child = 0 2.26.274.651 I slot print_timing: id 0 | task 99 | prompt processing, n_tokens = 117, progress = 0.97, t = 5.41 s / 21.61 tokens per second 2.27.410.730 I slot print_timing: id 1 | task 100 | prompt processing, n_tokens = 114, progress = 0.97, t = 5.41 s / 21.06 tokens per second 2.27.415.184 I slot print_timing: id 2 | task 101 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.41 s / 19.02 tokens per second 2.27.419.622 I slot print_timing: id 3 | task 102 | prompt processing, n_tokens = 168, progress = 0.98, t = 5.41 s / 31.03 tokens per second 2.28.010.583 I slot print_timing: id 0 | task 99 | prompt eval time = 6939.54 ms / 121 tokens ( 57.35 ms per token, 17.44 tokens per second) 2.28.010.585 I slot print_timing: id 0 | task 99 | eval time = 210.43 ms / 2 tokens ( 210.43 ms per token, 4.75 tokens per second) 2.28.010.586 I slot print_timing: id 0 | task 99 | total time = 7149.96 ms / 123 tokens 2.28.010.586 I slot print_timing: id 0 | task 99 | graphs reused = 1 2.28.010.586 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.010.612 I slot release: id 0 | task 99 | stop processing: n_tokens = 122, truncated = 0 2.28.010.759 I slot print_timing: id 1 | task 100 | prompt eval time = 6939.67 ms / 118 tokens ( 58.81 ms per token, 17.00 tokens per second) 2.28.010.764 I slot print_timing: id 1 | task 100 | eval time = 210.46 ms / 2 tokens ( 210.46 ms per token, 4.75 tokens per second) 2.28.010.765 I slot print_timing: id 1 | task 100 | total time = 7150.12 ms / 120 tokens 2.28.010.765 I slot print_timing: id 1 | task 100 | graphs reused = 1 2.28.010.765 I slot print_timing: id 1 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.010.788 I slot release: id 1 | task 100 | stop processing: n_tokens = 119, truncated = 0 2.28.010.956 I slot print_timing: id 2 | task 101 | prompt eval time = 6939.81 ms / 107 tokens ( 64.86 ms per token, 15.42 tokens per second) 2.28.010.957 I slot print_timing: id 2 | task 101 | eval time = 210.49 ms / 2 tokens ( 210.49 ms per token, 4.75 tokens per second) 2.28.010.958 I slot print_timing: id 2 | task 101 | total time = 7150.30 ms / 109 tokens 2.28.010.958 I slot print_timing: id 2 | task 101 | graphs reused = 1 2.28.010.958 I slot print_timing: id 2 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.010.978 I slot release: id 2 | task 101 | stop processing: n_tokens = 108, truncated = 0 2.28.011.130 I slot print_timing: id 3 | task 102 | prompt eval time = 6939.96 ms / 172 tokens ( 40.35 ms per token, 24.78 tokens per second) 2.28.011.136 I slot print_timing: id 3 | task 102 | eval time = 210.51 ms / 2 tokens ( 210.51 ms per token, 4.75 tokens per second) 2.28.011.136 I slot print_timing: id 3 | task 102 | total time = 7150.47 ms / 174 tokens 2.28.011.137 I slot print_timing: id 3 | task 102 | graphs reused = 1 2.28.011.137 I slot print_timing: id 3 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.011.146 I slot release: id 3 | task 102 | stop processing: n_tokens = 173, truncated = 0 2.28.016.983 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.244 2.28.017.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.28.050.159 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 2.28.050.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 2.28.081.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.693 MiB) 2.28.136.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 2.28.176.354 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.269 2.28.176.443 I slot launch_slot_: id 2 | task 107 | processing task, is_child = 0 2.28.176.483 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.230 2.28.176.523 I slot launch_slot_: id 0 | task 108 | processing task, is_child = 0 2.28.176.545 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.162 2.28.176.584 I slot launch_slot_: id 3 | task 109 | processing task, is_child = 0 2.35.521.819 I slot print_timing: id 0 | task 108 | prompt processing, n_tokens = 236, progress = 0.98, t = 7.35 s / 32.13 tokens per second 2.36.307.333 I slot print_timing: id 1 | task 106 | prompt processing, n_tokens = 132, progress = 0.97, t = 7.35 s / 17.97 tokens per second 2.36.311.780 I slot print_timing: id 2 | task 107 | prompt processing, n_tokens = 112, progress = 0.97, t = 7.35 s / 15.25 tokens per second 2.36.316.202 I slot print_timing: id 3 | task 109 | prompt processing, n_tokens = 173, progress = 0.98, t = 7.35 s / 23.55 tokens per second 2.36.907.452 I slot print_timing: id 0 | task 108 | prompt eval time = 8520.16 ms / 240 tokens ( 35.50 ms per token, 28.17 tokens per second) 2.36.907.454 I slot print_timing: id 0 | task 108 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 2.36.907.455 I slot print_timing: id 0 | task 108 | total time = 8730.86 ms / 242 tokens 2.36.907.455 I slot print_timing: id 0 | task 108 | graphs reused = 1 2.36.907.455 I slot print_timing: id 0 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.907.498 I slot release: id 0 | task 108 | stop processing: n_tokens = 241, truncated = 0 2.36.907.657 I slot print_timing: id 1 | task 106 | prompt eval time = 8520.34 ms / 136 tokens ( 62.65 ms per token, 15.96 tokens per second) 2.36.907.659 I slot print_timing: id 1 | task 106 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 2.36.907.660 I slot print_timing: id 1 | task 106 | total time = 8731.04 ms / 138 tokens 2.36.907.660 I slot print_timing: id 1 | task 106 | graphs reused = 1 2.36.907.660 I slot print_timing: id 1 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.907.699 I slot release: id 1 | task 106 | stop processing: n_tokens = 137, truncated = 0 2.36.907.864 I slot print_timing: id 2 | task 107 | prompt eval time = 8520.52 ms / 116 tokens ( 73.45 ms per token, 13.61 tokens per second) 2.36.907.866 I slot print_timing: id 2 | task 107 | eval time = 210.71 ms / 2 tokens ( 210.71 ms per token, 4.75 tokens per second) 2.36.907.867 I slot print_timing: id 2 | task 107 | total time = 8731.24 ms / 118 tokens 2.36.907.867 I slot print_timing: id 2 | task 107 | graphs reused = 1 2.36.907.867 I slot print_timing: id 2 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.907.902 I slot release: id 2 | task 107 | stop processing: n_tokens = 117, truncated = 0 2.36.908.060 I slot print_timing: id 3 | task 109 | prompt eval time = 8520.72 ms / 177 tokens ( 48.14 ms per token, 20.77 tokens per second) 2.36.908.062 I slot print_timing: id 3 | task 109 | eval time = 210.71 ms / 2 tokens ( 210.71 ms per token, 4.75 tokens per second) 2.36.908.063 I slot print_timing: id 3 | task 109 | total time = 8731.42 ms / 179 tokens 2.36.908.063 I slot print_timing: id 3 | task 109 | graphs reused = 1 2.36.908.063 I slot print_timing: id 3 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.908.083 I slot release: id 3 | task 109 | stop processing: n_tokens = 178, truncated = 0 2.36.913.688 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.218 (> 0.100 thold), f_keep = 0.265 2.36.913.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.568 MiB) 2.36.971.298 I slot launch_slot_: id 2 | task 113 | processing task, is_child = 0 2.36.971.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 2.37.283.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 2.37.339.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 2.37.373.103 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.116 2.37.373.205 I slot launch_slot_: id 0 | task 115 | processing task, is_child = 0 2.37.373.246 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 2.37.383.671 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 2.37.383.698 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.157 2.37.383.732 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 2.44.578.057 I slot print_timing: id 0 | task 115 | prompt processing, n_tokens = 156, progress = 0.97, t = 7.19 s / 21.68 tokens per second 2.45.729.826 I slot print_timing: id 1 | task 114 | prompt processing, n_tokens = 151, progress = 0.97, t = 7.19 s / 20.99 tokens per second 2.45.755.438 I slot print_timing: id 2 | task 113 | prompt processing, n_tokens = 138, progress = 0.97, t = 7.19 s / 19.18 tokens per second 2.45.759.918 I slot print_timing: id 3 | task 116 | prompt processing, n_tokens = 222, progress = 0.98, t = 7.19 s / 30.86 tokens per second 2.46.373.068 I slot print_timing: id 0 | task 115 | prompt eval time = 8777.23 ms / 160 tokens ( 54.86 ms per token, 18.23 tokens per second) 2.46.373.072 I slot print_timing: id 0 | task 115 | eval time = 212.09 ms / 2 tokens ( 212.09 ms per token, 4.71 tokens per second) 2.46.373.073 I slot print_timing: id 0 | task 115 | total time = 8989.33 ms / 162 tokens 2.46.373.073 I slot print_timing: id 0 | task 115 | graphs reused = 1 2.46.373.074 I slot print_timing: id 0 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.373.109 I slot release: id 0 | task 115 | stop processing: n_tokens = 161, truncated = 0 2.46.373.264 I slot print_timing: id 1 | task 114 | prompt eval time = 8777.62 ms / 155 tokens ( 56.63 ms per token, 17.66 tokens per second) 2.46.373.266 I slot print_timing: id 1 | task 114 | eval time = 211.88 ms / 2 tokens ( 211.88 ms per token, 4.72 tokens per second) 2.46.373.267 I slot print_timing: id 1 | task 114 | total time = 8989.50 ms / 157 tokens 2.46.373.267 I slot print_timing: id 1 | task 114 | graphs reused = 1 2.46.373.267 I slot print_timing: id 1 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.373.302 I slot release: id 1 | task 114 | stop processing: n_tokens = 156, truncated = 0 2.46.373.466 I slot print_timing: id 2 | task 113 | prompt eval time = 8778.34 ms / 142 tokens ( 61.82 ms per token, 16.18 tokens per second) 2.46.373.467 I slot print_timing: id 2 | task 113 | eval time = 211.35 ms / 2 tokens ( 211.35 ms per token, 4.73 tokens per second) 2.46.373.468 I slot print_timing: id 2 | task 113 | total time = 8989.68 ms / 144 tokens 2.46.373.469 I slot print_timing: id 2 | task 113 | graphs reused = 1 2.46.373.469 I slot print_timing: id 2 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.373.503 I slot release: id 2 | task 113 | stop processing: n_tokens = 143, truncated = 0 2.46.373.661 I slot print_timing: id 3 | task 116 | prompt eval time = 8778.95 ms / 226 tokens ( 38.84 ms per token, 25.74 tokens per second) 2.46.373.666 I slot print_timing: id 3 | task 116 | eval time = 210.93 ms / 2 tokens ( 210.93 ms per token, 4.74 tokens per second) 2.46.373.666 I slot print_timing: id 3 | task 116 | total time = 8989.87 ms / 228 tokens 2.46.373.666 I slot print_timing: id 3 | task 116 | graphs reused = 1 2.46.373.666 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.373.699 I slot release: id 3 | task 116 | stop processing: n_tokens = 227, truncated = 0 2.46.380.488 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 2.46.415.019 I slot launch_slot_: id 2 | task 120 | processing task, is_child = 0 2.46.415.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.46.451.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 2.46.492.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.882 MiB) 2.46.534.171 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 2.46.534.256 I slot launch_slot_: id 1 | task 121 | processing task, is_child = 0 2.46.534.299 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.174 2.46.534.336 I slot launch_slot_: id 0 | task 122 | processing task, is_child = 0 2.46.534.358 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 2.46.560.621 I slot launch_slot_: id 3 | task 123 | processing task, is_child = 0 2.52.227.663 I slot print_timing: id 0 | task 122 | prompt processing, n_tokens = 137, progress = 0.97, t = 5.67 s / 24.17 tokens per second 2.53.382.723 I slot print_timing: id 1 | task 121 | prompt processing, n_tokens = 110, progress = 0.96, t = 5.67 s / 19.41 tokens per second 2.53.406.192 I slot print_timing: id 2 | task 120 | prompt processing, n_tokens = 101, progress = 0.96, t = 5.67 s / 17.82 tokens per second 2.53.410.713 I slot print_timing: id 3 | task 123 | prompt processing, n_tokens = 188, progress = 0.98, t = 5.67 s / 33.17 tokens per second 2.54.015.906 I slot print_timing: id 0 | task 122 | prompt eval time = 7244.23 ms / 141 tokens ( 51.38 ms per token, 19.46 tokens per second) 2.54.015.909 I slot print_timing: id 0 | task 122 | eval time = 211.04 ms / 2 tokens ( 211.04 ms per token, 4.74 tokens per second) 2.54.015.909 I slot print_timing: id 0 | task 122 | total time = 7455.27 ms / 143 tokens 2.54.015.910 I slot print_timing: id 0 | task 122 | graphs reused = 1 2.54.015.910 I slot print_timing: id 0 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.015.959 I slot release: id 0 | task 122 | stop processing: n_tokens = 142, truncated = 0 2.54.016.112 I slot print_timing: id 1 | task 121 | prompt eval time = 7244.42 ms / 114 tokens ( 63.55 ms per token, 15.74 tokens per second) 2.54.016.115 I slot print_timing: id 1 | task 121 | eval time = 211.04 ms / 2 tokens ( 211.04 ms per token, 4.74 tokens per second) 2.54.016.116 I slot print_timing: id 1 | task 121 | total time = 7455.47 ms / 116 tokens 2.54.016.116 I slot print_timing: id 1 | task 121 | graphs reused = 1 2.54.016.116 I slot print_timing: id 1 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.016.144 I slot release: id 1 | task 121 | stop processing: n_tokens = 115, truncated = 0 2.54.016.306 I slot print_timing: id 2 | task 120 | prompt eval time = 7244.62 ms / 105 tokens ( 69.00 ms per token, 14.49 tokens per second) 2.54.016.307 I slot print_timing: id 2 | task 120 | eval time = 211.02 ms / 2 tokens ( 211.02 ms per token, 4.74 tokens per second) 2.54.016.308 I slot print_timing: id 2 | task 120 | total time = 7455.65 ms / 107 tokens 2.54.016.308 I slot print_timing: id 2 | task 120 | graphs reused = 1 2.54.016.308 I slot print_timing: id 2 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.016.334 I slot release: id 2 | task 120 | stop processing: n_tokens = 106, truncated = 0 2.54.016.498 I slot print_timing: id 3 | task 123 | prompt eval time = 7245.04 ms / 192 tokens ( 37.73 ms per token, 26.50 tokens per second) 2.54.016.500 I slot print_timing: id 3 | task 123 | eval time = 210.79 ms / 2 tokens ( 210.79 ms per token, 4.74 tokens per second) 2.54.016.500 I slot print_timing: id 3 | task 123 | total time = 7455.83 ms / 194 tokens 2.54.016.505 I slot print_timing: id 3 | task 123 | graphs reused = 1 2.54.016.507 I slot print_timing: id 3 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.016.547 I slot release: id 3 | task 123 | stop processing: n_tokens = 193, truncated = 0 2.54.023.335 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.252 2.54.065.957 I slot launch_slot_: id 1 | task 127 | processing task, is_child = 0 2.54.065.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 2.54.125.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.506 MiB) 2.54.181.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 2.54.221.515 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.197 2.54.221.594 I slot launch_slot_: id 0 | task 128 | processing task, is_child = 0 2.54.221.632 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.274 2.54.221.664 I slot launch_slot_: id 2 | task 129 | processing task, is_child = 0 2.54.221.684 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.145 2.54.221.718 I slot launch_slot_: id 3 | task 130 | processing task, is_child = 0 3.00.206.093 I slot print_timing: id 0 | task 128 | prompt processing, n_tokens = 168, progress = 0.98, t = 5.98 s / 28.07 tokens per second 3.00.519.078 I slot print_timing: id 1 | task 127 | prompt processing, n_tokens = 104, progress = 0.96, t = 5.98 s / 17.38 tokens per second 3.00.523.564 I slot print_timing: id 2 | task 129 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.98 s / 19.72 tokens per second 3.00.528.179 I slot print_timing: id 3 | task 130 | prompt processing, n_tokens = 131, progress = 0.97, t = 5.98 s / 21.89 tokens per second 3.01.119.907 I slot print_timing: id 0 | task 128 | prompt eval time = 6687.81 ms / 172 tokens ( 38.88 ms per token, 25.72 tokens per second) 3.01.119.910 I slot print_timing: id 0 | task 128 | eval time = 210.37 ms / 2 tokens ( 210.37 ms per token, 4.75 tokens per second) 3.01.119.910 I slot print_timing: id 0 | task 128 | total time = 6898.18 ms / 174 tokens 3.01.119.911 I slot print_timing: id 0 | task 128 | graphs reused = 1 3.01.119.911 I slot print_timing: id 0 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.119.959 I slot release: id 0 | task 128 | stop processing: n_tokens = 173, truncated = 0 3.01.120.119 I slot print_timing: id 1 | task 127 | prompt eval time = 6687.95 ms / 108 tokens ( 61.93 ms per token, 16.15 tokens per second) 3.01.120.124 I slot print_timing: id 1 | task 127 | eval time = 210.43 ms / 2 tokens ( 210.43 ms per token, 4.75 tokens per second) 3.01.120.124 I slot print_timing: id 1 | task 127 | total time = 6898.38 ms / 110 tokens 3.01.120.124 I slot print_timing: id 1 | task 127 | graphs reused = 1 3.01.120.125 I slot print_timing: id 1 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.120.146 I slot release: id 1 | task 127 | stop processing: n_tokens = 109, truncated = 0 3.01.120.307 I slot print_timing: id 2 | task 129 | prompt eval time = 6688.10 ms / 122 tokens ( 54.82 ms per token, 18.24 tokens per second) 3.01.120.310 I slot print_timing: id 2 | task 129 | eval time = 210.46 ms / 2 tokens ( 210.46 ms per token, 4.75 tokens per second) 3.01.120.310 I slot print_timing: id 2 | task 129 | total time = 6898.56 ms / 124 tokens 3.01.120.311 I slot print_timing: id 2 | task 129 | graphs reused = 1 3.01.120.311 I slot print_timing: id 2 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.120.335 I slot release: id 2 | task 129 | stop processing: n_tokens = 123, truncated = 0 3.01.120.519 I slot print_timing: id 3 | task 130 | prompt eval time = 6688.25 ms / 135 tokens ( 49.54 ms per token, 20.18 tokens per second) 3.01.120.522 I slot print_timing: id 3 | task 130 | eval time = 210.51 ms / 2 tokens ( 210.51 ms per token, 4.75 tokens per second) 3.01.120.522 I slot print_timing: id 3 | task 130 | total time = 6898.76 ms / 137 tokens 3.01.120.522 I slot print_timing: id 3 | task 130 | graphs reused = 1 3.01.120.523 I slot print_timing: id 3 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.120.563 I slot release: id 3 | task 130 | stop processing: n_tokens = 136, truncated = 0 3.01.126.197 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.162 3.01.126.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 3.01.171.836 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 3.01.171.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 3.01.204.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.756 MiB) 3.01.238.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 3.01.277.208 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.266 3.01.280.604 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 3.01.280.647 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.228 3.01.280.689 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 3.01.280.709 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.206 3.01.280.763 I slot launch_slot_: id 3 | task 137 | processing task, is_child = 0 3.07.531.544 I slot print_timing: id 0 | task 134 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.25 s / 20.96 tokens per second 3.07.965.036 I slot print_timing: id 1 | task 135 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.25 s / 18.56 tokens per second 3.07.971.034 I slot print_timing: id 2 | task 136 | prompt processing, n_tokens = 130, progress = 0.97, t = 6.25 s / 20.80 tokens per second 3.07.975.445 I slot print_timing: id 3 | task 137 | prompt processing, n_tokens = 155, progress = 0.97, t = 6.25 s / 24.80 tokens per second 3.08.566.877 I slot print_timing: id 0 | task 134 | prompt eval time = 7075.48 ms / 135 tokens ( 52.41 ms per token, 19.08 tokens per second) 3.08.566.883 I slot print_timing: id 0 | task 134 | eval time = 210.63 ms / 2 tokens ( 210.63 ms per token, 4.75 tokens per second) 3.08.566.884 I slot print_timing: id 0 | task 134 | total time = 7286.11 ms / 137 tokens 3.08.566.885 I slot print_timing: id 0 | task 134 | graphs reused = 1 3.08.566.885 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.566.920 I slot release: id 0 | task 134 | stop processing: n_tokens = 136, truncated = 0 3.08.567.074 I slot print_timing: id 1 | task 135 | prompt eval time = 7075.61 ms / 120 tokens ( 58.96 ms per token, 16.96 tokens per second) 3.08.567.080 I slot print_timing: id 1 | task 135 | eval time = 210.67 ms / 2 tokens ( 210.67 ms per token, 4.75 tokens per second) 3.08.567.080 I slot print_timing: id 1 | task 135 | total time = 7286.28 ms / 122 tokens 3.08.567.081 I slot print_timing: id 1 | task 135 | graphs reused = 1 3.08.567.081 I slot print_timing: id 1 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.567.118 I slot release: id 1 | task 135 | stop processing: n_tokens = 121, truncated = 0 3.08.567.278 I slot print_timing: id 2 | task 136 | prompt eval time = 7075.76 ms / 134 tokens ( 52.80 ms per token, 18.94 tokens per second) 3.08.567.280 I slot print_timing: id 2 | task 136 | eval time = 210.72 ms / 2 tokens ( 210.72 ms per token, 4.75 tokens per second) 3.08.567.280 I slot print_timing: id 2 | task 136 | total time = 7286.48 ms / 136 tokens 3.08.567.281 I slot print_timing: id 2 | task 136 | graphs reused = 1 3.08.567.281 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.567.312 I slot release: id 2 | task 136 | stop processing: n_tokens = 135, truncated = 0 3.08.567.485 I slot print_timing: id 3 | task 137 | prompt eval time = 7075.91 ms / 159 tokens ( 44.50 ms per token, 22.47 tokens per second) 3.08.567.487 I slot print_timing: id 3 | task 137 | eval time = 210.76 ms / 2 tokens ( 210.76 ms per token, 4.74 tokens per second) 3.08.567.487 I slot print_timing: id 3 | task 137 | total time = 7286.66 ms / 161 tokens 3.08.567.488 I slot print_timing: id 3 | task 137 | graphs reused = 1 3.08.567.490 I slot print_timing: id 3 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.567.535 I slot release: id 3 | task 137 | stop processing: n_tokens = 160, truncated = 0 3.08.573.486 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.206 3.08.582.349 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 3.08.582.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.506 MiB) 3.08.636.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.08.690.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 3.08.732.842 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.231 3.08.732.920 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 3.08.732.956 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.207 3.08.732.990 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 3.08.733.009 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.175 3.08.733.041 I slot launch_slot_: id 3 | task 144 | processing task, is_child = 0 3.16.292.378 I slot print_timing: id 0 | task 141 | prompt processing, n_tokens = 126, progress = 0.97, t = 7.56 s / 16.67 tokens per second 3.16.462.265 I slot print_timing: id 1 | task 142 | prompt processing, n_tokens = 176, progress = 0.98, t = 7.56 s / 23.28 tokens per second 3.16.467.345 I slot print_timing: id 2 | task 143 | prompt processing, n_tokens = 168, progress = 0.98, t = 7.56 s / 22.22 tokens per second 3.16.471.998 I slot print_timing: id 3 | task 144 | prompt processing, n_tokens = 171, progress = 0.98, t = 7.56 s / 22.62 tokens per second 3.17.064.296 I slot print_timing: id 0 | task 141 | prompt eval time = 8120.55 ms / 130 tokens ( 62.47 ms per token, 16.01 tokens per second) 3.17.064.298 I slot print_timing: id 0 | task 141 | eval time = 210.69 ms / 2 tokens ( 210.69 ms per token, 4.75 tokens per second) 3.17.064.298 I slot print_timing: id 0 | task 141 | total time = 8331.24 ms / 132 tokens 3.17.064.299 I slot print_timing: id 0 | task 141 | graphs reused = 1 3.17.064.299 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.064.354 I slot release: id 0 | task 141 | stop processing: n_tokens = 131, truncated = 0 3.17.064.506 I slot print_timing: id 1 | task 142 | prompt eval time = 8120.74 ms / 180 tokens ( 45.12 ms per token, 22.17 tokens per second) 3.17.064.512 I slot print_timing: id 1 | task 142 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 3.17.064.512 I slot print_timing: id 1 | task 142 | total time = 8331.44 ms / 182 tokens 3.17.064.513 I slot print_timing: id 1 | task 142 | graphs reused = 1 3.17.064.513 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.064.533 I slot release: id 1 | task 142 | stop processing: n_tokens = 181, truncated = 0 3.17.064.708 I slot print_timing: id 2 | task 143 | prompt eval time = 8120.93 ms / 172 tokens ( 47.21 ms per token, 21.18 tokens per second) 3.17.064.712 I slot print_timing: id 2 | task 143 | eval time = 210.71 ms / 2 tokens ( 210.71 ms per token, 4.75 tokens per second) 3.17.064.713 I slot print_timing: id 2 | task 143 | total time = 8331.64 ms / 174 tokens 3.17.064.713 I slot print_timing: id 2 | task 143 | graphs reused = 1 3.17.064.713 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.064.742 I slot release: id 2 | task 143 | stop processing: n_tokens = 173, truncated = 0 3.17.064.909 I slot print_timing: id 3 | task 144 | prompt eval time = 8121.13 ms / 175 tokens ( 46.41 ms per token, 21.55 tokens per second) 3.17.064.911 I slot print_timing: id 3 | task 144 | eval time = 210.69 ms / 2 tokens ( 210.69 ms per token, 4.75 tokens per second) 3.17.064.912 I slot print_timing: id 3 | task 144 | total time = 8331.82 ms / 177 tokens 3.17.064.912 I slot print_timing: id 3 | task 144 | graphs reused = 1 3.17.064.912 I slot print_timing: id 3 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.064.936 I slot release: id 3 | task 144 | stop processing: n_tokens = 176, truncated = 0 3.17.069.626 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.214 3.17.069.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 3.17.133.807 I slot launch_slot_: id 0 | task 149 | processing task, is_child = 0 3.17.133.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 3.17.178.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.17.254.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.17.946.839 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.155 3.17.947.341 I slot launch_slot_: id 1 | task 148 | processing task, is_child = 0 3.17.947.568 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 3.17.993.871 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 3.17.993.913 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 3.18.031.884 I slot launch_slot_: id 3 | task 151 | processing task, is_child = 0 3.23.183.567 I slot print_timing: id 0 | task 149 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.15 s / 21.55 tokens per second 3.23.513.915 I slot print_timing: id 1 | task 148 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.15 s / 23.10 tokens per second 3.23.542.161 I slot print_timing: id 2 | task 150 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.15 s / 23.10 tokens per second 3.23.555.999 I slot print_timing: id 3 | task 151 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.15 s / 21.55 tokens per second 3.24.148.469 I slot print_timing: id 0 | task 149 | prompt eval time = 5904.67 ms / 115 tokens ( 51.34 ms per token, 19.48 tokens per second) 3.24.148.473 I slot print_timing: id 0 | task 149 | eval time = 211.90 ms / 2 tokens ( 211.90 ms per token, 4.72 tokens per second) 3.24.148.474 I slot print_timing: id 0 | task 149 | total time = 6116.57 ms / 117 tokens 3.24.148.474 I slot print_timing: id 0 | task 149 | graphs reused = 1 3.24.148.475 I slot print_timing: id 0 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.148.522 I slot release: id 0 | task 149 | stop processing: n_tokens = 116, truncated = 0 3.24.148.717 I slot print_timing: id 1 | task 148 | prompt eval time = 5904.97 ms / 123 tokens ( 48.01 ms per token, 20.83 tokens per second) 3.24.148.719 I slot print_timing: id 1 | task 148 | eval time = 211.83 ms / 2 tokens ( 211.83 ms per token, 4.72 tokens per second) 3.24.148.720 I slot print_timing: id 1 | task 148 | total time = 6116.80 ms / 125 tokens 3.24.148.720 I slot print_timing: id 1 | task 148 | graphs reused = 1 3.24.148.721 I slot print_timing: id 1 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.148.731 I slot release: id 1 | task 148 | stop processing: n_tokens = 124, truncated = 0 3.24.148.896 I slot print_timing: id 2 | task 150 | prompt eval time = 5905.54 ms / 123 tokens ( 48.01 ms per token, 20.83 tokens per second) 3.24.148.899 I slot print_timing: id 2 | task 150 | eval time = 211.41 ms / 2 tokens ( 211.41 ms per token, 4.73 tokens per second) 3.24.148.899 I slot print_timing: id 2 | task 150 | total time = 6116.96 ms / 125 tokens 3.24.148.900 I slot print_timing: id 2 | task 150 | graphs reused = 1 3.24.148.900 I slot print_timing: id 2 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.148.943 I slot release: id 2 | task 150 | stop processing: n_tokens = 124, truncated = 0 3.24.149.100 I slot print_timing: id 3 | task 151 | prompt eval time = 5906.56 ms / 115 tokens ( 51.36 ms per token, 19.47 tokens per second) 3.24.149.104 I slot print_timing: id 3 | task 151 | eval time = 210.59 ms / 2 tokens ( 210.59 ms per token, 4.75 tokens per second) 3.24.149.104 I slot print_timing: id 3 | task 151 | total time = 6117.15 ms / 117 tokens 3.24.149.105 I slot print_timing: id 3 | task 151 | graphs reused = 1 3.24.149.105 I slot print_timing: id 3 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.149.138 I slot release: id 3 | task 151 | stop processing: n_tokens = 116, truncated = 0 3.24.154.929 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 3.24.189.268 I slot launch_slot_: id 3 | task 156 | processing task, is_child = 0 3.24.242.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 3.24.295.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.880 MiB) 3.24.325.204 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.241 3.24.325.295 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 3.24.325.332 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 3.24.325.372 I slot launch_slot_: id 1 | task 157 | processing task, is_child = 0 3.24.325.393 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 3.24.325.428 I slot launch_slot_: id 2 | task 158 | processing task, is_child = 0 3.30.488.522 I slot print_timing: id 0 | task 155 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.16 s / 20.44 tokens per second 3.30.801.081 I slot print_timing: id 1 | task 157 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.16 s / 20.12 tokens per second 3.30.805.502 I slot print_timing: id 2 | task 158 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.16 s / 22.23 tokens per second 3.30.809.934 I slot print_timing: id 3 | task 156 | prompt processing, n_tokens = 123, progress = 0.97, t = 6.16 s / 19.96 tokens per second 3.31.401.418 I slot print_timing: id 0 | task 155 | prompt eval time = 6865.18 ms / 130 tokens ( 52.81 ms per token, 18.94 tokens per second) 3.31.401.420 I slot print_timing: id 0 | task 155 | eval time = 210.80 ms / 2 tokens ( 210.80 ms per token, 4.74 tokens per second) 3.31.401.421 I slot print_timing: id 0 | task 155 | total time = 7075.98 ms / 132 tokens 3.31.401.421 I slot print_timing: id 0 | task 155 | graphs reused = 1 3.31.401.422 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.401.440 I slot release: id 0 | task 155 | stop processing: n_tokens = 131, truncated = 0 3.31.401.595 I slot print_timing: id 1 | task 157 | prompt eval time = 6865.37 ms / 128 tokens ( 53.64 ms per token, 18.64 tokens per second) 3.31.401.601 I slot print_timing: id 1 | task 157 | eval time = 210.77 ms / 2 tokens ( 210.77 ms per token, 4.74 tokens per second) 3.31.401.601 I slot print_timing: id 1 | task 157 | total time = 7076.14 ms / 130 tokens 3.31.401.602 I slot print_timing: id 1 | task 157 | graphs reused = 1 3.31.401.602 I slot print_timing: id 1 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.401.639 I slot release: id 1 | task 157 | stop processing: n_tokens = 129, truncated = 0 3.31.401.801 I slot print_timing: id 2 | task 158 | prompt eval time = 6865.59 ms / 141 tokens ( 48.69 ms per token, 20.54 tokens per second) 3.31.401.803 I slot print_timing: id 2 | task 158 | eval time = 210.74 ms / 2 tokens ( 210.74 ms per token, 4.75 tokens per second) 3.31.401.803 I slot print_timing: id 2 | task 158 | total time = 7076.33 ms / 143 tokens 3.31.401.804 I slot print_timing: id 2 | task 158 | graphs reused = 1 3.31.401.804 I slot print_timing: id 2 | task 158 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.401.823 I slot release: id 2 | task 158 | stop processing: n_tokens = 142, truncated = 0 3.31.402.014 I slot print_timing: id 3 | task 156 | prompt eval time = 6865.84 ms / 127 tokens ( 54.06 ms per token, 18.50 tokens per second) 3.31.402.016 I slot print_timing: id 3 | task 156 | eval time = 210.69 ms / 2 tokens ( 210.69 ms per token, 4.75 tokens per second) 3.31.402.017 I slot print_timing: id 3 | task 156 | total time = 7076.53 ms / 129 tokens 3.31.402.017 I slot print_timing: id 3 | task 156 | graphs reused = 1 3.31.402.017 I slot print_timing: id 3 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.402.030 I slot release: id 3 | task 156 | stop processing: n_tokens = 128, truncated = 0 3.31.407.822 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 3.31.407.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.31.458.728 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 3.31.458.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.321 MiB) 3.31.512.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 3.31.553.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 3.31.601.380 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 3.31.601.464 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 3.31.601.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 3.31.601.549 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 3.31.601.570 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.197 3.31.601.601 I slot launch_slot_: id 2 | task 165 | processing task, is_child = 0 3.37.550.749 I slot print_timing: id 0 | task 162 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.95 s / 20.00 tokens per second 3.37.983.118 I slot print_timing: id 1 | task 163 | prompt processing, n_tokens = 125, progress = 0.97, t = 5.95 s / 21.01 tokens per second 3.37.987.576 I slot print_timing: id 2 | task 165 | prompt processing, n_tokens = 157, progress = 0.98, t = 5.95 s / 26.39 tokens per second 3.38.013.293 I slot print_timing: id 3 | task 164 | prompt processing, n_tokens = 101, progress = 0.96, t = 5.95 s / 16.98 tokens per second 3.38.606.415 I slot print_timing: id 0 | task 162 | prompt eval time = 6794.01 ms / 123 tokens ( 55.24 ms per token, 18.10 tokens per second) 3.38.606.418 I slot print_timing: id 0 | task 162 | eval time = 210.79 ms / 2 tokens ( 210.79 ms per token, 4.74 tokens per second) 3.38.606.419 I slot print_timing: id 0 | task 162 | total time = 7004.80 ms / 125 tokens 3.38.606.419 I slot print_timing: id 0 | task 162 | graphs reused = 1 3.38.606.420 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.606.441 I slot release: id 0 | task 162 | stop processing: n_tokens = 124, truncated = 0 3.38.606.607 I slot print_timing: id 1 | task 163 | prompt eval time = 6794.15 ms / 129 tokens ( 52.67 ms per token, 18.99 tokens per second) 3.38.606.608 I slot print_timing: id 1 | task 163 | eval time = 210.82 ms / 2 tokens ( 210.82 ms per token, 4.74 tokens per second) 3.38.606.608 I slot print_timing: id 1 | task 163 | total time = 7004.97 ms / 131 tokens 3.38.606.609 I slot print_timing: id 1 | task 163 | graphs reused = 1 3.38.606.609 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.606.648 I slot release: id 1 | task 163 | stop processing: n_tokens = 130, truncated = 0 3.38.606.817 I slot print_timing: id 2 | task 165 | prompt eval time = 6794.47 ms / 161 tokens ( 42.20 ms per token, 23.70 tokens per second) 3.38.606.819 I slot print_timing: id 2 | task 165 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 3.38.606.819 I slot print_timing: id 2 | task 165 | total time = 7005.17 ms / 163 tokens 3.38.606.820 I slot print_timing: id 2 | task 165 | graphs reused = 1 3.38.606.820 I slot print_timing: id 2 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.606.858 I slot release: id 2 | task 165 | stop processing: n_tokens = 162, truncated = 0 3.38.607.038 I slot print_timing: id 3 | task 164 | prompt eval time = 6794.78 ms / 105 tokens ( 64.71 ms per token, 15.45 tokens per second) 3.38.607.041 I slot print_timing: id 3 | task 164 | eval time = 210.60 ms / 2 tokens ( 210.60 ms per token, 4.75 tokens per second) 3.38.607.041 I slot print_timing: id 3 | task 164 | total time = 7005.38 ms / 107 tokens 3.38.607.041 I slot print_timing: id 3 | task 164 | graphs reused = 1 3.38.607.041 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.607.157 I slot release: id 3 | task 164 | stop processing: n_tokens = 106, truncated = 0 3.38.613.550 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 3.38.613.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 3.38.661.286 I slot launch_slot_: id 3 | task 169 | processing task, is_child = 0 3.38.661.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 3.38.704.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 3.38.751.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.445 MiB) 3.38.798.975 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.226 3.38.799.062 I slot launch_slot_: id 0 | task 170 | processing task, is_child = 0 3.38.799.101 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.215 3.38.799.146 I slot launch_slot_: id 1 | task 171 | processing task, is_child = 0 3.38.799.167 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.173 3.38.799.209 I slot launch_slot_: id 2 | task 172 | processing task, is_child = 0 3.45.544.069 I slot print_timing: id 0 | task 170 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.74 s / 23.72 tokens per second 3.45.851.975 I slot print_timing: id 1 | task 171 | prompt processing, n_tokens = 150, progress = 0.97, t = 6.74 s / 22.24 tokens per second 3.45.856.440 I slot print_timing: id 2 | task 172 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.74 s / 20.31 tokens per second 3.45.860.861 I slot print_timing: id 3 | task 169 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.74 s / 15.72 tokens per second 3.46.452.382 I slot print_timing: id 0 | task 170 | prompt eval time = 7442.35 ms / 164 tokens ( 45.38 ms per token, 22.04 tokens per second) 3.46.452.387 I slot print_timing: id 0 | task 170 | eval time = 210.82 ms / 2 tokens ( 210.82 ms per token, 4.74 tokens per second) 3.46.452.388 I slot print_timing: id 0 | task 170 | total time = 7653.16 ms / 166 tokens 3.46.452.388 I slot print_timing: id 0 | task 170 | graphs reused = 1 3.46.452.388 I slot print_timing: id 0 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.452.442 I slot release: id 0 | task 170 | stop processing: n_tokens = 165, truncated = 0 3.46.452.594 I slot print_timing: id 1 | task 171 | prompt eval time = 7442.49 ms / 154 tokens ( 48.33 ms per token, 20.69 tokens per second) 3.46.452.598 I slot print_timing: id 1 | task 171 | eval time = 210.87 ms / 2 tokens ( 210.87 ms per token, 4.74 tokens per second) 3.46.452.598 I slot print_timing: id 1 | task 171 | total time = 7653.36 ms / 156 tokens 3.46.452.599 I slot print_timing: id 1 | task 171 | graphs reused = 1 3.46.452.599 I slot print_timing: id 1 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.452.620 I slot release: id 1 | task 171 | stop processing: n_tokens = 155, truncated = 0 3.46.452.780 I slot print_timing: id 2 | task 172 | prompt eval time = 7442.63 ms / 141 tokens ( 52.78 ms per token, 18.94 tokens per second) 3.46.452.783 I slot print_timing: id 2 | task 172 | eval time = 210.90 ms / 2 tokens ( 210.90 ms per token, 4.74 tokens per second) 3.46.452.783 I slot print_timing: id 2 | task 172 | total time = 7653.53 ms / 143 tokens 3.46.452.784 I slot print_timing: id 2 | task 172 | graphs reused = 1 3.46.452.784 I slot print_timing: id 2 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.452.809 I slot release: id 2 | task 172 | stop processing: n_tokens = 142, truncated = 0 3.46.452.963 I slot print_timing: id 3 | task 169 | prompt eval time = 7442.81 ms / 110 tokens ( 67.66 ms per token, 14.78 tokens per second) 3.46.452.966 I slot print_timing: id 3 | task 169 | eval time = 210.89 ms / 2 tokens ( 210.89 ms per token, 4.74 tokens per second) 3.46.452.967 I slot print_timing: id 3 | task 169 | total time = 7653.70 ms / 112 tokens 3.46.452.967 I slot print_timing: id 3 | task 169 | graphs reused = 1 3.46.452.967 I slot print_timing: id 3 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.452.987 I slot release: id 3 | task 169 | stop processing: n_tokens = 111, truncated = 0 3.46.459.104 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 3.46.459.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.443 MiB) 3.46.509.795 I slot launch_slot_: id 3 | task 176 | processing task, is_child = 0 3.46.509.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.46.549.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.320 MiB) 3.46.604.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.46.647.210 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.170 3.46.647.290 I slot launch_slot_: id 0 | task 177 | processing task, is_child = 0 3.46.647.328 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.181 3.46.647.366 I slot launch_slot_: id 1 | task 178 | processing task, is_child = 0 3.46.647.385 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.197 3.46.647.418 I slot launch_slot_: id 2 | task 179 | processing task, is_child = 0 3.52.208.716 I slot print_timing: id 0 | task 177 | prompt processing, n_tokens = 133, progress = 0.97, t = 5.56 s / 23.92 tokens per second 3.52.974.918 I slot print_timing: id 1 | task 178 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.56 s / 19.06 tokens per second 3.52.979.562 I slot print_timing: id 2 | task 179 | prompt processing, n_tokens = 144, progress = 0.97, t = 5.56 s / 25.89 tokens per second 3.52.984.632 I slot print_timing: id 3 | task 176 | prompt processing, n_tokens = 106, progress = 0.96, t = 5.56 s / 19.06 tokens per second 3.53.600.502 I slot print_timing: id 0 | task 177 | prompt eval time = 6742.57 ms / 137 tokens ( 49.22 ms per token, 20.32 tokens per second) 3.53.600.505 I slot print_timing: id 0 | task 177 | eval time = 210.50 ms / 2 tokens ( 210.50 ms per token, 4.75 tokens per second) 3.53.600.506 I slot print_timing: id 0 | task 177 | total time = 6953.07 ms / 139 tokens 3.53.600.506 I slot print_timing: id 0 | task 177 | graphs reused = 1 3.53.600.507 I slot print_timing: id 0 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.600.550 I slot release: id 0 | task 177 | stop processing: n_tokens = 138, truncated = 0 3.53.600.698 I slot print_timing: id 1 | task 178 | prompt eval time = 6742.72 ms / 110 tokens ( 61.30 ms per token, 16.31 tokens per second) 3.53.600.701 I slot print_timing: id 1 | task 178 | eval time = 210.53 ms / 2 tokens ( 210.53 ms per token, 4.75 tokens per second) 3.53.600.702 I slot print_timing: id 1 | task 178 | total time = 6953.26 ms / 112 tokens 3.53.600.702 I slot print_timing: id 1 | task 178 | graphs reused = 1 3.53.600.702 I slot print_timing: id 1 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.600.720 I slot release: id 1 | task 178 | stop processing: n_tokens = 111, truncated = 0 3.53.600.888 I slot print_timing: id 2 | task 179 | prompt eval time = 6742.88 ms / 148 tokens ( 45.56 ms per token, 21.95 tokens per second) 3.53.600.892 I slot print_timing: id 2 | task 179 | eval time = 210.56 ms / 2 tokens ( 210.56 ms per token, 4.75 tokens per second) 3.53.600.893 I slot print_timing: id 2 | task 179 | total time = 6953.43 ms / 150 tokens 3.53.600.893 I slot print_timing: id 2 | task 179 | graphs reused = 1 3.53.600.893 I slot print_timing: id 2 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.600.926 I slot release: id 2 | task 179 | stop processing: n_tokens = 149, truncated = 0 3.53.601.104 I slot print_timing: id 3 | task 176 | prompt eval time = 6743.03 ms / 110 tokens ( 61.30 ms per token, 16.31 tokens per second) 3.53.601.105 I slot print_timing: id 3 | task 176 | eval time = 210.60 ms / 2 tokens ( 210.60 ms per token, 4.75 tokens per second) 3.53.601.106 I slot print_timing: id 3 | task 176 | total time = 6953.63 ms / 112 tokens 3.53.601.106 I slot print_timing: id 3 | task 176 | graphs reused = 1 3.53.601.106 I slot print_timing: id 3 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.601.120 I slot release: id 3 | task 176 | stop processing: n_tokens = 111, truncated = 0 3.53.607.225 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.203 3.53.607.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 3.53.638.852 I slot launch_slot_: id 0 | task 185 | processing task, is_child = 0 3.53.638.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 3.53.669.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 3.53.682.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 3.53.714.731 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 3.53.714.812 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 3.53.714.849 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 3.53.714.880 I slot launch_slot_: id 3 | task 184 | processing task, is_child = 0 3.53.714.899 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.188 3.53.714.932 I slot launch_slot_: id 2 | task 186 | processing task, is_child = 0 3.59.953.468 I slot print_timing: id 0 | task 185 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.24 s / 19.08 tokens per second 4.00.384.468 I slot print_timing: id 1 | task 183 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.24 s / 23.72 tokens per second 4.00.388.934 I slot print_timing: id 2 | task 186 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.24 s / 20.20 tokens per second 4.00.415.033 I slot print_timing: id 3 | task 184 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.24 s / 17.31 tokens per second 4.01.006.500 I slot print_timing: id 0 | task 185 | prompt eval time = 7081.35 ms / 123 tokens ( 57.57 ms per token, 17.37 tokens per second) 4.01.006.505 I slot print_timing: id 0 | task 185 | eval time = 210.19 ms / 2 tokens ( 210.19 ms per token, 4.76 tokens per second) 4.01.006.505 I slot print_timing: id 0 | task 185 | total time = 7291.55 ms / 125 tokens 4.01.006.505 I slot print_timing: id 0 | task 185 | graphs reused = 1 4.01.006.506 I slot print_timing: id 0 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.006.530 I slot release: id 0 | task 185 | stop processing: n_tokens = 124, truncated = 0 4.01.006.687 I slot print_timing: id 1 | task 183 | prompt eval time = 7081.49 ms / 152 tokens ( 46.59 ms per token, 21.46 tokens per second) 4.01.006.689 I slot print_timing: id 1 | task 183 | eval time = 210.24 ms / 2 tokens ( 210.24 ms per token, 4.76 tokens per second) 4.01.006.690 I slot print_timing: id 1 | task 183 | total time = 7291.73 ms / 154 tokens 4.01.006.690 I slot print_timing: id 1 | task 183 | graphs reused = 1 4.01.006.690 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.006.705 I slot release: id 1 | task 183 | stop processing: n_tokens = 153, truncated = 0 4.01.006.865 I slot print_timing: id 2 | task 186 | prompt eval time = 7081.65 ms / 130 tokens ( 54.47 ms per token, 18.36 tokens per second) 4.01.006.870 I slot print_timing: id 2 | task 186 | eval time = 210.25 ms / 2 tokens ( 210.25 ms per token, 4.76 tokens per second) 4.01.006.870 I slot print_timing: id 2 | task 186 | total time = 7291.90 ms / 132 tokens 4.01.006.871 I slot print_timing: id 2 | task 186 | graphs reused = 1 4.01.006.871 I slot print_timing: id 2 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.006.924 I slot release: id 2 | task 186 | stop processing: n_tokens = 131, truncated = 0 4.01.007.083 I slot print_timing: id 3 | task 184 | prompt eval time = 7081.80 ms / 112 tokens ( 63.23 ms per token, 15.82 tokens per second) 4.01.007.085 I slot print_timing: id 3 | task 184 | eval time = 210.30 ms / 2 tokens ( 210.30 ms per token, 4.76 tokens per second) 4.01.007.086 I slot print_timing: id 3 | task 184 | total time = 7292.10 ms / 114 tokens 4.01.007.086 I slot print_timing: id 3 | task 184 | graphs reused = 1 4.01.007.086 I slot print_timing: id 3 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.007.103 I slot release: id 3 | task 184 | stop processing: n_tokens = 113, truncated = 0 4.01.012.810 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.226 4.01.012.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 4.01.045.130 I slot launch_slot_: id 0 | task 190 | processing task, is_child = 0 4.01.045.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.256 MiB) 4.01.101.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.01.160.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.569 MiB) 4.01.221.436 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 4.01.221.522 I slot launch_slot_: id 3 | task 192 | processing task, is_child = 0 4.01.221.580 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 4.01.221.623 I slot launch_slot_: id 2 | task 191 | processing task, is_child = 0 4.01.221.645 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.183 4.01.221.677 I slot launch_slot_: id 1 | task 193 | processing task, is_child = 0 4.07.940.305 I slot print_timing: id 0 | task 190 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.72 s / 22.77 tokens per second 4.08.246.262 I slot print_timing: id 1 | task 193 | prompt processing, n_tokens = 162, progress = 0.98, t = 6.72 s / 24.11 tokens per second 4.08.251.049 I slot print_timing: id 2 | task 191 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.72 s / 18.46 tokens per second 4.08.255.602 I slot print_timing: id 3 | task 192 | prompt processing, n_tokens = 110, progress = 0.96, t = 6.72 s / 16.37 tokens per second 4.08.847.171 I slot print_timing: id 0 | task 190 | prompt eval time = 7414.82 ms / 157 tokens ( 47.23 ms per token, 21.17 tokens per second) 4.08.847.176 I slot print_timing: id 0 | task 190 | eval time = 210.66 ms / 2 tokens ( 210.66 ms per token, 4.75 tokens per second) 4.08.847.176 I slot print_timing: id 0 | task 190 | total time = 7625.48 ms / 159 tokens 4.08.847.177 I slot print_timing: id 0 | task 190 | graphs reused = 1 4.08.847.177 I slot print_timing: id 0 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.847.216 I slot release: id 0 | task 190 | stop processing: n_tokens = 158, truncated = 0 4.08.847.365 I slot print_timing: id 1 | task 193 | prompt eval time = 7414.96 ms / 166 tokens ( 44.67 ms per token, 22.39 tokens per second) 4.08.847.368 I slot print_timing: id 1 | task 193 | eval time = 210.71 ms / 2 tokens ( 210.71 ms per token, 4.75 tokens per second) 4.08.847.369 I slot print_timing: id 1 | task 193 | total time = 7625.66 ms / 168 tokens 4.08.847.376 I slot print_timing: id 1 | task 193 | graphs reused = 1 4.08.847.378 I slot print_timing: id 1 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.847.404 I slot release: id 1 | task 193 | stop processing: n_tokens = 167, truncated = 0 4.08.847.562 I slot print_timing: id 2 | task 191 | prompt eval time = 7415.10 ms / 128 tokens ( 57.93 ms per token, 17.26 tokens per second) 4.08.847.568 I slot print_timing: id 2 | task 191 | eval time = 210.74 ms / 2 tokens ( 210.74 ms per token, 4.75 tokens per second) 4.08.847.568 I slot print_timing: id 2 | task 191 | total time = 7625.85 ms / 130 tokens 4.08.847.569 I slot print_timing: id 2 | task 191 | graphs reused = 1 4.08.847.569 I slot print_timing: id 2 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.847.594 I slot release: id 2 | task 191 | stop processing: n_tokens = 129, truncated = 0 4.08.847.762 I slot print_timing: id 3 | task 192 | prompt eval time = 7415.27 ms / 114 tokens ( 65.05 ms per token, 15.37 tokens per second) 4.08.847.765 I slot print_timing: id 3 | task 192 | eval time = 210.76 ms / 2 tokens ( 210.76 ms per token, 4.74 tokens per second) 4.08.847.765 I slot print_timing: id 3 | task 192 | total time = 7626.03 ms / 116 tokens 4.08.847.765 I slot print_timing: id 3 | task 192 | graphs reused = 1 4.08.847.765 I slot print_timing: id 3 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.847.775 I slot release: id 3 | task 192 | stop processing: n_tokens = 115, truncated = 0 4.08.853.435 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.177 4.08.853.465 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 4.08.916.722 I slot launch_slot_: id 0 | task 198 | processing task, is_child = 0 4.08.932.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.257 MiB) 4.08.965.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 4.08.973.139 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.168 4.08.973.218 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 4.08.973.255 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.217 4.08.973.290 I slot launch_slot_: id 2 | task 199 | processing task, is_child = 0 4.08.973.315 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.243 4.08.973.360 I slot launch_slot_: id 3 | task 200 | processing task, is_child = 0 4.15.669.381 I slot print_timing: id 0 | task 198 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.70 s / 20.46 tokens per second 4.16.103.461 I slot print_timing: id 1 | task 197 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.70 s / 15.53 tokens per second 4.16.109.675 I slot print_timing: id 2 | task 199 | prompt processing, n_tokens = 149, progress = 0.97, t = 6.70 s / 22.25 tokens per second 4.16.114.083 I slot print_timing: id 3 | task 200 | prompt processing, n_tokens = 175, progress = 0.98, t = 6.70 s / 26.14 tokens per second 4.16.705.541 I slot print_timing: id 0 | task 198 | prompt eval time = 7521.31 ms / 141 tokens ( 53.34 ms per token, 18.75 tokens per second) 4.16.705.543 I slot print_timing: id 0 | task 198 | eval time = 210.86 ms / 2 tokens ( 210.86 ms per token, 4.74 tokens per second) 4.16.705.544 I slot print_timing: id 0 | task 198 | total time = 7732.17 ms / 143 tokens 4.16.705.544 I slot print_timing: id 0 | task 198 | graphs reused = 1 4.16.705.545 I slot print_timing: id 0 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.705.567 I slot release: id 0 | task 198 | stop processing: n_tokens = 142, truncated = 0 4.16.705.716 I slot print_timing: id 1 | task 197 | prompt eval time = 7521.51 ms / 108 tokens ( 69.64 ms per token, 14.36 tokens per second) 4.16.705.718 I slot print_timing: id 1 | task 197 | eval time = 210.82 ms / 2 tokens ( 210.82 ms per token, 4.74 tokens per second) 4.16.705.719 I slot print_timing: id 1 | task 197 | total time = 7732.33 ms / 110 tokens 4.16.705.719 I slot print_timing: id 1 | task 197 | graphs reused = 1 4.16.705.719 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.705.733 I slot release: id 1 | task 197 | stop processing: n_tokens = 109, truncated = 0 4.16.705.905 I slot print_timing: id 2 | task 199 | prompt eval time = 7521.71 ms / 153 tokens ( 49.16 ms per token, 20.34 tokens per second) 4.16.705.907 I slot print_timing: id 2 | task 199 | eval time = 210.79 ms / 2 tokens ( 210.79 ms per token, 4.74 tokens per second) 4.16.705.908 I slot print_timing: id 2 | task 199 | total time = 7732.51 ms / 155 tokens 4.16.705.908 I slot print_timing: id 2 | task 199 | graphs reused = 1 4.16.705.909 I slot print_timing: id 2 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.705.920 I slot release: id 2 | task 199 | stop processing: n_tokens = 154, truncated = 0 4.16.706.078 I slot print_timing: id 3 | task 200 | prompt eval time = 7521.92 ms / 179 tokens ( 42.02 ms per token, 23.80 tokens per second) 4.16.706.080 I slot print_timing: id 3 | task 200 | eval time = 210.75 ms / 2 tokens ( 210.75 ms per token, 4.75 tokens per second) 4.16.706.080 I slot print_timing: id 3 | task 200 | total time = 7732.67 ms / 181 tokens 4.16.706.080 I slot print_timing: id 3 | task 200 | graphs reused = 1 4.16.706.081 I slot print_timing: id 3 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.706.117 I slot release: id 3 | task 200 | stop processing: n_tokens = 180, truncated = 0 4.16.712.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 4.16.712.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.16.722.670 I slot launch_slot_: id 0 | task 205 | processing task, is_child = 0 4.16.722.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.16.736.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.16.763.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 4.16.783.656 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 4.16.783.731 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 4.16.783.770 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.182 4.16.787.126 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 4.16.787.153 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.156 4.16.787.193 I slot launch_slot_: id 3 | task 207 | processing task, is_child = 0 4.22.745.481 I slot print_timing: id 0 | task 205 | prompt processing, n_tokens = 131, progress = 0.97, t = 5.96 s / 21.99 tokens per second 4.23.515.634 I slot print_timing: id 1 | task 204 | prompt processing, n_tokens = 130, progress = 0.97, t = 5.96 s / 21.82 tokens per second 4.23.520.240 I slot print_timing: id 2 | task 206 | prompt processing, n_tokens = 112, progress = 0.97, t = 5.96 s / 18.80 tokens per second 4.23.525.190 I slot print_timing: id 3 | task 207 | prompt processing, n_tokens = 154, progress = 0.97, t = 5.96 s / 25.85 tokens per second 4.24.116.944 I slot print_timing: id 0 | task 205 | prompt eval time = 7119.20 ms / 135 tokens ( 52.73 ms per token, 18.96 tokens per second) 4.24.116.949 I slot print_timing: id 0 | task 205 | eval time = 210.54 ms / 2 tokens ( 210.54 ms per token, 4.75 tokens per second) 4.24.116.950 I slot print_timing: id 0 | task 205 | total time = 7329.74 ms / 137 tokens 4.24.116.950 I slot print_timing: id 0 | task 205 | graphs reused = 1 4.24.116.951 I slot print_timing: id 0 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.117.004 I slot release: id 0 | task 205 | stop processing: n_tokens = 136, truncated = 0 4.24.117.150 I slot print_timing: id 1 | task 204 | prompt eval time = 7119.39 ms / 134 tokens ( 53.13 ms per token, 18.82 tokens per second) 4.24.117.155 I slot print_timing: id 1 | task 204 | eval time = 210.54 ms / 2 tokens ( 210.54 ms per token, 4.75 tokens per second) 4.24.117.156 I slot print_timing: id 1 | task 204 | total time = 7329.93 ms / 136 tokens 4.24.117.156 I slot print_timing: id 1 | task 204 | graphs reused = 1 4.24.117.156 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.117.167 I slot release: id 1 | task 204 | stop processing: n_tokens = 135, truncated = 0 4.24.117.344 I slot print_timing: id 2 | task 206 | prompt eval time = 7119.58 ms / 116 tokens ( 61.38 ms per token, 16.29 tokens per second) 4.24.117.346 I slot print_timing: id 2 | task 206 | eval time = 210.54 ms / 2 tokens ( 210.54 ms per token, 4.75 tokens per second) 4.24.117.346 I slot print_timing: id 2 | task 206 | total time = 7330.12 ms / 118 tokens 4.24.117.346 I slot print_timing: id 2 | task 206 | graphs reused = 1 4.24.117.347 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.117.359 I slot release: id 2 | task 206 | stop processing: n_tokens = 117, truncated = 0 4.24.117.526 I slot print_timing: id 3 | task 207 | prompt eval time = 7119.79 ms / 158 tokens ( 45.06 ms per token, 22.19 tokens per second) 4.24.117.527 I slot print_timing: id 3 | task 207 | eval time = 210.50 ms / 2 tokens ( 210.50 ms per token, 4.75 tokens per second) 4.24.117.527 I slot print_timing: id 3 | task 207 | total time = 7330.29 ms / 160 tokens 4.24.117.527 I slot print_timing: id 3 | task 207 | graphs reused = 1 4.24.117.528 I slot print_timing: id 3 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.117.557 I slot release: id 3 | task 207 | stop processing: n_tokens = 159, truncated = 0 4.24.123.154 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.248 4.24.142.108 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 4.24.150.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.24.166.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.24.176.243 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.206 4.24.179.629 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 4.24.179.668 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.207 4.24.179.701 I slot launch_slot_: id 1 | task 213 | processing task, is_child = 0 4.24.179.723 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.176 4.24.179.758 I slot launch_slot_: id 3 | task 214 | processing task, is_child = 0 4.30.418.429 I slot print_timing: id 0 | task 211 | prompt processing, n_tokens = 113, progress = 0.97, t = 6.24 s / 18.11 tokens per second 4.31.182.358 I slot print_timing: id 1 | task 213 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.24 s / 23.24 tokens per second 4.31.187.580 I slot print_timing: id 2 | task 212 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.24 s / 18.91 tokens per second 4.31.194.063 I slot print_timing: id 3 | task 214 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.24 s / 24.52 tokens per second 4.31.785.342 I slot print_timing: id 0 | task 211 | prompt eval time = 7394.82 ms / 117 tokens ( 63.20 ms per token, 15.82 tokens per second) 4.31.785.344 I slot print_timing: id 0 | task 211 | eval time = 210.75 ms / 2 tokens ( 210.75 ms per token, 4.75 tokens per second) 4.31.785.344 I slot print_timing: id 0 | task 211 | total time = 7605.57 ms / 119 tokens 4.31.785.345 I slot print_timing: id 0 | task 211 | graphs reused = 1 4.31.785.345 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.785.365 I slot release: id 0 | task 211 | stop processing: n_tokens = 118, truncated = 0 4.31.785.512 I slot print_timing: id 1 | task 213 | prompt eval time = 7395.01 ms / 149 tokens ( 49.63 ms per token, 20.15 tokens per second) 4.31.785.515 I slot print_timing: id 1 | task 213 | eval time = 210.72 ms / 2 tokens ( 210.72 ms per token, 4.75 tokens per second) 4.31.785.516 I slot print_timing: id 1 | task 213 | total time = 7605.73 ms / 151 tokens 4.31.785.516 I slot print_timing: id 1 | task 213 | graphs reused = 1 4.31.785.516 I slot print_timing: id 1 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.785.536 I slot release: id 1 | task 213 | stop processing: n_tokens = 150, truncated = 0 4.31.785.700 I slot print_timing: id 2 | task 212 | prompt eval time = 7395.20 ms / 122 tokens ( 60.62 ms per token, 16.50 tokens per second) 4.31.785.701 I slot print_timing: id 2 | task 212 | eval time = 210.70 ms / 2 tokens ( 210.70 ms per token, 4.75 tokens per second) 4.31.785.702 I slot print_timing: id 2 | task 212 | total time = 7605.90 ms / 124 tokens 4.31.785.702 I slot print_timing: id 2 | task 212 | graphs reused = 1 4.31.785.703 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.785.718 I slot release: id 2 | task 212 | stop processing: n_tokens = 123, truncated = 0 4.31.785.892 I slot print_timing: id 3 | task 214 | prompt eval time = 7395.41 ms / 157 tokens ( 47.10 ms per token, 21.23 tokens per second) 4.31.785.894 I slot print_timing: id 3 | task 214 | eval time = 210.68 ms / 2 tokens ( 210.68 ms per token, 4.75 tokens per second) 4.31.785.901 I slot print_timing: id 3 | task 214 | total time = 7606.08 ms / 159 tokens 4.31.785.903 I slot print_timing: id 3 | task 214 | graphs reused = 1 4.31.785.904 I slot print_timing: id 3 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.785.920 I slot release: id 3 | task 214 | stop processing: n_tokens = 158, truncated = 0 4.31.792.238 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.237 4.31.801.017 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 4.31.801.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 4.31.810.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 4.31.821.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 4.31.831.202 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.187 4.31.831.270 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 4.31.831.310 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.228 4.31.831.349 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 4.31.831.370 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.177 4.31.831.409 I slot launch_slot_: id 3 | task 221 | processing task, is_child = 0 4.39.287.909 I slot print_timing: id 0 | task 218 | prompt processing, n_tokens = 145, progress = 0.97, t = 7.46 s / 19.45 tokens per second 4.39.390.241 I slot print_timing: id 1 | task 219 | prompt processing, n_tokens = 156, progress = 0.97, t = 7.46 s / 20.92 tokens per second 4.39.394.628 I slot print_timing: id 2 | task 220 | prompt processing, n_tokens = 150, progress = 0.97, t = 7.46 s / 20.12 tokens per second 4.39.399.059 I slot print_timing: id 3 | task 221 | prompt processing, n_tokens = 151, progress = 0.97, t = 7.46 s / 20.25 tokens per second 4.39.990.896 I slot print_timing: id 0 | task 218 | prompt eval time = 7948.51 ms / 149 tokens ( 53.35 ms per token, 18.75 tokens per second) 4.39.990.901 I slot print_timing: id 0 | task 218 | eval time = 210.96 ms / 2 tokens ( 210.96 ms per token, 4.74 tokens per second) 4.39.990.901 I slot print_timing: id 0 | task 218 | total time = 8159.48 ms / 151 tokens 4.39.990.902 I slot print_timing: id 0 | task 218 | graphs reused = 1 4.39.990.902 I slot print_timing: id 0 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.990.924 I slot release: id 0 | task 218 | stop processing: n_tokens = 150, truncated = 0 4.39.991.068 I slot print_timing: id 1 | task 219 | prompt eval time = 7948.71 ms / 160 tokens ( 49.68 ms per token, 20.13 tokens per second) 4.39.991.070 I slot print_timing: id 1 | task 219 | eval time = 210.92 ms / 2 tokens ( 210.92 ms per token, 4.74 tokens per second) 4.39.991.071 I slot print_timing: id 1 | task 219 | total time = 8159.63 ms / 162 tokens 4.39.991.071 I slot print_timing: id 1 | task 219 | graphs reused = 1 4.39.991.071 I slot print_timing: id 1 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.991.100 I slot release: id 1 | task 219 | stop processing: n_tokens = 161, truncated = 0 4.39.991.273 I slot print_timing: id 2 | task 220 | prompt eval time = 7948.90 ms / 154 tokens ( 51.62 ms per token, 19.37 tokens per second) 4.39.991.275 I slot print_timing: id 2 | task 220 | eval time = 210.92 ms / 2 tokens ( 210.92 ms per token, 4.74 tokens per second) 4.39.991.275 I slot print_timing: id 2 | task 220 | total time = 8159.82 ms / 156 tokens 4.39.991.276 I slot print_timing: id 2 | task 220 | graphs reused = 1 4.39.991.276 I slot print_timing: id 2 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.991.312 I slot release: id 2 | task 220 | stop processing: n_tokens = 155, truncated = 0 4.39.991.473 I slot print_timing: id 3 | task 221 | prompt eval time = 7949.12 ms / 155 tokens ( 51.28 ms per token, 19.50 tokens per second) 4.39.991.475 I slot print_timing: id 3 | task 221 | eval time = 210.89 ms / 2 tokens ( 210.89 ms per token, 4.74 tokens per second) 4.39.991.475 I slot print_timing: id 3 | task 221 | total time = 8160.01 ms / 157 tokens 4.39.991.475 I slot print_timing: id 3 | task 221 | graphs reused = 1 4.39.991.476 I slot print_timing: id 3 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.991.486 I slot release: id 3 | task 221 | stop processing: n_tokens = 156, truncated = 0 4.39.997.529 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.187 4.39.997.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 4.40.012.848 I slot launch_slot_: id 0 | task 226 | processing task, is_child = 0 4.40.020.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.40.031.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 4.40.041.224 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.174 4.40.041.296 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 4.40.041.334 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.181 4.40.041.372 I slot launch_slot_: id 2 | task 227 | processing task, is_child = 0 4.40.041.393 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.179 4.40.041.424 I slot launch_slot_: id 3 | task 228 | processing task, is_child = 0 4.45.487.034 I slot print_timing: id 0 | task 226 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.45 s / 18.00 tokens per second 4.46.629.218 I slot print_timing: id 1 | task 225 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.45 s / 18.91 tokens per second 4.46.633.664 I slot print_timing: id 2 | task 227 | prompt processing, n_tokens = 110, progress = 0.96, t = 5.45 s / 20.20 tokens per second 4.46.638.099 I slot print_timing: id 3 | task 228 | prompt processing, n_tokens = 181, progress = 0.98, t = 5.45 s / 33.24 tokens per second 4.47.229.337 I slot print_timing: id 0 | task 226 | prompt eval time = 6977.31 ms / 102 tokens ( 68.41 ms per token, 14.62 tokens per second) 4.47.229.342 I slot print_timing: id 0 | task 226 | eval time = 210.59 ms / 2 tokens ( 210.59 ms per token, 4.75 tokens per second) 4.47.229.343 I slot print_timing: id 0 | task 226 | total time = 7187.90 ms / 104 tokens 4.47.229.343 I slot print_timing: id 0 | task 226 | graphs reused = 1 4.47.229.344 I slot print_timing: id 0 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.229.384 I slot release: id 0 | task 226 | stop processing: n_tokens = 103, truncated = 0 4.47.229.532 I slot print_timing: id 1 | task 225 | prompt eval time = 6977.49 ms / 107 tokens ( 65.21 ms per token, 15.34 tokens per second) 4.47.229.534 I slot print_timing: id 1 | task 225 | eval time = 210.59 ms / 2 tokens ( 210.59 ms per token, 4.75 tokens per second) 4.47.229.534 I slot print_timing: id 1 | task 225 | total time = 7188.08 ms / 109 tokens 4.47.229.534 I slot print_timing: id 1 | task 225 | graphs reused = 1 4.47.229.535 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.229.546 I slot release: id 1 | task 225 | stop processing: n_tokens = 108, truncated = 0 4.47.229.712 I slot print_timing: id 2 | task 227 | prompt eval time = 6977.67 ms / 114 tokens ( 61.21 ms per token, 16.34 tokens per second) 4.47.229.713 I slot print_timing: id 2 | task 227 | eval time = 210.57 ms / 2 tokens ( 210.57 ms per token, 4.75 tokens per second) 4.47.229.713 I slot print_timing: id 2 | task 227 | total time = 7188.25 ms / 116 tokens 4.47.229.713 I slot print_timing: id 2 | task 227 | graphs reused = 1 4.47.229.714 I slot print_timing: id 2 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.229.744 I slot release: id 2 | task 227 | stop processing: n_tokens = 115, truncated = 0 4.47.229.898 I slot print_timing: id 3 | task 228 | prompt eval time = 6977.88 ms / 185 tokens ( 37.72 ms per token, 26.51 tokens per second) 4.47.229.901 I slot print_timing: id 3 | task 228 | eval time = 210.54 ms / 2 tokens ( 210.54 ms per token, 4.75 tokens per second) 4.47.229.901 I slot print_timing: id 3 | task 228 | total time = 7188.42 ms / 187 tokens 4.47.229.901 I slot print_timing: id 3 | task 228 | graphs reused = 1 4.47.229.902 I slot print_timing: id 3 | task 228 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.229.912 I slot release: id 3 | task 228 | stop processing: n_tokens = 186, truncated = 0 4.47.235.664 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 4.47.235.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 4.47.246.222 I slot launch_slot_: id 0 | task 233 | processing task, is_child = 0 4.47.246.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.569 MiB) 4.47.255.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 4.47.268.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.47.289.472 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.259 4.47.289.541 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 4.47.289.587 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 4.47.289.622 I slot launch_slot_: id 2 | task 234 | processing task, is_child = 0 4.47.289.642 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.151 4.47.289.680 I slot launch_slot_: id 3 | task 235 | processing task, is_child = 0 4.53.381.468 I slot print_timing: id 0 | task 233 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.09 s / 17.40 tokens per second 4.54.148.697 I slot print_timing: id 1 | task 232 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.09 s / 19.37 tokens per second 4.54.153.511 I slot print_timing: id 2 | task 234 | prompt processing, n_tokens = 122, progress = 0.97, t = 6.09 s / 20.03 tokens per second 4.54.158.443 I slot print_timing: id 3 | task 235 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.09 s / 26.27 tokens per second 4.54.750.688 I slot print_timing: id 0 | task 233 | prompt eval time = 7250.18 ms / 110 tokens ( 65.91 ms per token, 15.17 tokens per second) 4.54.750.691 I slot print_timing: id 0 | task 233 | eval time = 210.82 ms / 2 tokens ( 210.82 ms per token, 4.74 tokens per second) 4.54.750.692 I slot print_timing: id 0 | task 233 | total time = 7460.99 ms / 112 tokens 4.54.750.693 I slot print_timing: id 0 | task 233 | graphs reused = 1 4.54.750.693 I slot print_timing: id 0 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.750.716 I slot release: id 0 | task 233 | stop processing: n_tokens = 111, truncated = 0 4.54.750.870 I slot print_timing: id 1 | task 232 | prompt eval time = 7250.33 ms / 122 tokens ( 59.43 ms per token, 16.83 tokens per second) 4.54.750.872 I slot print_timing: id 1 | task 232 | eval time = 210.84 ms / 2 tokens ( 210.84 ms per token, 4.74 tokens per second) 4.54.750.872 I slot print_timing: id 1 | task 232 | total time = 7461.17 ms / 124 tokens 4.54.750.873 I slot print_timing: id 1 | task 232 | graphs reused = 1 4.54.750.873 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.750.888 I slot release: id 1 | task 232 | stop processing: n_tokens = 123, truncated = 0 4.54.751.057 I slot print_timing: id 2 | task 234 | prompt eval time = 7250.48 ms / 126 tokens ( 57.54 ms per token, 17.38 tokens per second) 4.54.751.061 I slot print_timing: id 2 | task 234 | eval time = 210.86 ms / 2 tokens ( 210.86 ms per token, 4.74 tokens per second) 4.54.751.062 I slot print_timing: id 2 | task 234 | total time = 7461.35 ms / 128 tokens 4.54.751.062 I slot print_timing: id 2 | task 234 | graphs reused = 1 4.54.751.062 I slot print_timing: id 2 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.751.072 I slot release: id 2 | task 234 | stop processing: n_tokens = 127, truncated = 0 4.54.751.252 I slot print_timing: id 3 | task 235 | prompt eval time = 7250.64 ms / 164 tokens ( 44.21 ms per token, 22.62 tokens per second) 4.54.751.253 I slot print_timing: id 3 | task 235 | eval time = 210.89 ms / 2 tokens ( 210.89 ms per token, 4.74 tokens per second) 4.54.751.254 I slot print_timing: id 3 | task 235 | total time = 7461.53 ms / 166 tokens 4.54.751.254 I slot print_timing: id 3 | task 235 | graphs reused = 1 4.54.751.254 I slot print_timing: id 3 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.751.264 I slot release: id 3 | task 235 | stop processing: n_tokens = 165, truncated = 0 4.54.757.343 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.252 4.54.757.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 4.54.767.563 I slot launch_slot_: id 0 | task 240 | processing task, is_child = 0 4.54.767.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.54.777.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.318 MiB) 4.54.788.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 4.54.797.901 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 4.54.797.961 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 4.54.797.995 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.220 4.54.801.352 I slot launch_slot_: id 2 | task 242 | processing task, is_child = 0 4.54.801.374 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.170 4.54.804.681 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 5.00.902.568 I slot print_timing: id 0 | task 240 | prompt processing, n_tokens = 121, progress = 0.97, t = 6.10 s / 19.84 tokens per second 5.01.004.950 I slot print_timing: id 1 | task 239 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.10 s / 19.35 tokens per second 5.01.009.690 I slot print_timing: id 2 | task 242 | prompt processing, n_tokens = 134, progress = 0.97, t = 6.10 s / 21.97 tokens per second 5.01.014.691 I slot print_timing: id 3 | task 241 | prompt processing, n_tokens = 133, progress = 0.97, t = 6.10 s / 21.81 tokens per second 5.01.606.031 I slot print_timing: id 0 | task 240 | prompt eval time = 6591.19 ms / 125 tokens ( 52.73 ms per token, 18.96 tokens per second) 5.01.606.034 I slot print_timing: id 0 | task 240 | eval time = 210.15 ms / 2 tokens ( 210.15 ms per token, 4.76 tokens per second) 5.01.606.035 I slot print_timing: id 0 | task 240 | total time = 6801.34 ms / 127 tokens 5.01.606.035 I slot print_timing: id 0 | task 240 | graphs reused = 1 5.01.606.036 I slot print_timing: id 0 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.606.060 I slot release: id 0 | task 240 | stop processing: n_tokens = 126, truncated = 0 5.01.606.208 I slot print_timing: id 1 | task 239 | prompt eval time = 6591.38 ms / 122 tokens ( 54.03 ms per token, 18.51 tokens per second) 5.01.606.210 I slot print_timing: id 1 | task 239 | eval time = 210.13 ms / 2 tokens ( 210.13 ms per token, 4.76 tokens per second) 5.01.606.211 I slot print_timing: id 1 | task 239 | total time = 6801.51 ms / 124 tokens 5.01.606.211 I slot print_timing: id 1 | task 239 | graphs reused = 1 5.01.606.211 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.606.223 I slot release: id 1 | task 239 | stop processing: n_tokens = 123, truncated = 0 5.01.606.387 I slot print_timing: id 2 | task 242 | prompt eval time = 6591.57 ms / 138 tokens ( 47.76 ms per token, 20.94 tokens per second) 5.01.606.391 I slot print_timing: id 2 | task 242 | eval time = 210.11 ms / 2 tokens ( 210.11 ms per token, 4.76 tokens per second) 5.01.606.391 I slot print_timing: id 2 | task 242 | total time = 6801.68 ms / 140 tokens 5.01.606.391 I slot print_timing: id 2 | task 242 | graphs reused = 1 5.01.606.392 I slot print_timing: id 2 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.606.421 I slot release: id 2 | task 242 | stop processing: n_tokens = 139, truncated = 0 5.01.606.579 I slot print_timing: id 3 | task 241 | prompt eval time = 6591.77 ms / 137 tokens ( 48.12 ms per token, 20.78 tokens per second) 5.01.606.582 I slot print_timing: id 3 | task 241 | eval time = 210.09 ms / 2 tokens ( 210.09 ms per token, 4.76 tokens per second) 5.01.606.582 I slot print_timing: id 3 | task 241 | total time = 6801.86 ms / 139 tokens 5.01.606.582 I slot print_timing: id 3 | task 241 | graphs reused = 1 5.01.606.582 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.606.600 I slot release: id 3 | task 241 | stop processing: n_tokens = 138, truncated = 0 5.01.612.116 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.222 5.01.620.750 I slot launch_slot_: id 0 | task 247 | processing task, is_child = 0 5.01.628.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 5.01.636.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 5.01.651.571 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.228 5.01.655.486 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 5.01.655.525 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.201 5.01.655.558 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 5.01.655.576 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.203 5.01.655.609 I slot launch_slot_: id 3 | task 249 | processing task, is_child = 0 5.08.377.669 I slot print_timing: id 0 | task 247 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.72 s / 17.26 tokens per second 5.08.813.545 I slot print_timing: id 1 | task 246 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.72 s / 22.91 tokens per second 5.08.818.489 I slot print_timing: id 2 | task 248 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.72 s / 20.23 tokens per second 5.08.823.370 I slot print_timing: id 3 | task 249 | prompt processing, n_tokens = 164, progress = 0.98, t = 6.72 s / 24.40 tokens per second 5.09.415.507 I slot print_timing: id 0 | task 247 | prompt eval time = 7549.24 ms / 120 tokens ( 62.91 ms per token, 15.90 tokens per second) 5.09.415.509 I slot print_timing: id 0 | task 247 | eval time = 210.64 ms / 2 tokens ( 210.64 ms per token, 4.75 tokens per second) 5.09.415.509 I slot print_timing: id 0 | task 247 | total time = 7759.88 ms / 122 tokens 5.09.415.510 I slot print_timing: id 0 | task 247 | graphs reused = 1 5.09.415.510 I slot print_timing: id 0 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.415.533 I slot release: id 0 | task 247 | stop processing: n_tokens = 121, truncated = 0 5.09.415.685 I slot print_timing: id 1 | task 246 | prompt eval time = 7549.43 ms / 158 tokens ( 47.78 ms per token, 20.93 tokens per second) 5.09.415.689 I slot print_timing: id 1 | task 246 | eval time = 210.63 ms / 2 tokens ( 210.63 ms per token, 4.75 tokens per second) 5.09.415.690 I slot print_timing: id 1 | task 246 | total time = 7760.06 ms / 160 tokens 5.09.415.690 I slot print_timing: id 1 | task 246 | graphs reused = 1 5.09.415.690 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.415.705 I slot release: id 1 | task 246 | stop processing: n_tokens = 159, truncated = 0 5.09.415.875 I slot print_timing: id 2 | task 248 | prompt eval time = 7549.61 ms / 140 tokens ( 53.93 ms per token, 18.54 tokens per second) 5.09.415.877 I slot print_timing: id 2 | task 248 | eval time = 210.62 ms / 2 tokens ( 210.62 ms per token, 4.75 tokens per second) 5.09.415.877 I slot print_timing: id 2 | task 248 | total time = 7760.24 ms / 142 tokens 5.09.415.877 I slot print_timing: id 2 | task 248 | graphs reused = 1 5.09.415.878 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.415.890 I slot release: id 2 | task 248 | stop processing: n_tokens = 141, truncated = 0 5.09.416.070 I slot print_timing: id 3 | task 249 | prompt eval time = 7549.82 ms / 168 tokens ( 44.94 ms per token, 22.25 tokens per second) 5.09.416.072 I slot print_timing: id 3 | task 249 | eval time = 210.60 ms / 2 tokens ( 210.60 ms per token, 4.75 tokens per second) 5.09.416.073 I slot print_timing: id 3 | task 249 | total time = 7760.42 ms / 170 tokens 5.09.416.073 I slot print_timing: id 3 | task 249 | graphs reused = 1 5.09.416.073 I slot print_timing: id 3 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.416.107 I slot release: id 3 | task 249 | stop processing: n_tokens = 169, truncated = 0 5.09.421.965 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 5.09.429.983 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 5.09.430.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 5.09.438.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 5.09.446.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.881 MiB) 5.09.457.788 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.176 5.09.461.288 I slot launch_slot_: id 1 | task 254 | processing task, is_child = 0 5.09.461.329 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.199 5.09.461.365 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 5.09.461.389 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.166 5.09.461.422 I slot launch_slot_: id 3 | task 256 | processing task, is_child = 0 5.16.187.691 I slot print_timing: id 0 | task 253 | prompt processing, n_tokens = 99, progress = 0.96, t = 6.73 s / 14.72 tokens per second 5.16.621.913 I slot print_timing: id 1 | task 254 | prompt processing, n_tokens = 129, progress = 0.97, t = 6.73 s / 19.18 tokens per second 5.16.626.362 I slot print_timing: id 2 | task 255 | prompt processing, n_tokens = 178, progress = 0.98, t = 6.73 s / 26.46 tokens per second 5.16.630.803 I slot print_timing: id 3 | task 256 | prompt processing, n_tokens = 151, progress = 0.97, t = 6.73 s / 22.45 tokens per second 5.17.222.703 I slot print_timing: id 0 | task 253 | prompt eval time = 7550.28 ms / 103 tokens ( 73.30 ms per token, 13.64 tokens per second) 5.17.222.708 I slot print_timing: id 0 | task 253 | eval time = 210.99 ms / 2 tokens ( 210.99 ms per token, 4.74 tokens per second) 5.17.222.708 I slot print_timing: id 0 | task 253 | total time = 7761.27 ms / 105 tokens 5.17.222.709 I slot print_timing: id 0 | task 253 | graphs reused = 1 5.17.222.709 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.222.728 I slot release: id 0 | task 253 | stop processing: n_tokens = 104, truncated = 0 5.17.222.876 I slot print_timing: id 1 | task 254 | prompt eval time = 7550.47 ms / 133 tokens ( 56.77 ms per token, 17.61 tokens per second) 5.17.222.878 I slot print_timing: id 1 | task 254 | eval time = 210.97 ms / 2 tokens ( 210.97 ms per token, 4.74 tokens per second) 5.17.222.879 I slot print_timing: id 1 | task 254 | total time = 7761.44 ms / 135 tokens 5.17.222.879 I slot print_timing: id 1 | task 254 | graphs reused = 1 5.17.222.879 I slot print_timing: id 1 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.222.891 I slot release: id 1 | task 254 | stop processing: n_tokens = 134, truncated = 0 5.17.223.048 I slot print_timing: id 2 | task 255 | prompt eval time = 7550.67 ms / 182 tokens ( 41.49 ms per token, 24.10 tokens per second) 5.17.223.053 I slot print_timing: id 2 | task 255 | eval time = 210.93 ms / 2 tokens ( 210.93 ms per token, 4.74 tokens per second) 5.17.223.053 I slot print_timing: id 2 | task 255 | total time = 7761.60 ms / 184 tokens 5.17.223.054 I slot print_timing: id 2 | task 255 | graphs reused = 1 5.17.223.054 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.223.072 I slot release: id 2 | task 255 | stop processing: n_tokens = 183, truncated = 0 5.17.223.269 I slot print_timing: id 3 | task 256 | prompt eval time = 7550.88 ms / 155 tokens ( 48.72 ms per token, 20.53 tokens per second) 5.17.223.272 I slot print_timing: id 3 | task 256 | eval time = 210.92 ms / 2 tokens ( 210.92 ms per token, 4.74 tokens per second) 5.17.223.272 I slot print_timing: id 3 | task 256 | total time = 7761.80 ms / 157 tokens 5.17.223.272 I slot print_timing: id 3 | task 256 | graphs reused = 1 5.17.223.273 I slot print_timing: id 3 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 5.17.223.309 I slot release: id 3 | task 256 | stop processing: n_tokens = 156, truncated = 0 5.17.228.987 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.269 5.17.237.431 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 5.17.237.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.507 MiB) 5.17.245.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.568 MiB) 5.17.263.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 5.17.272.162 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.209 5.17.272.239 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 5.21.006.476 I slot print_timing: id 0 | task 260 | prompt eval time = 3548.63 ms / 144 tokens ( 24.64 ms per token, 40.58 tokens per second) 5.21.006.482 I slot print_timing: id 0 | task 260 | eval time = 185.56 ms / 2 tokens ( 185.56 ms per token, 5.39 tokens per second) 5.21.006.482 I slot print_timing: id 0 | task 260 | total time = 3734.19 ms / 146 tokens 5.21.006.483 I slot print_timing: id 0 | task 260 | graphs reused = 1 5.21.006.483 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.006.498 I slot release: id 0 | task 260 | stop processing: n_tokens = 145, truncated = 0 5.21.006.642 I slot print_timing: id 1 | task 261 | prompt eval time = 3548.78 ms / 124 tokens ( 28.62 ms per token, 34.94 tokens per second) 5.21.006.646 I slot print_timing: id 1 | task 261 | eval time = 185.56 ms / 2 tokens ( 185.56 ms per token, 5.39 tokens per second) 5.21.006.647 I slot print_timing: id 1 | task 261 | total time = 3734.34 ms / 126 tokens 5.21.006.647 I slot print_timing: id 1 | task 261 | graphs reused = 1 5.21.006.647 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.006.670 I slot release: id 1 | task 261 | stop processing: n_tokens = 125, truncated = 0 5.21.025.837 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 94684456629 5.21.025.946 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 5.21.025.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 5.21.034.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 5.21.042.413 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 94684456866 5.21.042.460 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 5.21.042.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 94688240055 5.21.042.522 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 5.21.042.538 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 94688240227 5.21.042.567 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 5.26.803.621 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.76 s / 25.34 tokens per second 5.27.994.612 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.76 s / 25.34 tokens per second 5.27.999.562 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.76 s / 25.34 tokens per second 5.28.004.026 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 146, progress = 0.12, t = 5.76 s / 25.34 tokens per second 5.28.015.358 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.97 s / 36.86 tokens per second 5.28.015.376 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.97 s / 36.86 tokens per second 5.28.015.400 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.97 s / 36.86 tokens per second 5.28.015.414 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 257, progress = 0.21, t = 6.97 s / 36.86 tokens per second 5.54.507.507 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 727, progress = 0.58, t = 33.46 s / 21.72 tokens per second 5.54.826.397 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 718, progress = 0.58, t = 33.46 s / 21.46 tokens per second 5.54.830.840 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 699, progress = 0.58, t = 33.46 s / 20.89 tokens per second 5.54.839.873 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 714, progress = 0.58, t = 33.46 s / 21.34 tokens per second 6.13.786.222 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 52.74 s / 21.33 tokens per second 6.14.113.579 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1125, progress = 0.91, t = 52.74 s / 21.33 tokens per second 6.14.146.282 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1125, progress = 0.93, t = 52.74 s / 21.33 tokens per second 6.14.540.896 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 52.74 s / 21.33 tokens per second 6.20.389.369 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1239, progress = 1.00, t = 59.35 s / 20.88 tokens per second 6.20.719.170 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1230, progress = 1.00, t = 59.35 s / 20.73 tokens per second 6.20.752.037 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1211, progress = 1.00, t = 59.35 s / 20.41 tokens per second 6.20.792.625 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 1226, progress = 1.00, t = 59.35 s / 20.66 tokens per second 6.37.651.458 I slot print_timing: id 2 | task 265 | prompt eval time = 60190.39 ms / 1215 tokens ( 49.54 ms per token, 20.19 tokens per second) 6.37.651.461 I slot print_timing: id 2 | task 265 | eval time = 16418.45 ms / 79 tokens ( 210.49 ms per token, 4.75 tokens per second) 6.37.651.462 I slot print_timing: id 2 | task 265 | total time = 76608.84 ms / 1294 tokens 6.37.651.462 I slot print_timing: id 2 | task 265 | graphs reused = 79 6.37.651.463 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.651.642 I slot release: id 2 | task 265 | stop processing: n_tokens = 1293, truncated = 0 6.37.940.339 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.886 6.37.940.375 I slot launch_slot_: id 2 | task 354 | processing task, is_child = 0 6.41.340.351 I slot print_timing: id 3 | task 266 | prompt eval time = 60191.39 ms / 1230 tokens ( 48.94 ms per token, 20.43 tokens per second) 6.41.340.354 I slot print_timing: id 3 | task 266 | eval time = 20106.32 ms / 87 tokens ( 233.79 ms per token, 4.28 tokens per second) 6.41.340.354 I slot print_timing: id 3 | task 266 | total time = 80297.71 ms / 1317 tokens 6.41.340.355 I slot print_timing: id 3 | task 266 | graphs reused = 83 6.41.340.355 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.340.443 I slot release: id 3 | task 266 | stop processing: n_tokens = 1316, truncated = 0 6.41.538.417 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.871 6.41.538.454 I slot launch_slot_: id 3 | task 363 | processing task, is_child = 0 6.46.118.725 I slot print_timing: id 0 | task 267 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 6.46.118.872 I slot print_timing: id 1 | task 268 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 6.49.279.785 I slot print_timing: id 0 | task 267 | n_gen = 115, tg = 4.06 t/s, tg_3s = 4.75 t/s 6.49.279.927 I slot print_timing: id 1 | task 268 | n_gen = 115, tg = 4.06 t/s, tg_3s = 4.75 t/s 6.52.438.031 I slot print_timing: id 0 | task 267 | n_gen = 130, tg = 4.13 t/s, tg_3s = 4.75 t/s 6.52.438.168 I slot print_timing: id 1 | task 268 | n_gen = 130, tg = 4.13 t/s, tg_3s = 4.75 t/s 6.55.598.073 I slot print_timing: id 0 | task 267 | n_gen = 145, tg = 4.19 t/s, tg_3s = 4.75 t/s 6.55.598.218 I slot print_timing: id 1 | task 268 | n_gen = 145, tg = 4.19 t/s, tg_3s = 4.75 t/s 6.58.759.303 I slot print_timing: id 0 | task 267 | n_gen = 160, tg = 4.24 t/s, tg_3s = 4.74 t/s 6.58.759.444 I slot print_timing: id 1 | task 268 | n_gen = 160, tg = 4.24 t/s, tg_3s = 4.74 t/s 7.01.921.424 I slot print_timing: id 0 | task 267 | n_gen = 175, tg = 4.28 t/s, tg_3s = 4.74 t/s 7.01.921.574 I slot print_timing: id 1 | task 268 | n_gen = 175, tg = 4.28 t/s, tg_3s = 4.74 t/s 7.03.187.360 I slot print_timing: id 2 | task 354 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.37 t/s 7.04.875.590 I slot print_timing: id 3 | task 363 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 7.05.085.772 I slot print_timing: id 0 | task 267 | n_gen = 190, tg = 4.31 t/s, tg_3s = 4.74 t/s 7.05.085.916 I slot print_timing: id 1 | task 268 | n_gen = 190, tg = 4.31 t/s, tg_3s = 4.74 t/s 7.06.352.381 I slot print_timing: id 2 | task 354 | n_gen = 115, tg = 4.37 t/s, tg_3s = 4.74 t/s 7.08.039.151 I slot print_timing: id 3 | task 363 | n_gen = 115, tg = 4.74 t/s, tg_3s = 4.74 t/s 7.08.249.189 I slot print_timing: id 0 | task 267 | n_gen = 205, tg = 4.34 t/s, tg_3s = 4.74 t/s 7.08.249.335 I slot print_timing: id 1 | task 268 | n_gen = 205, tg = 4.34 t/s, tg_3s = 4.74 t/s 7.09.514.299 I slot print_timing: id 2 | task 354 | n_gen = 130, tg = 4.41 t/s, tg_3s = 4.74 t/s 7.10.778.290 I slot print_timing: id 3 | task 363 | prompt eval time = 2474.29 ms / 139 tokens ( 17.80 ms per token, 56.18 tokens per second) 7.10.778.296 I slot print_timing: id 3 | task 363 | eval time = 26765.54 ms / 128 tokens ( 210.75 ms per token, 4.74 tokens per second) 7.10.778.296 I slot print_timing: id 3 | task 363 | total time = 29239.83 ms / 267 tokens 7.10.778.297 I slot print_timing: id 3 | task 363 | graphs reused = 209 7.10.778.297 I slot print_timing: id 3 | task 363 | graph reallocs = 0 / 0 (same size) / (changed size) 7.10.778.366 I slot release: id 3 | task 363 | stop processing: n_tokens = 1391, truncated = 0 7.10.976.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.824 7.10.976.658 I slot launch_slot_: id 3 | task 494 | processing task, is_child = 0 7.13.054.167 I slot print_timing: id 0 | task 267 | n_gen = 219, tg = 4.21 t/s, tg_3s = 2.91 t/s 7.13.054.320 I slot print_timing: id 1 | task 268 | n_gen = 219, tg = 4.21 t/s, tg_3s = 2.91 t/s 7.13.054.519 I slot print_timing: id 2 | task 354 | n_gen = 138, tg = 4.18 t/s, tg_3s = 2.26 t/s 7.16.190.276 I slot print_timing: id 0 | task 267 | n_gen = 233, tg = 4.22 t/s, tg_3s = 4.46 t/s 7.16.190.432 I slot print_timing: id 1 | task 268 | n_gen = 233, tg = 4.22 t/s, tg_3s = 4.46 t/s 7.16.190.581 I slot print_timing: id 2 | task 354 | n_gen = 152, tg = 4.21 t/s, tg_3s = 4.46 t/s 7.19.354.697 I slot print_timing: id 0 | task 267 | n_gen = 248, tg = 4.25 t/s, tg_3s = 4.74 t/s 7.19.354.849 I slot print_timing: id 1 | task 268 | n_gen = 248, tg = 4.25 t/s, tg_3s = 4.74 t/s 7.19.355.011 I slot print_timing: id 2 | task 354 | n_gen = 167, tg = 4.25 t/s, tg_3s = 4.74 t/s 7.22.516.989 I slot print_timing: id 0 | task 267 | n_gen = 263, tg = 4.28 t/s, tg_3s = 4.74 t/s 7.22.517.136 I slot print_timing: id 1 | task 268 | n_gen = 263, tg = 4.28 t/s, tg_3s = 4.74 t/s 7.22.517.291 I slot print_timing: id 2 | task 354 | n_gen = 182, tg = 4.29 t/s, tg_3s = 4.74 t/s 7.25.678.705 I slot print_timing: id 0 | task 267 | n_gen = 278, tg = 4.30 t/s, tg_3s = 4.74 t/s 7.25.678.844 I slot print_timing: id 1 | task 268 | n_gen = 278, tg = 4.30 t/s, tg_3s = 4.74 t/s 7.25.678.981 I slot print_timing: id 2 | task 354 | n_gen = 197, tg = 4.32 t/s, tg_3s = 4.74 t/s 7.28.841.434 I slot print_timing: id 0 | task 267 | n_gen = 293, tg = 4.32 t/s, tg_3s = 4.74 t/s 7.28.841.587 I slot print_timing: id 1 | task 268 | n_gen = 293, tg = 4.32 t/s, tg_3s = 4.74 t/s 7.28.841.746 I slot print_timing: id 2 | task 354 | n_gen = 212, tg = 4.35 t/s, tg_3s = 4.74 t/s 7.30.529.509 I slot print_timing: id 2 | task 354 | prompt eval time = 2345.59 ms / 132 tokens ( 17.77 ms per token, 56.28 tokens per second) 7.30.529.514 I slot print_timing: id 2 | task 354 | eval time = 50243.53 ms / 220 tokens ( 229.42 ms per token, 4.36 tokens per second) 7.30.529.515 I slot print_timing: id 2 | task 354 | total time = 52589.12 ms / 352 tokens 7.30.529.515 I slot print_timing: id 2 | task 354 | graphs reused = 288 7.30.529.516 I slot print_timing: id 2 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.529.571 I slot release: id 2 | task 354 | stop processing: n_tokens = 1476, truncated = 0 7.30.818.969 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.776 7.30.819.003 I slot launch_slot_: id 2 | task 579 | processing task, is_child = 0 7.32.620.080 I slot print_timing: id 0 | task 267 | n_gen = 303, tg = 4.23 t/s, tg_3s = 2.65 t/s 7.32.620.284 I slot print_timing: id 1 | task 268 | n_gen = 303, tg = 4.23 t/s, tg_3s = 2.65 t/s 7.35.638.790 I slot print_timing: id 0 | task 267 | n_gen = 316, tg = 4.23 t/s, tg_3s = 4.31 t/s 7.35.638.938 I slot print_timing: id 1 | task 268 | n_gen = 316, tg = 4.23 t/s, tg_3s = 4.31 t/s 7.36.270.764 I slot print_timing: id 3 | task 494 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 7.38.798.995 I slot print_timing: id 0 | task 267 | n_gen = 331, tg = 4.25 t/s, tg_3s = 4.75 t/s 7.38.799.138 I slot print_timing: id 1 | task 268 | n_gen = 331, tg = 4.25 t/s, tg_3s = 4.75 t/s 7.39.431.570 I slot print_timing: id 3 | task 494 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.75 t/s 7.41.959.532 I slot print_timing: id 0 | task 267 | n_gen = 346, tg = 4.27 t/s, tg_3s = 4.75 t/s 7.41.959.681 I slot print_timing: id 1 | task 268 | prompt eval time = 60189.49 ms / 1234 tokens ( 48.78 ms per token, 20.50 tokens per second) 7.41.959.684 I slot print_timing: id 1 | task 268 | eval time = 80727.60 ms / 346 tokens ( 233.99 ms per token, 4.27 tokens per second) 7.41.959.684 I slot print_timing: id 1 | task 268 | total time = 140917.09 ms / 1580 tokens 7.41.959.685 I slot print_timing: id 1 | task 268 | graphs reused = 329 7.41.959.685 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 7.41.959.731 I slot release: id 1 | task 268 | stop processing: n_tokens = 1579, truncated = 0 7.42.249.641 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.726 7.42.249.679 I slot launch_slot_: id 1 | task 625 | processing task, is_child = 0 7.44.507.681 I slot print_timing: id 3 | task 494 | n_gen = 129, tg = 4.12 t/s, tg_3s = 2.76 t/s 7.45.054.397 I slot print_timing: id 0 | task 267 | n_gen = 349, tg = 4.15 t/s, tg_3s = 0.97 t/s 7.47.585.341 I slot print_timing: id 3 | task 494 | n_gen = 142, tg = 4.13 t/s, tg_3s = 4.22 t/s 7.48.217.690 I slot print_timing: id 0 | task 267 | n_gen = 364, tg = 4.17 t/s, tg_3s = 4.74 t/s 7.50.744.983 I slot print_timing: id 3 | task 494 | n_gen = 157, tg = 4.18 t/s, tg_3s = 4.75 t/s 7.51.375.662 I slot print_timing: id 0 | task 267 | n_gen = 379, tg = 4.19 t/s, tg_3s = 4.75 t/s 7.53.903.405 I slot print_timing: id 3 | task 494 | n_gen = 172, tg = 4.23 t/s, tg_3s = 4.75 t/s 7.54.534.925 I slot print_timing: id 0 | task 267 | n_gen = 394, tg = 4.21 t/s, tg_3s = 4.75 t/s 7.56.431.175 I slot print_timing: id 2 | task 579 | n_gen = 100, tg = 4.24 t/s, tg_3s = 4.29 t/s 7.57.065.160 I slot print_timing: id 3 | task 494 | n_gen = 187, tg = 4.26 t/s, tg_3s = 4.74 t/s 7.57.696.920 I slot print_timing: id 0 | task 267 | n_gen = 409, tg = 4.23 t/s, tg_3s = 4.74 t/s 7.59.593.202 I slot print_timing: id 2 | task 579 | n_gen = 115, tg = 4.30 t/s, tg_3s = 4.74 t/s 8.00.225.104 I slot print_timing: id 3 | task 494 | n_gen = 202, tg = 4.30 t/s, tg_3s = 4.75 t/s 8.00.856.692 I slot print_timing: id 0 | task 267 | n_gen = 424, tg = 4.25 t/s, tg_3s = 4.75 t/s 8.01.700.714 I slot print_timing: id 0 | task 267 | prompt eval time = 60188.80 ms / 1243 tokens ( 48.42 ms per token, 20.65 tokens per second) 8.01.700.720 I slot print_timing: id 0 | task 267 | eval time = 100469.34 ms / 428 tokens ( 235.29 ms per token, 4.25 tokens per second) 8.01.700.720 I slot print_timing: id 0 | task 267 | total time = 160658.14 ms / 1671 tokens 8.01.700.721 I slot print_timing: id 0 | task 267 | graphs reused = 407 8.01.700.721 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.700.770 I slot release: id 0 | task 267 | stop processing: n_tokens = 1670, truncated = 0 8.01.899.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.686 8.01.899.854 I slot launch_slot_: id 0 | task 708 | processing task, is_child = 0 8.04.356.616 I slot print_timing: id 2 | task 579 | n_gen = 127, tg = 4.03 t/s, tg_3s = 2.52 t/s 8.04.356.827 I slot print_timing: id 3 | task 494 | n_gen = 211, tg = 4.13 t/s, tg_3s = 2.18 t/s 8.05.794.868 I slot print_timing: id 2 | task 579 | prompt eval time = 2287.38 ms / 114 tokens ( 20.06 ms per token, 49.84 tokens per second) 8.05.794.871 I slot print_timing: id 2 | task 579 | eval time = 32688.48 ms / 133 tokens ( 247.64 ms per token, 4.04 tokens per second) 8.05.794.871 I slot print_timing: id 2 | task 579 | total time = 34975.86 ms / 247 tokens 8.05.794.872 I slot print_timing: id 2 | task 579 | graphs reused = 412 8.05.794.872 I slot print_timing: id 2 | task 579 | graph reallocs = 0 / 0 (same size) / (changed size) 8.05.795.040 I slot release: id 2 | task 579 | stop processing: n_tokens = 1371, truncated = 0 8.06.085.594 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.836 8.06.085.642 I slot launch_slot_: id 2 | task 717 | processing task, is_child = 0 8.07.906.937 I slot print_timing: id 3 | task 494 | n_gen = 219, tg = 4.00 t/s, tg_3s = 2.25 t/s 8.10.289.573 I slot print_timing: id 1 | task 625 | n_gen = 100, tg = 3.92 t/s, tg_3s = 3.96 t/s 8.10.922.232 I slot print_timing: id 3 | task 494 | n_gen = 232, tg = 4.02 t/s, tg_3s = 4.31 t/s 8.13.447.647 I slot print_timing: id 1 | task 625 | n_gen = 115, tg = 4.02 t/s, tg_3s = 4.75 t/s 8.14.080.552 I slot print_timing: id 3 | task 494 | n_gen = 247, tg = 4.06 t/s, tg_3s = 4.75 t/s 8.16.608.978 I slot print_timing: id 1 | task 625 | n_gen = 130, tg = 4.09 t/s, tg_3s = 4.74 t/s 8.17.240.691 I slot print_timing: id 3 | task 494 | n_gen = 262, tg = 4.09 t/s, tg_3s = 4.75 t/s 8.19.772.452 I slot print_timing: id 1 | task 625 | n_gen = 145, tg = 4.15 t/s, tg_3s = 4.74 t/s 8.20.404.687 I slot print_timing: id 3 | task 494 | n_gen = 277, tg = 4.12 t/s, tg_3s = 4.74 t/s 8.22.932.777 I slot print_timing: id 1 | task 625 | n_gen = 160, tg = 4.20 t/s, tg_3s = 4.75 t/s 8.23.566.028 I slot print_timing: id 3 | task 494 | n_gen = 292, tg = 4.15 t/s, tg_3s = 4.74 t/s 8.26.095.113 I slot print_timing: id 1 | task 625 | n_gen = 175, tg = 4.24 t/s, tg_3s = 4.74 t/s 8.26.727.617 I slot print_timing: id 3 | task 494 | n_gen = 307, tg = 4.18 t/s, tg_3s = 4.74 t/s 8.27.571.083 I slot print_timing: id 0 | task 708 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 8.29.257.093 I slot print_timing: id 1 | task 625 | n_gen = 190, tg = 4.28 t/s, tg_3s = 4.74 t/s 8.29.257.240 I slot print_timing: id 2 | task 717 | n_gen = 100, tg = 4.74 t/s, tg_3s = 4.79 t/s 8.29.890.268 I slot print_timing: id 3 | task 494 | n_gen = 322, tg = 4.20 t/s, tg_3s = 4.74 t/s 8.30.733.476 I slot print_timing: id 0 | task 708 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.74 t/s 8.32.421.533 I slot print_timing: id 1 | task 625 | n_gen = 205, tg = 4.31 t/s, tg_3s = 4.74 t/s 8.32.421.695 I slot print_timing: id 2 | task 717 | n_gen = 115, tg = 4.74 t/s, tg_3s = 4.74 t/s 8.33.053.686 I slot print_timing: id 3 | task 494 | n_gen = 337, tg = 4.22 t/s, tg_3s = 4.74 t/s 8.33.896.047 I slot print_timing: id 0 | task 708 | n_gen = 130, tg = 4.42 t/s, tg_3s = 4.74 t/s 8.35.581.798 I slot print_timing: id 1 | task 625 | n_gen = 220, tg = 4.33 t/s, tg_3s = 4.75 t/s 8.35.581.948 I slot print_timing: id 2 | task 717 | n_gen = 130, tg = 4.74 t/s, tg_3s = 4.75 t/s 8.36.213.875 I slot print_timing: id 3 | task 494 | n_gen = 352, tg = 4.24 t/s, tg_3s = 4.75 t/s 8.37.056.271 I slot print_timing: id 0 | task 708 | n_gen = 145, tg = 4.46 t/s, tg_3s = 4.75 t/s 8.38.742.941 I slot print_timing: id 1 | task 625 | n_gen = 235, tg = 4.36 t/s, tg_3s = 4.75 t/s 8.38.743.086 I slot print_timing: id 2 | task 717 | n_gen = 145, tg = 4.74 t/s, tg_3s = 4.75 t/s 8.39.164.460 I slot print_timing: id 1 | task 625 | prompt eval time = 2804.90 ms / 141 tokens ( 19.89 ms per token, 50.27 tokens per second) 8.39.164.466 I slot print_timing: id 1 | task 625 | eval time = 54109.88 ms / 237 tokens ( 229.28 ms per token, 4.36 tokens per second) 8.39.164.467 I slot print_timing: id 1 | task 625 | total time = 56914.78 ms / 378 tokens 8.39.164.467 I slot print_timing: id 1 | task 625 | graphs reused = 556 8.39.164.468 I slot print_timing: id 1 | task 625 | graph reallocs = 0 / 0 (same size) / (changed size) 8.39.164.542 I slot release: id 1 | task 625 | stop processing: n_tokens = 1502, truncated = 0 8.39.454.245 I slot print_timing: id 3 | task 494 | n_gen = 367, tg = 4.26 t/s, tg_3s = 4.63 t/s 8.39.454.253 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.763 8.39.454.280 I slot launch_slot_: id 1 | task 867 | processing task, is_child = 0 8.40.992.261 I slot print_timing: id 0 | task 708 | n_gen = 157, tg = 4.30 t/s, tg_3s = 3.05 t/s 8.41.750.014 I slot print_timing: id 2 | task 717 | n_gen = 151, tg = 4.50 t/s, tg_3s = 2.00 t/s 8.42.592.703 I slot print_timing: id 3 | task 494 | n_gen = 374, tg = 4.18 t/s, tg_3s = 2.23 t/s 8.44.066.546 I slot print_timing: id 0 | task 708 | n_gen = 170, tg = 4.30 t/s, tg_3s = 4.23 t/s 8.44.910.269 I slot print_timing: id 2 | task 717 | n_gen = 166, tg = 4.52 t/s, tg_3s = 4.75 t/s 8.45.752.906 I slot print_timing: id 2 | task 717 | prompt eval time = 2306.91 ms / 125 tokens ( 18.46 ms per token, 54.18 tokens per second) 8.45.752.911 I slot print_timing: id 2 | task 717 | eval time = 37360.34 ms / 170 tokens ( 221.07 ms per token, 4.52 tokens per second) 8.45.752.912 I slot print_timing: id 2 | task 717 | total time = 39667.26 ms / 295 tokens 8.45.752.913 I slot print_timing: id 2 | task 717 | graphs reused = 575 8.45.752.913 I slot print_timing: id 2 | task 717 | graph reallocs = 0 / 0 (same size) / (changed size) 8.45.752.957 I slot release: id 2 | task 717 | stop processing: n_tokens = 1419, truncated = 0 8.45.753.105 I slot print_timing: id 3 | task 494 | n_gen = 389, tg = 4.20 t/s, tg_3s = 4.75 t/s 8.46.043.031 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.808 8.46.043.083 I slot launch_slot_: id 2 | task 891 | processing task, is_child = 0 8.47.512.379 I slot print_timing: id 0 | task 708 | n_gen = 180, tg = 4.18 t/s, tg_3s = 2.90 t/s 8.48.842.228 I slot print_timing: id 3 | task 494 | n_gen = 396, tg = 4.14 t/s, tg_3s = 2.27 t/s 8.49.895.290 I slot print_timing: id 3 | task 494 | prompt eval time = 2472.55 ms / 139 tokens ( 17.79 ms per token, 56.22 tokens per second) 8.49.895.293 I slot print_timing: id 3 | task 494 | eval time = 96446.07 ms / 401 tokens ( 241.12 ms per token, 4.15 tokens per second) 8.49.895.293 I slot print_timing: id 3 | task 494 | total time = 98918.62 ms / 540 tokens 8.49.895.294 I slot print_timing: id 3 | task 494 | graphs reused = 583 8.49.895.294 I slot print_timing: id 3 | task 494 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.895.375 I slot release: id 3 | task 494 | stop processing: n_tokens = 1664, truncated = 0 8.50.093.395 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.689 8.50.093.429 I slot launch_slot_: id 3 | task 904 | processing task, is_child = 0 8.51.484.087 I slot print_timing: id 0 | task 708 | n_gen = 192, tg = 4.09 t/s, tg_3s = 3.02 t/s 8.54.617.430 I slot print_timing: id 0 | task 708 | n_gen = 206, tg = 4.11 t/s, tg_3s = 4.47 t/s 8.57.772.645 I slot print_timing: id 0 | task 708 | n_gen = 221, tg = 4.15 t/s, tg_3s = 4.75 t/s 9.00.928.490 I slot print_timing: id 0 | task 708 | n_gen = 236, tg = 4.18 t/s, tg_3s = 4.75 t/s 9.04.085.511 I slot print_timing: id 0 | task 708 | n_gen = 251, tg = 4.21 t/s, tg_3s = 4.75 t/s 9.05.349.886 I slot print_timing: id 1 | task 867 | n_gen = 100, tg = 4.16 t/s, tg_3s = 4.20 t/s 9.06.613.510 I slot print_timing: id 0 | task 708 | prompt eval time = 2840.60 ms / 169 tokens ( 16.81 ms per token, 59.49 tokens per second) 9.06.613.515 I slot print_timing: id 0 | task 708 | eval time = 61873.05 ms / 263 tokens ( 236.16 ms per token, 4.23 tokens per second) 9.06.613.516 I slot print_timing: id 0 | task 708 | total time = 64713.65 ms / 432 tokens 9.06.613.516 I slot print_timing: id 0 | task 708 | graphs reused = 651 9.06.613.516 I slot print_timing: id 0 | task 708 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.613.571 I slot release: id 0 | task 708 | stop processing: n_tokens = 1556, truncated = 0 9.06.812.377 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.737 9.06.812.414 I slot launch_slot_: id 0 | task 978 | processing task, is_child = 0 9.08.537.117 I slot print_timing: id 1 | task 867 | n_gen = 108, tg = 3.96 t/s, tg_3s = 2.51 t/s 9.11.026.559 I slot print_timing: id 1 | task 867 | prompt eval time = 2081.90 ms / 101 tokens ( 20.61 ms per token, 48.51 tokens per second) 9.11.026.564 I slot print_timing: id 1 | task 867 | eval time = 29490.38 ms / 119 tokens ( 249.92 ms per token, 4.00 tokens per second) 9.11.026.565 I slot print_timing: id 1 | task 867 | total time = 31572.27 ms / 220 tokens 9.11.026.565 I slot print_timing: id 1 | task 867 | graphs reused = 661 9.11.026.566 I slot print_timing: id 1 | task 867 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.026.612 I slot release: id 1 | task 867 | stop processing: n_tokens = 1344, truncated = 0 9.11.316.640 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.853 9.11.316.675 I slot launch_slot_: id 1 | task 992 | processing task, is_child = 0 9.14.305.856 I slot print_timing: id 2 | task 891 | n_gen = 100, tg = 3.76 t/s, tg_3s = 3.80 t/s 9.16.831.323 I slot print_timing: id 3 | task 904 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 9.17.462.844 I slot print_timing: id 2 | task 891 | n_gen = 115, tg = 3.87 t/s, tg_3s = 4.75 t/s 9.19.989.448 I slot print_timing: id 3 | task 904 | n_gen = 115, tg = 4.06 t/s, tg_3s = 4.75 t/s 9.20.620.433 I slot print_timing: id 2 | task 891 | n_gen = 130, tg = 3.95 t/s, tg_3s = 4.75 t/s 9.23.155.013 I slot print_timing: id 3 | task 904 | n_gen = 130, tg = 4.12 t/s, tg_3s = 4.74 t/s 9.23.786.818 I slot print_timing: id 2 | task 891 | n_gen = 145, tg = 4.02 t/s, tg_3s = 4.74 t/s 9.26.314.705 I slot print_timing: id 3 | task 904 | n_gen = 145, tg = 4.18 t/s, tg_3s = 4.75 t/s 9.26.946.091 I slot print_timing: id 2 | task 891 | n_gen = 160, tg = 4.08 t/s, tg_3s = 4.75 t/s 9.29.471.831 I slot print_timing: id 3 | task 904 | n_gen = 160, tg = 4.23 t/s, tg_3s = 4.75 t/s 9.30.103.469 I slot print_timing: id 2 | task 891 | n_gen = 175, tg = 4.13 t/s, tg_3s = 4.75 t/s 9.31.365.926 I slot print_timing: id 0 | task 978 | prompt eval time = 2107.11 ms / 120 tokens ( 17.56 ms per token, 56.95 tokens per second) 9.31.365.931 I slot print_timing: id 0 | task 978 | eval time = 22446.39 ms / 96 tokens ( 236.28 ms per token, 4.23 tokens per second) 9.31.365.932 I slot print_timing: id 0 | task 978 | total time = 24553.50 ms / 216 tokens 9.31.365.932 I slot print_timing: id 0 | task 978 | graphs reused = 742 9.31.365.933 I slot print_timing: id 0 | task 978 | graph reallocs = 0 / 0 (same size) / (changed size) 9.31.366.011 I slot release: id 0 | task 978 | stop processing: n_tokens = 1340, truncated = 0 9.31.564.788 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.855 9.31.564.827 I slot launch_slot_: id 0 | task 1078 | processing task, is_child = 0 9.32.936.695 I slot print_timing: id 3 | task 904 | n_gen = 171, tg = 4.14 t/s, tg_3s = 3.17 t/s 9.33.318.506 I slot print_timing: id 2 | task 891 | n_gen = 184, tg = 4.04 t/s, tg_3s = 2.80 t/s 9.34.585.015 I slot print_timing: id 2 | task 891 | prompt eval time = 1954.28 ms / 101 tokens ( 19.35 ms per token, 51.68 tokens per second) 9.34.585.019 I slot print_timing: id 2 | task 891 | eval time = 46587.64 ms / 190 tokens ( 246.50 ms per token, 4.06 tokens per second) 9.34.585.020 I slot print_timing: id 2 | task 891 | total time = 48541.92 ms / 291 tokens 9.34.585.020 I slot print_timing: id 2 | task 891 | graphs reused = 748 9.34.585.021 I slot print_timing: id 2 | task 891 | graph reallocs = 0 / 0 (same size) / (changed size) 9.34.585.071 I slot release: id 2 | task 891 | stop processing: n_tokens = 1415, truncated = 0 9.34.874.593 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.810 9.34.874.631 I slot launch_slot_: id 2 | task 1088 | processing task, is_child = 0 9.36.686.287 I slot print_timing: id 3 | task 904 | n_gen = 180, tg = 3.99 t/s, tg_3s = 2.40 t/s 9.38.227.708 I slot print_timing: id 1 | task 992 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 9.39.703.456 I slot print_timing: id 3 | task 904 | n_gen = 193, tg = 4.01 t/s, tg_3s = 4.31 t/s 9.41.389.067 I slot print_timing: id 1 | task 992 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.74 t/s 9.42.862.568 I slot print_timing: id 3 | task 904 | n_gen = 208, tg = 4.06 t/s, tg_3s = 4.75 t/s 9.43.284.603 I slot print_timing: id 3 | task 904 | prompt eval time = 1785.76 ms / 95 tokens ( 18.80 ms per token, 53.20 tokens per second) 9.43.284.606 I slot print_timing: id 3 | task 904 | eval time = 51405.40 ms / 210 tokens ( 245.96 ms per token, 4.07 tokens per second) 9.43.284.606 I slot print_timing: id 3 | task 904 | total time = 53191.16 ms / 305 tokens 9.43.284.607 I slot print_timing: id 3 | task 904 | graphs reused = 776 9.43.284.607 I slot print_timing: id 3 | task 904 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.284.667 I slot release: id 3 | task 904 | stop processing: n_tokens = 1429, truncated = 0 9.43.482.611 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.802 9.43.482.651 I slot launch_slot_: id 3 | task 1121 | processing task, is_child = 0 9.44.874.635 I slot print_timing: id 1 | task 992 | n_gen = 126, tg = 4.06 t/s, tg_3s = 3.16 t/s 9.48.006.836 I slot print_timing: id 1 | task 992 | n_gen = 140, tg = 4.10 t/s, tg_3s = 4.47 t/s 9.51.166.316 I slot print_timing: id 1 | task 992 | n_gen = 155, tg = 4.15 t/s, tg_3s = 4.75 t/s 9.54.324.035 I slot print_timing: id 1 | task 992 | n_gen = 170, tg = 4.20 t/s, tg_3s = 4.75 t/s 9.57.481.103 I slot print_timing: id 0 | task 1078 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 9.57.481.249 I slot print_timing: id 1 | task 992 | n_gen = 185, tg = 4.24 t/s, tg_3s = 4.75 t/s 9.59.376.708 I slot print_timing: id 2 | task 1088 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 10.00.640.150 I slot print_timing: id 0 | task 1078 | n_gen = 115, tg = 4.17 t/s, tg_3s = 4.75 t/s 10.00.640.298 I slot print_timing: id 1 | task 992 | n_gen = 200, tg = 4.28 t/s, tg_3s = 4.75 t/s 10.02.535.159 I slot print_timing: id 2 | task 1088 | n_gen = 115, tg = 4.49 t/s, tg_3s = 4.75 t/s 10.03.798.236 I slot print_timing: id 0 | task 1078 | n_gen = 130, tg = 4.23 t/s, tg_3s = 4.75 t/s 10.03.798.382 I slot print_timing: id 1 | task 992 | n_gen = 215, tg = 4.31 t/s, tg_3s = 4.75 t/s 10.03.798.645 I slot print_timing: id 3 | task 1121 | prompt eval time = 1785.81 ms / 97 tokens ( 18.41 ms per token, 54.32 tokens per second) 10.03.798.646 I slot print_timing: id 3 | task 1121 | eval time = 18530.18 ms / 89 tokens ( 210.57 ms per token, 4.75 tokens per second) 10.03.798.647 I slot print_timing: id 3 | task 1121 | total time = 20315.99 ms / 186 tokens 10.03.798.647 I slot print_timing: id 3 | task 1121 | graphs reused = 863 10.03.798.648 I slot print_timing: id 3 | task 1121 | graph reallocs = 0 / 0 (same size) / (changed size) 10.03.798.706 I slot release: id 3 | task 1121 | stop processing: n_tokens = 1310, truncated = 0 10.03.997.275 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.875 10.03.997.308 I slot launch_slot_: id 3 | task 1213 | processing task, is_child = 0 10.05.768.959 I slot print_timing: id 2 | task 1088 | n_gen = 124, tg = 4.30 t/s, tg_3s = 2.78 t/s 10.06.612.953 I slot print_timing: id 0 | task 1078 | prompt eval time = 1753.39 ms / 86 tokens ( 20.39 ms per token, 49.05 tokens per second) 10.06.612.956 I slot print_timing: id 0 | task 1078 | eval time = 33294.73 ms / 137 tokens ( 244.81 ms per token, 4.08 tokens per second) 10.06.612.956 I slot print_timing: id 0 | task 1078 | total time = 35048.12 ms / 223 tokens 10.06.612.957 I slot print_timing: id 0 | task 1078 | graphs reused = 866 10.06.612.957 I slot print_timing: id 0 | task 1078 | graph reallocs = 0 / 0 (same size) / (changed size) 10.06.612.999 I slot release: id 0 | task 1078 | stop processing: n_tokens = 1347, truncated = 0 10.06.811.965 I slot print_timing: id 1 | task 992 | n_gen = 223, tg = 4.21 t/s, tg_3s = 2.65 t/s 10.06.812.248 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.851 10.06.812.277 I slot launch_slot_: id 0 | task 1221 | processing task, is_child = 0 10.08.881.291 I slot print_timing: id 2 | task 1088 | n_gen = 131, tg = 4.10 t/s, tg_3s = 2.25 t/s 10.09.935.669 I slot print_timing: id 1 | task 992 | n_gen = 230, tg = 4.10 t/s, tg_3s = 2.24 t/s 10.12.041.070 I slot print_timing: id 2 | task 1088 | n_gen = 146, tg = 4.16 t/s, tg_3s = 4.75 t/s 10.13.093.185 I slot print_timing: id 1 | task 992 | n_gen = 245, tg = 4.14 t/s, tg_3s = 4.75 t/s 10.15.198.400 I slot print_timing: id 2 | task 1088 | n_gen = 161, tg = 4.21 t/s, tg_3s = 4.75 t/s 10.16.252.055 I slot print_timing: id 1 | task 992 | n_gen = 260, tg = 4.17 t/s, tg_3s = 4.75 t/s 10.18.363.301 I slot print_timing: id 2 | task 1088 | n_gen = 176, tg = 4.25 t/s, tg_3s = 4.74 t/s 10.19.416.890 I slot print_timing: id 1 | task 992 | n_gen = 275, tg = 4.19 t/s, tg_3s = 4.74 t/s 10.21.522.609 I slot print_timing: id 2 | task 1088 | n_gen = 191, tg = 4.28 t/s, tg_3s = 4.75 t/s 10.22.577.076 I slot print_timing: id 1 | task 992 | n_gen = 290, tg = 4.22 t/s, tg_3s = 4.75 t/s 10.23.630.887 I slot print_timing: id 3 | task 1213 | prompt eval time = 1771.87 ms / 84 tokens ( 21.09 ms per token, 47.41 tokens per second) 10.23.630.891 I slot print_timing: id 3 | task 1213 | eval time = 17861.70 ms / 78 tokens ( 231.97 ms per token, 4.31 tokens per second) 10.23.630.900 I slot print_timing: id 3 | task 1213 | total time = 19633.57 ms / 162 tokens 10.23.630.903 I slot print_timing: id 3 | task 1213 | graphs reused = 935 10.23.630.903 I slot print_timing: id 3 | task 1213 | graph reallocs = 0 / 0 (same size) / (changed size) 10.23.630.945 I slot release: id 3 | task 1213 | stop processing: n_tokens = 1286, truncated = 0 10.23.829.557 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.891 10.23.829.597 I slot launch_slot_: id 3 | task 1295 | processing task, is_child = 0 10.25.219.850 I slot print_timing: id 2 | task 1088 | n_gen = 203, tg = 4.20 t/s, tg_3s = 3.25 t/s 10.25.614.365 I slot print_timing: id 1 | task 992 | n_gen = 298, tg = 4.15 t/s, tg_3s = 2.63 t/s 10.28.355.885 I slot print_timing: id 2 | task 1088 | n_gen = 217, tg = 4.22 t/s, tg_3s = 4.46 t/s 10.28.776.840 I slot print_timing: id 1 | task 992 | n_gen = 313, tg = 4.18 t/s, tg_3s = 4.74 t/s 10.31.093.116 I slot print_timing: id 0 | task 1221 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 10.31.514.845 I slot print_timing: id 2 | task 1088 | n_gen = 232, tg = 4.25 t/s, tg_3s = 4.75 t/s 10.31.935.838 I slot print_timing: id 1 | task 992 | n_gen = 328, tg = 4.20 t/s, tg_3s = 4.75 t/s 10.34.253.331 I slot print_timing: id 0 | task 1221 | n_gen = 115, tg = 4.49 t/s, tg_3s = 4.75 t/s 10.34.675.029 I slot print_timing: id 2 | task 1088 | n_gen = 247, tg = 4.28 t/s, tg_3s = 4.75 t/s 10.35.097.112 I slot print_timing: id 1 | task 992 | n_gen = 343, tg = 4.22 t/s, tg_3s = 4.74 t/s 10.36.360.775 I slot print_timing: id 1 | task 992 | prompt eval time = 2776.19 ms / 148 tokens ( 18.76 ms per token, 53.31 tokens per second) 10.36.360.781 I slot print_timing: id 1 | task 992 | eval time = 82267.90 ms / 349 tokens ( 236.40 ms per token, 4.23 tokens per second) 10.36.360.782 I slot print_timing: id 1 | task 992 | total time = 85044.09 ms / 497 tokens 10.36.360.782 I slot print_timing: id 1 | task 992 | graphs reused = 985 10.36.360.783 I slot print_timing: id 1 | task 992 | graph reallocs = 0 / 0 (same size) / (changed size) 10.36.360.839 I slot release: id 1 | task 992 | stop processing: n_tokens = 1621, truncated = 0 10.36.650.738 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.707 10.36.650.774 I slot launch_slot_: id 1 | task 1350 | processing task, is_child = 0 10.38.530.018 I slot print_timing: id 0 | task 1221 | n_gen = 127, tg = 4.25 t/s, tg_3s = 2.81 t/s 10.38.530.251 I slot print_timing: id 2 | task 1088 | n_gen = 257, tg = 4.17 t/s, tg_3s = 2.59 t/s 10.41.601.670 I slot print_timing: id 0 | task 1221 | n_gen = 140, tg = 4.25 t/s, tg_3s = 4.23 t/s 10.41.601.974 I slot print_timing: id 2 | task 1088 | n_gen = 270, tg = 4.18 t/s, tg_3s = 4.23 t/s 10.41.602.121 I slot print_timing: id 3 | task 1295 | prompt eval time = 1785.17 ms / 95 tokens ( 18.79 ms per token, 53.22 tokens per second) 10.41.602.122 I slot print_timing: id 3 | task 1295 | eval time = 15987.35 ms / 67 tokens ( 242.23 ms per token, 4.13 tokens per second) 10.41.602.123 I slot print_timing: id 3 | task 1295 | total time = 17772.52 ms / 162 tokens 10.41.602.123 I slot print_timing: id 3 | task 1295 | graphs reused = 996 10.41.602.124 I slot print_timing: id 3 | task 1295 | graph reallocs = 0 / 0 (same size) / (changed size) 10.41.602.169 I slot release: id 3 | task 1295 | stop processing: n_tokens = 1286, truncated = 0 10.41.800.894 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.891 10.41.800.924 I slot launch_slot_: id 3 | task 1366 | processing task, is_child = 0 10.44.635.679 I slot print_timing: id 0 | task 1221 | n_gen = 148, tg = 4.11 t/s, tg_3s = 2.64 t/s 10.44.635.967 I slot print_timing: id 2 | task 1088 | n_gen = 278, tg = 4.11 t/s, tg_3s = 2.64 t/s 10.47.796.657 I slot print_timing: id 0 | task 1221 | n_gen = 163, tg = 4.16 t/s, tg_3s = 4.75 t/s 10.47.796.955 I slot print_timing: id 2 | task 1088 | n_gen = 293, tg = 4.13 t/s, tg_3s = 4.75 t/s 10.50.956.703 I slot print_timing: id 0 | task 1221 | n_gen = 178, tg = 4.21 t/s, tg_3s = 4.75 t/s 10.50.956.969 I slot print_timing: id 2 | task 1088 | n_gen = 308, tg = 4.16 t/s, tg_3s = 4.75 t/s 10.53.062.599 I slot print_timing: id 0 | task 1221 | prompt eval time = 2068.73 ms / 101 tokens ( 20.48 ms per token, 48.82 tokens per second) 10.53.062.604 I slot print_timing: id 0 | task 1221 | eval time = 44181.59 ms / 188 tokens ( 236.27 ms per token, 4.23 tokens per second) 10.53.062.605 I slot print_timing: id 0 | task 1221 | total time = 46250.32 ms / 289 tokens 10.53.062.605 I slot print_timing: id 0 | task 1221 | graphs reused = 1039 10.53.062.605 I slot print_timing: id 0 | task 1221 | graph reallocs = 0 / 0 (same size) / (changed size) 10.53.062.649 I slot release: id 0 | task 1221 | stop processing: n_tokens = 1413, truncated = 0 10.53.260.940 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.811 10.53.260.974 I slot launch_slot_: id 0 | task 1415 | processing task, is_child = 0 10.54.635.586 I slot print_timing: id 2 | task 1088 | n_gen = 320, tg = 4.12 t/s, tg_3s = 3.26 t/s 10.55.230.429 I slot print_timing: id 2 | task 1088 | prompt eval time = 2296.67 ms / 133 tokens ( 17.27 ms per token, 57.91 tokens per second) 10.55.230.434 I slot print_timing: id 2 | task 1088 | eval time = 78059.12 ms / 322 tokens ( 243.17 ms per token, 4.11 tokens per second) 10.55.230.435 I slot print_timing: id 2 | task 1088 | total time = 80355.79 ms / 455 tokens 10.55.230.435 I slot print_timing: id 2 | task 1088 | graphs reused = 1040 10.55.230.436 I slot print_timing: id 2 | task 1088 | graph reallocs = 0 / 0 (same size) / (changed size) 10.55.230.496 I slot release: id 2 | task 1088 | stop processing: n_tokens = 1579, truncated = 0 10.55.519.646 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.726 10.55.519.681 I slot launch_slot_: id 2 | task 1420 | processing task, is_child = 0 11.04.211.827 I slot print_timing: id 1 | task 1350 | n_gen = 100, tg = 3.94 t/s, tg_3s = 3.98 t/s 11.07.368.944 I slot print_timing: id 1 | task 1350 | n_gen = 115, tg = 4.03 t/s, tg_3s = 4.75 t/s 11.07.369.234 I slot print_timing: id 3 | task 1366 | n_gen = 100, tg = 4.16 t/s, tg_3s = 4.20 t/s 11.10.525.990 I slot print_timing: id 1 | task 1350 | n_gen = 130, tg = 4.10 t/s, tg_3s = 4.75 t/s 11.10.526.277 I slot print_timing: id 3 | task 1366 | n_gen = 115, tg = 4.23 t/s, tg_3s = 4.75 t/s 11.12.209.512 I slot print_timing: id 3 | task 1366 | prompt eval time = 1778.70 ms / 90 tokens ( 19.76 ms per token, 50.60 tokens per second) 11.12.209.515 I slot print_timing: id 3 | task 1366 | eval time = 28629.87 ms / 123 tokens ( 234.67 ms per token, 4.26 tokens per second) 11.12.209.515 I slot print_timing: id 3 | task 1366 | total time = 30408.57 ms / 213 tokens 11.12.209.516 I slot print_timing: id 3 | task 1366 | graphs reused = 1109 11.12.209.516 I slot print_timing: id 3 | task 1366 | graph reallocs = 0 / 0 (same size) / (changed size) 11.12.209.561 I slot release: id 3 | task 1366 | stop processing: n_tokens = 1337, truncated = 0 11.12.407.708 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.858 11.12.407.743 I slot launch_slot_: id 3 | task 1494 | processing task, is_child = 0 11.14.141.258 I slot print_timing: id 1 | task 1350 | n_gen = 140, tg = 3.96 t/s, tg_3s = 2.77 t/s 11.17.273.966 I slot print_timing: id 1 | task 1350 | n_gen = 154, tg = 4.01 t/s, tg_3s = 4.47 t/s 11.19.170.573 I slot print_timing: id 0 | task 1415 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 11.20.013.250 I slot print_timing: id 2 | task 1420 | n_gen = 100, tg = 4.39 t/s, tg_3s = 4.44 t/s 11.20.434.078 I slot print_timing: id 1 | task 1350 | n_gen = 169, tg = 4.06 t/s, tg_3s = 4.75 t/s 11.22.329.264 I slot print_timing: id 0 | task 1415 | n_gen = 115, tg = 4.17 t/s, tg_3s = 4.75 t/s 11.23.171.777 I slot print_timing: id 2 | task 1420 | n_gen = 115, tg = 4.44 t/s, tg_3s = 4.75 t/s 11.23.592.687 I slot print_timing: id 1 | task 1350 | n_gen = 184, tg = 4.11 t/s, tg_3s = 4.75 t/s 11.24.645.060 I slot print_timing: id 0 | task 1415 | prompt eval time = 1756.11 ms / 96 tokens ( 18.29 ms per token, 54.67 tokens per second) 11.24.645.066 I slot print_timing: id 0 | task 1415 | eval time = 29627.97 ms / 126 tokens ( 237.02 ms per token, 4.22 tokens per second) 11.24.645.066 I slot print_timing: id 0 | task 1415 | total time = 31384.08 ms / 222 tokens 11.24.645.067 I slot print_timing: id 0 | task 1415 | graphs reused = 1156 11.24.645.067 I slot print_timing: id 0 | task 1415 | graph reallocs = 0 / 0 (same size) / (changed size) 11.24.645.116 I slot release: id 0 | task 1415 | stop processing: n_tokens = 1346, truncated = 0 11.24.843.772 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.851 11.24.843.804 I slot launch_slot_: id 0 | task 1546 | processing task, is_child = 0 11.26.903.067 I slot print_timing: id 1 | task 1350 | n_gen = 191, tg = 3.97 t/s, tg_3s = 2.11 t/s 11.26.903.263 I slot print_timing: id 2 | task 1420 | n_gen = 124, tg = 4.18 t/s, tg_3s = 2.41 t/s 11.28.760.464 I slot print_timing: id 2 | task 1420 | prompt eval time = 1957.46 ms / 87 tokens ( 22.50 ms per token, 44.45 tokens per second) 11.28.760.467 I slot print_timing: id 2 | task 1420 | eval time = 31283.31 ms / 132 tokens ( 238.80 ms per token, 4.19 tokens per second) 11.28.760.468 I slot print_timing: id 2 | task 1420 | total time = 33240.77 ms / 219 tokens 11.28.760.468 I slot print_timing: id 2 | task 1420 | graphs reused = 1163 11.28.760.469 I slot print_timing: id 2 | task 1420 | graph reallocs = 0 / 0 (same size) / (changed size) 11.28.760.510 I slot release: id 2 | task 1420 | stop processing: n_tokens = 1343, truncated = 0 11.29.049.936 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.853 11.29.049.970 I slot launch_slot_: id 2 | task 1557 | processing task, is_child = 0 11.31.231.278 I slot print_timing: id 1 | task 1350 | n_gen = 201, tg = 3.83 t/s, tg_3s = 2.31 t/s 11.34.243.195 I slot print_timing: id 1 | task 1350 | n_gen = 214, tg = 3.86 t/s, tg_3s = 4.32 t/s 11.37.401.477 I slot print_timing: id 1 | task 1350 | n_gen = 229, tg = 3.91 t/s, tg_3s = 4.75 t/s 11.39.719.677 I slot print_timing: id 3 | task 1494 | n_gen = 100, tg = 3.93 t/s, tg_3s = 3.97 t/s 11.40.561.939 I slot print_timing: id 1 | task 1350 | n_gen = 244, tg = 3.95 t/s, tg_3s = 4.75 t/s 11.42.880.445 I slot print_timing: id 3 | task 1494 | n_gen = 115, tg = 4.02 t/s, tg_3s = 4.75 t/s 11.43.723.130 I slot print_timing: id 1 | task 1350 | n_gen = 259, tg = 3.99 t/s, tg_3s = 4.75 t/s 11.46.040.428 I slot print_timing: id 3 | task 1494 | n_gen = 130, tg = 4.09 t/s, tg_3s = 4.75 t/s 11.46.885.488 I slot print_timing: id 1 | task 1350 | n_gen = 274, tg = 4.03 t/s, tg_3s = 4.74 t/s 11.49.206.716 I slot print_timing: id 3 | task 1494 | n_gen = 145, tg = 4.15 t/s, tg_3s = 4.74 t/s 11.50.049.811 I slot print_timing: id 1 | task 1350 | n_gen = 289, tg = 4.06 t/s, tg_3s = 4.74 t/s 11.50.470.637 I slot print_timing: id 0 | task 1546 | n_gen = 100, tg = 4.27 t/s, tg_3s = 4.31 t/s 11.52.366.510 I slot print_timing: id 3 | task 1494 | n_gen = 160, tg = 4.20 t/s, tg_3s = 4.75 t/s 11.52.577.137 I slot print_timing: id 2 | task 1557 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 11.53.209.128 I slot print_timing: id 1 | task 1350 | n_gen = 304, tg = 4.09 t/s, tg_3s = 4.75 t/s 11.53.630.375 I slot print_timing: id 0 | task 1546 | n_gen = 115, tg = 4.33 t/s, tg_3s = 4.75 t/s 11.55.526.431 I slot print_timing: id 3 | task 1494 | n_gen = 175, tg = 4.24 t/s, tg_3s = 4.75 t/s 11.55.736.711 I slot print_timing: id 1 | task 1350 | prompt eval time = 2421.90 ms / 130 tokens ( 18.63 ms per token, 53.68 tokens per second) 11.55.736.716 I slot print_timing: id 1 | task 1350 | eval time = 76664.03 ms / 316 tokens ( 243.38 ms per token, 4.11 tokens per second) 11.55.736.717 I slot print_timing: id 1 | task 1350 | total time = 79085.93 ms / 446 tokens 11.55.736.717 I slot print_timing: id 1 | task 1350 | graphs reused = 1275 11.55.736.718 I slot print_timing: id 1 | task 1350 | graph reallocs = 0 / 0 (same size) / (changed size) 11.55.736.768 I slot release: id 1 | task 1350 | stop processing: n_tokens = 1570, truncated = 0 11.55.736.915 I slot print_timing: id 2 | task 1557 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 11.56.026.786 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.730 11.56.026.818 I slot launch_slot_: id 1 | task 1675 | processing task, is_child = 0 11.57.562.110 I slot print_timing: id 0 | task 1546 | n_gen = 127, tg = 4.16 t/s, tg_3s = 3.05 t/s 11.58.529.071 I slot print_timing: id 3 | task 1494 | n_gen = 181, tg = 4.09 t/s, tg_3s = 2.00 t/s 11.58.739.450 I slot print_timing: id 2 | task 1557 | n_gen = 121, tg = 4.44 t/s, tg_3s = 2.00 t/s 12.00.634.272 I slot print_timing: id 0 | task 1546 | n_gen = 140, tg = 4.17 t/s, tg_3s = 4.23 t/s 12.01.687.234 I slot print_timing: id 3 | task 1494 | n_gen = 196, tg = 4.14 t/s, tg_3s = 4.75 t/s 12.01.897.769 I slot print_timing: id 2 | task 1557 | n_gen = 136, tg = 4.47 t/s, tg_3s = 4.75 t/s 12.03.792.932 I slot print_timing: id 0 | task 1546 | n_gen = 155, tg = 4.22 t/s, tg_3s = 4.75 t/s 12.04.845.678 I slot print_timing: id 3 | task 1494 | n_gen = 211, tg = 4.17 t/s, tg_3s = 4.75 t/s 12.05.056.032 I slot print_timing: id 2 | task 1557 | n_gen = 151, tg = 4.50 t/s, tg_3s = 4.75 t/s 12.06.951.385 I slot print_timing: id 0 | task 1546 | n_gen = 170, tg = 4.26 t/s, tg_3s = 4.75 t/s 12.08.006.590 I slot print_timing: id 3 | task 1494 | n_gen = 226, tg = 4.21 t/s, tg_3s = 4.75 t/s 12.08.216.908 I slot print_timing: id 2 | task 1557 | n_gen = 166, tg = 4.52 t/s, tg_3s = 4.75 t/s 12.10.113.241 I slot print_timing: id 0 | task 1546 | n_gen = 185, tg = 4.30 t/s, tg_3s = 4.74 t/s 12.11.167.775 I slot print_timing: id 3 | task 1494 | n_gen = 241, tg = 4.24 t/s, tg_3s = 4.75 t/s 12.11.378.364 I slot print_timing: id 2 | task 1557 | n_gen = 181, tg = 4.54 t/s, tg_3s = 4.74 t/s 12.13.274.346 I slot print_timing: id 0 | task 1546 | n_gen = 200, tg = 4.33 t/s, tg_3s = 4.75 t/s 12.14.328.875 I slot print_timing: id 3 | task 1494 | n_gen = 256, tg = 4.26 t/s, tg_3s = 4.75 t/s 12.14.539.391 I slot print_timing: id 2 | task 1557 | n_gen = 196, tg = 4.55 t/s, tg_3s = 4.75 t/s 12.16.435.459 I slot print_timing: id 0 | task 1546 | n_gen = 215, tg = 4.35 t/s, tg_3s = 4.75 t/s 12.17.488.638 I slot print_timing: id 3 | task 1494 | n_gen = 271, tg = 4.29 t/s, tg_3s = 4.75 t/s 12.17.698.953 I slot print_timing: id 2 | task 1557 | n_gen = 211, tg = 4.57 t/s, tg_3s = 4.75 t/s 12.18.963.717 I slot print_timing: id 1 | task 1675 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 12.19.595.954 I slot print_timing: id 0 | task 1546 | n_gen = 230, tg = 4.38 t/s, tg_3s = 4.75 t/s 12.20.652.657 I slot print_timing: id 3 | task 1494 | n_gen = 286, tg = 4.31 t/s, tg_3s = 4.74 t/s 12.20.863.207 I slot print_timing: id 2 | task 1557 | n_gen = 226, tg = 4.58 t/s, tg_3s = 4.74 t/s 12.22.128.573 I slot print_timing: id 1 | task 1675 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.74 t/s 12.22.761.565 I slot print_timing: id 0 | task 1546 | n_gen = 245, tg = 4.40 t/s, tg_3s = 4.74 t/s 12.23.815.046 I slot print_timing: id 3 | task 1494 | n_gen = 301, tg = 4.33 t/s, tg_3s = 4.74 t/s 12.24.025.775 I slot print_timing: id 2 | task 1557 | n_gen = 241, tg = 4.59 t/s, tg_3s = 4.74 t/s 12.25.290.353 I slot print_timing: id 1 | task 1675 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.74 t/s 12.25.922.307 I slot print_timing: id 0 | task 1546 | n_gen = 260, tg = 4.42 t/s, tg_3s = 4.75 t/s 12.26.976.505 I slot print_timing: id 3 | task 1494 | n_gen = 316, tg = 4.35 t/s, tg_3s = 4.74 t/s 12.27.187.239 I slot print_timing: id 2 | task 1557 | n_gen = 256, tg = 4.60 t/s, tg_3s = 4.74 t/s 12.28.452.536 I slot print_timing: id 1 | task 1675 | n_gen = 145, tg = 4.75 t/s, tg_3s = 4.74 t/s 12.29.085.264 I slot print_timing: id 0 | task 1546 | n_gen = 275, tg = 4.43 t/s, tg_3s = 4.74 t/s 12.30.140.478 I slot print_timing: id 3 | task 1494 | n_gen = 331, tg = 4.36 t/s, tg_3s = 4.74 t/s 12.30.350.959 I slot print_timing: id 2 | task 1557 | n_gen = 271, tg = 4.60 t/s, tg_3s = 4.74 t/s 12.31.616.020 I slot print_timing: id 1 | task 1675 | n_gen = 160, tg = 4.74 t/s, tg_3s = 4.74 t/s 12.32.248.444 I slot print_timing: id 0 | task 1546 | n_gen = 290, tg = 4.45 t/s, tg_3s = 4.74 t/s 12.33.302.661 I slot print_timing: id 3 | task 1494 | n_gen = 346, tg = 4.38 t/s, tg_3s = 4.74 t/s 12.33.513.238 I slot print_timing: id 2 | task 1557 | n_gen = 286, tg = 4.61 t/s, tg_3s = 4.74 t/s 12.34.778.627 I slot print_timing: id 1 | task 1675 | n_gen = 175, tg = 4.74 t/s, tg_3s = 4.74 t/s 12.35.410.825 I slot print_timing: id 0 | task 1546 | n_gen = 305, tg = 4.46 t/s, tg_3s = 4.74 t/s 12.35.832.521 I slot print_timing: id 1 | task 1675 | prompt eval time = 2078.47 ms / 93 tokens ( 22.35 ms per token, 44.74 tokens per second) 12.35.832.523 I slot print_timing: id 1 | task 1675 | eval time = 37727.22 ms / 180 tokens ( 210.77 ms per token, 4.74 tokens per second) 12.35.832.524 I slot print_timing: id 1 | task 1675 | total time = 39805.70 ms / 273 tokens 12.35.832.524 I slot print_timing: id 1 | task 1675 | graphs reused = 1452 12.35.832.525 I slot print_timing: id 1 | task 1675 | graph reallocs = 0 / 0 (same size) / (changed size) 12.35.832.572 I slot release: id 1 | task 1675 | stop processing: n_tokens = 1397, truncated = 0 12.36.123.087 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.820 12.36.123.122 I slot launch_slot_: id 1 | task 1858 | processing task, is_child = 0 12.37.653.962 I slot print_timing: id 2 | task 1557 | n_gen = 299, tg = 4.52 t/s, tg_3s = 3.14 t/s 12.37.654.146 I slot print_timing: id 3 | task 1494 | n_gen = 360, tg = 4.32 t/s, tg_3s = 3.22 t/s 12.38.620.623 I slot print_timing: id 0 | task 1546 | n_gen = 312, tg = 4.36 t/s, tg_3s = 2.18 t/s 12.40.728.606 I slot print_timing: id 2 | task 1557 | n_gen = 312, tg = 4.51 t/s, tg_3s = 4.23 t/s 12.40.728.754 I slot print_timing: id 3 | task 1494 | n_gen = 373, tg = 4.32 t/s, tg_3s = 4.23 t/s 12.41.782.941 I slot print_timing: id 0 | task 1546 | n_gen = 327, tg = 4.38 t/s, tg_3s = 4.74 t/s 12.43.893.423 I slot print_timing: id 2 | task 1557 | n_gen = 327, tg = 4.52 t/s, tg_3s = 4.74 t/s 12.43.893.571 I slot print_timing: id 3 | task 1494 | n_gen = 388, tg = 4.33 t/s, tg_3s = 4.74 t/s 12.44.948.160 I slot print_timing: id 0 | task 1546 | n_gen = 342, tg = 4.39 t/s, tg_3s = 4.74 t/s 12.47.056.078 I slot print_timing: id 2 | task 1557 | n_gen = 342, tg = 4.53 t/s, tg_3s = 4.74 t/s 12.47.056.228 I slot print_timing: id 3 | task 1494 | n_gen = 403, tg = 4.35 t/s, tg_3s = 4.74 t/s 12.48.110.290 I slot print_timing: id 0 | task 1546 | n_gen = 357, tg = 4.40 t/s, tg_3s = 4.74 t/s 12.50.217.149 I slot print_timing: id 2 | task 1557 | n_gen = 357, tg = 4.53 t/s, tg_3s = 4.75 t/s 12.50.217.306 I slot print_timing: id 3 | task 1494 | n_gen = 418, tg = 4.36 t/s, tg_3s = 4.75 t/s 12.50.427.622 I slot print_timing: id 1 | task 1858 | prompt eval time = 2073.94 ms / 87 tokens ( 23.84 ms per token, 41.95 tokens per second) 12.50.427.627 I slot print_timing: id 1 | task 1858 | eval time = 12230.55 ms / 59 tokens ( 210.87 ms per token, 4.74 tokens per second) 12.50.427.628 I slot print_timing: id 1 | task 1858 | total time = 14304.49 ms / 146 tokens 12.50.427.628 I slot print_timing: id 1 | task 1858 | graphs reused = 1509 12.50.427.629 I slot print_timing: id 1 | task 1858 | graph reallocs = 0 / 0 (same size) / (changed size) 12.50.427.673 I slot release: id 1 | task 1858 | stop processing: n_tokens = 1270, truncated = 0 12.50.718.445 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.902 12.50.718.484 I slot launch_slot_: id 1 | task 1920 | processing task, is_child = 0 12.52.259.891 I slot print_timing: id 0 | task 1546 | n_gen = 370, tg = 4.34 t/s, tg_3s = 3.13 t/s 12.53.228.295 I slot print_timing: id 2 | task 1557 | n_gen = 363, tg = 4.44 t/s, tg_3s = 1.99 t/s 12.53.228.450 I slot print_timing: id 3 | task 1494 | n_gen = 424, tg = 4.29 t/s, tg_3s = 1.99 t/s 12.55.336.632 I slot print_timing: id 0 | task 1546 | n_gen = 383, tg = 4.34 t/s, tg_3s = 4.23 t/s 12.56.391.618 I slot print_timing: id 2 | task 1557 | n_gen = 378, tg = 4.45 t/s, tg_3s = 4.74 t/s 12.56.391.765 I slot print_timing: id 3 | task 1494 | n_gen = 439, tg = 4.30 t/s, tg_3s = 4.74 t/s 12.58.502.284 I slot print_timing: id 0 | task 1546 | n_gen = 398, tg = 4.35 t/s, tg_3s = 4.74 t/s 12.59.555.714 I slot print_timing: id 2 | task 1557 | n_gen = 393, tg = 4.46 t/s, tg_3s = 4.74 t/s 12.59.555.874 I slot print_timing: id 3 | task 1494 | n_gen = 454, tg = 4.31 t/s, tg_3s = 4.74 t/s 13.01.668.060 I slot print_timing: id 0 | task 1546 | n_gen = 413, tg = 4.37 t/s, tg_3s = 4.74 t/s 13.02.724.110 I slot print_timing: id 2 | task 1557 | n_gen = 408, tg = 4.47 t/s, tg_3s = 4.73 t/s 13.02.724.258 I slot print_timing: id 3 | task 1494 | n_gen = 469, tg = 4.33 t/s, tg_3s = 4.73 t/s 13.04.832.141 I slot print_timing: id 0 | task 1546 | n_gen = 428, tg = 4.38 t/s, tg_3s = 4.74 t/s 13.05.465.929 I slot print_timing: id 0 | task 1546 | prompt eval time = 2440.86 ms / 137 tokens ( 17.82 ms per token, 56.13 tokens per second) 13.05.465.934 I slot print_timing: id 0 | task 1546 | eval time = 98181.25 ms / 431 tokens ( 228.33 ms per token, 4.38 tokens per second) 13.05.465.935 I slot print_timing: id 0 | task 1546 | total time = 100622.12 ms / 568 tokens 13.05.465.935 I slot print_timing: id 0 | task 1546 | graphs reused = 1568 13.05.465.936 I slot print_timing: id 0 | task 1546 | graph reallocs = 0 / 0 (same size) / (changed size) 13.05.465.985 I slot release: id 0 | task 1546 | stop processing: n_tokens = 1692, truncated = 0 13.05.665.354 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.677 13.05.665.389 I slot launch_slot_: id 0 | task 1984 | processing task, is_child = 0 13.07.352.609 I slot print_timing: id 2 | task 1557 | n_gen = 423, tg = 4.41 t/s, tg_3s = 3.24 t/s 13.07.352.837 I slot print_timing: id 3 | task 1494 | n_gen = 484, tg = 4.28 t/s, tg_3s = 3.24 t/s 13.09.212.064 I slot print_timing: id 2 | task 1557 | prompt eval time = 2665.18 ms / 153 tokens ( 17.42 ms per token, 57.41 tokens per second) 13.09.212.069 I slot print_timing: id 2 | task 1557 | eval time = 97496.90 ms / 431 tokens ( 226.74 ms per token, 4.41 tokens per second) 13.09.212.070 I slot print_timing: id 2 | task 1557 | total time = 100162.08 ms / 584 tokens 13.09.212.071 I slot print_timing: id 2 | task 1557 | graphs reused = 1575 13.09.212.071 I slot print_timing: id 2 | task 1557 | graph reallocs = 0 / 0 (same size) / (changed size) 13.09.212.120 I slot release: id 2 | task 1557 | stop processing: n_tokens = 1708, truncated = 0 13.09.501.608 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.671 13.09.501.649 I slot launch_slot_: id 2 | task 1995 | processing task, is_child = 0 13.11.303.141 I slot print_timing: id 3 | task 1494 | n_gen = 494, tg = 4.22 t/s, tg_3s = 2.53 t/s 13.13.053.435 I slot print_timing: id 1 | task 1920 | prompt eval time = 2085.35 ms / 98 tokens ( 21.28 ms per token, 46.99 tokens per second) 13.13.053.450 I slot print_timing: id 1 | task 1920 | eval time = 20249.59 ms / 80 tokens ( 256.32 ms per token, 3.90 tokens per second) 13.13.053.452 I slot print_timing: id 1 | task 1920 | total time = 22334.94 ms / 178 tokens 13.13.053.453 I slot print_timing: id 1 | task 1920 | graphs reused = 1580 13.13.053.453 I slot print_timing: id 1 | task 1920 | graph reallocs = 0 / 0 (same size) / (changed size) 13.13.053.498 I slot release: id 1 | task 1920 | stop processing: n_tokens = 1302, truncated = 0 13.13.343.605 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.880 13.13.343.636 I slot launch_slot_: id 1 | task 2005 | processing task, is_child = 0 13.15.212.862 I slot print_timing: id 3 | task 1494 | n_gen = 503, tg = 4.16 t/s, tg_3s = 2.30 t/s 13.18.284.020 I slot print_timing: id 3 | task 1494 | n_gen = 516, tg = 4.16 t/s, tg_3s = 4.23 t/s 13.21.440.860 I slot print_timing: id 3 | task 1494 | n_gen = 531, tg = 4.18 t/s, tg_3s = 4.75 t/s 13.24.602.752 I slot print_timing: id 3 | task 1494 | n_gen = 546, tg = 4.19 t/s, tg_3s = 4.74 t/s 13.27.763.271 I slot print_timing: id 3 | task 1494 | n_gen = 561, tg = 4.20 t/s, tg_3s = 4.75 t/s 13.30.292.411 I slot print_timing: id 3 | task 1494 | prompt eval time = 2128.46 ms / 131 tokens ( 16.25 ms per token, 61.55 tokens per second) 13.30.292.416 I slot print_timing: id 3 | task 1494 | eval time = 135756.20 ms / 573 tokens ( 237.34 ms per token, 4.21 tokens per second) 13.30.292.417 I slot print_timing: id 3 | task 1494 | total time = 137884.66 ms / 704 tokens 13.30.292.418 I slot print_timing: id 3 | task 1494 | graphs reused = 1647 13.30.292.418 I slot print_timing: id 3 | task 1494 | graph reallocs = 0 / 0 (same size) / (changed size) 13.30.292.474 I slot release: id 3 | task 1494 | stop processing: n_tokens = 1828, truncated = 0 13.30.489.926 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.627 13.30.489.969 I slot launch_slot_: id 3 | task 2078 | processing task, is_child = 0 13.33.960.265 I slot print_timing: id 0 | task 1984 | n_gen = 100, tg = 3.77 t/s, tg_3s = 3.81 t/s 13.36.067.166 I slot print_timing: id 2 | task 1995 | n_gen = 100, tg = 4.08 t/s, tg_3s = 4.12 t/s 13.37.118.645 I slot print_timing: id 0 | task 1984 | n_gen = 115, tg = 3.88 t/s, tg_3s = 4.75 t/s 13.37.963.156 I slot print_timing: id 1 | task 2005 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 13.39.225.844 I slot print_timing: id 2 | task 1995 | n_gen = 115, tg = 4.15 t/s, tg_3s = 4.75 t/s 13.40.277.200 I slot print_timing: id 0 | task 1984 | n_gen = 130, tg = 3.96 t/s, tg_3s = 4.75 t/s 13.41.118.512 I slot print_timing: id 1 | task 2005 | n_gen = 115, tg = 4.49 t/s, tg_3s = 4.75 t/s 13.42.382.043 I slot print_timing: id 2 | task 1995 | n_gen = 130, tg = 4.22 t/s, tg_3s = 4.75 t/s 13.43.435.470 I slot print_timing: id 0 | task 1984 | n_gen = 145, tg = 4.03 t/s, tg_3s = 4.75 t/s 13.44.277.515 I slot print_timing: id 1 | task 2005 | n_gen = 130, tg = 4.52 t/s, tg_3s = 4.75 t/s 13.45.542.149 I slot print_timing: id 2 | task 1995 | n_gen = 145, tg = 4.27 t/s, tg_3s = 4.75 t/s 13.46.593.856 I slot print_timing: id 0 | task 1984 | n_gen = 160, tg = 4.09 t/s, tg_3s = 4.75 t/s 13.47.435.943 I slot print_timing: id 1 | task 2005 | n_gen = 145, tg = 4.55 t/s, tg_3s = 4.75 t/s 13.48.700.781 I slot print_timing: id 2 | task 1995 | n_gen = 160, tg = 4.31 t/s, tg_3s = 4.75 t/s 13.49.753.227 I slot print_timing: id 0 | task 1984 | n_gen = 175, tg = 4.14 t/s, tg_3s = 4.75 t/s 13.50.595.035 I slot print_timing: id 1 | task 2005 | n_gen = 160, tg = 4.56 t/s, tg_3s = 4.75 t/s 13.51.859.079 I slot print_timing: id 2 | task 1995 | n_gen = 175, tg = 4.34 t/s, tg_3s = 4.75 t/s 13.52.912.511 I slot print_timing: id 0 | task 1984 | n_gen = 190, tg = 4.18 t/s, tg_3s = 4.75 t/s 13.53.124.443 I slot print_timing: id 3 | task 2078 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 13.53.756.361 I slot print_timing: id 1 | task 2005 | n_gen = 175, tg = 4.58 t/s, tg_3s = 4.74 t/s 13.54.177.665 I slot print_timing: id 1 | task 2005 | prompt eval time = 2411.32 ms / 122 tokens ( 19.76 ms per token, 50.59 tokens per second) 13.54.177.668 I slot print_timing: id 1 | task 2005 | eval time = 38422.71 ms / 177 tokens ( 218.31 ms per token, 4.58 tokens per second) 13.54.177.668 I slot print_timing: id 1 | task 2005 | total time = 40834.02 ms / 299 tokens 13.54.177.669 I slot print_timing: id 1 | task 2005 | graphs reused = 1750 13.54.177.669 I slot print_timing: id 1 | task 2005 | graph reallocs = 0 / 0 (same size) / (changed size) 13.54.177.717 I slot release: id 1 | task 2005 | stop processing: n_tokens = 1423, truncated = 0 13.54.467.129 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.805 13.54.467.170 I slot launch_slot_: id 1 | task 2186 | processing task, is_child = 0 13.56.330.118 I slot print_timing: id 0 | task 1984 | n_gen = 198, tg = 4.05 t/s, tg_3s = 2.34 t/s 13.56.330.371 I slot print_timing: id 2 | task 1995 | n_gen = 188, tg = 4.20 t/s, tg_3s = 2.91 t/s 13.56.330.610 I slot print_timing: id 3 | task 2078 | n_gen = 107, tg = 4.41 t/s, tg_3s = 2.18 t/s 13.59.402.842 I slot print_timing: id 0 | task 1984 | n_gen = 211, tg = 4.06 t/s, tg_3s = 4.23 t/s 13.59.403.132 I slot print_timing: id 2 | task 1995 | n_gen = 201, tg = 4.20 t/s, tg_3s = 4.23 t/s 13.59.403.277 I slot print_timing: id 3 | task 2078 | n_gen = 120, tg = 4.39 t/s, tg_3s = 4.23 t/s 14.02.559.971 I slot print_timing: id 0 | task 1984 | n_gen = 226, tg = 4.10 t/s, tg_3s = 4.75 t/s 14.02.560.260 I slot print_timing: id 2 | task 1995 | n_gen = 216, tg = 4.23 t/s, tg_3s = 4.75 t/s 14.02.560.412 I slot print_timing: id 3 | task 2078 | n_gen = 135, tg = 4.42 t/s, tg_3s = 4.75 t/s 14.05.719.128 I slot print_timing: id 0 | task 1984 | n_gen = 241, tg = 4.14 t/s, tg_3s = 4.75 t/s 14.05.720.743 I slot print_timing: id 2 | task 1995 | n_gen = 231, tg = 4.26 t/s, tg_3s = 4.75 t/s 14.05.721.012 I slot print_timing: id 3 | task 2078 | n_gen = 150, tg = 4.46 t/s, tg_3s = 4.75 t/s 14.06.563.281 I slot print_timing: id 2 | task 1995 | prompt eval time = 2286.19 ms / 113 tokens ( 20.23 ms per token, 49.43 tokens per second) 14.06.563.286 I slot print_timing: id 2 | task 1995 | eval time = 54775.43 ms / 235 tokens ( 234.08 ms per token, 4.27 tokens per second) 14.06.563.288 I slot print_timing: id 2 | task 1995 | total time = 57061.62 ms / 348 tokens 14.06.563.288 I slot print_timing: id 2 | task 1995 | graphs reused = 1795 14.06.563.289 I slot print_timing: id 2 | task 1995 | graph reallocs = 0 / 0 (same size) / (changed size) 14.06.563.340 I slot release: id 2 | task 1995 | stop processing: n_tokens = 1472, truncated = 0 14.06.853.378 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.779 14.06.853.413 I slot launch_slot_: id 2 | task 2236 | processing task, is_child = 0 14.09.029.095 I slot print_timing: id 0 | task 1984 | n_gen = 247, tg = 4.01 t/s, tg_3s = 1.81 t/s 14.09.029.482 I slot print_timing: id 3 | task 2078 | n_gen = 156, tg = 4.22 t/s, tg_3s = 1.81 t/s 14.12.046.482 I slot print_timing: id 0 | task 1984 | n_gen = 260, tg = 4.03 t/s, tg_3s = 4.31 t/s 14.12.046.911 I slot print_timing: id 3 | task 2078 | n_gen = 169, tg = 4.22 t/s, tg_3s = 4.31 t/s 14.15.206.041 I slot print_timing: id 0 | task 1984 | n_gen = 275, tg = 4.06 t/s, tg_3s = 4.75 t/s 14.15.206.441 I slot print_timing: id 3 | task 2078 | n_gen = 184, tg = 4.26 t/s, tg_3s = 4.75 t/s 14.18.366.148 I slot print_timing: id 0 | task 1984 | n_gen = 290, tg = 4.09 t/s, tg_3s = 4.75 t/s 14.18.366.549 I slot print_timing: id 3 | task 2078 | n_gen = 199, tg = 4.30 t/s, tg_3s = 4.75 t/s 14.20.051.968 I slot print_timing: id 1 | task 2186 | n_gen = 100, tg = 4.27 t/s, tg_3s = 4.31 t/s 14.21.315.257 I slot print_timing: id 3 | task 2078 | prompt eval time = 1785.73 ms / 96 tokens ( 18.60 ms per token, 53.76 tokens per second) 14.21.315.259 I slot print_timing: id 3 | task 2078 | eval time = 49039.55 ms / 213 tokens ( 231.32 ms per token, 4.32 tokens per second) 14.21.315.260 I slot print_timing: id 3 | task 2078 | total time = 50825.28 ms / 309 tokens 14.21.315.260 I slot print_timing: id 3 | task 2078 | graphs reused = 1850 14.21.315.261 I slot print_timing: id 3 | task 2078 | graph reallocs = 0 / 0 (same size) / (changed size) 14.21.315.312 I slot release: id 3 | task 2078 | stop processing: n_tokens = 1433, truncated = 0 14.21.513.409 I slot print_timing: id 0 | task 1984 | n_gen = 305, tg = 4.12 t/s, tg_3s = 4.77 t/s 14.21.513.718 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.800 14.21.513.754 I slot launch_slot_: id 3 | task 2296 | processing task, is_child = 0 14.23.241.954 I slot print_timing: id 1 | task 2186 | n_gen = 108, tg = 4.06 t/s, tg_3s = 2.51 t/s 14.24.691.690 I slot print_timing: id 0 | task 1984 | n_gen = 312, tg = 4.04 t/s, tg_3s = 2.20 t/s 14.26.376.305 I slot print_timing: id 1 | task 2186 | n_gen = 122, tg = 4.10 t/s, tg_3s = 4.47 t/s 14.27.849.026 I slot print_timing: id 0 | task 1984 | n_gen = 327, tg = 4.07 t/s, tg_3s = 4.75 t/s 14.29.534.519 I slot print_timing: id 1 | task 2186 | n_gen = 137, tg = 4.16 t/s, tg_3s = 4.75 t/s 14.31.007.961 I slot print_timing: id 0 | task 1984 | n_gen = 342, tg = 4.09 t/s, tg_3s = 4.75 t/s 14.32.062.321 I slot print_timing: id 2 | task 2236 | n_gen = 100, tg = 4.39 t/s, tg_3s = 4.43 t/s 14.32.693.800 I slot print_timing: id 1 | task 2186 | n_gen = 152, tg = 4.22 t/s, tg_3s = 4.75 t/s 14.34.168.110 I slot print_timing: id 0 | task 1984 | n_gen = 357, tg = 4.12 t/s, tg_3s = 4.75 t/s 14.35.221.383 I slot print_timing: id 2 | task 2236 | n_gen = 115, tg = 4.43 t/s, tg_3s = 4.75 t/s 14.35.852.943 I slot print_timing: id 1 | task 2186 | n_gen = 167, tg = 4.26 t/s, tg_3s = 4.75 t/s 14.37.326.823 I slot print_timing: id 0 | task 1984 | n_gen = 372, tg = 4.14 t/s, tg_3s = 4.75 t/s 14.38.380.552 I slot print_timing: id 2 | task 2236 | n_gen = 130, tg = 4.47 t/s, tg_3s = 4.75 t/s 14.39.013.070 I slot print_timing: id 1 | task 2186 | n_gen = 182, tg = 4.30 t/s, tg_3s = 4.75 t/s 14.40.487.201 I slot print_timing: id 0 | task 1984 | n_gen = 387, tg = 4.16 t/s, tg_3s = 4.75 t/s 14.40.696.566 I slot print_timing: id 0 | task 1984 | prompt eval time = 2068.27 ms / 105 tokens ( 19.70 ms per token, 50.77 tokens per second) 14.40.696.568 I slot print_timing: id 0 | task 1984 | eval time = 92962.90 ms / 388 tokens ( 240.21 ms per token, 4.16 tokens per second) 14.40.696.569 I slot print_timing: id 0 | task 1984 | total time = 95031.17 ms / 493 tokens 14.40.696.569 I slot print_timing: id 0 | task 1984 | graphs reused = 1930 14.40.696.570 I slot print_timing: id 0 | task 1984 | graph reallocs = 0 / 0 (same size) / (changed size) 14.40.696.620 I slot release: id 0 | task 1984 | stop processing: n_tokens = 1617, truncated = 0 14.40.895.641 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.709 14.40.895.679 I slot launch_slot_: id 0 | task 2381 | processing task, is_child = 0 14.42.595.247 I slot print_timing: id 1 | task 2186 | n_gen = 192, tg = 4.18 t/s, tg_3s = 2.79 t/s 14.42.595.446 I slot print_timing: id 2 | task 2236 | n_gen = 143, tg = 4.29 t/s, tg_3s = 3.08 t/s 14.45.716.364 I slot print_timing: id 1 | task 2186 | n_gen = 206, tg = 4.20 t/s, tg_3s = 4.49 t/s 14.45.716.518 I slot print_timing: id 2 | task 2236 | n_gen = 157, tg = 4.31 t/s, tg_3s = 4.49 t/s 14.46.137.751 I slot print_timing: id 3 | task 2296 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.44 t/s 14.48.874.877 I slot print_timing: id 1 | task 2186 | prompt eval time = 2406.02 ms / 113 tokens ( 21.29 ms per token, 46.97 tokens per second) 14.48.874.883 I slot print_timing: id 1 | task 2186 | eval time = 52001.68 ms / 221 tokens ( 236.37 ms per token, 4.23 tokens per second) 14.48.874.883 I slot print_timing: id 1 | task 2186 | total time = 54407.70 ms / 334 tokens 14.48.874.884 I slot print_timing: id 1 | task 2186 | graphs reused = 1958 14.48.874.884 I slot print_timing: id 1 | task 2186 | graph reallocs = 0 / 0 (same size) / (changed size) 14.48.874.961 I slot release: id 1 | task 2186 | stop processing: n_tokens = 1458, truncated = 0 14.48.875.106 I slot print_timing: id 2 | task 2236 | n_gen = 172, tg = 4.34 t/s, tg_3s = 4.75 t/s 14.49.164.512 I slot print_timing: id 3 | task 2296 | n_gen = 114, tg = 4.43 t/s, tg_3s = 4.63 t/s 14.49.164.520 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.786 14.49.164.545 I slot launch_slot_: id 1 | task 2413 | processing task, is_child = 0 14.52.003.675 I slot print_timing: id 2 | task 2236 | n_gen = 177, tg = 4.14 t/s, tg_3s = 1.60 t/s 14.52.214.200 I slot print_timing: id 3 | task 2296 | n_gen = 119, tg = 4.13 t/s, tg_3s = 1.64 t/s 14.55.162.679 I slot print_timing: id 2 | task 2236 | n_gen = 192, tg = 4.18 t/s, tg_3s = 4.75 t/s 14.55.373.346 I slot print_timing: id 3 | task 2296 | n_gen = 134, tg = 4.19 t/s, tg_3s = 4.75 t/s 14.58.319.168 I slot print_timing: id 2 | task 2236 | n_gen = 207, tg = 4.22 t/s, tg_3s = 4.75 t/s 14.58.529.723 I slot print_timing: id 3 | task 2296 | n_gen = 149, tg = 4.24 t/s, tg_3s = 4.75 t/s 15.01.475.024 I slot print_timing: id 2 | task 2236 | n_gen = 222, tg = 4.25 t/s, tg_3s = 4.75 t/s 15.01.685.296 I slot print_timing: id 3 | task 2296 | n_gen = 164, tg = 4.28 t/s, tg_3s = 4.75 t/s 15.04.634.366 I slot print_timing: id 2 | task 2236 | n_gen = 237, tg = 4.28 t/s, tg_3s = 4.75 t/s 15.04.845.232 I slot print_timing: id 3 | task 2296 | n_gen = 179, tg = 4.32 t/s, tg_3s = 4.75 t/s 15.05.897.737 I slot print_timing: id 0 | task 2381 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 15.07.792.295 I slot print_timing: id 2 | task 2236 | n_gen = 252, tg = 4.31 t/s, tg_3s = 4.75 t/s 15.08.004.223 I slot print_timing: id 3 | task 2296 | n_gen = 194, tg = 4.35 t/s, tg_3s = 4.75 t/s 15.09.057.522 I slot print_timing: id 0 | task 2381 | n_gen = 115, tg = 4.37 t/s, tg_3s = 4.75 t/s 15.10.955.138 I slot print_timing: id 2 | task 2236 | n_gen = 267, tg = 4.33 t/s, tg_3s = 4.74 t/s 15.11.165.951 I slot print_timing: id 3 | task 2296 | n_gen = 209, tg = 4.38 t/s, tg_3s = 4.74 t/s 15.12.217.267 I slot print_timing: id 0 | task 2381 | n_gen = 130, tg = 4.41 t/s, tg_3s = 4.75 t/s 15.12.428.127 I slot print_timing: id 1 | task 2413 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 15.14.113.688 I slot print_timing: id 2 | task 2236 | n_gen = 282, tg = 4.35 t/s, tg_3s = 4.75 t/s 15.14.324.524 I slot print_timing: id 3 | task 2296 | n_gen = 224, tg = 4.40 t/s, tg_3s = 4.75 t/s 15.15.377.490 I slot print_timing: id 0 | task 2381 | n_gen = 145, tg = 4.44 t/s, tg_3s = 4.75 t/s 15.15.588.170 I slot print_timing: id 1 | task 2413 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 15.17.273.558 I slot print_timing: id 2 | task 2236 | n_gen = 297, tg = 4.37 t/s, tg_3s = 4.75 t/s 15.17.484.263 I slot print_timing: id 3 | task 2296 | n_gen = 239, tg = 4.42 t/s, tg_3s = 4.75 t/s 15.18.537.008 I slot print_timing: id 0 | task 2381 | n_gen = 160, tg = 4.47 t/s, tg_3s = 4.75 t/s 15.18.747.789 I slot print_timing: id 1 | task 2413 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 15.20.433.657 I slot print_timing: id 2 | task 2236 | n_gen = 312, tg = 4.39 t/s, tg_3s = 4.75 t/s 15.20.644.684 I slot print_timing: id 3 | task 2296 | n_gen = 254, tg = 4.44 t/s, tg_3s = 4.75 t/s 15.21.697.996 I slot print_timing: id 0 | task 2381 | n_gen = 175, tg = 4.49 t/s, tg_3s = 4.75 t/s 15.21.908.940 I slot print_timing: id 1 | task 2413 | n_gen = 145, tg = 4.75 t/s, tg_3s = 4.75 t/s 15.23.594.765 I slot print_timing: id 2 | task 2236 | n_gen = 327, tg = 4.40 t/s, tg_3s = 4.75 t/s 15.23.805.744 I slot print_timing: id 3 | task 2296 | n_gen = 269, tg = 4.45 t/s, tg_3s = 4.75 t/s 15.24.861.127 I slot print_timing: id 0 | task 2381 | n_gen = 190, tg = 4.51 t/s, tg_3s = 4.74 t/s 15.25.071.945 I slot print_timing: id 1 | task 2413 | n_gen = 160, tg = 4.75 t/s, tg_3s = 4.74 t/s 15.26.757.760 I slot print_timing: id 2 | task 2236 | n_gen = 342, tg = 4.41 t/s, tg_3s = 4.74 t/s 15.26.968.660 I slot print_timing: id 3 | task 2296 | n_gen = 284, tg = 4.47 t/s, tg_3s = 4.74 t/s 15.28.021.835 I slot print_timing: id 0 | task 2381 | n_gen = 205, tg = 4.53 t/s, tg_3s = 4.75 t/s 15.28.232.620 I slot print_timing: id 1 | task 2413 | n_gen = 175, tg = 4.75 t/s, tg_3s = 4.75 t/s 15.28.232.760 I slot print_timing: id 2 | task 2236 | prompt eval time = 2660.83 ms / 149 tokens ( 17.86 ms per token, 56.00 tokens per second) 15.28.232.762 I slot print_timing: id 2 | task 2236 | eval time = 78718.51 ms / 349 tokens ( 226.20 ms per token, 4.42 tokens per second) 15.28.232.762 I slot print_timing: id 2 | task 2236 | total time = 81379.34 ms / 498 tokens 15.28.232.763 I slot print_timing: id 2 | task 2236 | graphs reused = 2130 15.28.232.763 I slot print_timing: id 2 | task 2236 | graph reallocs = 0 / 0 (same size) / (changed size) 15.28.232.826 I slot release: id 2 | task 2236 | stop processing: n_tokens = 1622, truncated = 0 15.28.523.012 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.707 15.28.523.044 I slot launch_slot_: id 2 | task 2591 | processing task, is_child = 0 15.30.689.363 I slot print_timing: id 3 | task 2296 | n_gen = 292, tg = 4.34 t/s, tg_3s = 2.15 t/s 15.31.173.621 I slot print_timing: id 0 | task 2381 | n_gen = 209, tg = 4.32 t/s, tg_3s = 1.27 t/s 15.31.386.745 I slot print_timing: id 1 | task 2413 | n_gen = 179, tg = 4.47 t/s, tg_3s = 1.27 t/s 15.33.708.831 I slot print_timing: id 3 | task 2296 | n_gen = 305, tg = 4.34 t/s, tg_3s = 4.31 t/s 15.34.340.312 I slot print_timing: id 0 | task 2381 | n_gen = 224, tg = 4.34 t/s, tg_3s = 4.74 t/s 15.34.550.964 I slot print_timing: id 1 | task 2413 | n_gen = 194, tg = 4.49 t/s, tg_3s = 4.74 t/s 15.36.870.507 I slot print_timing: id 3 | task 2296 | n_gen = 320, tg = 4.36 t/s, tg_3s = 4.74 t/s 15.37.502.411 I slot print_timing: id 0 | task 2381 | n_gen = 239, tg = 4.36 t/s, tg_3s = 4.74 t/s 15.37.713.165 I slot print_timing: id 1 | task 2413 | n_gen = 209, tg = 4.51 t/s, tg_3s = 4.74 t/s 15.40.031.753 I slot print_timing: id 3 | task 2296 | n_gen = 335, tg = 4.37 t/s, tg_3s = 4.74 t/s 15.40.663.076 I slot print_timing: id 0 | task 2381 | n_gen = 254, tg = 4.39 t/s, tg_3s = 4.75 t/s 15.40.873.730 I slot print_timing: id 1 | task 2413 | n_gen = 224, tg = 4.52 t/s, tg_3s = 4.75 t/s 15.43.191.898 I slot print_timing: id 3 | task 2296 | n_gen = 350, tg = 4.39 t/s, tg_3s = 4.75 t/s 15.43.823.484 I slot print_timing: id 0 | task 2381 | n_gen = 269, tg = 4.40 t/s, tg_3s = 4.75 t/s 15.44.034.262 I slot print_timing: id 1 | task 2413 | n_gen = 239, tg = 4.54 t/s, tg_3s = 4.75 t/s 15.46.352.766 I slot print_timing: id 3 | task 2296 | n_gen = 365, tg = 4.40 t/s, tg_3s = 4.75 t/s 15.46.984.728 I slot print_timing: id 0 | task 2381 | n_gen = 284, tg = 4.42 t/s, tg_3s = 4.74 t/s 15.47.195.668 I slot print_timing: id 1 | task 2413 | n_gen = 254, tg = 4.55 t/s, tg_3s = 4.74 t/s 15.48.670.621 I slot print_timing: id 0 | task 2381 | prompt eval time = 2081.06 ms / 117 tokens ( 17.79 ms per token, 56.22 tokens per second) 15.48.670.626 I slot print_timing: id 0 | task 2381 | eval time = 65693.87 ms / 292 tokens ( 225.75 ms per token, 4.43 tokens per second) 15.48.670.628 I slot print_timing: id 0 | task 2381 | total time = 67774.93 ms / 409 tokens 15.48.670.628 I slot print_timing: id 0 | task 2381 | graphs reused = 2212 15.48.670.629 I slot print_timing: id 0 | task 2381 | graph reallocs = 0 / 0 (same size) / (changed size) 15.48.672.016 I slot release: id 0 | task 2381 | stop processing: n_tokens = 1533, truncated = 0 15.48.872.138 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.748 15.48.872.169 I slot launch_slot_: id 0 | task 2678 | processing task, is_child = 0 15.50.247.340 I slot print_timing: id 1 | task 2413 | n_gen = 263, tg = 4.47 t/s, tg_3s = 2.95 t/s 15.50.247.655 I slot print_timing: id 3 | task 2296 | n_gen = 378, tg = 4.35 t/s, tg_3s = 3.34 t/s 15.51.686.487 I slot print_timing: id 3 | task 2296 | prompt eval time = 2123.07 ms / 131 tokens ( 16.21 ms per token, 61.70 tokens per second) 15.51.686.492 I slot print_timing: id 3 | task 2296 | eval time = 88049.65 ms / 384 tokens ( 229.89 ms per token, 4.35 tokens per second) 15.51.686.493 I slot print_timing: id 3 | task 2296 | total time = 90172.72 ms / 515 tokens 15.51.686.493 I slot print_timing: id 3 | task 2296 | graphs reused = 2217 15.51.686.494 I slot print_timing: id 3 | task 2296 | graph reallocs = 0 / 0 (same size) / (changed size) 15.51.686.544 I slot release: id 3 | task 2296 | stop processing: n_tokens = 1639, truncated = 0 15.51.885.199 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.699 15.51.885.236 I slot launch_slot_: id 3 | task 2687 | processing task, is_child = 0 15.53.586.041 I slot print_timing: id 1 | task 2413 | n_gen = 271, tg = 4.35 t/s, tg_3s = 2.40 t/s 15.55.035.464 I slot print_timing: id 2 | task 2591 | n_gen = 100, tg = 4.15 t/s, tg_3s = 4.19 t/s 15.56.720.928 I slot print_timing: id 1 | task 2413 | n_gen = 285, tg = 4.36 t/s, tg_3s = 4.47 t/s 15.58.198.161 I slot print_timing: id 2 | task 2591 | n_gen = 115, tg = 4.22 t/s, tg_3s = 4.74 t/s 15.59.882.695 I slot print_timing: id 1 | task 2413 | n_gen = 300, tg = 4.38 t/s, tg_3s = 4.74 t/s 16.01.356.493 I slot print_timing: id 2 | task 2591 | n_gen = 130, tg = 4.27 t/s, tg_3s = 4.75 t/s 16.03.039.678 I slot print_timing: id 1 | task 2413 | n_gen = 315, tg = 4.39 t/s, tg_3s = 4.75 t/s 16.04.512.918 I slot print_timing: id 2 | task 2591 | n_gen = 145, tg = 4.32 t/s, tg_3s = 4.75 t/s 16.06.197.131 I slot print_timing: id 1 | task 2413 | n_gen = 330, tg = 4.41 t/s, tg_3s = 4.75 t/s 16.07.039.629 I slot print_timing: id 1 | task 2413 | prompt eval time = 2415.56 ms / 127 tokens ( 19.02 ms per token, 52.58 tokens per second) 16.07.039.632 I slot print_timing: id 1 | task 2413 | eval time = 75459.52 ms / 334 tokens ( 226.61 ms per token, 4.41 tokens per second) 16.07.039.632 I slot print_timing: id 1 | task 2413 | total time = 77875.08 ms / 461 tokens 16.07.039.637 I slot print_timing: id 1 | task 2413 | graphs reused = 2277 16.07.039.637 I slot print_timing: id 1 | task 2413 | graph reallocs = 0 / 0 (same size) / (changed size) 16.07.039.687 I slot release: id 1 | task 2413 | stop processing: n_tokens = 1585, truncated = 0 16.07.329.267 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.723 16.07.329.307 I slot launch_slot_: id 1 | task 2753 | processing task, is_child = 0 16.08.869.649 I slot print_timing: id 2 | task 2591 | n_gen = 159, tg = 4.19 t/s, tg_3s = 3.21 t/s 16.11.939.553 I slot print_timing: id 2 | task 2591 | n_gen = 172, tg = 4.19 t/s, tg_3s = 4.23 t/s 16.14.886.175 I slot print_timing: id 0 | task 2678 | n_gen = 100, tg = 4.08 t/s, tg_3s = 4.12 t/s 16.14.886.603 I slot print_timing: id 3 | task 2687 | prompt eval time = 2094.30 ms / 104 tokens ( 20.14 ms per token, 49.66 tokens per second) 16.14.886.605 I slot print_timing: id 3 | task 2687 | eval time = 20907.06 ms / 92 tokens ( 229.75 ms per token, 4.35 tokens per second) 16.14.886.605 I slot print_timing: id 3 | task 2687 | total time = 23001.36 ms / 196 tokens 16.14.886.606 I slot print_timing: id 3 | task 2687 | graphs reused = 2302 16.14.886.606 I slot print_timing: id 3 | task 2687 | graph reallocs = 0 / 0 (same size) / (changed size) 16.14.886.649 I slot release: id 3 | task 2687 | stop processing: n_tokens = 1320, truncated = 0 16.15.085.044 I slot print_timing: id 2 | task 2591 | n_gen = 187, tg = 4.24 t/s, tg_3s = 4.77 t/s 16.15.085.049 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.868 16.15.085.076 I slot launch_slot_: id 3 | task 2783 | processing task, is_child = 0 16.18.022.730 I slot print_timing: id 0 | task 2678 | n_gen = 107, tg = 3.87 t/s, tg_3s = 2.23 t/s 16.18.233.538 I slot print_timing: id 2 | task 2591 | n_gen = 194, tg = 4.10 t/s, tg_3s = 2.22 t/s 16.21.179.058 I slot print_timing: id 0 | task 2678 | n_gen = 122, tg = 3.96 t/s, tg_3s = 4.75 t/s 16.21.389.682 I slot print_timing: id 2 | task 2591 | n_gen = 209, tg = 4.14 t/s, tg_3s = 4.75 t/s 16.24.337.894 I slot print_timing: id 0 | task 2678 | n_gen = 137, tg = 4.03 t/s, tg_3s = 4.75 t/s 16.24.548.269 I slot print_timing: id 2 | task 2591 | n_gen = 224, tg = 4.18 t/s, tg_3s = 4.75 t/s 16.27.494.391 I slot print_timing: id 0 | task 2678 | n_gen = 152, tg = 4.10 t/s, tg_3s = 4.75 t/s 16.27.705.006 I slot print_timing: id 2 | task 2591 | n_gen = 239, tg = 4.21 t/s, tg_3s = 4.75 t/s 16.30.020.489 I slot print_timing: id 1 | task 2753 | prompt eval time = 2082.50 ms / 98 tokens ( 21.25 ms per token, 47.06 tokens per second) 16.30.020.494 I slot print_timing: id 1 | task 2753 | eval time = 20608.68 ms / 91 tokens ( 228.99 ms per token, 4.37 tokens per second) 16.30.020.496 I slot print_timing: id 1 | task 2753 | total time = 22691.17 ms / 189 tokens 16.30.020.496 I slot print_timing: id 1 | task 2753 | graphs reused = 2362 16.30.020.497 I slot print_timing: id 1 | task 2753 | graph reallocs = 0 / 0 (same size) / (changed size) 16.30.020.548 I slot release: id 1 | task 2753 | stop processing: n_tokens = 1313, truncated = 0 16.30.310.450 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.873 16.30.310.484 I slot launch_slot_: id 1 | task 2848 | processing task, is_child = 0 16.32.165.462 I slot print_timing: id 0 | task 2678 | n_gen = 166, tg = 3.97 t/s, tg_3s = 3.00 t/s 16.32.165.633 I slot print_timing: id 2 | task 2591 | n_gen = 252, tg = 4.12 t/s, tg_3s = 2.91 t/s 16.34.607.998 I slot print_timing: id 3 | task 2783 | prompt eval time = 2094.20 ms / 102 tokens ( 20.53 ms per token, 48.71 tokens per second) 16.34.608.001 I slot print_timing: id 3 | task 2783 | eval time = 17428.71 ms / 74 tokens ( 238.75 ms per token, 4.19 tokens per second) 16.34.608.001 I slot print_timing: id 3 | task 2783 | total time = 19522.91 ms / 176 tokens 16.34.608.002 I slot print_timing: id 3 | task 2783 | graphs reused = 2370 16.34.608.002 I slot print_timing: id 3 | task 2783 | graph reallocs = 0 / 0 (same size) / (changed size) 16.34.608.045 I slot release: id 3 | task 2783 | stop processing: n_tokens = 1300, truncated = 0 16.34.805.486 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.882 16.34.805.522 I slot launch_slot_: id 3 | task 2861 | processing task, is_child = 0 16.36.525.577 I slot print_timing: id 0 | task 2678 | n_gen = 178, tg = 3.86 t/s, tg_3s = 2.75 t/s 16.36.525.910 I slot print_timing: id 2 | task 2591 | n_gen = 264, tg = 4.02 t/s, tg_3s = 2.75 t/s 16.39.663.336 I slot print_timing: id 0 | task 2678 | n_gen = 192, tg = 3.90 t/s, tg_3s = 4.46 t/s 16.39.663.630 I slot print_timing: id 2 | task 2591 | n_gen = 278, tg = 4.04 t/s, tg_3s = 4.46 t/s 16.40.926.822 I slot print_timing: id 0 | task 2678 | prompt eval time = 1758.05 ms / 96 tokens ( 18.31 ms per token, 54.61 tokens per second) 16.40.926.825 I slot print_timing: id 0 | task 2678 | eval time = 50296.60 ms / 198 tokens ( 255.31 ms per token, 3.92 tokens per second) 16.40.926.826 I slot print_timing: id 0 | task 2678 | total time = 52054.64 ms / 294 tokens 16.40.926.826 I slot print_timing: id 0 | task 2678 | graphs reused = 2387 16.40.926.827 I slot print_timing: id 0 | task 2678 | graph reallocs = 0 / 0 (same size) / (changed size) 16.40.926.875 I slot release: id 0 | task 2678 | stop processing: n_tokens = 1418, truncated = 0 16.41.126.063 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.808 16.41.126.095 I slot launch_slot_: id 0 | task 2884 | processing task, is_child = 0 16.42.832.726 I slot print_timing: id 2 | task 2591 | n_gen = 286, tg = 3.98 t/s, tg_3s = 2.52 t/s 16.45.952.469 I slot print_timing: id 2 | task 2591 | n_gen = 300, tg = 4.00 t/s, tg_3s = 4.49 t/s 16.49.110.120 I slot print_timing: id 2 | task 2591 | n_gen = 315, tg = 4.03 t/s, tg_3s = 4.75 t/s 16.52.271.268 I slot print_timing: id 2 | task 2591 | n_gen = 330, tg = 4.06 t/s, tg_3s = 4.75 t/s 16.53.323.972 I slot print_timing: id 2 | task 2591 | prompt eval time = 2650.95 ms / 137 tokens ( 19.35 ms per token, 51.68 tokens per second) 16.53.323.975 I slot print_timing: id 2 | task 2591 | eval time = 82149.97 ms / 335 tokens ( 245.96 ms per token, 4.07 tokens per second) 16.53.323.976 I slot print_timing: id 2 | task 2591 | total time = 84800.92 ms / 472 tokens 16.53.323.976 I slot print_timing: id 2 | task 2591 | graphs reused = 2435 16.53.323.976 I slot print_timing: id 2 | task 2591 | graph reallocs = 0 / 0 (same size) / (changed size) 16.53.324.026 I slot release: id 2 | task 2591 | stop processing: n_tokens = 1596, truncated = 0 16.53.613.957 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.718 16.53.614.005 I slot launch_slot_: id 2 | task 2936 | processing task, is_child = 0 16.58.844.857 I slot print_timing: id 1 | task 2848 | n_gen = 100, tg = 3.79 t/s, tg_3s = 3.83 t/s 17.01.372.233 I slot print_timing: id 3 | task 2861 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 17.02.003.733 I slot print_timing: id 1 | task 2848 | n_gen = 115, tg = 3.89 t/s, tg_3s = 4.75 t/s 17.03.899.211 I slot print_timing: id 3 | task 2861 | prompt eval time = 2115.45 ms / 122 tokens ( 17.34 ms per token, 57.67 tokens per second) 17.03.899.214 I slot print_timing: id 3 | task 2861 | eval time = 26978.23 ms / 112 tokens ( 243.05 ms per token, 4.11 tokens per second) 17.03.899.214 I slot print_timing: id 3 | task 2861 | total time = 29093.68 ms / 234 tokens 17.03.899.215 I slot print_timing: id 3 | task 2861 | graphs reused = 2472 17.03.899.215 I slot print_timing: id 3 | task 2861 | graph reallocs = 0 / 0 (same size) / (changed size) 17.03.899.269 I slot release: id 3 | task 2861 | stop processing: n_tokens = 1358, truncated = 0 17.04.098.046 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.844 17.04.098.082 I slot launch_slot_: id 3 | task 2978 | processing task, is_child = 0 17.05.477.318 I slot print_timing: id 1 | task 2848 | n_gen = 126, tg = 3.81 t/s, tg_3s = 3.17 t/s 17.07.348.032 I slot print_timing: id 0 | task 2884 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 17.08.613.146 I slot print_timing: id 1 | task 2848 | n_gen = 140, tg = 3.87 t/s, tg_3s = 4.46 t/s 17.10.507.911 I slot print_timing: id 0 | task 2884 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.75 t/s 17.11.770.948 I slot print_timing: id 1 | task 2848 | n_gen = 155, tg = 3.94 t/s, tg_3s = 4.75 t/s 17.13.666.016 I slot print_timing: id 0 | task 2884 | n_gen = 130, tg = 4.24 t/s, tg_3s = 4.75 t/s 17.14.928.729 I slot print_timing: id 1 | task 2848 | n_gen = 170, tg = 4.00 t/s, tg_3s = 4.75 t/s 17.16.825.496 I slot print_timing: id 0 | task 2884 | n_gen = 145, tg = 4.28 t/s, tg_3s = 4.75 t/s 17.18.091.400 I slot print_timing: id 1 | task 2848 | n_gen = 185, tg = 4.05 t/s, tg_3s = 4.74 t/s 17.18.091.670 I slot print_timing: id 2 | task 2936 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.51 t/s 17.19.986.185 I slot print_timing: id 0 | task 2884 | n_gen = 160, tg = 4.32 t/s, tg_3s = 4.75 t/s 17.21.249.073 I slot print_timing: id 1 | task 2848 | n_gen = 200, tg = 4.10 t/s, tg_3s = 4.75 t/s 17.21.249.216 I slot print_timing: id 2 | task 2936 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.75 t/s 17.23.145.516 I slot print_timing: id 0 | task 2884 | n_gen = 175, tg = 4.36 t/s, tg_3s = 4.75 t/s 17.24.410.378 I slot print_timing: id 1 | task 2848 | n_gen = 215, tg = 4.14 t/s, tg_3s = 4.74 t/s 17.24.410.519 I slot print_timing: id 2 | task 2936 | n_gen = 130, tg = 4.52 t/s, tg_3s = 4.74 t/s 17.26.306.018 I slot print_timing: id 0 | task 2884 | n_gen = 190, tg = 4.39 t/s, tg_3s = 4.75 t/s 17.26.727.669 I slot print_timing: id 3 | task 2978 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 17.27.569.708 I slot print_timing: id 1 | task 2848 | n_gen = 230, tg = 4.17 t/s, tg_3s = 4.75 t/s 17.27.569.862 I slot print_timing: id 2 | task 2936 | n_gen = 145, tg = 4.55 t/s, tg_3s = 4.75 t/s 17.29.467.573 I slot print_timing: id 0 | task 2884 | n_gen = 205, tg = 4.41 t/s, tg_3s = 4.74 t/s 17.29.890.455 I slot print_timing: id 3 | task 2978 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.74 t/s 17.30.732.623 I slot print_timing: id 1 | task 2848 | n_gen = 245, tg = 4.21 t/s, tg_3s = 4.74 t/s 17.30.732.773 I slot print_timing: id 2 | task 2936 | n_gen = 160, tg = 4.56 t/s, tg_3s = 4.74 t/s 17.32.627.917 I slot print_timing: id 0 | task 2884 | n_gen = 220, tg = 4.43 t/s, tg_3s = 4.75 t/s 17.33.049.109 I slot print_timing: id 3 | task 2978 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 17.33.891.141 I slot print_timing: id 1 | task 2848 | n_gen = 260, tg = 4.23 t/s, tg_3s = 4.75 t/s 17.33.891.288 I slot print_timing: id 2 | task 2936 | n_gen = 175, tg = 4.58 t/s, tg_3s = 4.75 t/s 17.35.156.258 I slot print_timing: id 3 | task 2978 | prompt eval time = 1774.88 ms / 86 tokens ( 20.64 ms per token, 48.45 tokens per second) 17.35.156.264 I slot print_timing: id 3 | task 2978 | eval time = 29283.29 ms / 140 tokens ( 210.67 ms per token, 4.75 tokens per second) 17.35.156.264 I slot print_timing: id 3 | task 2978 | total time = 31058.17 ms / 226 tokens 17.35.156.265 I slot print_timing: id 3 | task 2978 | graphs reused = 2610 17.35.156.265 I slot print_timing: id 3 | task 2978 | graph reallocs = 0 / 0 (same size) / (changed size) 17.35.156.309 I slot release: id 3 | task 2978 | stop processing: n_tokens = 1350, truncated = 0 17.35.355.161 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.849 17.35.355.200 I slot launch_slot_: id 3 | task 3121 | processing task, is_child = 0 17.37.062.465 I slot print_timing: id 0 | task 2884 | n_gen = 234, tg = 4.33 t/s, tg_3s = 3.16 t/s 17.37.062.714 I slot print_timing: id 1 | task 2848 | n_gen = 268, tg = 4.15 t/s, tg_3s = 2.52 t/s 17.37.062.949 I slot print_timing: id 2 | task 2936 | n_gen = 183, tg = 4.42 t/s, tg_3s = 2.52 t/s 17.38.515.266 I slot print_timing: id 1 | task 2848 | prompt eval time = 2398.63 ms / 108 tokens ( 22.21 ms per token, 45.03 tokens per second) 17.38.515.269 I slot print_timing: id 1 | task 2848 | eval time = 65806.14 ms / 274 tokens ( 241.05 ms per token, 4.15 tokens per second) 17.38.515.270 I slot print_timing: id 1 | task 2848 | total time = 68204.77 ms / 382 tokens 17.38.515.270 I slot print_timing: id 1 | task 2848 | graphs reused = 2614 17.38.515.271 I slot print_timing: id 1 | task 2848 | graph reallocs = 0 / 0 (same size) / (changed size) 17.38.515.317 I slot release: id 1 | task 2848 | stop processing: n_tokens = 1506, truncated = 0 17.38.805.147 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.761 17.38.805.195 I slot launch_slot_: id 1 | task 3130 | processing task, is_child = 0 17.40.343.481 I slot print_timing: id 0 | task 2884 | n_gen = 242, tg = 4.22 t/s, tg_3s = 2.44 t/s 17.40.343.655 I slot print_timing: id 2 | task 2936 | n_gen = 191, tg = 4.27 t/s, tg_3s = 2.44 t/s 17.43.415.043 I slot print_timing: id 0 | task 2884 | n_gen = 255, tg = 4.22 t/s, tg_3s = 4.23 t/s 17.43.415.329 I slot print_timing: id 2 | task 2936 | n_gen = 204, tg = 4.27 t/s, tg_3s = 4.23 t/s 17.46.574.098 I slot print_timing: id 0 | task 2884 | n_gen = 270, tg = 4.25 t/s, tg_3s = 4.75 t/s 17.46.574.386 I slot print_timing: id 2 | task 2936 | n_gen = 219, tg = 4.30 t/s, tg_3s = 4.75 t/s 17.49.733.489 I slot print_timing: id 0 | task 2884 | n_gen = 285, tg = 4.27 t/s, tg_3s = 4.75 t/s 17.49.733.761 I slot print_timing: id 2 | task 2936 | n_gen = 234, tg = 4.33 t/s, tg_3s = 4.75 t/s 17.52.894.617 I slot print_timing: id 0 | task 2884 | n_gen = 300, tg = 4.29 t/s, tg_3s = 4.75 t/s 17.52.894.889 I slot print_timing: id 2 | task 2936 | n_gen = 249, tg = 4.35 t/s, tg_3s = 4.75 t/s 17.56.054.340 I slot print_timing: id 0 | task 2884 | n_gen = 315, tg = 4.31 t/s, tg_3s = 4.75 t/s 17.56.054.631 I slot print_timing: id 2 | task 2936 | n_gen = 264, tg = 4.37 t/s, tg_3s = 4.75 t/s 17.59.212.902 I slot print_timing: id 0 | task 2884 | n_gen = 330, tg = 4.33 t/s, tg_3s = 4.75 t/s 17.59.213.187 I slot print_timing: id 2 | task 2936 | prompt eval time = 2283.17 ms / 111 tokens ( 20.57 ms per token, 48.62 tokens per second) 17.59.213.189 I slot print_timing: id 2 | task 2936 | eval time = 63316.01 ms / 279 tokens ( 227.76 ms per token, 4.39 tokens per second) 17.59.213.190 I slot print_timing: id 2 | task 2936 | total time = 65599.17 ms / 390 tokens 17.59.213.190 I slot print_timing: id 2 | task 2936 | graphs reused = 2699 17.59.213.191 I slot print_timing: id 2 | task 2936 | graph reallocs = 0 / 0 (same size) / (changed size) 17.59.213.242 I slot release: id 2 | task 2936 | stop processing: n_tokens = 1514, truncated = 0 17.59.502.927 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.757 17.59.502.962 I slot launch_slot_: id 2 | task 3221 | processing task, is_child = 0 18.01.678.738 I slot print_timing: id 3 | task 3121 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 18.02.309.981 I slot print_timing: id 0 | task 2884 | n_gen = 337, tg = 4.25 t/s, tg_3s = 2.26 t/s 18.03.362.762 I slot print_timing: id 1 | task 3130 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 18.04.837.642 I slot print_timing: id 3 | task 3121 | n_gen = 115, tg = 4.16 t/s, tg_3s = 4.75 t/s 18.05.468.778 I slot print_timing: id 0 | task 2884 | n_gen = 352, tg = 4.27 t/s, tg_3s = 4.75 t/s 18.06.521.068 I slot print_timing: id 1 | task 3130 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 18.07.995.578 I slot print_timing: id 3 | task 3121 | n_gen = 130, tg = 4.22 t/s, tg_3s = 4.75 t/s 18.08.626.529 I slot print_timing: id 0 | task 2884 | n_gen = 367, tg = 4.29 t/s, tg_3s = 4.75 t/s 18.09.259.254 I slot print_timing: id 1 | task 3130 | prompt eval time = 2080.71 ms / 98 tokens ( 21.23 ms per token, 47.10 tokens per second) 18.09.259.260 I slot print_timing: id 1 | task 3130 | eval time = 28373.34 ms / 128 tokens ( 223.41 ms per token, 4.48 tokens per second) 18.09.259.261 I slot print_timing: id 1 | task 3130 | total time = 30454.05 ms / 226 tokens 18.09.259.261 I slot print_timing: id 1 | task 3130 | graphs reused = 2735 18.09.259.262 I slot print_timing: id 1 | task 3130 | graph reallocs = 0 / 0 (same size) / (changed size) 18.09.259.306 I slot release: id 1 | task 3130 | stop processing: n_tokens = 1350, truncated = 0 18.09.549.205 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.849 18.09.549.242 I slot launch_slot_: id 1 | task 3262 | processing task, is_child = 0 18.11.420.654 I slot print_timing: id 3 | task 3121 | n_gen = 138, tg = 4.03 t/s, tg_3s = 2.34 t/s 18.11.962.231 I slot print_timing: id 0 | task 2884 | n_gen = 373, tg = 4.19 t/s, tg_3s = 1.80 t/s 18.14.491.460 I slot print_timing: id 3 | task 3121 | n_gen = 151, tg = 4.05 t/s, tg_3s = 4.23 t/s 18.15.122.975 I slot print_timing: id 0 | task 2884 | n_gen = 388, tg = 4.21 t/s, tg_3s = 4.75 t/s 18.17.650.573 I slot print_timing: id 3 | task 3121 | n_gen = 166, tg = 4.11 t/s, tg_3s = 4.75 t/s 18.18.282.184 I slot print_timing: id 0 | task 2884 | n_gen = 403, tg = 4.23 t/s, tg_3s = 4.75 t/s 18.20.809.585 I slot print_timing: id 3 | task 3121 | n_gen = 181, tg = 4.15 t/s, tg_3s = 4.75 t/s 18.21.441.193 I slot print_timing: id 0 | task 2884 | n_gen = 418, tg = 4.25 t/s, tg_3s = 4.75 t/s 18.23.971.281 I slot print_timing: id 3 | task 3121 | n_gen = 196, tg = 4.19 t/s, tg_3s = 4.74 t/s 18.24.393.487 I slot print_timing: id 2 | task 3221 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 18.24.604.048 I slot print_timing: id 0 | task 2884 | n_gen = 433, tg = 4.26 t/s, tg_3s = 4.74 t/s 18.26.502.066 I slot print_timing: id 3 | task 3121 | prompt eval time = 2102.45 ms / 106 tokens ( 19.83 ms per token, 50.42 tokens per second) 18.26.502.070 I slot print_timing: id 3 | task 3121 | eval time = 49044.40 ms / 208 tokens ( 236.93 ms per token, 4.22 tokens per second) 18.26.502.070 I slot print_timing: id 3 | task 3121 | total time = 51146.86 ms / 314 tokens 18.26.502.071 I slot print_timing: id 3 | task 3121 | graphs reused = 2803 18.26.502.071 I slot print_timing: id 3 | task 3121 | graph reallocs = 0 / 0 (same size) / (changed size) 18.26.502.117 I slot release: id 3 | task 3121 | stop processing: n_tokens = 1438, truncated = 0 18.26.700.858 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.797 18.26.700.883 I slot launch_slot_: id 3 | task 3335 | processing task, is_child = 0 18.28.404.743 I slot print_timing: id 0 | task 2884 | n_gen = 444, tg = 4.21 t/s, tg_3s = 2.89 t/s 18.28.405.153 I slot print_timing: id 2 | task 3221 | n_gen = 112, tg = 4.12 t/s, tg_3s = 2.99 t/s 18.28.799.084 I slot print_timing: id 1 | task 3262 | prompt eval time = 2413.16 ms / 121 tokens ( 19.94 ms per token, 50.14 tokens per second) 18.28.799.090 I slot print_timing: id 1 | task 3262 | eval time = 16836.68 ms / 73 tokens ( 233.84 ms per token, 4.28 tokens per second) 18.28.799.090 I slot print_timing: id 1 | task 3262 | total time = 19249.84 ms / 194 tokens 18.28.799.091 I slot print_timing: id 1 | task 3262 | graphs reused = 2803 18.28.799.091 I slot print_timing: id 1 | task 3262 | graph reallocs = 0 / 0 (same size) / (changed size) 18.28.799.163 I slot release: id 1 | task 3262 | stop processing: n_tokens = 1318, truncated = 0 18.29.088.547 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.869 18.29.088.585 I slot launch_slot_: id 1 | task 3339 | processing task, is_child = 0 18.31.593.947 I slot print_timing: id 0 | task 2884 | n_gen = 450, tg = 4.14 t/s, tg_3s = 1.88 t/s 18.31.594.248 I slot print_timing: id 2 | task 3221 | n_gen = 118, tg = 3.88 t/s, tg_3s = 1.88 t/s 18.34.753.105 I slot print_timing: id 0 | task 2884 | n_gen = 465, tg = 4.16 t/s, tg_3s = 4.75 t/s 18.34.753.392 I slot print_timing: id 2 | task 3221 | n_gen = 133, tg = 3.97 t/s, tg_3s = 4.75 t/s 18.37.912.359 I slot print_timing: id 0 | task 2884 | n_gen = 480, tg = 4.18 t/s, tg_3s = 4.75 t/s 18.37.912.670 I slot print_timing: id 2 | task 3221 | n_gen = 148, tg = 4.03 t/s, tg_3s = 4.75 t/s 18.38.332.514 I slot print_timing: id 2 | task 3221 | prompt eval time = 1962.60 ms / 91 tokens ( 21.57 ms per token, 46.37 tokens per second) 18.38.332.520 I slot print_timing: id 2 | task 3221 | eval time = 36866.95 ms / 150 tokens ( 247.43 ms per token, 4.04 tokens per second) 18.38.332.521 I slot print_timing: id 2 | task 3221 | total time = 38829.54 ms / 241 tokens 18.38.332.522 I slot print_timing: id 2 | task 3221 | graphs reused = 2836 18.38.332.522 I slot print_timing: id 2 | task 3221 | graph reallocs = 0 / 0 (same size) / (changed size) 18.38.332.567 I slot release: id 2 | task 3221 | stop processing: n_tokens = 1365, truncated = 0 18.38.621.867 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.840 18.38.621.902 I slot launch_slot_: id 2 | task 3377 | processing task, is_child = 0 18.41.279.637 I slot print_timing: id 0 | task 2884 | n_gen = 485, tg = 4.10 t/s, tg_3s = 1.48 t/s 18.44.441.452 I slot print_timing: id 0 | task 2884 | n_gen = 500, tg = 4.12 t/s, tg_3s = 4.74 t/s 18.47.600.434 I slot print_timing: id 0 | task 2884 | n_gen = 515, tg = 4.13 t/s, tg_3s = 4.75 t/s 18.48.232.297 I slot print_timing: id 0 | task 2884 | prompt eval time = 2088.37 ms / 124 tokens ( 16.84 ms per token, 59.38 tokens per second) 18.48.232.299 I slot print_timing: id 0 | task 2884 | eval time = 125017.83 ms / 518 tokens ( 241.81 ms per token, 4.14 tokens per second) 18.48.232.300 I slot print_timing: id 0 | task 2884 | total time = 127106.20 ms / 642 tokens 18.48.232.300 I slot print_timing: id 0 | task 2884 | graphs reused = 2868 18.48.232.300 I slot print_timing: id 0 | task 2884 | graph reallocs = 0 / 0 (same size) / (changed size) 18.48.232.348 I slot release: id 0 | task 2884 | stop processing: n_tokens = 1766, truncated = 0 18.48.430.741 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.649 18.48.430.781 I slot launch_slot_: id 0 | task 3414 | processing task, is_child = 0 18.52.191.486 I slot print_timing: id 3 | task 3335 | prompt eval time = 2098.61 ms / 105 tokens ( 19.99 ms per token, 50.03 tokens per second) 18.52.191.489 I slot print_timing: id 3 | task 3335 | eval time = 23391.99 ms / 85 tokens ( 278.48 ms per token, 3.59 tokens per second) 18.52.191.490 I slot print_timing: id 3 | task 3335 | total time = 25490.60 ms / 190 tokens 18.52.191.491 I slot print_timing: id 3 | task 3335 | graphs reused = 2876 18.52.191.491 I slot print_timing: id 3 | task 3335 | graph reallocs = 0 / 0 (same size) / (changed size) 18.52.191.563 I slot release: id 3 | task 3335 | stop processing: n_tokens = 1314, truncated = 0 18.52.390.105 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.872 18.52.390.141 I slot launch_slot_: id 3 | task 3426 | processing task, is_child = 0 18.57.826.917 I slot print_timing: id 1 | task 3339 | prompt eval time = 2081.74 ms / 95 tokens ( 21.91 ms per token, 45.63 tokens per second) 18.57.826.922 I slot print_timing: id 1 | task 3339 | eval time = 26656.58 ms / 99 tokens ( 272.01 ms per token, 3.68 tokens per second) 18.57.826.923 I slot print_timing: id 1 | task 3339 | total time = 28738.32 ms / 194 tokens 18.57.826.923 I slot print_timing: id 1 | task 3339 | graphs reused = 2889 18.57.826.924 I slot print_timing: id 1 | task 3339 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.826.968 I slot release: id 1 | task 3339 | stop processing: n_tokens = 1318, truncated = 0 18.58.116.265 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.869 18.58.116.300 I slot launch_slot_: id 1 | task 3444 | processing task, is_child = 0 19.07.896.098 I slot print_timing: id 2 | task 3377 | n_gen = 100, tg = 3.72 t/s, tg_3s = 3.76 t/s 19.11.054.708 I slot print_timing: id 2 | task 3377 | n_gen = 115, tg = 3.83 t/s, tg_3s = 4.75 t/s 19.14.214.052 I slot print_timing: id 2 | task 3377 | n_gen = 130, tg = 3.92 t/s, tg_3s = 4.75 t/s 19.15.477.161 I slot print_timing: id 0 | task 3414 | n_gen = 100, tg = 3.96 t/s, tg_3s = 4.00 t/s 19.17.372.319 I slot print_timing: id 2 | task 3377 | n_gen = 145, tg = 3.99 t/s, tg_3s = 4.75 t/s 19.17.793.414 I slot print_timing: id 3 | task 3426 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 19.18.635.550 I slot print_timing: id 0 | task 3414 | n_gen = 115, tg = 4.05 t/s, tg_3s = 4.75 t/s 19.20.531.402 I slot print_timing: id 2 | task 3377 | n_gen = 160, tg = 4.05 t/s, tg_3s = 4.75 t/s 19.20.952.542 I slot print_timing: id 3 | task 3426 | n_gen = 115, tg = 4.37 t/s, tg_3s = 4.75 t/s 19.21.373.238 I slot print_timing: id 1 | task 3444 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 19.21.794.197 I slot print_timing: id 0 | task 3414 | n_gen = 130, tg = 4.12 t/s, tg_3s = 4.75 t/s 19.23.689.718 I slot print_timing: id 2 | task 3377 | n_gen = 175, tg = 4.10 t/s, tg_3s = 4.75 t/s 19.24.110.841 I slot print_timing: id 3 | task 3426 | n_gen = 130, tg = 4.41 t/s, tg_3s = 4.75 t/s 19.24.531.928 I slot print_timing: id 1 | task 3444 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 19.24.952.859 I slot print_timing: id 0 | task 3414 | n_gen = 145, tg = 4.18 t/s, tg_3s = 4.75 t/s 19.26.848.265 I slot print_timing: id 2 | task 3377 | n_gen = 190, tg = 4.15 t/s, tg_3s = 4.75 t/s 19.27.269.508 I slot print_timing: id 3 | task 3426 | n_gen = 145, tg = 4.45 t/s, tg_3s = 4.75 t/s 19.27.690.277 I slot print_timing: id 1 | task 3444 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 19.28.112.218 I slot print_timing: id 0 | task 3414 | n_gen = 160, tg = 4.23 t/s, tg_3s = 4.75 t/s 19.30.008.042 I slot print_timing: id 2 | task 3377 | n_gen = 205, tg = 4.19 t/s, tg_3s = 4.75 t/s 19.30.429.407 I slot print_timing: id 3 | task 3426 | n_gen = 160, tg = 4.47 t/s, tg_3s = 4.75 t/s 19.30.850.697 I slot print_timing: id 1 | task 3444 | n_gen = 145, tg = 4.75 t/s, tg_3s = 4.75 t/s 19.31.271.937 I slot print_timing: id 0 | task 3414 | n_gen = 175, tg = 4.27 t/s, tg_3s = 4.75 t/s 19.33.169.857 I slot print_timing: id 2 | task 3377 | n_gen = 220, tg = 4.22 t/s, tg_3s = 4.74 t/s 19.33.591.274 I slot print_timing: id 3 | task 3426 | n_gen = 175, tg = 4.49 t/s, tg_3s = 4.74 t/s 19.34.012.165 I slot print_timing: id 1 | task 3444 | n_gen = 160, tg = 4.75 t/s, tg_3s = 4.74 t/s 19.34.434.561 I slot print_timing: id 0 | task 3414 | n_gen = 190, tg = 4.30 t/s, tg_3s = 4.74 t/s 19.36.330.261 I slot print_timing: id 2 | task 3377 | n_gen = 235, tg = 4.25 t/s, tg_3s = 4.75 t/s 19.36.751.623 I slot print_timing: id 3 | task 3426 | n_gen = 190, tg = 4.51 t/s, tg_3s = 4.75 t/s 19.37.172.372 I slot print_timing: id 1 | task 3444 | n_gen = 175, tg = 4.75 t/s, tg_3s = 4.75 t/s 19.37.593.320 I slot print_timing: id 0 | task 3414 | n_gen = 205, tg = 4.33 t/s, tg_3s = 4.75 t/s 19.38.225.351 I slot print_timing: id 0 | task 3414 | prompt eval time = 2075.25 ms / 110 tokens ( 18.87 ms per token, 53.01 tokens per second) 19.38.225.357 I slot print_timing: id 0 | task 3414 | eval time = 47719.31 ms / 208 tokens ( 230.53 ms per token, 4.34 tokens per second) 19.38.225.357 I slot print_timing: id 0 | task 3414 | total time = 49794.56 ms / 318 tokens 19.38.225.358 I slot print_timing: id 0 | task 3414 | graphs reused = 3067 19.38.225.358 I slot print_timing: id 0 | task 3414 | graph reallocs = 0 / 0 (same size) / (changed size) 19.38.225.404 I slot release: id 0 | task 3414 | stop processing: n_tokens = 1442, truncated = 0 19.38.424.946 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.795 19.38.424.976 I slot launch_slot_: id 0 | task 3627 | processing task, is_child = 0 19.40.135.928 I slot print_timing: id 2 | task 3377 | n_gen = 246, tg = 4.16 t/s, tg_3s = 2.89 t/s 19.40.136.154 I slot print_timing: id 3 | task 3426 | n_gen = 199, tg = 4.37 t/s, tg_3s = 2.66 t/s 19.40.519.127 I slot print_timing: id 1 | task 3444 | n_gen = 183, tg = 4.55 t/s, tg_3s = 2.39 t/s 19.43.258.439 I slot print_timing: id 1 | task 3444 | prompt eval time = 2404.57 ms / 115 tokens ( 20.91 ms per token, 47.83 tokens per second) 19.43.258.442 I slot print_timing: id 1 | task 3444 | eval time = 42737.56 ms / 196 tokens ( 219.17 ms per token, 4.56 tokens per second) 19.43.258.442 I slot print_timing: id 1 | task 3444 | total time = 45142.13 ms / 311 tokens 19.43.258.443 I slot print_timing: id 1 | task 3444 | graphs reused = 3080 19.43.258.443 I slot print_timing: id 1 | task 3444 | graph reallocs = 0 / 0 (same size) / (changed size) 19.43.258.503 I slot release: id 1 | task 3444 | stop processing: n_tokens = 1435, truncated = 0 19.43.258.647 I slot print_timing: id 2 | task 3377 | n_gen = 260, tg = 4.18 t/s, tg_3s = 4.48 t/s 19.43.258.792 I slot print_timing: id 3 | task 3426 | n_gen = 213, tg = 4.38 t/s, tg_3s = 4.48 t/s 19.43.548.272 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.799 19.43.548.309 I slot launch_slot_: id 1 | task 3644 | processing task, is_child = 0 19.46.461.159 I slot print_timing: id 2 | task 3377 | n_gen = 267, tg = 4.08 t/s, tg_3s = 2.19 t/s 19.46.461.323 I slot print_timing: id 3 | task 3426 | n_gen = 220, tg = 4.25 t/s, tg_3s = 2.19 t/s 19.48.989.540 I slot print_timing: id 2 | task 3377 | prompt eval time = 2658.15 ms / 144 tokens ( 18.46 ms per token, 54.17 tokens per second) 19.48.989.543 I slot print_timing: id 2 | task 3377 | eval time = 67709.48 ms / 279 tokens ( 243.56 ms per token, 4.11 tokens per second) 19.48.989.544 I slot print_timing: id 2 | task 3377 | total time = 70367.63 ms / 423 tokens 19.48.989.544 I slot print_timing: id 2 | task 3377 | graphs reused = 3094 19.48.989.545 I slot print_timing: id 2 | task 3377 | graph reallocs = 0 / 0 (same size) / (changed size) 19.48.989.594 I slot release: id 2 | task 3377 | stop processing: n_tokens = 1547, truncated = 0 19.49.278.960 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.741 19.49.278.996 I slot launch_slot_: id 2 | task 3664 | processing task, is_child = 0 19.51.071.276 I slot print_timing: id 3 | task 3426 | n_gen = 234, tg = 4.15 t/s, tg_3s = 3.04 t/s 19.54.081.977 I slot print_timing: id 3 | task 3426 | n_gen = 247, tg = 4.16 t/s, tg_3s = 4.32 t/s 19.57.241.834 I slot print_timing: id 3 | task 3426 | n_gen = 262, tg = 4.19 t/s, tg_3s = 4.75 t/s 20.00.398.480 I slot print_timing: id 3 | task 3426 | n_gen = 277, tg = 4.21 t/s, tg_3s = 4.75 t/s 20.00.608.933 I slot print_timing: id 1 | task 3644 | prompt eval time = 2068.24 ms / 81 tokens ( 25.53 ms per token, 39.16 tokens per second) 20.00.608.934 I slot print_timing: id 1 | task 3644 | eval time = 14992.38 ms / 63 tokens ( 241.81 ms per token, 4.14 tokens per second) 20.00.608.935 I slot print_timing: id 1 | task 3644 | total time = 17060.62 ms / 144 tokens 20.00.608.935 I slot print_timing: id 1 | task 3644 | graphs reused = 3135 20.00.608.936 I slot print_timing: id 1 | task 3644 | graph reallocs = 0 / 0 (same size) / (changed size) 20.00.608.986 I slot release: id 1 | task 3644 | stop processing: n_tokens = 1268, truncated = 0 20.00.898.568 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.904 20.00.898.600 I slot launch_slot_: id 1 | task 3711 | processing task, is_child = 0 20.03.525.495 I slot print_timing: id 3 | task 3426 | n_gen = 282, tg = 4.09 t/s, tg_3s = 1.60 t/s 20.04.788.162 I slot print_timing: id 2 | task 3664 | prompt eval time = 2276.31 ms / 104 tokens ( 21.89 ms per token, 45.69 tokens per second) 20.04.788.165 I slot print_timing: id 2 | task 3664 | eval time = 13232.85 ms / 54 tokens ( 249.68 ms per token, 4.01 tokens per second) 20.04.788.166 I slot print_timing: id 2 | task 3664 | total time = 15509.16 ms / 158 tokens 20.04.788.167 I slot print_timing: id 2 | task 3664 | graphs reused = 3141 20.04.788.167 I slot print_timing: id 2 | task 3664 | graph reallocs = 0 / 0 (same size) / (changed size) 20.04.788.211 I slot release: id 2 | task 3664 | stop processing: n_tokens = 1282, truncated = 0 20.05.077.849 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.894 20.05.077.879 I slot launch_slot_: id 2 | task 3722 | processing task, is_child = 0 20.06.871.912 I slot print_timing: id 3 | task 3426 | n_gen = 290, tg = 4.01 t/s, tg_3s = 2.39 t/s 20.09.044.156 I slot print_timing: id 0 | task 3627 | n_gen = 100, tg = 3.47 t/s, tg_3s = 3.51 t/s 20.09.886.549 I slot print_timing: id 3 | task 3426 | n_gen = 303, tg = 4.03 t/s, tg_3s = 4.31 t/s 20.12.201.937 I slot print_timing: id 0 | task 3627 | n_gen = 115, tg = 3.60 t/s, tg_3s = 4.75 t/s 20.13.045.580 I slot print_timing: id 3 | task 3426 | n_gen = 318, tg = 4.06 t/s, tg_3s = 4.75 t/s 20.13.466.466 I slot print_timing: id 3 | task 3426 | prompt eval time = 2488.01 ms / 158 tokens ( 15.75 ms per token, 63.50 tokens per second) 20.13.466.469 I slot print_timing: id 3 | task 3426 | eval time = 78588.30 ms / 320 tokens ( 246.36 ms per token, 4.06 tokens per second) 20.13.466.470 I slot print_timing: id 3 | task 3426 | total time = 81076.31 ms / 478 tokens 20.13.466.470 I slot print_timing: id 3 | task 3426 | graphs reused = 3169 20.13.466.480 I slot print_timing: id 3 | task 3426 | graph reallocs = 0 / 0 (same size) / (changed size) 20.13.466.529 I slot release: id 3 | task 3426 | stop processing: n_tokens = 1602, truncated = 0 20.13.664.446 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.715 20.13.664.474 I slot launch_slot_: id 3 | task 3755 | processing task, is_child = 0 20.15.390.717 I slot print_timing: id 0 | task 3627 | n_gen = 123, tg = 3.50 t/s, tg_3s = 2.51 t/s 20.18.522.581 I slot print_timing: id 0 | task 3627 | n_gen = 137, tg = 3.58 t/s, tg_3s = 4.47 t/s 20.21.678.461 I slot print_timing: id 0 | task 3627 | n_gen = 152, tg = 3.67 t/s, tg_3s = 4.75 t/s 20.24.834.894 I slot print_timing: id 0 | task 3627 | n_gen = 167, tg = 3.75 t/s, tg_3s = 4.75 t/s 20.27.784.538 I slot print_timing: id 1 | task 3711 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 20.27.995.081 I slot print_timing: id 0 | task 3627 | n_gen = 182, tg = 3.81 t/s, tg_3s = 4.75 t/s 20.29.890.950 I slot print_timing: id 2 | task 3722 | n_gen = 100, tg = 4.39 t/s, tg_3s = 4.44 t/s 20.30.943.439 I slot print_timing: id 1 | task 3711 | n_gen = 115, tg = 4.13 t/s, tg_3s = 4.75 t/s 20.31.153.754 I slot print_timing: id 0 | task 3627 | n_gen = 197, tg = 3.87 t/s, tg_3s = 4.75 t/s 20.33.048.003 I slot print_timing: id 2 | task 3722 | n_gen = 115, tg = 4.44 t/s, tg_3s = 4.75 t/s 20.34.100.755 I slot print_timing: id 1 | task 3711 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.75 t/s 20.34.311.245 I slot print_timing: id 0 | task 3627 | n_gen = 212, tg = 3.92 t/s, tg_3s = 4.75 t/s 20.36.209.153 I slot print_timing: id 2 | task 3722 | n_gen = 130, tg = 4.47 t/s, tg_3s = 4.75 t/s 20.36.630.807 I slot print_timing: id 3 | task 3755 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 20.37.262.391 I slot print_timing: id 1 | task 3711 | n_gen = 145, tg = 4.24 t/s, tg_3s = 4.74 t/s 20.37.474.080 I slot print_timing: id 0 | task 3627 | n_gen = 227, tg = 3.97 t/s, tg_3s = 4.74 t/s 20.39.371.111 I slot print_timing: id 2 | task 3722 | n_gen = 145, tg = 4.50 t/s, tg_3s = 4.74 t/s 20.39.371.262 I slot print_timing: id 3 | task 3755 | prompt eval time = 2120.02 ms / 126 tokens ( 16.83 ms per token, 59.43 tokens per second) 20.39.371.263 I slot print_timing: id 3 | task 3755 | eval time = 23586.76 ms / 113 tokens ( 210.60 ms per token, 4.75 tokens per second) 20.39.371.264 I slot print_timing: id 3 | task 3755 | total time = 25706.78 ms / 239 tokens 20.39.371.264 I slot print_timing: id 3 | task 3755 | graphs reused = 3280 20.39.371.265 I slot print_timing: id 3 | task 3755 | graph reallocs = 0 / 0 (same size) / (changed size) 20.39.371.324 I slot release: id 3 | task 3755 | stop processing: n_tokens = 1363, truncated = 0 20.39.570.160 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.841 20.39.570.198 I slot launch_slot_: id 3 | task 3871 | processing task, is_child = 0 20.41.295.405 I slot print_timing: id 0 | task 3627 | n_gen = 238, tg = 3.90 t/s, tg_3s = 2.88 t/s 20.41.295.611 I slot print_timing: id 1 | task 3711 | n_gen = 157, tg = 4.11 t/s, tg_3s = 2.98 t/s 20.42.535.760 I slot print_timing: id 2 | task 3722 | n_gen = 152, tg = 4.29 t/s, tg_3s = 2.21 t/s 20.44.430.831 I slot print_timing: id 0 | task 3627 | n_gen = 252, tg = 3.93 t/s, tg_3s = 4.47 t/s 20.44.430.974 I slot print_timing: id 1 | task 3711 | n_gen = 171, tg = 4.13 t/s, tg_3s = 4.47 t/s 20.45.699.257 I slot print_timing: id 2 | task 3722 | n_gen = 167, tg = 4.33 t/s, tg_3s = 4.74 t/s 20.47.596.820 I slot print_timing: id 0 | task 3627 | n_gen = 267, tg = 3.97 t/s, tg_3s = 4.74 t/s 20.47.596.969 I slot print_timing: id 1 | task 3711 | n_gen = 186, tg = 4.18 t/s, tg_3s = 4.74 t/s 20.48.860.838 I slot print_timing: id 2 | task 3722 | n_gen = 182, tg = 4.36 t/s, tg_3s = 4.74 t/s 20.50.756.537 I slot print_timing: id 0 | task 3627 | n_gen = 282, tg = 4.00 t/s, tg_3s = 4.75 t/s 20.50.756.682 I slot print_timing: id 1 | task 3711 | n_gen = 201, tg = 4.22 t/s, tg_3s = 4.75 t/s 20.52.022.689 I slot print_timing: id 2 | task 3722 | n_gen = 197, tg = 4.39 t/s, tg_3s = 4.74 t/s 20.53.707.323 I slot print_timing: id 1 | task 3711 | prompt eval time = 2414.18 ms / 125 tokens ( 19.31 ms per token, 51.78 tokens per second) 20.53.707.329 I slot print_timing: id 1 | task 3711 | eval time = 50394.54 ms / 215 tokens ( 235.49 ms per token, 4.25 tokens per second) 20.53.707.329 I slot print_timing: id 1 | task 3711 | total time = 52808.72 ms / 340 tokens 20.53.707.330 I slot print_timing: id 1 | task 3711 | graphs reused = 3335 20.53.707.330 I slot print_timing: id 1 | task 3711 | graph reallocs = 0 / 0 (same size) / (changed size) 20.53.707.379 I slot release: id 1 | task 3711 | stop processing: n_tokens = 1464, truncated = 0 20.53.996.515 I slot print_timing: id 0 | task 3627 | n_gen = 297, tg = 4.03 t/s, tg_3s = 4.63 t/s 20.53.996.822 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.783 20.53.996.861 I slot launch_slot_: id 1 | task 3932 | processing task, is_child = 0 20.55.850.217 I slot print_timing: id 2 | task 3722 | n_gen = 207, tg = 4.25 t/s, tg_3s = 2.61 t/s 20.57.028.794 I slot print_timing: id 0 | task 3627 | n_gen = 302, tg = 3.93 t/s, tg_3s = 1.65 t/s 20.58.923.883 I slot print_timing: id 2 | task 3722 | n_gen = 220, tg = 4.25 t/s, tg_3s = 4.23 t/s 21.00.186.848 I slot print_timing: id 0 | task 3627 | n_gen = 317, tg = 3.97 t/s, tg_3s = 4.75 t/s 21.02.085.690 I slot print_timing: id 2 | task 3722 | n_gen = 235, tg = 4.28 t/s, tg_3s = 4.74 t/s 21.03.348.638 I slot print_timing: id 0 | task 3627 | n_gen = 332, tg = 4.00 t/s, tg_3s = 4.74 t/s 21.04.612.873 I slot print_timing: id 3 | task 3871 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 21.05.245.542 I slot print_timing: id 2 | task 3722 | n_gen = 250, tg = 4.30 t/s, tg_3s = 4.75 t/s 21.06.509.011 I slot print_timing: id 0 | task 3627 | n_gen = 347, tg = 4.02 t/s, tg_3s = 4.75 t/s 21.07.774.423 I slot print_timing: id 3 | task 3871 | n_gen = 115, tg = 4.37 t/s, tg_3s = 4.74 t/s 21.08.406.200 I slot print_timing: id 2 | task 3722 | n_gen = 265, tg = 4.32 t/s, tg_3s = 4.75 t/s 21.09.670.119 I slot print_timing: id 0 | task 3627 | n_gen = 362, tg = 4.05 t/s, tg_3s = 4.75 t/s 21.10.934.481 I slot print_timing: id 3 | task 3871 | n_gen = 130, tg = 4.41 t/s, tg_3s = 4.75 t/s 21.11.566.338 I slot print_timing: id 2 | task 3722 | n_gen = 280, tg = 4.35 t/s, tg_3s = 4.75 t/s 21.12.831.000 I slot print_timing: id 0 | task 3627 | n_gen = 377, tg = 4.07 t/s, tg_3s = 4.75 t/s 21.14.095.864 I slot print_timing: id 3 | task 3871 | n_gen = 145, tg = 4.44 t/s, tg_3s = 4.74 t/s 21.14.727.647 I slot print_timing: id 2 | task 3722 | n_gen = 295, tg = 4.36 t/s, tg_3s = 4.74 t/s 21.15.991.809 I slot print_timing: id 0 | task 3627 | n_gen = 392, tg = 4.10 t/s, tg_3s = 4.75 t/s 21.17.256.209 I slot print_timing: id 1 | task 3932 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 21.17.256.483 I slot print_timing: id 3 | task 3871 | n_gen = 160, tg = 4.47 t/s, tg_3s = 4.75 t/s 21.17.888.514 I slot print_timing: id 2 | task 3722 | n_gen = 310, tg = 4.38 t/s, tg_3s = 4.75 t/s 21.19.152.682 I slot print_timing: id 0 | task 3627 | n_gen = 407, tg = 4.12 t/s, tg_3s = 4.75 t/s 21.20.418.547 I slot print_timing: id 1 | task 3932 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.74 t/s 21.20.418.820 I slot print_timing: id 3 | task 3871 | n_gen = 175, tg = 4.49 t/s, tg_3s = 4.74 t/s 21.21.051.062 I slot print_timing: id 2 | task 3722 | n_gen = 325, tg = 4.40 t/s, tg_3s = 4.74 t/s 21.22.315.199 I slot print_timing: id 0 | task 3627 | n_gen = 422, tg = 4.14 t/s, tg_3s = 4.74 t/s 21.23.581.582 I slot print_timing: id 1 | task 3932 | n_gen = 130, tg = 4.74 t/s, tg_3s = 4.74 t/s 21.23.581.875 I slot print_timing: id 3 | task 3871 | n_gen = 190, tg = 4.51 t/s, tg_3s = 4.74 t/s 21.24.213.751 I slot print_timing: id 2 | task 3722 | n_gen = 340, tg = 4.41 t/s, tg_3s = 4.74 t/s 21.25.478.892 I slot print_timing: id 0 | task 3627 | n_gen = 437, tg = 4.15 t/s, tg_3s = 4.74 t/s 21.26.744.531 I slot print_timing: id 1 | task 3932 | n_gen = 145, tg = 4.74 t/s, tg_3s = 4.74 t/s 21.26.744.804 I slot print_timing: id 3 | task 3871 | n_gen = 205, tg = 4.53 t/s, tg_3s = 4.74 t/s 21.27.376.822 I slot print_timing: id 2 | task 3722 | n_gen = 355, tg = 4.42 t/s, tg_3s = 4.74 t/s 21.28.643.394 I slot print_timing: id 0 | task 3627 | n_gen = 452, tg = 4.17 t/s, tg_3s = 4.74 t/s 21.29.909.405 I slot print_timing: id 1 | task 3932 | n_gen = 160, tg = 4.74 t/s, tg_3s = 4.74 t/s 21.29.909.679 I slot print_timing: id 3 | task 3871 | n_gen = 220, tg = 4.54 t/s, tg_3s = 4.74 t/s 21.30.541.784 I slot print_timing: id 2 | task 3722 | n_gen = 370, tg = 4.44 t/s, tg_3s = 4.74 t/s 21.31.807.963 I slot print_timing: id 0 | task 3627 | n_gen = 467, tg = 4.19 t/s, tg_3s = 4.74 t/s 21.33.073.698 I slot print_timing: id 1 | task 3932 | n_gen = 175, tg = 4.74 t/s, tg_3s = 4.74 t/s 21.33.073.972 I slot print_timing: id 3 | task 3871 | n_gen = 235, tg = 4.55 t/s, tg_3s = 4.74 t/s 21.33.706.614 I slot print_timing: id 2 | task 3722 | n_gen = 385, tg = 4.45 t/s, tg_3s = 4.74 t/s 21.34.972.062 I slot print_timing: id 0 | task 3627 | n_gen = 482, tg = 4.20 t/s, tg_3s = 4.74 t/s 21.36.237.785 I slot print_timing: id 1 | task 3932 | n_gen = 190, tg = 4.74 t/s, tg_3s = 4.74 t/s 21.36.238.078 I slot print_timing: id 3 | task 3871 | n_gen = 250, tg = 4.56 t/s, tg_3s = 4.74 t/s 21.36.871.773 I slot print_timing: id 2 | task 3722 | n_gen = 400, tg = 4.46 t/s, tg_3s = 4.74 t/s 21.38.136.832 I slot print_timing: id 0 | task 3627 | n_gen = 497, tg = 4.22 t/s, tg_3s = 4.74 t/s 21.39.402.216 I slot print_timing: id 1 | task 3932 | n_gen = 205, tg = 4.74 t/s, tg_3s = 4.74 t/s 21.39.402.497 I slot print_timing: id 3 | task 3871 | n_gen = 265, tg = 4.57 t/s, tg_3s = 4.74 t/s 21.40.035.541 I slot print_timing: id 2 | task 3722 | n_gen = 415, tg = 4.47 t/s, tg_3s = 4.74 t/s 21.40.457.155 I slot print_timing: id 1 | task 3932 | prompt eval time = 2396.52 ms / 108 tokens ( 22.19 ms per token, 45.07 tokens per second) 21.40.457.160 I slot print_timing: id 1 | task 3932 | eval time = 44063.77 ms / 210 tokens ( 210.83 ms per token, 4.74 tokens per second) 21.40.457.160 I slot print_timing: id 1 | task 3932 | total time = 46460.29 ms / 318 tokens 21.40.457.161 I slot print_timing: id 1 | task 3932 | graphs reused = 3543 21.40.457.161 I slot print_timing: id 1 | task 3932 | graph reallocs = 0 / 0 (same size) / (changed size) 21.40.457.211 I slot release: id 1 | task 3932 | stop processing: n_tokens = 1442, truncated = 0 21.40.747.842 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.795 21.40.747.874 I slot launch_slot_: id 1 | task 4145 | processing task, is_child = 0 21.42.291.868 I slot print_timing: id 0 | task 3627 | n_gen = 510, tg = 4.18 t/s, tg_3s = 3.13 t/s 21.42.833.059 I slot print_timing: id 3 | task 3871 | n_gen = 273, tg = 4.45 t/s, tg_3s = 2.33 t/s 21.43.047.231 I slot print_timing: id 2 | task 3722 | n_gen = 421, tg = 4.39 t/s, tg_3s = 1.99 t/s 21.45.367.061 I slot print_timing: id 0 | task 3627 | n_gen = 523, tg = 4.18 t/s, tg_3s = 4.23 t/s 21.45.999.812 I slot print_timing: id 3 | task 3871 | n_gen = 288, tg = 4.46 t/s, tg_3s = 4.74 t/s 21.46.210.551 I slot print_timing: id 2 | task 3722 | n_gen = 436, tg = 4.40 t/s, tg_3s = 4.74 t/s 21.48.529.967 I slot print_timing: id 0 | task 3627 | n_gen = 538, tg = 4.19 t/s, tg_3s = 4.74 t/s 21.49.165.686 I slot print_timing: id 3 | task 3871 | n_gen = 303, tg = 4.48 t/s, tg_3s = 4.74 t/s 21.49.376.446 I slot print_timing: id 2 | task 3722 | n_gen = 451, tg = 4.41 t/s, tg_3s = 4.74 t/s 21.49.376.586 I slot print_timing: id 3 | task 3871 | prompt eval time = 2121.06 ms / 125 tokens ( 16.97 ms per token, 58.93 tokens per second) 21.49.376.593 I slot print_timing: id 3 | task 3871 | eval time = 67685.33 ms / 304 tokens ( 223.38 ms per token, 4.48 tokens per second) 21.49.376.593 I slot print_timing: id 3 | task 3871 | total time = 69806.38 ms / 429 tokens 21.49.376.594 I slot print_timing: id 3 | task 3871 | graphs reused = 3572 21.49.376.594 I slot print_timing: id 3 | task 3871 | graph reallocs = 0 / 0 (same size) / (changed size) 21.49.376.640 I slot release: id 3 | task 3871 | stop processing: n_tokens = 1553, truncated = 0 21.49.575.641 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.738 21.49.575.675 I slot launch_slot_: id 3 | task 4180 | processing task, is_child = 0 21.52.012.360 I slot print_timing: id 0 | task 3627 | n_gen = 544, tg = 4.13 t/s, tg_3s = 1.72 t/s 21.52.405.521 I slot print_timing: id 2 | task 3722 | n_gen = 454, tg = 4.31 t/s, tg_3s = 0.99 t/s 21.55.148.128 I slot print_timing: id 0 | task 3627 | n_gen = 558, tg = 4.14 t/s, tg_3s = 4.46 t/s 21.55.570.032 I slot print_timing: id 2 | task 3722 | n_gen = 469, tg = 4.32 t/s, tg_3s = 4.74 t/s 21.58.310.879 I slot print_timing: id 0 | task 3627 | n_gen = 573, tg = 4.15 t/s, tg_3s = 4.74 t/s 21.58.732.867 I slot print_timing: id 2 | task 3722 | n_gen = 484, tg = 4.34 t/s, tg_3s = 4.74 t/s 22.01.474.848 I slot print_timing: id 0 | task 3627 | n_gen = 588, tg = 4.16 t/s, tg_3s = 4.74 t/s 22.01.896.607 I slot print_timing: id 2 | task 3722 | n_gen = 499, tg = 4.35 t/s, tg_3s = 4.74 t/s 22.04.638.729 I slot print_timing: id 0 | task 3627 | n_gen = 603, tg = 4.18 t/s, tg_3s = 4.74 t/s 22.05.060.798 I slot print_timing: id 2 | task 3722 | n_gen = 514, tg = 4.36 t/s, tg_3s = 4.74 t/s 22.06.115.289 I slot print_timing: id 1 | task 4145 | n_gen = 100, tg = 4.25 t/s, tg_3s = 4.30 t/s 22.07.594.032 I slot print_timing: id 0 | task 3627 | prompt eval time = 2094.01 ms / 128 tokens ( 16.36 ms per token, 61.13 tokens per second) 22.07.594.034 I slot print_timing: id 0 | task 3627 | eval time = 147075.03 ms / 617 tokens ( 238.76 ms per token, 4.19 tokens per second) 22.07.594.035 I slot print_timing: id 0 | task 3627 | total time = 149169.04 ms / 745 tokens 22.07.594.035 I slot print_timing: id 0 | task 3627 | graphs reused = 3643 22.07.594.036 I slot print_timing: id 0 | task 3627 | graph reallocs = 0 / 0 (same size) / (changed size) 22.07.594.084 I slot release: id 0 | task 3627 | stop processing: n_tokens = 1869, truncated = 0 22.07.794.729 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.613 22.07.794.783 I slot launch_slot_: id 0 | task 4256 | processing task, is_child = 0 22.09.165.669 I slot print_timing: id 1 | task 4145 | n_gen = 109, tg = 4.10 t/s, tg_3s = 2.95 t/s 22.09.165.881 I slot print_timing: id 2 | task 3722 | n_gen = 528, tg = 4.33 t/s, tg_3s = 3.41 t/s 22.12.288.771 I slot print_timing: id 1 | task 4145 | n_gen = 123, tg = 4.14 t/s, tg_3s = 4.48 t/s 22.12.288.947 I slot print_timing: id 2 | task 3722 | n_gen = 542, tg = 4.33 t/s, tg_3s = 4.48 t/s 22.14.605.128 I slot print_timing: id 3 | task 4180 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 22.15.446.977 I slot print_timing: id 1 | task 4145 | n_gen = 138, tg = 4.20 t/s, tg_3s = 4.75 t/s 22.15.447.134 I slot print_timing: id 2 | task 3722 | n_gen = 557, tg = 4.34 t/s, tg_3s = 4.75 t/s 22.17.767.011 I slot print_timing: id 3 | task 4180 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.74 t/s 22.18.609.579 I slot print_timing: id 1 | task 4145 | n_gen = 153, tg = 4.25 t/s, tg_3s = 4.74 t/s 22.18.609.728 I slot print_timing: id 2 | task 3722 | n_gen = 572, tg = 4.35 t/s, tg_3s = 4.74 t/s 22.19.241.488 I slot print_timing: id 1 | task 4145 | prompt eval time = 2084.90 ms / 100 tokens ( 20.85 ms per token, 47.96 tokens per second) 22.19.241.491 I slot print_timing: id 1 | task 4145 | eval time = 36408.71 ms / 156 tokens ( 234.89 ms per token, 4.26 tokens per second) 22.19.241.491 I slot print_timing: id 1 | task 4145 | total time = 38493.61 ms / 256 tokens 22.19.241.492 I slot print_timing: id 1 | task 4145 | graphs reused = 3688 22.19.241.492 I slot print_timing: id 1 | task 4145 | graph reallocs = 0 / 0 (same size) / (changed size) 22.19.241.540 I slot release: id 1 | task 4145 | stop processing: n_tokens = 1380, truncated = 0 22.19.531.454 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.830 22.19.531.493 I slot launch_slot_: id 1 | task 4306 | processing task, is_child = 0 22.21.058.525 I slot print_timing: id 3 | task 4180 | n_gen = 124, tg = 4.29 t/s, tg_3s = 2.73 t/s 22.21.813.889 I slot print_timing: id 2 | task 3722 | n_gen = 579, tg = 4.30 t/s, tg_3s = 2.18 t/s 22.24.129.739 I slot print_timing: id 3 | task 4180 | n_gen = 137, tg = 4.29 t/s, tg_3s = 4.23 t/s 22.24.972.327 I slot print_timing: id 2 | task 3722 | n_gen = 594, tg = 4.31 t/s, tg_3s = 4.75 t/s 22.27.289.444 I slot print_timing: id 3 | task 4180 | n_gen = 152, tg = 4.33 t/s, tg_3s = 4.75 t/s 22.28.131.629 I slot print_timing: id 2 | task 3722 | n_gen = 609, tg = 4.32 t/s, tg_3s = 4.75 t/s 22.28.552.457 I slot print_timing: id 0 | task 4256 | prompt eval time = 1753.08 ms / 89 tokens ( 19.70 ms per token, 50.77 tokens per second) 22.28.552.462 I slot print_timing: id 0 | task 4256 | eval time = 19004.58 ms / 83 tokens ( 231.76 ms per token, 4.31 tokens per second) 22.28.552.462 I slot print_timing: id 0 | task 4256 | total time = 20757.66 ms / 172 tokens 22.28.552.463 I slot print_timing: id 0 | task 4256 | graphs reused = 3720 22.28.552.463 I slot print_timing: id 0 | task 4256 | graph reallocs = 0 / 0 (same size) / (changed size) 22.28.552.506 I slot release: id 0 | task 4256 | stop processing: n_tokens = 1296, truncated = 0 22.28.751.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.884 22.28.751.492 I slot launch_slot_: id 0 | task 4343 | processing task, is_child = 0 22.30.448.429 I slot print_timing: id 3 | task 4180 | n_gen = 160, tg = 4.18 t/s, tg_3s = 2.53 t/s 22.31.253.181 I slot print_timing: id 2 | task 3722 | n_gen = 616, tg = 4.27 t/s, tg_3s = 2.24 t/s 22.33.569.091 I slot print_timing: id 3 | task 4180 | n_gen = 174, tg = 4.20 t/s, tg_3s = 4.49 t/s 22.34.411.514 I slot print_timing: id 2 | task 3722 | n_gen = 631, tg = 4.28 t/s, tg_3s = 4.75 t/s 22.35.887.038 I slot print_timing: id 3 | task 4180 | prompt eval time = 2830.05 ms / 171 tokens ( 16.55 ms per token, 60.42 tokens per second) 22.35.887.044 I slot print_timing: id 3 | task 4180 | eval time = 43481.30 ms / 185 tokens ( 236.31 ms per token, 4.23 tokens per second) 22.35.887.045 I slot print_timing: id 3 | task 4180 | total time = 46311.35 ms / 356 tokens 22.35.887.046 I slot print_timing: id 3 | task 4180 | graphs reused = 3744 22.35.887.046 I slot print_timing: id 3 | task 4180 | graph reallocs = 0 / 0 (same size) / (changed size) 22.35.887.091 I slot release: id 3 | task 4180 | stop processing: n_tokens = 1480, truncated = 0 22.36.085.814 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.774 22.36.085.841 I slot launch_slot_: id 3 | task 4371 | processing task, is_child = 0 22.37.476.918 I slot print_timing: id 2 | task 3722 | n_gen = 640, tg = 4.26 t/s, tg_3s = 2.94 t/s 22.40.610.302 I slot print_timing: id 2 | task 3722 | n_gen = 654, tg = 4.26 t/s, tg_3s = 4.47 t/s 22.43.768.465 I slot print_timing: id 2 | task 3722 | n_gen = 669, tg = 4.27 t/s, tg_3s = 4.75 t/s 22.45.453.539 I slot print_timing: id 1 | task 4306 | n_gen = 100, tg = 4.15 t/s, tg_3s = 4.19 t/s 22.46.717.543 I slot print_timing: id 1 | task 4306 | prompt eval time = 2069.11 ms / 82 tokens ( 25.23 ms per token, 39.63 tokens per second) 22.46.717.548 I slot print_timing: id 1 | task 4306 | eval time = 25116.93 ms / 106 tokens ( 239.21 ms per token, 4.18 tokens per second) 22.46.717.549 I slot print_timing: id 1 | task 4306 | total time = 27186.04 ms / 188 tokens 22.46.717.549 I slot print_timing: id 1 | task 4306 | graphs reused = 3785 22.46.717.549 I slot print_timing: id 1 | task 4306 | graph reallocs = 0 / 0 (same size) / (changed size) 22.46.717.597 I slot release: id 1 | task 4306 | stop processing: n_tokens = 1312, truncated = 0 22.47.007.306 I slot print_timing: id 2 | task 3722 | n_gen = 684, tg = 4.28 t/s, tg_3s = 4.63 t/s 22.47.007.461 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.873 22.47.007.489 I slot launch_slot_: id 1 | task 4417 | processing task, is_child = 0 22.49.830.747 I slot print_timing: id 0 | task 4343 | prompt eval time = 2077.56 ms / 114 tokens ( 18.22 ms per token, 54.87 tokens per second) 22.49.830.752 I slot print_timing: id 0 | task 4343 | eval time = 19001.69 ms / 75 tokens ( 256.78 ms per token, 3.89 tokens per second) 22.49.830.752 I slot print_timing: id 0 | task 4343 | total time = 21079.25 ms / 189 tokens 22.49.830.753 I slot print_timing: id 0 | task 4343 | graphs reused = 3786 22.49.830.753 I slot print_timing: id 0 | task 4343 | graph reallocs = 0 / 0 (same size) / (changed size) 22.49.830.795 I slot release: id 0 | task 4343 | stop processing: n_tokens = 1313, truncated = 0 22.50.029.571 I slot print_timing: id 2 | task 3722 | n_gen = 689, tg = 4.23 t/s, tg_3s = 1.65 t/s 22.50.029.724 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.873 22.50.029.758 I slot launch_slot_: id 0 | task 4423 | processing task, is_child = 0 22.53.052.031 I slot print_timing: id 2 | task 3722 | n_gen = 697, tg = 4.20 t/s, tg_3s = 2.65 t/s 22.56.210.241 I slot print_timing: id 2 | task 3722 | n_gen = 712, tg = 4.21 t/s, tg_3s = 4.75 t/s 22.58.105.976 I slot print_timing: id 3 | task 4371 | prompt eval time = 1785.76 ms / 98 tokens ( 18.22 ms per token, 54.88 tokens per second) 22.58.105.979 I slot print_timing: id 3 | task 4371 | eval time = 20234.37 ms / 81 tokens ( 252.93 ms per token, 3.95 tokens per second) 22.58.105.979 I slot print_timing: id 3 | task 4371 | total time = 22020.13 ms / 179 tokens 22.58.105.980 I slot print_timing: id 3 | task 4371 | graphs reused = 3816 22.58.105.980 I slot print_timing: id 3 | task 4371 | graph reallocs = 0 / 0 (same size) / (changed size) 22.58.106.026 I slot release: id 3 | task 4371 | stop processing: n_tokens = 1303, truncated = 0 22.58.304.766 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.880 22.58.304.799 I slot launch_slot_: id 3 | task 4457 | processing task, is_child = 0 23.00.015.290 I slot print_timing: id 2 | task 3722 | n_gen = 723, tg = 4.18 t/s, tg_3s = 2.89 t/s 23.03.149.542 I slot print_timing: id 2 | task 3722 | n_gen = 737, tg = 4.19 t/s, tg_3s = 4.47 t/s 23.06.308.581 I slot print_timing: id 2 | task 3722 | n_gen = 752, tg = 4.20 t/s, tg_3s = 4.75 t/s 23.09.467.894 I slot print_timing: id 2 | task 3722 | n_gen = 767, tg = 4.21 t/s, tg_3s = 4.75 t/s 23.12.629.210 I slot print_timing: id 2 | task 3722 | n_gen = 782, tg = 4.22 t/s, tg_3s = 4.74 t/s 23.13.261.531 I slot print_timing: id 1 | task 4417 | n_gen = 100, tg = 4.15 t/s, tg_3s = 4.19 t/s 23.14.314.584 I slot print_timing: id 0 | task 4423 | n_gen = 100, tg = 4.39 t/s, tg_3s = 4.44 t/s 23.15.789.747 I slot print_timing: id 2 | task 3722 | n_gen = 797, tg = 4.22 t/s, tg_3s = 4.75 t/s 23.16.422.025 I slot print_timing: id 1 | task 4417 | n_gen = 115, tg = 4.22 t/s, tg_3s = 4.75 t/s 23.17.475.910 I slot print_timing: id 0 | task 4423 | n_gen = 115, tg = 4.44 t/s, tg_3s = 4.74 t/s 23.18.952.290 I slot print_timing: id 2 | task 3722 | n_gen = 812, tg = 4.23 t/s, tg_3s = 4.74 t/s 23.19.585.012 I slot print_timing: id 1 | task 4417 | n_gen = 130, tg = 4.27 t/s, tg_3s = 4.74 t/s 23.20.641.054 I slot print_timing: id 0 | task 4423 | n_gen = 130, tg = 4.47 t/s, tg_3s = 4.74 t/s 23.21.281.441 I slot print_timing: id 3 | task 4457 | n_gen = 100, tg = 4.74 t/s, tg_3s = 4.79 t/s 23.22.128.024 I slot print_timing: id 2 | task 3722 | n_gen = 827, tg = 4.24 t/s, tg_3s = 4.72 t/s 23.22.762.919 I slot print_timing: id 1 | task 4417 | n_gen = 145, tg = 4.32 t/s, tg_3s = 4.72 t/s 23.23.821.166 I slot print_timing: id 0 | task 4423 | n_gen = 145, tg = 4.50 t/s, tg_3s = 4.72 t/s 23.24.456.534 I slot print_timing: id 3 | task 4457 | n_gen = 115, tg = 4.74 t/s, tg_3s = 4.72 t/s 23.25.304.324 I slot print_timing: id 2 | task 3722 | n_gen = 842, tg = 4.25 t/s, tg_3s = 4.72 t/s 23.25.939.376 I slot print_timing: id 1 | task 4417 | n_gen = 160, tg = 4.35 t/s, tg_3s = 4.72 t/s 23.26.998.165 I slot print_timing: id 0 | task 4423 | n_gen = 160, tg = 4.52 t/s, tg_3s = 4.72 t/s 23.27.633.071 I slot print_timing: id 3 | task 4457 | n_gen = 130, tg = 4.74 t/s, tg_3s = 4.72 t/s 23.28.479.566 I slot print_timing: id 2 | task 3722 | n_gen = 857, tg = 4.26 t/s, tg_3s = 4.72 t/s 23.29.114.354 I slot print_timing: id 1 | task 4417 | n_gen = 175, tg = 4.38 t/s, tg_3s = 4.72 t/s 23.30.172.677 I slot print_timing: id 0 | task 4423 | n_gen = 175, tg = 4.53 t/s, tg_3s = 4.73 t/s 23.30.807.571 I slot print_timing: id 3 | task 4457 | n_gen = 145, tg = 4.74 t/s, tg_3s = 4.73 t/s 23.31.653.820 I slot print_timing: id 2 | task 3722 | n_gen = 872, tg = 4.26 t/s, tg_3s = 4.73 t/s 23.32.288.622 I slot print_timing: id 1 | task 4417 | n_gen = 190, tg = 4.41 t/s, tg_3s = 4.73 t/s 23.33.346.701 I slot print_timing: id 0 | task 4423 | n_gen = 190, tg = 4.55 t/s, tg_3s = 4.73 t/s 23.33.982.242 I slot print_timing: id 3 | task 4457 | n_gen = 160, tg = 4.74 t/s, tg_3s = 4.72 t/s 23.34.828.564 I slot print_timing: id 2 | task 3722 | n_gen = 887, tg = 4.27 t/s, tg_3s = 4.72 t/s 23.35.463.577 I slot print_timing: id 1 | task 4417 | n_gen = 205, tg = 4.43 t/s, tg_3s = 4.72 t/s 23.36.521.942 I slot print_timing: id 0 | task 4423 | n_gen = 205, tg = 4.56 t/s, tg_3s = 4.72 t/s 23.37.157.517 I slot print_timing: id 3 | task 4457 | n_gen = 175, tg = 4.73 t/s, tg_3s = 4.72 t/s 23.38.004.118 I slot print_timing: id 2 | task 3722 | n_gen = 902, tg = 4.28 t/s, tg_3s = 4.72 t/s 23.38.638.453 I slot print_timing: id 1 | task 4417 | n_gen = 220, tg = 4.45 t/s, tg_3s = 4.72 t/s 23.39.696.575 I slot print_timing: id 0 | task 4423 | n_gen = 220, tg = 4.57 t/s, tg_3s = 4.72 t/s 23.40.333.079 I slot print_timing: id 3 | task 4457 | n_gen = 190, tg = 4.73 t/s, tg_3s = 4.72 t/s 23.41.180.435 I slot print_timing: id 2 | task 3722 | n_gen = 917, tg = 4.28 t/s, tg_3s = 4.72 t/s 23.41.814.949 I slot print_timing: id 1 | task 4417 | n_gen = 235, tg = 4.46 t/s, tg_3s = 4.72 t/s 23.42.873.787 I slot print_timing: id 0 | task 4423 | n_gen = 235, tg = 4.58 t/s, tg_3s = 4.72 t/s 23.43.510.259 I slot print_timing: id 3 | task 4457 | n_gen = 205, tg = 4.73 t/s, tg_3s = 4.72 t/s 23.44.357.222 I slot print_timing: id 2 | task 3722 | n_gen = 932, tg = 4.29 t/s, tg_3s = 4.72 t/s 23.44.991.976 I slot print_timing: id 1 | task 4417 | n_gen = 250, tg = 4.48 t/s, tg_3s = 4.72 t/s 23.46.048.786 I slot print_timing: id 0 | task 4423 | n_gen = 250, tg = 4.59 t/s, tg_3s = 4.72 t/s 23.46.684.955 I slot print_timing: id 3 | task 4457 | n_gen = 220, tg = 4.73 t/s, tg_3s = 4.72 t/s 23.47.532.007 I slot print_timing: id 2 | task 3722 | n_gen = 947, tg = 4.30 t/s, tg_3s = 4.72 t/s 23.48.167.962 I slot print_timing: id 1 | task 4417 | n_gen = 265, tg = 4.49 t/s, tg_3s = 4.72 t/s 23.49.227.399 I slot print_timing: id 0 | task 4423 | n_gen = 265, tg = 4.60 t/s, tg_3s = 4.72 t/s 23.49.863.174 I slot print_timing: id 3 | task 4457 | n_gen = 235, tg = 4.73 t/s, tg_3s = 4.72 t/s 23.50.710.069 I slot print_timing: id 2 | task 3722 | n_gen = 962, tg = 4.30 t/s, tg_3s = 4.72 t/s 23.51.133.486 I slot print_timing: id 3 | task 4457 | prompt eval time = 2104.04 ms / 113 tokens ( 18.62 ms per token, 53.71 tokens per second) 23.51.133.489 I slot print_timing: id 3 | task 4457 | eval time = 50724.64 ms / 241 tokens ( 211.35 ms per token, 4.73 tokens per second) 23.51.133.489 I slot print_timing: id 3 | task 4457 | total time = 52828.68 ms / 354 tokens 23.51.133.490 I slot print_timing: id 3 | task 4457 | graphs reused = 4054 23.51.133.490 I slot print_timing: id 3 | task 4457 | graph reallocs = 0 / 0 (same size) / (changed size) 23.51.133.536 I slot release: id 3 | task 4457 | stop processing: n_tokens = 1478, truncated = 0 23.51.332.990 I slot print_timing: id 1 | task 4417 | n_gen = 280, tg = 4.51 t/s, tg_3s = 4.74 t/s 23.51.333.148 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.775 23.51.333.178 I slot launch_slot_: id 3 | task 4701 | processing task, is_child = 0 23.53.084.201 I slot print_timing: id 0 | task 4423 | n_gen = 276, tg = 4.49 t/s, tg_3s = 2.85 t/s 23.53.908.193 I slot print_timing: id 2 | task 3722 | n_gen = 969, tg = 4.27 t/s, tg_3s = 2.19 t/s 23.54.542.895 I slot print_timing: id 1 | task 4417 | n_gen = 287, tg = 4.39 t/s, tg_3s = 2.18 t/s 23.56.237.283 I slot print_timing: id 0 | task 4423 | n_gen = 290, tg = 4.48 t/s, tg_3s = 4.44 t/s 23.57.085.864 I slot print_timing: id 2 | task 3722 | n_gen = 984, tg = 4.28 t/s, tg_3s = 4.72 t/s 23.57.720.897 I slot print_timing: id 1 | task 4417 | n_gen = 302, tg = 4.41 t/s, tg_3s = 4.72 t/s 23.59.413.705 I slot print_timing: id 0 | task 4423 | n_gen = 305, tg = 4.50 t/s, tg_3s = 4.72 t/s 24.00.262.042 I slot print_timing: id 2 | task 3722 | n_gen = 999, tg = 4.28 t/s, tg_3s = 4.72 t/s 24.00.897.081 I slot print_timing: id 1 | task 4417 | n_gen = 317, tg = 4.42 t/s, tg_3s = 4.72 t/s 24.02.590.914 I slot print_timing: id 0 | task 4423 | n_gen = 320, tg = 4.51 t/s, tg_3s = 4.72 t/s 24.03.438.788 I slot print_timing: id 2 | task 3722 | n_gen = 1014, tg = 4.29 t/s, tg_3s = 4.72 t/s 24.04.074.225 I slot print_timing: id 1 | task 4417 | n_gen = 332, tg = 4.43 t/s, tg_3s = 4.72 t/s 24.04.286.146 I slot print_timing: id 1 | task 4417 | prompt eval time = 2399.63 ms / 109 tokens ( 22.01 ms per token, 45.42 tokens per second) 24.04.286.148 I slot print_timing: id 1 | task 4417 | eval time = 74879.02 ms / 333 tokens ( 225.54 ms per token, 4.43 tokens per second) 24.04.286.149 I slot print_timing: id 1 | task 4417 | total time = 77278.65 ms / 442 tokens 24.04.286.149 I slot print_timing: id 1 | task 4417 | graphs reused = 4104 24.04.286.150 I slot print_timing: id 1 | task 4417 | graph reallocs = 0 / 0 (same size) / (changed size) 24.04.286.197 I slot release: id 1 | task 4417 | stop processing: n_tokens = 1566, truncated = 0 24.04.576.157 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.732 24.04.576.198 I slot launch_slot_: id 1 | task 4756 | processing task, is_child = 0 24.06.800.356 I slot print_timing: id 0 | task 4423 | n_gen = 330, tg = 4.39 t/s, tg_3s = 2.38 t/s 24.06.800.511 I slot print_timing: id 2 | task 3722 | n_gen = 1020, tg = 4.26 t/s, tg_3s = 1.78 t/s 24.07.980.744 I slot print_timing: id 2 | task 3722 | prompt eval time = 2278.18 ms / 103 tokens ( 22.12 ms per token, 45.21 tokens per second) 24.07.980.749 I slot print_timing: id 2 | task 3722 | eval time = 240624.67 ms / 1024 tokens ( 235.21 ms per token, 4.25 tokens per second) 24.07.980.749 I slot print_timing: id 2 | task 3722 | total time = 242902.86 ms / 1127 tokens 24.07.980.750 I slot print_timing: id 2 | task 3722 | graphs reused = 4106 24.07.980.750 I slot print_timing: id 2 | task 3722 | graph reallocs = 0 / 0 (same size) / (changed size) 24.07.980.792 I slot release: id 2 | task 3722 | stop processing: n_tokens = 2251, truncated = 0 24.08.270.166 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.509 24.08.270.202 I slot launch_slot_: id 2 | task 4763 | processing task, is_child = 0 24.10.069.927 I slot print_timing: id 0 | task 4423 | n_gen = 336, tg = 4.28 t/s, tg_3s = 1.84 t/s 24.12.240.176 I slot print_timing: id 0 | task 4423 | prompt eval time = 1755.89 ms / 97 tokens ( 18.10 ms per token, 55.24 tokens per second) 24.12.240.181 I slot print_timing: id 0 | task 4423 | eval time = 80454.52 ms / 345 tokens ( 233.88 ms per token, 4.28 tokens per second) 24.12.240.182 I slot print_timing: id 0 | task 4423 | total time = 82210.41 ms / 442 tokens 24.12.240.182 I slot print_timing: id 0 | task 4423 | graphs reused = 4113 24.12.240.182 I slot print_timing: id 0 | task 4423 | graph reallocs = 0 / 0 (same size) / (changed size) 24.12.240.230 I slot release: id 0 | task 4423 | stop processing: n_tokens = 1566, truncated = 0 24.12.439.007 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.732 24.12.439.038 I slot launch_slot_: id 0 | task 4775 | processing task, is_child = 0 24.20.404.862 I slot print_timing: id 3 | task 4701 | n_gen = 100, tg = 3.68 t/s, tg_3s = 3.71 t/s 24.23.557.498 I slot print_timing: id 3 | task 4701 | n_gen = 115, tg = 3.79 t/s, tg_3s = 4.76 t/s 24.26.712.260 I slot print_timing: id 3 | task 4701 | n_gen = 130, tg = 3.88 t/s, tg_3s = 4.75 t/s 24.29.869.852 I slot print_timing: id 3 | task 4701 | n_gen = 145, tg = 3.96 t/s, tg_3s = 4.75 t/s 24.31.765.044 I slot print_timing: id 1 | task 4756 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 24.33.028.161 I slot print_timing: id 2 | task 4763 | n_gen = 100, tg = 4.41 t/s, tg_3s = 4.45 t/s 24.33.028.316 I slot print_timing: id 3 | task 4701 | n_gen = 160, tg = 4.02 t/s, tg_3s = 4.75 t/s 24.34.922.915 I slot print_timing: id 1 | task 4756 | n_gen = 115, tg = 4.13 t/s, tg_3s = 4.75 t/s 24.35.343.870 I slot print_timing: id 0 | task 4775 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 24.36.185.066 I slot print_timing: id 2 | task 4763 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 24.36.185.217 I slot print_timing: id 3 | task 4701 | n_gen = 175, tg = 4.07 t/s, tg_3s = 4.75 t/s 24.38.078.709 I slot print_timing: id 1 | task 4756 | n_gen = 130, tg = 4.20 t/s, tg_3s = 4.75 t/s 24.38.499.456 I slot print_timing: id 0 | task 4775 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 24.39.341.878 I slot print_timing: id 2 | task 4763 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.75 t/s 24.39.342.025 I slot print_timing: id 3 | task 4701 | n_gen = 190, tg = 4.12 t/s, tg_3s = 4.75 t/s 24.41.235.702 I slot print_timing: id 1 | task 4756 | n_gen = 145, tg = 4.25 t/s, tg_3s = 4.75 t/s 24.41.656.767 I slot print_timing: id 0 | task 4775 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 24.42.499.261 I slot print_timing: id 2 | task 4763 | n_gen = 145, tg = 4.51 t/s, tg_3s = 4.75 t/s 24.42.499.430 I slot print_timing: id 3 | task 4701 | n_gen = 205, tg = 4.16 t/s, tg_3s = 4.75 t/s 24.44.394.503 I slot print_timing: id 1 | task 4756 | n_gen = 160, tg = 4.29 t/s, tg_3s = 4.75 t/s 24.44.815.303 I slot print_timing: id 0 | task 4775 | n_gen = 145, tg = 4.75 t/s, tg_3s = 4.75 t/s 24.45.658.926 I slot print_timing: id 2 | task 4763 | n_gen = 160, tg = 4.53 t/s, tg_3s = 4.75 t/s 24.45.659.085 I slot print_timing: id 3 | task 4701 | n_gen = 220, tg = 4.20 t/s, tg_3s = 4.75 t/s 24.47.553.992 I slot print_timing: id 1 | task 4756 | n_gen = 175, tg = 4.33 t/s, tg_3s = 4.75 t/s 24.47.975.302 I slot print_timing: id 0 | task 4775 | n_gen = 160, tg = 4.75 t/s, tg_3s = 4.75 t/s 24.48.817.975 I slot print_timing: id 2 | task 4763 | n_gen = 175, tg = 4.55 t/s, tg_3s = 4.75 t/s 24.48.818.128 I slot print_timing: id 3 | task 4701 | n_gen = 235, tg = 4.23 t/s, tg_3s = 4.75 t/s 24.50.712.242 I slot print_timing: id 1 | task 4756 | n_gen = 190, tg = 4.36 t/s, tg_3s = 4.75 t/s 24.51.133.254 I slot print_timing: id 0 | task 4775 | n_gen = 175, tg = 4.75 t/s, tg_3s = 4.75 t/s 24.51.764.695 I slot print_timing: id 0 | task 4775 | prompt eval time = 2071.89 ms / 109 tokens ( 19.01 ms per token, 52.61 tokens per second) 24.51.764.700 I slot print_timing: id 0 | task 4775 | eval time = 37253.75 ms / 178 tokens ( 210.47 ms per token, 4.75 tokens per second) 24.51.764.700 I slot print_timing: id 0 | task 4775 | total time = 39325.65 ms / 287 tokens 24.51.764.701 I slot print_timing: id 0 | task 4775 | graphs reused = 4290 24.51.764.701 I slot print_timing: id 0 | task 4775 | graph reallocs = 0 / 0 (same size) / (changed size) 24.51.764.743 I slot release: id 0 | task 4775 | stop processing: n_tokens = 1411, truncated = 0 24.51.963.921 I slot print_timing: id 2 | task 4763 | n_gen = 190, tg = 4.56 t/s, tg_3s = 4.77 t/s 24.51.964.074 I slot print_timing: id 3 | task 4701 | n_gen = 250, tg = 4.26 t/s, tg_3s = 4.77 t/s 24.51.964.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.812 24.51.964.102 I slot launch_slot_: id 0 | task 4956 | processing task, is_child = 0 24.53.718.045 I slot print_timing: id 1 | task 4756 | n_gen = 198, tg = 4.25 t/s, tg_3s = 2.66 t/s 24.54.984.007 I slot print_timing: id 2 | task 4763 | n_gen = 198, tg = 4.43 t/s, tg_3s = 2.65 t/s 24.54.984.166 I slot print_timing: id 3 | task 4701 | n_gen = 258, tg = 4.18 t/s, tg_3s = 2.65 t/s 24.56.878.229 I slot print_timing: id 1 | task 4756 | n_gen = 213, tg = 4.28 t/s, tg_3s = 4.75 t/s 24.58.140.145 I slot print_timing: id 2 | task 4763 | n_gen = 213, tg = 4.46 t/s, tg_3s = 4.75 t/s 24.58.140.295 I slot print_timing: id 3 | task 4701 | n_gen = 273, tg = 4.21 t/s, tg_3s = 4.75 t/s 25.00.036.383 I slot print_timing: id 1 | task 4756 | n_gen = 228, tg = 4.31 t/s, tg_3s = 4.75 t/s 25.01.300.996 I slot print_timing: id 2 | task 4763 | n_gen = 228, tg = 4.47 t/s, tg_3s = 4.75 t/s 25.01.301.138 I slot print_timing: id 3 | task 4701 | n_gen = 288, tg = 4.23 t/s, tg_3s = 4.75 t/s 25.02.988.431 I slot print_timing: id 3 | task 4701 | prompt eval time = 2148.16 ms / 119 tokens ( 18.05 ms per token, 55.40 tokens per second) 25.02.988.437 I slot print_timing: id 3 | task 4701 | eval time = 69507.08 ms / 296 tokens ( 235.62 ms per token, 4.24 tokens per second) 25.02.988.438 I slot print_timing: id 3 | task 4701 | total time = 71655.24 ms / 415 tokens 25.02.988.438 I slot print_timing: id 3 | task 4701 | graphs reused = 4333 25.02.988.439 I slot print_timing: id 3 | task 4701 | graph reallocs = 0 / 0 (same size) / (changed size) 25.02.988.489 I slot release: id 3 | task 4701 | stop processing: n_tokens = 1539, truncated = 0 25.03.186.505 I slot print_timing: id 1 | task 4756 | n_gen = 243, tg = 4.33 t/s, tg_3s = 4.76 t/s 25.03.186.666 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.745 25.03.186.695 I slot launch_slot_: id 3 | task 5004 | processing task, is_child = 0 25.04.576.296 I slot print_timing: id 2 | task 4763 | n_gen = 238, tg = 4.39 t/s, tg_3s = 3.05 t/s 25.06.235.743 I slot print_timing: id 1 | task 4756 | n_gen = 251, tg = 4.25 t/s, tg_3s = 2.62 t/s 25.07.709.353 I slot print_timing: id 2 | task 4763 | n_gen = 252, tg = 4.39 t/s, tg_3s = 4.47 t/s 25.09.393.738 I slot print_timing: id 1 | task 4756 | n_gen = 266, tg = 4.27 t/s, tg_3s = 4.75 t/s 25.10.867.062 I slot print_timing: id 2 | task 4763 | n_gen = 267, tg = 4.41 t/s, tg_3s = 4.75 t/s 25.12.554.486 I slot print_timing: id 1 | task 4756 | n_gen = 281, tg = 4.29 t/s, tg_3s = 4.75 t/s 25.14.028.718 I slot print_timing: id 2 | task 4763 | n_gen = 282, tg = 4.43 t/s, tg_3s = 4.74 t/s 25.15.712.042 I slot print_timing: id 1 | task 4756 | n_gen = 296, tg = 4.31 t/s, tg_3s = 4.75 t/s 25.15.922.483 I slot print_timing: id 0 | task 4956 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.50 t/s 25.17.186.485 I slot print_timing: id 2 | task 4763 | n_gen = 297, tg = 4.44 t/s, tg_3s = 4.75 t/s 25.18.872.957 I slot print_timing: id 1 | task 4756 | n_gen = 311, tg = 4.33 t/s, tg_3s = 4.75 t/s 25.19.083.330 I slot print_timing: id 0 | task 4956 | n_gen = 115, tg = 4.49 t/s, tg_3s = 4.75 t/s 25.20.347.936 I slot print_timing: id 2 | task 4763 | n_gen = 312, tg = 4.46 t/s, tg_3s = 4.74 t/s 25.22.034.585 I slot print_timing: id 1 | task 4756 | n_gen = 326, tg = 4.35 t/s, tg_3s = 4.74 t/s 25.22.245.041 I slot print_timing: id 0 | task 4956 | n_gen = 130, tg = 4.52 t/s, tg_3s = 4.74 t/s 25.23.508.807 I slot print_timing: id 2 | task 4763 | n_gen = 327, tg = 4.47 t/s, tg_3s = 4.75 t/s 25.24.140.882 I slot print_timing: id 0 | task 4956 | prompt eval time = 1753.80 ms / 95 tokens ( 18.46 ms per token, 54.17 tokens per second) 25.24.140.889 I slot print_timing: id 0 | task 4956 | eval time = 30422.98 ms / 139 tokens ( 220.46 ms per token, 4.54 tokens per second) 25.24.140.890 I slot print_timing: id 0 | task 4956 | total time = 32176.77 ms / 234 tokens 25.24.140.890 I slot print_timing: id 0 | task 4956 | graphs reused = 4422 25.24.140.890 I slot print_timing: id 0 | task 4956 | graph reallocs = 0 / 0 (same size) / (changed size) 25.24.140.935 I slot release: id 0 | task 4956 | stop processing: n_tokens = 1358, truncated = 0 25.24.339.691 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.844 25.24.339.724 I slot launch_slot_: id 0 | task 5099 | processing task, is_child = 0 25.26.044.188 I slot print_timing: id 1 | task 4756 | n_gen = 338, tg = 4.28 t/s, tg_3s = 2.99 t/s 25.26.639.538 I slot print_timing: id 2 | task 4763 | n_gen = 334, tg = 4.38 t/s, tg_3s = 2.24 t/s 25.27.482.235 I slot print_timing: id 3 | task 5004 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.44 t/s 25.28.535.846 I slot print_timing: id 1 | task 4756 | prompt eval time = 2766.84 ms / 134 tokens ( 20.65 ms per token, 48.43 tokens per second) 25.28.535.851 I slot print_timing: id 1 | task 4756 | eval time = 81192.81 ms / 349 tokens ( 233.31 ms per token, 4.29 tokens per second) 25.28.535.852 I slot print_timing: id 1 | task 4756 | total time = 83959.64 ms / 483 tokens 25.28.535.852 I slot print_timing: id 1 | task 4756 | graphs reused = 4432 25.28.535.853 I slot print_timing: id 1 | task 4756 | graph reallocs = 0 / 0 (same size) / (changed size) 25.28.535.904 I slot release: id 1 | task 4756 | stop processing: n_tokens = 1607, truncated = 0 25.28.826.333 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.713 25.28.826.426 I slot launch_slot_: id 1 | task 5113 | processing task, is_child = 0 25.31.418.726 I slot print_timing: id 2 | task 4763 | n_gen = 345, tg = 4.25 t/s, tg_3s = 2.30 t/s 25.31.418.903 I slot print_timing: id 3 | task 5004 | n_gen = 107, tg = 4.01 t/s, tg_3s = 1.78 t/s 25.32.805.468 I slot print_timing: id 3 | task 5004 | prompt eval time = 1784.22 ms / 96 tokens ( 18.59 ms per token, 53.81 tokens per second) 25.32.805.471 I slot print_timing: id 3 | task 5004 | eval time = 27834.55 ms / 112 tokens ( 250.76 ms per token, 3.99 tokens per second) 25.32.805.471 I slot print_timing: id 3 | task 5004 | total time = 29618.77 ms / 208 tokens 25.32.805.472 I slot print_timing: id 3 | task 5004 | graphs reused = 4435 25.32.805.472 I slot print_timing: id 3 | task 5004 | graph reallocs = 0 / 0 (same size) / (changed size) 25.32.805.521 I slot release: id 3 | task 5004 | stop processing: n_tokens = 1332, truncated = 0 25.33.004.017 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.860 25.33.004.047 I slot launch_slot_: id 3 | task 5121 | processing task, is_child = 0 25.34.719.414 I slot print_timing: id 2 | task 4763 | n_gen = 352, tg = 4.17 t/s, tg_3s = 2.12 t/s 25.37.852.970 I slot print_timing: id 2 | task 4763 | n_gen = 366, tg = 4.18 t/s, tg_3s = 4.47 t/s 25.41.011.670 I slot print_timing: id 2 | task 4763 | n_gen = 381, tg = 4.20 t/s, tg_3s = 4.75 t/s 25.41.432.841 I slot print_timing: id 2 | task 4763 | prompt eval time = 2284.24 ms / 112 tokens ( 20.39 ms per token, 49.03 tokens per second) 25.41.432.847 I slot print_timing: id 2 | task 4763 | eval time = 90878.39 ms / 383 tokens ( 237.90 ms per token, 4.20 tokens per second) 25.41.432.848 I slot print_timing: id 2 | task 4763 | total time = 93162.63 ms / 495 tokens 25.41.432.848 I slot print_timing: id 2 | task 4763 | graphs reused = 4464 25.41.432.849 I slot print_timing: id 2 | task 4763 | graph reallocs = 0 / 0 (same size) / (changed size) 25.41.432.899 I slot release: id 2 | task 4763 | stop processing: n_tokens = 1619, truncated = 0 25.41.721.341 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.708 25.41.721.369 I slot launch_slot_: id 2 | task 5155 | processing task, is_child = 0 25.53.680.862 I slot print_timing: id 0 | task 5099 | n_gen = 100, tg = 3.63 t/s, tg_3s = 3.67 t/s 25.56.418.103 I slot print_timing: id 1 | task 5113 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 25.56.839.112 I slot print_timing: id 0 | task 5099 | n_gen = 115, tg = 3.75 t/s, tg_3s = 4.75 t/s 25.57.893.287 I slot print_timing: id 3 | task 5121 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 25.59.578.105 I slot print_timing: id 1 | task 5113 | n_gen = 115, tg = 4.13 t/s, tg_3s = 4.75 t/s 25.59.998.822 I slot print_timing: id 0 | task 5099 | n_gen = 130, tg = 3.84 t/s, tg_3s = 4.75 t/s 26.01.051.309 I slot print_timing: id 3 | task 5121 | n_gen = 115, tg = 4.40 t/s, tg_3s = 4.75 t/s 26.02.737.892 I slot print_timing: id 1 | task 5113 | n_gen = 130, tg = 4.19 t/s, tg_3s = 4.75 t/s 26.03.158.858 I slot print_timing: id 0 | task 5099 | n_gen = 145, tg = 3.92 t/s, tg_3s = 4.75 t/s 26.04.212.859 I slot print_timing: id 3 | task 5121 | n_gen = 130, tg = 4.43 t/s, tg_3s = 4.74 t/s 26.04.845.145 I slot print_timing: id 2 | task 5155 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 26.05.897.607 I slot print_timing: id 1 | task 5113 | n_gen = 145, tg = 4.24 t/s, tg_3s = 4.75 t/s 26.06.318.720 I slot print_timing: id 0 | task 5099 | n_gen = 160, tg = 3.99 t/s, tg_3s = 4.75 t/s 26.07.371.604 I slot print_timing: id 3 | task 5121 | n_gen = 145, tg = 4.46 t/s, tg_3s = 4.75 t/s 26.08.003.242 I slot print_timing: id 2 | task 5155 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 26.09.057.132 I slot print_timing: id 1 | task 5113 | n_gen = 160, tg = 4.29 t/s, tg_3s = 4.75 t/s 26.09.478.129 I slot print_timing: id 0 | task 5099 | n_gen = 175, tg = 4.04 t/s, tg_3s = 4.75 t/s 26.10.531.514 I slot print_timing: id 3 | task 5121 | n_gen = 160, tg = 4.49 t/s, tg_3s = 4.75 t/s 26.10.952.749 I slot print_timing: id 2 | task 5155 | prompt eval time = 2277.36 ms / 104 tokens ( 21.90 ms per token, 45.67 tokens per second) 26.10.952.753 I slot print_timing: id 2 | task 5155 | eval time = 26954.02 ms / 129 tokens ( 210.58 ms per token, 4.75 tokens per second) 26.10.952.755 I slot print_timing: id 2 | task 5155 | total time = 29231.38 ms / 233 tokens 26.10.952.756 I slot print_timing: id 2 | task 5155 | graphs reused = 4591 26.10.952.756 I slot print_timing: id 2 | task 5155 | graph reallocs = 0 / 0 (same size) / (changed size) 26.10.952.805 I slot release: id 2 | task 5155 | stop processing: n_tokens = 1357, truncated = 0 26.11.242.261 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.845 26.11.242.298 I slot launch_slot_: id 2 | task 5287 | processing task, is_child = 0 26.13.038.231 I slot print_timing: id 0 | task 5099 | n_gen = 184, tg = 3.93 t/s, tg_3s = 2.53 t/s 26.13.038.389 I slot print_timing: id 1 | task 5113 | n_gen = 171, tg = 4.14 t/s, tg_3s = 2.76 t/s 26.13.735.892 I slot print_timing: id 3 | task 5121 | n_gen = 166, tg = 4.27 t/s, tg_3s = 1.87 t/s 26.16.051.861 I slot print_timing: id 0 | task 5099 | n_gen = 197, tg = 3.95 t/s, tg_3s = 4.31 t/s 26.16.052.002 I slot print_timing: id 1 | task 5113 | n_gen = 184, tg = 4.15 t/s, tg_3s = 4.31 t/s 26.16.894.152 I slot print_timing: id 3 | task 5121 | n_gen = 181, tg = 4.31 t/s, tg_3s = 4.75 t/s 26.19.211.332 I slot print_timing: id 0 | task 5099 | n_gen = 212, tg = 4.00 t/s, tg_3s = 4.75 t/s 26.19.211.474 I slot print_timing: id 1 | task 5113 | n_gen = 199, tg = 4.19 t/s, tg_3s = 4.75 t/s 26.20.054.063 I slot print_timing: id 3 | task 5121 | n_gen = 196, tg = 4.34 t/s, tg_3s = 4.75 t/s 26.22.370.253 I slot print_timing: id 0 | task 5099 | n_gen = 227, tg = 4.04 t/s, tg_3s = 4.75 t/s 26.22.370.399 I slot print_timing: id 1 | task 5113 | n_gen = 214, tg = 4.23 t/s, tg_3s = 4.75 t/s 26.23.213.081 I slot print_timing: id 3 | task 5121 | n_gen = 211, tg = 4.37 t/s, tg_3s = 4.75 t/s 26.25.529.843 I slot print_timing: id 0 | task 5099 | n_gen = 242, tg = 4.08 t/s, tg_3s = 4.75 t/s 26.25.529.991 I slot print_timing: id 1 | task 5113 | n_gen = 229, tg = 4.26 t/s, tg_3s = 4.75 t/s 26.26.373.036 I slot print_timing: id 3 | task 5121 | n_gen = 226, tg = 4.39 t/s, tg_3s = 4.75 t/s 26.28.689.728 I slot print_timing: id 0 | task 5099 | n_gen = 257, tg = 4.11 t/s, tg_3s = 4.75 t/s 26.28.689.873 I slot print_timing: id 1 | task 5113 | n_gen = 244, tg = 4.28 t/s, tg_3s = 4.75 t/s 26.29.535.610 I slot print_timing: id 3 | task 5121 | n_gen = 241, tg = 4.41 t/s, tg_3s = 4.74 t/s 26.31.852.759 I slot print_timing: id 0 | task 5099 | n_gen = 272, tg = 4.14 t/s, tg_3s = 4.74 t/s 26.31.852.899 I slot print_timing: id 1 | task 5113 | n_gen = 259, tg = 4.31 t/s, tg_3s = 4.74 t/s 26.32.696.226 I slot print_timing: id 3 | task 5121 | n_gen = 256, tg = 4.43 t/s, tg_3s = 4.75 t/s 26.34.382.119 I slot print_timing: id 2 | task 5287 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 26.35.014.237 I slot print_timing: id 0 | task 5099 | n_gen = 287, tg = 4.17 t/s, tg_3s = 4.74 t/s 26.35.014.384 I slot print_timing: id 1 | task 5113 | n_gen = 274, tg = 4.33 t/s, tg_3s = 4.74 t/s 26.35.858.742 I slot print_timing: id 3 | task 5121 | n_gen = 271, tg = 4.44 t/s, tg_3s = 4.74 t/s 26.37.545.422 I slot print_timing: id 2 | task 5287 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.74 t/s 26.38.177.706 I slot print_timing: id 0 | task 5099 | n_gen = 302, tg = 4.19 t/s, tg_3s = 4.74 t/s 26.38.177.849 I slot print_timing: id 1 | task 5113 | n_gen = 289, tg = 4.35 t/s, tg_3s = 4.74 t/s 26.39.021.012 I slot print_timing: id 3 | task 5121 | n_gen = 286, tg = 4.46 t/s, tg_3s = 4.74 t/s 26.40.707.129 I slot print_timing: id 2 | task 5287 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.74 t/s 26.41.339.285 I slot print_timing: id 0 | task 5099 | n_gen = 317, tg = 4.22 t/s, tg_3s = 4.74 t/s 26.41.339.427 I slot print_timing: id 1 | task 5113 | n_gen = 304, tg = 4.37 t/s, tg_3s = 4.74 t/s 26.42.184.430 I slot print_timing: id 3 | task 5121 | n_gen = 301, tg = 4.47 t/s, tg_3s = 4.74 t/s 26.43.870.556 I slot print_timing: id 2 | task 5287 | n_gen = 145, tg = 4.75 t/s, tg_3s = 4.74 t/s 26.44.502.998 I slot print_timing: id 0 | task 5099 | n_gen = 332, tg = 4.24 t/s, tg_3s = 4.74 t/s 26.44.503.156 I slot print_timing: id 1 | task 5113 | n_gen = 319, tg = 4.38 t/s, tg_3s = 4.74 t/s 26.45.346.364 I slot print_timing: id 3 | task 5121 | n_gen = 316, tg = 4.49 t/s, tg_3s = 4.74 t/s 26.47.033.662 I slot print_timing: id 2 | task 5287 | n_gen = 160, tg = 4.74 t/s, tg_3s = 4.74 t/s 26.47.665.616 I slot print_timing: id 0 | task 5099 | n_gen = 347, tg = 4.26 t/s, tg_3s = 4.74 t/s 26.47.665.764 I slot print_timing: id 1 | task 5113 | n_gen = 334, tg = 4.40 t/s, tg_3s = 4.74 t/s 26.48.509.535 I slot print_timing: id 3 | task 5121 | n_gen = 331, tg = 4.50 t/s, tg_3s = 4.74 t/s 26.50.195.993 I slot print_timing: id 2 | task 5287 | n_gen = 175, tg = 4.74 t/s, tg_3s = 4.74 t/s 26.50.828.587 I slot print_timing: id 0 | task 5099 | n_gen = 362, tg = 4.28 t/s, tg_3s = 4.74 t/s 26.50.828.730 I slot print_timing: id 1 | task 5113 | n_gen = 349, tg = 4.41 t/s, tg_3s = 4.74 t/s 26.51.039.863 I slot print_timing: id 3 | task 5121 | prompt eval time = 2110.30 ms / 117 tokens ( 18.04 ms per token, 55.44 tokens per second) 26.51.039.866 I slot print_timing: id 3 | task 5121 | eval time = 75925.51 ms / 343 tokens ( 222.00 ms per token, 4.50 tokens per second) 26.51.039.867 I slot print_timing: id 3 | task 5121 | total time = 78035.81 ms / 460 tokens 26.51.039.867 I slot print_timing: id 3 | task 5121 | graphs reused = 4767 26.51.039.868 I slot print_timing: id 3 | task 5121 | graph reallocs = 0 / 0 (same size) / (changed size) 26.51.039.920 I slot release: id 3 | task 5121 | stop processing: n_tokens = 1584, truncated = 0 26.51.238.378 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.723 26.51.238.409 I slot launch_slot_: id 3 | task 5469 | processing task, is_child = 0 26.53.352.210 I slot print_timing: id 2 | task 5287 | n_gen = 182, tg = 4.54 t/s, tg_3s = 2.22 t/s 26.53.986.700 I slot print_timing: id 0 | task 5099 | n_gen = 369, tg = 4.20 t/s, tg_3s = 2.22 t/s 26.53.986.850 I slot print_timing: id 1 | task 5113 | n_gen = 356, tg = 4.33 t/s, tg_3s = 2.22 t/s 26.56.516.304 I slot print_timing: id 2 | task 5287 | n_gen = 197, tg = 4.56 t/s, tg_3s = 4.74 t/s 26.57.148.300 I slot print_timing: id 0 | task 5099 | n_gen = 384, tg = 4.22 t/s, tg_3s = 4.74 t/s 26.57.148.446 I slot print_timing: id 1 | task 5113 | n_gen = 371, tg = 4.34 t/s, tg_3s = 4.74 t/s 26.59.677.175 I slot print_timing: id 2 | task 5287 | n_gen = 212, tg = 4.57 t/s, tg_3s = 4.75 t/s 27.00.309.167 I slot print_timing: id 0 | task 5099 | n_gen = 399, tg = 4.24 t/s, tg_3s = 4.75 t/s 27.00.309.310 I slot print_timing: id 1 | task 5113 | n_gen = 386, tg = 4.36 t/s, tg_3s = 4.75 t/s 27.02.838.768 I slot print_timing: id 2 | task 5287 | n_gen = 227, tg = 4.58 t/s, tg_3s = 4.74 t/s 27.03.471.260 I slot print_timing: id 0 | task 5099 | n_gen = 414, tg = 4.26 t/s, tg_3s = 4.74 t/s 27.03.471.407 I slot print_timing: id 1 | task 5113 | n_gen = 401, tg = 4.37 t/s, tg_3s = 4.74 t/s 27.04.525.786 I slot print_timing: id 0 | task 5099 | prompt eval time = 2085.31 ms / 122 tokens ( 17.09 ms per token, 58.50 tokens per second) 27.04.525.791 I slot print_timing: id 0 | task 5099 | eval time = 98100.74 ms / 419 tokens ( 234.69 ms per token, 4.26 tokens per second) 27.04.525.792 I slot print_timing: id 0 | task 5099 | total time = 100186.05 ms / 541 tokens 27.04.525.792 I slot print_timing: id 0 | task 5099 | graphs reused = 4819 27.04.525.793 I slot print_timing: id 0 | task 5099 | graph reallocs = 0 / 0 (same size) / (changed size) 27.04.525.844 I slot release: id 0 | task 5099 | stop processing: n_tokens = 1665, truncated = 0 27.04.725.393 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.688 27.04.725.420 I slot launch_slot_: id 0 | task 5526 | processing task, is_child = 0 27.06.419.159 I slot print_timing: id 2 | task 5287 | n_gen = 237, tg = 4.46 t/s, tg_3s = 2.79 t/s 27.06.800.819 I slot print_timing: id 1 | task 5113 | n_gen = 409, tg = 4.30 t/s, tg_3s = 2.40 t/s 27.09.543.421 I slot print_timing: id 2 | task 5287 | n_gen = 251, tg = 4.46 t/s, tg_3s = 4.48 t/s 27.09.964.368 I slot print_timing: id 1 | task 5113 | n_gen = 424, tg = 4.32 t/s, tg_3s = 4.74 t/s 27.12.070.774 I slot print_timing: id 1 | task 5113 | prompt eval time = 3134.13 ms / 166 tokens ( 18.88 ms per token, 52.97 tokens per second) 27.12.070.780 I slot print_timing: id 1 | task 5113 | eval time = 100110.20 ms / 434 tokens ( 231.20 ms per token, 4.33 tokens per second) 27.12.070.780 I slot print_timing: id 1 | task 5113 | total time = 103244.33 ms / 600 tokens 27.12.070.781 I slot print_timing: id 1 | task 5113 | graphs reused = 4844 27.12.070.781 I slot print_timing: id 1 | task 5113 | graph reallocs = 0 / 0 (same size) / (changed size) 27.12.070.827 I slot release: id 1 | task 5113 | stop processing: n_tokens = 1724, truncated = 0 27.12.070.970 I slot print_timing: id 2 | task 5287 | prompt eval time = 2280.63 ms / 108 tokens ( 21.12 ms per token, 47.36 tokens per second) 27.12.070.972 I slot print_timing: id 2 | task 5287 | eval time = 58548.04 ms / 263 tokens ( 223.47 ms per token, 4.47 tokens per second) 27.12.070.972 I slot print_timing: id 2 | task 5287 | total time = 60828.67 ms / 371 tokens 27.12.070.973 I slot print_timing: id 2 | task 5287 | graphs reused = 4844 27.12.070.973 I slot print_timing: id 2 | task 5287 | graph reallocs = 0 / 0 (same size) / (changed size) 27.12.071.007 I slot release: id 2 | task 5287 | stop processing: n_tokens = 1495, truncated = 0 27.12.285.118 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.665 27.12.285.165 I slot launch_slot_: id 1 | task 5555 | processing task, is_child = 0 27.12.285.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 27.12.285.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 27.12.285.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 27.12.517.458 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.767 27.12.517.514 I slot launch_slot_: id 2 | task 5556 | processing task, is_child = 0 27.15.647.798 I slot print_timing: id 1 | task 5555 | prompt processing, n_tokens = 115, progress = 1.00, t = 3.13 s / 36.74 tokens per second 27.15.655.622 I slot print_timing: id 2 | task 5556 | prompt processing, n_tokens = 112, progress = 1.00, t = 3.12 s / 35.87 tokens per second 27.19.318.777 I slot print_timing: id 3 | task 5469 | n_gen = 100, tg = 3.81 t/s, tg_3s = 3.85 t/s 27.22.474.762 I slot print_timing: id 3 | task 5469 | n_gen = 115, tg = 3.91 t/s, tg_3s = 4.75 t/s 27.25.631.991 I slot print_timing: id 3 | task 5469 | n_gen = 130, tg = 4.00 t/s, tg_3s = 4.75 t/s 27.28.789.292 I slot print_timing: id 3 | task 5469 | n_gen = 145, tg = 4.06 t/s, tg_3s = 4.75 t/s 27.31.103.848 I slot print_timing: id 0 | task 5526 | n_gen = 100, tg = 4.07 t/s, tg_3s = 4.11 t/s 27.31.946.689 I slot print_timing: id 3 | task 5469 | n_gen = 160, tg = 4.12 t/s, tg_3s = 4.75 t/s 27.34.265.611 I slot print_timing: id 0 | task 5526 | n_gen = 115, tg = 4.15 t/s, tg_3s = 4.74 t/s 27.35.109.032 I slot print_timing: id 3 | task 5469 | n_gen = 175, tg = 4.17 t/s, tg_3s = 4.74 t/s 27.37.003.412 I slot print_timing: id 1 | task 5555 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 27.37.003.555 I slot print_timing: id 2 | task 5556 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 27.37.424.592 I slot print_timing: id 0 | task 5526 | n_gen = 130, tg = 4.21 t/s, tg_3s = 4.75 t/s 27.38.267.439 I slot print_timing: id 3 | task 5469 | n_gen = 190, tg = 4.21 t/s, tg_3s = 4.75 t/s 27.39.952.040 I slot print_timing: id 2 | task 5556 | prompt eval time = 3634.58 ms / 116 tokens ( 31.33 ms per token, 31.92 tokens per second) 27.39.952.043 I slot print_timing: id 2 | task 5556 | eval time = 23792.32 ms / 114 tokens ( 210.55 ms per token, 4.75 tokens per second) 27.39.952.044 I slot print_timing: id 2 | task 5556 | total time = 27426.90 ms / 230 tokens 27.39.952.044 I slot print_timing: id 2 | task 5556 | graphs reused = 4956 27.39.952.045 I slot print_timing: id 2 | task 5556 | graph reallocs = 0 / 0 (same size) / (changed size) 27.39.952.100 I slot release: id 2 | task 5556 | stop processing: n_tokens = 1354, truncated = 0 27.40.241.294 I slot print_timing: id 1 | task 5555 | n_gen = 115, tg = 4.73 t/s, tg_3s = 4.63 t/s 27.40.241.456 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.846 27.40.241.486 I slot launch_slot_: id 2 | task 5673 | processing task, is_child = 0 27.42.050.799 I slot print_timing: id 0 | task 5526 | n_gen = 144, tg = 4.06 t/s, tg_3s = 3.03 t/s 27.42.051.214 I slot print_timing: id 3 | task 5469 | n_gen = 200, tg = 4.09 t/s, tg_3s = 2.64 t/s 27.43.379.694 I slot print_timing: id 1 | task 5555 | n_gen = 121, tg = 4.41 t/s, tg_3s = 1.91 t/s 27.45.064.628 I slot print_timing: id 0 | task 5526 | n_gen = 157, tg = 4.08 t/s, tg_3s = 4.31 t/s 27.45.065.052 I slot print_timing: id 3 | task 5469 | n_gen = 213, tg = 4.10 t/s, tg_3s = 4.31 t/s 27.46.539.045 I slot print_timing: id 1 | task 5555 | n_gen = 136, tg = 4.44 t/s, tg_3s = 4.75 t/s 27.48.223.007 I slot print_timing: id 0 | task 5526 | n_gen = 172, tg = 4.13 t/s, tg_3s = 4.75 t/s 27.48.223.408 I slot print_timing: id 3 | task 5469 | n_gen = 228, tg = 4.14 t/s, tg_3s = 4.75 t/s 27.49.697.977 I slot print_timing: id 1 | task 5555 | n_gen = 151, tg = 4.47 t/s, tg_3s = 4.75 t/s 27.51.382.566 I slot print_timing: id 0 | task 5526 | n_gen = 187, tg = 4.17 t/s, tg_3s = 4.75 t/s 27.51.382.968 I slot print_timing: id 3 | task 5469 | n_gen = 243, tg = 4.17 t/s, tg_3s = 4.75 t/s 27.52.014.346 I slot print_timing: id 0 | task 5526 | prompt eval time = 2075.26 ms / 112 tokens ( 18.53 ms per token, 53.97 tokens per second) 27.52.014.351 I slot print_timing: id 0 | task 5526 | eval time = 45213.66 ms / 190 tokens ( 239.23 ms per token, 4.18 tokens per second) 27.52.014.352 I slot print_timing: id 0 | task 5526 | total time = 47288.92 ms / 302 tokens 27.52.014.352 I slot print_timing: id 0 | task 5526 | graphs reused = 5000 27.52.014.352 I slot print_timing: id 0 | task 5526 | graph reallocs = 0 / 0 (same size) / (changed size) 27.52.014.399 I slot release: id 0 | task 5526 | stop processing: n_tokens = 1426, truncated = 0 27.52.213.232 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.804 27.52.213.266 I slot launch_slot_: id 0 | task 5722 | processing task, is_child = 0 27.53.900.899 I slot print_timing: id 1 | task 5555 | n_gen = 164, tg = 4.32 t/s, tg_3s = 3.09 t/s 27.54.495.978 I slot print_timing: id 3 | task 5469 | n_gen = 250, tg = 4.07 t/s, tg_3s = 2.25 t/s 27.57.022.471 I slot print_timing: id 1 | task 5555 | n_gen = 178, tg = 4.33 t/s, tg_3s = 4.48 t/s 27.57.654.136 I slot print_timing: id 3 | task 5469 | n_gen = 265, tg = 4.11 t/s, tg_3s = 4.75 t/s 28.00.180.190 I slot print_timing: id 1 | task 5555 | n_gen = 193, tg = 4.36 t/s, tg_3s = 4.75 t/s 28.00.815.101 I slot print_timing: id 3 | task 5469 | n_gen = 280, tg = 4.14 t/s, tg_3s = 4.75 t/s 28.03.341.550 I slot print_timing: id 1 | task 5555 | n_gen = 208, tg = 4.39 t/s, tg_3s = 4.74 t/s 28.03.973.483 I slot print_timing: id 3 | task 5469 | n_gen = 295, tg = 4.16 t/s, tg_3s = 4.75 t/s 28.05.025.578 I slot print_timing: id 2 | task 5673 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 28.06.499.630 I slot print_timing: id 1 | task 5555 | n_gen = 223, tg = 4.41 t/s, tg_3s = 4.75 t/s 28.07.131.313 I slot print_timing: id 3 | task 5469 | n_gen = 310, tg = 4.19 t/s, tg_3s = 4.75 t/s 28.07.973.604 I slot print_timing: id 3 | task 5469 | prompt eval time = 2114.03 ms / 133 tokens ( 15.89 ms per token, 62.91 tokens per second) 28.07.973.610 I slot print_timing: id 3 | task 5469 | eval time = 74621.16 ms / 314 tokens ( 238.41 ms per token, 4.19 tokens per second) 28.07.973.610 I slot print_timing: id 3 | task 5469 | total time = 76735.19 ms / 447 tokens 28.07.973.611 I slot print_timing: id 3 | task 5469 | graphs reused = 5064 28.07.973.611 I slot print_timing: id 3 | task 5469 | graph reallocs = 0 / 0 (same size) / (changed size) 28.07.973.665 I slot release: id 3 | task 5469 | stop processing: n_tokens = 1571, truncated = 0 28.08.172.111 I slot print_timing: id 2 | task 5673 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.77 t/s 28.08.172.115 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.729 28.08.172.147 I slot launch_slot_: id 3 | task 5791 | processing task, is_child = 0 28.09.890.855 I slot print_timing: id 1 | task 5555 | n_gen = 232, tg = 4.30 t/s, tg_3s = 2.65 t/s 28.11.340.231 I slot print_timing: id 2 | task 5673 | n_gen = 122, tg = 4.20 t/s, tg_3s = 2.21 t/s 28.11.550.748 I slot print_timing: id 1 | task 5555 | prompt eval time = 3641.98 ms / 119 tokens ( 30.60 ms per token, 32.67 tokens per second) 28.11.550.752 I slot print_timing: id 1 | task 5555 | eval time = 55391.25 ms / 239 tokens ( 232.74 ms per token, 4.30 tokens per second) 28.11.550.753 I slot print_timing: id 1 | task 5555 | total time = 59033.23 ms / 358 tokens 28.11.550.753 I slot print_timing: id 1 | task 5555 | graphs reused = 5069 28.11.550.754 I slot print_timing: id 1 | task 5555 | graph reallocs = 0 / 0 (same size) / (changed size) 28.11.550.810 I slot release: id 1 | task 5555 | stop processing: n_tokens = 1482, truncated = 0 28.11.840.508 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.773 28.11.840.546 I slot launch_slot_: id 1 | task 5801 | processing task, is_child = 0 28.14.451.037 I slot print_timing: id 2 | task 5673 | n_gen = 127, tg = 3.95 t/s, tg_3s = 1.61 t/s 28.17.607.037 I slot print_timing: id 2 | task 5673 | n_gen = 142, tg = 4.02 t/s, tg_3s = 4.75 t/s 28.18.868.176 I slot print_timing: id 0 | task 5722 | n_gen = 100, tg = 4.03 t/s, tg_3s = 4.07 t/s 28.20.762.654 I slot print_timing: id 2 | task 5673 | n_gen = 157, tg = 4.08 t/s, tg_3s = 4.75 t/s 28.22.025.035 I slot print_timing: id 0 | task 5722 | prompt eval time = 2069.32 ms / 103 tokens ( 20.09 ms per token, 49.77 tokens per second) 28.22.025.041 I slot print_timing: id 0 | task 5722 | eval time = 27742.44 ms / 115 tokens ( 243.35 ms per token, 4.11 tokens per second) 28.22.025.041 I slot print_timing: id 0 | task 5722 | total time = 29811.76 ms / 218 tokens 28.22.025.042 I slot print_timing: id 0 | task 5722 | graphs reused = 5105 28.22.025.042 I slot print_timing: id 0 | task 5722 | graph reallocs = 0 / 0 (same size) / (changed size) 28.22.025.086 I slot release: id 0 | task 5722 | stop processing: n_tokens = 1342, truncated = 0 28.22.223.584 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.854 28.22.223.620 I slot launch_slot_: id 0 | task 5842 | processing task, is_child = 0 28.23.981.423 I slot print_timing: id 2 | task 5673 | n_gen = 166, tg = 3.98 t/s, tg_3s = 2.80 t/s 28.27.139.810 I slot print_timing: id 2 | task 5673 | n_gen = 181, tg = 4.04 t/s, tg_3s = 4.75 t/s 28.30.293.960 I slot print_timing: id 2 | task 5673 | n_gen = 196, tg = 4.08 t/s, tg_3s = 4.76 t/s 28.33.451.076 I slot print_timing: id 2 | task 5673 | n_gen = 211, tg = 4.12 t/s, tg_3s = 4.75 t/s 28.34.503.404 I slot print_timing: id 3 | task 5791 | n_gen = 100, tg = 4.09 t/s, tg_3s = 4.13 t/s 28.34.924.139 I slot print_timing: id 2 | task 5673 | prompt eval time = 2294.45 ms / 119 tokens ( 19.28 ms per token, 51.86 tokens per second) 28.34.924.144 I slot print_timing: id 2 | task 5673 | eval time = 52388.19 ms / 218 tokens ( 241.42 ms per token, 4.14 tokens per second) 28.34.924.145 I slot print_timing: id 2 | task 5673 | total time = 54682.64 ms / 337 tokens 28.34.924.146 I slot print_timing: id 2 | task 5673 | graphs reused = 5157 28.34.924.146 I slot print_timing: id 2 | task 5673 | graph reallocs = 0 / 0 (same size) / (changed size) 28.34.924.192 I slot release: id 2 | task 5673 | stop processing: n_tokens = 1461, truncated = 0 28.35.214.085 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.784 28.35.214.132 I slot launch_slot_: id 2 | task 5898 | processing task, is_child = 0 28.37.609.515 I slot print_timing: id 3 | task 5791 | n_gen = 107, tg = 3.88 t/s, tg_3s = 2.25 t/s 28.38.030.050 I slot print_timing: id 1 | task 5801 | n_gen = 100, tg = 4.16 t/s, tg_3s = 4.20 t/s 28.38.871.544 I slot print_timing: id 0 | task 5842 | prompt eval time = 1757.46 ms / 97 tokens ( 18.12 ms per token, 55.19 tokens per second) 28.38.871.546 I slot print_timing: id 0 | task 5842 | eval time = 14890.45 ms / 64 tokens ( 236.36 ms per token, 4.23 tokens per second) 28.38.871.547 I slot print_timing: id 0 | task 5842 | total time = 16647.91 ms / 161 tokens 28.38.871.547 I slot print_timing: id 0 | task 5842 | graphs reused = 5164 28.38.871.548 I slot print_timing: id 0 | task 5842 | graph reallocs = 0 / 0 (same size) / (changed size) 28.38.871.602 I slot release: id 0 | task 5842 | stop processing: n_tokens = 1285, truncated = 0 28.39.070.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.892 28.39.070.846 I slot launch_slot_: id 0 | task 5910 | processing task, is_child = 0 28.41.489.556 I slot print_timing: id 1 | task 5801 | n_gen = 106, tg = 3.85 t/s, tg_3s = 1.73 t/s 28.41.489.938 I slot print_timing: id 3 | task 5791 | n_gen = 115, tg = 3.65 t/s, tg_3s = 2.06 t/s 28.42.927.784 I slot print_timing: id 3 | task 5791 | prompt eval time = 2113.82 ms / 120 tokens ( 17.62 ms per token, 56.77 tokens per second) 28.42.927.787 I slot print_timing: id 3 | task 5791 | eval time = 32641.81 ms / 121 tokens ( 272.02 ms per token, 3.68 tokens per second) 28.42.927.788 I slot print_timing: id 3 | task 5791 | total time = 34755.63 ms / 241 tokens 28.42.927.788 I slot print_timing: id 3 | task 5791 | graphs reused = 5169 28.42.927.789 I slot print_timing: id 3 | task 5791 | graph reallocs = 0 / 0 (same size) / (changed size) 28.42.927.833 I slot release: id 3 | task 5791 | stop processing: n_tokens = 1365, truncated = 0 28.43.126.247 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.840 28.43.126.273 I slot launch_slot_: id 3 | task 5919 | processing task, is_child = 0 28.44.844.138 I slot print_timing: id 1 | task 5801 | n_gen = 114, tg = 3.69 t/s, tg_3s = 2.38 t/s 28.47.764.864 I slot print_timing: id 1 | task 5801 | prompt eval time = 2396.73 ms / 108 tokens ( 22.19 ms per token, 45.06 tokens per second) 28.47.764.867 I slot print_timing: id 1 | task 5801 | eval time = 33527.57 ms / 127 tokens ( 266.09 ms per token, 3.76 tokens per second) 28.47.764.868 I slot print_timing: id 1 | task 5801 | total time = 35924.31 ms / 235 tokens 28.47.764.868 I slot print_timing: id 1 | task 5801 | graphs reused = 5180 28.47.764.869 I slot print_timing: id 1 | task 5801 | graph reallocs = 0 / 0 (same size) / (changed size) 28.47.764.921 I slot release: id 1 | task 5801 | stop processing: n_tokens = 1359, truncated = 0 28.48.055.311 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.843 28.48.055.350 I slot launch_slot_: id 1 | task 5935 | processing task, is_child = 0 28.59.304.472 I slot print_timing: id 2 | task 5898 | prompt eval time = 1970.94 ms / 100 tokens ( 19.71 ms per token, 50.74 tokens per second) 28.59.304.477 I slot print_timing: id 2 | task 5898 | eval time = 22119.39 ms / 77 tokens ( 291.04 ms per token, 3.44 tokens per second) 28.59.304.477 I slot print_timing: id 2 | task 5898 | total time = 24090.33 ms / 177 tokens 28.59.304.478 I slot print_timing: id 2 | task 5898 | graphs reused = 5221 28.59.304.478 I slot print_timing: id 2 | task 5898 | graph reallocs = 0 / 0 (same size) / (changed size) 28.59.304.522 I slot release: id 2 | task 5898 | stop processing: n_tokens = 1301, truncated = 0 28.59.593.661 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.881 28.59.593.694 I slot launch_slot_: id 2 | task 5981 | processing task, is_child = 0 29.08.397.823 I slot print_timing: id 0 | task 5910 | n_gen = 100, tg = 3.73 t/s, tg_3s = 3.77 t/s 29.10.083.606 I slot print_timing: id 3 | task 5919 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 29.11.557.041 I slot print_timing: id 0 | task 5910 | n_gen = 115, tg = 3.84 t/s, tg_3s = 4.75 t/s 29.13.241.547 I slot print_timing: id 1 | task 5935 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 29.13.241.822 I slot print_timing: id 3 | task 5919 | n_gen = 115, tg = 4.07 t/s, tg_3s = 4.75 t/s 29.14.715.489 I slot print_timing: id 0 | task 5910 | n_gen = 130, tg = 3.93 t/s, tg_3s = 4.75 t/s 29.16.401.081 I slot print_timing: id 1 | task 5935 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.75 t/s 29.16.401.378 I slot print_timing: id 3 | task 5919 | n_gen = 130, tg = 4.14 t/s, tg_3s = 4.75 t/s 29.17.874.684 I slot print_timing: id 0 | task 5910 | n_gen = 145, tg = 4.00 t/s, tg_3s = 4.75 t/s 29.19.558.950 I slot print_timing: id 1 | task 5935 | n_gen = 130, tg = 4.43 t/s, tg_3s = 4.75 t/s 29.19.559.240 I slot print_timing: id 3 | task 5919 | n_gen = 145, tg = 4.20 t/s, tg_3s = 4.75 t/s 29.21.033.408 I slot print_timing: id 0 | task 5910 | n_gen = 160, tg = 4.06 t/s, tg_3s = 4.75 t/s 29.22.717.427 I slot print_timing: id 1 | task 5935 | n_gen = 145, tg = 4.46 t/s, tg_3s = 4.75 t/s 29.22.717.572 I slot print_timing: id 2 | task 5981 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 29.22.717.714 I slot print_timing: id 3 | task 5919 | n_gen = 160, tg = 4.24 t/s, tg_3s = 4.75 t/s 29.24.191.155 I slot print_timing: id 0 | task 5910 | n_gen = 175, tg = 4.11 t/s, tg_3s = 4.75 t/s 29.25.877.615 I slot print_timing: id 1 | task 5935 | n_gen = 160, tg = 4.49 t/s, tg_3s = 4.75 t/s 29.25.877.759 I slot print_timing: id 2 | task 5981 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 29.25.877.899 I slot print_timing: id 3 | task 5919 | n_gen = 175, tg = 4.28 t/s, tg_3s = 4.75 t/s 29.27.351.680 I slot print_timing: id 0 | task 5910 | n_gen = 190, tg = 4.16 t/s, tg_3s = 4.75 t/s 29.27.986.061 I slot print_timing: id 3 | task 5919 | prompt eval time = 2111.72 ms / 119 tokens ( 17.75 ms per token, 56.35 tokens per second) 29.27.986.064 I slot print_timing: id 3 | task 5919 | eval time = 42748.06 ms / 185 tokens ( 232.33 ms per token, 4.30 tokens per second) 29.27.986.065 I slot print_timing: id 3 | task 5919 | total time = 44859.78 ms / 304 tokens 29.27.986.065 I slot print_timing: id 3 | task 5919 | graphs reused = 5344 29.27.986.066 I slot print_timing: id 3 | task 5919 | graph reallocs = 0 / 0 (same size) / (changed size) 29.27.986.108 I slot release: id 3 | task 5919 | stop processing: n_tokens = 1428, truncated = 0 29.28.184.967 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.803 29.28.184.994 I slot launch_slot_: id 3 | task 6109 | processing task, is_child = 0 29.29.899.327 I slot print_timing: id 1 | task 5935 | n_gen = 172, tg = 4.34 t/s, tg_3s = 2.98 t/s 29.29.899.546 I slot print_timing: id 2 | task 5981 | n_gen = 127, tg = 4.50 t/s, tg_3s = 2.98 t/s 29.30.506.779 I slot print_timing: id 0 | task 5910 | n_gen = 197, tg = 4.03 t/s, tg_3s = 2.22 t/s 29.33.034.014 I slot print_timing: id 1 | task 5935 | n_gen = 186, tg = 4.35 t/s, tg_3s = 4.47 t/s 29.33.034.176 I slot print_timing: id 2 | task 5981 | n_gen = 141, tg = 4.49 t/s, tg_3s = 4.47 t/s 29.33.665.039 I slot print_timing: id 0 | task 5910 | n_gen = 212, tg = 4.07 t/s, tg_3s = 4.75 t/s 29.36.191.182 I slot print_timing: id 1 | task 5935 | n_gen = 201, tg = 4.37 t/s, tg_3s = 4.75 t/s 29.36.191.337 I slot print_timing: id 2 | task 5981 | n_gen = 156, tg = 4.52 t/s, tg_3s = 4.75 t/s 29.36.823.326 I slot print_timing: id 0 | task 5910 | n_gen = 227, tg = 4.11 t/s, tg_3s = 4.75 t/s 29.39.349.390 I slot print_timing: id 1 | task 5935 | n_gen = 216, tg = 4.40 t/s, tg_3s = 4.75 t/s 29.39.349.532 I slot print_timing: id 2 | task 5981 | n_gen = 171, tg = 4.54 t/s, tg_3s = 4.75 t/s 29.39.983.786 I slot print_timing: id 0 | task 5910 | n_gen = 242, tg = 4.15 t/s, tg_3s = 4.75 t/s 29.42.511.896 I slot print_timing: id 1 | task 5935 | n_gen = 231, tg = 4.42 t/s, tg_3s = 4.74 t/s 29.42.512.053 I slot print_timing: id 2 | task 5981 | n_gen = 186, tg = 4.55 t/s, tg_3s = 4.74 t/s 29.43.143.751 I slot print_timing: id 0 | task 5910 | n_gen = 257, tg = 4.18 t/s, tg_3s = 4.75 t/s 29.43.987.177 I slot print_timing: id 1 | task 5935 | prompt eval time = 2404.81 ms / 114 tokens ( 21.09 ms per token, 47.41 tokens per second) 29.43.987.179 I slot print_timing: id 1 | task 5935 | eval time = 53527.00 ms / 238 tokens ( 225.85 ms per token, 4.43 tokens per second) 29.43.987.181 I slot print_timing: id 1 | task 5935 | total time = 55931.81 ms / 352 tokens 29.43.987.181 I slot print_timing: id 1 | task 5935 | graphs reused = 5407 29.43.987.182 I slot print_timing: id 1 | task 5935 | graph reallocs = 0 / 0 (same size) / (changed size) 29.43.987.232 I slot release: id 1 | task 5935 | stop processing: n_tokens = 1476, truncated = 0 29.44.276.644 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.776 29.44.276.682 I slot launch_slot_: id 1 | task 6178 | processing task, is_child = 0 29.45.808.613 I slot print_timing: id 2 | task 5981 | n_gen = 195, tg = 4.42 t/s, tg_3s = 2.73 t/s 29.46.351.768 I slot print_timing: id 0 | task 5910 | n_gen = 264, tg = 4.08 t/s, tg_3s = 2.18 t/s 29.48.882.196 I slot print_timing: id 2 | task 5981 | n_gen = 208, tg = 4.40 t/s, tg_3s = 4.23 t/s 29.49.513.642 I slot print_timing: id 0 | task 5910 | n_gen = 279, tg = 4.11 t/s, tg_3s = 4.74 t/s 29.52.040.899 I slot print_timing: id 2 | task 5981 | n_gen = 223, tg = 4.42 t/s, tg_3s = 4.75 t/s 29.52.672.163 I slot print_timing: id 0 | task 5910 | n_gen = 294, tg = 4.14 t/s, tg_3s = 4.75 t/s 29.52.883.042 I slot print_timing: id 3 | task 6109 | n_gen = 100, tg = 4.38 t/s, tg_3s = 4.43 t/s 29.55.199.549 I slot print_timing: id 2 | task 5981 | n_gen = 238, tg = 4.44 t/s, tg_3s = 4.75 t/s 29.55.831.467 I slot print_timing: id 0 | task 5910 | n_gen = 309, tg = 4.16 t/s, tg_3s = 4.75 t/s 29.56.042.532 I slot print_timing: id 3 | task 6109 | n_gen = 115, tg = 4.43 t/s, tg_3s = 4.75 t/s 29.56.463.844 I slot print_timing: id 2 | task 5981 | prompt eval time = 2276.37 ms / 104 tokens ( 21.89 ms per token, 45.69 tokens per second) 29.56.463.850 I slot print_timing: id 2 | task 5981 | eval time = 54593.77 ms / 244 tokens ( 224.67 ms per token, 4.45 tokens per second) 29.56.463.850 I slot print_timing: id 2 | task 5981 | total time = 56870.14 ms / 348 tokens 29.56.463.851 I slot print_timing: id 2 | task 5981 | graphs reused = 5454 29.56.463.851 I slot print_timing: id 2 | task 5981 | graph reallocs = 0 / 0 (same size) / (changed size) 29.56.463.897 I slot release: id 2 | task 5981 | stop processing: n_tokens = 1472, truncated = 0 29.56.753.246 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.779 29.56.753.282 I slot launch_slot_: id 2 | task 6230 | processing task, is_child = 0 29.59.058.530 I slot print_timing: id 0 | task 5910 | n_gen = 315, tg = 4.07 t/s, tg_3s = 1.86 t/s 29.59.059.117 I slot print_timing: id 3 | task 6109 | n_gen = 120, tg = 4.14 t/s, tg_3s = 1.66 t/s 30.02.218.833 I slot print_timing: id 0 | task 5910 | n_gen = 330, tg = 4.09 t/s, tg_3s = 4.75 t/s 30.02.219.278 I slot print_timing: id 3 | task 6109 | n_gen = 135, tg = 4.20 t/s, tg_3s = 4.75 t/s 30.05.377.640 I slot print_timing: id 0 | task 5910 | n_gen = 345, tg = 4.12 t/s, tg_3s = 4.75 t/s 30.05.378.055 I slot print_timing: id 3 | task 6109 | n_gen = 150, tg = 4.25 t/s, tg_3s = 4.75 t/s 30.08.536.879 I slot print_timing: id 0 | task 5910 | n_gen = 360, tg = 4.14 t/s, tg_3s = 4.75 t/s 30.08.537.311 I slot print_timing: id 3 | task 6109 | n_gen = 165, tg = 4.29 t/s, tg_3s = 4.75 t/s 30.09.169.013 I slot print_timing: id 1 | task 6178 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 30.11.698.907 I slot print_timing: id 0 | task 5910 | n_gen = 375, tg = 4.16 t/s, tg_3s = 4.74 t/s 30.11.699.317 I slot print_timing: id 3 | task 6109 | n_gen = 180, tg = 4.32 t/s, tg_3s = 4.74 t/s 30.12.331.005 I slot print_timing: id 1 | task 6178 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.74 t/s 30.14.859.364 I slot print_timing: id 0 | task 5910 | n_gen = 390, tg = 4.18 t/s, tg_3s = 4.75 t/s 30.14.859.503 I slot print_timing: id 1 | task 6178 | prompt eval time = 2075.30 ms / 88 tokens ( 23.58 ms per token, 42.40 tokens per second) 30.14.859.504 I slot print_timing: id 1 | task 6178 | eval time = 28507.52 ms / 127 tokens ( 226.25 ms per token, 4.42 tokens per second) 30.14.859.505 I slot print_timing: id 1 | task 6178 | total time = 30582.82 ms / 215 tokens 30.14.859.505 I slot print_timing: id 1 | task 6178 | graphs reused = 5528 30.14.859.506 I slot print_timing: id 1 | task 6178 | graph reallocs = 0 / 0 (same size) / (changed size) 30.14.859.549 I slot release: id 1 | task 6178 | stop processing: n_tokens = 1339, truncated = 0 30.14.859.832 I slot print_timing: id 3 | task 6109 | n_gen = 195, tg = 4.35 t/s, tg_3s = 4.75 t/s 30.15.149.576 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.856 30.15.149.613 I slot launch_slot_: id 1 | task 6309 | processing task, is_child = 0 30.18.068.463 I slot print_timing: id 0 | task 5910 | n_gen = 397, tg = 4.12 t/s, tg_3s = 2.18 t/s 30.18.068.863 I slot print_timing: id 3 | task 6109 | n_gen = 202, tg = 4.21 t/s, tg_3s = 2.18 t/s 30.19.332.903 I slot print_timing: id 3 | task 6109 | prompt eval time = 2109.02 ms / 117 tokens ( 18.03 ms per token, 55.48 tokens per second) 30.19.332.908 I slot print_timing: id 3 | task 6109 | eval time = 49038.87 ms / 208 tokens ( 236.90 ms per token, 4.22 tokens per second) 30.19.332.909 I slot print_timing: id 3 | task 6109 | total time = 51147.90 ms / 325 tokens 30.19.332.909 I slot print_timing: id 3 | task 6109 | graphs reused = 5537 30.19.332.910 I slot print_timing: id 3 | task 6109 | graph reallocs = 0 / 0 (same size) / (changed size) 30.19.332.958 I slot release: id 3 | task 6109 | stop processing: n_tokens = 1449, truncated = 0 30.19.531.339 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.791 30.19.531.369 I slot launch_slot_: id 3 | task 6323 | processing task, is_child = 0 30.21.620.996 I slot print_timing: id 0 | task 5910 | n_gen = 405, tg = 4.05 t/s, tg_3s = 2.25 t/s 30.23.703.159 I slot print_timing: id 2 | task 6230 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 30.24.757.175 I slot print_timing: id 0 | task 5910 | prompt eval time = 2801.99 ms / 172 tokens ( 16.29 ms per token, 61.38 tokens per second) 30.24.757.180 I slot print_timing: id 0 | task 5910 | eval time = 102884.33 ms / 419 tokens ( 246.13 ms per token, 4.06 tokens per second) 30.24.757.181 I slot print_timing: id 0 | task 5910 | total time = 105686.32 ms / 591 tokens 30.24.757.181 I slot print_timing: id 0 | task 5910 | graphs reused = 5549 30.24.757.182 I slot print_timing: id 0 | task 5910 | graph reallocs = 0 / 0 (same size) / (changed size) 30.24.757.229 I slot release: id 0 | task 5910 | stop processing: n_tokens = 1715, truncated = 0 30.24.956.520 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.668 30.24.956.552 I slot launch_slot_: id 0 | task 6340 | processing task, is_child = 0 30.27.039.184 I slot print_timing: id 2 | task 6230 | n_gen = 108, tg = 3.82 t/s, tg_3s = 2.40 t/s 30.30.197.191 I slot print_timing: id 2 | task 6230 | n_gen = 123, tg = 3.92 t/s, tg_3s = 4.75 t/s 30.33.355.084 I slot print_timing: id 2 | task 6230 | n_gen = 138, tg = 3.99 t/s, tg_3s = 4.75 t/s 30.36.512.153 I slot print_timing: id 2 | task 6230 | n_gen = 153, tg = 4.06 t/s, tg_3s = 4.75 t/s 30.37.985.540 I slot print_timing: id 1 | task 6309 | prompt eval time = 2073.28 ms / 87 tokens ( 23.83 ms per token, 41.96 tokens per second) 30.37.985.545 I slot print_timing: id 1 | task 6309 | eval time = 20762.63 ms / 82 tokens ( 256.33 ms per token, 3.90 tokens per second) 30.37.985.545 I slot print_timing: id 1 | task 6309 | total time = 22835.92 ms / 169 tokens 30.37.985.546 I slot print_timing: id 1 | task 6309 | graphs reused = 5601 30.37.985.546 I slot print_timing: id 1 | task 6309 | graph reallocs = 0 / 0 (same size) / (changed size) 30.37.985.589 I slot release: id 1 | task 6309 | stop processing: n_tokens = 1293, truncated = 0 30.38.274.828 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.886 30.38.274.860 I slot launch_slot_: id 1 | task 6396 | processing task, is_child = 0 30.40.129.909 I slot print_timing: id 2 | task 6230 | n_gen = 162, tg = 3.92 t/s, tg_3s = 2.49 t/s 30.43.200.663 I slot print_timing: id 2 | task 6230 | n_gen = 175, tg = 3.94 t/s, tg_3s = 4.23 t/s 30.46.358.589 I slot print_timing: id 2 | task 6230 | n_gen = 190, tg = 4.00 t/s, tg_3s = 4.75 t/s 30.46.569.354 I slot print_timing: id 3 | task 6323 | n_gen = 100, tg = 4.03 t/s, tg_3s = 4.07 t/s 30.49.517.214 I slot print_timing: id 2 | task 6230 | n_gen = 205, tg = 4.04 t/s, tg_3s = 4.75 t/s 30.49.727.920 I slot print_timing: id 3 | task 6323 | n_gen = 115, tg = 4.11 t/s, tg_3s = 4.75 t/s 30.49.937.860 I slot print_timing: id 0 | task 6340 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.37 t/s 30.52.675.014 I slot print_timing: id 2 | task 6230 | n_gen = 220, tg = 4.08 t/s, tg_3s = 4.75 t/s 30.52.885.756 I slot print_timing: id 3 | task 6323 | n_gen = 130, tg = 4.18 t/s, tg_3s = 4.75 t/s 30.53.095.695 I slot print_timing: id 0 | task 6340 | n_gen = 115, tg = 4.38 t/s, tg_3s = 4.75 t/s 30.55.833.470 I slot print_timing: id 2 | task 6230 | n_gen = 235, tg = 4.12 t/s, tg_3s = 4.75 t/s 30.56.044.309 I slot print_timing: id 3 | task 6323 | n_gen = 145, tg = 4.23 t/s, tg_3s = 4.75 t/s 30.56.254.578 I slot print_timing: id 0 | task 6340 | n_gen = 130, tg = 4.42 t/s, tg_3s = 4.75 t/s 30.58.993.435 I slot print_timing: id 2 | task 6230 | n_gen = 250, tg = 4.15 t/s, tg_3s = 4.75 t/s 30.59.204.139 I slot print_timing: id 3 | task 6323 | n_gen = 160, tg = 4.28 t/s, tg_3s = 4.75 t/s 30.59.414.334 I slot print_timing: id 0 | task 6340 | n_gen = 145, tg = 4.45 t/s, tg_3s = 4.75 t/s 31.01.310.871 I slot print_timing: id 2 | task 6230 | prompt eval time = 2305.68 ms / 129 tokens ( 17.87 ms per token, 55.95 tokens per second) 31.01.310.876 I slot print_timing: id 2 | task 6230 | eval time = 62251.90 ms / 261 tokens ( 239.43 ms per token, 4.18 tokens per second) 31.01.310.876 I slot print_timing: id 2 | task 6230 | total time = 64557.58 ms / 390 tokens 31.01.310.877 I slot print_timing: id 2 | task 6230 | graphs reused = 5698 31.01.310.877 I slot print_timing: id 2 | task 6230 | graph reallocs = 0 / 0 (same size) / (changed size) 31.01.310.927 I slot release: id 2 | task 6230 | stop processing: n_tokens = 1514, truncated = 0 31.01.600.678 I slot print_timing: id 1 | task 6396 | n_gen = 100, tg = 4.73 t/s, tg_3s = 4.78 t/s 31.01.600.838 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.757 31.01.600.874 I slot launch_slot_: id 2 | task 6498 | processing task, is_child = 0 31.03.763.661 I slot print_timing: id 0 | task 6340 | n_gen = 156, tg = 4.22 t/s, tg_3s = 2.53 t/s 31.03.764.082 I slot print_timing: id 3 | task 6323 | n_gen = 172, tg = 4.10 t/s, tg_3s = 2.63 t/s 31.04.249.468 I slot print_timing: id 0 | task 6340 | prompt eval time = 2082.36 ms / 118 tokens ( 17.65 ms per token, 56.67 tokens per second) 31.04.249.470 I slot print_timing: id 0 | task 6340 | eval time = 37210.55 ms / 157 tokens ( 238.53 ms per token, 4.19 tokens per second) 31.04.249.471 I slot print_timing: id 0 | task 6340 | total time = 39292.91 ms / 275 tokens 31.04.249.471 I slot print_timing: id 0 | task 6340 | graphs reused = 5698 31.04.249.472 I slot print_timing: id 0 | task 6340 | graph reallocs = 0 / 0 (same size) / (changed size) 31.04.249.519 I slot release: id 0 | task 6340 | stop processing: n_tokens = 1399, truncated = 0 31.04.448.951 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.819 31.04.448.980 I slot launch_slot_: id 0 | task 6502 | processing task, is_child = 0 31.05.818.107 I slot print_timing: id 1 | task 6396 | n_gen = 104, tg = 4.10 t/s, tg_3s = 0.95 t/s 31.06.836.375 I slot print_timing: id 3 | task 6323 | n_gen = 179, tg = 3.97 t/s, tg_3s = 2.28 t/s 31.08.941.632 I slot print_timing: id 1 | task 6396 | n_gen = 118, tg = 4.14 t/s, tg_3s = 4.48 t/s 31.09.994.165 I slot print_timing: id 3 | task 6323 | n_gen = 194, tg = 4.02 t/s, tg_3s = 4.75 t/s 31.12.099.218 I slot print_timing: id 1 | task 6396 | n_gen = 133, tg = 4.20 t/s, tg_3s = 4.75 t/s 31.13.151.904 I slot print_timing: id 3 | task 6323 | n_gen = 209, tg = 4.07 t/s, tg_3s = 4.75 t/s 31.15.256.469 I slot print_timing: id 1 | task 6396 | n_gen = 148, tg = 4.25 t/s, tg_3s = 4.75 t/s 31.16.309.290 I slot print_timing: id 3 | task 6323 | n_gen = 224, tg = 4.11 t/s, tg_3s = 4.75 t/s 31.18.413.799 I slot print_timing: id 1 | task 6396 | n_gen = 163, tg = 4.29 t/s, tg_3s = 4.75 t/s 31.19.467.658 I slot print_timing: id 3 | task 6323 | n_gen = 239, tg = 4.14 t/s, tg_3s = 4.75 t/s 31.21.572.863 I slot print_timing: id 1 | task 6396 | n_gen = 178, tg = 4.33 t/s, tg_3s = 4.75 t/s 31.22.625.496 I slot print_timing: id 3 | task 6323 | n_gen = 254, tg = 4.17 t/s, tg_3s = 4.75 t/s 31.24.732.953 I slot print_timing: id 1 | task 6396 | n_gen = 193, tg = 4.36 t/s, tg_3s = 4.75 t/s 31.25.787.300 I slot print_timing: id 3 | task 6323 | n_gen = 269, tg = 4.20 t/s, tg_3s = 4.74 t/s 31.26.421.029 I slot print_timing: id 2 | task 6498 | n_gen = 100, tg = 4.47 t/s, tg_3s = 4.51 t/s 31.27.053.566 I slot print_timing: id 0 | task 6502 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 31.27.896.880 I slot print_timing: id 1 | task 6396 | n_gen = 208, tg = 4.38 t/s, tg_3s = 4.74 t/s 31.28.950.283 I slot print_timing: id 3 | task 6323 | n_gen = 284, tg = 4.23 t/s, tg_3s = 4.74 t/s 31.29.581.927 I slot print_timing: id 2 | task 6498 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.75 t/s 31.30.003.523 I slot print_timing: id 3 | task 6323 | prompt eval time = 2484.72 ms / 152 tokens ( 16.35 ms per token, 61.17 tokens per second) 31.30.003.530 I slot print_timing: id 3 | task 6323 | eval time = 67987.43 ms / 289 tokens ( 236.07 ms per token, 4.24 tokens per second) 31.30.003.530 I slot print_timing: id 3 | task 6323 | total time = 70472.15 ms / 441 tokens 31.30.003.531 I slot print_timing: id 3 | task 6323 | graphs reused = 5810 31.30.003.531 I slot print_timing: id 3 | task 6323 | graph reallocs = 0 / 0 (same size) / (changed size) 31.30.003.577 I slot release: id 3 | task 6323 | stop processing: n_tokens = 1565, truncated = 0 31.30.201.937 I slot print_timing: id 0 | task 6502 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.76 t/s 31.30.202.246 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.732 31.30.202.273 I slot launch_slot_: id 3 | task 6619 | processing task, is_child = 0 31.31.921.152 I slot print_timing: id 1 | task 6396 | n_gen = 220, tg = 4.27 t/s, tg_3s = 2.98 t/s 31.32.738.292 I slot print_timing: id 2 | task 6498 | n_gen = 122, tg = 4.25 t/s, tg_3s = 2.22 t/s 31.33.369.570 I slot print_timing: id 0 | task 6502 | n_gen = 122, tg = 4.45 t/s, tg_3s = 2.21 t/s 31.35.054.865 I slot print_timing: id 0 | task 6502 | prompt eval time = 1751.90 ms / 92 tokens ( 19.04 ms per token, 52.51 tokens per second) 31.35.054.867 I slot print_timing: id 0 | task 6502 | eval time = 28853.97 ms / 130 tokens ( 223.67 ms per token, 4.47 tokens per second) 31.35.054.868 I slot print_timing: id 0 | task 6502 | total time = 30605.88 ms / 222 tokens 31.35.054.869 I slot print_timing: id 0 | task 6502 | graphs reused = 5822 31.35.054.869 I slot print_timing: id 0 | task 6502 | graph reallocs = 0 / 0 (same size) / (changed size) 31.35.054.914 I slot release: id 0 | task 6502 | stop processing: n_tokens = 1346, truncated = 0 31.35.055.061 I slot print_timing: id 1 | task 6396 | n_gen = 234, tg = 4.28 t/s, tg_3s = 4.47 t/s 31.35.254.055 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.851 31.35.254.086 I slot launch_slot_: id 0 | task 6636 | processing task, is_child = 0 31.36.968.889 I slot print_timing: id 2 | task 6498 | n_gen = 135, tg = 4.10 t/s, tg_3s = 3.07 t/s 31.38.193.948 I slot print_timing: id 1 | task 6396 | n_gen = 241, tg = 4.17 t/s, tg_3s = 2.23 t/s 31.40.090.798 I slot print_timing: id 2 | task 6498 | n_gen = 149, tg = 4.13 t/s, tg_3s = 4.48 t/s 31.41.354.428 I slot print_timing: id 1 | task 6396 | n_gen = 256, tg = 4.20 t/s, tg_3s = 4.75 t/s 31.43.251.222 I slot print_timing: id 2 | task 6498 | n_gen = 164, tg = 4.18 t/s, tg_3s = 4.75 t/s 31.44.514.523 I slot print_timing: id 1 | task 6396 | n_gen = 271, tg = 4.23 t/s, tg_3s = 4.75 t/s 31.46.410.471 I slot print_timing: id 2 | task 6498 | n_gen = 179, tg = 4.22 t/s, tg_3s = 4.75 t/s 31.47.253.983 I slot print_timing: id 2 | task 6498 | prompt eval time = 2649.11 ms / 135 tokens ( 19.62 ms per token, 50.96 tokens per second) 31.47.253.985 I slot print_timing: id 2 | task 6498 | eval time = 43003.99 ms / 183 tokens ( 236.29 ms per token, 4.23 tokens per second) 31.47.253.986 I slot print_timing: id 2 | task 6498 | total time = 45653.10 ms / 318 tokens 31.47.253.987 I slot print_timing: id 2 | task 6498 | graphs reused = 5869 31.47.253.987 I slot print_timing: id 2 | task 6498 | graph reallocs = 0 / 0 (same size) / (changed size) 31.47.254.037 I slot release: id 2 | task 6498 | stop processing: n_tokens = 1442, truncated = 0 31.47.543.647 I slot print_timing: id 1 | task 6396 | n_gen = 285, tg = 4.25 t/s, tg_3s = 4.62 t/s 31.47.543.811 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.795 31.47.543.856 I slot launch_slot_: id 2 | task 6687 | processing task, is_child = 0 31.50.564.645 I slot print_timing: id 1 | task 6396 | n_gen = 292, tg = 4.16 t/s, tg_3s = 2.32 t/s 31.53.723.644 I slot print_timing: id 1 | task 6396 | n_gen = 307, tg = 4.19 t/s, tg_3s = 4.75 t/s 31.56.462.039 I slot print_timing: id 3 | task 6619 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 31.56.882.742 I slot print_timing: id 1 | task 6396 | n_gen = 322, tg = 4.21 t/s, tg_3s = 4.75 t/s 31.59.620.412 I slot print_timing: id 3 | task 6619 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.75 t/s 31.59.830.664 I slot print_timing: id 0 | task 6636 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 32.00.041.424 I slot print_timing: id 1 | task 6396 | n_gen = 337, tg = 4.23 t/s, tg_3s = 4.75 t/s 32.02.779.414 I slot print_timing: id 3 | task 6619 | n_gen = 130, tg = 4.23 t/s, tg_3s = 4.75 t/s 32.02.989.479 I slot print_timing: id 0 | task 6636 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 32.03.200.088 I slot print_timing: id 1 | task 6396 | n_gen = 352, tg = 4.25 t/s, tg_3s = 4.75 t/s 32.05.938.426 I slot print_timing: id 3 | task 6619 | n_gen = 145, tg = 4.28 t/s, tg_3s = 4.75 t/s 32.06.148.645 I slot print_timing: id 0 | task 6636 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.75 t/s 32.06.359.352 I slot print_timing: id 1 | task 6396 | n_gen = 367, tg = 4.27 t/s, tg_3s = 4.75 t/s 32.09.098.709 I slot print_timing: id 3 | task 6619 | n_gen = 160, tg = 4.32 t/s, tg_3s = 4.75 t/s 32.09.308.643 I slot print_timing: id 0 | task 6636 | n_gen = 145, tg = 4.51 t/s, tg_3s = 4.75 t/s 32.09.519.452 I slot print_timing: id 1 | task 6396 | n_gen = 382, tg = 4.29 t/s, tg_3s = 4.75 t/s 32.10.361.684 I slot print_timing: id 2 | task 6687 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 32.10.572.219 I slot print_timing: id 1 | task 6396 | prompt eval time = 2397.39 ms / 110 tokens ( 21.79 ms per token, 45.88 tokens per second) 32.10.572.225 I slot print_timing: id 1 | task 6396 | eval time = 89899.96 ms / 387 tokens ( 232.90 ms per token, 4.29 tokens per second) 32.10.572.226 I slot print_timing: id 1 | task 6396 | total time = 92297.35 ms / 497 tokens 32.10.572.226 I slot print_timing: id 1 | task 6396 | graphs reused = 5967 32.10.572.227 I slot print_timing: id 1 | task 6396 | graph reallocs = 0 / 0 (same size) / (changed size) 32.10.572.275 I slot release: id 1 | task 6396 | stop processing: n_tokens = 1621, truncated = 0 32.10.862.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.707 32.10.862.438 I slot launch_slot_: id 1 | task 6791 | processing task, is_child = 0 32.12.403.881 I slot print_timing: id 0 | task 6636 | n_gen = 153, tg = 4.34 t/s, tg_3s = 2.58 t/s 32.12.404.218 I slot print_timing: id 3 | task 6619 | n_gen = 169, tg = 4.19 t/s, tg_3s = 2.72 t/s 32.13.371.091 I slot print_timing: id 2 | task 6687 | n_gen = 106, tg = 4.40 t/s, tg_3s = 1.99 t/s 32.15.475.055 I slot print_timing: id 0 | task 6636 | n_gen = 166, tg = 4.33 t/s, tg_3s = 4.23 t/s 32.15.475.502 I slot print_timing: id 3 | task 6619 | n_gen = 182, tg = 4.19 t/s, tg_3s = 4.23 t/s 32.16.527.951 I slot print_timing: id 2 | task 6687 | n_gen = 121, tg = 4.44 t/s, tg_3s = 4.75 t/s 32.18.634.710 I slot print_timing: id 0 | task 6636 | n_gen = 181, tg = 4.36 t/s, tg_3s = 4.75 t/s 32.18.635.133 I slot print_timing: id 3 | task 6619 | n_gen = 197, tg = 4.23 t/s, tg_3s = 4.75 t/s 32.19.688.027 I slot print_timing: id 2 | task 6687 | n_gen = 136, tg = 4.47 t/s, tg_3s = 4.75 t/s 32.21.794.096 I slot print_timing: id 0 | task 6636 | n_gen = 196, tg = 4.39 t/s, tg_3s = 4.75 t/s 32.21.794.488 I slot print_timing: id 3 | task 6619 | n_gen = 212, tg = 4.26 t/s, tg_3s = 4.75 t/s 32.22.636.830 I slot print_timing: id 3 | task 6619 | prompt eval time = 2112.84 ms / 120 tokens ( 17.61 ms per token, 56.80 tokens per second) 32.22.636.836 I slot print_timing: id 3 | task 6619 | eval time = 50321.71 ms / 216 tokens ( 234.05 ms per token, 4.27 tokens per second) 32.22.636.837 I slot print_timing: id 3 | task 6619 | total time = 52434.55 ms / 336 tokens 32.22.636.837 I slot print_timing: id 3 | task 6619 | graphs reused = 6012 32.22.636.838 I slot print_timing: id 3 | task 6619 | graph reallocs = 0 / 0 (same size) / (changed size) 32.22.636.886 I slot release: id 3 | task 6619 | stop processing: n_tokens = 1460, truncated = 0 32.22.835.329 I slot print_timing: id 2 | task 6687 | n_gen = 151, tg = 4.50 t/s, tg_3s = 4.77 t/s 32.22.835.337 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.785 32.22.835.364 I slot launch_slot_: id 3 | task 6841 | processing task, is_child = 0 32.24.945.695 I slot print_timing: id 0 | task 6636 | n_gen = 203, tg = 4.24 t/s, tg_3s = 2.22 t/s 32.26.000.511 I slot print_timing: id 2 | task 6687 | n_gen = 158, tg = 4.30 t/s, tg_3s = 2.21 t/s 32.28.106.334 I slot print_timing: id 0 | task 6636 | n_gen = 218, tg = 4.28 t/s, tg_3s = 4.75 t/s 32.29.159.255 I slot print_timing: id 2 | task 6687 | n_gen = 173, tg = 4.34 t/s, tg_3s = 4.75 t/s 32.31.264.930 I slot print_timing: id 0 | task 6636 | n_gen = 233, tg = 4.30 t/s, tg_3s = 4.75 t/s 32.32.317.628 I slot print_timing: id 2 | task 6687 | n_gen = 188, tg = 4.37 t/s, tg_3s = 4.75 t/s 32.34.422.311 I slot print_timing: id 0 | task 6636 | n_gen = 248, tg = 4.33 t/s, tg_3s = 4.75 t/s 32.35.475.093 I slot print_timing: id 1 | task 6791 | n_gen = 100, tg = 4.39 t/s, tg_3s = 4.44 t/s 32.35.475.251 I slot print_timing: id 2 | task 6687 | n_gen = 203, tg = 4.39 t/s, tg_3s = 4.75 t/s 32.36.739.465 I slot print_timing: id 1 | task 6791 | prompt eval time = 2085.37 ms / 98 tokens ( 21.28 ms per token, 46.99 tokens per second) 32.36.739.468 I slot print_timing: id 1 | task 6791 | eval time = 23791.65 ms / 106 tokens ( 226.59 ms per token, 4.41 tokens per second) 32.36.739.469 I slot print_timing: id 1 | task 6791 | total time = 25877.02 ms / 204 tokens 32.36.739.469 I slot print_timing: id 1 | task 6791 | graphs reused = 6067 32.36.739.469 I slot print_timing: id 1 | task 6791 | graph reallocs = 0 / 0 (same size) / (changed size) 32.36.739.512 I slot release: id 1 | task 6791 | stop processing: n_tokens = 1328, truncated = 0 32.37.029.221 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.863 32.37.029.267 I slot launch_slot_: id 1 | task 6901 | processing task, is_child = 0 32.38.907.462 I slot print_timing: id 0 | task 6636 | n_gen = 261, tg = 4.22 t/s, tg_3s = 2.90 t/s 32.38.907.618 I slot print_timing: id 2 | task 6687 | n_gen = 211, tg = 4.25 t/s, tg_3s = 2.33 t/s 32.41.979.796 I slot print_timing: id 0 | task 6636 | n_gen = 274, tg = 4.22 t/s, tg_3s = 4.23 t/s 32.41.980.063 I slot print_timing: id 2 | task 6687 | n_gen = 224, tg = 4.25 t/s, tg_3s = 4.23 t/s 32.45.140.969 I slot print_timing: id 0 | task 6636 | n_gen = 289, tg = 4.25 t/s, tg_3s = 4.75 t/s 32.45.141.253 I slot print_timing: id 2 | task 6687 | n_gen = 239, tg = 4.28 t/s, tg_3s = 4.75 t/s 32.47.881.301 I slot print_timing: id 3 | task 6841 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 32.48.301.856 I slot print_timing: id 0 | task 6636 | n_gen = 304, tg = 4.27 t/s, tg_3s = 4.75 t/s 32.48.302.143 I slot print_timing: id 2 | task 6687 | n_gen = 254, tg = 4.30 t/s, tg_3s = 4.75 t/s 32.51.042.674 I slot print_timing: id 3 | task 6841 | n_gen = 115, tg = 4.37 t/s, tg_3s = 4.74 t/s 32.51.463.435 I slot print_timing: id 0 | task 6636 | n_gen = 319, tg = 4.29 t/s, tg_3s = 4.74 t/s 32.51.463.720 I slot print_timing: id 2 | task 6687 | n_gen = 269, tg = 4.33 t/s, tg_3s = 4.74 t/s 32.54.201.705 I slot print_timing: id 3 | task 6841 | n_gen = 130, tg = 4.41 t/s, tg_3s = 4.75 t/s 32.54.622.634 I slot print_timing: id 0 | task 6636 | n_gen = 334, tg = 4.31 t/s, tg_3s = 4.75 t/s 32.54.622.915 I slot print_timing: id 2 | task 6687 | n_gen = 284, tg = 4.35 t/s, tg_3s = 4.75 t/s 32.57.363.072 I slot print_timing: id 3 | task 6841 | n_gen = 145, tg = 4.44 t/s, tg_3s = 4.74 t/s 32.57.784.076 I slot print_timing: id 0 | task 6636 | n_gen = 349, tg = 4.33 t/s, tg_3s = 4.74 t/s 32.57.784.351 I slot print_timing: id 2 | task 6687 | n_gen = 299, tg = 4.36 t/s, tg_3s = 4.74 t/s 33.00.312.354 I slot print_timing: id 1 | task 6901 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 33.00.523.250 I slot print_timing: id 3 | task 6841 | n_gen = 160, tg = 4.47 t/s, tg_3s = 4.75 t/s 33.00.944.301 I slot print_timing: id 0 | task 6636 | n_gen = 364, tg = 4.34 t/s, tg_3s = 4.75 t/s 33.00.944.564 I slot print_timing: id 2 | task 6687 | n_gen = 314, tg = 4.38 t/s, tg_3s = 4.75 t/s 33.02.419.331 I slot print_timing: id 0 | task 6636 | prompt eval time = 2095.52 ms / 131 tokens ( 16.00 ms per token, 62.51 tokens per second) 33.02.419.333 I slot print_timing: id 0 | task 6636 | eval time = 85069.71 ms / 371 tokens ( 229.92 ms per token, 4.35 tokens per second) 33.02.419.333 I slot print_timing: id 0 | task 6636 | total time = 87165.24 ms / 502 tokens 33.02.419.334 I slot print_timing: id 0 | task 6636 | graphs reused = 6174 33.02.419.334 I slot print_timing: id 0 | task 6636 | graph reallocs = 0 / 0 (same size) / (changed size) 33.02.419.378 I slot release: id 0 | task 6636 | stop processing: n_tokens = 1626, truncated = 0 33.02.618.378 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.705 33.02.618.406 I slot launch_slot_: id 0 | task 7014 | processing task, is_child = 0 33.04.304.520 I slot print_timing: id 1 | task 6901 | n_gen = 112, tg = 4.47 t/s, tg_3s = 3.01 t/s 33.04.304.705 I slot print_timing: id 2 | task 6687 | n_gen = 323, tg = 4.31 t/s, tg_3s = 2.68 t/s 33.04.304.920 I slot print_timing: id 3 | task 6841 | n_gen = 171, tg = 4.32 t/s, tg_3s = 2.91 t/s 33.07.428.337 I slot print_timing: id 1 | task 6901 | n_gen = 126, tg = 4.47 t/s, tg_3s = 4.48 t/s 33.07.428.500 I slot print_timing: id 2 | task 6687 | n_gen = 337, tg = 4.31 t/s, tg_3s = 4.48 t/s 33.07.428.655 I slot print_timing: id 3 | task 6841 | n_gen = 185, tg = 4.33 t/s, tg_3s = 4.48 t/s 33.09.745.639 I slot print_timing: id 2 | task 6687 | prompt eval time = 1965.98 ms / 95 tokens ( 20.69 ms per token, 48.32 tokens per second) 33.09.745.644 I slot print_timing: id 2 | task 6687 | eval time = 80235.80 ms / 348 tokens ( 231.23 ms per token, 4.32 tokens per second) 33.09.745.645 I slot print_timing: id 2 | task 6687 | total time = 82201.77 ms / 443 tokens 33.09.745.645 I slot print_timing: id 2 | task 6687 | graphs reused = 6198 33.09.745.646 I slot print_timing: id 2 | task 6687 | graph reallocs = 0 / 0 (same size) / (changed size) 33.09.745.691 I slot release: id 2 | task 6687 | stop processing: n_tokens = 1567, truncated = 0 33.10.035.033 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.731 33.10.035.083 I slot launch_slot_: id 2 | task 7042 | processing task, is_child = 0 33.11.845.931 I slot print_timing: id 1 | task 6901 | n_gen = 139, tg = 4.26 t/s, tg_3s = 2.94 t/s 33.11.846.088 I slot print_timing: id 3 | task 6841 | n_gen = 198, tg = 4.20 t/s, tg_3s = 2.94 t/s 33.14.859.446 I slot print_timing: id 1 | task 6901 | n_gen = 152, tg = 4.26 t/s, tg_3s = 4.31 t/s 33.14.859.716 I slot print_timing: id 3 | task 6841 | n_gen = 211, tg = 4.21 t/s, tg_3s = 4.31 t/s 33.18.015.349 I slot print_timing: id 1 | task 6901 | n_gen = 167, tg = 4.30 t/s, tg_3s = 4.75 t/s 33.18.015.643 I slot print_timing: id 3 | task 6841 | n_gen = 226, tg = 4.24 t/s, tg_3s = 4.75 t/s 33.21.175.829 I slot print_timing: id 1 | task 6901 | n_gen = 182, tg = 4.34 t/s, tg_3s = 4.75 t/s 33.21.176.123 I slot print_timing: id 3 | task 6841 | n_gen = 241, tg = 4.27 t/s, tg_3s = 4.75 t/s 33.24.337.086 I slot print_timing: id 1 | task 6901 | n_gen = 197, tg = 4.37 t/s, tg_3s = 4.74 t/s 33.24.337.387 I slot print_timing: id 3 | task 6841 | n_gen = 256, tg = 4.29 t/s, tg_3s = 4.74 t/s 33.27.496.045 I slot print_timing: id 0 | task 7014 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 33.27.496.197 I slot print_timing: id 1 | task 6901 | n_gen = 212, tg = 4.39 t/s, tg_3s = 4.75 t/s 33.27.496.491 I slot print_timing: id 3 | task 6841 | n_gen = 271, tg = 4.32 t/s, tg_3s = 4.75 t/s 33.30.654.130 I slot print_timing: id 0 | task 7014 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.75 t/s 33.30.654.270 I slot print_timing: id 1 | task 6901 | n_gen = 227, tg = 4.41 t/s, tg_3s = 4.75 t/s 33.30.654.544 I slot print_timing: id 3 | task 6841 | n_gen = 286, tg = 4.34 t/s, tg_3s = 4.75 t/s 33.33.185.487 I slot print_timing: id 2 | task 7042 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.79 t/s 33.33.816.236 I slot print_timing: id 0 | task 7014 | n_gen = 130, tg = 4.43 t/s, tg_3s = 4.74 t/s 33.33.816.385 I slot print_timing: id 1 | task 6901 | n_gen = 242, tg = 4.43 t/s, tg_3s = 4.74 t/s 33.33.816.657 I slot print_timing: id 3 | task 6841 | n_gen = 301, tg = 4.36 t/s, tg_3s = 4.74 t/s 33.36.343.848 I slot print_timing: id 2 | task 7042 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 33.36.975.311 I slot print_timing: id 0 | task 7014 | n_gen = 145, tg = 4.46 t/s, tg_3s = 4.75 t/s 33.36.975.450 I slot print_timing: id 1 | task 6901 | n_gen = 257, tg = 4.45 t/s, tg_3s = 4.75 t/s 33.36.975.734 I slot print_timing: id 3 | task 6841 | n_gen = 316, tg = 4.37 t/s, tg_3s = 4.75 t/s 33.39.501.922 I slot print_timing: id 2 | task 7042 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 33.40.133.712 I slot print_timing: id 0 | task 7014 | n_gen = 160, tg = 4.49 t/s, tg_3s = 4.75 t/s 33.40.133.860 I slot print_timing: id 1 | task 6901 | n_gen = 272, tg = 4.47 t/s, tg_3s = 4.75 t/s 33.40.134.138 I slot print_timing: id 3 | task 6841 | n_gen = 331, tg = 4.39 t/s, tg_3s = 4.75 t/s 33.41.398.308 I slot print_timing: id 3 | task 6841 | prompt eval time = 2110.76 ms / 116 tokens ( 18.20 ms per token, 54.96 tokens per second) 33.41.398.311 I slot print_timing: id 3 | task 6841 | eval time = 76452.17 ms / 337 tokens ( 227.54 ms per token, 4.39 tokens per second) 33.41.398.312 I slot print_timing: id 3 | task 6841 | total time = 78562.94 ms / 453 tokens 33.41.398.312 I slot print_timing: id 3 | task 6841 | graphs reused = 6334 33.41.398.313 I slot print_timing: id 3 | task 6841 | graph reallocs = 0 / 0 (same size) / (changed size) 33.41.398.371 I slot release: id 3 | task 6841 | stop processing: n_tokens = 1577, truncated = 0 33.41.596.183 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.727 33.41.596.219 I slot launch_slot_: id 3 | task 7184 | processing task, is_child = 0 33.43.314.290 I slot print_timing: id 0 | task 7014 | n_gen = 168, tg = 4.32 t/s, tg_3s = 2.52 t/s 33.43.314.476 I slot print_timing: id 1 | task 6901 | n_gen = 280, tg = 4.37 t/s, tg_3s = 2.52 t/s 33.43.314.694 I slot print_timing: id 2 | task 7042 | n_gen = 141, tg = 4.52 t/s, tg_3s = 2.89 t/s 33.46.451.073 I slot print_timing: id 0 | task 7014 | n_gen = 182, tg = 4.33 t/s, tg_3s = 4.46 t/s 33.46.451.223 I slot print_timing: id 1 | task 6901 | n_gen = 294, tg = 4.37 t/s, tg_3s = 4.46 t/s 33.46.451.371 I slot print_timing: id 2 | task 7042 | n_gen = 155, tg = 4.51 t/s, tg_3s = 4.46 t/s 33.46.661.747 I slot print_timing: id 1 | task 6901 | prompt eval time = 2421.77 ms / 130 tokens ( 18.63 ms per token, 53.68 tokens per second) 33.46.661.756 I slot print_timing: id 1 | task 6901 | eval time = 67210.70 ms / 295 tokens ( 228.61 ms per token, 4.37 tokens per second) 33.46.661.757 I slot print_timing: id 1 | task 6901 | total time = 69632.48 ms / 425 tokens 33.46.661.758 I slot print_timing: id 1 | task 6901 | graphs reused = 6346 33.46.661.758 I slot print_timing: id 1 | task 6901 | graph reallocs = 0 / 0 (same size) / (changed size) 33.46.661.822 I slot release: id 1 | task 6901 | stop processing: n_tokens = 1549, truncated = 0 33.46.951.897 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.740 33.46.951.932 I slot launch_slot_: id 1 | task 7202 | processing task, is_child = 0 33.49.574.562 I slot print_timing: id 0 | task 7014 | n_gen = 187, tg = 4.14 t/s, tg_3s = 1.60 t/s 33.49.574.899 I slot print_timing: id 2 | task 7042 | n_gen = 160, tg = 4.27 t/s, tg_3s = 1.60 t/s 33.52.732.121 I slot print_timing: id 0 | task 7014 | n_gen = 202, tg = 4.18 t/s, tg_3s = 4.75 t/s 33.52.732.398 I slot print_timing: id 2 | task 7042 | n_gen = 175, tg = 4.31 t/s, tg_3s = 4.75 t/s 33.55.889.936 I slot print_timing: id 0 | task 7014 | n_gen = 217, tg = 4.22 t/s, tg_3s = 4.75 t/s 33.55.890.208 I slot print_timing: id 2 | task 7042 | n_gen = 190, tg = 4.34 t/s, tg_3s = 4.75 t/s 33.59.045.169 I slot print_timing: id 0 | task 7014 | n_gen = 232, tg = 4.25 t/s, tg_3s = 4.75 t/s 33.59.045.454 I slot print_timing: id 2 | task 7042 | n_gen = 205, tg = 4.37 t/s, tg_3s = 4.75 t/s 34.02.202.262 I slot print_timing: id 0 | task 7014 | n_gen = 247, tg = 4.28 t/s, tg_3s = 4.75 t/s 34.02.202.540 I slot print_timing: id 2 | task 7042 | n_gen = 220, tg = 4.39 t/s, tg_3s = 4.75 t/s 34.03.886.073 I slot print_timing: id 0 | task 7014 | prompt eval time = 2068.64 ms / 103 tokens ( 20.08 ms per token, 49.79 tokens per second) 34.03.886.079 I slot print_timing: id 0 | task 7014 | eval time = 59199.02 ms / 255 tokens ( 233.07 ms per token, 4.29 tokens per second) 34.03.886.079 I slot print_timing: id 0 | task 7014 | total time = 61267.66 ms / 358 tokens 34.03.886.080 I slot print_timing: id 0 | task 7014 | graphs reused = 6414 34.03.886.080 I slot print_timing: id 0 | task 7014 | graph reallocs = 0 / 0 (same size) / (changed size) 34.03.886.127 I slot release: id 0 | task 7014 | stop processing: n_tokens = 1482, truncated = 0 34.04.085.049 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.773 34.04.085.082 I slot launch_slot_: id 0 | task 7275 | processing task, is_child = 0 34.05.784.065 I slot print_timing: id 2 | task 7042 | n_gen = 230, tg = 4.28 t/s, tg_3s = 2.79 t/s 34.08.273.716 I slot print_timing: id 3 | task 7184 | n_gen = 100, tg = 4.03 t/s, tg_3s = 4.07 t/s 34.08.904.770 I slot print_timing: id 2 | task 7042 | n_gen = 244, tg = 4.30 t/s, tg_3s = 4.49 t/s 34.11.431.779 I slot print_timing: id 3 | task 7184 | n_gen = 115, tg = 4.11 t/s, tg_3s = 4.75 t/s 34.11.851.674 I slot print_timing: id 1 | task 7202 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 34.12.062.357 I slot print_timing: id 2 | task 7042 | n_gen = 259, tg = 4.32 t/s, tg_3s = 4.75 t/s 34.14.587.757 I slot print_timing: id 3 | task 7184 | n_gen = 130, tg = 4.18 t/s, tg_3s = 4.75 t/s 34.15.009.826 I slot print_timing: id 1 | task 7202 | n_gen = 115, tg = 4.44 t/s, tg_3s = 4.75 t/s 34.15.221.456 I slot print_timing: id 2 | task 7042 | n_gen = 274, tg = 4.34 t/s, tg_3s = 4.75 t/s 34.17.746.733 I slot print_timing: id 3 | task 7184 | n_gen = 145, tg = 4.23 t/s, tg_3s = 4.75 t/s 34.18.168.599 I slot print_timing: id 1 | task 7202 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.75 t/s 34.18.379.332 I slot print_timing: id 2 | task 7042 | n_gen = 289, tg = 4.36 t/s, tg_3s = 4.75 t/s 34.20.910.633 I slot print_timing: id 3 | task 7184 | n_gen = 160, tg = 4.27 t/s, tg_3s = 4.74 t/s 34.21.331.275 I slot print_timing: id 1 | task 7202 | n_gen = 145, tg = 4.50 t/s, tg_3s = 4.74 t/s 34.21.541.697 I slot print_timing: id 2 | task 7042 | n_gen = 304, tg = 4.38 t/s, tg_3s = 4.74 t/s 34.24.068.129 I slot print_timing: id 3 | task 7184 | n_gen = 175, tg = 4.31 t/s, tg_3s = 4.75 t/s 34.24.490.186 I slot print_timing: id 1 | task 7202 | n_gen = 160, tg = 4.53 t/s, tg_3s = 4.75 t/s 34.24.700.907 I slot print_timing: id 2 | task 7042 | n_gen = 319, tg = 4.39 t/s, tg_3s = 4.75 t/s 34.27.017.807 I slot print_timing: id 0 | task 7275 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 34.27.228.856 I slot print_timing: id 3 | task 7184 | n_gen = 190, tg = 4.34 t/s, tg_3s = 4.75 t/s 34.27.649.020 I slot print_timing: id 1 | task 7202 | n_gen = 175, tg = 4.54 t/s, tg_3s = 4.75 t/s 34.27.860.147 I slot print_timing: id 2 | task 7042 | n_gen = 334, tg = 4.41 t/s, tg_3s = 4.75 t/s 34.30.179.108 I slot print_timing: id 0 | task 7275 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.74 t/s 34.30.390.252 I slot print_timing: id 3 | task 7184 | n_gen = 205, tg = 4.37 t/s, tg_3s = 4.74 t/s 34.30.812.297 I slot print_timing: id 1 | task 7202 | n_gen = 190, tg = 4.56 t/s, tg_3s = 4.74 t/s 34.31.023.235 I slot print_timing: id 2 | task 7042 | n_gen = 349, tg = 4.42 t/s, tg_3s = 4.74 t/s 34.33.339.584 I slot print_timing: id 0 | task 7275 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 34.33.550.352 I slot print_timing: id 3 | task 7184 | n_gen = 220, tg = 4.39 t/s, tg_3s = 4.75 t/s 34.33.971.444 I slot print_timing: id 1 | task 7202 | n_gen = 205, tg = 4.57 t/s, tg_3s = 4.75 t/s 34.34.182.219 I slot print_timing: id 2 | task 7042 | n_gen = 364, tg = 4.43 t/s, tg_3s = 4.75 t/s 34.36.289.649 I slot print_timing: id 1 | task 7202 | prompt eval time = 2411.08 ms / 123 tokens ( 19.60 ms per token, 51.01 tokens per second) 34.36.289.653 I slot print_timing: id 1 | task 7202 | eval time = 46926.63 ms / 216 tokens ( 218.26 ms per token, 4.58 tokens per second) 34.36.289.654 I slot print_timing: id 1 | task 7202 | total time = 49337.71 ms / 339 tokens 34.36.289.654 I slot print_timing: id 1 | task 7202 | graphs reused = 6556 34.36.289.655 I slot print_timing: id 1 | task 7202 | graph reallocs = 0 / 0 (same size) / (changed size) 34.36.289.698 I slot release: id 1 | task 7202 | stop processing: n_tokens = 1463, truncated = 0 34.36.579.299 I slot print_timing: id 0 | task 7275 | n_gen = 145, tg = 4.73 t/s, tg_3s = 4.63 t/s 34.36.579.591 I slot print_timing: id 3 | task 7184 | n_gen = 234, tg = 4.41 t/s, tg_3s = 4.62 t/s 34.36.579.602 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.783 34.36.579.634 I slot launch_slot_: id 1 | task 7422 | processing task, is_child = 0 34.38.108.114 I slot print_timing: id 2 | task 7042 | n_gen = 376, tg = 4.37 t/s, tg_3s = 3.06 t/s 34.39.705.615 I slot print_timing: id 0 | task 7275 | n_gen = 152, tg = 4.50 t/s, tg_3s = 2.24 t/s 34.39.706.050 I slot print_timing: id 3 | task 7184 | n_gen = 241, tg = 4.29 t/s, tg_3s = 2.24 t/s 34.41.180.486 I slot print_timing: id 2 | task 7042 | n_gen = 389, tg = 4.37 t/s, tg_3s = 4.23 t/s 34.42.865.194 I slot print_timing: id 0 | task 7275 | n_gen = 167, tg = 4.52 t/s, tg_3s = 4.75 t/s 34.42.865.604 I slot print_timing: id 3 | task 7184 | n_gen = 256, tg = 4.31 t/s, tg_3s = 4.75 t/s 34.44.340.414 I slot print_timing: id 2 | task 7042 | n_gen = 404, tg = 4.38 t/s, tg_3s = 4.75 t/s 34.46.025.518 I slot print_timing: id 0 | task 7275 | n_gen = 182, tg = 4.54 t/s, tg_3s = 4.75 t/s 34.46.025.924 I slot print_timing: id 3 | task 7184 | n_gen = 271, tg = 4.33 t/s, tg_3s = 4.75 t/s 34.47.501.793 I slot print_timing: id 2 | task 7042 | n_gen = 419, tg = 4.39 t/s, tg_3s = 4.74 t/s 34.48.976.554 I slot print_timing: id 2 | task 7042 | prompt eval time = 2295.05 ms / 122 tokens ( 18.81 ms per token, 53.16 tokens per second) 34.48.976.560 I slot print_timing: id 2 | task 7042 | eval time = 96646.41 ms / 426 tokens ( 227.40 ms per token, 4.40 tokens per second) 34.48.976.560 I slot print_timing: id 2 | task 7042 | total time = 98941.46 ms / 548 tokens 34.48.976.560 I slot print_timing: id 2 | task 7042 | graphs reused = 6604 34.48.976.561 I slot print_timing: id 2 | task 7042 | graph reallocs = 0 / 0 (same size) / (changed size) 34.48.976.606 I slot release: id 2 | task 7042 | stop processing: n_tokens = 1672, truncated = 0 34.49.265.864 I slot print_timing: id 0 | task 7275 | n_gen = 197, tg = 4.55 t/s, tg_3s = 4.63 t/s 34.49.266.156 I slot print_timing: id 3 | task 7184 | n_gen = 286, tg = 4.35 t/s, tg_3s = 4.63 t/s 34.49.266.163 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.685 34.49.266.192 I slot launch_slot_: id 2 | task 7475 | processing task, is_child = 0 34.52.284.818 I slot print_timing: id 0 | task 7275 | n_gen = 204, tg = 4.40 t/s, tg_3s = 2.32 t/s 34.52.285.257 I slot print_timing: id 3 | task 7184 | n_gen = 293, tg = 4.26 t/s, tg_3s = 2.32 t/s 34.55.445.168 I slot print_timing: id 0 | task 7275 | n_gen = 219, tg = 4.42 t/s, tg_3s = 4.75 t/s 34.55.445.603 I slot print_timing: id 3 | task 7184 | n_gen = 308, tg = 4.28 t/s, tg_3s = 4.75 t/s 34.58.603.864 I slot print_timing: id 0 | task 7275 | n_gen = 234, tg = 4.44 t/s, tg_3s = 4.75 t/s 34.58.604.298 I slot print_timing: id 3 | task 7184 | n_gen = 323, tg = 4.30 t/s, tg_3s = 4.75 t/s 35.01.131.870 I slot print_timing: id 1 | task 7422 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 35.01.763.225 I slot print_timing: id 0 | task 7275 | n_gen = 249, tg = 4.46 t/s, tg_3s = 4.75 t/s 35.01.763.645 I slot print_timing: id 3 | task 7184 | n_gen = 338, tg = 4.32 t/s, tg_3s = 4.75 t/s 35.04.291.918 I slot print_timing: id 1 | task 7422 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 35.04.923.351 I slot print_timing: id 0 | task 7275 | n_gen = 264, tg = 4.48 t/s, tg_3s = 4.75 t/s 35.04.923.757 I slot print_timing: id 3 | task 7184 | n_gen = 353, tg = 4.33 t/s, tg_3s = 4.75 t/s 35.07.451.879 I slot print_timing: id 1 | task 7422 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.75 t/s 35.08.083.701 I slot print_timing: id 0 | task 7275 | n_gen = 279, tg = 4.49 t/s, tg_3s = 4.75 t/s 35.08.084.109 I slot print_timing: id 3 | task 7184 | n_gen = 368, tg = 4.35 t/s, tg_3s = 4.75 t/s 35.08.505.335 I slot print_timing: id 2 | task 7475 | prompt eval time = 1962.45 ms / 95 tokens ( 20.66 ms per token, 48.41 tokens per second) 35.08.505.341 I slot print_timing: id 2 | task 7475 | eval time = 17276.68 ms / 83 tokens ( 210.69 ms per token, 4.75 tokens per second) 35.08.505.341 I slot print_timing: id 2 | task 7475 | total time = 19239.14 ms / 178 tokens 35.08.505.342 I slot print_timing: id 2 | task 7475 | graphs reused = 6685 35.08.505.342 I slot print_timing: id 2 | task 7475 | graph reallocs = 0 / 0 (same size) / (changed size) 35.08.505.388 I slot release: id 2 | task 7475 | stop processing: n_tokens = 1302, truncated = 0 35.08.795.082 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.880 35.08.795.115 I slot launch_slot_: id 2 | task 7561 | processing task, is_child = 0 35.10.975.169 I slot print_timing: id 1 | task 7422 | n_gen = 137, tg = 4.21 t/s, tg_3s = 1.99 t/s 35.11.460.905 I slot print_timing: id 0 | task 7275 | n_gen = 284, tg = 4.33 t/s, tg_3s = 1.48 t/s 35.11.461.445 I slot print_timing: id 3 | task 7184 | n_gen = 373, tg = 4.24 t/s, tg_3s = 1.48 t/s 35.13.992.280 I slot print_timing: id 1 | task 7422 | n_gen = 150, tg = 4.22 t/s, tg_3s = 4.31 t/s 35.14.624.257 I slot print_timing: id 0 | task 7275 | n_gen = 299, tg = 4.35 t/s, tg_3s = 4.74 t/s 35.14.624.681 I slot print_timing: id 3 | task 7184 | n_gen = 388, tg = 4.26 t/s, tg_3s = 4.74 t/s 35.17.152.666 I slot print_timing: id 1 | task 7422 | n_gen = 165, tg = 4.26 t/s, tg_3s = 4.75 t/s 35.17.785.420 I slot print_timing: id 0 | task 7275 | n_gen = 314, tg = 4.37 t/s, tg_3s = 4.75 t/s 35.17.785.839 I slot print_timing: id 3 | task 7184 | n_gen = 403, tg = 4.27 t/s, tg_3s = 4.75 t/s 35.20.314.660 I slot print_timing: id 1 | task 7422 | n_gen = 180, tg = 4.30 t/s, tg_3s = 4.74 t/s 35.20.946.657 I slot print_timing: id 0 | task 7275 | n_gen = 329, tg = 4.39 t/s, tg_3s = 4.74 t/s 35.20.947.064 I slot print_timing: id 3 | task 7184 | n_gen = 418, tg = 4.29 t/s, tg_3s = 4.74 t/s 35.23.476.715 I slot print_timing: id 1 | task 7422 | n_gen = 195, tg = 4.33 t/s, tg_3s = 4.74 t/s 35.24.108.832 I slot print_timing: id 0 | task 7275 | n_gen = 344, tg = 4.40 t/s, tg_3s = 4.74 t/s 35.24.109.255 I slot print_timing: id 3 | task 7184 | n_gen = 433, tg = 4.30 t/s, tg_3s = 4.74 t/s 35.26.639.489 I slot print_timing: id 1 | task 7422 | n_gen = 210, tg = 4.36 t/s, tg_3s = 4.74 t/s 35.27.271.989 I slot print_timing: id 0 | task 7275 | n_gen = 359, tg = 4.41 t/s, tg_3s = 4.74 t/s 35.27.272.382 I slot print_timing: id 3 | task 7184 | n_gen = 448, tg = 4.32 t/s, tg_3s = 4.74 t/s 35.29.801.908 I slot print_timing: id 1 | task 7422 | n_gen = 225, tg = 4.38 t/s, tg_3s = 4.74 t/s 35.30.434.464 I slot print_timing: id 0 | task 7275 | n_gen = 374, tg = 4.43 t/s, tg_3s = 4.74 t/s 35.30.434.883 I slot print_timing: id 3 | task 7184 | n_gen = 463, tg = 4.33 t/s, tg_3s = 4.74 t/s 35.32.331.988 I slot print_timing: id 2 | task 7561 | n_gen = 100, tg = 4.74 t/s, tg_3s = 4.79 t/s 35.32.964.621 I slot print_timing: id 1 | task 7422 | n_gen = 240, tg = 4.40 t/s, tg_3s = 4.74 t/s 35.33.596.891 I slot print_timing: id 0 | task 7275 | n_gen = 389, tg = 4.44 t/s, tg_3s = 4.74 t/s 35.33.597.341 I slot print_timing: id 3 | task 7184 | n_gen = 478, tg = 4.34 t/s, tg_3s = 4.74 t/s 35.33.807.797 I slot print_timing: id 0 | task 7275 | prompt eval time = 2080.32 ms / 118 tokens ( 17.63 ms per token, 56.72 tokens per second) 35.33.807.798 I slot print_timing: id 0 | task 7275 | eval time = 87642.39 ms / 390 tokens ( 225.30 ms per token, 4.44 tokens per second) 35.33.807.799 I slot print_timing: id 0 | task 7275 | total time = 89722.71 ms / 508 tokens 35.33.807.799 I slot print_timing: id 0 | task 7275 | graphs reused = 6790 35.33.807.800 I slot print_timing: id 0 | task 7275 | graph reallocs = 0 / 0 (same size) / (changed size) 35.33.807.851 I slot release: id 0 | task 7275 | stop processing: n_tokens = 1632, truncated = 0 35.34.006.966 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.702 35.34.006.999 I slot launch_slot_: id 0 | task 7671 | processing task, is_child = 0 35.35.375.164 I slot print_timing: id 2 | task 7561 | n_gen = 109, tg = 4.52 t/s, tg_3s = 2.96 t/s 35.35.970.666 I slot print_timing: id 1 | task 7422 | n_gen = 248, tg = 4.31 t/s, tg_3s = 2.66 t/s 35.36.603.895 I slot print_timing: id 3 | task 7184 | n_gen = 486, tg = 4.30 t/s, tg_3s = 2.66 t/s 35.38.500.017 I slot print_timing: id 2 | task 7561 | n_gen = 123, tg = 4.51 t/s, tg_3s = 4.48 t/s 35.38.710.789 I slot print_timing: id 3 | task 7184 | prompt eval time = 2114.22 ms / 133 tokens ( 15.90 ms per token, 62.91 tokens per second) 35.38.710.792 I slot print_timing: id 3 | task 7184 | eval time = 115000.35 ms / 496 tokens ( 232.32 ms per token, 4.30 tokens per second) 35.38.710.793 I slot print_timing: id 3 | task 7184 | total time = 117114.56 ms / 629 tokens 35.38.710.793 I slot print_timing: id 3 | task 7184 | graphs reused = 6804 35.38.710.794 I slot print_timing: id 3 | task 7184 | graph reallocs = 0 / 0 (same size) / (changed size) 35.38.710.850 I slot release: id 3 | task 7184 | stop processing: n_tokens = 1753, truncated = 0 35.38.909.549 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.654 35.38.909.576 I slot launch_slot_: id 3 | task 7689 | processing task, is_child = 0 35.40.301.895 I slot print_timing: id 1 | task 7422 | prompt eval time = 2069.44 ms / 101 tokens ( 20.49 ms per token, 48.81 tokens per second) 35.40.301.898 I slot print_timing: id 1 | task 7422 | eval time = 61652.81 ms / 263 tokens ( 235.32 ms per token, 4.25 tokens per second) 35.40.301.898 I slot print_timing: id 1 | task 7422 | total time = 63722.25 ms / 364 tokens 35.40.301.899 I slot print_timing: id 1 | task 7422 | graphs reused = 6804 35.40.301.899 I slot print_timing: id 1 | task 7422 | graph reallocs = 0 / 0 (same size) / (changed size) 35.40.301.950 I slot release: id 1 | task 7422 | stop processing: n_tokens = 1488, truncated = 0 35.40.768.329 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.770 35.40.768.371 I slot launch_slot_: id 1 | task 7692 | processing task, is_child = 0 35.42.303.073 I slot print_timing: id 2 | task 7561 | n_gen = 128, tg = 4.12 t/s, tg_3s = 1.31 t/s 35.45.371.851 I slot print_timing: id 2 | task 7561 | n_gen = 141, tg = 4.13 t/s, tg_3s = 4.24 t/s 35.48.530.134 I slot print_timing: id 2 | task 7561 | n_gen = 156, tg = 4.18 t/s, tg_3s = 4.75 t/s 35.51.688.241 I slot print_timing: id 2 | task 7561 | n_gen = 171, tg = 4.23 t/s, tg_3s = 4.75 t/s 35.52.108.753 I slot print_timing: id 0 | task 7671 | prompt eval time = 1749.16 ms / 89 tokens ( 19.65 ms per token, 50.88 tokens per second) 35.52.108.758 I slot print_timing: id 0 | task 7671 | eval time = 16352.58 ms / 64 tokens ( 259.56 ms per token, 3.85 tokens per second) 35.52.108.758 I slot print_timing: id 0 | task 7671 | total time = 18101.75 ms / 153 tokens 35.52.108.759 I slot print_timing: id 0 | task 7671 | graphs reused = 6847 35.52.108.759 I slot print_timing: id 0 | task 7671 | graph reallocs = 0 / 0 (same size) / (changed size) 35.52.108.823 I slot release: id 0 | task 7671 | stop processing: n_tokens = 1277, truncated = 0 35.52.307.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.897 35.52.307.893 I slot launch_slot_: id 0 | task 7740 | processing task, is_child = 0 35.54.808.247 I slot print_timing: id 2 | task 7561 | n_gen = 178, tg = 4.08 t/s, tg_3s = 2.24 t/s 35.57.964.828 I slot print_timing: id 2 | task 7561 | n_gen = 193, tg = 4.13 t/s, tg_3s = 4.75 t/s 36.01.122.387 I slot print_timing: id 2 | task 7561 | n_gen = 208, tg = 4.17 t/s, tg_3s = 4.75 t/s 36.04.279.603 I slot print_timing: id 2 | task 7561 | n_gen = 223, tg = 4.20 t/s, tg_3s = 4.75 t/s 36.04.911.540 I slot print_timing: id 3 | task 7689 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 36.05.332.462 I slot print_timing: id 1 | task 7692 | n_gen = 100, tg = 4.40 t/s, tg_3s = 4.45 t/s 36.07.438.613 I slot print_timing: id 2 | task 7561 | n_gen = 238, tg = 4.23 t/s, tg_3s = 4.75 t/s 36.08.070.452 I slot print_timing: id 3 | task 7689 | n_gen = 115, tg = 4.18 t/s, tg_3s = 4.75 t/s 36.08.491.503 I slot print_timing: id 1 | task 7692 | n_gen = 115, tg = 4.45 t/s, tg_3s = 4.75 t/s 36.10.597.706 I slot print_timing: id 2 | task 7561 | n_gen = 253, tg = 4.26 t/s, tg_3s = 4.75 t/s 36.11.229.272 I slot print_timing: id 3 | task 7689 | n_gen = 130, tg = 4.23 t/s, tg_3s = 4.75 t/s 36.11.649.979 I slot print_timing: id 1 | task 7692 | n_gen = 130, tg = 4.48 t/s, tg_3s = 4.75 t/s 36.13.757.623 I slot print_timing: id 2 | task 7561 | n_gen = 268, tg = 4.29 t/s, tg_3s = 4.75 t/s 36.14.389.240 I slot print_timing: id 3 | task 7689 | n_gen = 145, tg = 4.28 t/s, tg_3s = 4.75 t/s 36.14.810.130 I slot print_timing: id 1 | task 7692 | n_gen = 145, tg = 4.50 t/s, tg_3s = 4.75 t/s 36.15.231.143 I slot print_timing: id 0 | task 7740 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 36.16.917.699 I slot print_timing: id 2 | task 7561 | n_gen = 283, tg = 4.31 t/s, tg_3s = 4.75 t/s 36.17.548.656 I slot print_timing: id 1 | task 7692 | prompt eval time = 2076.70 ms / 92 tokens ( 22.57 ms per token, 44.30 tokens per second) 36.17.548.659 I slot print_timing: id 1 | task 7692 | eval time = 34703.58 ms / 158 tokens ( 221.04 ms per token, 4.52 tokens per second) 36.17.548.660 I slot print_timing: id 1 | task 7692 | total time = 36780.28 ms / 250 tokens 36.17.548.660 I slot print_timing: id 1 | task 7692 | graphs reused = 6956 36.17.548.660 I slot print_timing: id 1 | task 7692 | graph reallocs = 0 / 0 (same size) / (changed size) 36.17.548.707 I slot release: id 1 | task 7692 | stop processing: n_tokens = 1374, truncated = 0 36.17.549.010 I slot print_timing: id 3 | task 7689 | n_gen = 160, tg = 4.32 t/s, tg_3s = 4.75 t/s 36.17.838.774 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.834 36.17.838.805 I slot launch_slot_: id 1 | task 7854 | processing task, is_child = 0 36.19.705.453 I slot print_timing: id 0 | task 7740 | n_gen = 113, tg = 4.42 t/s, tg_3s = 2.91 t/s 36.20.247.971 I slot print_timing: id 2 | task 7561 | n_gen = 289, tg = 4.19 t/s, tg_3s = 1.80 t/s 36.20.672.190 I slot print_timing: id 3 | task 7689 | n_gen = 165, tg = 4.11 t/s, tg_3s = 1.60 t/s 36.22.777.351 I slot print_timing: id 0 | task 7740 | n_gen = 126, tg = 4.40 t/s, tg_3s = 4.23 t/s 36.23.409.315 I slot print_timing: id 2 | task 7561 | n_gen = 304, tg = 4.21 t/s, tg_3s = 4.74 t/s 36.23.831.634 I slot print_timing: id 3 | task 7689 | n_gen = 180, tg = 4.16 t/s, tg_3s = 4.75 t/s 36.25.938.504 I slot print_timing: id 0 | task 7740 | n_gen = 141, tg = 4.44 t/s, tg_3s = 4.75 t/s 36.26.570.964 I slot print_timing: id 2 | task 7561 | n_gen = 319, tg = 4.23 t/s, tg_3s = 4.74 t/s 36.26.992.187 I slot print_timing: id 3 | task 7689 | n_gen = 195, tg = 4.20 t/s, tg_3s = 4.75 t/s 36.29.099.271 I slot print_timing: id 0 | task 7740 | n_gen = 156, tg = 4.46 t/s, tg_3s = 4.75 t/s 36.29.731.036 I slot print_timing: id 2 | task 7561 | n_gen = 334, tg = 4.25 t/s, tg_3s = 4.75 t/s 36.30.152.228 I slot print_timing: id 3 | task 7689 | n_gen = 210, tg = 4.23 t/s, tg_3s = 4.75 t/s 36.32.259.330 I slot print_timing: id 0 | task 7740 | n_gen = 171, tg = 4.49 t/s, tg_3s = 4.75 t/s 36.32.892.903 I slot print_timing: id 2 | task 7561 | n_gen = 349, tg = 4.27 t/s, tg_3s = 4.74 t/s 36.33.314.552 I slot print_timing: id 3 | task 7689 | n_gen = 225, tg = 4.26 t/s, tg_3s = 4.74 t/s 36.35.421.075 I slot print_timing: id 0 | task 7740 | n_gen = 186, tg = 4.51 t/s, tg_3s = 4.74 t/s 36.36.053.523 I slot print_timing: id 2 | task 7561 | n_gen = 364, tg = 4.29 t/s, tg_3s = 4.75 t/s 36.36.476.360 I slot print_timing: id 3 | task 7689 | n_gen = 240, tg = 4.29 t/s, tg_3s = 4.74 t/s 36.38.583.403 I slot print_timing: id 0 | task 7740 | prompt eval time = 2076.91 ms / 113 tokens ( 18.38 ms per token, 54.41 tokens per second) 36.38.583.409 I slot print_timing: id 0 | task 7740 | eval time = 44198.60 ms / 201 tokens ( 220.99 ms per token, 4.53 tokens per second) 36.38.583.409 I slot print_timing: id 0 | task 7740 | total time = 46275.50 ms / 314 tokens 36.38.583.410 I slot print_timing: id 0 | task 7740 | graphs reused = 7042 36.38.583.410 I slot print_timing: id 0 | task 7740 | graph reallocs = 0 / 0 (same size) / (changed size) 36.38.583.453 I slot release: id 0 | task 7740 | stop processing: n_tokens = 1438, truncated = 0 36.38.782.111 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.797 36.38.782.147 I slot launch_slot_: id 0 | task 7945 | processing task, is_child = 0 36.40.152.982 I slot print_timing: id 2 | task 7561 | n_gen = 378, tg = 4.25 t/s, tg_3s = 3.42 t/s 36.40.153.150 I slot print_timing: id 3 | task 7689 | n_gen = 252, tg = 4.23 t/s, tg_3s = 3.26 t/s 36.42.432.170 I slot print_timing: id 1 | task 7854 | n_gen = 100, tg = 4.46 t/s, tg_3s = 4.51 t/s 36.43.275.033 I slot print_timing: id 2 | task 7561 | n_gen = 392, tg = 4.26 t/s, tg_3s = 4.48 t/s 36.43.275.200 I slot print_timing: id 3 | task 7689 | n_gen = 266, tg = 4.24 t/s, tg_3s = 4.48 t/s 36.45.591.941 I slot print_timing: id 1 | task 7854 | n_gen = 115, tg = 4.50 t/s, tg_3s = 4.75 t/s 36.46.434.725 I slot print_timing: id 2 | task 7561 | n_gen = 407, tg = 4.27 t/s, tg_3s = 4.75 t/s 36.46.434.881 I slot print_timing: id 3 | task 7689 | n_gen = 281, tg = 4.26 t/s, tg_3s = 4.75 t/s 36.48.751.622 I slot print_timing: id 1 | task 7854 | n_gen = 130, tg = 4.53 t/s, tg_3s = 4.75 t/s 36.49.594.272 I slot print_timing: id 2 | task 7561 | n_gen = 422, tg = 4.29 t/s, tg_3s = 4.75 t/s 36.49.594.425 I slot print_timing: id 3 | task 7689 | n_gen = 296, tg = 4.29 t/s, tg_3s = 4.75 t/s 36.51.913.261 I slot print_timing: id 1 | task 7854 | n_gen = 145, tg = 4.55 t/s, tg_3s = 4.74 t/s 36.52.755.281 I slot print_timing: id 2 | task 7561 | n_gen = 437, tg = 4.30 t/s, tg_3s = 4.75 t/s 36.52.755.442 I slot print_timing: id 3 | task 7689 | n_gen = 311, tg = 4.31 t/s, tg_3s = 4.75 t/s 36.52.966.229 I slot print_timing: id 3 | task 7689 | prompt eval time = 1858.74 ms / 99 tokens ( 18.78 ms per token, 53.26 tokens per second) 36.52.966.233 I slot print_timing: id 3 | task 7689 | eval time = 72197.90 ms / 312 tokens ( 232.15 ms per token, 4.31 tokens per second) 36.52.966.233 I slot print_timing: id 3 | task 7689 | total time = 74056.65 ms / 411 tokens 36.52.966.234 I slot print_timing: id 3 | task 7689 | graphs reused = 7101 36.52.966.234 I slot print_timing: id 3 | task 7689 | graph reallocs = 0 / 0 (same size) / (changed size) 36.52.966.284 I slot release: id 3 | task 7689 | stop processing: n_tokens = 1535, truncated = 0 36.53.164.954 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.747 36.53.164.990 I slot launch_slot_: id 3 | task 8008 | processing task, is_child = 0 36.55.599.848 I slot print_timing: id 1 | task 7854 | n_gen = 152, tg = 4.27 t/s, tg_3s = 1.90 t/s 36.55.994.784 I slot print_timing: id 2 | task 7561 | n_gen = 441, tg = 4.21 t/s, tg_3s = 1.23 t/s 36.58.735.513 I slot print_timing: id 1 | task 7854 | n_gen = 166, tg = 4.29 t/s, tg_3s = 4.46 t/s 36.59.156.452 I slot print_timing: id 2 | task 7561 | n_gen = 456, tg = 4.22 t/s, tg_3s = 4.74 t/s 37.00.209.525 I slot print_timing: id 0 | task 7945 | prompt eval time = 1751.10 ms / 90 tokens ( 19.46 ms per token, 51.40 tokens per second) 37.00.209.528 I slot print_timing: id 0 | task 7945 | eval time = 19676.27 ms / 83 tokens ( 239.95 ms per token, 4.17 tokens per second) 37.00.209.528 I slot print_timing: id 0 | task 7945 | total time = 21427.37 ms / 173 tokens 37.00.209.529 I slot print_timing: id 0 | task 7945 | graphs reused = 7120 37.00.209.529 I slot print_timing: id 0 | task 7945 | graph reallocs = 0 / 0 (same size) / (changed size) 37.00.209.577 I slot release: id 0 | task 7945 | stop processing: n_tokens = 1297, truncated = 0 37.00.409.578 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.884 37.00.409.632 I slot launch_slot_: id 0 | task 8032 | processing task, is_child = 0 37.02.100.246 I slot print_timing: id 1 | task 7854 | n_gen = 175, tg = 4.16 t/s, tg_3s = 2.67 t/s 37.02.481.855 I slot print_timing: id 2 | task 7561 | n_gen = 464, tg = 4.17 t/s, tg_3s = 2.41 t/s 37.05.220.268 I slot print_timing: id 1 | task 7854 | n_gen = 189, tg = 4.18 t/s, tg_3s = 4.49 t/s 37.05.641.714 I slot print_timing: id 2 | task 7561 | n_gen = 479, tg = 4.19 t/s, tg_3s = 4.75 t/s 37.07.956.901 I slot print_timing: id 2 | task 7561 | prompt eval time = 2666.18 ms / 152 tokens ( 17.54 ms per token, 57.01 tokens per second) 37.07.956.904 I slot print_timing: id 2 | task 7561 | eval time = 116495.60 ms / 490 tokens ( 238.23 ms per token, 4.20 tokens per second) 37.07.956.904 I slot print_timing: id 2 | task 7561 | total time = 119161.78 ms / 642 tokens 37.07.956.905 I slot print_timing: id 2 | task 7561 | graphs reused = 7146 37.07.956.905 I slot print_timing: id 2 | task 7561 | graph reallocs = 0 / 0 (same size) / (changed size) 37.07.956.959 I slot release: id 2 | task 7561 | stop processing: n_tokens = 1766, truncated = 0 37.08.245.647 I slot print_timing: id 1 | task 7854 | n_gen = 203, tg = 4.21 t/s, tg_3s = 4.63 t/s 37.08.245.800 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.649 37.08.245.830 I slot launch_slot_: id 2 | task 8062 | processing task, is_child = 0 37.11.327.267 I slot print_timing: id 1 | task 7854 | n_gen = 207, tg = 4.03 t/s, tg_3s = 1.30 t/s 37.14.483.645 I slot print_timing: id 1 | task 7854 | n_gen = 222, tg = 4.07 t/s, tg_3s = 4.75 t/s 37.17.639.862 I slot print_timing: id 1 | task 7854 | n_gen = 237, tg = 4.11 t/s, tg_3s = 4.75 t/s 37.20.799.296 I slot print_timing: id 1 | task 7854 | n_gen = 252, tg = 4.15 t/s, tg_3s = 4.75 t/s 37.20.799.592 I slot print_timing: id 3 | task 8008 | n_gen = 100, tg = 3.99 t/s, tg_3s = 4.03 t/s 37.23.959.246 I slot print_timing: id 1 | task 7854 | n_gen = 267, tg = 4.18 t/s, tg_3s = 4.75 t/s 37.23.959.541 I slot print_timing: id 3 | task 8008 | n_gen = 115, tg = 4.08 t/s, tg_3s = 4.75 t/s 37.25.643.125 I slot print_timing: id 0 | task 8032 | n_gen = 100, tg = 4.27 t/s, tg_3s = 4.32 t/s 37.27.116.404 I slot print_timing: id 1 | task 7854 | n_gen = 282, tg = 4.20 t/s, tg_3s = 4.75 t/s 37.27.116.687 I slot print_timing: id 3 | task 8008 | n_gen = 130, tg = 4.15 t/s, tg_3s = 4.75 t/s 37.28.801.641 I slot print_timing: id 0 | task 8032 | n_gen = 115, tg = 4.33 t/s, tg_3s = 4.75 t/s 37.30.304.373 I slot print_timing: id 1 | task 7854 | n_gen = 297, tg = 4.23 t/s, tg_3s = 4.71 t/s 37.30.305.993 I slot print_timing: id 3 | task 8008 | n_gen = 145, tg = 4.20 t/s, tg_3s = 4.70 t/s 37.31.839.092 I slot print_timing: id 0 | task 8032 | n_gen = 129, tg = 4.36 t/s, tg_3s = 4.61 t/s 37.31.840.298 I slot print_timing: id 2 | task 8062 | n_gen = 100, tg = 4.73 t/s, tg_3s = 4.78 t/s 37.33.376.094 I slot print_timing: id 1 | task 7854 | n_gen = 311, tg = 4.24 t/s, tg_3s = 4.56 t/s 37.33.377.641 I slot print_timing: id 3 | task 8008 | n_gen = 159, tg = 4.23 t/s, tg_3s = 4.56 t/s 37.34.911.442 I slot print_timing: id 0 | task 8032 | n_gen = 143, tg = 4.38 t/s, tg_3s = 4.56 t/s 37.34.912.988 I slot print_timing: id 2 | task 8062 | n_gen = 114, tg = 4.71 t/s, tg_3s = 4.56 t/s 37.36.446.380 I slot print_timing: id 1 | task 7854 | n_gen = 325, tg = 4.25 t/s, tg_3s = 4.56 t/s 37.36.447.212 I slot print_timing: id 3 | task 8008 | n_gen = 173, tg = 4.25 t/s, tg_3s = 4.56 t/s 37.37.988.447 I slot print_timing: id 0 | task 8032 | n_gen = 157, tg = 4.39 t/s, tg_3s = 4.55 t/s 37.37.989.943 I slot print_timing: id 2 | task 8062 | n_gen = 128, tg = 4.69 t/s, tg_3s = 4.55 t/s 37.39.521.979 I slot print_timing: id 1 | task 7854 | n_gen = 339, tg = 4.26 t/s, tg_3s = 4.55 t/s 37.39.523.664 I slot print_timing: id 3 | task 8008 | n_gen = 187, tg = 4.27 t/s, tg_3s = 4.55 t/s 37.41.058.046 I slot print_timing: id 0 | task 8032 | n_gen = 171, tg = 4.41 t/s, tg_3s = 4.56 t/s 37.41.059.718 I slot print_timing: id 2 | task 8062 | n_gen = 142, tg = 4.68 t/s, tg_3s = 4.56 t/s 37.41.719.619 I slot print_timing: id 1 | task 7854 | prompt eval time = 2409.02 ms / 118 tokens ( 20.42 ms per token, 48.98 tokens per second) 37.41.719.627 I slot print_timing: id 1 | task 7854 | eval time = 81471.77 ms / 349 tokens ( 234.11 ms per token, 4.27 tokens per second) 37.41.719.629 I slot print_timing: id 1 | task 7854 | total time = 83880.80 ms / 467 tokens 37.41.719.630 I slot print_timing: id 1 | task 7854 | graphs reused = 7288 37.41.719.630 I slot print_timing: id 1 | task 7854 | graph reallocs = 0 / 0 (same size) / (changed size) 37.41.720.952 I slot release: id 1 | task 7854 | stop processing: n_tokens = 1591, truncated = 0 37.42.021.626 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.720 37.42.021.858 I slot launch_slot_: id 1 | task 8210 | processing task, is_child = 0 37.43.895.283 I slot print_timing: id 3 | task 8008 | n_gen = 199, tg = 4.13 t/s, tg_3s = 2.74 t/s 37.44.449.496 I slot print_timing: id 0 | task 8032 | n_gen = 177, tg = 4.19 t/s, tg_3s = 1.77 t/s 37.44.450.676 I slot print_timing: id 2 | task 8062 | n_gen = 148, tg = 4.38 t/s, tg_3s = 1.77 t/s 37.47.079.702 I slot print_timing: id 3 | task 8008 | n_gen = 212, tg = 4.13 t/s, tg_3s = 4.08 t/s 37.47.520.562 I slot print_timing: id 0 | task 8032 | n_gen = 191, tg = 4.22 t/s, tg_3s = 4.56 t/s 37.47.522.153 I slot print_timing: id 2 | task 8062 | n_gen = 162, tg = 4.40 t/s, tg_3s = 4.56 t/s 37.50.160.077 I slot print_timing: id 3 | task 8008 | n_gen = 226, tg = 4.15 t/s, tg_3s = 4.54 t/s 37.50.594.124 I slot print_timing: id 0 | task 8032 | n_gen = 205, tg = 4.24 t/s, tg_3s = 4.55 t/s 37.50.595.804 I slot print_timing: id 2 | task 8062 | n_gen = 176, tg = 4.41 t/s, tg_3s = 4.55 t/s 37.53.220.918 I slot print_timing: id 3 | task 8008 | n_gen = 240, tg = 4.18 t/s, tg_3s = 4.57 t/s 37.53.655.104 I slot print_timing: id 0 | task 8032 | n_gen = 219, tg = 4.26 t/s, tg_3s = 4.57 t/s 37.53.656.830 I slot print_timing: id 2 | task 8062 | n_gen = 190, tg = 4.42 t/s, tg_3s = 4.57 t/s 37.56.285.726 I slot print_timing: id 3 | task 8008 | n_gen = 254, tg = 4.20 t/s, tg_3s = 4.57 t/s 37.56.725.398 I slot print_timing: id 0 | task 8032 | n_gen = 233, tg = 4.28 t/s, tg_3s = 4.56 t/s 37.56.727.048 I slot print_timing: id 2 | task 8062 | n_gen = 204, tg = 4.43 t/s, tg_3s = 4.56 t/s 37.59.381.544 I slot print_timing: id 3 | task 8008 | n_gen = 268, tg = 4.21 t/s, tg_3s = 4.52 t/s 37.59.821.873 I slot print_timing: id 0 | task 8032 | n_gen = 247, tg = 4.29 t/s, tg_3s = 4.52 t/s 37.59.823.453 I slot print_timing: id 2 | task 8062 | n_gen = 218, tg = 4.44 t/s, tg_3s = 4.52 t/s 38.02.447.553 I slot print_timing: id 3 | task 8008 | n_gen = 282, tg = 4.23 t/s, tg_3s = 4.57 t/s 38.02.888.182 I slot print_timing: id 0 | task 8032 | n_gen = 261, tg = 4.30 t/s, tg_3s = 4.57 t/s 38.02.889.867 I slot print_timing: id 2 | task 8062 | n_gen = 232, tg = 4.44 t/s, tg_3s = 4.57 t/s 38.05.507.660 I slot print_timing: id 3 | task 8008 | n_gen = 296, tg = 4.24 t/s, tg_3s = 4.58 t/s 38.05.946.059 I slot print_timing: id 0 | task 8032 | n_gen = 275, tg = 4.32 t/s, tg_3s = 4.58 t/s 38.05.946.744 I slot print_timing: id 2 | task 8062 | n_gen = 246, tg = 4.45 t/s, tg_3s = 4.58 t/s 38.06.166.725 I slot print_timing: id 1 | task 8210 | n_gen = 100, tg = 4.56 t/s, tg_3s = 4.60 t/s 38.08.588.508 I slot print_timing: id 3 | task 8008 | n_gen = 310, tg = 4.26 t/s, tg_3s = 4.54 t/s 38.09.023.593 I slot print_timing: id 0 | task 8032 | n_gen = 289, tg = 4.33 t/s, tg_3s = 4.55 t/s 38.09.025.093 I slot print_timing: id 2 | task 8062 | n_gen = 260, tg = 4.46 t/s, tg_3s = 4.55 t/s 38.09.245.159 I slot print_timing: id 1 | task 8210 | n_gen = 114, tg = 4.56 t/s, tg_3s = 4.55 t/s 38.09.460.746 I slot print_timing: id 0 | task 8032 | prompt eval time = 2071.91 ms / 107 tokens ( 19.36 ms per token, 51.64 tokens per second) 38.09.460.756 I slot print_timing: id 0 | task 8032 | eval time = 66979.18 ms / 291 tokens ( 230.96 ms per token, 4.33 tokens per second) 38.09.460.758 I slot print_timing: id 0 | task 8032 | total time = 69051.09 ms / 398 tokens 38.09.460.760 I slot print_timing: id 0 | task 8032 | graphs reused = 7400 38.09.460.762 I slot print_timing: id 0 | task 8032 | graph reallocs = 0 / 0 (same size) / (changed size) 38.09.460.989 I slot release: id 0 | task 8032 | stop processing: n_tokens = 1522, truncated = 0 38.09.672.030 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.753 38.09.672.296 I slot launch_slot_: id 0 | task 8328 | processing task, is_child = 0 38.11.751.619 I slot print_timing: id 3 | task 8008 | n_gen = 316, tg = 4.16 t/s, tg_3s = 1.90 t/s 38.12.146.652 I slot print_timing: id 2 | task 8062 | n_gen = 265, tg = 4.31 t/s, tg_3s = 1.60 t/s 38.12.367.006 I slot print_timing: id 1 | task 8210 | n_gen = 119, tg = 4.23 t/s, tg_3s = 1.60 t/s 38.14.782.055 I slot print_timing: id 3 | task 8008 | n_gen = 329, tg = 4.16 t/s, tg_3s = 4.29 t/s 38.15.218.774 I slot print_timing: id 2 | task 8062 | n_gen = 279, tg = 4.32 t/s, tg_3s = 4.56 t/s 38.15.436.972 I slot print_timing: id 1 | task 8210 | n_gen = 133, tg = 4.26 t/s, tg_3s = 4.56 t/s 38.17.846.146 I slot print_timing: id 3 | task 8008 | n_gen = 343, tg = 4.18 t/s, tg_3s = 4.57 t/s 38.18.282.888 I slot print_timing: id 2 | task 8062 | n_gen = 293, tg = 4.33 t/s, tg_3s = 4.57 t/s 38.18.504.018 I slot print_timing: id 1 | task 8210 | n_gen = 147, tg = 4.29 t/s, tg_3s = 4.56 t/s 38.19.160.930 I slot print_timing: id 1 | task 8210 | prompt eval time = 2428.08 ms / 109 tokens ( 22.28 ms per token, 44.89 tokens per second) 38.19.160.948 I slot print_timing: id 1 | task 8210 | eval time = 34710.94 ms / 150 tokens ( 232.96 ms per token, 4.29 tokens per second) 38.19.160.951 I slot print_timing: id 1 | task 8210 | total time = 37139.01 ms / 259 tokens 38.19.160.954 I slot print_timing: id 1 | task 8210 | graphs reused = 7432 38.19.160.957 I slot print_timing: id 1 | task 8210 | graph reallocs = 0 / 0 (same size) / (changed size) 38.19.161.197 I slot release: id 1 | task 8210 | stop processing: n_tokens = 1383, truncated = 0 38.19.460.927 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.829 38.19.461.204 I slot launch_slot_: id 1 | task 8364 | processing task, is_child = 0 38.21.337.361 I slot print_timing: id 2 | task 8062 | n_gen = 299, tg = 4.23 t/s, tg_3s = 1.96 t/s 38.21.338.328 I slot print_timing: id 3 | task 8008 | n_gen = 351, tg = 4.10 t/s, tg_3s = 2.29 t/s 38.24.518.483 I slot print_timing: id 2 | task 8062 | n_gen = 312, tg = 4.22 t/s, tg_3s = 4.09 t/s 38.24.519.324 I slot print_timing: id 3 | task 8008 | n_gen = 364, tg = 4.10 t/s, tg_3s = 4.09 t/s 38.27.577.008 I slot print_timing: id 2 | task 8062 | n_gen = 326, tg = 4.24 t/s, tg_3s = 4.58 t/s 38.27.577.848 I slot print_timing: id 3 | task 8008 | n_gen = 378, tg = 4.12 t/s, tg_3s = 4.58 t/s 38.28.463.829 I slot print_timing: id 3 | task 8008 | prompt eval time = 2830.00 ms / 170 tokens ( 16.65 ms per token, 60.07 tokens per second) 38.28.463.843 I slot print_timing: id 3 | task 8008 | eval time = 92468.81 ms / 382 tokens ( 242.70 ms per token, 4.12 tokens per second) 38.28.463.844 I slot print_timing: id 3 | task 8008 | total time = 95298.81 ms / 552 tokens 38.28.463.846 I slot print_timing: id 3 | task 8008 | graphs reused = 7461 38.28.463.847 I slot print_timing: id 3 | task 8008 | graph reallocs = 0 / 0 (same size) / (changed size) 38.28.464.010 I slot release: id 3 | task 8008 | stop processing: n_tokens = 1676, truncated = 0 38.28.671.197 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.684 38.28.671.371 I slot launch_slot_: id 3 | task 8398 | processing task, is_child = 0 38.30.761.427 I slot print_timing: id 2 | task 8062 | n_gen = 332, tg = 4.14 t/s, tg_3s = 1.88 t/s 38.31.579.595 I slot print_timing: id 2 | task 8062 | prompt eval time = 2658.43 ms / 147 tokens ( 18.08 ms per token, 55.30 tokens per second) 38.31.579.601 I slot print_timing: id 2 | task 8062 | eval time = 80675.33 ms / 335 tokens ( 241.54 ms per token, 4.14 tokens per second) 38.31.579.602 I slot print_timing: id 2 | task 8062 | total time = 83333.76 ms / 482 tokens 38.31.579.602 I slot print_timing: id 2 | task 8062 | graphs reused = 7462 38.31.579.603 I slot print_timing: id 2 | task 8062 | graph reallocs = 0 / 0 (same size) / (changed size) 38.31.579.648 I slot release: id 2 | task 8062 | stop processing: n_tokens = 1606, truncated = 0 38.31.869.297 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.714 38.31.869.330 I slot launch_slot_: id 2 | task 8404 | processing task, is_child = 0 38.39.636.914 I slot print_timing: id 0 | task 8328 | n_gen = 100, tg = 3.60 t/s, tg_3s = 3.64 t/s 38.42.793.333 I slot print_timing: id 0 | task 8328 | n_gen = 115, tg = 3.72 t/s, tg_3s = 4.75 t/s 38.45.951.278 I slot print_timing: id 0 | task 8328 | n_gen = 130, tg = 3.82 t/s, tg_3s = 4.75 t/s 38.47.003.977 I slot print_timing: id 1 | task 8364 | n_gen = 100, tg = 3.94 t/s, tg_3s = 3.98 t/s 38.49.109.273 I slot print_timing: id 0 | task 8328 | n_gen = 145, tg = 3.90 t/s, tg_3s = 4.75 t/s 38.50.163.933 I slot print_timing: id 1 | task 8364 | n_gen = 115, tg = 4.03 t/s, tg_3s = 4.75 t/s 38.52.269.808 I slot print_timing: id 0 | task 8328 | n_gen = 160, tg = 3.96 t/s, tg_3s = 4.75 t/s 38.53.323.110 I slot print_timing: id 1 | task 8364 | n_gen = 130, tg = 4.10 t/s, tg_3s = 4.75 t/s 38.53.955.047 I slot print_timing: id 3 | task 8398 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.39 t/s 38.55.008.628 I slot print_timing: id 2 | task 8404 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 38.55.429.538 I slot print_timing: id 0 | task 8328 | n_gen = 175, tg = 4.02 t/s, tg_3s = 4.75 t/s 38.56.482.189 I slot print_timing: id 1 | task 8364 | n_gen = 145, tg = 4.16 t/s, tg_3s = 4.75 t/s 38.57.113.963 I slot print_timing: id 3 | task 8398 | n_gen = 115, tg = 4.39 t/s, tg_3s = 4.75 t/s 38.58.166.819 I slot print_timing: id 2 | task 8404 | n_gen = 115, tg = 4.75 t/s, tg_3s = 4.75 t/s 38.58.587.966 I slot print_timing: id 0 | task 8328 | n_gen = 190, tg = 4.07 t/s, tg_3s = 4.75 t/s 38.59.641.041 I slot print_timing: id 1 | task 8364 | n_gen = 160, tg = 4.21 t/s, tg_3s = 4.75 t/s 39.00.273.130 I slot print_timing: id 3 | task 8398 | n_gen = 130, tg = 4.43 t/s, tg_3s = 4.75 t/s 39.01.326.164 I slot print_timing: id 2 | task 8404 | n_gen = 130, tg = 4.75 t/s, tg_3s = 4.75 t/s 39.01.747.316 I slot print_timing: id 0 | task 8328 | n_gen = 205, tg = 4.11 t/s, tg_3s = 4.75 t/s 39.02.801.381 I slot print_timing: id 1 | task 8364 | n_gen = 175, tg = 4.25 t/s, tg_3s = 4.75 t/s 39.03.433.109 I slot print_timing: id 3 | task 8398 | n_gen = 145, tg = 4.46 t/s, tg_3s = 4.75 t/s 39.04.486.488 I slot print_timing: id 2 | task 8404 | n_gen = 145, tg = 4.75 t/s, tg_3s = 4.75 t/s 39.04.907.221 I slot print_timing: id 0 | task 8328 | n_gen = 220, tg = 4.15 t/s, tg_3s = 4.75 t/s 39.05.960.079 I slot print_timing: id 1 | task 8364 | n_gen = 190, tg = 4.29 t/s, tg_3s = 4.75 t/s 39.06.591.601 I slot print_timing: id 3 | task 8398 | n_gen = 160, tg = 4.49 t/s, tg_3s = 4.75 t/s 39.07.641.244 I slot print_timing: id 2 | task 8404 | n_gen = 160, tg = 4.75 t/s, tg_3s = 4.75 t/s 39.08.062.261 I slot print_timing: id 0 | task 8328 | n_gen = 235, tg = 4.18 t/s, tg_3s = 4.75 t/s 39.09.115.904 I slot print_timing: id 1 | task 8364 | n_gen = 205, tg = 4.32 t/s, tg_3s = 4.75 t/s 39.09.748.589 I slot print_timing: id 3 | task 8398 | n_gen = 175, tg = 4.51 t/s, tg_3s = 4.75 t/s 39.10.591.029 I slot print_timing: id 2 | task 8404 | prompt eval time = 2295.15 ms / 122 tokens ( 18.81 ms per token, 53.16 tokens per second) 39.10.591.032 I slot print_timing: id 2 | task 8404 | eval time = 36426.54 ms / 174 tokens ( 210.56 ms per token, 4.75 tokens per second) 39.10.591.033 I slot print_timing: id 2 | task 8404 | total time = 38721.69 ms / 296 tokens 39.10.591.033 I slot print_timing: id 2 | task 8404 | graphs reused = 7634 39.10.591.034 I slot print_timing: id 2 | task 8404 | graph reallocs = 0 / 0 (same size) / (changed size) 39.10.591.087 I slot release: id 2 | task 8404 | stop processing: n_tokens = 1420, truncated = 0 39.10.880.618 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.807 39.10.880.651 I slot launch_slot_: id 2 | task 8581 | processing task, is_child = 0 39.12.360.845 I slot print_timing: id 0 | task 8328 | n_gen = 249, tg = 4.12 t/s, tg_3s = 3.26 t/s 39.12.361.058 I slot print_timing: id 1 | task 8364 | n_gen = 214, tg = 4.22 t/s, tg_3s = 2.77 t/s 39.12.846.218 I slot print_timing: id 3 | task 8398 | n_gen = 182, tg = 4.34 t/s, tg_3s = 2.26 t/s 39.15.374.854 I slot print_timing: id 0 | task 8328 | n_gen = 262, tg = 4.13 t/s, tg_3s = 4.31 t/s 39.15.375.001 I slot print_timing: id 1 | task 8364 | prompt eval time = 2432.00 ms / 110 tokens ( 22.11 ms per token, 45.23 tokens per second) 39.15.375.002 I slot print_timing: id 1 | task 8364 | eval time = 53481.78 ms / 227 tokens ( 236.65 ms per token, 4.23 tokens per second) 39.15.375.003 I slot print_timing: id 1 | task 8364 | total time = 55913.78 ms / 337 tokens 39.15.375.003 I slot print_timing: id 1 | task 8364 | graphs reused = 7645 39.15.375.004 I slot print_timing: id 1 | task 8364 | graph reallocs = 0 / 0 (same size) / (changed size) 39.15.375.051 I slot release: id 1 | task 8364 | stop processing: n_tokens = 1461, truncated = 0 39.15.664.772 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.784 39.15.664.815 I slot launch_slot_: id 1 | task 8597 | processing task, is_child = 0 39.17.521.776 I slot print_timing: id 3 | task 8398 | n_gen = 196, tg = 4.21 t/s, tg_3s = 2.99 t/s 39.18.487.800 I slot print_timing: id 0 | task 8328 | n_gen = 267, tg = 4.01 t/s, tg_3s = 1.61 t/s 39.20.597.759 I slot print_timing: id 3 | task 8398 | n_gen = 209, tg = 4.21 t/s, tg_3s = 4.23 t/s 39.21.650.284 I slot print_timing: id 0 | task 8328 | n_gen = 282, tg = 4.04 t/s, tg_3s = 4.74 t/s 39.23.755.919 I slot print_timing: id 3 | task 8398 | n_gen = 224, tg = 4.24 t/s, tg_3s = 4.75 t/s 39.24.807.874 I slot print_timing: id 0 | task 8328 | n_gen = 297, tg = 4.07 t/s, tg_3s = 4.75 t/s 39.26.913.972 I slot print_timing: id 3 | task 8398 | n_gen = 239, tg = 4.27 t/s, tg_3s = 4.75 t/s 39.27.966.132 I slot print_timing: id 0 | task 8328 | n_gen = 312, tg = 4.10 t/s, tg_3s = 4.75 t/s 39.30.073.095 I slot print_timing: id 3 | task 8398 | n_gen = 254, tg = 4.29 t/s, tg_3s = 4.75 t/s 39.31.126.221 I slot print_timing: id 0 | task 8328 | n_gen = 327, tg = 4.13 t/s, tg_3s = 4.75 t/s 39.33.233.560 I slot print_timing: id 3 | task 8398 | n_gen = 269, tg = 4.32 t/s, tg_3s = 4.75 t/s 39.34.285.848 I slot print_timing: id 0 | task 8328 | n_gen = 342, tg = 4.15 t/s, tg_3s = 4.75 t/s 39.35.760.089 I slot print_timing: id 2 | task 8581 | n_gen = 100, tg = 4.32 t/s, tg_3s = 4.36 t/s 39.36.391.640 I slot print_timing: id 3 | task 8398 | n_gen = 284, tg = 4.34 t/s, tg_3s = 4.75 t/s 39.37.443.333 I slot print_timing: id 0 | task 8328 | n_gen = 357, tg = 4.17 t/s, tg_3s = 4.75 t/s 39.38.917.189 I slot print_timing: id 1 | task 8597 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 39.38.917.344 I slot print_timing: id 2 | task 8581 | n_gen = 115, tg = 4.37 t/s, tg_3s = 4.75 t/s 39.39.548.936 I slot print_timing: id 0 | task 8328 | prompt eval time = 2472.56 ms / 139 tokens ( 17.79 ms per token, 56.22 tokens per second) 39.39.548.942 I slot print_timing: id 0 | task 8328 | eval time = 87404.05 ms / 367 tokens ( 238.81 ms per token, 4.19 tokens per second) 39.39.548.942 I slot print_timing: id 0 | task 8328 | total time = 89876.61 ms / 506 tokens 39.39.548.943 I slot print_timing: id 0 | task 8328 | graphs reused = 7745 39.39.548.943 I slot print_timing: id 0 | task 8328 | graph reallocs = 0 / 0 (same size) / (changed size) 39.39.548.990 I slot release: id 0 | task 8328 | stop processing: n_tokens = 1630, truncated = 0 39.39.549.495 I slot print_timing: id 3 | task 8398 | n_gen = 299, tg = 4.36 t/s, tg_3s = 4.75 t/s 39.39.747.855 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.703 39.39.747.886 I slot launch_slot_: id 0 | task 8703 | processing task, is_child = 0 39.42.026.378 I slot print_timing: id 1 | task 8597 | n_gen = 107, tg = 4.42 t/s, tg_3s = 2.25 t/s 39.42.026.528 I slot print_timing: id 2 | task 8581 | n_gen = 122, tg = 4.15 t/s, tg_3s = 2.25 t/s 39.42.236.788 I slot print_timing: id 1 | task 8597 | prompt eval time = 2399.40 ms / 111 tokens ( 21.62 ms per token, 46.26 tokens per second) 39.42.236.790 I slot print_timing: id 1 | task 8597 | eval time = 24172.56 ms / 108 tokens ( 225.91 ms per token, 4.43 tokens per second) 39.42.236.790 I slot print_timing: id 1 | task 8597 | total time = 26571.97 ms / 219 tokens 39.42.236.791 I slot print_timing: id 1 | task 8597 | graphs reused = 7747 39.42.236.791 I slot print_timing: id 1 | task 8597 | graph reallocs = 0 / 0 (same size) / (changed size) 39.42.236.834 I slot release: id 1 | task 8597 | stop processing: n_tokens = 1343, truncated = 0 39.42.525.784 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.853 39.42.525.826 I slot launch_slot_: id 1 | task 8709 | processing task, is_child = 0 39.44.377.868 I slot print_timing: id 3 | task 8398 | n_gen = 306, tg = 4.17 t/s, tg_3s = 1.45 t/s 39.45.134.131 I slot print_timing: id 2 | task 8581 | n_gen = 127, tg = 3.90 t/s, tg_3s = 1.61 t/s 39.46.187.423 I slot print_timing: id 3 | task 8398 | prompt eval time = 2484.70 ms / 134 tokens ( 18.54 ms per token, 53.93 tokens per second) 39.46.187.430 I slot print_timing: id 3 | task 8398 | eval time = 75031.32 ms / 313 tokens ( 240.49 ms per token, 4.16 tokens per second) 39.46.187.431 I slot print_timing: id 3 | task 8398 | total time = 77516.02 ms / 447 tokens 39.46.187.431 I slot print_timing: id 3 | task 8398 | graphs reused = 7752 39.46.187.431 I slot print_timing: id 3 | task 8398 | graph reallocs = 0 / 0 (same size) / (changed size) 39.46.187.476 I slot release: id 3 | task 8398 | stop processing: n_tokens = 1571, truncated = 0 39.46.385.116 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.729 39.46.385.145 I slot launch_slot_: id 3 | task 8719 | processing task, is_child = 0 39.48.819.400 I slot print_timing: id 2 | task 8581 | n_gen = 134, tg = 3.70 t/s, tg_3s = 1.90 t/s 39.51.949.812 I slot print_timing: id 2 | task 8581 | n_gen = 148, tg = 3.76 t/s, tg_3s = 4.47 t/s 39.55.105.763 I slot print_timing: id 2 | task 8581 | n_gen = 163, tg = 3.83 t/s, tg_3s = 4.75 t/s 39.58.257.753 I slot print_timing: id 2 | task 8581 | n_gen = 178, tg = 3.90 t/s, tg_3s = 4.76 t/s 40.01.414.966 I slot print_timing: id 2 | task 8581 | n_gen = 193, tg = 3.95 t/s, tg_3s = 4.75 t/s 40.04.571.764 I slot print_timing: id 2 | task 8581 | n_gen = 208, tg = 4.00 t/s, tg_3s = 4.75 t/s 40.07.098.055 I slot print_timing: id 0 | task 8703 | n_gen = 100, tg = 3.92 t/s, tg_3s = 3.96 t/s 40.07.729.942 I slot print_timing: id 2 | task 8581 | n_gen = 223, tg = 4.04 t/s, tg_3s = 4.75 t/s 40.08.150.817 I slot print_timing: id 1 | task 8709 | n_gen = 100, tg = 4.26 t/s, tg_3s = 4.30 t/s 40.10.045.886 I slot print_timing: id 3 | task 8719 | n_gen = 100, tg = 4.75 t/s, tg_3s = 4.80 t/s 40.10.255.786 I slot print_timing: id 0 | task 8703 | n_gen = 115, tg = 4.01 t/s, tg_3s = 4.75 t/s 40.10.887.664 I slot print_timing: id 2 | task 8581 | n_gen = 238, tg = 4.08 t/s, tg_3s = 4.75 t/s 40.11.308.641 I slot print_timing: id 1 | task 8709 | n_gen = 115, tg = 4.32 t/s, tg_3s = 4.75 t/s 40.12.150.775 I slot print_timing: id 0 | task 8703 | prompt eval time = 2065.84 ms / 101 tokens ( 20.45 ms per token, 48.89 tokens per second) 40.12.150.780 I slot print_timing: id 0 | task 8703 | eval time = 30337.04 ms / 124 tokens ( 246.64 ms per token, 4.05 tokens per second) 40.12.150.781 I slot print_timing: id 0 | task 8703 | total time = 32402.88 ms / 225 tokens 40.12.150.781 I slot print_timing: id 0 | task 8703 | graphs reused = 7860 40.12.150.782 I slot print_timing: id 0 | task 8703 | graph reallocs = 0 / 0 (same size) / (changed size) 40.12.150.830 I slot release: id 0 | task 8703 | stop processing: n_tokens = 1349, truncated = 0 40.12.349.508 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.850 40.12.349.546 I slot launch_slot_: id 0 | task 8832 | processing task, is_child = 0 40.14.042.521 I slot print_timing: id 2 | task 8581 | n_gen = 246, tg = 4.00 t/s, tg_3s = 2.54 t/s 40.14.042.683 I slot print_timing: id 3 | task 8719 | n_gen = 112, tg = 4.47 t/s, tg_3s = 3.00 t/s 40.14.424.603 I slot print_timing: id 1 | task 8709 | n_gen = 122, tg = 4.10 t/s, tg_3s = 2.25 t/s 40.17.163.895 I slot print_timing: id 2 | task 8581 | n_gen = 260, tg = 4.03 t/s, tg_3s = 4.49 t/s 40.17.164.041 I slot print_timing: id 3 | task 8719 | n_gen = 126, tg = 4.47 t/s, tg_3s = 4.49 t/s 40.17.585.019 I slot print_timing: id 1 | task 8709 | n_gen = 137, tg = 4.16 t/s, tg_3s = 4.75 t/s 40.20.333.657 I slot print_timing: id 2 | task 8581 | n_gen = 275, tg = 4.06 t/s, tg_3s = 4.73 t/s 40.20.333.810 I slot print_timing: id 3 | task 8719 | n_gen = 141, tg = 4.50 t/s, tg_3s = 4.73 t/s 40.20.756.644 I slot print_timing: id 1 | task 8709 | n_gen = 152, tg = 4.21 t/s, tg_3s = 4.73 t/s 40.23.502.815 I slot print_timing: id 2 | task 8581 | prompt eval time = 1965.42 ms / 96 tokens ( 20.47 ms per token, 48.84 tokens per second) 40.23.502.820 I slot print_timing: id 2 | task 8581 | eval time = 70656.74 ms / 290 tokens ( 244.49 ms per token, 4.09 tokens per second) 40.23.502.820 I slot print_timing: id 2 | task 8581 | total time = 72622.16 ms / 386 tokens 40.23.502.821 I slot print_timing: id 2 | task 8581 | graphs reused = 7903 40.23.502.821 I slot print_timing: id 2 | task 8581 | graph reallocs = 0 / 0 (same size) / (changed size) 40.23.502.871 I slot release: id 2 | task 8581 | stop processing: n_tokens = 1510, truncated = 0 40.23.503.026 I slot print_timing: id 3 | task 8719 | n_gen = 156, tg = 4.52 t/s, tg_3s = 4.73 t/s 40.23.793.813 I slot print_timing: id 1 | task 8709 | n_gen = 166, tg = 4.24 t/s, tg_3s = 4.61 t/s 40.23.793.968 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.759 40.23.794.002 I slot launch_slot_: id 2 | task 8879 | processing task, is_child = 0 40.26.531.935 I slot print_timing: id 3 | task 8719 | n_gen = 161, tg = 4.29 t/s, tg_3s = 1.65 t/s 40.26.953.700 I slot print_timing: id 1 | task 8709 | n_gen = 172, tg = 4.07 t/s, tg_3s = 1.90 t/s 40.29.697.457 I slot print_timing: id 3 | task 8719 | n_gen = 176, tg = 4.32 t/s, tg_3s = 4.74 t/s 40.30.119.181 I slot print_timing: id 1 | task 8709 | n_gen = 187, tg = 4.12 t/s, tg_3s = 4.74 t/s 40.32.864.129 I slot print_timing: id 3 | task 8719 | n_gen = 191, tg = 4.35 t/s, tg_3s = 4.74 t/s 40.33.286.255 I slot print_timing: id 1 | task 8709 | n_gen = 202, tg = 4.16 t/s, tg_3s = 4.74 t/s 40.34.974.978 I slot print_timing: id 1 | task 8709 | prompt eval time = 2395.43 ms / 108 tokens ( 22.18 ms per token, 45.09 tokens per second) 40.34.974.984 I slot print_timing: id 1 | task 8709 | eval time = 50053.71 ms / 210 tokens ( 239.49 ms per token, 4.18 tokens per second) 40.34.974.985 I slot print_timing: id 1 | task 8709 | total time = 52449.14 ms / 318 tokens 40.34.974.986 I slot print_timing: id 1 | task 8709 | graphs reused = 7944 40.34.974.986 I slot print_timing: id 1 | task 8709 | graph reallocs = 0 / 0 (same size) / (changed size) 40.34.975.030 I slot release: id 1 | task 8709 | stop processing: n_tokens = 1442, truncated = 0 40.35.265.667 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.795 40.35.265.709 I slot launch_slot_: id 1 | task 8925 | processing task, is_child = 0 40.36.805.385 I slot print_timing: id 3 | task 8719 | n_gen = 203, tg = 4.24 t/s, tg_3s = 3.04 t/s 40.39.040.479 I slot print_timing: id 0 | task 8832 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 40.39.884.334 I slot print_timing: id 3 | task 8719 | n_gen = 216, tg = 4.24 t/s, tg_3s = 4.22 t/s 40.42.205.923 I slot print_timing: id 0 | task 8832 | n_gen = 115, tg = 4.10 t/s, tg_3s = 4.74 t/s 40.43.050.523 I slot print_timing: id 3 | task 8719 | n_gen = 231, tg = 4.27 t/s, tg_3s = 4.74 t/s 40.45.371.745 I slot print_timing: id 0 | task 8832 | n_gen = 130, tg = 4.17 t/s, tg_3s = 4.74 t/s 40.46.216.744 I slot print_timing: id 3 | task 8719 | n_gen = 246, tg = 4.30 t/s, tg_3s = 4.74 t/s 40.46.852.539 I slot print_timing: id 0 | task 8832 | prompt eval time = 2074.92 ms / 110 tokens ( 18.86 ms per token, 53.01 tokens per second) 40.46.852.542 I slot print_timing: id 0 | task 8832 | eval time = 32428.07 ms / 137 tokens ( 238.44 ms per token, 4.19 tokens per second) 40.46.852.542 I slot print_timing: id 0 | task 8832 | total time = 34502.99 ms / 247 tokens 40.46.852.543 I slot print_timing: id 0 | task 8832 | graphs reused = 7987 40.46.852.543 I slot print_timing: id 0 | task 8832 | graph reallocs = 0 / 0 (same size) / (changed size) 40.46.852.612 I slot release: id 0 | task 8832 | stop processing: n_tokens = 1371, truncated = 0 40.47.051.779 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.836 40.47.051.814 I slot launch_slot_: id 0 | task 8974 | processing task, is_child = 0 40.49.509.354 I slot print_timing: id 3 | task 8719 | n_gen = 252, tg = 4.16 t/s, tg_3s = 1.82 t/s 40.50.778.604 I slot print_timing: id 2 | task 8879 | n_gen = 100, tg = 4.01 t/s, tg_3s = 4.05 t/s 40.52.678.028 I slot print_timing: id 3 | task 8719 | n_gen = 267, tg = 4.19 t/s, tg_3s = 4.73 t/s 40.53.944.342 I slot print_timing: id 2 | task 8879 | n_gen = 115, tg = 4.10 t/s, tg_3s = 4.74 t/s 40.55.844.591 I slot print_timing: id 3 | task 8719 | n_gen = 282, tg = 4.22 t/s, tg_3s = 4.74 t/s 40.56.899.513 I slot print_timing: id 1 | task 8925 | prompt eval time = 2083.57 ms / 95 tokens ( 21.93 ms per token, 45.59 tokens per second) 40.56.899.516 I slot print_timing: id 1 | task 8925 | eval time = 19550.22 ms / 84 tokens ( 235.54 ms per token, 4.25 tokens per second) 40.56.899.517 I slot print_timing: id 1 | task 8925 | total time = 21633.80 ms / 179 tokens 40.56.899.517 I slot print_timing: id 1 | task 8925 | graphs reused = 8022 40.56.899.517 I slot print_timing: id 1 | task 8925 | graph reallocs = 0 / 0 (same size) / (changed size) 40.56.899.568 I slot release: id 1 | task 8925 | stop processing: n_tokens = 1303, truncated = 0 40.57.189.616 I slot print_timing: id 2 | task 8879 | n_gen = 130, tg = 4.15 t/s, tg_3s = 4.62 t/s 40.57.189.776 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.880 40.57.189.810 I slot launch_slot_: id 1 | task 9013 | processing task, is_child = 0 40.59.275.205 I slot print_timing: id 3 | task 8719 | n_gen = 290, tg = 4.12 t/s, tg_3s = 2.33 t/s 41.00.333.141 I slot print_timing: id 2 | task 8879 | n_gen = 137, tg = 3.97 t/s, tg_3s = 2.23 t/s 41.02.444.402 I slot print_timing: id 3 | task 8719 | n_gen = 305, tg = 4.15 t/s, tg_3s = 4.73 t/s 41.03.497.033 I slot print_timing: id 2 | task 8879 | n_gen = 152, tg = 4.04 t/s, tg_3s = 4.74 t/s 41.05.604.239 I slot print_timing: id 3 | task 8719 | n_gen = 320, tg = 4.18 t/s, tg_3s = 4.75 t/s 41.06.657.215 I slot print_timing: id 2 | task 8879 | n_gen = 167, tg = 4.09 t/s, tg_3s = 4.75 t/s 41.08.763.978 I slot print_timing: id 3 | task 8719 | n_gen = 335, tg = 4.20 t/s, tg_3s = 4.75 t/s 41.09.816.440 I slot print_timing: id 2 | task 8879 | n_gen = 182, tg = 4.14 t/s, tg_3s = 4.75 t/s 41.11.922.741 I slot print_timing: id 3 | task 8719 | n_gen = 350, tg = 4.22 t/s, tg_3s = 4.75 t/s 41.12.132.769 I slot print_timing: id 0 | task 8974 | n_gen = 100, tg = 4.38 t/s, tg_3s = 4.42 t/s 41.12.975.587 I slot print_timing: id 2 | task 8879 | n_gen = 197, tg = 4.18 t/s, tg_3s = 4.75 t/s 41.15.082.268 I slot print_timing: id 3 | task 8719 | n_gen = 365, tg = 4.24 t/s, tg_3s = 4.75 t/s 41.15.292.413 I slot print_timing: id 0 | task 8974 | n_gen = 115, tg = 4.42 t/s, tg_3s = 4.75 t/s 41.15.924.722 I slot print_timing: id 2 | task 8879 | prompt eval time = 2313.20 ms / 128 tokens ( 18.07 ms per token, 55.33 tokens per second) 41.15.924.724 I slot print_timing: id 2 | task 8879 | eval time = 49817.51 ms / 211 tokens ( 237.23 ms per token, 4.22 tokens per second) 41.15.924.725 I slot print_timing: id 2 | task 8879 | total time = 52130.71 ms / 339 tokens 41.15.924.725 I slot print_timing: id 2 | task 8879 | graphs reused = 8100 41.15.924.726 I slot print_timing: id 2 | task 8879 | graph reallocs = 0 / 0 (same size) / (changed size) 41.15.924.770 I slot release: id 2 | task 8879 | stop processing: n_tokens = 1463, truncated = 0 41.18.240.775 I slot print_timing: id 3 | task 8719 | n_gen = 377, tg = 4.22 t/s, tg_3s = 3.80 t/s 41.18.529.869 I slot print_timing: id 0 | task 8974 | n_gen = 127, tg = 4.34 t/s, tg_3s = 3.71 t/s 41.21.425.176 I slot print_timing: id 1 | task 9013 | prompt eval time = 2085.00 ms / 96 tokens ( 21.72 ms per token, 46.04 tokens per second) 41.21.425.181 I slot print_timing: id 1 | task 9013 | eval time = 22150.36 ms / 99 tokens ( 226.02 ms per token, 4.42 tokens per second) 41.21.425.181 I slot print_timing: id 1 | task 9013 | total time = 24235.36 ms / 195 tokens 41.21.425.182 I slot print_timing: id 1 | task 9013 | graphs reused = 8100 41.21.425.182 I slot print_timing: id 1 | task 9013 | graph reallocs = 0 / 0 (same size) / (changed size) 41.21.425.225 I slot release: id 1 | task 9013 | stop processing: n_tokens = 1319, truncated = 0 41.21.425.406 I slot print_timing: id 3 | task 8719 | n_gen = 388, tg = 4.20 t/s, tg_3s = 3.45 t/s 41.21.638.889 I slot print_timing: id 0 | task 8974 | n_gen = 138, tg = 4.26 t/s, tg_3s = 3.54 t/s 41.22.921.935 I slot print_timing: id 3 | task 8719 | prompt eval time = 2828.77 ms / 166 tokens ( 17.04 ms per token, 58.68 tokens per second) 41.22.921.938 I slot print_timing: id 3 | task 8719 | eval time = 93708.01 ms / 395 tokens ( 237.84 ms per token, 4.20 tokens per second) 41.22.921.939 I slot print_timing: id 3 | task 8719 | total time = 96536.79 ms / 561 tokens 41.22.921.940 I slot print_timing: id 3 | task 8719 | graphs reused = 8100 41.22.921.940 I slot print_timing: id 3 | task 8719 | graph reallocs = 0 / 0 (same size) / (changed size) 41.22.921.987 I slot release: id 3 | task 8719 | stop processing: n_tokens = 1685, truncated = 0 41.24.719.644 I slot print_timing: id 0 | task 8974 | n_gen = 161, tg = 4.54 t/s, tg_3s = 7.47 t/s 41.27.781.818 I slot print_timing: id 0 | task 8974 | n_gen = 190, tg = 4.94 t/s, tg_3s = 9.47 t/s 41.30.843.094 I slot print_timing: id 0 | task 8974 | n_gen = 219, tg = 5.27 t/s, tg_3s = 9.47 t/s 41.33.904.076 I slot print_timing: id 0 | task 8974 | n_gen = 248, tg = 5.56 t/s, tg_3s = 9.47 t/s 41.36.969.278 I slot print_timing: id 0 | task 8974 | n_gen = 277, tg = 5.82 t/s, tg_3s = 9.46 t/s 41.40.029.764 I slot print_timing: id 0 | task 8974 | n_gen = 306, tg = 6.04 t/s, tg_3s = 9.48 t/s 41.40.557.832 I slot print_timing: id 0 | task 8974 | prompt eval time = 2456.94 ms / 142 tokens ( 17.30 ms per token, 57.80 tokens per second) 41.40.557.834 I slot print_timing: id 0 | task 8974 | eval time = 51049.07 ms / 311 tokens ( 164.67 ms per token, 6.07 tokens per second) 41.40.557.835 I slot print_timing: id 0 | task 8974 | total time = 53506.01 ms / 453 tokens 41.40.557.835 I slot print_timing: id 0 | task 8974 | graphs reused = 8265 41.40.557.835 I slot print_timing: id 0 | task 8974 | graph reallocs = 0 / 0 (same size) / (changed size) 41.40.557.885 I slot release: id 0 | task 8974 | stop processing: n_tokens = 1577, truncated = 0 41.40.595.144 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1463, t_last = 96843158327 41.40.595.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 41.40.595.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 41.41.149.172 I slot launch_slot_: id 2 | task 9288 | processing task, is_child = 0 41.41.149.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 41.41.149.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 41.41.149.678 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.443 MiB) 41.42.125.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.882 MiB) 41.42.125.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 41.42.125.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.193 MiB) 41.43.050.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 41.43.050.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 41.43.050.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 41.43.975.605 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1319, t_last = 96848658782 41.43.975.831 I slot launch_slot_: id 1 | task 9289 | processing task, is_child = 0 41.43.975.979 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1685, t_last = 96850155544 41.43.976.092 I slot launch_slot_: id 3 | task 9290 | processing task, is_child = 0 41.43.976.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1577, t_last = 96867791442 41.43.976.268 I slot launch_slot_: id 0 | task 9291 | processing task, is_child = 0 41.50.920.504 I slot print_timing: id 0 | task 9291 | prompt processing, n_tokens = 154, progress = 0.16, t = 6.94 s / 22.18 tokens per second 41.51.691.370 I slot print_timing: id 1 | task 9289 | prompt processing, n_tokens = 137, progress = 0.17, t = 6.94 s / 19.73 tokens per second 41.51.903.561 I slot print_timing: id 2 | task 9288 | prompt processing, n_tokens = 124, progress = 0.16, t = 6.94 s / 17.86 tokens per second 41.51.966.478 I slot print_timing: id 3 | task 9290 | prompt processing, n_tokens = 168, progress = 0.17, t = 6.94 s / 24.19 tokens per second 41.58.387.686 I slot print_timing: id 0 | task 9291 | prompt processing, n_tokens = 279, progress = 0.29, t = 14.41 s / 19.36 tokens per second 41.58.387.703 I slot print_timing: id 1 | task 9289 | prompt processing, n_tokens = 261, progress = 0.32, t = 14.41 s / 18.11 tokens per second 41.58.387.708 I slot print_timing: id 2 | task 9288 | prompt processing, n_tokens = 263, progress = 0.34, t = 14.41 s / 18.25 tokens per second 41.59.541.633 I slot print_timing: id 3 | task 9290 | prompt processing, n_tokens = 387, progress = 0.39, t = 14.41 s / 26.85 tokens per second 42.04.009.916 I slot print_timing: id 0 | task 9291 | prompt processing, n_tokens = 436, progress = 0.46, t = 20.03 s / 21.76 tokens per second 42.07.666.947 I slot print_timing: id 1 | task 9289 | prompt processing, n_tokens = 290, progress = 0.36, t = 20.03 s / 14.48 tokens per second 42.07.680.651 I slot print_timing: id 2 | task 9288 | prompt processing, n_tokens = 656, progress = 0.84, t = 20.03 s / 32.75 tokens per second 42.07.694.085 I slot print_timing: id 3 | task 9290 | prompt processing, n_tokens = 471, progress = 0.48, t = 20.03 s / 23.51 tokens per second 42.19.501.388 I slot print_timing: id 0 | task 9291 | prompt processing, n_tokens = 835, progress = 0.88, t = 35.53 s / 23.50 tokens per second 42.22.824.017 I slot print_timing: id 1 | task 9289 | prompt processing, n_tokens = 642, progress = 0.80, t = 35.52 s / 18.07 tokens per second 42.22.837.863 I slot print_timing: id 2 | task 9288 | prompt processing, n_tokens = 775, progress = 0.99, t = 35.52 s / 21.82 tokens per second 42.22.851.818 I slot print_timing: id 3 | task 9290 | prompt processing, n_tokens = 877, progress = 0.89, t = 35.52 s / 24.69 tokens per second 42.28.113.531 I slot print_timing: id 0 | task 9291 | prompt processing, n_tokens = 948, progress = 1.00, t = 44.14 s / 21.48 tokens per second 42.28.130.072 I slot print_timing: id 1 | task 9289 | prompt processing, n_tokens = 802, progress = 1.00, t = 44.14 s / 18.17 tokens per second 42.28.144.139 I slot print_timing: id 3 | task 9290 | prompt processing, n_tokens = 983, progress = 1.00, t = 44.14 s / 22.27 tokens per second 42.28.714.767 I slot print_timing: id 2 | task 9288 | prompt eval time = 44136.97 ms / 779 tokens ( 56.66 ms per token, 17.65 tokens per second) 42.28.714.774 I slot print_timing: id 2 | task 9288 | eval time = 601.25 ms / 2 tokens ( 601.25 ms per token, 1.66 tokens per second) 42.28.714.774 I slot print_timing: id 2 | task 9288 | total time = 44738.23 ms / 781 tokens 42.28.714.775 I slot print_timing: id 2 | task 9288 | graphs reused = 8265 42.28.714.775 I slot print_timing: id 2 | task 9288 | graph reallocs = 0 / 0 (same size) / (changed size) 42.28.715.078 I slot release: id 2 | task 9288 | stop processing: n_tokens = 780, truncated = 0 42.29.003.403 I slot print_timing: id 0 | task 9291 | prompt eval time = 44737.83 ms / 952 tokens ( 46.99 ms per token, 21.28 tokens per second) 42.29.003.407 I slot print_timing: id 0 | task 9291 | eval time = 289.28 ms / 2 tokens ( 289.28 ms per token, 3.46 tokens per second) 42.29.003.407 I slot print_timing: id 0 | task 9291 | total time = 45027.11 ms / 954 tokens 42.29.003.408 I slot print_timing: id 0 | task 9291 | graphs reused = 8265 42.29.003.408 I slot print_timing: id 0 | task 9291 | graph reallocs = 0 / 0 (same size) / (changed size) 42.29.005.077 I slot release: id 0 | task 9291 | stop processing: n_tokens = 953, truncated = 0 42.29.005.611 I slot print_timing: id 1 | task 9289 | prompt eval time = 44738.08 ms / 806 tokens ( 55.51 ms per token, 18.02 tokens per second) 42.29.005.620 I slot print_timing: id 1 | task 9289 | eval time = 291.09 ms / 2 tokens ( 291.09 ms per token, 3.44 tokens per second) 42.29.005.621 I slot print_timing: id 1 | task 9289 | total time = 45029.17 ms / 808 tokens 42.29.005.621 I slot print_timing: id 1 | task 9289 | graphs reused = 8265 42.29.005.621 I slot print_timing: id 1 | task 9289 | graph reallocs = 0 / 0 (same size) / (changed size) 42.29.005.738 I slot release: id 1 | task 9289 | stop processing: n_tokens = 807, truncated = 0 42.29.006.174 I slot print_timing: id 3 | task 9290 | prompt eval time = 44739.16 ms / 987 tokens ( 45.33 ms per token, 22.06 tokens per second) 42.29.006.178 I slot print_timing: id 3 | task 9290 | eval time = 290.39 ms / 2 tokens ( 290.39 ms per token, 3.44 tokens per second) 42.29.006.178 I slot print_timing: id 3 | task 9290 | total time = 45029.55 ms / 989 tokens 42.29.006.178 I slot print_timing: id 3 | task 9290 | graphs reused = 8265 42.29.006.179 I slot print_timing: id 3 | task 9290 | graph reallocs = 0 / 0 (same size) / (changed size) 42.29.006.310 I slot release: id 3 | task 9290 | stop processing: n_tokens = 988, truncated = 0 42.29.006.319 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 96915948638 42.29.006.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.943 MiB) 42.29.006.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 42.29.632.890 I slot launch_slot_: id 2 | task 9299 | processing task, is_child = 0 42.29.632.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 42.29.632.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 42.29.632.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 42.29.761.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.819 MiB) 42.29.761.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.755 MiB) 42.29.917.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.631 MiB) 42.29.917.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 42.29.917.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 42.30.249.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 96916238636 42.30.249.206 I slot launch_slot_: id 0 | task 9300 | processing task, is_child = 0 42.30.249.293 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 96916239296 42.30.249.357 I slot launch_slot_: id 1 | task 9301 | processing task, is_child = 0 42.30.249.403 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 96916239867 42.30.249.466 I slot launch_slot_: id 3 | task 9302 | processing task, is_child = 0 42.41.535.819 I slot print_timing: id 0 | task 9300 | prompt processing, n_tokens = 260, progress = 0.32, t = 11.29 s / 23.04 tokens per second 42.41.535.834 I slot print_timing: id 1 | task 9301 | prompt processing, n_tokens = 260, progress = 0.30, t = 11.29 s / 23.04 tokens per second 42.41.535.840 I slot print_timing: id 2 | task 9299 | prompt processing, n_tokens = 260, progress = 0.32, t = 11.29 s / 23.04 tokens per second 42.41.535.845 I slot print_timing: id 3 | task 9302 | prompt processing, n_tokens = 260, progress = 0.31, t = 11.29 s / 23.04 tokens per second 42.44.808.686 I slot print_timing: id 0 | task 9300 | prompt processing, n_tokens = 288, progress = 0.36, t = 14.56 s / 19.78 tokens per second 42.45.582.530 I slot print_timing: id 1 | task 9301 | prompt processing, n_tokens = 339, progress = 0.40, t = 14.56 s / 23.28 tokens per second 42.45.586.997 I slot print_timing: id 2 | task 9299 | prompt processing, n_tokens = 285, progress = 0.36, t = 14.56 s / 19.58 tokens per second 42.45.591.408 I slot print_timing: id 3 | task 9302 | prompt processing, n_tokens = 330, progress = 0.39, t = 14.56 s / 22.67 tokens per second 43.03.196.078 I slot print_timing: id 0 | task 9300 | prompt processing, n_tokens = 696, progress = 0.87, t = 32.95 s / 21.13 tokens per second 43.03.972.438 I slot print_timing: id 1 | task 9301 | prompt processing, n_tokens = 696, progress = 0.81, t = 32.95 s / 21.13 tokens per second 43.03.976.861 I slot print_timing: id 2 | task 9299 | prompt processing, n_tokens = 696, progress = 0.87, t = 32.95 s / 21.13 tokens per second 43.03.981.287 I slot print_timing: id 3 | task 9302 | prompt processing, n_tokens = 696, progress = 0.82, t = 32.95 s / 21.13 tokens per second 43.09.789.819 I slot print_timing: id 0 | task 9300 | prompt processing, n_tokens = 800, progress = 1.00, t = 39.54 s / 20.23 tokens per second 43.10.569.205 I slot print_timing: id 1 | task 9301 | prompt processing, n_tokens = 851, progress = 1.00, t = 39.54 s / 21.52 tokens per second 43.10.573.751 I slot print_timing: id 2 | task 9299 | prompt processing, n_tokens = 797, progress = 1.00, t = 39.54 s / 20.16 tokens per second 43.10.578.279 I slot print_timing: id 3 | task 9302 | prompt processing, n_tokens = 842, progress = 1.00, t = 39.54 s / 21.29 tokens per second 43.11.286.698 I slot print_timing: id 0 | task 9300 | prompt eval time = 40825.27 ms / 804 tokens ( 50.78 ms per token, 19.69 tokens per second) 43.11.286.703 I slot print_timing: id 0 | task 9300 | eval time = 211.95 ms / 2 tokens ( 211.95 ms per token, 4.72 tokens per second) 43.11.286.703 I slot print_timing: id 0 | task 9300 | total time = 41037.22 ms / 806 tokens 43.11.286.704 I slot print_timing: id 0 | task 9300 | graphs reused = 8265 43.11.286.704 I slot print_timing: id 0 | task 9300 | graph reallocs = 0 / 0 (same size) / (changed size) 43.11.288.232 I slot release: id 0 | task 9300 | stop processing: n_tokens = 805, truncated = 0 43.11.288.521 I slot print_timing: id 1 | task 9301 | prompt eval time = 40825.37 ms / 855 tokens ( 47.75 ms per token, 20.94 tokens per second) 43.11.288.524 I slot print_timing: id 1 | task 9301 | eval time = 213.61 ms / 2 tokens ( 213.61 ms per token, 4.68 tokens per second) 43.11.288.524 I slot print_timing: id 1 | task 9301 | total time = 41038.98 ms / 857 tokens 43.11.288.525 I slot print_timing: id 1 | task 9301 | graphs reused = 8265 43.11.288.525 I slot print_timing: id 1 | task 9301 | graph reallocs = 0 / 0 (same size) / (changed size) 43.11.288.572 I slot release: id 1 | task 9301 | stop processing: n_tokens = 856, truncated = 0 43.11.288.891 I slot print_timing: id 2 | task 9299 | prompt eval time = 40825.48 ms / 801 tokens ( 50.97 ms per token, 19.62 tokens per second) 43.11.288.893 I slot print_timing: id 2 | task 9299 | eval time = 213.82 ms / 2 tokens ( 213.82 ms per token, 4.68 tokens per second) 43.11.288.894 I slot print_timing: id 2 | task 9299 | total time = 41039.30 ms / 803 tokens 43.11.288.894 I slot print_timing: id 2 | task 9299 | graphs reused = 8265 43.11.288.894 I slot print_timing: id 2 | task 9299 | graph reallocs = 0 / 0 (same size) / (changed size) 43.11.288.927 I slot release: id 2 | task 9299 | stop processing: n_tokens = 802, truncated = 0 43.11.289.280 I slot print_timing: id 3 | task 9302 | prompt eval time = 40825.62 ms / 846 tokens ( 48.26 ms per token, 20.72 tokens per second) 43.11.289.284 I slot print_timing: id 3 | task 9302 | eval time = 214.02 ms / 2 tokens ( 214.02 ms per token, 4.67 tokens per second) 43.11.289.284 I slot print_timing: id 3 | task 9302 | total time = 41039.64 ms / 848 tokens 43.11.289.284 I slot print_timing: id 3 | task 9302 | graphs reused = 8265 43.11.289.285 I slot print_timing: id 3 | task 9302 | graph reallocs = 0 / 0 (same size) / (changed size) 43.11.290.046 I slot release: id 3 | task 9302 | stop processing: n_tokens = 847, truncated = 0 43.11.299.773 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.899 43.11.299.800 I slot launch_slot_: id 0 | task 9310 | processing task, is_child = 0 43.11.299.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 43.11.299.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 43.11.299.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 841.603 MiB) 43.12.818.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 839.602 MiB) 43.13.069.408 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 96958522129 43.13.069.593 I slot launch_slot_: id 1 | task 9311 | processing task, is_child = 0 43.13.069.689 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 96958522484 43.13.069.753 I slot launch_slot_: id 2 | task 9312 | processing task, is_child = 0 43.13.069.800 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 96958523604 43.13.069.862 I slot launch_slot_: id 3 | task 9313 | processing task, is_child = 0 43.20.756.453 I slot print_timing: id 0 | task 9310 | prompt processing, n_tokens = 125, progress = 1.00, t = 7.69 s / 16.26 tokens per second 43.21.063.043 I slot print_timing: id 1 | task 9311 | prompt processing, n_tokens = 171, progress = 0.18, t = 7.67 s / 22.29 tokens per second 43.21.086.708 I slot print_timing: id 2 | task 9312 | prompt processing, n_tokens = 160, progress = 0.18, t = 7.67 s / 20.86 tokens per second 43.21.091.194 I slot print_timing: id 3 | task 9313 | prompt processing, n_tokens = 160, progress = 0.18, t = 7.67 s / 20.86 tokens per second 43.27.789.603 I slot print_timing: id 1 | task 9311 | prompt processing, n_tokens = 340, progress = 0.35, t = 14.70 s / 23.12 tokens per second 43.27.789.614 I slot print_timing: id 2 | task 9312 | prompt processing, n_tokens = 342, progress = 0.38, t = 14.70 s / 23.26 tokens per second 43.27.789.620 I slot print_timing: id 3 | task 9313 | prompt processing, n_tokens = 342, progress = 0.39, t = 14.70 s / 23.26 tokens per second 43.30.403.575 I slot print_timing: id 0 | task 9310 | prompt eval time = 14719.71 ms / 129 tokens ( 114.11 ms per token, 8.76 tokens per second) 43.30.403.578 I slot print_timing: id 0 | task 9310 | eval time = 2613.99 ms / 2 tokens ( 2613.99 ms per token, 0.38 tokens per second) 43.30.403.579 I slot print_timing: id 0 | task 9310 | total time = 17333.69 ms / 131 tokens 43.30.403.579 I slot print_timing: id 0 | task 9310 | graphs reused = 8265 43.30.403.580 I slot print_timing: id 0 | task 9310 | graph reallocs = 0 / 0 (same size) / (changed size) 43.30.404.223 I slot release: id 0 | task 9310 | stop processing: n_tokens = 826, truncated = 0 43.30.404.238 I slot print_timing: id 1 | task 9311 | prompt processing, n_tokens = 447, progress = 0.46, t = 17.32 s / 25.81 tokens per second 43.30.419.558 I slot print_timing: id 2 | task 9312 | prompt processing, n_tokens = 380, progress = 0.42, t = 17.32 s / 21.94 tokens per second 43.30.431.818 I slot print_timing: id 3 | task 9313 | prompt processing, n_tokens = 364, progress = 0.41, t = 17.32 s / 21.02 tokens per second 43.44.095.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 96977637781 43.44.095.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 846.730 MiB) 43.44.426.090 I slot launch_slot_: id 0 | task 9318 | processing task, is_child = 0 43.44.426.240 I slot print_timing: id 1 | task 9311 | prompt processing, n_tokens = 831, progress = 0.86, t = 31.01 s / 26.80 tokens per second 43.44.434.186 I slot print_timing: id 2 | task 9312 | prompt processing, n_tokens = 754, progress = 0.84, t = 31.01 s / 24.31 tokens per second 43.44.439.239 I slot print_timing: id 3 | task 9313 | prompt processing, n_tokens = 754, progress = 0.86, t = 31.01 s / 24.31 tokens per second 43.51.528.758 I slot print_timing: id 0 | task 9318 | prompt processing, n_tokens = 182, progress = 0.18, t = 7.10 s / 25.62 tokens per second 43.51.837.749 I slot print_timing: id 1 | task 9311 | prompt processing, n_tokens = 959, progress = 1.00, t = 38.44 s / 24.95 tokens per second 43.51.851.819 I slot print_timing: id 2 | task 9312 | prompt processing, n_tokens = 892, progress = 1.00, t = 38.44 s / 23.20 tokens per second 43.51.865.986 I slot print_timing: id 3 | task 9313 | prompt processing, n_tokens = 876, progress = 1.00, t = 38.44 s / 22.79 tokens per second 43.54.840.720 I slot print_timing: id 0 | task 9318 | prompt processing, n_tokens = 403, progress = 0.41, t = 10.41 s / 38.70 tokens per second 43.56.177.279 I slot print_timing: id 1 | task 9311 | prompt eval time = 41754.47 ms / 963 tokens ( 43.36 ms per token, 23.06 tokens per second) 43.56.177.282 I slot print_timing: id 1 | task 9311 | eval time = 1337.49 ms / 2 tokens ( 1337.49 ms per token, 0.75 tokens per second) 43.56.177.283 I slot print_timing: id 1 | task 9311 | total time = 43091.96 ms / 965 tokens 43.56.177.283 I slot print_timing: id 1 | task 9311 | graphs reused = 8265 43.56.177.283 I slot print_timing: id 1 | task 9311 | graph reallocs = 0 / 0 (same size) / (changed size) 43.56.179.232 I slot release: id 1 | task 9311 | stop processing: n_tokens = 964, truncated = 0 43.56.180.024 I slot print_timing: id 2 | task 9312 | prompt eval time = 41754.83 ms / 896 tokens ( 46.60 ms per token, 21.46 tokens per second) 43.56.180.027 I slot print_timing: id 2 | task 9312 | eval time = 1339.80 ms / 2 tokens ( 1339.80 ms per token, 0.75 tokens per second) 43.56.180.028 I slot print_timing: id 2 | task 9312 | total time = 43094.63 ms / 898 tokens 43.56.180.028 I slot print_timing: id 2 | task 9312 | graphs reused = 8265 43.56.180.029 I slot print_timing: id 2 | task 9312 | graph reallocs = 0 / 0 (same size) / (changed size) 43.56.181.135 I slot release: id 2 | task 9312 | stop processing: n_tokens = 897, truncated = 0 43.56.181.637 I slot print_timing: id 3 | task 9313 | prompt eval time = 41755.23 ms / 880 tokens ( 47.45 ms per token, 21.08 tokens per second) 43.56.181.646 I slot print_timing: id 3 | task 9313 | eval time = 1340.95 ms / 2 tokens ( 1340.95 ms per token, 0.75 tokens per second) 43.56.181.647 I slot print_timing: id 3 | task 9313 | total time = 43096.18 ms / 882 tokens 43.56.181.647 I slot print_timing: id 3 | task 9313 | graphs reused = 8265 43.56.181.647 I slot print_timing: id 3 | task 9313 | graph reallocs = 0 / 0 (same size) / (changed size) 43.56.181.729 I slot release: id 3 | task 9313 | stop processing: n_tokens = 881, truncated = 0 43.56.181.746 I slot print_timing: id 0 | task 9318 | prompt processing, n_tokens = 471, progress = 0.48, t = 11.75 s / 40.08 tokens per second 43.56.205.063 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 97003412791 43.56.205.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 830.599 MiB) 44.00.946.568 I slot launch_slot_: id 1 | task 9323 | processing task, is_child = 0 44.00.946.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 853.482 MiB) 44.01.063.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.899 MiB) 44.01.187.565 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 97003414694 44.01.187.684 I slot launch_slot_: id 2 | task 9324 | processing task, is_child = 0 44.01.187.730 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 97003415286 44.01.187.795 I slot launch_slot_: id 3 | task 9325 | processing task, is_child = 0 44.01.187.802 I slot print_timing: id 0 | task 9318 | prompt processing, n_tokens = 872, progress = 0.88, t = 11.78 s / 74.03 tokens per second 44.07.202.613 I slot print_timing: id 0 | task 9318 | prompt processing, n_tokens = 983, progress = 1.00, t = 22.78 s / 43.16 tokens per second 44.07.981.132 I slot print_timing: id 1 | task 9323 | prompt processing, n_tokens = 182, progress = 0.18, t = 5.99 s / 30.37 tokens per second 44.07.985.571 I slot print_timing: id 2 | task 9324 | prompt processing, n_tokens = 129, progress = 0.14, t = 5.99 s / 21.52 tokens per second 44.07.990.057 I slot print_timing: id 3 | task 9325 | prompt processing, n_tokens = 129, progress = 0.07, t = 5.99 s / 21.52 tokens per second 44.14.943.647 I slot print_timing: id 1 | task 9323 | prompt processing, n_tokens = 403, progress = 0.39, t = 13.73 s / 29.34 tokens per second 44.14.943.661 I slot print_timing: id 2 | task 9324 | prompt processing, n_tokens = 283, progress = 0.31, t = 13.73 s / 20.61 tokens per second 44.14.943.677 I slot print_timing: id 3 | task 9325 | prompt processing, n_tokens = 283, progress = 0.16, t = 13.73 s / 20.61 tokens per second 44.23.648.917 I slot print_timing: id 0 | task 9318 | prompt eval time = 30517.51 ms / 987 tokens ( 30.92 ms per token, 32.34 tokens per second) 44.23.648.919 I slot print_timing: id 0 | task 9318 | eval time = 8705.28 ms / 2 tokens ( 8705.28 ms per token, 0.11 tokens per second) 44.23.648.920 I slot print_timing: id 0 | task 9318 | total time = 39222.79 ms / 989 tokens 44.23.648.920 I slot print_timing: id 0 | task 9318 | graphs reused = 8265 44.23.648.921 I slot print_timing: id 0 | task 9318 | graph reallocs = 0 / 0 (same size) / (changed size) 44.23.649.015 I slot release: id 0 | task 9318 | stop processing: n_tokens = 988, truncated = 0 44.23.649.028 I slot print_timing: id 1 | task 9323 | prompt processing, n_tokens = 506, progress = 0.50, t = 22.44 s / 22.55 tokens per second 44.23.654.248 I slot print_timing: id 2 | task 9324 | prompt processing, n_tokens = 408, progress = 0.44, t = 22.44 s / 18.18 tokens per second 44.23.658.910 I slot print_timing: id 3 | task 9325 | prompt processing, n_tokens = 753, progress = 0.42, t = 22.44 s / 33.56 tokens per second 44.36.275.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 97030882572 44.36.275.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 44.38.504.140 I slot launch_slot_: id 0 | task 9330 | processing task, is_child = 0 44.38.504.234 I slot print_timing: id 1 | task 9323 | prompt processing, n_tokens = 872, progress = 0.85, t = 35.07 s / 24.87 tokens per second 44.38.508.700 I slot print_timing: id 2 | task 9324 | prompt processing, n_tokens = 753, progress = 0.81, t = 35.07 s / 21.47 tokens per second 44.38.513.193 I slot print_timing: id 3 | task 9325 | prompt processing, n_tokens = 1264, progress = 0.71, t = 35.07 s / 36.05 tokens per second 44.46.148.125 I slot print_timing: id 0 | task 9330 | prompt processing, n_tokens = 129, progress = 0.14, t = 7.64 s / 16.88 tokens per second 44.50.230.008 I slot print_timing: id 1 | task 9323 | prompt processing, n_tokens = 1018, progress = 1.00, t = 44.94 s / 22.65 tokens per second 44.50.234.549 I slot print_timing: id 2 | task 9324 | prompt processing, n_tokens = 920, progress = 1.00, t = 44.94 s / 20.47 tokens per second 44.50.262.069 I slot print_timing: id 3 | task 9325 | prompt processing, n_tokens = 1776, progress = 1.00, t = 44.94 s / 39.52 tokens per second 44.52.519.997 I slot print_timing: id 0 | task 9330 | prompt processing, n_tokens = 283, progress = 0.30, t = 14.01 s / 20.19 tokens per second 44.54.558.942 I slot print_timing: id 1 | task 9323 | prompt eval time = 51310.36 ms / 1022 tokens ( 50.21 ms per token, 19.92 tokens per second) 44.54.558.945 I slot print_timing: id 1 | task 9323 | eval time = 2039.45 ms / 2 tokens ( 2039.45 ms per token, 0.49 tokens per second) 44.54.558.946 I slot print_timing: id 1 | task 9323 | total time = 53349.80 ms / 1024 tokens 44.54.558.946 I slot print_timing: id 1 | task 9323 | graphs reused = 8265 44.54.558.947 I slot print_timing: id 1 | task 9323 | graph reallocs = 0 / 0 (same size) / (changed size) 44.54.559.033 I slot release: id 1 | task 9323 | stop processing: n_tokens = 1023, truncated = 0 44.54.559.287 I slot print_timing: id 2 | task 9324 | prompt eval time = 51310.53 ms / 924 tokens ( 55.53 ms per token, 18.01 tokens per second) 44.54.559.292 I slot print_timing: id 2 | task 9324 | eval time = 2039.55 ms / 2 tokens ( 2039.55 ms per token, 0.49 tokens per second) 44.54.559.293 I slot print_timing: id 2 | task 9324 | total time = 53350.07 ms / 926 tokens 44.54.559.293 I slot print_timing: id 2 | task 9324 | graphs reused = 8265 44.54.559.293 I slot print_timing: id 2 | task 9324 | graph reallocs = 0 / 0 (same size) / (changed size) 44.54.560.751 I slot release: id 2 | task 9324 | stop processing: n_tokens = 925, truncated = 0 44.54.561.291 I slot print_timing: id 3 | task 9325 | prompt eval time = 51310.70 ms / 1780 tokens ( 28.83 ms per token, 34.69 tokens per second) 44.54.561.298 I slot print_timing: id 3 | task 9325 | eval time = 2041.30 ms / 2 tokens ( 2041.30 ms per token, 0.49 tokens per second) 44.54.561.299 I slot print_timing: id 3 | task 9325 | total time = 53352.00 ms / 1782 tokens 44.54.561.299 I slot print_timing: id 3 | task 9325 | graphs reused = 8265 44.54.561.299 I slot print_timing: id 3 | task 9325 | graph reallocs = 0 / 0 (same size) / (changed size) 44.54.563.589 I slot release: id 3 | task 9325 | stop processing: n_tokens = 1781, truncated = 0 44.54.563.610 I slot print_timing: id 0 | task 9330 | prompt processing, n_tokens = 421, progress = 0.45, t = 16.05 s / 26.22 tokens per second 44.54.574.885 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 97061792590 44.54.574.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.587 MiB) 44.58.652.458 I slot launch_slot_: id 1 | task 9335 | processing task, is_child = 0 44.58.652.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 44.58.882.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 44.59.185.592 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 97061794311 44.59.185.744 I slot launch_slot_: id 2 | task 9336 | processing task, is_child = 0 44.59.185.818 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 97061797147 44.59.185.906 I slot launch_slot_: id 3 | task 9337 | processing task, is_child = 0 44.59.185.920 I slot print_timing: id 0 | task 9330 | prompt processing, n_tokens = 753, progress = 0.80, t = 16.07 s / 46.86 tokens per second 45.05.617.644 I slot print_timing: id 0 | task 9330 | prompt processing, n_tokens = 933, progress = 1.00, t = 27.11 s / 34.41 tokens per second 45.06.389.836 I slot print_timing: id 1 | task 9335 | prompt processing, n_tokens = 140, progress = 0.16, t = 6.43 s / 21.78 tokens per second 45.06.534.852 I slot print_timing: id 2 | task 9336 | prompt processing, n_tokens = 118, progress = 0.16, t = 6.43 s / 18.36 tokens per second 45.06.583.451 I slot print_timing: id 3 | task 9337 | prompt processing, n_tokens = 118, progress = 0.17, t = 6.43 s / 18.36 tokens per second 45.11.113.550 I slot print_timing: id 1 | task 9335 | prompt processing, n_tokens = 268, progress = 0.30, t = 11.92 s / 22.48 tokens per second 45.11.113.561 I slot print_timing: id 2 | task 9336 | prompt processing, n_tokens = 225, progress = 0.30, t = 11.92 s / 18.87 tokens per second 45.11.128.530 I slot print_timing: id 3 | task 9337 | prompt processing, n_tokens = 197, progress = 0.28, t = 11.92 s / 16.52 tokens per second 45.21.649.476 I slot print_timing: id 0 | task 9330 | prompt eval time = 32609.37 ms / 937 tokens ( 34.80 ms per token, 28.73 tokens per second) 45.21.649.482 I slot print_timing: id 0 | task 9330 | eval time = 10535.95 ms / 2 tokens (10535.95 ms per token, 0.09 tokens per second) 45.21.649.483 I slot print_timing: id 0 | task 9330 | total time = 43145.32 ms / 939 tokens 45.21.649.483 I slot print_timing: id 0 | task 9330 | graphs reused = 8265 45.21.649.484 I slot print_timing: id 0 | task 9330 | graph reallocs = 0 / 0 (same size) / (changed size) 45.21.650.151 I slot release: id 0 | task 9330 | stop processing: n_tokens = 938, truncated = 0 45.21.650.177 I slot print_timing: id 1 | task 9335 | prompt processing, n_tokens = 364, progress = 0.41, t = 22.46 s / 16.21 tokens per second 45.21.667.061 I slot print_timing: id 2 | task 9336 | prompt processing, n_tokens = 603, progress = 0.81, t = 22.46 s / 26.85 tokens per second 45.21.680.559 I slot print_timing: id 3 | task 9337 | prompt processing, n_tokens = 603, progress = 0.85, t = 22.46 s / 26.85 tokens per second 45.26.202.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 97088883711 45.26.202.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.274 MiB) 45.29.507.436 I slot launch_slot_: id 0 | task 9342 | processing task, is_child = 0 45.29.507.526 I slot print_timing: id 1 | task 9335 | prompt processing, n_tokens = 769, progress = 0.87, t = 27.01 s / 28.47 tokens per second 45.29.511.976 I slot print_timing: id 2 | task 9336 | prompt processing, n_tokens = 737, progress = 0.99, t = 27.01 s / 27.28 tokens per second 45.29.524.596 I slot print_timing: id 3 | task 9337 | prompt processing, n_tokens = 709, progress = 0.99, t = 27.01 s / 26.25 tokens per second 45.32.812.041 I slot print_timing: id 0 | task 9342 | prompt processing, n_tokens = 118, progress = 0.16, t = 3.30 s / 35.72 tokens per second 45.32.819.557 I slot print_timing: id 1 | task 9335 | prompt processing, n_tokens = 876, progress = 1.00, t = 33.62 s / 26.06 tokens per second 45.34.372.376 I slot print_timing: id 2 | task 9336 | prompt eval time = 33620.65 ms / 741 tokens ( 45.37 ms per token, 22.04 tokens per second) 45.34.372.380 I slot print_timing: id 2 | task 9336 | eval time = 1560.77 ms / 2 tokens ( 1560.77 ms per token, 0.64 tokens per second) 45.34.372.380 I slot print_timing: id 2 | task 9336 | total time = 35181.42 ms / 743 tokens 45.34.372.381 I slot print_timing: id 2 | task 9336 | graphs reused = 8265 45.34.372.381 I slot print_timing: id 2 | task 9336 | graph reallocs = 0 / 0 (same size) / (changed size) 45.34.374.321 I slot release: id 2 | task 9336 | stop processing: n_tokens = 742, truncated = 0 45.34.374.784 I slot print_timing: id 3 | task 9337 | prompt eval time = 33621.02 ms / 713 tokens ( 47.15 ms per token, 21.21 tokens per second) 45.34.374.787 I slot print_timing: id 3 | task 9337 | eval time = 1562.75 ms / 2 tokens ( 1562.75 ms per token, 0.64 tokens per second) 45.34.374.788 I slot print_timing: id 3 | task 9337 | total time = 35183.77 ms / 715 tokens 45.34.374.788 I slot print_timing: id 3 | task 9337 | graphs reused = 8265 45.34.374.788 I slot print_timing: id 3 | task 9337 | graph reallocs = 0 / 0 (same size) / (changed size) 45.34.375.051 I slot release: id 3 | task 9337 | stop processing: n_tokens = 714, truncated = 0 45.34.375.072 I slot print_timing: id 0 | task 9342 | prompt processing, n_tokens = 200, progress = 0.28, t = 4.86 s / 41.12 tokens per second 45.39.224.895 I slot print_timing: id 1 | task 9335 | prompt eval time = 35181.32 ms / 880 tokens ( 39.98 ms per token, 25.01 tokens per second) 45.39.224.898 I slot print_timing: id 1 | task 9335 | eval time = 4852.71 ms / 2 tokens ( 4852.71 ms per token, 0.21 tokens per second) 45.39.224.898 I slot print_timing: id 1 | task 9335 | total time = 40034.03 ms / 882 tokens 45.39.224.899 I slot print_timing: id 1 | task 9335 | graphs reused = 8265 45.39.224.899 I slot print_timing: id 1 | task 9335 | graph reallocs = 0 / 0 (same size) / (changed size) 45.39.226.886 I slot release: id 1 | task 9335 | stop processing: n_tokens = 881, truncated = 0 45.39.226.908 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.850 45.39.227.025 I slot launch_slot_: id 2 | task 9346 | processing task, is_child = 0 45.39.227.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.088 MiB) 45.39.372.037 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 45.39.506.002 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 45.39.506.081 I slot launch_slot_: id 3 | task 9347 | processing task, is_child = 0 45.39.506.135 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 97106460444 45.39.506.205 I slot launch_slot_: id 1 | task 9348 | processing task, is_child = 0 45.39.506.211 I slot print_timing: id 0 | task 9342 | prompt processing, n_tokens = 603, progress = 0.84, t = 9.72 s / 62.06 tokens per second 45.45.462.813 I slot print_timing: id 0 | task 9342 | prompt processing, n_tokens = 712, progress = 0.99, t = 15.96 s / 44.62 tokens per second 45.45.636.411 I slot print_timing: id 1 | task 9348 | prompt processing, n_tokens = 133, progress = 0.15, t = 5.94 s / 22.38 tokens per second 45.45.640.895 I slot print_timing: id 2 | task 9346 | prompt processing, n_tokens = 112, progress = 0.99, t = 5.94 s / 18.85 tokens per second 45.45.645.443 I slot print_timing: id 3 | task 9347 | prompt processing, n_tokens = 118, progress = 0.99, t = 5.94 s / 19.88 tokens per second 45.47.869.832 I slot print_timing: id 1 | task 9348 | prompt processing, n_tokens = 277, progress = 0.32, t = 8.35 s / 33.18 tokens per second 45.49.378.825 I slot print_timing: id 0 | task 9342 | prompt eval time = 18361.94 ms / 716 tokens ( 25.65 ms per token, 38.99 tokens per second) 45.49.378.832 I slot print_timing: id 0 | task 9342 | eval time = 1509.44 ms / 2 tokens ( 1509.44 ms per token, 0.66 tokens per second) 45.49.378.833 I slot print_timing: id 0 | task 9342 | total time = 19871.37 ms / 718 tokens 45.49.378.833 I slot print_timing: id 0 | task 9342 | graphs reused = 8265 45.49.378.834 I slot print_timing: id 0 | task 9342 | graph reallocs = 0 / 0 (same size) / (changed size) 45.49.378.876 I slot release: id 0 | task 9342 | stop processing: n_tokens = 717, truncated = 0 45.49.379.114 I slot print_timing: id 2 | task 9346 | prompt eval time = 8349.49 ms / 116 tokens ( 71.98 ms per token, 13.89 tokens per second) 45.49.379.116 I slot print_timing: id 2 | task 9346 | eval time = 1509.51 ms / 2 tokens ( 1509.51 ms per token, 0.66 tokens per second) 45.49.379.117 I slot print_timing: id 2 | task 9346 | total time = 9859.00 ms / 118 tokens 45.49.379.117 I slot print_timing: id 2 | task 9346 | graphs reused = 8265 45.49.379.117 I slot print_timing: id 2 | task 9346 | graph reallocs = 0 / 0 (same size) / (changed size) 45.49.379.145 I slot release: id 2 | task 9346 | stop processing: n_tokens = 720, truncated = 0 45.49.379.395 I slot print_timing: id 3 | task 9347 | prompt eval time = 8342.03 ms / 122 tokens ( 68.38 ms per token, 14.62 tokens per second) 45.49.379.397 I slot print_timing: id 3 | task 9347 | eval time = 1509.57 ms / 2 tokens ( 1509.57 ms per token, 0.66 tokens per second) 45.49.379.398 I slot print_timing: id 3 | task 9347 | total time = 9851.60 ms / 124 tokens 45.49.379.398 I slot print_timing: id 3 | task 9347 | graphs reused = 8265 45.49.379.398 I slot print_timing: id 3 | task 9347 | graph reallocs = 0 / 0 (same size) / (changed size) 45.49.379.417 I slot release: id 3 | task 9347 | stop processing: n_tokens = 726, truncated = 0 45.49.379.426 I slot print_timing: id 1 | task 9348 | prompt processing, n_tokens = 360, progress = 0.41, t = 9.86 s / 36.52 tokens per second 45.49.392.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 97116612433 45.49.392.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.403 MiB) 45.54.134.549 I slot launch_slot_: id 0 | task 9353 | processing task, is_child = 0 45.54.134.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 45.54.269.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 45.54.399.418 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 97116612702 45.54.399.523 I slot launch_slot_: id 2 | task 9354 | processing task, is_child = 0 45.54.399.564 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 97116612974 45.54.399.621 I slot launch_slot_: id 3 | task 9355 | processing task, is_child = 0 45.54.399.701 I slot print_timing: id 1 | task 9348 | prompt processing, n_tokens = 766, progress = 0.87, t = 9.87 s / 77.59 tokens per second 46.00.308.871 I slot print_timing: id 0 | task 9353 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.91 s / 24.03 tokens per second 46.01.474.874 I slot print_timing: id 1 | task 9348 | prompt processing, n_tokens = 872, progress = 1.00, t = 20.79 s / 41.95 tokens per second 46.01.479.511 I slot print_timing: id 2 | task 9354 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.90 s / 24.05 tokens per second 46.01.483.956 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.90 s / 24.05 tokens per second 46.09.172.265 I slot print_timing: id 0 | task 9353 | prompt processing, n_tokens = 345, progress = 0.35, t = 14.77 s / 23.35 tokens per second 46.09.172.281 I slot print_timing: id 2 | task 9354 | prompt processing, n_tokens = 345, progress = 0.33, t = 14.77 s / 23.36 tokens per second 46.09.172.288 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 345, progress = 0.34, t = 14.77 s / 23.36 tokens per second 46.14.932.963 I slot print_timing: id 1 | task 9348 | prompt eval time = 29652.20 ms / 876 tokens ( 33.85 ms per token, 29.54 tokens per second) 46.14.932.968 I slot print_timing: id 1 | task 9348 | eval time = 5760.71 ms / 2 tokens ( 5760.71 ms per token, 0.17 tokens per second) 46.14.932.969 I slot print_timing: id 1 | task 9348 | total time = 35412.91 ms / 878 tokens 46.14.932.969 I slot print_timing: id 1 | task 9348 | graphs reused = 8265 46.14.932.970 I slot print_timing: id 1 | task 9348 | graph reallocs = 0 / 0 (same size) / (changed size) 46.14.934.981 I slot release: id 1 | task 9348 | stop processing: n_tokens = 877, truncated = 0 46.14.935.009 I slot print_timing: id 0 | task 9353 | prompt processing, n_tokens = 476, progress = 0.48, t = 20.53 s / 23.18 tokens per second 46.14.941.660 I slot print_timing: id 2 | task 9354 | prompt processing, n_tokens = 518, progress = 0.50, t = 20.53 s / 25.23 tokens per second 46.14.946.173 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 490, progress = 0.49, t = 20.53 s / 23.87 tokens per second 46.27.678.137 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 97142168540 46.27.678.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 46.28.118.221 I slot launch_slot_: id 1 | task 9360 | processing task, is_child = 0 46.28.118.235 I slot print_timing: id 0 | task 9353 | prompt processing, n_tokens = 861, progress = 0.87, t = 33.28 s / 25.87 tokens per second 46.28.122.772 I slot print_timing: id 2 | task 9354 | prompt processing, n_tokens = 861, progress = 0.83, t = 33.27 s / 25.88 tokens per second 46.28.127.210 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 861, progress = 0.86, t = 33.27 s / 25.88 tokens per second 46.34.969.234 I slot print_timing: id 0 | task 9353 | prompt processing, n_tokens = 988, progress = 1.00, t = 40.57 s / 24.35 tokens per second 46.35.409.993 I slot print_timing: id 1 | task 9360 | prompt processing, n_tokens = 142, progress = 0.14, t = 6.85 s / 20.74 tokens per second 46.35.414.447 I slot print_timing: id 2 | task 9354 | prompt processing, n_tokens = 1030, progress = 1.00, t = 40.56 s / 25.39 tokens per second 46.35.418.975 I slot print_timing: id 3 | task 9355 | prompt processing, n_tokens = 1002, progress = 1.00, t = 40.56 s / 24.70 tokens per second 46.38.369.512 I slot print_timing: id 1 | task 9360 | prompt processing, n_tokens = 345, progress = 0.35, t = 10.25 s / 33.67 tokens per second 46.40.572.848 I slot print_timing: id 0 | task 9353 | prompt eval time = 43969.41 ms / 992 tokens ( 44.32 ms per token, 22.56 tokens per second) 46.40.572.850 I slot print_timing: id 0 | task 9353 | eval time = 2203.79 ms / 2 tokens ( 2203.79 ms per token, 0.45 tokens per second) 46.40.572.851 I slot print_timing: id 0 | task 9353 | total time = 46173.20 ms / 994 tokens 46.40.572.852 I slot print_timing: id 0 | task 9353 | graphs reused = 8265 46.40.572.852 I slot print_timing: id 0 | task 9353 | graph reallocs = 0 / 0 (same size) / (changed size) 46.40.572.909 I slot release: id 0 | task 9353 | stop processing: n_tokens = 993, truncated = 0 46.40.573.138 I slot print_timing: id 2 | task 9354 | prompt eval time = 43964.96 ms / 1034 tokens ( 42.52 ms per token, 23.52 tokens per second) 46.40.573.140 I slot print_timing: id 2 | task 9354 | eval time = 2203.87 ms / 2 tokens ( 2203.87 ms per token, 0.45 tokens per second) 46.40.573.140 I slot print_timing: id 2 | task 9354 | total time = 46168.82 ms / 1036 tokens 46.40.573.140 I slot print_timing: id 2 | task 9354 | graphs reused = 8265 46.40.573.141 I slot print_timing: id 2 | task 9354 | graph reallocs = 0 / 0 (same size) / (changed size) 46.40.573.189 I slot release: id 2 | task 9354 | stop processing: n_tokens = 1035, truncated = 0 46.40.573.427 I slot print_timing: id 3 | task 9355 | prompt eval time = 43965.13 ms / 1006 tokens ( 43.70 ms per token, 22.88 tokens per second) 46.40.573.428 I slot print_timing: id 3 | task 9355 | eval time = 2203.92 ms / 2 tokens ( 2203.92 ms per token, 0.45 tokens per second) 46.40.573.429 I slot print_timing: id 3 | task 9355 | total time = 46169.05 ms / 1008 tokens 46.40.573.429 I slot print_timing: id 3 | task 9355 | graphs reused = 8265 46.40.573.429 I slot print_timing: id 3 | task 9355 | graph reallocs = 0 / 0 (same size) / (changed size) 46.40.573.458 I slot release: id 3 | task 9355 | stop processing: n_tokens = 1007, truncated = 0 46.40.573.467 I slot print_timing: id 1 | task 9360 | prompt processing, n_tokens = 483, progress = 0.48, t = 12.45 s / 38.80 tokens per second 46.40.586.320 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.895 46.40.586.358 I slot launch_slot_: id 0 | task 9365 | processing task, is_child = 0 46.40.586.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.092 MiB) 46.44.959.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.965 MiB) 46.45.078.154 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 97167806746 46.45.078.280 I slot launch_slot_: id 2 | task 9366 | processing task, is_child = 0 46.45.078.330 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 97167807015 46.45.078.402 I slot launch_slot_: id 3 | task 9367 | processing task, is_child = 0 46.45.086.023 I slot print_timing: id 1 | task 9360 | prompt processing, n_tokens = 861, progress = 0.86, t = 12.46 s / 69.08 tokens per second 46.51.713.633 I slot print_timing: id 0 | task 9365 | prompt processing, n_tokens = 128, progress = 1.00, t = 6.64 s / 19.29 tokens per second 46.52.497.915 I slot print_timing: id 1 | task 9360 | prompt processing, n_tokens = 995, progress = 1.00, t = 23.59 s / 42.18 tokens per second 46.52.502.784 I slot print_timing: id 2 | task 9366 | prompt processing, n_tokens = 193, progress = 0.22, t = 6.62 s / 29.14 tokens per second 46.52.507.205 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 115, progress = 0.11, t = 6.62 s / 17.36 tokens per second 46.56.962.704 I slot print_timing: id 2 | task 9366 | prompt processing, n_tokens = 327, progress = 0.37, t = 11.87 s / 27.54 tokens per second 46.56.962.714 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 293, progress = 0.29, t = 11.87 s / 24.68 tokens per second 47.00.537.223 I slot print_timing: id 0 | task 9365 | prompt eval time = 11884.03 ms / 132 tokens ( 90.03 ms per token, 11.11 tokens per second) 47.00.537.225 I slot print_timing: id 0 | task 9365 | eval time = 3574.77 ms / 2 tokens ( 3574.77 ms per token, 0.28 tokens per second) 47.00.537.226 I slot print_timing: id 0 | task 9365 | total time = 15458.81 ms / 134 tokens 47.00.537.226 I slot print_timing: id 0 | task 9365 | graphs reused = 8265 47.00.537.227 I slot print_timing: id 0 | task 9365 | graph reallocs = 0 / 0 (same size) / (changed size) 47.00.537.268 I slot release: id 0 | task 9365 | stop processing: n_tokens = 994, truncated = 0 47.00.537.492 I slot print_timing: id 1 | task 9360 | prompt eval time = 28839.99 ms / 999 tokens ( 28.87 ms per token, 34.64 tokens per second) 47.00.537.495 I slot print_timing: id 1 | task 9360 | eval time = 3574.80 ms / 2 tokens ( 3574.80 ms per token, 0.28 tokens per second) 47.00.537.496 I slot print_timing: id 1 | task 9360 | total time = 32414.78 ms / 1001 tokens 47.00.537.496 I slot print_timing: id 1 | task 9360 | graphs reused = 8265 47.00.537.496 I slot print_timing: id 1 | task 9360 | graph reallocs = 0 / 0 (same size) / (changed size) 47.00.537.527 I slot release: id 1 | task 9360 | stop processing: n_tokens = 1000, truncated = 0 47.00.537.535 I slot print_timing: id 2 | task 9366 | prompt processing, n_tokens = 363, progress = 0.41, t = 15.45 s / 23.50 tokens per second 47.00.545.705 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 502, progress = 0.49, t = 15.45 s / 32.50 tokens per second 47.06.786.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 97187770825 47.06.786.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.484 MiB) 47.07.941.453 I slot launch_slot_: id 0 | task 9372 | processing task, is_child = 0 47.07.941.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.777 MiB) 47.08.084.303 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 97187771084 47.08.084.837 I slot launch_slot_: id 1 | task 9373 | processing task, is_child = 0 47.08.085.052 I slot print_timing: id 2 | task 9366 | prompt processing, n_tokens = 730, progress = 0.83, t = 21.70 s / 33.65 tokens per second 47.08.091.497 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 773, progress = 0.76, t = 21.70 s / 35.63 tokens per second 47.14.402.141 I slot print_timing: id 0 | task 9372 | prompt processing, n_tokens = 115, progress = 0.13, t = 6.32 s / 18.20 tokens per second 47.15.559.666 I slot print_timing: id 1 | task 9373 | prompt processing, n_tokens = 115, progress = 0.11, t = 6.32 s / 18.20 tokens per second 47.15.564.080 I slot print_timing: id 2 | task 9366 | prompt processing, n_tokens = 875, progress = 1.00, t = 29.31 s / 29.85 tokens per second 47.15.574.418 I slot print_timing: id 3 | task 9367 | prompt processing, n_tokens = 1014, progress = 1.00, t = 29.31 s / 34.59 tokens per second 47.19.998.633 I slot print_timing: id 0 | task 9372 | prompt processing, n_tokens = 293, progress = 0.33, t = 11.91 s / 24.59 tokens per second 47.19.998.648 I slot print_timing: id 1 | task 9373 | prompt processing, n_tokens = 293, progress = 0.29, t = 11.91 s / 24.59 tokens per second 47.23.871.663 I slot print_timing: id 2 | task 9366 | prompt eval time = 34907.95 ms / 879 tokens ( 39.71 ms per token, 25.18 tokens per second) 47.23.871.667 I slot print_timing: id 2 | task 9366 | eval time = 3873.26 ms / 2 tokens ( 3873.26 ms per token, 0.26 tokens per second) 47.23.871.668 I slot print_timing: id 2 | task 9366 | total time = 38781.21 ms / 881 tokens 47.23.871.668 I slot print_timing: id 2 | task 9366 | graphs reused = 8265 47.23.871.669 I slot print_timing: id 2 | task 9366 | graph reallocs = 0 / 0 (same size) / (changed size) 47.23.871.750 I slot release: id 2 | task 9366 | stop processing: n_tokens = 880, truncated = 0 47.23.872.002 I slot print_timing: id 3 | task 9367 | prompt eval time = 34908.10 ms / 1018 tokens ( 34.29 ms per token, 29.16 tokens per second) 47.23.872.004 I slot print_timing: id 3 | task 9367 | eval time = 3873.38 ms / 2 tokens ( 3873.38 ms per token, 0.26 tokens per second) 47.23.872.005 I slot print_timing: id 3 | task 9367 | total time = 38781.48 ms / 1020 tokens 47.23.872.005 I slot print_timing: id 3 | task 9367 | graphs reused = 8265 47.23.872.005 I slot print_timing: id 3 | task 9367 | graph reallocs = 0 / 0 (same size) / (changed size) 47.23.872.980 I slot release: id 3 | task 9367 | stop processing: n_tokens = 1019, truncated = 0 47.23.873.007 I slot print_timing: id 0 | task 9372 | prompt processing, n_tokens = 380, progress = 0.42, t = 15.79 s / 24.07 tokens per second 47.23.880.879 I slot print_timing: id 1 | task 9373 | prompt processing, n_tokens = 493, progress = 0.49, t = 15.79 s / 31.23 tokens per second 47.30.470.057 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.786 47.30.470.122 I slot launch_slot_: id 3 | task 9378 | processing task, is_child = 0 47.30.470.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 47.31.962.321 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 97211105307 47.31.962.438 I slot launch_slot_: id 2 | task 9379 | processing task, is_child = 0 47.31.962.446 I slot print_timing: id 0 | task 9372 | prompt processing, n_tokens = 773, progress = 0.86, t = 22.39 s / 34.53 tokens per second 47.31.977.334 I slot print_timing: id 1 | task 9373 | prompt processing, n_tokens = 773, progress = 0.77, t = 22.39 s / 34.53 tokens per second 47.39.187.556 I slot print_timing: id 0 | task 9372 | prompt processing, n_tokens = 892, progress = 1.00, t = 31.10 s / 28.68 tokens per second 47.39.497.175 I slot print_timing: id 1 | task 9373 | prompt processing, n_tokens = 1005, progress = 1.00, t = 31.10 s / 32.31 tokens per second 47.39.503.513 I slot print_timing: id 2 | task 9379 | prompt processing, n_tokens = 115, progress = 0.12, t = 7.21 s / 15.96 tokens per second 47.39.507.938 I slot print_timing: id 3 | task 9378 | prompt processing, n_tokens = 125, progress = 1.00, t = 7.21 s / 17.35 tokens per second 47.42.090.412 I slot print_timing: id 2 | task 9379 | prompt processing, n_tokens = 293, progress = 0.30, t = 10.11 s / 28.99 tokens per second 47.44.595.293 I slot print_timing: id 0 | task 9372 | prompt eval time = 34004.90 ms / 896 tokens ( 37.95 ms per token, 26.35 tokens per second) 47.44.595.297 I slot print_timing: id 0 | task 9372 | eval time = 2505.53 ms / 2 tokens ( 2505.53 ms per token, 0.40 tokens per second) 47.44.595.297 I slot print_timing: id 0 | task 9372 | total time = 36510.44 ms / 898 tokens 47.44.595.298 I slot print_timing: id 0 | task 9372 | graphs reused = 8265 47.44.595.298 I slot print_timing: id 0 | task 9372 | graph reallocs = 0 / 0 (same size) / (changed size) 47.44.595.462 I slot release: id 0 | task 9372 | stop processing: n_tokens = 897, truncated = 0 47.44.595.693 I slot print_timing: id 1 | task 9373 | prompt eval time = 34005.09 ms / 1009 tokens ( 33.70 ms per token, 29.67 tokens per second) 47.44.595.696 I slot print_timing: id 1 | task 9373 | eval time = 2505.64 ms / 2 tokens ( 2505.64 ms per token, 0.40 tokens per second) 47.44.595.697 I slot print_timing: id 1 | task 9373 | total time = 36510.73 ms / 1011 tokens 47.44.595.697 I slot print_timing: id 1 | task 9373 | graphs reused = 8265 47.44.595.697 I slot print_timing: id 1 | task 9373 | graph reallocs = 0 / 0 (same size) / (changed size) 47.44.597.992 I slot release: id 1 | task 9373 | stop processing: n_tokens = 1010, truncated = 0 47.44.598.318 I slot print_timing: id 3 | task 9378 | prompt eval time = 10108.56 ms / 129 tokens ( 78.36 ms per token, 12.76 tokens per second) 47.44.598.321 I slot print_timing: id 3 | task 9378 | eval time = 2507.91 ms / 2 tokens ( 2507.91 ms per token, 0.40 tokens per second) 47.44.598.322 I slot print_timing: id 3 | task 9378 | total time = 12616.47 ms / 131 tokens 47.44.598.322 I slot print_timing: id 3 | task 9378 | graphs reused = 8265 47.44.598.322 I slot print_timing: id 3 | task 9378 | graph reallocs = 0 / 0 (same size) / (changed size) 47.44.598.365 I slot release: id 3 | task 9378 | stop processing: n_tokens = 903, truncated = 0 47.44.598.384 I slot print_timing: id 2 | task 9379 | prompt processing, n_tokens = 469, progress = 0.48, t = 12.61 s / 37.18 tokens per second 47.44.612.512 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 47.44.612.549 I slot launch_slot_: id 0 | task 9384 | processing task, is_child = 0 47.44.612.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.772 MiB) 47.48.266.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 47.48.412.825 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 97231831551 47.48.412.952 I slot launch_slot_: id 1 | task 9386 | processing task, is_child = 0 47.48.412.998 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 97231831922 47.48.413.068 I slot launch_slot_: id 3 | task 9385 | processing task, is_child = 0 47.48.422.859 I slot print_timing: id 2 | task 9379 | prompt processing, n_tokens = 773, progress = 0.78, t = 12.63 s / 61.20 tokens per second 47.53.991.327 I slot print_timing: id 0 | task 9384 | prompt processing, n_tokens = 104, progress = 1.00, t = 5.58 s / 18.64 tokens per second 47.55.161.155 I slot print_timing: id 1 | task 9386 | prompt processing, n_tokens = 116, progress = 0.13, t = 5.57 s / 20.83 tokens per second 47.55.165.590 I slot print_timing: id 2 | task 9379 | prompt processing, n_tokens = 981, progress = 1.00, t = 22.01 s / 44.57 tokens per second 47.55.170.768 I slot print_timing: id 3 | task 9385 | prompt processing, n_tokens = 116, progress = 0.12, t = 5.56 s / 20.85 tokens per second 47.58.512.133 I slot print_timing: id 1 | task 9386 | prompt processing, n_tokens = 232, progress = 0.26, t = 10.09 s / 23.00 tokens per second 47.58.512.144 I slot print_timing: id 3 | task 9385 | prompt processing, n_tokens = 232, progress = 0.24, t = 10.08 s / 23.01 tokens per second 48.03.296.651 I slot print_timing: id 0 | task 9384 | prompt eval time = 10098.81 ms / 108 tokens ( 93.51 ms per token, 10.69 tokens per second) 48.03.296.654 I slot print_timing: id 0 | task 9384 | eval time = 4784.76 ms / 2 tokens ( 4784.76 ms per token, 0.21 tokens per second) 48.03.296.654 I slot print_timing: id 0 | task 9384 | total time = 14883.57 ms / 110 tokens 48.03.296.655 I slot print_timing: id 0 | task 9384 | graphs reused = 8265 48.03.296.655 I slot print_timing: id 0 | task 9384 | graph reallocs = 0 / 0 (same size) / (changed size) 48.03.296.713 I slot release: id 0 | task 9384 | stop processing: n_tokens = 882, truncated = 0 48.03.296.938 I slot print_timing: id 2 | task 9379 | prompt eval time = 26530.35 ms / 985 tokens ( 26.93 ms per token, 37.13 tokens per second) 48.03.296.940 I slot print_timing: id 2 | task 9379 | eval time = 4784.82 ms / 2 tokens ( 4784.82 ms per token, 0.21 tokens per second) 48.03.296.941 I slot print_timing: id 2 | task 9379 | total time = 31315.16 ms / 987 tokens 48.03.296.941 I slot print_timing: id 2 | task 9379 | graphs reused = 8265 48.03.296.941 I slot print_timing: id 2 | task 9379 | graph reallocs = 0 / 0 (same size) / (changed size) 48.03.297.004 I slot release: id 2 | task 9379 | stop processing: n_tokens = 986, truncated = 0 48.03.297.012 I slot print_timing: id 1 | task 9386 | prompt processing, n_tokens = 390, progress = 0.43, t = 14.87 s / 26.22 tokens per second 48.03.305.059 I slot print_timing: id 3 | task 9385 | prompt processing, n_tokens = 436, progress = 0.46, t = 14.87 s / 29.32 tokens per second 48.07.639.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 97250530270 48.07.639.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 48.11.672.493 I slot launch_slot_: id 0 | task 9391 | processing task, is_child = 0 48.11.672.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 48.11.803.006 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 97250530562 48.11.803.134 I slot launch_slot_: id 2 | task 9392 | processing task, is_child = 0 48.11.803.225 I slot print_timing: id 1 | task 9386 | prompt processing, n_tokens = 774, progress = 0.85, t = 19.22 s / 40.28 tokens per second 48.11.807.765 I slot print_timing: id 3 | task 9385 | prompt processing, n_tokens = 774, progress = 0.81, t = 19.21 s / 40.29 tokens per second 48.19.292.979 I slot print_timing: id 0 | task 9391 | prompt processing, n_tokens = 116, progress = 0.12, t = 7.49 s / 15.49 tokens per second 48.19.459.005 I slot print_timing: id 1 | task 9386 | prompt processing, n_tokens = 902, progress = 1.00, t = 30.87 s / 29.22 tokens per second 48.19.463.515 I slot print_timing: id 2 | task 9392 | prompt processing, n_tokens = 176, progress = 0.13, t = 7.49 s / 23.51 tokens per second 48.19.468.063 I slot print_timing: id 3 | task 9385 | prompt processing, n_tokens = 948, progress = 1.00, t = 30.87 s / 30.71 tokens per second 48.24.241.108 I slot print_timing: id 0 | task 9391 | prompt processing, n_tokens = 232, progress = 0.25, t = 12.44 s / 18.65 tokens per second 48.24.241.121 I slot print_timing: id 2 | task 9392 | prompt processing, n_tokens = 431, progress = 0.32, t = 12.43 s / 34.67 tokens per second 48.31.459.708 I slot print_timing: id 1 | task 9386 | prompt eval time = 35818.08 ms / 906 tokens ( 39.53 ms per token, 25.29 tokens per second) 48.31.459.713 I slot print_timing: id 1 | task 9386 | eval time = 7218.83 ms / 2 tokens ( 7218.83 ms per token, 0.14 tokens per second) 48.31.459.713 I slot print_timing: id 1 | task 9386 | total time = 43036.91 ms / 908 tokens 48.31.459.714 I slot print_timing: id 1 | task 9386 | graphs reused = 8265 48.31.459.714 I slot print_timing: id 1 | task 9386 | graph reallocs = 0 / 0 (same size) / (changed size) 48.31.460.428 I slot release: id 1 | task 9386 | stop processing: n_tokens = 907, truncated = 0 48.31.460.858 I slot print_timing: id 3 | task 9385 | prompt eval time = 35813.80 ms / 952 tokens ( 37.62 ms per token, 26.58 tokens per second) 48.31.460.872 I slot print_timing: id 3 | task 9385 | eval time = 7219.76 ms / 2 tokens ( 7219.76 ms per token, 0.14 tokens per second) 48.31.460.874 I slot print_timing: id 3 | task 9385 | total time = 43033.56 ms / 954 tokens 48.31.460.875 I slot print_timing: id 3 | task 9385 | graphs reused = 8265 48.31.460.877 I slot print_timing: id 3 | task 9385 | graph reallocs = 0 / 0 (same size) / (changed size) 48.31.460.925 I slot release: id 3 | task 9385 | stop processing: n_tokens = 953, truncated = 0 48.31.460.945 I slot print_timing: id 0 | task 9391 | prompt processing, n_tokens = 424, progress = 0.45, t = 19.66 s / 21.57 tokens per second 48.31.468.112 I slot print_timing: id 2 | task 9392 | prompt processing, n_tokens = 840, progress = 0.62, t = 19.65 s / 42.74 tokens per second 48.35.515.971 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 97278693986 48.35.516.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.964 MiB) 48.39.192.669 I slot launch_slot_: id 1 | task 9397 | processing task, is_child = 0 48.39.192.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.842 MiB) 48.39.287.706 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 97278694482 48.39.287.820 I slot launch_slot_: id 3 | task 9398 | processing task, is_child = 0 48.39.287.828 I slot print_timing: id 0 | task 9391 | prompt processing, n_tokens = 774, progress = 0.82, t = 23.71 s / 32.64 tokens per second 48.39.315.107 I slot print_timing: id 2 | task 9392 | prompt processing, n_tokens = 1152, progress = 0.85, t = 23.71 s / 48.59 tokens per second 48.47.839.617 I slot print_timing: id 0 | task 9391 | prompt processing, n_tokens = 936, progress = 1.00, t = 36.04 s / 25.97 tokens per second 48.48.276.423 I slot print_timing: id 1 | task 9397 | prompt processing, n_tokens = 176, progress = 0.14, t = 8.52 s / 20.65 tokens per second 48.48.280.845 I slot print_timing: id 2 | task 9392 | prompt processing, n_tokens = 1352, progress = 1.00, t = 36.03 s / 37.52 tokens per second 48.48.285.417 I slot print_timing: id 3 | task 9398 | prompt processing, n_tokens = 176, progress = 0.13, t = 8.52 s / 20.66 tokens per second 48.54.501.115 I slot print_timing: id 1 | task 9397 | prompt processing, n_tokens = 431, progress = 0.34, t = 15.19 s / 28.38 tokens per second 48.54.501.131 I slot print_timing: id 3 | task 9398 | prompt processing, n_tokens = 431, progress = 0.32, t = 15.18 s / 28.39 tokens per second 49.03.241.570 I slot print_timing: id 0 | task 9391 | prompt eval time = 42697.75 ms / 940 tokens ( 45.42 ms per token, 22.02 tokens per second) 49.03.241.575 I slot print_timing: id 0 | task 9391 | eval time = 8740.68 ms / 2 tokens ( 8740.68 ms per token, 0.11 tokens per second) 49.03.241.575 I slot print_timing: id 0 | task 9391 | total time = 51438.43 ms / 942 tokens 49.03.241.575 I slot print_timing: id 0 | task 9391 | graphs reused = 8265 49.03.241.576 I slot print_timing: id 0 | task 9391 | graph reallocs = 0 / 0 (same size) / (changed size) 49.03.241.616 I slot release: id 0 | task 9391 | stop processing: n_tokens = 941, truncated = 0 49.03.241.855 I slot print_timing: id 2 | task 9392 | prompt eval time = 42693.41 ms / 1356 tokens ( 31.48 ms per token, 31.76 tokens per second) 49.03.241.858 I slot print_timing: id 2 | task 9392 | eval time = 8740.75 ms / 2 tokens ( 8740.75 ms per token, 0.11 tokens per second) 49.03.241.858 I slot print_timing: id 2 | task 9392 | total time = 51434.16 ms / 1358 tokens 49.03.241.858 I slot print_timing: id 2 | task 9392 | graphs reused = 8265 49.03.241.859 I slot print_timing: id 2 | task 9392 | graph reallocs = 0 / 0 (same size) / (changed size) 49.03.243.805 I slot release: id 2 | task 9392 | stop processing: n_tokens = 1357, truncated = 0 49.03.243.841 I slot print_timing: id 1 | task 9397 | prompt processing, n_tokens = 743, progress = 0.59, t = 23.93 s / 31.05 tokens per second 49.03.250.884 I slot print_timing: id 3 | task 9398 | prompt processing, n_tokens = 826, progress = 0.62, t = 23.92 s / 34.53 tokens per second 49.08.025.383 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 49.08.025.445 I slot launch_slot_: id 2 | task 9403 | processing task, is_child = 0 49.08.025.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.092 MiB) 49.12.061.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 97310475173 49.12.061.857 I slot launch_slot_: id 0 | task 9404 | processing task, is_child = 0 49.12.061.941 I slot print_timing: id 1 | task 9397 | prompt processing, n_tokens = 1152, progress = 0.92, t = 28.71 s / 40.12 tokens per second 49.12.074.413 I slot print_timing: id 3 | task 9398 | prompt processing, n_tokens = 1152, progress = 0.86, t = 28.71 s / 40.13 tokens per second 49.18.880.094 I slot print_timing: id 0 | task 9404 | prompt processing, n_tokens = 139, progress = 0.18, t = 6.82 s / 20.39 tokens per second 49.19.660.612 I slot print_timing: id 1 | task 9397 | prompt processing, n_tokens = 1255, progress = 1.00, t = 39.57 s / 31.72 tokens per second 49.19.665.186 I slot print_timing: id 2 | task 9403 | prompt processing, n_tokens = 144, progress = 1.00, t = 6.81 s / 21.14 tokens per second 49.19.669.752 I slot print_timing: id 3 | task 9398 | prompt processing, n_tokens = 1338, progress = 1.00, t = 39.56 s / 33.82 tokens per second 49.21.890.632 I slot print_timing: id 0 | task 9404 | prompt processing, n_tokens = 276, progress = 0.35, t = 9.83 s / 28.08 tokens per second 49.26.827.930 I slot print_timing: id 1 | task 9397 | prompt eval time = 42575.13 ms / 1259 tokens ( 33.82 ms per token, 29.57 tokens per second) 49.26.827.932 I slot print_timing: id 1 | task 9397 | eval time = 4937.75 ms / 2 tokens ( 4937.75 ms per token, 0.20 tokens per second) 49.26.827.933 I slot print_timing: id 1 | task 9397 | total time = 47512.88 ms / 1261 tokens 49.26.827.933 I slot print_timing: id 1 | task 9397 | graphs reused = 8265 49.26.827.934 I slot print_timing: id 1 | task 9397 | graph reallocs = 0 / 0 (same size) / (changed size) 49.26.827.989 I slot release: id 1 | task 9397 | stop processing: n_tokens = 1260, truncated = 0 49.26.828.221 I slot print_timing: id 2 | task 9403 | prompt eval time = 9823.58 ms / 148 tokens ( 66.38 ms per token, 15.07 tokens per second) 49.26.828.223 I slot print_timing: id 2 | task 9403 | eval time = 4937.82 ms / 2 tokens ( 4937.82 ms per token, 0.20 tokens per second) 49.26.828.224 I slot print_timing: id 2 | task 9403 | total time = 14761.40 ms / 150 tokens 49.26.828.224 I slot print_timing: id 2 | task 9403 | graphs reused = 8265 49.26.828.224 I slot print_timing: id 2 | task 9403 | graph reallocs = 0 / 0 (same size) / (changed size) 49.26.828.257 I slot release: id 2 | task 9403 | stop processing: n_tokens = 1301, truncated = 0 49.26.828.514 I slot print_timing: id 3 | task 9398 | prompt eval time = 42571.07 ms / 1342 tokens ( 31.72 ms per token, 31.52 tokens per second) 49.26.828.516 I slot print_timing: id 3 | task 9398 | eval time = 4937.90 ms / 2 tokens ( 4937.90 ms per token, 0.20 tokens per second) 49.26.828.517 I slot print_timing: id 3 | task 9398 | total time = 47508.96 ms / 1344 tokens 49.26.828.517 I slot print_timing: id 3 | task 9398 | graphs reused = 8265 49.26.828.517 I slot print_timing: id 3 | task 9398 | graph reallocs = 0 / 0 (same size) / (changed size) 49.26.828.563 I slot release: id 3 | task 9398 | stop processing: n_tokens = 1343, truncated = 0 49.26.828.572 I slot print_timing: id 0 | task 9404 | prompt processing, n_tokens = 681, progress = 0.86, t = 14.77 s / 46.12 tokens per second 49.26.857.214 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 97334061546 49.26.857.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.279 MiB) 49.28.344.799 I slot launch_slot_: id 1 | task 9409 | processing task, is_child = 0 49.28.344.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.654 MiB) 49.29.179.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.151 MiB) 49.29.708.745 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 97334061814 49.29.709.217 I slot launch_slot_: id 2 | task 9410 | processing task, is_child = 0 49.29.709.285 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 97334062120 49.29.709.433 I slot launch_slot_: id 3 | task 9411 | processing task, is_child = 0 49.29.709.447 I slot print_timing: id 0 | task 9404 | prompt processing, n_tokens = 788, progress = 0.99, t = 14.80 s / 53.26 tokens per second 49.35.479.331 I slot print_timing: id 1 | task 9409 | prompt processing, n_tokens = 139, progress = 0.17, t = 5.74 s / 24.21 tokens per second 49.35.509.977 I slot print_timing: id 2 | task 9410 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.74 s / 25.95 tokens per second 49.35.543.705 I slot print_timing: id 3 | task 9411 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.74 s / 25.95 tokens per second 49.40.869.762 I slot print_timing: id 0 | task 9404 | prompt eval time = 23417.44 ms / 792 tokens ( 29.57 ms per token, 33.82 tokens per second) 49.40.869.764 I slot print_timing: id 0 | task 9404 | eval time = 5390.45 ms / 2 tokens ( 5390.45 ms per token, 0.19 tokens per second) 49.40.869.765 I slot print_timing: id 0 | task 9404 | total time = 28807.89 ms / 794 tokens 49.40.869.765 I slot print_timing: id 0 | task 9404 | graphs reused = 8265 49.40.869.766 I slot print_timing: id 0 | task 9404 | graph reallocs = 0 / 0 (same size) / (changed size) 49.40.871.108 I slot release: id 0 | task 9404 | stop processing: n_tokens = 793, truncated = 0 49.40.871.164 I slot print_timing: id 1 | task 9409 | prompt processing, n_tokens = 287, progress = 0.36, t = 11.13 s / 25.78 tokens per second 49.40.871.183 I slot print_timing: id 2 | task 9410 | prompt processing, n_tokens = 285, progress = 0.32, t = 11.13 s / 25.60 tokens per second 49.40.871.191 I slot print_timing: id 3 | task 9411 | prompt processing, n_tokens = 285, progress = 0.33, t = 11.13 s / 25.60 tokens per second 49.42.714.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 97348104666 49.42.714.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.279 MiB) 49.43.149.550 I slot launch_slot_: id 0 | task 9415 | processing task, is_child = 0 49.43.149.656 I slot print_timing: id 1 | task 9409 | prompt processing, n_tokens = 292, progress = 0.36, t = 12.98 s / 22.50 tokens per second 49.43.154.127 I slot print_timing: id 2 | task 9410 | prompt processing, n_tokens = 375, progress = 0.42, t = 12.98 s / 28.90 tokens per second 49.43.191.264 I slot print_timing: id 3 | task 9411 | prompt processing, n_tokens = 343, progress = 0.40, t = 12.98 s / 26.43 tokens per second 49.58.773.596 I slot print_timing: id 0 | task 9415 | prompt processing, n_tokens = 163, progress = 0.21, t = 15.62 s / 10.43 tokens per second 49.59.209.318 I slot print_timing: id 1 | task 9409 | prompt processing, n_tokens = 681, progress = 0.84, t = 29.04 s / 23.45 tokens per second 49.59.217.559 I slot print_timing: id 2 | task 9410 | prompt processing, n_tokens = 741, progress = 0.83, t = 29.04 s / 25.52 tokens per second 49.59.231.906 I slot print_timing: id 3 | task 9411 | prompt processing, n_tokens = 741, progress = 0.86, t = 29.04 s / 25.52 tokens per second 50.05.199.235 I slot print_timing: id 0 | task 9415 | prompt processing, n_tokens = 274, progress = 0.35, t = 22.05 s / 12.43 tokens per second 50.05.635.929 I slot print_timing: id 1 | task 9409 | prompt processing, n_tokens = 804, progress = 1.00, t = 35.46 s / 22.67 tokens per second 50.05.656.166 I slot print_timing: id 2 | task 9410 | prompt processing, n_tokens = 887, progress = 1.00, t = 35.46 s / 25.01 tokens per second 50.05.749.483 I slot print_timing: id 3 | task 9411 | prompt processing, n_tokens = 855, progress = 1.00, t = 35.46 s / 24.11 tokens per second 50.10.530.426 I slot print_timing: id 0 | task 9415 | prompt processing, n_tokens = 655, progress = 0.83, t = 27.38 s / 23.92 tokens per second 50.12.683.702 I slot print_timing: id 1 | task 9409 | prompt eval time = 40793.04 ms / 808 tokens ( 50.49 ms per token, 19.81 tokens per second) 50.12.683.708 I slot print_timing: id 1 | task 9409 | eval time = 2154.16 ms / 2 tokens ( 2154.16 ms per token, 0.46 tokens per second) 50.12.683.708 I slot print_timing: id 1 | task 9409 | total time = 42947.21 ms / 810 tokens 50.12.683.709 I slot print_timing: id 1 | task 9409 | graphs reused = 8265 50.12.683.709 I slot print_timing: id 1 | task 9409 | graph reallocs = 0 / 0 (same size) / (changed size) 50.12.683.939 I slot release: id 1 | task 9409 | stop processing: n_tokens = 809, truncated = 0 50.12.684.405 I slot print_timing: id 2 | task 9410 | prompt eval time = 40793.29 ms / 891 tokens ( 45.78 ms per token, 21.84 tokens per second) 50.12.684.409 I slot print_timing: id 2 | task 9410 | eval time = 2154.43 ms / 2 tokens ( 2154.43 ms per token, 0.46 tokens per second) 50.12.684.409 I slot print_timing: id 2 | task 9410 | total time = 42947.72 ms / 893 tokens 50.12.684.409 I slot print_timing: id 2 | task 9410 | graphs reused = 8265 50.12.684.410 I slot print_timing: id 2 | task 9410 | graph reallocs = 0 / 0 (same size) / (changed size) 50.12.687.521 I slot release: id 2 | task 9410 | stop processing: n_tokens = 892, truncated = 0 50.12.688.365 I slot print_timing: id 3 | task 9411 | prompt eval time = 40793.61 ms / 859 tokens ( 47.49 ms per token, 21.06 tokens per second) 50.12.688.368 I slot print_timing: id 3 | task 9411 | eval time = 2157.96 ms / 2 tokens ( 2157.96 ms per token, 0.46 tokens per second) 50.12.688.369 I slot print_timing: id 3 | task 9411 | total time = 42951.57 ms / 861 tokens 50.12.688.369 I slot print_timing: id 3 | task 9411 | graphs reused = 8265 50.12.688.370 I slot print_timing: id 3 | task 9411 | graph reallocs = 0 / 0 (same size) / (changed size) 50.12.688.431 I slot release: id 3 | task 9411 | stop processing: n_tokens = 860, truncated = 0 50.12.688.448 I slot print_timing: id 0 | task 9415 | prompt processing, n_tokens = 786, progress = 0.99, t = 29.53 s / 26.61 tokens per second 50.12.899.294 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 97379917497 50.12.899.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 50.13.061.331 I slot launch_slot_: id 1 | task 9421 | processing task, is_child = 0 50.13.061.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.276 MiB) 50.13.245.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.779 MiB) 50.13.369.631 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 97379921080 50.13.369.758 I slot launch_slot_: id 2 | task 9422 | processing task, is_child = 0 50.13.369.809 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 97379921988 50.13.369.870 I slot launch_slot_: id 3 | task 9423 | processing task, is_child = 0 50.19.426.554 I slot print_timing: id 0 | task 9415 | prompt eval time = 29749.72 ms / 790 tokens ( 37.66 ms per token, 26.55 tokens per second) 50.19.426.557 I slot print_timing: id 0 | task 9415 | eval time = 6527.26 ms / 2 tokens ( 6527.26 ms per token, 0.15 tokens per second) 50.19.426.558 I slot print_timing: id 0 | task 9415 | total time = 36276.99 ms / 792 tokens 50.19.426.559 I slot print_timing: id 0 | task 9415 | graphs reused = 8265 50.19.426.559 I slot print_timing: id 0 | task 9415 | graph reallocs = 0 / 0 (same size) / (changed size) 50.19.426.699 I slot release: id 0 | task 9415 | stop processing: n_tokens = 791, truncated = 0 50.19.426.713 I slot print_timing: id 1 | task 9421 | prompt processing, n_tokens = 163, progress = 0.21, t = 6.06 s / 26.91 tokens per second 50.19.433.229 I slot print_timing: id 2 | task 9422 | prompt processing, n_tokens = 163, progress = 0.21, t = 6.06 s / 26.91 tokens per second 50.19.448.254 I slot print_timing: id 3 | task 9423 | prompt processing, n_tokens = 163, progress = 0.19, t = 6.06 s / 26.91 tokens per second 50.22.954.267 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 50.22.954.352 I slot launch_slot_: id 0 | task 9426 | processing task, is_child = 0 50.23.393.585 I slot print_timing: id 1 | task 9421 | prompt processing, n_tokens = 258, progress = 0.33, t = 9.58 s / 26.92 tokens per second 50.23.398.082 I slot print_timing: id 2 | task 9422 | prompt processing, n_tokens = 262, progress = 0.34, t = 9.58 s / 27.34 tokens per second 50.23.405.727 I slot print_timing: id 3 | task 9423 | prompt processing, n_tokens = 287, progress = 0.34, t = 9.58 s / 29.94 tokens per second 50.35.158.723 I slot print_timing: id 0 | task 9426 | prompt processing, n_tokens = 143, progress = 1.00, t = 12.20 s / 11.72 tokens per second 50.35.333.819 I slot print_timing: id 1 | task 9421 | prompt processing, n_tokens = 655, progress = 0.85, t = 21.79 s / 30.06 tokens per second 50.35.346.864 I slot print_timing: id 2 | task 9422 | prompt processing, n_tokens = 655, progress = 0.84, t = 21.79 s / 30.06 tokens per second 50.35.361.788 I slot print_timing: id 3 | task 9423 | prompt processing, n_tokens = 339, progress = 0.40, t = 21.79 s / 15.56 tokens per second 50.42.556.094 I slot print_timing: id 1 | task 9421 | prompt processing, n_tokens = 770, progress = 0.99, t = 29.19 s / 26.38 tokens per second 50.42.564.309 I slot print_timing: id 2 | task 9422 | prompt processing, n_tokens = 774, progress = 0.99, t = 29.19 s / 26.52 tokens per second 50.42.600.333 I slot print_timing: id 3 | task 9423 | prompt processing, n_tokens = 655, progress = 0.77, t = 29.19 s / 22.44 tokens per second 50.45.362.343 I slot print_timing: id 0 | task 9426 | prompt eval time = 19601.72 ms / 147 tokens ( 133.35 ms per token, 7.50 tokens per second) 50.45.362.346 I slot print_timing: id 0 | task 9426 | eval time = 2806.25 ms / 2 tokens ( 2806.25 ms per token, 0.36 tokens per second) 50.45.362.348 I slot print_timing: id 0 | task 9426 | total time = 22407.98 ms / 149 tokens 50.45.362.348 I slot print_timing: id 0 | task 9426 | graphs reused = 8265 50.45.362.349 I slot print_timing: id 0 | task 9426 | graph reallocs = 0 / 0 (same size) / (changed size) 50.45.364.057 I slot release: id 0 | task 9426 | stop processing: n_tokens = 803, truncated = 0 50.45.365.099 I slot print_timing: id 3 | task 9423 | prompt processing, n_tokens = 851, progress = 1.00, t = 31.99 s / 26.60 tokens per second 50.45.751.922 I slot print_timing: id 1 | task 9421 | prompt eval time = 31994.68 ms / 774 tokens ( 41.34 ms per token, 24.19 tokens per second) 50.45.751.924 I slot print_timing: id 1 | task 9421 | eval time = 387.35 ms / 2 tokens ( 387.35 ms per token, 2.58 tokens per second) 50.45.751.925 I slot print_timing: id 1 | task 9421 | total time = 32382.03 ms / 776 tokens 50.45.751.925 I slot print_timing: id 1 | task 9421 | graphs reused = 8265 50.45.751.926 I slot print_timing: id 1 | task 9421 | graph reallocs = 0 / 0 (same size) / (changed size) 50.45.751.980 I slot release: id 1 | task 9421 | stop processing: n_tokens = 775, truncated = 0 50.45.752.171 I slot print_timing: id 2 | task 9422 | prompt eval time = 31995.11 ms / 778 tokens ( 41.12 ms per token, 24.32 tokens per second) 50.45.752.173 I slot print_timing: id 2 | task 9422 | eval time = 387.11 ms / 2 tokens ( 387.11 ms per token, 2.58 tokens per second) 50.45.752.174 I slot print_timing: id 2 | task 9422 | total time = 32382.22 ms / 780 tokens 50.45.752.174 I slot print_timing: id 2 | task 9422 | graphs reused = 8265 50.45.752.174 I slot print_timing: id 2 | task 9422 | graph reallocs = 0 / 0 (same size) / (changed size) 50.45.752.215 I slot release: id 2 | task 9422 | stop processing: n_tokens = 779, truncated = 0 50.45.752.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 97412597615 50.45.752.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.839 MiB) 50.45.972.934 I slot launch_slot_: id 0 | task 9431 | processing task, is_child = 0 50.45.972.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 50.46.122.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.965 MiB) 50.46.289.620 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 97412985537 50.46.289.731 I slot launch_slot_: id 1 | task 9432 | processing task, is_child = 0 50.46.289.776 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 97412985772 50.46.289.841 I slot launch_slot_: id 2 | task 9433 | processing task, is_child = 0 50.53.050.614 I slot print_timing: id 3 | task 9423 | prompt eval time = 32382.40 ms / 855 tokens ( 37.87 ms per token, 26.40 tokens per second) 50.53.050.617 I slot print_timing: id 3 | task 9423 | eval time = 7298.21 ms / 2 tokens ( 7298.21 ms per token, 0.14 tokens per second) 50.53.050.617 I slot print_timing: id 3 | task 9423 | total time = 39680.60 ms / 857 tokens 50.53.050.618 I slot print_timing: id 3 | task 9423 | graphs reused = 8265 50.53.050.618 I slot print_timing: id 3 | task 9423 | graph reallocs = 0 / 0 (same size) / (changed size) 50.53.050.672 I slot release: id 3 | task 9423 | stop processing: n_tokens = 856, truncated = 0 50.53.050.684 I slot print_timing: id 0 | task 9431 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.76 s / 27.07 tokens per second 50.53.057.448 I slot print_timing: id 1 | task 9432 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.76 s / 27.07 tokens per second 50.53.064.405 I slot print_timing: id 2 | task 9433 | prompt processing, n_tokens = 183, progress = 0.19, t = 6.76 s / 27.07 tokens per second 50.53.076.892 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 97420284229 50.53.076.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 826.910 MiB) 50.58.523.778 I slot launch_slot_: id 3 | task 9436 | processing task, is_child = 0 50.58.523.797 I slot print_timing: id 0 | task 9431 | prompt processing, n_tokens = 333, progress = 0.34, t = 6.79 s / 49.06 tokens per second 50.58.523.808 I slot print_timing: id 1 | task 9432 | prompt processing, n_tokens = 333, progress = 0.35, t = 6.79 s / 49.06 tokens per second 50.58.523.815 I slot print_timing: id 2 | task 9433 | prompt processing, n_tokens = 333, progress = 0.35, t = 6.79 s / 49.07 tokens per second 51.03.843.525 I slot print_timing: id 0 | task 9431 | prompt processing, n_tokens = 455, progress = 0.47, t = 17.55 s / 25.92 tokens per second 51.04.999.916 I slot print_timing: id 1 | task 9432 | prompt processing, n_tokens = 448, progress = 0.46, t = 17.55 s / 25.52 tokens per second 51.05.004.359 I slot print_timing: id 2 | task 9433 | prompt processing, n_tokens = 428, progress = 0.45, t = 17.55 s / 24.38 tokens per second 51.05.008.777 I slot print_timing: id 3 | task 9436 | prompt processing, n_tokens = 183, progress = 0.19, t = 5.32 s / 34.40 tokens per second 51.20.452.299 I slot print_timing: id 0 | task 9431 | prompt processing, n_tokens = 836, progress = 0.86, t = 34.16 s / 24.47 tokens per second 51.20.884.795 I slot print_timing: id 1 | task 9432 | prompt processing, n_tokens = 836, progress = 0.87, t = 34.16 s / 24.47 tokens per second 51.20.889.635 I slot print_timing: id 2 | task 9433 | prompt processing, n_tokens = 836, progress = 0.89, t = 34.16 s / 24.47 tokens per second 51.20.894.108 I slot print_timing: id 3 | task 9436 | prompt processing, n_tokens = 333, progress = 0.35, t = 21.93 s / 15.19 tokens per second 51.26.940.972 I slot print_timing: id 0 | task 9431 | prompt processing, n_tokens = 967, progress = 1.00, t = 40.65 s / 23.79 tokens per second 51.27.116.852 I slot print_timing: id 1 | task 9432 | prompt processing, n_tokens = 960, progress = 1.00, t = 40.65 s / 23.62 tokens per second 51.27.128.620 I slot print_timing: id 2 | task 9433 | prompt processing, n_tokens = 940, progress = 1.00, t = 40.65 s / 23.12 tokens per second 51.27.133.262 I slot print_timing: id 3 | task 9436 | prompt processing, n_tokens = 431, progress = 0.46, t = 28.42 s / 15.17 tokens per second 51.32.255.485 I slot print_timing: id 3 | task 9436 | prompt processing, n_tokens = 836, progress = 0.88, t = 33.73 s / 24.78 tokens per second 51.33.961.857 I slot print_timing: id 0 | task 9431 | prompt eval time = 45965.19 ms / 971 tokens ( 47.34 ms per token, 21.12 tokens per second) 51.33.961.860 I slot print_timing: id 0 | task 9431 | eval time = 1706.82 ms / 2 tokens ( 1706.82 ms per token, 0.59 tokens per second) 51.33.961.873 I slot print_timing: id 0 | task 9431 | total time = 47672.00 ms / 973 tokens 51.33.961.876 I slot print_timing: id 0 | task 9431 | graphs reused = 8265 51.33.961.876 I slot print_timing: id 0 | task 9431 | graph reallocs = 0 / 0 (same size) / (changed size) 51.33.961.957 I slot release: id 0 | task 9431 | stop processing: n_tokens = 972, truncated = 0 51.33.962.171 I slot print_timing: id 1 | task 9432 | prompt eval time = 45965.30 ms / 964 tokens ( 47.68 ms per token, 20.97 tokens per second) 51.33.962.177 I slot print_timing: id 1 | task 9432 | eval time = 1706.92 ms / 2 tokens ( 1706.92 ms per token, 0.59 tokens per second) 51.33.962.177 I slot print_timing: id 1 | task 9432 | total time = 47672.22 ms / 966 tokens 51.33.962.177 I slot print_timing: id 1 | task 9432 | graphs reused = 8265 51.33.962.178 I slot print_timing: id 1 | task 9432 | graph reallocs = 0 / 0 (same size) / (changed size) 51.33.962.205 I slot release: id 1 | task 9432 | stop processing: n_tokens = 965, truncated = 0 51.33.962.444 I slot print_timing: id 2 | task 9433 | prompt eval time = 45965.45 ms / 944 tokens ( 48.69 ms per token, 20.54 tokens per second) 51.33.962.446 I slot print_timing: id 2 | task 9433 | eval time = 1706.97 ms / 2 tokens ( 1706.97 ms per token, 0.59 tokens per second) 51.33.962.447 I slot print_timing: id 2 | task 9433 | total time = 47672.42 ms / 946 tokens 51.33.962.447 I slot print_timing: id 2 | task 9433 | graphs reused = 8265 51.33.962.447 I slot print_timing: id 2 | task 9433 | graph reallocs = 0 / 0 (same size) / (changed size) 51.33.962.471 I slot release: id 2 | task 9433 | stop processing: n_tokens = 945, truncated = 0 51.33.962.479 I slot print_timing: id 3 | task 9436 | prompt processing, n_tokens = 943, progress = 1.00, t = 35.44 s / 26.61 tokens per second 51.34.148.045 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 972, t_last = 97461195514 51.34.148.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 829.473 MiB) 51.34.289.488 I slot launch_slot_: id 0 | task 9443 | processing task, is_child = 0 51.34.289.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 832.099 MiB) 51.34.382.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 797.712 MiB) 51.34.498.943 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 97461195762 51.34.499.053 I slot launch_slot_: id 1 | task 9444 | processing task, is_child = 0 51.34.499.107 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.914 51.34.499.127 I slot launch_slot_: id 2 | task 9445 | processing task, is_child = 0 51.40.546.808 I slot print_timing: id 3 | task 9436 | prompt eval time = 35624.22 ms / 947 tokens ( 37.62 ms per token, 26.58 tokens per second) 51.40.546.811 I slot print_timing: id 3 | task 9436 | eval time = 6398.76 ms / 2 tokens ( 6398.76 ms per token, 0.16 tokens per second) 51.40.546.812 I slot print_timing: id 3 | task 9436 | total time = 42022.98 ms / 949 tokens 51.40.546.812 I slot print_timing: id 3 | task 9436 | graphs reused = 8265 51.40.546.813 I slot print_timing: id 3 | task 9436 | graph reallocs = 0 / 0 (same size) / (changed size) 51.40.546.850 I slot release: id 3 | task 9436 | stop processing: n_tokens = 948, truncated = 0 51.40.546.862 I slot print_timing: id 0 | task 9443 | prompt processing, n_tokens = 162, progress = 0.20, t = 6.05 s / 26.79 tokens per second 51.40.552.300 I slot print_timing: id 1 | task 9444 | prompt processing, n_tokens = 162, progress = 0.20, t = 6.05 s / 26.79 tokens per second 51.40.556.737 I slot print_timing: id 2 | task 9445 | prompt processing, n_tokens = 129, progress = 1.00, t = 6.05 s / 21.33 tokens per second 51.43.909.796 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 97467780407 51.43.909.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.712 MiB) 51.44.021.378 I slot launch_slot_: id 3 | task 9448 | processing task, is_child = 0 51.44.021.395 I slot print_timing: id 0 | task 9443 | prompt processing, n_tokens = 282, progress = 0.35, t = 9.41 s / 29.97 tokens per second 51.44.025.845 I slot print_timing: id 1 | task 9444 | prompt processing, n_tokens = 283, progress = 0.35, t = 9.41 s / 30.07 tokens per second 51.55.255.971 I slot print_timing: id 2 | task 9445 | prompt eval time = 9410.51 ms / 133 tokens ( 70.76 ms per token, 14.13 tokens per second) 51.55.255.974 I slot print_timing: id 2 | task 9445 | eval time = 11346.18 ms / 2 tokens (11346.18 ms per token, 0.09 tokens per second) 51.55.255.974 I slot print_timing: id 2 | task 9445 | total time = 20756.69 ms / 135 tokens 51.55.255.975 I slot print_timing: id 2 | task 9445 | graphs reused = 8265 51.55.255.975 I slot print_timing: id 2 | task 9445 | graph reallocs = 0 / 0 (same size) / (changed size) 51.55.256.026 I slot release: id 2 | task 9445 | stop processing: n_tokens = 970, truncated = 0 51.55.256.047 I slot print_timing: id 0 | task 9443 | prompt processing, n_tokens = 679, progress = 0.85, t = 20.76 s / 32.71 tokens per second 51.55.261.526 I slot print_timing: id 1 | task 9444 | prompt processing, n_tokens = 679, progress = 0.85, t = 20.76 s / 32.71 tokens per second 51.55.266.756 I slot print_timing: id 3 | task 9448 | prompt processing, n_tokens = 137, progress = 0.14, t = 11.23 s / 12.20 tokens per second 51.58.317.795 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 97482489583 51.58.317.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.901 MiB) 52.00.892.768 I slot launch_slot_: id 2 | task 9451 | processing task, is_child = 0 52.00.892.780 I slot print_timing: id 0 | task 9443 | prompt processing, n_tokens = 794, progress = 0.99, t = 23.82 s / 33.34 tokens per second 52.00.925.388 I slot print_timing: id 1 | task 9444 | prompt processing, n_tokens = 795, progress = 0.99, t = 23.82 s / 33.38 tokens per second 52.00.930.012 I slot print_timing: id 3 | task 9448 | prompt processing, n_tokens = 335, progress = 0.34, t = 14.29 s / 23.45 tokens per second 52.04.525.228 I slot print_timing: id 2 | task 9451 | prompt processing, n_tokens = 137, progress = 0.14, t = 3.59 s / 38.11 tokens per second 52.04.533.652 I slot print_timing: id 3 | task 9448 | prompt processing, n_tokens = 459, progress = 0.47, t = 20.49 s / 22.40 tokens per second 52.11.704.411 I slot print_timing: id 0 | task 9443 | prompt eval time = 30025.85 ms / 798 tokens ( 37.63 ms per token, 26.58 tokens per second) 52.11.704.417 I slot print_timing: id 0 | task 9443 | eval time = 7179.42 ms / 2 tokens ( 7179.42 ms per token, 0.14 tokens per second) 52.11.704.421 I slot print_timing: id 0 | task 9443 | total time = 37205.27 ms / 800 tokens 52.11.704.422 I slot print_timing: id 0 | task 9443 | graphs reused = 8265 52.11.704.422 I slot print_timing: id 0 | task 9443 | graph reallocs = 0 / 0 (same size) / (changed size) 52.11.706.383 I slot release: id 0 | task 9443 | stop processing: n_tokens = 799, truncated = 0 52.11.706.848 I slot print_timing: id 1 | task 9444 | prompt eval time = 30026.01 ms / 799 tokens ( 37.58 ms per token, 26.61 tokens per second) 52.11.706.864 I slot print_timing: id 1 | task 9444 | eval time = 7181.62 ms / 2 tokens ( 7181.62 ms per token, 0.14 tokens per second) 52.11.706.867 I slot print_timing: id 1 | task 9444 | total time = 37207.63 ms / 801 tokens 52.11.706.867 I slot print_timing: id 1 | task 9444 | graphs reused = 8265 52.11.706.868 I slot print_timing: id 1 | task 9444 | graph reallocs = 0 / 0 (same size) / (changed size) 52.11.706.920 I slot release: id 1 | task 9444 | stop processing: n_tokens = 800, truncated = 0 52.11.706.942 I slot print_timing: id 2 | task 9451 | prompt processing, n_tokens = 335, progress = 0.35, t = 10.77 s / 31.09 tokens per second 52.11.706.958 I slot print_timing: id 3 | task 9448 | prompt processing, n_tokens = 826, progress = 0.85, t = 27.67 s / 29.85 tokens per second 52.14.323.264 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 97498939941 52.14.323.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.901 MiB) 52.15.102.185 I slot launch_slot_: id 0 | task 9455 | processing task, is_child = 0 52.15.102.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.337 MiB) 52.15.150.642 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 97498940477 52.15.150.751 I slot launch_slot_: id 1 | task 9456 | processing task, is_child = 0 52.15.150.880 I slot print_timing: id 2 | task 9451 | prompt processing, n_tokens = 437, progress = 0.46, t = 13.39 s / 32.63 tokens per second 52.15.155.374 I slot print_timing: id 3 | task 9448 | prompt processing, n_tokens = 971, progress = 1.00, t = 30.29 s / 32.05 tokens per second 52.23.416.344 I slot print_timing: id 0 | task 9455 | prompt processing, n_tokens = 137, progress = 0.14, t = 8.27 s / 16.58 tokens per second 52.23.422.089 I slot print_timing: id 1 | task 9456 | prompt processing, n_tokens = 139, progress = 0.15, t = 8.27 s / 16.82 tokens per second 52.23.426.523 I slot print_timing: id 2 | task 9451 | prompt processing, n_tokens = 826, progress = 0.87, t = 22.49 s / 36.73 tokens per second 52.29.832.531 I slot print_timing: id 3 | task 9448 | prompt eval time = 39386.03 ms / 975 tokens ( 40.40 ms per token, 24.75 tokens per second) 52.29.832.534 I slot print_timing: id 3 | task 9448 | eval time = 6416.20 ms / 2 tokens ( 6416.20 ms per token, 0.16 tokens per second) 52.29.832.534 I slot print_timing: id 3 | task 9448 | total time = 45802.23 ms / 977 tokens 52.29.832.535 I slot print_timing: id 3 | task 9448 | graphs reused = 8265 52.29.832.535 I slot print_timing: id 3 | task 9448 | graph reallocs = 0 / 0 (same size) / (changed size) 52.29.832.640 I slot release: id 3 | task 9448 | stop processing: n_tokens = 976, truncated = 0 52.29.832.653 I slot print_timing: id 0 | task 9455 | prompt processing, n_tokens = 335, progress = 0.35, t = 14.68 s / 22.82 tokens per second 52.29.832.664 I slot print_timing: id 1 | task 9456 | prompt processing, n_tokens = 304, progress = 0.33, t = 14.68 s / 20.71 tokens per second 52.29.832.671 I slot print_timing: id 2 | task 9451 | prompt processing, n_tokens = 949, progress = 1.00, t = 28.90 s / 32.83 tokens per second 52.32.789.283 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 97517066198 52.32.789.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.586 MiB) 52.32.830.852 I slot launch_slot_: id 3 | task 9460 | processing task, is_child = 0 52.32.830.868 I slot print_timing: id 0 | task 9455 | prompt processing, n_tokens = 445, progress = 0.46, t = 17.64 s / 25.23 tokens per second 52.32.837.166 I slot print_timing: id 1 | task 9456 | prompt processing, n_tokens = 414, progress = 0.45, t = 17.64 s / 23.47 tokens per second 52.43.592.109 I slot print_timing: id 2 | task 9451 | prompt eval time = 31859.34 ms / 953 tokens ( 33.43 ms per token, 29.91 tokens per second) 52.43.592.111 I slot print_timing: id 2 | task 9451 | eval time = 10802.83 ms / 2 tokens (10802.83 ms per token, 0.09 tokens per second) 52.43.592.112 I slot print_timing: id 2 | task 9451 | total time = 42662.17 ms / 955 tokens 52.43.592.112 I slot print_timing: id 2 | task 9451 | graphs reused = 8265 52.43.592.113 I slot print_timing: id 2 | task 9451 | graph reallocs = 0 / 0 (same size) / (changed size) 52.43.592.163 I slot release: id 2 | task 9451 | stop processing: n_tokens = 954, truncated = 0 52.43.592.176 I slot print_timing: id 0 | task 9455 | prompt processing, n_tokens = 826, progress = 0.86, t = 28.44 s / 29.04 tokens per second 52.43.597.416 I slot print_timing: id 1 | task 9456 | prompt processing, n_tokens = 779, progress = 0.84, t = 28.44 s / 27.39 tokens per second 52.43.602.489 I slot print_timing: id 3 | task 9460 | prompt processing, n_tokens = 139, progress = 0.15, t = 10.73 s / 12.96 tokens per second 52.47.260.929 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 97530825720 52.47.260.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.836 MiB) 52.49.457.772 I slot launch_slot_: id 2 | task 9463 | processing task, is_child = 0 52.49.457.784 I slot print_timing: id 0 | task 9455 | prompt processing, n_tokens = 957, progress = 1.00, t = 32.11 s / 29.80 tokens per second 52.49.485.912 I slot print_timing: id 1 | task 9456 | prompt processing, n_tokens = 926, progress = 1.00, t = 32.11 s / 28.84 tokens per second 52.49.490.531 I slot print_timing: id 3 | task 9460 | prompt processing, n_tokens = 304, progress = 0.34, t = 14.40 s / 21.12 tokens per second 52.52.524.610 I slot print_timing: id 2 | task 9463 | prompt processing, n_tokens = 139, progress = 0.15, t = 3.03 s / 45.82 tokens per second 52.52.532.274 I slot print_timing: id 3 | task 9460 | prompt processing, n_tokens = 382, progress = 0.43, t = 19.66 s / 19.43 tokens per second 52.59.686.024 I slot print_timing: id 0 | task 9455 | prompt eval time = 37373.60 ms / 961 tokens ( 38.89 ms per token, 25.71 tokens per second) 52.59.686.027 I slot print_timing: id 0 | task 9455 | eval time = 7161.66 ms / 2 tokens ( 7161.66 ms per token, 0.14 tokens per second) 52.59.686.028 I slot print_timing: id 0 | task 9455 | total time = 44535.26 ms / 963 tokens 52.59.686.028 I slot print_timing: id 0 | task 9455 | graphs reused = 8265 52.59.686.029 I slot print_timing: id 0 | task 9455 | graph reallocs = 0 / 0 (same size) / (changed size) 52.59.686.087 I slot release: id 0 | task 9455 | stop processing: n_tokens = 962, truncated = 0 52.59.686.330 I slot print_timing: id 1 | task 9456 | prompt eval time = 37373.78 ms / 930 tokens ( 40.19 ms per token, 24.88 tokens per second) 52.59.686.332 I slot print_timing: id 1 | task 9456 | eval time = 7161.73 ms / 2 tokens ( 7161.73 ms per token, 0.14 tokens per second) 52.59.686.333 I slot print_timing: id 1 | task 9456 | total time = 44535.51 ms / 932 tokens 52.59.686.333 I slot print_timing: id 1 | task 9456 | graphs reused = 8265 52.59.686.333 I slot print_timing: id 1 | task 9456 | graph reallocs = 0 / 0 (same size) / (changed size) 52.59.688.430 I slot release: id 1 | task 9456 | stop processing: n_tokens = 931, truncated = 0 52.59.688.459 I slot print_timing: id 2 | task 9463 | prompt processing, n_tokens = 304, progress = 0.34, t = 10.20 s / 29.82 tokens per second 52.59.688.477 I slot print_timing: id 3 | task 9460 | prompt processing, n_tokens = 779, progress = 0.87, t = 26.82 s / 29.04 tokens per second 53.01.901.923 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.867 53.01.901.993 I slot launch_slot_: id 1 | task 9467 | processing task, is_child = 0 53.01.902.052 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 53.02.669.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 97546919644 53.02.669.771 I slot launch_slot_: id 0 | task 9468 | processing task, is_child = 0 53.02.677.491 I slot print_timing: id 2 | task 9463 | prompt processing, n_tokens = 386, progress = 0.43, t = 12.41 s / 31.10 tokens per second 53.02.682.048 I slot print_timing: id 3 | task 9460 | prompt processing, n_tokens = 894, progress = 1.00, t = 29.04 s / 30.79 tokens per second 53.10.506.056 I slot print_timing: id 0 | task 9468 | prompt processing, n_tokens = 139, progress = 0.15, t = 7.84 s / 17.74 tokens per second 53.10.512.921 I slot print_timing: id 1 | task 9467 | prompt processing, n_tokens = 107, progress = 1.00, t = 7.84 s / 13.66 tokens per second 53.10.517.503 I slot print_timing: id 2 | task 9463 | prompt processing, n_tokens = 779, progress = 0.86, t = 21.02 s / 37.07 tokens per second 53.14.657.387 I slot print_timing: id 3 | task 9460 | prompt eval time = 37640.92 ms / 898 tokens ( 41.92 ms per token, 23.86 tokens per second) 53.14.657.391 I slot print_timing: id 3 | task 9460 | eval time = 4151.34 ms / 2 tokens ( 4151.34 ms per token, 0.24 tokens per second) 53.14.657.391 I slot print_timing: id 3 | task 9460 | total time = 41792.26 ms / 900 tokens 53.14.657.392 I slot print_timing: id 3 | task 9460 | graphs reused = 8265 53.14.657.392 I slot print_timing: id 3 | task 9460 | graph reallocs = 0 / 0 (same size) / (changed size) 53.14.657.505 I slot release: id 3 | task 9460 | stop processing: n_tokens = 899, truncated = 0 53.14.657.520 I slot print_timing: id 0 | task 9468 | prompt processing, n_tokens = 304, progress = 0.34, t = 11.99 s / 25.36 tokens per second 53.14.657.530 I slot print_timing: id 2 | task 9463 | prompt processing, n_tokens = 898, progress = 1.00, t = 25.17 s / 35.68 tokens per second 53.16.164.036 I slot print_timing: id 1 | task 9467 | prompt eval time = 11987.29 ms / 111 tokens ( 107.99 ms per token, 9.26 tokens per second) 53.16.164.038 I slot print_timing: id 1 | task 9467 | eval time = 1506.87 ms / 2 tokens ( 1506.87 ms per token, 0.66 tokens per second) 53.16.164.039 I slot print_timing: id 1 | task 9467 | total time = 13494.16 ms / 113 tokens 53.16.164.040 I slot print_timing: id 1 | task 9467 | graphs reused = 8265 53.16.164.040 I slot print_timing: id 1 | task 9467 | graph reallocs = 0 / 0 (same size) / (changed size) 53.16.164.081 I slot release: id 1 | task 9467 | stop processing: n_tokens = 891, truncated = 0 53.16.164.263 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 97561891063 53.16.164.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.903 MiB) 53.16.194.632 I slot launch_slot_: id 3 | task 9472 | processing task, is_child = 0 53.16.194.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.466 MiB) 53.16.234.288 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 97563397638 53.16.234.389 I slot launch_slot_: id 1 | task 9473 | processing task, is_child = 0 53.16.234.396 I slot print_timing: id 0 | task 9468 | prompt processing, n_tokens = 383, progress = 0.43, t = 13.49 s / 28.38 tokens per second 53.25.623.983 I slot print_timing: id 2 | task 9463 | prompt eval time = 26673.80 ms / 902 tokens ( 29.57 ms per token, 33.82 tokens per second) 53.25.623.986 I slot print_timing: id 2 | task 9463 | eval time = 9459.67 ms / 2 tokens ( 9459.67 ms per token, 0.11 tokens per second) 53.25.623.987 I slot print_timing: id 2 | task 9463 | total time = 36133.47 ms / 904 tokens 53.25.623.988 I slot print_timing: id 2 | task 9463 | graphs reused = 8265 53.25.623.988 I slot print_timing: id 2 | task 9463 | graph reallocs = 0 / 0 (same size) / (changed size) 53.25.624.492 I slot release: id 2 | task 9463 | stop processing: n_tokens = 903, truncated = 0 53.25.624.539 I slot print_timing: id 0 | task 9468 | prompt processing, n_tokens = 779, progress = 0.87, t = 22.95 s / 33.94 tokens per second 53.25.641.943 I slot print_timing: id 1 | task 9473 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.38 s / 20.14 tokens per second 53.25.652.989 I slot print_timing: id 3 | task 9472 | prompt processing, n_tokens = 189, progress = 0.15, t = 9.38 s / 20.14 tokens per second 53.30.061.120 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 97572858050 53.30.061.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.215 MiB) 53.32.646.928 I slot launch_slot_: id 2 | task 9476 | processing task, is_child = 0 53.32.646.940 I slot print_timing: id 0 | task 9468 | prompt processing, n_tokens = 895, progress = 1.00, t = 27.39 s / 32.67 tokens per second 53.32.671.034 I slot print_timing: id 1 | task 9473 | prompt processing, n_tokens = 402, progress = 0.33, t = 13.82 s / 29.08 tokens per second 53.32.671.148 I slot print_timing: id 3 | task 9472 | prompt processing, n_tokens = 402, progress = 0.33, t = 13.82 s / 29.08 tokens per second 53.43.078.514 I slot print_timing: id 1 | task 9473 | prompt processing, n_tokens = 720, progress = 0.58, t = 26.82 s / 26.85 tokens per second 53.43.088.549 I slot print_timing: id 2 | task 9476 | prompt processing, n_tokens = 189, progress = 0.15, t = 10.38 s / 18.20 tokens per second 53.43.102.318 I slot print_timing: id 3 | task 9472 | prompt processing, n_tokens = 709, progress = 0.58, t = 26.82 s / 26.44 tokens per second 53.54.131.202 I slot print_timing: id 0 | task 9468 | prompt eval time = 40408.71 ms / 899 tokens ( 44.95 ms per token, 22.25 tokens per second) 53.54.131.204 I slot print_timing: id 0 | task 9468 | eval time = 11052.71 ms / 2 tokens (11052.71 ms per token, 0.09 tokens per second) 53.54.131.204 I slot print_timing: id 0 | task 9468 | total time = 51461.42 ms / 901 tokens 53.54.131.205 I slot print_timing: id 0 | task 9468 | graphs reused = 8265 53.54.131.206 I slot print_timing: id 0 | task 9468 | graph reallocs = 0 / 0 (same size) / (changed size) 53.54.131.296 I slot release: id 0 | task 9468 | stop processing: n_tokens = 900, truncated = 0 53.54.131.317 I slot print_timing: id 1 | task 9473 | prompt processing, n_tokens = 1061, progress = 0.86, t = 37.89 s / 28.00 tokens per second 53.54.149.284 I slot print_timing: id 2 | task 9476 | prompt processing, n_tokens = 402, progress = 0.31, t = 21.46 s / 18.73 tokens per second 53.54.149.302 I slot print_timing: id 3 | task 9472 | prompt processing, n_tokens = 1061, progress = 0.87, t = 37.89 s / 28.00 tokens per second 54.00.065.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 97601364854 54.00.065.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.403 MiB) 54.02.651.011 I slot launch_slot_: id 0 | task 9480 | processing task, is_child = 0 54.02.651.113 I slot print_timing: id 1 | task 9473 | prompt processing, n_tokens = 1232, progress = 1.00, t = 43.83 s / 28.11 tokens per second 54.02.655.672 I slot print_timing: id 2 | task 9476 | prompt processing, n_tokens = 774, progress = 0.60, t = 27.39 s / 28.25 tokens per second 54.02.660.141 I slot print_timing: id 3 | task 9472 | prompt processing, n_tokens = 1221, progress = 1.00, t = 43.83 s / 27.86 tokens per second 54.11.077.749 I slot print_timing: id 0 | task 9480 | prompt processing, n_tokens = 402, progress = 0.16, t = 8.43 s / 47.71 tokens per second 54.11.085.814 I slot print_timing: id 2 | task 9476 | prompt processing, n_tokens = 1061, progress = 0.82, t = 38.41 s / 27.63 tokens per second 54.20.518.061 I slot print_timing: id 1 | task 9473 | prompt eval time = 54838.51 ms / 1236 tokens ( 44.37 ms per token, 22.54 tokens per second) 54.20.518.064 I slot print_timing: id 1 | task 9473 | eval time = 9440.69 ms / 2 tokens ( 9440.69 ms per token, 0.11 tokens per second) 54.20.518.065 I slot print_timing: id 1 | task 9473 | total time = 64279.20 ms / 1238 tokens 54.20.518.065 I slot print_timing: id 1 | task 9473 | graphs reused = 8265 54.20.518.066 I slot print_timing: id 1 | task 9473 | graph reallocs = 0 / 0 (same size) / (changed size) 54.20.518.183 I slot release: id 1 | task 9473 | stop processing: n_tokens = 1237, truncated = 0 54.20.518.418 I slot print_timing: id 3 | task 9472 | prompt eval time = 54838.80 ms / 1225 tokens ( 44.77 ms per token, 22.34 tokens per second) 54.20.518.422 I slot print_timing: id 3 | task 9472 | eval time = 9440.68 ms / 2 tokens ( 9440.68 ms per token, 0.11 tokens per second) 54.20.518.423 I slot print_timing: id 3 | task 9472 | total time = 64279.49 ms / 1227 tokens 54.20.518.423 I slot print_timing: id 3 | task 9472 | graphs reused = 8265 54.20.518.423 I slot print_timing: id 3 | task 9472 | graph reallocs = 0 / 0 (same size) / (changed size) 54.20.518.473 I slot release: id 3 | task 9472 | stop processing: n_tokens = 1226, truncated = 0 54.20.518.483 I slot print_timing: id 0 | task 9480 | prompt processing, n_tokens = 961, progress = 0.37, t = 17.87 s / 53.79 tokens per second 54.20.518.509 I slot print_timing: id 2 | task 9476 | prompt processing, n_tokens = 1286, progress = 1.00, t = 47.85 s / 26.88 tokens per second 54.33.550.491 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 97627751741 54.33.550.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.778 MiB) 54.33.728.722 I slot launch_slot_: id 1 | task 9484 | processing task, is_child = 0 54.33.728.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 54.33.846.716 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 97627752030 54.33.846.843 I slot launch_slot_: id 3 | task 9485 | processing task, is_child = 0 54.33.846.854 I slot print_timing: id 0 | task 9480 | prompt processing, n_tokens = 2071, progress = 0.80, t = 30.90 s / 67.03 tokens per second 54.46.170.107 I slot print_timing: id 2 | task 9476 | prompt eval time = 60879.43 ms / 1290 tokens ( 47.19 ms per token, 21.19 tokens per second) 54.46.170.112 I slot print_timing: id 2 | task 9476 | eval time = 12619.62 ms / 2 tokens (12619.62 ms per token, 0.08 tokens per second) 54.46.170.113 I slot print_timing: id 2 | task 9476 | total time = 73499.05 ms / 1292 tokens 54.46.170.113 I slot print_timing: id 2 | task 9476 | graphs reused = 8265 54.46.170.114 I slot print_timing: id 2 | task 9476 | graph reallocs = 0 / 0 (same size) / (changed size) 54.46.170.191 I slot release: id 2 | task 9476 | stop processing: n_tokens = 1291, truncated = 0 54.46.170.206 I slot print_timing: id 0 | task 9480 | prompt processing, n_tokens = 2288, progress = 0.88, t = 43.52 s / 52.57 tokens per second 54.46.175.824 I slot print_timing: id 1 | task 9484 | prompt processing, n_tokens = 402, progress = 0.16, t = 12.30 s / 32.67 tokens per second 54.46.180.941 I slot print_timing: id 3 | task 9485 | prompt processing, n_tokens = 402, progress = 0.15, t = 12.30 s / 32.67 tokens per second 55.02.290.134 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 97653403749 55.02.290.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 55.03.081.223 I slot launch_slot_: id 2 | task 9488 | processing task, is_child = 0 55.03.081.238 I slot print_timing: id 0 | task 9480 | prompt processing, n_tokens = 2583, progress = 1.00, t = 59.64 s / 43.31 tokens per second 55.03.085.949 I slot print_timing: id 1 | task 9484 | prompt processing, n_tokens = 961, progress = 0.38, t = 28.42 s / 33.81 tokens per second 55.03.086.079 I slot print_timing: id 3 | task 9485 | prompt processing, n_tokens = 961, progress = 0.35, t = 28.42 s / 33.81 tokens per second 55.27.491.517 I slot print_timing: id 1 | task 9484 | prompt processing, n_tokens = 1984, progress = 0.79, t = 53.62 s / 37.00 tokens per second 55.27.497.244 I slot print_timing: id 2 | task 9488 | prompt processing, n_tokens = 402, progress = 0.15, t = 24.41 s / 16.47 tokens per second 55.27.501.686 I slot print_timing: id 3 | task 9485 | prompt processing, n_tokens = 1580, progress = 0.58, t = 53.62 s / 29.46 tokens per second 55.45.608.900 I slot print_timing: id 0 | task 9480 | prompt eval time = 84840.47 ms / 2587 tokens ( 32.79 ms per token, 30.49 tokens per second) 55.45.608.906 I slot print_timing: id 0 | task 9480 | eval time = 18117.40 ms / 2 tokens (18117.40 ms per token, 0.06 tokens per second) 55.45.608.906 I slot print_timing: id 0 | task 9480 | total time = 102957.87 ms / 2589 tokens 55.45.608.907 I slot print_timing: id 0 | task 9480 | graphs reused = 8265 55.45.608.907 I slot print_timing: id 0 | task 9480 | graph reallocs = 0 / 0 (same size) / (changed size) 55.45.613.251 I slot release: id 0 | task 9480 | stop processing: n_tokens = 2588, truncated = 0 55.45.613.301 I slot print_timing: id 1 | task 9484 | prompt processing, n_tokens = 2288, progress = 0.92, t = 71.74 s / 31.89 tokens per second 55.45.620.326 I slot print_timing: id 2 | task 9488 | prompt processing, n_tokens = 961, progress = 0.36, t = 42.52 s / 22.60 tokens per second 55.45.620.350 I slot print_timing: id 3 | task 9485 | prompt processing, n_tokens = 2226, progress = 0.81, t = 71.74 s / 31.03 tokens per second 55.57.412.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 97712846810 55.57.413.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.153 MiB) 55.57.413.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.778 MiB) 56.02.978.697 I slot launch_slot_: id 0 | task 9492 | processing task, is_child = 0 56.02.978.943 I slot print_timing: id 1 | task 9484 | prompt processing, n_tokens = 2496, progress = 1.00, t = 83.55 s / 29.88 tokens per second 56.02.983.724 I slot print_timing: id 2 | task 9488 | prompt processing, n_tokens = 2139, progress = 0.81, t = 54.33 s / 39.37 tokens per second 56.02.994.371 I slot print_timing: id 3 | task 9485 | prompt processing, n_tokens = 2288, progress = 0.83, t = 83.55 s / 27.39 tokens per second 56.13.522.186 I slot print_timing: id 0 | task 9492 | prompt processing, n_tokens = 208, progress = 0.12, t = 10.52 s / 19.77 tokens per second 56.13.533.840 I slot print_timing: id 2 | task 9488 | prompt processing, n_tokens = 2288, progress = 0.86, t = 70.41 s / 32.49 tokens per second 56.13.544.814 I slot print_timing: id 3 | task 9485 | prompt processing, n_tokens = 2738, progress = 1.00, t = 99.63 s / 27.48 tokens per second 56.22.032.388 I slot print_timing: id 1 | task 9484 | prompt eval time = 99655.74 ms / 2500 tokens ( 39.86 ms per token, 25.09 tokens per second) 56.22.032.391 I slot print_timing: id 1 | task 9484 | eval time = 8510.23 ms / 2 tokens ( 8510.23 ms per token, 0.12 tokens per second) 56.22.032.391 I slot print_timing: id 1 | task 9484 | total time = 108165.96 ms / 2502 tokens 56.22.032.392 I slot print_timing: id 1 | task 9484 | graphs reused = 8265 56.22.032.392 I slot print_timing: id 1 | task 9484 | graph reallocs = 0 / 0 (same size) / (changed size) 56.22.032.868 I slot release: id 1 | task 9484 | stop processing: n_tokens = 2501, truncated = 0 56.22.033.306 I slot print_timing: id 0 | task 9492 | prompt processing, n_tokens = 520, progress = 0.29, t = 19.05 s / 27.29 tokens per second 56.22.033.335 I slot print_timing: id 2 | task 9488 | prompt processing, n_tokens = 2651, progress = 1.00, t = 78.95 s / 33.58 tokens per second 56.31.040.522 I slot print_timing: id 3 | task 9485 | prompt eval time = 108166.76 ms / 2742 tokens ( 39.45 ms per token, 25.35 tokens per second) 56.31.040.525 I slot print_timing: id 3 | task 9485 | eval time = 9007.24 ms / 2 tokens ( 9007.24 ms per token, 0.11 tokens per second) 56.31.040.525 I slot print_timing: id 3 | task 9485 | total time = 117174.00 ms / 2744 tokens 56.31.040.526 I slot print_timing: id 3 | task 9485 | graphs reused = 8265 56.31.040.526 I slot print_timing: id 3 | task 9485 | graph reallocs = 0 / 0 (same size) / (changed size) 56.31.040.678 I slot release: id 3 | task 9485 | stop processing: n_tokens = 2743, truncated = 0 56.31.040.687 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 97749266427 56.31.040.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.278 MiB) 56.31.142.246 I slot launch_slot_: id 1 | task 9496 | processing task, is_child = 0 56.31.142.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.339 MiB) 56.31.311.421 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 97758274236 56.31.311.596 I slot launch_slot_: id 3 | task 9497 | processing task, is_child = 0 56.31.311.605 I slot print_timing: id 0 | task 9492 | prompt processing, n_tokens = 1263, progress = 0.71, t = 28.06 s / 45.01 tokens per second 56.38.935.438 I slot print_timing: id 2 | task 9488 | prompt eval time = 87954.39 ms / 2655 tokens ( 33.13 ms per token, 30.19 tokens per second) 56.38.935.440 I slot print_timing: id 2 | task 9488 | eval time = 7895.06 ms / 2 tokens ( 7895.06 ms per token, 0.13 tokens per second) 56.38.935.441 I slot print_timing: id 2 | task 9488 | total time = 95849.45 ms / 2657 tokens 56.38.935.441 I slot print_timing: id 2 | task 9488 | graphs reused = 8265 56.38.935.442 I slot print_timing: id 2 | task 9488 | graph reallocs = 0 / 0 (same size) / (changed size) 56.38.935.583 I slot release: id 2 | task 9488 | stop processing: n_tokens = 2656, truncated = 0 56.38.935.598 I slot print_timing: id 0 | task 9492 | prompt processing, n_tokens = 1447, progress = 0.81, t = 35.96 s / 40.24 tokens per second 56.38.943.140 I slot print_timing: id 1 | task 9496 | prompt processing, n_tokens = 208, progress = 0.11, t = 7.60 s / 27.36 tokens per second 56.38.956.211 I slot print_timing: id 3 | task 9497 | prompt processing, n_tokens = 208, progress = 0.10, t = 7.60 s / 27.36 tokens per second 56.46.595.842 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 97766169142 56.46.595.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.839 MiB) 56.50.257.577 I slot launch_slot_: id 2 | task 9500 | processing task, is_child = 0 56.50.257.589 I slot print_timing: id 0 | task 9492 | prompt processing, n_tokens = 1775, progress = 1.00, t = 43.62 s / 40.70 tokens per second 56.50.270.207 I slot print_timing: id 1 | task 9496 | prompt processing, n_tokens = 520, progress = 0.28, t = 15.26 s / 34.07 tokens per second 56.50.270.408 I slot print_timing: id 3 | task 9497 | prompt processing, n_tokens = 520, progress = 0.25, t = 15.26 s / 34.07 tokens per second 57.13.417.226 I slot print_timing: id 1 | task 9496 | prompt processing, n_tokens = 1325, progress = 0.72, t = 42.08 s / 31.49 tokens per second 57.13.423.165 I slot print_timing: id 2 | task 9500 | prompt processing, n_tokens = 208, progress = 0.11, t = 23.15 s / 8.99 tokens per second 57.13.427.618 I slot print_timing: id 3 | task 9497 | prompt processing, n_tokens = 1447, progress = 0.71, t = 42.08 s / 34.38 tokens per second 57.20.021.584 I slot print_timing: id 0 | task 9492 | prompt eval time = 70438.48 ms / 1779 tokens ( 39.59 ms per token, 25.26 tokens per second) 57.20.021.590 I slot print_timing: id 0 | task 9492 | eval time = 6604.37 ms / 2 tokens ( 6604.37 ms per token, 0.15 tokens per second) 57.20.021.591 I slot print_timing: id 0 | task 9492 | total time = 77042.86 ms / 1781 tokens 57.20.021.592 I slot print_timing: id 0 | task 9492 | graphs reused = 8265 57.20.021.592 I slot print_timing: id 0 | task 9492 | graph reallocs = 0 / 0 (same size) / (changed size) 57.20.021.754 I slot release: id 0 | task 9492 | stop processing: n_tokens = 1780, truncated = 0 57.20.021.772 I slot print_timing: id 1 | task 9496 | prompt processing, n_tokens = 1447, progress = 0.79, t = 48.69 s / 29.72 tokens per second 57.20.032.910 I slot print_timing: id 2 | task 9500 | prompt processing, n_tokens = 520, progress = 0.28, t = 29.75 s / 17.48 tokens per second 57.20.032.932 I slot print_timing: id 3 | task 9497 | prompt processing, n_tokens = 1532, progress = 0.75, t = 48.69 s / 31.47 tokens per second 57.36.829.186 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 57.36.829.263 I slot launch_slot_: id 0 | task 9504 | processing task, is_child = 0 57.40.510.309 I slot print_timing: id 1 | task 9496 | prompt processing, n_tokens = 1837, progress = 1.00, t = 65.50 s / 28.05 tokens per second 57.40.514.967 I slot print_timing: id 2 | task 9500 | prompt processing, n_tokens = 1336, progress = 0.72, t = 46.56 s / 28.69 tokens per second 57.40.543.051 I slot print_timing: id 3 | task 9497 | prompt processing, n_tokens = 2044, progress = 1.00, t = 65.50 s / 31.21 tokens per second 57.48.351.034 I slot print_timing: id 0 | task 9504 | prompt processing, n_tokens = 511, progress = 1.00, t = 11.52 s / 44.35 tokens per second 57.48.359.795 I slot print_timing: id 2 | task 9500 | prompt processing, n_tokens = 1447, progress = 0.78, t = 58.08 s / 24.91 tokens per second 57.53.635.964 I slot print_timing: id 1 | task 9496 | prompt eval time = 77016.87 ms / 1841 tokens ( 41.83 ms per token, 23.90 tokens per second) 57.53.635.970 I slot print_timing: id 1 | task 9496 | eval time = 5285.16 ms / 2 tokens ( 5285.16 ms per token, 0.19 tokens per second) 57.53.635.971 I slot print_timing: id 1 | task 9496 | total time = 82302.03 ms / 1843 tokens 57.53.635.972 I slot print_timing: id 1 | task 9496 | graphs reused = 8265 57.53.635.972 I slot print_timing: id 1 | task 9496 | graph reallocs = 0 / 0 (same size) / (changed size) 57.53.636.064 I slot release: id 1 | task 9496 | stop processing: n_tokens = 1842, truncated = 0 57.53.636.307 I slot print_timing: id 3 | task 9497 | prompt eval time = 77016.91 ms / 2048 tokens ( 37.61 ms per token, 26.59 tokens per second) 57.53.636.310 I slot print_timing: id 3 | task 9497 | eval time = 5285.28 ms / 2 tokens ( 5285.28 ms per token, 0.19 tokens per second) 57.53.636.311 I slot print_timing: id 3 | task 9497 | total time = 82302.19 ms / 2050 tokens 57.53.636.311 I slot print_timing: id 3 | task 9497 | graphs reused = 8265 57.53.636.311 I slot print_timing: id 3 | task 9497 | graph reallocs = 0 / 0 (same size) / (changed size) 57.53.639.462 I slot release: id 3 | task 9497 | stop processing: n_tokens = 2049, truncated = 0 57.53.639.494 I slot print_timing: id 2 | task 9500 | prompt processing, n_tokens = 1848, progress = 1.00, t = 63.37 s / 29.16 tokens per second 57.53.954.539 I slot print_timing: id 0 | task 9504 | prompt eval time = 16806.48 ms / 515 tokens ( 32.63 ms per token, 30.64 tokens per second) 57.53.954.542 I slot print_timing: id 0 | task 9504 | eval time = 318.77 ms / 2 tokens ( 318.77 ms per token, 3.14 tokens per second) 57.53.954.542 I slot print_timing: id 0 | task 9504 | total time = 17125.26 ms / 517 tokens 57.53.954.543 I slot print_timing: id 0 | task 9504 | graphs reused = 8265 57.53.954.543 I slot print_timing: id 0 | task 9504 | graph reallocs = 0 / 0 (same size) / (changed size) 57.53.955.734 I slot release: id 0 | task 9504 | stop processing: n_tokens = 1963, truncated = 0 57.53.956.566 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 97840869622 57.53.956.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 57.54.396.955 I slot launch_slot_: id 1 | task 9508 | processing task, is_child = 0 57.54.397.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.402 MiB) 57.55.060.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.472 MiB) 57.55.561.714 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.756 57.55.561.796 I slot launch_slot_: id 0 | task 9509 | processing task, is_child = 0 57.55.561.899 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 97840873022 57.55.562.014 I slot launch_slot_: id 3 | task 9510 | processing task, is_child = 0 58.03.666.366 I slot print_timing: id 2 | task 9500 | prompt eval time = 63686.33 ms / 1852 tokens ( 34.39 ms per token, 29.08 tokens per second) 58.03.666.368 I slot print_timing: id 2 | task 9500 | eval time = 9709.80 ms / 2 tokens ( 9709.80 ms per token, 0.10 tokens per second) 58.03.666.370 I slot print_timing: id 2 | task 9500 | total time = 73396.12 ms / 1854 tokens 58.03.666.370 I slot print_timing: id 2 | task 9500 | graphs reused = 8265 58.03.666.371 I slot print_timing: id 2 | task 9500 | graph reallocs = 0 / 0 (same size) / (changed size) 58.03.669.286 I slot release: id 2 | task 9500 | stop processing: n_tokens = 1853, truncated = 0 58.03.669.319 I slot print_timing: id 0 | task 9509 | prompt processing, n_tokens = 330, progress = 1.00, t = 8.10 s / 40.72 tokens per second 58.03.704.303 I slot print_timing: id 1 | task 9508 | prompt processing, n_tokens = 130, progress = 0.18, t = 8.04 s / 16.17 tokens per second 58.03.721.597 I slot print_timing: id 3 | task 9510 | prompt processing, n_tokens = 130, progress = 0.17, t = 8.04 s / 16.17 tokens per second 58.06.610.053 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 97850902845 58.06.610.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 824.784 MiB) 58.06.817.582 I slot launch_slot_: id 2 | task 9513 | processing task, is_child = 0 58.06.817.600 I slot print_timing: id 1 | task 9508 | prompt processing, n_tokens = 210, progress = 0.29, t = 10.92 s / 19.22 tokens per second 58.06.869.663 I slot print_timing: id 3 | task 9510 | prompt processing, n_tokens = 232, progress = 0.31, t = 10.92 s / 21.24 tokens per second 58.18.071.212 I slot print_timing: id 0 | task 9509 | prompt eval time = 11048.02 ms / 334 tokens ( 33.08 ms per token, 30.23 tokens per second) 58.18.071.215 I slot print_timing: id 0 | task 9509 | eval time = 11461.17 ms / 2 tokens (11461.17 ms per token, 0.09 tokens per second) 58.18.071.215 I slot print_timing: id 0 | task 9509 | total time = 22509.19 ms / 336 tokens 58.18.071.216 I slot print_timing: id 0 | task 9509 | graphs reused = 8265 58.18.071.216 I slot print_timing: id 0 | task 9509 | graph reallocs = 0 / 0 (same size) / (changed size) 58.18.071.308 I slot release: id 0 | task 9509 | stop processing: n_tokens = 1782, truncated = 0 58.18.071.323 I slot print_timing: id 1 | task 9508 | prompt processing, n_tokens = 615, progress = 0.85, t = 22.44 s / 27.40 tokens per second 58.18.100.833 I slot print_timing: id 2 | task 9513 | prompt processing, n_tokens = 130, progress = 0.17, t = 11.20 s / 11.61 tokens per second 58.18.164.670 I slot print_timing: id 3 | task 9510 | prompt processing, n_tokens = 615, progress = 0.82, t = 22.44 s / 27.40 tokens per second 58.22.563.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 97865304867 58.22.563.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 828.848 MiB) 58.22.889.640 I slot launch_slot_: id 0 | task 9516 | processing task, is_child = 0 58.22.889.868 I slot print_timing: id 1 | task 9508 | prompt processing, n_tokens = 722, progress = 0.99, t = 26.93 s / 26.81 tokens per second 58.22.894.700 I slot print_timing: id 2 | task 9513 | prompt processing, n_tokens = 245, progress = 0.32, t = 15.69 s / 15.61 tokens per second 58.22.908.011 I slot print_timing: id 3 | task 9510 | prompt processing, n_tokens = 744, progress = 0.99, t = 26.93 s / 27.62 tokens per second 58.29.134.560 I slot print_timing: id 0 | task 9516 | prompt processing, n_tokens = 130, progress = 0.18, t = 6.24 s / 20.82 tokens per second 58.29.165.175 I slot print_timing: id 2 | task 9513 | prompt processing, n_tokens = 615, progress = 0.81, t = 22.26 s / 27.62 tokens per second 58.32.456.254 I slot print_timing: id 1 | task 9508 | prompt eval time = 33506.19 ms / 726 tokens ( 46.15 ms per token, 21.67 tokens per second) 58.32.456.262 I slot print_timing: id 1 | task 9508 | eval time = 3322.00 ms / 2 tokens ( 3322.00 ms per token, 0.30 tokens per second) 58.32.456.268 I slot print_timing: id 1 | task 9508 | total time = 36828.18 ms / 728 tokens 58.32.456.269 I slot print_timing: id 1 | task 9508 | graphs reused = 8265 58.32.456.271 I slot print_timing: id 1 | task 9508 | graph reallocs = 0 / 0 (same size) / (changed size) 58.32.456.341 I slot release: id 1 | task 9508 | stop processing: n_tokens = 727, truncated = 0 58.32.456.580 I slot print_timing: id 3 | task 9510 | prompt eval time = 33506.30 ms / 748 tokens ( 44.79 ms per token, 22.32 tokens per second) 58.32.456.586 I slot print_timing: id 3 | task 9510 | eval time = 3322.04 ms / 2 tokens ( 3322.04 ms per token, 0.30 tokens per second) 58.32.456.586 I slot print_timing: id 3 | task 9510 | total time = 36828.34 ms / 750 tokens 58.32.456.586 I slot print_timing: id 3 | task 9510 | graphs reused = 8265 58.32.456.587 I slot print_timing: id 3 | task 9510 | graph reallocs = 0 / 0 (same size) / (changed size) 58.32.456.609 I slot release: id 3 | task 9510 | stop processing: n_tokens = 749, truncated = 0 58.32.456.616 I slot print_timing: id 0 | task 9516 | prompt processing, n_tokens = 209, progress = 0.29, t = 9.57 s / 21.85 tokens per second 58.32.471.622 I slot print_timing: id 2 | task 9513 | prompt processing, n_tokens = 757, progress = 0.99, t = 25.59 s / 29.59 tokens per second 58.37.393.275 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 58.37.393.346 I slot launch_slot_: id 1 | task 9520 | processing task, is_child = 0 58.37.393.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 909.940 MiB) 58.37.504.761 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 97879690166 58.37.504.874 I slot launch_slot_: id 3 | task 9521 | processing task, is_child = 0 58.37.504.882 I slot print_timing: id 0 | task 9516 | prompt processing, n_tokens = 615, progress = 0.85, t = 14.50 s / 42.40 tokens per second 58.42.106.074 I slot print_timing: id 2 | task 9513 | prompt eval time = 30523.77 ms / 761 tokens ( 40.11 ms per token, 24.93 tokens per second) 58.42.106.080 I slot print_timing: id 2 | task 9513 | eval time = 4712.80 ms / 2 tokens ( 4712.80 ms per token, 0.21 tokens per second) 58.42.106.080 I slot print_timing: id 2 | task 9513 | total time = 35236.57 ms / 763 tokens 58.42.106.081 I slot print_timing: id 2 | task 9513 | graphs reused = 8265 58.42.106.081 I slot print_timing: id 2 | task 9513 | graph reallocs = 0 / 0 (same size) / (changed size) 58.42.106.128 I slot release: id 2 | task 9513 | stop processing: n_tokens = 762, truncated = 0 58.42.106.138 I slot print_timing: id 0 | task 9516 | prompt processing, n_tokens = 721, progress = 0.99, t = 19.22 s / 37.52 tokens per second 58.42.112.262 I slot print_timing: id 1 | task 9520 | prompt processing, n_tokens = 120, progress = 0.99, t = 4.59 s / 26.16 tokens per second 58.42.116.862 I slot print_timing: id 3 | task 9521 | prompt processing, n_tokens = 117, progress = 0.15, t = 4.58 s / 25.55 tokens per second 58.44.167.156 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 97889339685 58.44.167.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 904.501 MiB) 58.44.289.476 I slot launch_slot_: id 2 | task 9524 | processing task, is_child = 0 58.44.289.556 I slot print_timing: id 3 | task 9521 | prompt processing, n_tokens = 257, progress = 0.32, t = 6.64 s / 38.70 tokens per second 58.47.123.005 I slot print_timing: id 0 | task 9516 | prompt eval time = 21277.25 ms / 725 tokens ( 29.35 ms per token, 34.07 tokens per second) 58.47.123.008 I slot print_timing: id 0 | task 9516 | eval time = 2956.10 ms / 2 tokens ( 2956.10 ms per token, 0.34 tokens per second) 58.47.123.009 I slot print_timing: id 0 | task 9516 | total time = 24233.35 ms / 727 tokens 58.47.123.009 I slot print_timing: id 0 | task 9516 | graphs reused = 8265 58.47.123.010 I slot print_timing: id 0 | task 9516 | graph reallocs = 0 / 0 (same size) / (changed size) 58.47.123.044 I slot release: id 0 | task 9516 | stop processing: n_tokens = 726, truncated = 0 58.47.123.282 I slot print_timing: id 1 | task 9520 | prompt eval time = 6648.16 ms / 124 tokens ( 53.61 ms per token, 18.65 tokens per second) 58.47.123.285 I slot print_timing: id 1 | task 9520 | eval time = 2956.13 ms / 2 tokens ( 2956.13 ms per token, 0.34 tokens per second) 58.47.123.285 I slot print_timing: id 1 | task 9520 | total time = 9604.29 ms / 126 tokens 58.47.123.285 I slot print_timing: id 1 | task 9520 | graphs reused = 8265 58.47.123.286 I slot print_timing: id 1 | task 9520 | graph reallocs = 0 / 0 (same size) / (changed size) 58.47.123.328 I slot release: id 1 | task 9520 | stop processing: n_tokens = 740, truncated = 0 58.47.130.696 I slot print_timing: id 3 | task 9521 | prompt processing, n_tokens = 282, progress = 0.35, t = 9.60 s / 29.39 tokens per second 58.51.501.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 97894356601 58.51.501.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.631 MiB) 58.53.349.019 I slot launch_slot_: id 0 | task 9527 | processing task, is_child = 0 58.53.349.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 914.192 MiB) 58.53.503.830 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 97894356885 58.53.503.937 I slot launch_slot_: id 1 | task 9528 | processing task, is_child = 0 58.53.504.063 I slot print_timing: id 2 | task 9524 | prompt processing, n_tokens = 352, progress = 0.34, t = 7.21 s / 48.81 tokens per second 58.53.504.070 I slot print_timing: id 3 | task 9521 | prompt processing, n_tokens = 631, progress = 0.79, t = 13.97 s / 45.15 tokens per second 59.01.116.223 I slot print_timing: id 0 | task 9527 | prompt processing, n_tokens = 155, progress = 0.19, t = 7.61 s / 20.36 tokens per second 59.01.426.094 I slot print_timing: id 1 | task 9528 | prompt processing, n_tokens = 155, progress = 0.19, t = 7.61 s / 20.36 tokens per second 59.01.430.547 I slot print_timing: id 2 | task 9524 | prompt processing, n_tokens = 526, progress = 0.50, t = 16.83 s / 31.26 tokens per second 59.01.434.968 I slot print_timing: id 3 | task 9521 | prompt processing, n_tokens = 794, progress = 0.99, t = 23.59 s / 33.66 tokens per second 59.09.082.655 I slot print_timing: id 0 | task 9527 | prompt processing, n_tokens = 277, progress = 0.35, t = 15.58 s / 17.78 tokens per second 59.09.082.668 I slot print_timing: id 1 | task 9528 | prompt processing, n_tokens = 277, progress = 0.34, t = 15.58 s / 17.78 tokens per second 59.09.082.677 I slot print_timing: id 2 | task 9524 | prompt processing, n_tokens = 893, progress = 0.86, t = 24.79 s / 36.02 tokens per second 59.11.930.007 I slot print_timing: id 3 | task 9521 | prompt eval time = 31556.07 ms / 798 tokens ( 39.54 ms per token, 25.29 tokens per second) 59.11.930.010 I slot print_timing: id 3 | task 9521 | eval time = 2847.36 ms / 2 tokens ( 2847.36 ms per token, 0.35 tokens per second) 59.11.930.010 I slot print_timing: id 3 | task 9521 | total time = 34403.43 ms / 800 tokens 59.11.930.011 I slot print_timing: id 3 | task 9521 | graphs reused = 8265 59.11.931.061 I slot print_timing: id 3 | task 9521 | graph reallocs = 0 / 0 (same size) / (changed size) 59.11.931.163 I slot release: id 3 | task 9521 | stop processing: n_tokens = 799, truncated = 0 59.11.931.190 I slot print_timing: id 0 | task 9527 | prompt processing, n_tokens = 283, progress = 0.35, t = 18.43 s / 15.36 tokens per second 59.11.937.682 I slot print_timing: id 1 | task 9528 | prompt processing, n_tokens = 293, progress = 0.36, t = 18.43 s / 15.90 tokens per second 59.11.942.770 I slot print_timing: id 2 | task 9524 | prompt processing, n_tokens = 1038, progress = 1.00, t = 27.64 s / 37.55 tokens per second 59.21.302.614 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 97919164722 59.21.302.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.298 MiB) 59.21.424.538 I slot launch_slot_: id 3 | task 9533 | processing task, is_child = 0 59.21.424.553 I slot print_timing: id 0 | task 9527 | prompt processing, n_tokens = 679, progress = 0.85, t = 27.80 s / 24.43 tokens per second 59.21.441.692 I slot print_timing: id 1 | task 9528 | prompt processing, n_tokens = 679, progress = 0.84, t = 27.80 s / 24.43 tokens per second 59.26.846.675 I slot print_timing: id 2 | task 9524 | prompt eval time = 37013.12 ms / 1042 tokens ( 35.52 ms per token, 28.15 tokens per second) 59.26.846.678 I slot print_timing: id 2 | task 9524 | eval time = 5544.06 ms / 2 tokens ( 5544.06 ms per token, 0.18 tokens per second) 59.26.846.678 I slot print_timing: id 2 | task 9524 | total time = 42557.18 ms / 1044 tokens 59.26.846.679 I slot print_timing: id 2 | task 9524 | graphs reused = 8265 59.26.846.679 I slot print_timing: id 2 | task 9524 | graph reallocs = 0 / 0 (same size) / (changed size) 59.26.846.741 I slot release: id 2 | task 9524 | stop processing: n_tokens = 1043, truncated = 0 59.26.846.753 I slot print_timing: id 0 | task 9527 | prompt processing, n_tokens = 795, progress = 0.99, t = 33.34 s / 23.84 tokens per second 59.26.858.278 I slot print_timing: id 1 | task 9528 | prompt processing, n_tokens = 805, progress = 1.00, t = 33.34 s / 24.14 tokens per second 59.26.863.266 I slot print_timing: id 3 | task 9533 | prompt processing, n_tokens = 138, progress = 0.16, t = 5.24 s / 26.33 tokens per second 59.29.289.234 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 97934080298 59.29.289.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.863 MiB) 59.29.402.159 I slot launch_slot_: id 2 | task 9536 | processing task, is_child = 0 59.29.402.259 I slot print_timing: id 3 | task 9533 | prompt processing, n_tokens = 319, progress = 0.38, t = 7.68 s / 41.51 tokens per second 59.31.537.661 I slot print_timing: id 0 | task 9527 | prompt eval time = 35785.06 ms / 799 tokens ( 44.79 ms per token, 22.33 tokens per second) 59.31.537.664 I slot print_timing: id 0 | task 9527 | eval time = 2248.65 ms / 2 tokens ( 2248.65 ms per token, 0.44 tokens per second) 59.31.537.664 I slot print_timing: id 0 | task 9527 | total time = 38033.71 ms / 801 tokens 59.31.537.665 I slot print_timing: id 0 | task 9527 | graphs reused = 8265 59.31.537.665 I slot print_timing: id 0 | task 9527 | graph reallocs = 0 / 0 (same size) / (changed size) 59.31.539.356 I slot release: id 0 | task 9527 | stop processing: n_tokens = 800, truncated = 0 59.31.539.825 I slot print_timing: id 1 | task 9528 | prompt eval time = 35785.22 ms / 809 tokens ( 44.23 ms per token, 22.61 tokens per second) 59.31.539.830 I slot print_timing: id 1 | task 9528 | eval time = 2250.59 ms / 2 tokens ( 2250.59 ms per token, 0.44 tokens per second) 59.31.539.831 I slot print_timing: id 1 | task 9528 | total time = 38035.81 ms / 811 tokens 59.31.539.831 I slot print_timing: id 1 | task 9528 | graphs reused = 8265 59.31.539.832 I slot print_timing: id 1 | task 9528 | graph reallocs = 0 / 0 (same size) / (changed size) 59.31.539.884 I slot release: id 1 | task 9528 | stop processing: n_tokens = 810, truncated = 0 59.31.547.773 I slot print_timing: id 3 | task 9533 | prompt processing, n_tokens = 329, progress = 0.39, t = 9.93 s / 33.12 tokens per second 59.35.901.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 97938772918 59.38.688.736 I slot launch_slot_: id 0 | task 9539 | processing task, is_child = 0 59.38.688.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 876.240 MiB) 59.38.870.209 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 97938773441 59.38.870.348 I slot launch_slot_: id 1 | task 9540 | processing task, is_child = 0 59.38.870.519 I slot print_timing: id 2 | task 9536 | prompt processing, n_tokens = 319, progress = 0.38, t = 6.50 s / 49.08 tokens per second 59.38.870.526 I slot print_timing: id 3 | task 9533 | prompt processing, n_tokens = 723, progress = 0.86, t = 14.30 s / 50.57 tokens per second 59.42.556.677 I slot print_timing: id 0 | task 9539 | prompt processing, n_tokens = 138, progress = 0.15, t = 3.69 s / 37.44 tokens per second 59.44.049.112 I slot print_timing: id 1 | task 9540 | prompt processing, n_tokens = 138, progress = 0.15, t = 3.69 s / 37.44 tokens per second 59.44.094.654 I slot print_timing: id 2 | task 9536 | prompt processing, n_tokens = 323, progress = 0.38, t = 13.15 s / 24.55 tokens per second 59.44.107.122 I slot print_timing: id 3 | task 9533 | prompt processing, n_tokens = 841, progress = 1.00, t = 20.95 s / 40.14 tokens per second 59.53.416.947 I slot print_timing: id 0 | task 9539 | prompt processing, n_tokens = 319, progress = 0.35, t = 14.55 s / 21.93 tokens per second 59.53.416.957 I slot print_timing: id 1 | task 9540 | prompt processing, n_tokens = 319, progress = 0.35, t = 14.55 s / 21.93 tokens per second 59.53.416.963 I slot print_timing: id 2 | task 9536 | prompt processing, n_tokens = 723, progress = 0.86, t = 24.01 s / 30.11 tokens per second 59.57.240.977 I slot print_timing: id 3 | task 9533 | prompt eval time = 31812.56 ms / 845 tokens ( 37.65 ms per token, 26.56 tokens per second) 59.57.240.982 I slot print_timing: id 3 | task 9533 | eval time = 3824.05 ms / 2 tokens ( 3824.05 ms per token, 0.26 tokens per second) 59.57.240.983 I slot print_timing: id 3 | task 9533 | total time = 35636.61 ms / 847 tokens 59.57.240.983 I slot print_timing: id 3 | task 9533 | graphs reused = 8265 59.57.240.984 I slot print_timing: id 3 | task 9533 | graph reallocs = 0 / 0 (same size) / (changed size) 59.57.242.925 I slot release: id 3 | task 9533 | stop processing: n_tokens = 846, truncated = 0 59.57.242.960 I slot print_timing: id 0 | task 9539 | prompt processing, n_tokens = 394, progress = 0.43, t = 18.37 s / 21.45 tokens per second 59.57.261.207 I slot print_timing: id 1 | task 9540 | prompt processing, n_tokens = 385, progress = 0.43, t = 18.37 s / 20.96 tokens per second 59.57.276.026 I slot print_timing: id 2 | task 9536 | prompt processing, n_tokens = 835, progress = 1.00, t = 27.84 s / 29.99 tokens per second 60.05.587.634 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 60.05.587.701 I slot launch_slot_: id 3 | task 9545 | processing task, is_child = 0 60.05.587.709 I slot print_timing: id 0 | task 9539 | prompt processing, n_tokens = 723, progress = 0.79, t = 26.72 s / 27.06 tokens per second 60.05.604.782 I slot print_timing: id 1 | task 9540 | prompt processing, n_tokens = 723, progress = 0.80, t = 26.72 s / 27.06 tokens per second 60.12.030.384 I slot print_timing: id 2 | task 9536 | prompt eval time = 36185.45 ms / 839 tokens ( 43.13 ms per token, 23.19 tokens per second) 60.12.030.399 I slot print_timing: id 2 | task 9536 | eval time = 6442.76 ms / 2 tokens ( 6442.76 ms per token, 0.16 tokens per second) 60.12.030.401 I slot print_timing: id 2 | task 9536 | total time = 42628.21 ms / 841 tokens 60.12.030.401 I slot print_timing: id 2 | task 9536 | graphs reused = 8265 60.12.030.402 I slot print_timing: id 2 | task 9536 | graph reallocs = 0 / 0 (same size) / (changed size) 60.12.030.449 I slot release: id 2 | task 9536 | stop processing: n_tokens = 840, truncated = 0 60.12.030.461 I slot print_timing: id 0 | task 9539 | prompt processing, n_tokens = 906, progress = 1.00, t = 33.16 s / 27.32 tokens per second 60.12.038.191 I slot print_timing: id 1 | task 9540 | prompt processing, n_tokens = 897, progress = 1.00, t = 33.16 s / 27.05 tokens per second 60.12.056.917 I slot print_timing: id 3 | task 9545 | prompt processing, n_tokens = 135, progress = 1.00, t = 6.41 s / 21.06 tokens per second 60.12.530.332 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 97979264007 60.12.530.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.986 MiB) 60.12.727.416 I slot launch_slot_: id 2 | task 9548 | processing task, is_child = 0 60.14.522.650 I slot print_timing: id 0 | task 9539 | prompt eval time = 33659.21 ms / 910 tokens ( 36.99 ms per token, 27.04 tokens per second) 60.14.522.653 I slot print_timing: id 0 | task 9539 | eval time = 1993.08 ms / 2 tokens ( 1993.08 ms per token, 0.50 tokens per second) 60.14.522.653 I slot print_timing: id 0 | task 9539 | total time = 35652.29 ms / 912 tokens 60.14.522.654 I slot print_timing: id 0 | task 9539 | graphs reused = 8265 60.14.522.654 I slot print_timing: id 0 | task 9539 | graph reallocs = 0 / 0 (same size) / (changed size) 60.14.524.339 I slot release: id 0 | task 9539 | stop processing: n_tokens = 911, truncated = 0 60.14.525.201 I slot print_timing: id 1 | task 9540 | prompt eval time = 33659.51 ms / 901 tokens ( 37.36 ms per token, 26.77 tokens per second) 60.14.525.214 I slot print_timing: id 1 | task 9540 | eval time = 1995.22 ms / 2 tokens ( 1995.22 ms per token, 0.50 tokens per second) 60.14.525.216 I slot print_timing: id 1 | task 9540 | total time = 35654.73 ms / 903 tokens 60.14.525.217 I slot print_timing: id 1 | task 9540 | graphs reused = 8265 60.14.525.217 I slot print_timing: id 1 | task 9540 | graph reallocs = 0 / 0 (same size) / (changed size) 60.14.525.312 I slot release: id 1 | task 9540 | stop processing: n_tokens = 902, truncated = 0 60.14.526.253 I slot print_timing: id 3 | task 9545 | prompt eval time = 6910.81 ms / 139 tokens ( 49.72 ms per token, 20.11 tokens per second) 60.14.526.258 I slot print_timing: id 3 | task 9545 | eval time = 1995.93 ms / 2 tokens ( 1995.93 ms per token, 0.50 tokens per second) 60.14.526.258 I slot print_timing: id 3 | task 9545 | total time = 8906.73 ms / 141 tokens 60.14.526.258 I slot print_timing: id 3 | task 9545 | graphs reused = 8265 60.14.526.259 I slot print_timing: id 3 | task 9545 | graph reallocs = 0 / 0 (same size) / (changed size) 60.14.526.340 I slot release: id 3 | task 9545 | stop processing: n_tokens = 863, truncated = 0 60.14.544.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 97981757898 60.14.544.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.547 MiB) 60.15.321.907 I slot launch_slot_: id 0 | task 9551 | processing task, is_child = 0 60.15.321.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.961 MiB) 60.15.440.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.773 MiB) 60.15.638.012 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 97981758870 60.15.638.125 I slot launch_slot_: id 1 | task 9552 | processing task, is_child = 0 60.15.638.170 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 97981759899 60.15.638.231 I slot launch_slot_: id 3 | task 9553 | processing task, is_child = 0 60.21.317.410 I slot print_timing: id 0 | task 9551 | prompt processing, n_tokens = 122, progress = 0.16, t = 5.68 s / 21.48 tokens per second 60.24.952.908 I slot print_timing: id 1 | task 9552 | prompt processing, n_tokens = 119, progress = 0.14, t = 5.68 s / 20.95 tokens per second 60.24.957.588 I slot print_timing: id 2 | task 9548 | prompt processing, n_tokens = 583, progress = 0.85, t = 8.59 s / 67.87 tokens per second 60.24.970.402 I slot print_timing: id 3 | task 9553 | prompt processing, n_tokens = 119, progress = 0.14, t = 5.67 s / 20.97 tokens per second 60.30.739.907 I slot print_timing: id 0 | task 9551 | prompt processing, n_tokens = 253, progress = 0.33, t = 15.10 s / 16.75 tokens per second 60.31.174.394 I slot print_timing: id 1 | task 9552 | prompt processing, n_tokens = 246, progress = 0.30, t = 15.10 s / 16.29 tokens per second 60.31.174.404 I slot print_timing: id 2 | task 9548 | prompt processing, n_tokens = 684, progress = 0.99, t = 18.01 s / 37.97 tokens per second 60.31.181.181 I slot print_timing: id 3 | task 9553 | prompt processing, n_tokens = 246, progress = 0.29, t = 15.10 s / 16.29 tokens per second 60.37.855.295 I slot print_timing: id 0 | task 9551 | prompt processing, n_tokens = 632, progress = 0.82, t = 22.22 s / 28.45 tokens per second 60.37.863.026 I slot print_timing: id 1 | task 9552 | prompt processing, n_tokens = 309, progress = 0.37, t = 22.22 s / 13.91 tokens per second 60.37.867.603 I slot print_timing: id 3 | task 9553 | prompt processing, n_tokens = 335, progress = 0.39, t = 22.21 s / 15.08 tokens per second 60.49.013.129 I slot print_timing: id 2 | task 9548 | prompt eval time = 25127.85 ms / 688 tokens ( 36.52 ms per token, 27.38 tokens per second) 60.49.013.134 I slot print_timing: id 2 | task 9548 | eval time = 11157.84 ms / 2 tokens (11157.84 ms per token, 0.09 tokens per second) 60.49.013.136 I slot print_timing: id 2 | task 9548 | total time = 36285.69 ms / 690 tokens 60.49.013.136 I slot print_timing: id 2 | task 9548 | graphs reused = 8265 60.49.013.137 I slot print_timing: id 2 | task 9548 | graph reallocs = 0 / 0 (same size) / (changed size) 60.49.014.912 I slot release: id 2 | task 9548 | stop processing: n_tokens = 689, truncated = 0 60.49.014.955 I slot print_timing: id 0 | task 9551 | prompt processing, n_tokens = 765, progress = 0.99, t = 33.37 s / 22.92 tokens per second 60.49.024.241 I slot print_timing: id 1 | task 9552 | prompt processing, n_tokens = 708, progress = 0.86, t = 33.37 s / 21.21 tokens per second 60.49.029.162 I slot print_timing: id 3 | task 9553 | prompt processing, n_tokens = 708, progress = 0.83, t = 33.37 s / 21.22 tokens per second 60.52.574.074 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 98016248471 60.52.574.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 60.52.680.953 I slot launch_slot_: id 2 | task 9559 | processing task, is_child = 0 60.52.680.966 I slot print_timing: id 1 | task 9552 | prompt processing, n_tokens = 821, progress = 1.00, t = 36.94 s / 22.23 tokens per second 60.52.708.057 I slot print_timing: id 3 | task 9553 | prompt processing, n_tokens = 847, progress = 1.00, t = 36.93 s / 22.93 tokens per second 60.54.751.110 I slot print_timing: id 0 | task 9551 | prompt eval time = 36935.83 ms / 769 tokens ( 48.03 ms per token, 20.82 tokens per second) 60.54.752.226 I slot print_timing: id 0 | task 9551 | eval time = 2177.04 ms / 2 tokens ( 2177.04 ms per token, 0.46 tokens per second) 60.54.752.231 I slot print_timing: id 0 | task 9551 | total time = 39112.86 ms / 771 tokens 60.54.752.231 I slot print_timing: id 0 | task 9551 | graphs reused = 8265 60.54.752.232 I slot print_timing: id 0 | task 9551 | graph reallocs = 0 / 0 (same size) / (changed size) 60.54.754.198 I slot release: id 0 | task 9551 | stop processing: n_tokens = 770, truncated = 0 60.56.525.908 I slot print_timing: id 1 | task 9552 | prompt eval time = 39116.39 ms / 825 tokens ( 47.41 ms per token, 21.09 tokens per second) 60.56.525.911 I slot print_timing: id 1 | task 9552 | eval time = 1771.19 ms / 2 tokens ( 1771.19 ms per token, 0.56 tokens per second) 60.56.525.912 I slot print_timing: id 1 | task 9552 | total time = 40887.58 ms / 827 tokens 60.56.525.912 I slot print_timing: id 1 | task 9552 | graphs reused = 8265 60.56.525.913 I slot print_timing: id 1 | task 9552 | graph reallocs = 0 / 0 (same size) / (changed size) 60.56.525.996 I slot release: id 1 | task 9552 | stop processing: n_tokens = 826, truncated = 0 60.56.526.245 I slot print_timing: id 3 | task 9553 | prompt eval time = 39112.36 ms / 851 tokens ( 45.96 ms per token, 21.76 tokens per second) 60.56.526.247 I slot print_timing: id 3 | task 9553 | eval time = 1771.01 ms / 2 tokens ( 1771.01 ms per token, 0.56 tokens per second) 60.56.526.247 I slot print_timing: id 3 | task 9553 | total time = 40883.37 ms / 853 tokens 60.56.526.248 I slot print_timing: id 3 | task 9553 | graphs reused = 8265 60.56.526.248 I slot print_timing: id 3 | task 9553 | graph reallocs = 0 / 0 (same size) / (changed size) 60.56.526.285 I slot release: id 3 | task 9553 | stop processing: n_tokens = 852, truncated = 0 60.56.526.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 98021987756 60.56.526.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 60.56.650.389 I slot launch_slot_: id 0 | task 9562 | processing task, is_child = 0 60.56.650.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 60.56.732.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.342 MiB) 60.56.846.145 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 98023759555 60.56.846.261 I slot launch_slot_: id 1 | task 9563 | processing task, is_child = 0 60.56.846.308 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 98023759842 60.56.846.375 I slot launch_slot_: id 3 | task 9564 | processing task, is_child = 0 60.56.846.516 I slot print_timing: id 2 | task 9559 | prompt processing, n_tokens = 236, progress = 0.31, t = 3.82 s / 61.82 tokens per second 61.01.985.466 I slot print_timing: id 0 | task 9562 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.14 s / 20.43 tokens per second 61.05.622.740 I slot print_timing: id 1 | task 9563 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.14 s / 20.43 tokens per second 61.05.627.365 I slot print_timing: id 2 | task 9559 | prompt processing, n_tokens = 632, progress = 0.84, t = 9.28 s / 68.12 tokens per second 61.05.631.793 I slot print_timing: id 3 | task 9564 | prompt processing, n_tokens = 105, progress = 0.14, t = 5.13 s / 20.45 tokens per second 61.11.217.254 I slot print_timing: id 0 | task 9562 | prompt processing, n_tokens = 197, progress = 0.28, t = 14.37 s / 13.71 tokens per second 61.11.320.309 I slot print_timing: id 1 | task 9563 | prompt processing, n_tokens = 203, progress = 0.28, t = 14.37 s / 14.13 tokens per second 61.11.324.897 I slot print_timing: id 2 | task 9559 | prompt processing, n_tokens = 748, progress = 0.99, t = 18.51 s / 40.41 tokens per second 61.11.329.753 I slot print_timing: id 3 | task 9564 | prompt processing, n_tokens = 220, progress = 0.30, t = 14.37 s / 15.31 tokens per second 61.25.323.632 I slot print_timing: id 0 | task 9562 | prompt processing, n_tokens = 603, progress = 0.85, t = 28.48 s / 21.17 tokens per second 61.25.331.055 I slot print_timing: id 1 | task 9563 | prompt processing, n_tokens = 603, progress = 0.84, t = 28.48 s / 21.18 tokens per second 61.25.335.611 I slot print_timing: id 3 | task 9564 | prompt processing, n_tokens = 603, progress = 0.82, t = 28.47 s / 21.18 tokens per second 61.29.808.873 I slot print_timing: id 2 | task 9559 | prompt eval time = 32615.62 ms / 752 tokens ( 43.37 ms per token, 23.06 tokens per second) 61.29.808.876 I slot print_timing: id 2 | task 9559 | eval time = 4485.25 ms / 2 tokens ( 4485.25 ms per token, 0.22 tokens per second) 61.29.808.876 I slot print_timing: id 2 | task 9559 | total time = 37100.87 ms / 754 tokens 61.29.808.877 I slot print_timing: id 2 | task 9559 | graphs reused = 8265 61.29.808.877 I slot print_timing: id 2 | task 9559 | graph reallocs = 0 / 0 (same size) / (changed size) 61.29.809.784 I slot release: id 2 | task 9559 | stop processing: n_tokens = 753, truncated = 0 61.29.809.807 I slot print_timing: id 0 | task 9562 | prompt processing, n_tokens = 709, progress = 0.99, t = 32.96 s / 21.51 tokens per second 61.29.840.927 I slot print_timing: id 1 | task 9563 | prompt processing, n_tokens = 715, progress = 0.99, t = 32.96 s / 21.69 tokens per second 61.29.845.441 I slot print_timing: id 3 | task 9564 | prompt processing, n_tokens = 732, progress = 0.99, t = 32.96 s / 22.21 tokens per second 61.30.253.464 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 98057043343 61.30.253.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 61.30.372.589 I slot launch_slot_: id 2 | task 9570 | processing task, is_child = 0 61.32.148.255 I slot print_timing: id 0 | task 9562 | prompt eval time = 33406.64 ms / 713 tokens ( 46.85 ms per token, 21.34 tokens per second) 61.32.148.258 I slot print_timing: id 0 | task 9562 | eval time = 1895.23 ms / 2 tokens ( 1895.23 ms per token, 0.53 tokens per second) 61.32.148.259 I slot print_timing: id 0 | task 9562 | total time = 35301.86 ms / 715 tokens 61.32.148.259 I slot print_timing: id 0 | task 9562 | graphs reused = 8265 61.32.148.260 I slot print_timing: id 0 | task 9562 | graph reallocs = 0 / 0 (same size) / (changed size) 61.32.148.350 I slot release: id 0 | task 9562 | stop processing: n_tokens = 714, truncated = 0 61.32.148.581 I slot print_timing: id 1 | task 9563 | prompt eval time = 33406.74 ms / 719 tokens ( 46.46 ms per token, 21.52 tokens per second) 61.32.148.583 I slot print_timing: id 1 | task 9563 | eval time = 1895.38 ms / 2 tokens ( 1895.38 ms per token, 0.53 tokens per second) 61.32.148.585 I slot print_timing: id 1 | task 9563 | total time = 35302.12 ms / 721 tokens 61.32.148.585 I slot print_timing: id 1 | task 9563 | graphs reused = 8265 61.32.148.585 I slot print_timing: id 1 | task 9563 | graph reallocs = 0 / 0 (same size) / (changed size) 61.32.148.622 I slot release: id 1 | task 9563 | stop processing: n_tokens = 720, truncated = 0 61.32.148.861 I slot print_timing: id 3 | task 9564 | prompt eval time = 33402.44 ms / 736 tokens ( 45.38 ms per token, 22.03 tokens per second) 61.32.148.863 I slot print_timing: id 3 | task 9564 | eval time = 1895.40 ms / 2 tokens ( 1895.40 ms per token, 0.53 tokens per second) 61.32.148.864 I slot print_timing: id 3 | task 9564 | total time = 35297.84 ms / 738 tokens 61.32.148.864 I slot print_timing: id 3 | task 9564 | graphs reused = 8265 61.32.148.864 I slot print_timing: id 3 | task 9564 | graph reallocs = 0 / 0 (same size) / (changed size) 61.32.148.891 I slot release: id 3 | task 9564 | stop processing: n_tokens = 737, truncated = 0 61.32.159.267 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.884 61.32.159.302 I slot launch_slot_: id 0 | task 9573 | processing task, is_child = 0 61.32.159.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.775 MiB) 61.33.314.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 800.650 MiB) 61.33.419.911 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.876 61.33.419.979 I slot launch_slot_: id 1 | task 9574 | processing task, is_child = 0 61.33.420.024 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 61.33.420.048 I slot launch_slot_: id 3 | task 9575 | processing task, is_child = 0 61.38.801.126 I slot print_timing: id 0 | task 9573 | prompt processing, n_tokens = 100, progress = 0.99, t = 5.38 s / 18.58 tokens per second 61.42.446.554 I slot print_timing: id 1 | task 9574 | prompt processing, n_tokens = 102, progress = 0.99, t = 5.37 s / 18.98 tokens per second 61.42.456.366 I slot print_timing: id 2 | task 9570 | prompt processing, n_tokens = 603, progress = 0.85, t = 8.43 s / 71.54 tokens per second 61.42.484.119 I slot print_timing: id 3 | task 9575 | prompt processing, n_tokens = 108, progress = 0.99, t = 5.36 s / 20.14 tokens per second 61.44.340.078 I slot print_timing: id 2 | task 9570 | prompt processing, n_tokens = 706, progress = 0.99, t = 13.97 s / 50.55 tokens per second 61.44.824.082 I slot print_timing: id 0 | task 9573 | prompt eval time = 10919.58 ms / 104 tokens ( 105.00 ms per token, 9.52 tokens per second) 61.44.824.087 I slot print_timing: id 0 | task 9573 | eval time = 484.45 ms / 2 tokens ( 484.45 ms per token, 2.06 tokens per second) 61.44.824.087 I slot print_timing: id 0 | task 9573 | total time = 11404.02 ms / 106 tokens 61.44.824.088 I slot print_timing: id 0 | task 9573 | graphs reused = 8265 61.44.824.088 I slot print_timing: id 0 | task 9573 | graph reallocs = 0 / 0 (same size) / (changed size) 61.44.824.121 I slot release: id 0 | task 9573 | stop processing: n_tokens = 708, truncated = 0 61.44.824.357 I slot print_timing: id 1 | task 9574 | prompt eval time = 10912.12 ms / 106 tokens ( 102.94 ms per token, 9.71 tokens per second) 61.44.824.363 I slot print_timing: id 1 | task 9574 | eval time = 484.52 ms / 2 tokens ( 484.52 ms per token, 2.06 tokens per second) 61.44.824.363 I slot print_timing: id 1 | task 9574 | total time = 11396.64 ms / 108 tokens 61.44.824.364 I slot print_timing: id 1 | task 9574 | graphs reused = 8265 61.44.824.364 I slot print_timing: id 1 | task 9574 | graph reallocs = 0 / 0 (same size) / (changed size) 61.44.824.399 I slot release: id 1 | task 9574 | stop processing: n_tokens = 710, truncated = 0 61.44.825.347 I slot print_timing: id 3 | task 9575 | prompt eval time = 10900.39 ms / 112 tokens ( 97.32 ms per token, 10.27 tokens per second) 61.44.825.350 I slot print_timing: id 3 | task 9575 | eval time = 485.28 ms / 2 tokens ( 485.28 ms per token, 2.06 tokens per second) 61.44.825.353 I slot print_timing: id 3 | task 9575 | total time = 11385.66 ms / 114 tokens 61.44.825.353 I slot print_timing: id 3 | task 9575 | graphs reused = 8265 61.44.825.353 I slot print_timing: id 3 | task 9575 | graph reallocs = 0 / 0 (same size) / (changed size) 61.44.825.394 I slot release: id 3 | task 9575 | stop processing: n_tokens = 716, truncated = 0 61.44.936.234 I slot print_timing: id 2 | task 9570 | prompt eval time = 14452.38 ms / 710 tokens ( 20.36 ms per token, 49.13 tokens per second) 61.44.936.236 I slot print_timing: id 2 | task 9570 | eval time = 111.25 ms / 2 tokens ( 111.25 ms per token, 8.99 tokens per second) 61.44.936.237 I slot print_timing: id 2 | task 9570 | total time = 14563.63 ms / 712 tokens 61.44.936.237 I slot print_timing: id 2 | task 9570 | graphs reused = 8265 61.44.936.237 I slot print_timing: id 2 | task 9570 | graph reallocs = 0 / 0 (same size) / (changed size) 61.44.937.304 I slot release: id 2 | task 9570 | stop processing: n_tokens = 711, truncated = 0 61.44.937.316 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 61.44.937.385 I slot launch_slot_: id 0 | task 9580 | processing task, is_child = 0 61.44.937.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.089 MiB) 61.44.988.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.527 MiB) 61.45.030.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.088 MiB) 61.45.088.397 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 61.45.088.461 I slot launch_slot_: id 1 | task 9581 | processing task, is_child = 0 61.45.088.543 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 61.45.088.567 I slot launch_slot_: id 2 | task 9582 | processing task, is_child = 0 61.45.088.612 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 61.45.088.631 I slot launch_slot_: id 3 | task 9583 | processing task, is_child = 0 61.50.579.948 I slot print_timing: id 0 | task 9580 | prompt processing, n_tokens = 109, progress = 0.99, t = 5.49 s / 19.85 tokens per second 61.51.347.230 I slot print_timing: id 1 | task 9581 | prompt processing, n_tokens = 110, progress = 0.99, t = 5.48 s / 20.06 tokens per second 61.51.351.926 I slot print_timing: id 2 | task 9582 | prompt processing, n_tokens = 144, progress = 0.99, t = 5.48 s / 26.30 tokens per second 61.51.356.658 I slot print_timing: id 3 | task 9583 | prompt processing, n_tokens = 102, progress = 0.99, t = 5.46 s / 18.67 tokens per second 61.51.951.900 I slot print_timing: id 0 | task 9580 | prompt eval time = 6651.10 ms / 113 tokens ( 58.86 ms per token, 16.99 tokens per second) 61.51.951.905 I slot print_timing: id 0 | task 9580 | eval time = 212.16 ms / 2 tokens ( 212.16 ms per token, 4.71 tokens per second) 61.51.951.906 I slot print_timing: id 0 | task 9580 | total time = 6863.26 ms / 115 tokens 61.51.951.906 I slot print_timing: id 0 | task 9580 | graphs reused = 8265 61.51.951.906 I slot print_timing: id 0 | task 9580 | graph reallocs = 0 / 0 (same size) / (changed size) 61.51.952.257 I slot release: id 0 | task 9580 | stop processing: n_tokens = 717, truncated = 0 61.51.952.409 I slot print_timing: id 1 | task 9581 | prompt eval time = 6643.64 ms / 114 tokens ( 58.28 ms per token, 17.16 tokens per second) 61.51.952.411 I slot print_timing: id 1 | task 9581 | eval time = 212.49 ms / 2 tokens ( 212.49 ms per token, 4.71 tokens per second) 61.51.952.415 I slot print_timing: id 1 | task 9581 | total time = 6856.14 ms / 116 tokens 61.51.952.416 I slot print_timing: id 1 | task 9581 | graphs reused = 8265 61.51.952.416 I slot print_timing: id 1 | task 9581 | graph reallocs = 0 / 0 (same size) / (changed size) 61.51.952.873 I slot release: id 1 | task 9581 | stop processing: n_tokens = 718, truncated = 0 61.51.953.171 I slot print_timing: id 2 | task 9582 | prompt eval time = 6636.25 ms / 148 tokens ( 44.84 ms per token, 22.30 tokens per second) 61.51.953.176 I slot print_timing: id 2 | task 9582 | eval time = 213.06 ms / 2 tokens ( 213.06 ms per token, 4.69 tokens per second) 61.51.953.176 I slot print_timing: id 2 | task 9582 | total time = 6849.31 ms / 150 tokens 61.51.953.177 I slot print_timing: id 2 | task 9582 | graphs reused = 8265 61.51.953.177 I slot print_timing: id 2 | task 9582 | graph reallocs = 0 / 0 (same size) / (changed size) 61.51.953.210 I slot release: id 2 | task 9582 | stop processing: n_tokens = 752, truncated = 0 61.51.953.485 I slot print_timing: id 3 | task 9583 | prompt eval time = 6624.67 ms / 106 tokens ( 62.50 ms per token, 16.00 tokens per second) 61.51.953.489 I slot print_timing: id 3 | task 9583 | eval time = 213.16 ms / 2 tokens ( 213.16 ms per token, 4.69 tokens per second) 61.51.953.490 I slot print_timing: id 3 | task 9583 | total time = 6837.84 ms / 108 tokens 61.51.953.490 I slot print_timing: id 3 | task 9583 | graphs reused = 8265 61.51.953.490 I slot print_timing: id 3 | task 9583 | graph reallocs = 0 / 0 (same size) / (changed size) 61.51.953.527 I slot release: id 3 | task 9583 | stop processing: n_tokens = 710, truncated = 0 61.51.964.710 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 98079185815 61.51.964.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 791.209 MiB) 61.52.003.606 I slot launch_slot_: id 0 | task 9587 | processing task, is_child = 0 61.52.003.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.274 MiB) 61.52.039.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 61.52.074.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.401 MiB) 61.52.122.233 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 98079186436 61.52.122.329 I slot launch_slot_: id 1 | task 9588 | processing task, is_child = 0 61.52.122.412 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 98079186768 61.52.122.476 I slot launch_slot_: id 2 | task 9589 | processing task, is_child = 0 61.52.122.524 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 98079187085 61.52.122.582 I slot launch_slot_: id 3 | task 9590 | processing task, is_child = 0 62.00.491.301 I slot print_timing: id 0 | task 9587 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.37 s / 21.51 tokens per second 62.00.682.562 I slot print_timing: id 1 | task 9588 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.37 s / 21.51 tokens per second 62.00.691.551 I slot print_timing: id 2 | task 9589 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.37 s / 21.87 tokens per second 62.00.706.622 I slot print_timing: id 3 | task 9590 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.37 s / 21.87 tokens per second 62.06.198.739 I slot print_timing: id 0 | task 9587 | prompt processing, n_tokens = 296, progress = 0.34, t = 14.08 s / 21.03 tokens per second 62.06.198.753 I slot print_timing: id 1 | task 9588 | prompt processing, n_tokens = 296, progress = 0.33, t = 14.08 s / 21.03 tokens per second 62.06.198.760 I slot print_timing: id 2 | task 9589 | prompt processing, n_tokens = 364, progress = 0.34, t = 14.08 s / 25.86 tokens per second 62.06.198.773 I slot print_timing: id 3 | task 9590 | prompt processing, n_tokens = 364, progress = 0.33, t = 14.08 s / 25.86 tokens per second 62.15.126.677 I slot print_timing: id 0 | task 9587 | prompt processing, n_tokens = 364, progress = 0.41, t = 23.00 s / 15.82 tokens per second 62.15.432.353 I slot print_timing: id 1 | task 9588 | prompt processing, n_tokens = 380, progress = 0.42, t = 23.00 s / 16.52 tokens per second 62.15.442.775 I slot print_timing: id 2 | task 9589 | prompt processing, n_tokens = 566, progress = 0.52, t = 23.00 s / 24.60 tokens per second 62.15.475.918 I slot print_timing: id 3 | task 9590 | prompt processing, n_tokens = 575, progress = 0.53, t = 23.00 s / 25.00 tokens per second 62.32.426.627 I slot print_timing: id 0 | task 9587 | prompt processing, n_tokens = 762, progress = 0.87, t = 40.30 s / 18.91 tokens per second 62.32.748.015 I slot print_timing: id 1 | task 9588 | prompt processing, n_tokens = 762, progress = 0.85, t = 40.30 s / 18.91 tokens per second 62.32.753.939 I slot print_timing: id 2 | task 9589 | prompt processing, n_tokens = 905, progress = 0.84, t = 40.30 s / 22.45 tokens per second 62.32.768.288 I slot print_timing: id 3 | task 9590 | prompt processing, n_tokens = 905, progress = 0.83, t = 40.30 s / 22.45 tokens per second 62.40.291.508 I slot print_timing: id 0 | task 9587 | prompt processing, n_tokens = 876, progress = 1.00, t = 48.17 s / 18.19 tokens per second 62.40.599.048 I slot print_timing: id 1 | task 9588 | prompt processing, n_tokens = 892, progress = 1.00, t = 48.17 s / 18.52 tokens per second 62.40.611.314 I slot print_timing: id 2 | task 9589 | prompt processing, n_tokens = 1078, progress = 1.00, t = 48.17 s / 22.38 tokens per second 62.40.615.935 I slot print_timing: id 3 | task 9590 | prompt processing, n_tokens = 1087, progress = 1.00, t = 48.17 s / 22.57 tokens per second 62.41.213.795 I slot print_timing: id 0 | task 9587 | prompt eval time = 48878.46 ms / 880 tokens ( 55.54 ms per token, 18.00 tokens per second) 62.41.213.799 I slot print_timing: id 0 | task 9587 | eval time = 212.74 ms / 2 tokens ( 212.74 ms per token, 4.70 tokens per second) 62.41.213.800 I slot print_timing: id 0 | task 9587 | total time = 49091.20 ms / 882 tokens 62.41.213.800 I slot print_timing: id 0 | task 9587 | graphs reused = 8265 62.41.213.801 I slot print_timing: id 0 | task 9587 | graph reallocs = 0 / 0 (same size) / (changed size) 62.41.215.136 I slot release: id 0 | task 9587 | stop processing: n_tokens = 881, truncated = 0 62.41.215.433 I slot print_timing: id 1 | task 9588 | prompt eval time = 48878.60 ms / 896 tokens ( 54.55 ms per token, 18.33 tokens per second) 62.41.215.442 I slot print_timing: id 1 | task 9588 | eval time = 214.18 ms / 2 tokens ( 214.18 ms per token, 4.67 tokens per second) 62.41.215.443 I slot print_timing: id 1 | task 9588 | total time = 49092.77 ms / 898 tokens 62.41.215.443 I slot print_timing: id 1 | task 9588 | graphs reused = 8265 62.41.215.443 I slot print_timing: id 1 | task 9588 | graph reallocs = 0 / 0 (same size) / (changed size) 62.41.215.503 I slot release: id 1 | task 9588 | stop processing: n_tokens = 897, truncated = 0 62.41.215.843 I slot print_timing: id 2 | task 9589 | prompt eval time = 48878.76 ms / 1082 tokens ( 45.17 ms per token, 22.14 tokens per second) 62.41.215.844 I slot print_timing: id 2 | task 9589 | eval time = 214.37 ms / 2 tokens ( 214.37 ms per token, 4.66 tokens per second) 62.41.215.845 I slot print_timing: id 2 | task 9589 | total time = 49093.13 ms / 1084 tokens 62.41.215.845 I slot print_timing: id 2 | task 9589 | graphs reused = 8265 62.41.215.856 I slot print_timing: id 2 | task 9589 | graph reallocs = 0 / 0 (same size) / (changed size) 62.41.215.958 I slot release: id 2 | task 9589 | stop processing: n_tokens = 1083, truncated = 0 62.41.216.273 I slot print_timing: id 3 | task 9590 | prompt eval time = 48878.90 ms / 1091 tokens ( 44.80 ms per token, 22.32 tokens per second) 62.41.216.278 I slot print_timing: id 3 | task 9590 | eval time = 214.60 ms / 2 tokens ( 214.60 ms per token, 4.66 tokens per second) 62.41.216.278 I slot print_timing: id 3 | task 9590 | total time = 49093.50 ms / 1093 tokens 62.41.216.278 I slot print_timing: id 3 | task 9590 | graphs reused = 8265 62.41.216.279 I slot print_timing: id 3 | task 9590 | graph reallocs = 0 / 0 (same size) / (changed size) 62.41.216.342 I slot release: id 3 | task 9590 | stop processing: n_tokens = 1092, truncated = 0 62.41.230.088 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.895 62.41.230.117 I slot launch_slot_: id 3 | task 9599 | processing task, is_child = 0 62.41.230.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.211 MiB) 62.41.407.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 62.41.496.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 62.41.642.662 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.901 62.41.642.736 I slot launch_slot_: id 2 | task 9598 | processing task, is_child = 0 62.41.642.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 98128448694 62.41.649.069 I slot launch_slot_: id 0 | task 9600 | processing task, is_child = 0 62.41.649.121 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 98128449060 62.41.649.181 I slot launch_slot_: id 1 | task 9601 | processing task, is_child = 0 62.50.071.759 I slot print_timing: id 0 | task 9600 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.42 s / 20.18 tokens per second 62.50.391.450 I slot print_timing: id 1 | task 9601 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.41 s / 21.75 tokens per second 62.50.400.327 I slot print_timing: id 2 | task 9598 | prompt processing, n_tokens = 162, progress = 1.00, t = 8.41 s / 19.26 tokens per second 62.50.405.549 I slot print_timing: id 3 | task 9599 | prompt processing, n_tokens = 176, progress = 1.00, t = 8.40 s / 20.94 tokens per second 62.52.991.658 I slot print_timing: id 1 | task 9601 | prompt processing, n_tokens = 364, progress = 0.34, t = 11.33 s / 32.12 tokens per second 62.55.921.909 I slot print_timing: id 0 | task 9600 | prompt eval time = 11341.86 ms / 174 tokens ( 65.18 ms per token, 15.34 tokens per second) 62.55.921.912 I slot print_timing: id 0 | task 9600 | eval time = 2930.85 ms / 2 tokens ( 2930.85 ms per token, 0.34 tokens per second) 62.55.921.912 I slot print_timing: id 0 | task 9600 | total time = 14272.71 ms / 176 tokens 62.55.921.913 I slot print_timing: id 0 | task 9600 | graphs reused = 8265 62.55.921.913 I slot print_timing: id 0 | task 9600 | graph reallocs = 0 / 0 (same size) / (changed size) 62.55.921.983 I slot release: id 0 | task 9600 | stop processing: n_tokens = 1080, truncated = 0 62.55.922.212 I slot print_timing: id 2 | task 9598 | prompt eval time = 11331.58 ms / 166 tokens ( 68.26 ms per token, 14.65 tokens per second) 62.55.922.215 I slot print_timing: id 2 | task 9598 | eval time = 2930.81 ms / 2 tokens ( 2930.81 ms per token, 0.34 tokens per second) 62.55.922.215 I slot print_timing: id 2 | task 9598 | total time = 14262.39 ms / 168 tokens 62.55.922.216 I slot print_timing: id 2 | task 9598 | graphs reused = 8265 62.55.922.216 I slot print_timing: id 2 | task 9598 | graph reallocs = 0 / 0 (same size) / (changed size) 62.55.922.268 I slot release: id 2 | task 9598 | stop processing: n_tokens = 1072, truncated = 0 62.55.922.496 I slot print_timing: id 3 | task 9599 | prompt eval time = 11324.05 ms / 180 tokens ( 62.91 ms per token, 15.90 tokens per second) 62.55.922.498 I slot print_timing: id 3 | task 9599 | eval time = 2930.85 ms / 2 tokens ( 2930.85 ms per token, 0.34 tokens per second) 62.55.922.499 I slot print_timing: id 3 | task 9599 | total time = 14254.89 ms / 182 tokens 62.55.922.499 I slot print_timing: id 3 | task 9599 | graphs reused = 8265 62.55.922.499 I slot print_timing: id 3 | task 9599 | graph reallocs = 0 / 0 (same size) / (changed size) 62.55.922.536 I slot release: id 3 | task 9599 | stop processing: n_tokens = 1086, truncated = 0 62.55.922.545 I slot print_timing: id 1 | task 9601 | prompt processing, n_tokens = 564, progress = 0.52, t = 14.26 s / 39.55 tokens per second 62.55.934.528 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.905 62.55.934.563 I slot launch_slot_: id 0 | task 9606 | processing task, is_child = 0 62.59.972.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 63.00.115.316 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.911 63.00.115.397 I slot launch_slot_: id 2 | task 9607 | processing task, is_child = 0 63.00.115.461 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.900 63.00.115.498 I slot launch_slot_: id 3 | task 9608 | processing task, is_child = 0 63.00.123.117 I slot print_timing: id 1 | task 9601 | prompt processing, n_tokens = 905, progress = 0.84, t = 14.27 s / 63.40 tokens per second 63.08.400.606 I slot print_timing: id 0 | task 9606 | prompt processing, n_tokens = 173, progress = 1.00, t = 8.29 s / 20.88 tokens per second 63.08.722.166 I slot print_timing: id 1 | task 9601 | prompt processing, n_tokens = 1076, progress = 1.00, t = 26.74 s / 40.24 tokens per second 63.08.726.677 I slot print_timing: id 2 | task 9607 | prompt processing, n_tokens = 164, progress = 1.00, t = 8.27 s / 19.82 tokens per second 63.08.731.265 I slot print_timing: id 3 | task 9608 | prompt processing, n_tokens = 179, progress = 1.00, t = 8.27 s / 21.66 tokens per second 63.09.329.557 I slot print_timing: id 0 | task 9606 | prompt eval time = 9001.72 ms / 177 tokens ( 50.86 ms per token, 19.66 tokens per second) 63.09.329.560 I slot print_timing: id 0 | task 9606 | eval time = 212.32 ms / 2 tokens ( 212.32 ms per token, 4.71 tokens per second) 63.09.329.561 I slot print_timing: id 0 | task 9606 | total time = 9214.04 ms / 179 tokens 63.09.329.561 I slot print_timing: id 0 | task 9606 | graphs reused = 8265 63.09.329.562 I slot print_timing: id 0 | task 9606 | graph reallocs = 0 / 0 (same size) / (changed size) 63.09.329.614 I slot release: id 0 | task 9606 | stop processing: n_tokens = 1083, truncated = 0 63.09.329.762 I slot print_timing: id 1 | task 9601 | prompt eval time = 27457.63 ms / 1080 tokens ( 25.42 ms per token, 39.33 tokens per second) 63.09.329.764 I slot print_timing: id 1 | task 9601 | eval time = 212.38 ms / 2 tokens ( 212.38 ms per token, 4.71 tokens per second) 63.09.329.765 I slot print_timing: id 1 | task 9601 | total time = 27670.00 ms / 1082 tokens 63.09.329.779 I slot print_timing: id 1 | task 9601 | graphs reused = 8265 63.09.329.781 I slot print_timing: id 1 | task 9601 | graph reallocs = 0 / 0 (same size) / (changed size) 63.09.329.824 I slot release: id 1 | task 9601 | stop processing: n_tokens = 1081, truncated = 0 63.09.329.982 I slot print_timing: id 2 | task 9607 | prompt eval time = 8989.97 ms / 168 tokens ( 53.51 ms per token, 18.69 tokens per second) 63.09.329.983 I slot print_timing: id 2 | task 9607 | eval time = 212.44 ms / 2 tokens ( 212.44 ms per token, 4.71 tokens per second) 63.09.329.984 I slot print_timing: id 2 | task 9607 | total time = 9202.41 ms / 170 tokens 63.09.329.984 I slot print_timing: id 2 | task 9607 | graphs reused = 8265 63.09.329.984 I slot print_timing: id 2 | task 9607 | graph reallocs = 0 / 0 (same size) / (changed size) 63.09.330.021 I slot release: id 2 | task 9607 | stop processing: n_tokens = 1074, truncated = 0 63.09.330.179 I slot print_timing: id 3 | task 9608 | prompt eval time = 8982.42 ms / 183 tokens ( 49.08 ms per token, 20.37 tokens per second) 63.09.330.181 I slot print_timing: id 3 | task 9608 | eval time = 212.47 ms / 2 tokens ( 212.47 ms per token, 4.71 tokens per second) 63.09.330.181 I slot print_timing: id 3 | task 9608 | total time = 9194.89 ms / 185 tokens 63.09.330.181 I slot print_timing: id 3 | task 9608 | graphs reused = 8265 63.09.330.182 I slot print_timing: id 3 | task 9608 | graph reallocs = 0 / 0 (same size) / (changed size) 63.09.330.215 I slot release: id 3 | task 9608 | stop processing: n_tokens = 1089, truncated = 0 63.09.342.056 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.902 63.09.342.085 I slot launch_slot_: id 0 | task 9612 | processing task, is_child = 0 63.09.342.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.585 MiB) 63.09.444.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.897 MiB) 63.09.589.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 63.10.364.434 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.904 63.10.364.619 I slot launch_slot_: id 1 | task 9613 | processing task, is_child = 0 63.10.364.784 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.910 63.10.364.814 I slot launch_slot_: id 2 | task 9614 | processing task, is_child = 0 63.10.364.868 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.897 63.10.364.887 I slot launch_slot_: id 3 | task 9615 | processing task, is_child = 0 63.18.615.905 I slot print_timing: id 0 | task 9612 | prompt processing, n_tokens = 171, progress = 1.00, t = 8.25 s / 20.72 tokens per second 63.18.797.545 I slot print_timing: id 1 | task 9613 | prompt processing, n_tokens = 166, progress = 1.00, t = 8.20 s / 20.24 tokens per second 63.18.836.241 I slot print_timing: id 2 | task 9614 | prompt processing, n_tokens = 167, progress = 1.00, t = 8.18 s / 20.41 tokens per second 63.18.864.053 I slot print_timing: id 3 | task 9615 | prompt processing, n_tokens = 174, progress = 1.00, t = 8.16 s / 21.32 tokens per second 63.19.468.192 I slot print_timing: id 0 | task 9612 | prompt eval time = 8888.44 ms / 175 tokens ( 50.79 ms per token, 19.69 tokens per second) 63.19.468.195 I slot print_timing: id 0 | task 9612 | eval time = 214.85 ms / 2 tokens ( 214.85 ms per token, 4.65 tokens per second) 63.19.468.195 I slot print_timing: id 0 | task 9612 | total time = 9103.29 ms / 177 tokens 63.19.468.196 I slot print_timing: id 0 | task 9612 | graphs reused = 8265 63.19.468.196 I slot print_timing: id 0 | task 9612 | graph reallocs = 0 / 0 (same size) / (changed size) 63.19.468.421 I slot release: id 0 | task 9612 | stop processing: n_tokens = 1081, truncated = 0 63.19.468.847 I slot print_timing: id 1 | task 9613 | prompt eval time = 8840.10 ms / 170 tokens ( 52.00 ms per token, 19.23 tokens per second) 63.19.468.849 I slot print_timing: id 1 | task 9613 | eval time = 214.94 ms / 2 tokens ( 214.94 ms per token, 4.65 tokens per second) 63.19.468.849 I slot print_timing: id 1 | task 9613 | total time = 9055.04 ms / 172 tokens 63.19.468.850 I slot print_timing: id 1 | task 9613 | graphs reused = 8265 63.19.468.850 I slot print_timing: id 1 | task 9613 | graph reallocs = 0 / 0 (same size) / (changed size) 63.19.468.885 I slot release: id 1 | task 9613 | stop processing: n_tokens = 1076, truncated = 0 63.19.469.446 I slot print_timing: id 2 | task 9614 | prompt eval time = 8819.86 ms / 171 tokens ( 51.58 ms per token, 19.39 tokens per second) 63.19.469.451 I slot print_timing: id 2 | task 9614 | eval time = 214.54 ms / 2 tokens ( 214.54 ms per token, 4.66 tokens per second) 63.19.469.451 I slot print_timing: id 2 | task 9614 | total time = 9034.40 ms / 173 tokens 63.19.469.452 I slot print_timing: id 2 | task 9614 | graphs reused = 8265 63.19.469.452 I slot print_timing: id 2 | task 9614 | graph reallocs = 0 / 0 (same size) / (changed size) 63.19.469.491 I slot release: id 2 | task 9614 | stop processing: n_tokens = 1077, truncated = 0 63.19.469.815 I slot print_timing: id 3 | task 9615 | prompt eval time = 8801.59 ms / 178 tokens ( 49.45 ms per token, 20.22 tokens per second) 63.19.469.817 I slot print_timing: id 3 | task 9615 | eval time = 214.28 ms / 2 tokens ( 214.28 ms per token, 4.67 tokens per second) 63.19.469.818 I slot print_timing: id 3 | task 9615 | total time = 9015.87 ms / 180 tokens 63.19.469.818 I slot print_timing: id 3 | task 9615 | graphs reused = 8265 63.19.469.818 I slot print_timing: id 3 | task 9615 | graph reallocs = 0 / 0 (same size) / (changed size) 63.19.469.897 I slot release: id 3 | task 9615 | stop processing: n_tokens = 1084, truncated = 0 63.19.490.369 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.904 63.19.490.398 I slot launch_slot_: id 0 | task 9619 | processing task, is_child = 0 63.19.490.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.022 MiB) 63.19.997.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.148 MiB) 63.20.191.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 63.20.384.206 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.908 63.20.384.278 I slot launch_slot_: id 1 | task 9620 | processing task, is_child = 0 63.20.384.389 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1077, t_last = 98166703048 63.20.384.466 I slot launch_slot_: id 2 | task 9621 | processing task, is_child = 0 63.20.384.525 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1084, t_last = 98166703455 63.20.384.604 I slot launch_slot_: id 3 | task 9622 | processing task, is_child = 0 63.28.681.285 I slot print_timing: id 0 | task 9619 | prompt processing, n_tokens = 169, progress = 1.00, t = 8.30 s / 20.37 tokens per second 63.29.852.655 I slot print_timing: id 1 | task 9620 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.26 s / 20.57 tokens per second 63.29.865.112 I slot print_timing: id 2 | task 9621 | prompt processing, n_tokens = 210, progress = 0.21, t = 8.25 s / 25.45 tokens per second 63.29.877.323 I slot print_timing: id 3 | task 9622 | prompt processing, n_tokens = 210, progress = 0.20, t = 8.25 s / 25.45 tokens per second 63.34.610.469 I slot print_timing: id 2 | task 9621 | prompt processing, n_tokens = 393, progress = 0.39, t = 14.18 s / 27.71 tokens per second 63.34.610.482 I slot print_timing: id 3 | task 9622 | prompt processing, n_tokens = 393, progress = 0.38, t = 14.18 s / 27.71 tokens per second 63.37.737.503 I slot print_timing: id 0 | task 9619 | prompt eval time = 14225.37 ms / 173 tokens ( 82.23 ms per token, 12.16 tokens per second) 63.37.737.506 I slot print_timing: id 0 | task 9619 | eval time = 3127.52 ms / 2 tokens ( 3127.52 ms per token, 0.32 tokens per second) 63.37.737.507 I slot print_timing: id 0 | task 9619 | total time = 17352.89 ms / 175 tokens 63.37.737.507 I slot print_timing: id 0 | task 9619 | graphs reused = 8265 63.37.737.508 I slot print_timing: id 0 | task 9619 | graph reallocs = 0 / 0 (same size) / (changed size) 63.37.737.613 I slot release: id 0 | task 9619 | stop processing: n_tokens = 1079, truncated = 0 63.37.738.019 I slot print_timing: id 1 | task 9620 | prompt eval time = 14193.62 ms / 174 tokens ( 81.57 ms per token, 12.26 tokens per second) 63.37.738.022 I slot print_timing: id 1 | task 9620 | eval time = 3127.56 ms / 2 tokens ( 3127.56 ms per token, 0.32 tokens per second) 63.37.738.022 I slot print_timing: id 1 | task 9620 | total time = 17321.18 ms / 176 tokens 63.37.738.022 I slot print_timing: id 1 | task 9620 | graphs reused = 8265 63.37.738.023 I slot print_timing: id 1 | task 9620 | graph reallocs = 0 / 0 (same size) / (changed size) 63.37.738.059 I slot release: id 1 | task 9620 | stop processing: n_tokens = 1080, truncated = 0 63.37.738.067 I slot print_timing: id 2 | task 9621 | prompt processing, n_tokens = 501, progress = 0.49, t = 17.31 s / 28.94 tokens per second 63.37.755.701 I slot print_timing: id 3 | task 9622 | prompt processing, n_tokens = 515, progress = 0.50, t = 17.31 s / 29.75 tokens per second 63.46.173.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 98184971171 63.46.173.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 63.46.496.986 I slot launch_slot_: id 0 | task 9627 | processing task, is_child = 0 63.46.497.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 63.46.676.590 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 98184971616 63.46.676.707 I slot launch_slot_: id 1 | task 9628 | processing task, is_child = 0 63.46.676.894 I slot print_timing: id 2 | task 9621 | prompt processing, n_tokens = 878, progress = 0.86, t = 25.74 s / 34.10 tokens per second 63.46.681.320 I slot print_timing: id 3 | task 9622 | prompt processing, n_tokens = 878, progress = 0.85, t = 25.74 s / 34.10 tokens per second 63.54.821.678 I slot print_timing: id 0 | task 9627 | prompt processing, n_tokens = 210, progress = 0.20, t = 8.14 s / 25.78 tokens per second 63.55.140.093 I slot print_timing: id 1 | task 9628 | prompt processing, n_tokens = 210, progress = 0.19, t = 8.14 s / 25.78 tokens per second 63.55.152.241 I slot print_timing: id 2 | task 9621 | prompt processing, n_tokens = 1013, progress = 1.00, t = 34.39 s / 29.45 tokens per second 63.55.156.759 I slot print_timing: id 3 | task 9622 | prompt processing, n_tokens = 1027, progress = 1.00, t = 34.39 s / 29.86 tokens per second 63.59.887.539 I slot print_timing: id 0 | task 9627 | prompt processing, n_tokens = 393, progress = 0.37, t = 13.21 s / 29.75 tokens per second 63.59.887.550 I slot print_timing: id 1 | task 9628 | prompt processing, n_tokens = 393, progress = 0.36, t = 13.21 s / 29.75 tokens per second 64.04.869.659 I slot print_timing: id 2 | task 9621 | prompt eval time = 39459.00 ms / 1017 tokens ( 38.80 ms per token, 25.77 tokens per second) 64.04.869.662 I slot print_timing: id 2 | task 9621 | eval time = 4982.36 ms / 2 tokens ( 4982.36 ms per token, 0.20 tokens per second) 64.04.869.668 I slot print_timing: id 2 | task 9621 | total time = 44441.36 ms / 1019 tokens 64.04.869.669 I slot print_timing: id 2 | task 9621 | graphs reused = 8265 64.04.869.669 I slot print_timing: id 2 | task 9621 | graph reallocs = 0 / 0 (same size) / (changed size) 64.04.871.605 I slot release: id 2 | task 9621 | stop processing: n_tokens = 1018, truncated = 0 64.04.872.059 I slot print_timing: id 3 | task 9622 | prompt eval time = 39459.14 ms / 1031 tokens ( 38.27 ms per token, 26.13 tokens per second) 64.04.872.062 I slot print_timing: id 3 | task 9622 | eval time = 4984.53 ms / 2 tokens ( 4984.53 ms per token, 0.20 tokens per second) 64.04.872.063 I slot print_timing: id 3 | task 9622 | total time = 44443.67 ms / 1033 tokens 64.04.872.063 I slot print_timing: id 3 | task 9622 | graphs reused = 8265 64.04.872.063 I slot print_timing: id 3 | task 9622 | graph reallocs = 0 / 0 (same size) / (changed size) 64.04.872.136 I slot release: id 3 | task 9622 | stop processing: n_tokens = 1032, truncated = 0 64.04.872.161 I slot print_timing: id 0 | task 9627 | prompt processing, n_tokens = 555, progress = 0.52, t = 18.19 s / 30.51 tokens per second 64.04.885.118 I slot print_timing: id 1 | task 9628 | prompt processing, n_tokens = 590, progress = 0.53, t = 18.19 s / 32.43 tokens per second 64.11.470.806 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.890 64.11.470.885 I slot launch_slot_: id 2 | task 9633 | processing task, is_child = 0 64.11.470.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 64.12.240.601 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.878 64.12.240.684 I slot launch_slot_: id 3 | task 9634 | processing task, is_child = 0 64.12.240.695 I slot print_timing: id 0 | task 9627 | prompt processing, n_tokens = 878, progress = 0.82, t = 24.79 s / 35.41 tokens per second 64.12.255.181 I slot print_timing: id 1 | task 9628 | prompt processing, n_tokens = 878, progress = 0.79, t = 24.79 s / 35.41 tokens per second 64.21.249.489 I slot print_timing: id 0 | task 9627 | prompt processing, n_tokens = 1067, progress = 1.00, t = 34.57 s / 30.86 tokens per second 64.21.570.506 I slot print_timing: id 1 | task 9628 | prompt processing, n_tokens = 1102, progress = 1.00, t = 34.57 s / 31.87 tokens per second 64.21.575.475 I slot print_timing: id 2 | task 9633 | prompt processing, n_tokens = 148, progress = 1.00, t = 8.98 s / 16.48 tokens per second 64.21.591.048 I slot print_timing: id 3 | task 9634 | prompt processing, n_tokens = 163, progress = 1.00, t = 8.97 s / 18.17 tokens per second 64.22.407.722 I slot print_timing: id 0 | task 9627 | prompt eval time = 35509.60 ms / 1071 tokens ( 33.16 ms per token, 30.16 tokens per second) 64.22.407.730 I slot print_timing: id 0 | task 9627 | eval time = 221.35 ms / 2 tokens ( 221.35 ms per token, 4.52 tokens per second) 64.22.407.731 I slot print_timing: id 0 | task 9627 | total time = 35730.95 ms / 1073 tokens 64.22.407.732 I slot print_timing: id 0 | task 9627 | graphs reused = 8265 64.22.407.741 I slot print_timing: id 0 | task 9627 | graph reallocs = 0 / 0 (same size) / (changed size) 64.22.409.034 I slot release: id 0 | task 9627 | stop processing: n_tokens = 1072, truncated = 0 64.22.409.936 I slot print_timing: id 1 | task 9628 | prompt eval time = 35510.90 ms / 1106 tokens ( 32.11 ms per token, 31.15 tokens per second) 64.22.409.942 I slot print_timing: id 1 | task 9628 | eval time = 222.21 ms / 2 tokens ( 222.21 ms per token, 4.50 tokens per second) 64.22.409.943 I slot print_timing: id 1 | task 9628 | total time = 35733.11 ms / 1108 tokens 64.22.409.944 I slot print_timing: id 1 | task 9628 | graphs reused = 8265 64.22.409.945 I slot print_timing: id 1 | task 9628 | graph reallocs = 0 / 0 (same size) / (changed size) 64.22.411.483 I slot release: id 1 | task 9628 | stop processing: n_tokens = 1107, truncated = 0 64.22.412.268 I slot print_timing: id 2 | task 9633 | prompt eval time = 9919.21 ms / 152 tokens ( 65.26 ms per token, 15.32 tokens per second) 64.22.412.278 I slot print_timing: id 2 | task 9633 | eval time = 222.94 ms / 2 tokens ( 222.94 ms per token, 4.49 tokens per second) 64.22.412.280 I slot print_timing: id 2 | task 9633 | total time = 10142.15 ms / 154 tokens 64.22.412.282 I slot print_timing: id 2 | task 9633 | graphs reused = 8265 64.22.412.284 I slot print_timing: id 2 | task 9633 | graph reallocs = 0 / 0 (same size) / (changed size) 64.22.413.269 I slot release: id 2 | task 9633 | stop processing: n_tokens = 1031, truncated = 0 64.22.414.618 I slot print_timing: id 3 | task 9634 | prompt eval time = 9912.29 ms / 167 tokens ( 59.36 ms per token, 16.85 tokens per second) 64.22.414.623 I slot print_timing: id 3 | task 9634 | eval time = 224.22 ms / 2 tokens ( 224.22 ms per token, 4.46 tokens per second) 64.22.414.624 I slot print_timing: id 3 | task 9634 | total time = 10136.51 ms / 169 tokens 64.22.414.625 I slot print_timing: id 3 | task 9634 | graphs reused = 8265 64.22.414.626 I slot print_timing: id 3 | task 9634 | graph reallocs = 0 / 0 (same size) / (changed size) 64.22.414.750 I slot release: id 3 | task 9634 | stop processing: n_tokens = 1046, truncated = 0 64.22.435.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 98229642594 64.22.435.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.031 MiB) 64.22.883.720 I slot launch_slot_: id 0 | task 9638 | processing task, is_child = 0 64.22.883.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.718 MiB) 64.23.174.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.281 MiB) 64.23.478.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.218 MiB) 64.23.758.486 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 98229645043 64.23.758.625 I slot launch_slot_: id 1 | task 9639 | processing task, is_child = 0 64.23.758.727 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 98229646828 64.23.758.805 I slot launch_slot_: id 2 | task 9640 | processing task, is_child = 0 64.23.758.857 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 98229648307 64.23.758.925 I slot launch_slot_: id 3 | task 9641 | processing task, is_child = 0 64.29.560.261 I slot print_timing: id 0 | task 9638 | prompt processing, n_tokens = 136, progress = 0.19, t = 5.80 s / 23.44 tokens per second 64.30.027.048 I slot print_timing: id 1 | task 9639 | prompt processing, n_tokens = 136, progress = 0.18, t = 5.80 s / 23.44 tokens per second 64.30.039.370 I slot print_timing: id 2 | task 9640 | prompt processing, n_tokens = 136, progress = 0.18, t = 5.80 s / 23.44 tokens per second 64.30.052.544 I slot print_timing: id 3 | task 9641 | prompt processing, n_tokens = 136, progress = 0.17, t = 5.80 s / 23.44 tokens per second 64.34.980.508 I slot print_timing: id 0 | task 9638 | prompt processing, n_tokens = 213, progress = 0.29, t = 11.22 s / 18.98 tokens per second 64.35.414.482 I slot print_timing: id 1 | task 9639 | prompt processing, n_tokens = 224, progress = 0.30, t = 11.22 s / 19.96 tokens per second 64.35.428.534 I slot print_timing: id 2 | task 9640 | prompt processing, n_tokens = 237, progress = 0.31, t = 11.22 s / 21.12 tokens per second 64.35.442.879 I slot print_timing: id 3 | task 9641 | prompt processing, n_tokens = 259, progress = 0.32, t = 11.22 s / 23.08 tokens per second 64.50.014.820 I slot print_timing: id 0 | task 9638 | prompt processing, n_tokens = 623, progress = 0.85, t = 26.26 s / 23.73 tokens per second 64.50.327.401 I slot print_timing: id 1 | task 9639 | prompt processing, n_tokens = 623, progress = 0.84, t = 26.26 s / 23.73 tokens per second 64.50.341.639 I slot print_timing: id 2 | task 9640 | prompt processing, n_tokens = 623, progress = 0.83, t = 26.26 s / 23.73 tokens per second 64.50.355.300 I slot print_timing: id 3 | task 9641 | prompt processing, n_tokens = 281, progress = 0.35, t = 26.26 s / 10.70 tokens per second 64.56.419.097 I slot print_timing: id 0 | task 9638 | prompt processing, n_tokens = 725, progress = 0.99, t = 32.66 s / 22.20 tokens per second 64.59.012.134 I slot print_timing: id 1 | task 9639 | prompt processing, n_tokens = 736, progress = 0.99, t = 32.66 s / 22.54 tokens per second 64.59.026.216 I slot print_timing: id 2 | task 9640 | prompt processing, n_tokens = 749, progress = 0.99, t = 32.66 s / 22.93 tokens per second 64.59.040.248 I slot print_timing: id 3 | task 9641 | prompt processing, n_tokens = 623, progress = 0.78, t = 32.66 s / 19.08 tokens per second 65.01.646.520 I slot print_timing: id 3 | task 9641 | prompt processing, n_tokens = 793, progress = 0.99, t = 37.89 s / 20.93 tokens per second 65.02.207.336 I slot print_timing: id 0 | task 9638 | prompt eval time = 37886.50 ms / 729 tokens ( 51.97 ms per token, 19.24 tokens per second) 65.02.207.357 I slot print_timing: id 0 | task 9638 | eval time = 561.84 ms / 2 tokens ( 561.84 ms per token, 1.78 tokens per second) 65.02.207.360 I slot print_timing: id 0 | task 9638 | total time = 38448.35 ms / 731 tokens 65.02.207.362 I slot print_timing: id 0 | task 9638 | graphs reused = 8265 65.02.207.364 I slot print_timing: id 0 | task 9638 | graph reallocs = 0 / 0 (same size) / (changed size) 65.02.211.248 I slot release: id 0 | task 9638 | stop processing: n_tokens = 730, truncated = 0 65.02.212.746 I slot print_timing: id 1 | task 9639 | prompt eval time = 37886.83 ms / 740 tokens ( 51.20 ms per token, 19.53 tokens per second) 65.02.212.755 I slot print_timing: id 1 | task 9639 | eval time = 566.86 ms / 2 tokens ( 566.86 ms per token, 1.76 tokens per second) 65.02.212.757 I slot print_timing: id 1 | task 9639 | total time = 38453.70 ms / 742 tokens 65.02.212.758 I slot print_timing: id 1 | task 9639 | graphs reused = 8265 65.02.212.759 I slot print_timing: id 1 | task 9639 | graph reallocs = 0 / 0 (same size) / (changed size) 65.02.212.856 I slot release: id 1 | task 9639 | stop processing: n_tokens = 741, truncated = 0 65.02.214.272 I slot print_timing: id 2 | task 9640 | prompt eval time = 37887.38 ms / 753 tokens ( 50.32 ms per token, 19.87 tokens per second) 65.02.214.279 I slot print_timing: id 2 | task 9640 | eval time = 567.77 ms / 2 tokens ( 567.77 ms per token, 1.76 tokens per second) 65.02.214.280 I slot print_timing: id 2 | task 9640 | total time = 38455.15 ms / 755 tokens 65.02.214.292 I slot print_timing: id 2 | task 9640 | graphs reused = 8265 65.02.214.296 I slot print_timing: id 2 | task 9640 | graph reallocs = 0 / 0 (same size) / (changed size) 65.02.214.915 I slot release: id 2 | task 9640 | stop processing: n_tokens = 754, truncated = 0 65.02.327.388 I slot print_timing: id 3 | task 9641 | prompt eval time = 38457.00 ms / 797 tokens ( 48.25 ms per token, 20.72 tokens per second) 65.02.327.397 I slot print_timing: id 3 | task 9641 | eval time = 111.20 ms / 2 tokens ( 111.20 ms per token, 8.99 tokens per second) 65.02.327.398 I slot print_timing: id 3 | task 9641 | total time = 38568.20 ms / 799 tokens 65.02.327.399 I slot print_timing: id 3 | task 9641 | graphs reused = 8265 65.02.327.400 I slot print_timing: id 3 | task 9641 | graph reallocs = 0 / 0 (same size) / (changed size) 65.02.327.503 I slot release: id 3 | task 9641 | stop processing: n_tokens = 798, truncated = 0 65.02.327.518 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.881 65.02.327.593 I slot launch_slot_: id 1 | task 9649 | processing task, is_child = 0 65.02.327.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.406 MiB) 65.02.549.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.468 MiB) 65.02.757.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.906 MiB) 65.02.943.552 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.892 65.02.943.613 I slot launch_slot_: id 0 | task 9650 | processing task, is_child = 0 65.02.943.704 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.863 65.02.943.725 I slot launch_slot_: id 2 | task 9651 | processing task, is_child = 0 65.02.943.785 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.816 65.02.943.807 I slot launch_slot_: id 3 | task 9652 | processing task, is_child = 0 65.08.656.120 I slot print_timing: id 0 | task 9650 | prompt processing, n_tokens = 119, progress = 0.99, t = 5.71 s / 20.83 tokens per second 65.09.089.699 I slot print_timing: id 1 | task 9649 | prompt processing, n_tokens = 112, progress = 0.99, t = 5.70 s / 19.63 tokens per second 65.09.104.856 I slot print_timing: id 2 | task 9651 | prompt processing, n_tokens = 106, progress = 0.99, t = 5.69 s / 18.63 tokens per second 65.09.134.261 I slot print_timing: id 3 | task 9652 | prompt processing, n_tokens = 128, progress = 0.99, t = 5.67 s / 22.57 tokens per second 65.09.740.914 I slot print_timing: id 0 | task 9650 | prompt eval time = 6585.45 ms / 123 tokens ( 53.54 ms per token, 18.68 tokens per second) 65.09.740.916 I slot print_timing: id 0 | task 9650 | eval time = 211.64 ms / 2 tokens ( 211.64 ms per token, 4.72 tokens per second) 65.09.740.917 I slot print_timing: id 0 | task 9650 | total time = 6797.09 ms / 125 tokens 65.09.740.917 I slot print_timing: id 0 | task 9650 | graphs reused = 8265 65.09.740.917 I slot print_timing: id 0 | task 9650 | graph reallocs = 0 / 0 (same size) / (changed size) 65.09.742.775 I slot release: id 0 | task 9650 | stop processing: n_tokens = 747, truncated = 0 65.09.743.070 I slot print_timing: id 1 | task 9649 | prompt eval time = 6577.95 ms / 116 tokens ( 56.71 ms per token, 17.63 tokens per second) 65.09.743.073 I slot print_timing: id 1 | task 9649 | eval time = 213.64 ms / 2 tokens ( 213.64 ms per token, 4.68 tokens per second) 65.09.743.074 I slot print_timing: id 1 | task 9649 | total time = 6791.58 ms / 118 tokens 65.09.743.074 I slot print_timing: id 1 | task 9649 | graphs reused = 8265 65.09.743.074 I slot print_timing: id 1 | task 9649 | graph reallocs = 0 / 0 (same size) / (changed size) 65.09.743.429 I slot release: id 1 | task 9649 | stop processing: n_tokens = 740, truncated = 0 65.09.743.762 I slot print_timing: id 2 | task 9651 | prompt eval time = 6561.76 ms / 110 tokens ( 59.65 ms per token, 16.76 tokens per second) 65.09.743.765 I slot print_timing: id 2 | task 9651 | eval time = 214.16 ms / 2 tokens ( 214.16 ms per token, 4.67 tokens per second) 65.09.743.765 I slot print_timing: id 2 | task 9651 | total time = 6775.92 ms / 112 tokens 65.09.743.765 I slot print_timing: id 2 | task 9651 | graphs reused = 8265 65.09.743.766 I slot print_timing: id 2 | task 9651 | graph reallocs = 0 / 0 (same size) / (changed size) 65.09.744.119 I slot release: id 2 | task 9651 | stop processing: n_tokens = 734, truncated = 0 65.09.744.463 I slot print_timing: id 3 | task 9652 | prompt eval time = 6546.11 ms / 132 tokens ( 49.59 ms per token, 20.16 tokens per second) 65.09.744.469 I slot print_timing: id 3 | task 9652 | eval time = 214.68 ms / 2 tokens ( 214.68 ms per token, 4.66 tokens per second) 65.09.744.469 I slot print_timing: id 3 | task 9652 | total time = 6760.78 ms / 134 tokens 65.09.744.470 I slot print_timing: id 3 | task 9652 | graphs reused = 8265 65.09.744.470 I slot print_timing: id 3 | task 9652 | graph reallocs = 0 / 0 (same size) / (changed size) 65.09.744.555 I slot release: id 3 | task 9652 | stop processing: n_tokens = 756, truncated = 0 65.09.754.931 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.871 65.09.754.957 I slot launch_slot_: id 0 | task 9656 | processing task, is_child = 0 65.09.755.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.593 MiB) 65.09.907.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.656 MiB) 65.10.040.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.655 MiB) 65.10.153.323 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 98276976986 65.10.153.423 I slot launch_slot_: id 1 | task 9657 | processing task, is_child = 0 65.10.153.506 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 98276977678 65.10.153.562 I slot launch_slot_: id 2 | task 9658 | processing task, is_child = 0 65.10.153.605 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 98276978115 65.10.153.662 I slot launch_slot_: id 3 | task 9659 | processing task, is_child = 0 65.15.602.256 I slot print_timing: id 0 | task 9656 | prompt processing, n_tokens = 120, progress = 0.99, t = 5.45 s / 22.02 tokens per second 65.17.149.651 I slot print_timing: id 1 | task 9657 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.44 s / 29.77 tokens per second 65.17.154.143 I slot print_timing: id 2 | task 9658 | prompt processing, n_tokens = 162, progress = 0.16, t = 5.44 s / 29.77 tokens per second 65.17.167.723 I slot print_timing: id 3 | task 9659 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.44 s / 29.77 tokens per second 65.24.211.778 I slot print_timing: id 1 | task 9657 | prompt processing, n_tokens = 350, progress = 0.36, t = 14.05 s / 24.91 tokens per second 65.24.211.796 I slot print_timing: id 2 | task 9658 | prompt processing, n_tokens = 350, progress = 0.35, t = 14.05 s / 24.91 tokens per second 65.24.211.802 I slot print_timing: id 3 | task 9659 | prompt processing, n_tokens = 350, progress = 0.37, t = 14.05 s / 24.91 tokens per second 65.28.915.240 I slot print_timing: id 0 | task 9656 | prompt eval time = 14058.09 ms / 124 tokens ( 113.37 ms per token, 8.82 tokens per second) 65.28.915.245 I slot print_timing: id 0 | task 9656 | eval time = 4703.47 ms / 2 tokens ( 4703.47 ms per token, 0.21 tokens per second) 65.28.915.246 I slot print_timing: id 0 | task 9656 | total time = 18761.56 ms / 126 tokens 65.28.915.246 I slot print_timing: id 0 | task 9656 | graphs reused = 8265 65.28.915.247 I slot print_timing: id 0 | task 9656 | graph reallocs = 0 / 0 (same size) / (changed size) 65.28.916.284 I slot release: id 0 | task 9656 | stop processing: n_tokens = 748, truncated = 0 65.28.916.310 I slot print_timing: id 1 | task 9657 | prompt processing, n_tokens = 457, progress = 0.47, t = 18.75 s / 24.37 tokens per second 65.28.923.913 I slot print_timing: id 2 | task 9658 | prompt processing, n_tokens = 474, progress = 0.48, t = 18.75 s / 25.28 tokens per second 65.28.928.584 I slot print_timing: id 3 | task 9659 | prompt processing, n_tokens = 439, progress = 0.46, t = 18.75 s / 23.41 tokens per second 65.41.630.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 98296149842 65.41.630.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 65.42.400.699 I slot launch_slot_: id 0 | task 9664 | processing task, is_child = 0 65.42.400.775 I slot print_timing: id 1 | task 9657 | prompt processing, n_tokens = 820, progress = 0.84, t = 31.47 s / 26.06 tokens per second 65.42.405.209 I slot print_timing: id 2 | task 9658 | prompt processing, n_tokens = 820, progress = 0.83, t = 31.47 s / 26.06 tokens per second 65.42.409.632 I slot print_timing: id 3 | task 9659 | prompt processing, n_tokens = 820, progress = 0.86, t = 31.47 s / 26.06 tokens per second 65.49.721.472 I slot print_timing: id 0 | task 9664 | prompt processing, n_tokens = 162, progress = 0.16, t = 7.32 s / 22.13 tokens per second 65.50.156.780 I slot print_timing: id 1 | task 9657 | prompt processing, n_tokens = 969, progress = 1.00, t = 39.56 s / 24.49 tokens per second 65.50.161.366 I slot print_timing: id 2 | task 9658 | prompt processing, n_tokens = 986, progress = 1.00, t = 39.56 s / 24.92 tokens per second 65.50.165.911 I slot print_timing: id 3 | task 9659 | prompt processing, n_tokens = 951, progress = 1.00, t = 39.56 s / 24.04 tokens per second 65.52.758.353 I slot print_timing: id 0 | task 9664 | prompt processing, n_tokens = 350, progress = 0.34, t = 10.36 s / 33.79 tokens per second 65.55.165.805 I slot print_timing: id 1 | task 9657 | prompt eval time = 42596.54 ms / 973 tokens ( 43.78 ms per token, 22.84 tokens per second) 65.55.165.810 I slot print_timing: id 1 | task 9657 | eval time = 2407.94 ms / 2 tokens ( 2407.94 ms per token, 0.42 tokens per second) 65.55.165.810 I slot print_timing: id 1 | task 9657 | total time = 45004.48 ms / 975 tokens 65.55.165.811 I slot print_timing: id 1 | task 9657 | graphs reused = 8265 65.55.165.811 I slot print_timing: id 1 | task 9657 | graph reallocs = 0 / 0 (same size) / (changed size) 65.55.169.958 I slot release: id 1 | task 9657 | stop processing: n_tokens = 974, truncated = 0 65.55.170.432 I slot print_timing: id 2 | task 9658 | prompt eval time = 42596.72 ms / 990 tokens ( 43.03 ms per token, 23.24 tokens per second) 65.55.170.436 I slot print_timing: id 2 | task 9658 | eval time = 2412.33 ms / 2 tokens ( 2412.33 ms per token, 0.41 tokens per second) 65.55.170.436 I slot print_timing: id 2 | task 9658 | total time = 45009.05 ms / 992 tokens 65.55.170.436 I slot print_timing: id 2 | task 9658 | graphs reused = 8265 65.55.170.437 I slot print_timing: id 2 | task 9658 | graph reallocs = 0 / 0 (same size) / (changed size) 65.55.170.647 I slot release: id 2 | task 9658 | stop processing: n_tokens = 991, truncated = 0 65.55.171.085 I slot print_timing: id 3 | task 9659 | prompt eval time = 42596.91 ms / 955 tokens ( 44.60 ms per token, 22.42 tokens per second) 65.55.171.090 I slot print_timing: id 3 | task 9659 | eval time = 2412.74 ms / 2 tokens ( 2412.74 ms per token, 0.41 tokens per second) 65.55.171.090 I slot print_timing: id 3 | task 9659 | total time = 45009.65 ms / 957 tokens 65.55.171.091 I slot print_timing: id 3 | task 9659 | graphs reused = 8265 65.55.171.091 I slot print_timing: id 3 | task 9659 | graph reallocs = 0 / 0 (same size) / (changed size) 65.55.171.899 I slot release: id 3 | task 9659 | stop processing: n_tokens = 956, truncated = 0 65.55.171.918 I slot print_timing: id 0 | task 9664 | prompt processing, n_tokens = 528, progress = 0.51, t = 12.76 s / 41.36 tokens per second 65.55.182.080 I slot print_timing: id 0 | task 9664 | prompt processing, n_tokens = 820, progress = 0.79, t = 12.78 s / 64.16 tokens per second 65.58.839.260 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 98322403517 65.58.839.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 817.344 MiB) 66.01.449.799 I slot launch_slot_: id 1 | task 9670 | processing task, is_child = 0 66.01.449.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.592 MiB) 66.01.569.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.530 MiB) 66.01.655.168 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 98322404205 66.01.655.297 I slot launch_slot_: id 2 | task 9671 | processing task, is_child = 0 66.01.655.346 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 98322405459 66.01.655.417 I slot launch_slot_: id 3 | task 9672 | processing task, is_child = 0 66.01.655.424 I slot print_timing: id 0 | task 9664 | prompt processing, n_tokens = 1040, progress = 1.00, t = 16.44 s / 63.27 tokens per second 66.11.287.816 I slot print_timing: id 1 | task 9670 | prompt processing, n_tokens = 204, progress = 0.18, t = 9.60 s / 21.24 tokens per second 66.11.293.875 I slot print_timing: id 2 | task 9671 | prompt processing, n_tokens = 204, progress = 0.18, t = 9.60 s / 21.24 tokens per second 66.11.298.298 I slot print_timing: id 3 | task 9672 | prompt processing, n_tokens = 372, progress = 0.18, t = 9.60 s / 38.73 tokens per second 66.18.125.780 I slot print_timing: id 0 | task 9664 | prompt eval time = 28887.09 ms / 1044 tokens ( 27.67 ms per token, 36.14 tokens per second) 66.18.125.787 I slot print_timing: id 0 | task 9664 | eval time = 6837.97 ms / 2 tokens ( 6837.97 ms per token, 0.15 tokens per second) 66.18.125.787 I slot print_timing: id 0 | task 9664 | total time = 35725.06 ms / 1046 tokens 66.18.125.788 I slot print_timing: id 0 | task 9664 | graphs reused = 8265 66.18.125.788 I slot print_timing: id 0 | task 9664 | graph reallocs = 0 / 0 (same size) / (changed size) 66.18.127.470 I slot release: id 0 | task 9664 | stop processing: n_tokens = 1045, truncated = 0 66.18.127.500 I slot print_timing: id 1 | task 9670 | prompt processing, n_tokens = 350, progress = 0.31, t = 16.44 s / 21.29 tokens per second 66.18.127.519 I slot print_timing: id 2 | task 9671 | prompt processing, n_tokens = 350, progress = 0.30, t = 16.44 s / 21.29 tokens per second 66.18.127.531 I slot print_timing: id 3 | task 9672 | prompt processing, n_tokens = 640, progress = 0.31, t = 16.44 s / 38.92 tokens per second 66.34.314.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 98345361029 66.34.314.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.773 MiB) 66.35.820.359 I slot launch_slot_: id 0 | task 9676 | processing task, is_child = 0 66.35.820.473 I slot print_timing: id 1 | task 9670 | prompt processing, n_tokens = 608, progress = 0.54, t = 32.63 s / 18.63 tokens per second 66.35.824.927 I slot print_timing: id 2 | task 9671 | prompt processing, n_tokens = 645, progress = 0.56, t = 32.63 s / 19.77 tokens per second 66.35.829.388 I slot print_timing: id 3 | task 9672 | prompt processing, n_tokens = 1575, progress = 0.75, t = 32.63 s / 48.27 tokens per second 66.50.896.303 I slot print_timing: id 0 | task 9676 | prompt processing, n_tokens = 372, progress = 0.18, t = 15.08 s / 24.68 tokens per second 66.51.065.452 I slot print_timing: id 1 | task 9670 | prompt processing, n_tokens = 977, progress = 0.87, t = 49.21 s / 19.85 tokens per second 66.51.069.861 I slot print_timing: id 2 | task 9671 | prompt processing, n_tokens = 977, progress = 0.84, t = 49.21 s / 19.85 tokens per second 66.51.074.295 I slot print_timing: id 3 | task 9672 | prompt processing, n_tokens = 1761, progress = 0.84, t = 49.21 s / 35.78 tokens per second 67.00.436.348 I slot print_timing: id 0 | task 9676 | prompt processing, n_tokens = 640, progress = 0.31, t = 24.62 s / 26.00 tokens per second 67.00.436.379 I slot print_timing: id 1 | task 9670 | prompt processing, n_tokens = 1120, progress = 1.00, t = 58.75 s / 19.06 tokens per second 67.02.323.603 I slot print_timing: id 2 | task 9671 | prompt processing, n_tokens = 1157, progress = 1.00, t = 58.75 s / 19.69 tokens per second 67.02.328.158 I slot print_timing: id 3 | task 9672 | prompt processing, n_tokens = 2087, progress = 1.00, t = 58.75 s / 35.52 tokens per second 67.13.634.203 I slot print_timing: id 0 | task 9676 | prompt processing, n_tokens = 1578, progress = 0.75, t = 37.81 s / 41.73 tokens per second 67.16.128.804 I slot print_timing: id 1 | task 9670 | prompt eval time = 71950.33 ms / 1124 tokens ( 64.01 ms per token, 15.62 tokens per second) 67.16.128.809 I slot print_timing: id 1 | task 9670 | eval time = 2495.08 ms / 2 tokens ( 2495.08 ms per token, 0.40 tokens per second) 67.16.128.810 I slot print_timing: id 1 | task 9670 | total time = 74445.41 ms / 1126 tokens 67.16.128.810 I slot print_timing: id 1 | task 9670 | graphs reused = 8265 67.16.128.811 I slot print_timing: id 1 | task 9670 | graph reallocs = 0 / 0 (same size) / (changed size) 67.16.128.913 I slot release: id 1 | task 9670 | stop processing: n_tokens = 1125, truncated = 0 67.16.129.154 I slot print_timing: id 2 | task 9671 | prompt eval time = 71950.49 ms / 1161 tokens ( 61.97 ms per token, 16.14 tokens per second) 67.16.129.157 I slot print_timing: id 2 | task 9671 | eval time = 2495.20 ms / 2 tokens ( 2495.20 ms per token, 0.40 tokens per second) 67.16.129.157 I slot print_timing: id 2 | task 9671 | total time = 74445.69 ms / 1163 tokens 67.16.129.157 I slot print_timing: id 2 | task 9671 | graphs reused = 8265 67.16.129.158 I slot print_timing: id 2 | task 9671 | graph reallocs = 0 / 0 (same size) / (changed size) 67.16.129.195 I slot release: id 2 | task 9671 | stop processing: n_tokens = 1162, truncated = 0 67.16.129.464 I slot print_timing: id 3 | task 9672 | prompt eval time = 71950.66 ms / 2091 tokens ( 34.41 ms per token, 29.06 tokens per second) 67.16.129.467 I slot print_timing: id 3 | task 9672 | eval time = 2495.28 ms / 2 tokens ( 2495.28 ms per token, 0.40 tokens per second) 67.16.129.467 I slot print_timing: id 3 | task 9672 | total time = 74445.94 ms / 2093 tokens 67.16.129.468 I slot print_timing: id 3 | task 9672 | graphs reused = 8265 67.16.129.468 I slot print_timing: id 3 | task 9672 | graph reallocs = 0 / 0 (same size) / (changed size) 67.16.129.761 I slot release: id 3 | task 9672 | stop processing: n_tokens = 2092, truncated = 0 67.16.129.788 I slot print_timing: id 0 | task 9676 | prompt processing, n_tokens = 1761, progress = 0.84, t = 40.31 s / 43.69 tokens per second 67.16.144.631 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.856 67.16.144.666 I slot launch_slot_: id 3 | task 9682 | processing task, is_child = 0 67.16.144.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.273 MiB) 67.20.228.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.024 MiB) 67.20.270.046 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 98403362471 67.20.270.194 I slot launch_slot_: id 1 | task 9683 | processing task, is_child = 0 67.20.270.251 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 98403362752 67.20.270.324 I slot launch_slot_: id 2 | task 9684 | processing task, is_child = 0 67.20.270.332 I slot print_timing: id 0 | task 9676 | prompt processing, n_tokens = 2090, progress = 1.00, t = 40.32 s / 51.83 tokens per second 67.32.490.057 I slot print_timing: id 1 | task 9683 | prompt processing, n_tokens = 372, progress = 0.18, t = 12.21 s / 30.45 tokens per second 67.32.496.168 I slot print_timing: id 2 | task 9684 | prompt processing, n_tokens = 372, progress = 0.18, t = 12.21 s / 30.46 tokens per second 67.32.500.633 I slot print_timing: id 3 | task 9682 | prompt processing, n_tokens = 276, progress = 1.00, t = 12.21 s / 22.60 tokens per second 67.39.154.714 I slot print_timing: id 0 | task 9676 | prompt eval time = 56669.67 ms / 2094 tokens ( 27.06 ms per token, 36.95 tokens per second) 67.39.154.717 I slot print_timing: id 0 | task 9676 | eval time = 6664.66 ms / 2 tokens ( 6664.66 ms per token, 0.15 tokens per second) 67.39.154.718 I slot print_timing: id 0 | task 9676 | total time = 63334.33 ms / 2096 tokens 67.39.154.718 I slot print_timing: id 0 | task 9676 | graphs reused = 8265 67.39.154.719 I slot print_timing: id 0 | task 9676 | graph reallocs = 0 / 0 (same size) / (changed size) 67.39.156.469 I slot release: id 0 | task 9676 | stop processing: n_tokens = 2095, truncated = 0 67.39.157.018 I slot print_timing: id 1 | task 9683 | prompt processing, n_tokens = 640, progress = 0.30, t = 18.88 s / 33.90 tokens per second 67.39.157.052 I slot print_timing: id 2 | task 9684 | prompt processing, n_tokens = 640, progress = 0.31, t = 18.88 s / 33.90 tokens per second 68.00.822.453 I slot print_timing: id 3 | task 9682 | prompt eval time = 18881.85 ms / 280 tokens ( 67.44 ms per token, 14.83 tokens per second) 68.00.822.456 I slot print_timing: id 3 | task 9682 | eval time = 21665.45 ms / 2 tokens (21665.45 ms per token, 0.05 tokens per second) 68.00.822.456 I slot print_timing: id 3 | task 9682 | total time = 40547.29 ms / 282 tokens 68.00.822.457 I slot print_timing: id 3 | task 9682 | graphs reused = 8265 68.00.822.457 I slot print_timing: id 3 | task 9682 | graph reallocs = 0 / 0 (same size) / (changed size) 68.00.824.223 I slot release: id 3 | task 9682 | stop processing: n_tokens = 2042, truncated = 0 68.00.824.245 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.854 68.00.824.363 I slot launch_slot_: id 0 | task 9688 | processing task, is_child = 0 68.00.824.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 68.02.184.643 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.876 68.02.185.409 I slot launch_slot_: id 3 | task 9689 | processing task, is_child = 0 68.02.307.277 I slot print_timing: id 1 | task 9683 | prompt processing, n_tokens = 1589, progress = 0.75, t = 40.55 s / 39.19 tokens per second 68.02.314.683 I slot print_timing: id 2 | task 9684 | prompt processing, n_tokens = 1541, progress = 0.75, t = 40.55 s / 38.01 tokens per second 68.14.460.520 I slot print_timing: id 0 | task 9688 | prompt processing, n_tokens = 365, progress = 1.00, t = 12.28 s / 29.74 tokens per second 68.15.624.577 I slot print_timing: id 1 | task 9683 | prompt processing, n_tokens = 1761, progress = 0.84, t = 54.19 s / 32.50 tokens per second 68.15.650.685 I slot print_timing: id 2 | task 9684 | prompt processing, n_tokens = 1761, progress = 0.86, t = 54.19 s / 32.50 tokens per second 68.15.663.781 I slot print_timing: id 3 | task 9689 | prompt processing, n_tokens = 296, progress = 1.00, t = 12.07 s / 24.52 tokens per second 68.23.517.135 I slot print_timing: id 1 | task 9683 | prompt processing, n_tokens = 2101, progress = 1.00, t = 63.24 s / 33.22 tokens per second 68.23.535.539 I slot print_timing: id 2 | task 9684 | prompt processing, n_tokens = 2053, progress = 1.00, t = 63.24 s / 32.46 tokens per second 68.24.192.604 I slot print_timing: id 0 | task 9688 | prompt eval time = 21331.23 ms / 369 tokens ( 57.81 ms per token, 17.30 tokens per second) 68.24.192.607 I slot print_timing: id 0 | task 9688 | eval time = 675.90 ms / 2 tokens ( 675.90 ms per token, 1.48 tokens per second) 68.24.192.607 I slot print_timing: id 0 | task 9688 | total time = 22007.13 ms / 371 tokens 68.24.192.608 I slot print_timing: id 0 | task 9688 | graphs reused = 8265 68.24.192.608 I slot print_timing: id 0 | task 9688 | graph reallocs = 0 / 0 (same size) / (changed size) 68.24.193.604 I slot release: id 0 | task 9688 | stop processing: n_tokens = 2131, truncated = 0 68.24.196.002 I slot print_timing: id 3 | task 9689 | prompt eval time = 21126.70 ms / 300 tokens ( 70.42 ms per token, 14.20 tokens per second) 68.24.196.005 I slot print_timing: id 3 | task 9689 | eval time = 678.87 ms / 2 tokens ( 678.87 ms per token, 1.47 tokens per second) 68.24.196.005 I slot print_timing: id 3 | task 9689 | total time = 21805.57 ms / 302 tokens 68.24.196.006 I slot print_timing: id 3 | task 9689 | graphs reused = 8265 68.24.196.006 I slot print_timing: id 3 | task 9689 | graph reallocs = 0 / 0 (same size) / (changed size) 68.24.196.475 I slot release: id 3 | task 9689 | stop processing: n_tokens = 2062, truncated = 0 68.24.380.819 I slot print_timing: id 1 | task 9683 | prompt eval time = 63919.39 ms / 2105 tokens ( 30.37 ms per token, 32.93 tokens per second) 68.24.380.821 I slot print_timing: id 1 | task 9683 | eval time = 186.44 ms / 2 tokens ( 186.44 ms per token, 5.36 tokens per second) 68.24.380.822 I slot print_timing: id 1 | task 9683 | total time = 64105.83 ms / 2107 tokens 68.24.380.822 I slot print_timing: id 1 | task 9683 | graphs reused = 8265 68.24.380.823 I slot print_timing: id 1 | task 9683 | graph reallocs = 0 / 0 (same size) / (changed size) 68.24.381.040 I slot release: id 1 | task 9683 | stop processing: n_tokens = 2106, truncated = 0 68.24.381.413 I slot print_timing: id 2 | task 9684 | prompt eval time = 63920.04 ms / 2057 tokens ( 31.07 ms per token, 32.18 tokens per second) 68.24.381.415 I slot print_timing: id 2 | task 9684 | eval time = 186.31 ms / 2 tokens ( 186.31 ms per token, 5.37 tokens per second) 68.24.381.417 I slot print_timing: id 2 | task 9684 | total time = 64106.35 ms / 2059 tokens 68.24.381.417 I slot print_timing: id 2 | task 9684 | graphs reused = 8265 68.24.381.418 I slot print_timing: id 2 | task 9684 | graph reallocs = 0 / 0 (same size) / (changed size) 68.24.382.307 I slot release: id 2 | task 9684 | stop processing: n_tokens = 2058, truncated = 0 68.24.382.332 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.840 68.24.382.444 I slot launch_slot_: id 0 | task 9694 | processing task, is_child = 0 68.24.382.599 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.023 MiB) 68.24.382.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.398 MiB) 68.24.710.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.898 MiB) 68.25.252.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.028 MiB) 68.25.806.306 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.850 68.25.806.391 I slot launch_slot_: id 1 | task 9695 | processing task, is_child = 0 68.25.806.582 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.870 68.25.806.611 I slot launch_slot_: id 2 | task 9696 | processing task, is_child = 0 68.25.806.709 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.868 68.25.806.743 I slot launch_slot_: id 3 | task 9697 | processing task, is_child = 0 68.40.643.669 I slot print_timing: id 0 | task 9694 | prompt processing, n_tokens = 376, progress = 1.00, t = 14.84 s / 25.34 tokens per second 68.41.823.383 I slot print_timing: id 1 | task 9695 | prompt processing, n_tokens = 463, progress = 1.00, t = 14.80 s / 31.27 tokens per second 68.41.837.614 I slot print_timing: id 2 | task 9696 | prompt processing, n_tokens = 254, progress = 1.00, t = 14.69 s / 17.29 tokens per second 68.41.851.437 I slot print_timing: id 3 | task 9697 | prompt processing, n_tokens = 206, progress = 1.00, t = 14.60 s / 14.11 tokens per second 68.42.470.654 I slot print_timing: id 0 | task 9694 | prompt eval time = 16448.08 ms / 380 tokens ( 43.28 ms per token, 23.10 tokens per second) 68.42.470.659 I slot print_timing: id 0 | task 9694 | eval time = 215.82 ms / 2 tokens ( 215.82 ms per token, 4.63 tokens per second) 68.42.470.660 I slot print_timing: id 0 | task 9694 | total time = 16663.90 ms / 382 tokens 68.42.470.660 I slot print_timing: id 0 | task 9694 | graphs reused = 8265 68.42.470.660 I slot print_timing: id 0 | task 9694 | graph reallocs = 0 / 0 (same size) / (changed size) 68.42.470.758 I slot release: id 0 | task 9694 | stop processing: n_tokens = 2142, truncated = 0 68.42.470.980 I slot print_timing: id 1 | task 9695 | prompt eval time = 16416.45 ms / 467 tokens ( 35.15 ms per token, 28.45 tokens per second) 68.42.470.982 I slot print_timing: id 1 | task 9695 | eval time = 215.81 ms / 2 tokens ( 215.81 ms per token, 4.63 tokens per second) 68.42.470.984 I slot print_timing: id 1 | task 9695 | total time = 16632.26 ms / 469 tokens 68.42.470.984 I slot print_timing: id 1 | task 9695 | graphs reused = 8265 68.42.470.984 I slot print_timing: id 1 | task 9695 | graph reallocs = 0 / 0 (same size) / (changed size) 68.42.471.074 I slot release: id 1 | task 9695 | stop processing: n_tokens = 2229, truncated = 0 68.42.471.362 I slot print_timing: id 2 | task 9696 | prompt eval time = 16305.71 ms / 258 tokens ( 63.20 ms per token, 15.82 tokens per second) 68.42.471.384 I slot print_timing: id 2 | task 9696 | eval time = 215.81 ms / 2 tokens ( 215.81 ms per token, 4.63 tokens per second) 68.42.471.384 I slot print_timing: id 2 | task 9696 | total time = 16521.52 ms / 260 tokens 68.42.471.392 I slot print_timing: id 2 | task 9696 | graphs reused = 8265 68.42.471.393 I slot print_timing: id 2 | task 9696 | graph reallocs = 0 / 0 (same size) / (changed size) 68.42.472.671 I slot release: id 2 | task 9696 | stop processing: n_tokens = 2020, truncated = 0 68.42.473.014 I slot print_timing: id 3 | task 9697 | prompt eval time = 16217.08 ms / 210 tokens ( 77.22 ms per token, 12.95 tokens per second) 68.42.473.017 I slot print_timing: id 3 | task 9697 | eval time = 216.75 ms / 2 tokens ( 216.75 ms per token, 4.61 tokens per second) 68.42.473.017 I slot print_timing: id 3 | task 9697 | total time = 16433.83 ms / 212 tokens 68.42.473.017 I slot print_timing: id 3 | task 9697 | graphs reused = 8265 68.42.473.018 I slot print_timing: id 3 | task 9697 | graph reallocs = 0 / 0 (same size) / (changed size) 68.42.473.121 I slot release: id 3 | task 9697 | stop processing: n_tokens = 1972, truncated = 0 68.42.487.733 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.836 68.42.487.767 I slot launch_slot_: id 0 | task 9701 | processing task, is_child = 0 68.42.487.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.091 MiB) 68.42.682.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.903 MiB) 68.42.948.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.467 MiB) 68.43.422.356 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.803 68.43.422.426 I slot launch_slot_: id 1 | task 9702 | processing task, is_child = 0 68.43.422.602 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.886 68.43.422.626 I slot launch_slot_: id 2 | task 9703 | processing task, is_child = 0 68.43.422.711 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.908 68.43.422.728 I slot launch_slot_: id 3 | task 9704 | processing task, is_child = 0 68.55.077.912 I slot print_timing: id 0 | task 9701 | prompt processing, n_tokens = 300, progress = 1.00, t = 11.66 s / 25.74 tokens per second 68.56.952.410 I slot print_timing: id 1 | task 9702 | prompt processing, n_tokens = 249, progress = 1.00, t = 11.64 s / 21.39 tokens per second 68.56.973.929 I slot print_timing: id 2 | task 9703 | prompt processing, n_tokens = 208, progress = 1.00, t = 11.63 s / 17.88 tokens per second 68.56.995.635 I slot print_timing: id 3 | task 9704 | prompt processing, n_tokens = 341, progress = 1.00, t = 11.63 s / 29.33 tokens per second 68.57.613.109 I slot print_timing: id 0 | task 9701 | prompt eval time = 13974.96 ms / 304 tokens ( 45.97 ms per token, 21.75 tokens per second) 68.57.613.112 I slot print_timing: id 0 | task 9701 | eval time = 215.41 ms / 2 tokens ( 215.41 ms per token, 4.64 tokens per second) 68.57.613.112 I slot print_timing: id 0 | task 9701 | total time = 14190.37 ms / 306 tokens 68.57.613.113 I slot print_timing: id 0 | task 9701 | graphs reused = 8265 68.57.613.113 I slot print_timing: id 0 | task 9701 | graph reallocs = 0 / 0 (same size) / (changed size) 68.57.614.443 I slot release: id 0 | task 9701 | stop processing: n_tokens = 2066, truncated = 0 68.57.614.780 I slot print_timing: id 1 | task 9702 | prompt eval time = 13960.73 ms / 253 tokens ( 55.18 ms per token, 18.12 tokens per second) 68.57.614.789 I slot print_timing: id 1 | task 9702 | eval time = 216.73 ms / 2 tokens ( 216.73 ms per token, 4.61 tokens per second) 68.57.614.789 I slot print_timing: id 1 | task 9702 | total time = 14177.46 ms / 255 tokens 68.57.614.790 I slot print_timing: id 1 | task 9702 | graphs reused = 8265 68.57.614.790 I slot print_timing: id 1 | task 9702 | graph reallocs = 0 / 0 (same size) / (changed size) 68.57.615.433 I slot release: id 1 | task 9702 | stop processing: n_tokens = 2015, truncated = 0 68.57.616.057 I slot print_timing: id 2 | task 9703 | prompt eval time = 13953.69 ms / 212 tokens ( 65.82 ms per token, 15.19 tokens per second) 68.57.616.061 I slot print_timing: id 2 | task 9703 | eval time = 217.50 ms / 2 tokens ( 217.50 ms per token, 4.60 tokens per second) 68.57.616.064 I slot print_timing: id 2 | task 9703 | total time = 14171.18 ms / 214 tokens 68.57.616.064 I slot print_timing: id 2 | task 9703 | graphs reused = 8265 68.57.616.065 I slot print_timing: id 2 | task 9703 | graph reallocs = 0 / 0 (same size) / (changed size) 68.57.616.180 I slot release: id 2 | task 9703 | stop processing: n_tokens = 1974, truncated = 0 68.57.616.476 I slot print_timing: id 3 | task 9704 | prompt eval time = 13946.54 ms / 345 tokens ( 40.42 ms per token, 24.74 tokens per second) 68.57.616.481 I slot print_timing: id 3 | task 9704 | eval time = 217.28 ms / 2 tokens ( 217.28 ms per token, 4.60 tokens per second) 68.57.616.482 I slot print_timing: id 3 | task 9704 | total time = 14163.82 ms / 347 tokens 68.57.616.482 I slot print_timing: id 3 | task 9704 | graphs reused = 8265 68.57.616.483 I slot print_timing: id 3 | task 9704 | graph reallocs = 0 / 0 (same size) / (changed size) 68.57.617.140 I slot release: id 3 | task 9704 | stop processing: n_tokens = 2107, truncated = 0 68.57.629.905 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.866 68.57.629.932 I slot launch_slot_: id 0 | task 9708 | processing task, is_child = 0 68.57.630.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 818.469 MiB) 68.57.820.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 820.783 MiB) 68.58.038.842 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 875.803 MiB) 68.58.222.638 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.888 68.58.222.715 I slot launch_slot_: id 1 | task 9709 | processing task, is_child = 0 68.58.222.924 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.850 68.58.222.950 I slot launch_slot_: id 3 | task 9710 | processing task, is_child = 0 68.58.223.044 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.906 68.58.223.067 I slot launch_slot_: id 2 | task 9711 | processing task, is_child = 0 69.12.807.673 I slot print_timing: id 0 | task 9708 | prompt processing, n_tokens = 206, progress = 1.00, t = 14.58 s / 14.12 tokens per second 69.13.603.865 I slot print_timing: id 1 | task 9709 | prompt processing, n_tokens = 401, progress = 1.00, t = 14.57 s / 27.52 tokens per second 69.13.613.076 I slot print_timing: id 2 | task 9711 | prompt processing, n_tokens = 300, progress = 1.00, t = 14.56 s / 20.60 tokens per second 69.13.621.657 I slot print_timing: id 3 | task 9710 | prompt processing, n_tokens = 349, progress = 1.00, t = 14.55 s / 23.98 tokens per second 69.14.230.851 I slot print_timing: id 0 | task 9708 | prompt eval time = 15791.63 ms / 210 tokens ( 75.20 ms per token, 13.30 tokens per second) 69.14.230.860 I slot print_timing: id 0 | task 9708 | eval time = 216.14 ms / 2 tokens ( 216.14 ms per token, 4.63 tokens per second) 69.14.230.862 I slot print_timing: id 0 | task 9708 | total time = 16007.77 ms / 212 tokens 69.14.230.863 I slot print_timing: id 0 | task 9708 | graphs reused = 8265 69.14.230.864 I slot print_timing: id 0 | task 9708 | graph reallocs = 0 / 0 (same size) / (changed size) 69.14.230.975 I slot release: id 0 | task 9708 | stop processing: n_tokens = 1972, truncated = 0 69.14.231.310 I slot print_timing: id 1 | task 9709 | prompt eval time = 15777.20 ms / 405 tokens ( 38.96 ms per token, 25.67 tokens per second) 69.14.231.312 I slot print_timing: id 1 | task 9709 | eval time = 216.04 ms / 2 tokens ( 216.04 ms per token, 4.63 tokens per second) 69.14.231.314 I slot print_timing: id 1 | task 9709 | total time = 15993.24 ms / 407 tokens 69.14.231.314 I slot print_timing: id 1 | task 9709 | graphs reused = 8265 69.14.231.315 I slot print_timing: id 1 | task 9709 | graph reallocs = 0 / 0 (same size) / (changed size) 69.14.232.457 I slot release: id 1 | task 9709 | stop processing: n_tokens = 2167, truncated = 0 69.14.232.871 I slot print_timing: id 2 | task 9711 | prompt eval time = 15770.38 ms / 304 tokens ( 51.88 ms per token, 19.28 tokens per second) 69.14.232.874 I slot print_timing: id 2 | task 9711 | eval time = 216.61 ms / 2 tokens ( 216.61 ms per token, 4.62 tokens per second) 69.14.232.874 I slot print_timing: id 2 | task 9711 | total time = 15986.99 ms / 306 tokens 69.14.232.874 I slot print_timing: id 2 | task 9711 | graphs reused = 8265 69.14.232.875 I slot print_timing: id 2 | task 9711 | graph reallocs = 0 / 0 (same size) / (changed size) 69.14.232.936 I slot release: id 2 | task 9711 | stop processing: n_tokens = 2066, truncated = 0 69.14.233.301 I slot print_timing: id 3 | task 9710 | prompt eval time = 15763.29 ms / 353 tokens ( 44.66 ms per token, 22.39 tokens per second) 69.14.233.304 I slot print_timing: id 3 | task 9710 | eval time = 216.27 ms / 2 tokens ( 216.27 ms per token, 4.62 tokens per second) 69.14.233.305 I slot print_timing: id 3 | task 9710 | total time = 15979.57 ms / 355 tokens 69.14.233.305 I slot print_timing: id 3 | task 9710 | graphs reused = 8265 69.14.233.305 I slot print_timing: id 3 | task 9710 | graph reallocs = 0 / 0 (same size) / (changed size) 69.14.233.387 I slot release: id 3 | task 9710 | stop processing: n_tokens = 2115, truncated = 0 69.14.244.755 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.907 69.14.244.781 I slot launch_slot_: id 0 | task 9715 | processing task, is_child = 0 69.14.244.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.804 MiB) 69.14.480.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 876.803 MiB) 69.14.714.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.053 MiB) 69.14.916.660 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 69.14.916.739 I slot launch_slot_: id 3 | task 9716 | processing task, is_child = 0 69.14.916.931 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.826 69.14.916.956 I slot launch_slot_: id 1 | task 9717 | processing task, is_child = 0 69.14.917.050 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.866 69.14.917.069 I slot launch_slot_: id 2 | task 9718 | processing task, is_child = 0 69.27.262.276 I slot print_timing: id 0 | task 9715 | prompt processing, n_tokens = 268, progress = 1.00, t = 12.35 s / 21.71 tokens per second 69.29.151.668 I slot print_timing: id 1 | task 9717 | prompt processing, n_tokens = 232, progress = 1.00, t = 12.33 s / 18.81 tokens per second 69.29.156.749 I slot print_timing: id 2 | task 9718 | prompt processing, n_tokens = 409, progress = 1.00, t = 12.33 s / 33.18 tokens per second 69.29.161.464 I slot print_timing: id 3 | task 9716 | prompt processing, n_tokens = 260, progress = 1.00, t = 12.32 s / 21.11 tokens per second 69.29.768.930 I slot print_timing: id 0 | task 9715 | prompt eval time = 14637.59 ms / 272 tokens ( 53.81 ms per token, 18.58 tokens per second) 69.29.768.934 I slot print_timing: id 0 | task 9715 | eval time = 214.25 ms / 2 tokens ( 214.25 ms per token, 4.67 tokens per second) 69.29.768.934 I slot print_timing: id 0 | task 9715 | total time = 14851.85 ms / 274 tokens 69.29.768.935 I slot print_timing: id 0 | task 9715 | graphs reused = 8265 69.29.768.935 I slot print_timing: id 0 | task 9715 | graph reallocs = 0 / 0 (same size) / (changed size) 69.29.769.046 I slot release: id 0 | task 9715 | stop processing: n_tokens = 2034, truncated = 0 69.29.769.208 I slot print_timing: id 1 | task 9717 | prompt eval time = 14625.64 ms / 236 tokens ( 61.97 ms per token, 16.14 tokens per second) 69.29.769.213 I slot print_timing: id 1 | task 9717 | eval time = 214.38 ms / 2 tokens ( 214.38 ms per token, 4.66 tokens per second) 69.29.769.213 I slot print_timing: id 1 | task 9717 | total time = 14840.02 ms / 238 tokens 69.29.769.213 I slot print_timing: id 1 | task 9717 | graphs reused = 8265 69.29.769.214 I slot print_timing: id 1 | task 9717 | graph reallocs = 0 / 0 (same size) / (changed size) 69.29.769.775 I slot release: id 1 | task 9717 | stop processing: n_tokens = 1998, truncated = 0 69.29.769.939 I slot print_timing: id 2 | task 9718 | prompt eval time = 14618.23 ms / 413 tokens ( 35.40 ms per token, 28.25 tokens per second) 69.29.769.942 I slot print_timing: id 2 | task 9718 | eval time = 214.91 ms / 2 tokens ( 214.91 ms per token, 4.65 tokens per second) 69.29.769.943 I slot print_timing: id 2 | task 9718 | total time = 14833.14 ms / 415 tokens 69.29.769.943 I slot print_timing: id 2 | task 9718 | graphs reused = 8265 69.29.769.943 I slot print_timing: id 2 | task 9718 | graph reallocs = 0 / 0 (same size) / (changed size) 69.29.770.018 I slot release: id 2 | task 9718 | stop processing: n_tokens = 2175, truncated = 0 69.29.770.181 I slot print_timing: id 3 | task 9716 | prompt eval time = 14610.83 ms / 264 tokens ( 55.34 ms per token, 18.07 tokens per second) 69.29.770.185 I slot print_timing: id 3 | task 9716 | eval time = 214.99 ms / 2 tokens ( 214.99 ms per token, 4.65 tokens per second) 69.29.770.185 I slot print_timing: id 3 | task 9716 | total time = 14825.81 ms / 266 tokens 69.29.770.186 I slot print_timing: id 3 | task 9716 | graphs reused = 8265 69.29.770.186 I slot print_timing: id 3 | task 9716 | graph reallocs = 0 / 0 (same size) / (changed size) 69.29.770.231 I slot release: id 3 | task 9716 | stop processing: n_tokens = 2026, truncated = 0 69.29.781.374 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.823 69.29.781.410 I slot launch_slot_: id 2 | task 9722 | processing task, is_child = 0 69.29.781.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 887.495 MiB) 69.30.102.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.427 MiB) 69.30.256.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.426 MiB) 69.30.409.850 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.880 69.30.409.923 I slot launch_slot_: id 0 | task 9723 | processing task, is_child = 0 69.30.410.113 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.895 69.30.410.137 I slot launch_slot_: id 1 | task 9724 | processing task, is_child = 0 69.30.410.224 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2026, t_last = 98537003788 69.30.410.335 I slot launch_slot_: id 3 | task 9725 | processing task, is_child = 0 69.40.511.544 I slot print_timing: id 0 | task 9723 | prompt processing, n_tokens = 192, progress = 1.00, t = 10.10 s / 19.01 tokens per second 69.42.356.933 I slot print_timing: id 1 | task 9724 | prompt processing, n_tokens = 145, progress = 1.00, t = 10.09 s / 14.37 tokens per second 69.42.361.587 I slot print_timing: id 2 | task 9722 | prompt processing, n_tokens = 226, progress = 1.00, t = 10.09 s / 22.41 tokens per second 69.42.374.331 I slot print_timing: id 3 | task 9725 | prompt processing, n_tokens = 363, progress = 0.25, t = 10.08 s / 36.02 tokens per second 69.45.343.514 I slot print_timing: id 3 | task 9725 | prompt processing, n_tokens = 575, progress = 0.39, t = 14.91 s / 38.57 tokens per second 69.49.931.967 I slot print_timing: id 0 | task 9723 | prompt eval time = 14932.69 ms / 196 tokens ( 76.19 ms per token, 13.13 tokens per second) 69.49.931.969 I slot print_timing: id 0 | task 9723 | eval time = 4588.93 ms / 2 tokens ( 4588.93 ms per token, 0.22 tokens per second) 69.49.931.970 I slot print_timing: id 0 | task 9723 | total time = 19521.62 ms / 198 tokens 69.49.931.970 I slot print_timing: id 0 | task 9723 | graphs reused = 8265 69.49.931.971 I slot print_timing: id 0 | task 9723 | graph reallocs = 0 / 0 (same size) / (changed size) 69.49.932.062 I slot release: id 0 | task 9723 | stop processing: n_tokens = 1958, truncated = 0 69.49.932.298 I slot print_timing: id 1 | task 9724 | prompt eval time = 14925.30 ms / 149 tokens ( 100.17 ms per token, 9.98 tokens per second) 69.49.932.304 I slot print_timing: id 1 | task 9724 | eval time = 4589.03 ms / 2 tokens ( 4589.03 ms per token, 0.22 tokens per second) 69.49.932.305 I slot print_timing: id 1 | task 9724 | total time = 19514.33 ms / 151 tokens 69.49.932.305 I slot print_timing: id 1 | task 9724 | graphs reused = 8265 69.49.932.305 I slot print_timing: id 1 | task 9724 | graph reallocs = 0 / 0 (same size) / (changed size) 69.49.932.364 I slot release: id 1 | task 9724 | stop processing: n_tokens = 1911, truncated = 0 69.49.932.619 I slot print_timing: id 2 | task 9722 | prompt eval time = 14917.94 ms / 230 tokens ( 64.86 ms per token, 15.42 tokens per second) 69.49.932.622 I slot print_timing: id 2 | task 9722 | eval time = 4589.12 ms / 2 tokens ( 4589.12 ms per token, 0.22 tokens per second) 69.49.932.622 I slot print_timing: id 2 | task 9722 | total time = 19507.06 ms / 232 tokens 69.49.932.622 I slot print_timing: id 2 | task 9722 | graphs reused = 8265 69.49.932.623 I slot print_timing: id 2 | task 9722 | graph reallocs = 0 / 0 (same size) / (changed size) 69.49.932.680 I slot release: id 2 | task 9722 | stop processing: n_tokens = 1992, truncated = 0 69.49.932.692 I slot print_timing: id 3 | task 9725 | prompt processing, n_tokens = 959, progress = 0.65, t = 19.50 s / 49.18 tokens per second 69.49.947.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 98557165620 69.49.947.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.115 MiB) 69.53.681.862 I slot launch_slot_: id 0 | task 9730 | processing task, is_child = 0 69.53.681.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.551 MiB) 69.53.960.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.867 MiB) 69.54.248.187 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 98557165921 69.54.248.438 I slot launch_slot_: id 1 | task 9731 | processing task, is_child = 0 69.54.248.539 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 98557166237 69.54.248.658 I slot launch_slot_: id 2 | task 9732 | processing task, is_child = 0 69.54.249.183 I slot print_timing: id 3 | task 9725 | prompt processing, n_tokens = 1275, progress = 0.86, t = 19.51 s / 65.34 tokens per second 70.06.039.560 I slot print_timing: id 0 | task 9730 | prompt processing, n_tokens = 261, progress = 0.26, t = 11.79 s / 22.14 tokens per second 70.08.633.116 I slot print_timing: id 1 | task 9731 | prompt processing, n_tokens = 363, progress = 0.23, t = 11.79 s / 30.79 tokens per second 70.08.663.749 I slot print_timing: id 2 | task 9732 | prompt processing, n_tokens = 363, progress = 0.22, t = 11.79 s / 30.79 tokens per second 70.08.714.019 I slot print_timing: id 3 | task 9725 | prompt processing, n_tokens = 1471, progress = 1.00, t = 35.61 s / 41.31 tokens per second 70.15.717.428 I slot print_timing: id 0 | task 9730 | prompt processing, n_tokens = 409, progress = 0.41, t = 21.47 s / 19.05 tokens per second 70.15.717.445 I slot print_timing: id 1 | task 9731 | prompt processing, n_tokens = 575, progress = 0.37, t = 21.47 s / 26.78 tokens per second 70.15.717.463 I slot print_timing: id 2 | task 9732 | prompt processing, n_tokens = 575, progress = 0.34, t = 21.47 s / 26.78 tokens per second 70.29.096.590 I slot print_timing: id 3 | task 9725 | prompt eval time = 45284.25 ms / 1475 tokens ( 30.70 ms per token, 32.57 tokens per second) 70.29.096.593 I slot print_timing: id 3 | task 9725 | eval time = 13379.18 ms / 2 tokens (13379.18 ms per token, 0.07 tokens per second) 70.29.096.593 I slot print_timing: id 3 | task 9725 | total time = 58663.43 ms / 1477 tokens 70.29.096.594 I slot print_timing: id 3 | task 9725 | graphs reused = 8265 70.29.096.594 I slot print_timing: id 3 | task 9725 | graph reallocs = 0 / 0 (same size) / (changed size) 70.29.099.294 I slot release: id 3 | task 9725 | stop processing: n_tokens = 1476, truncated = 0 70.29.099.365 I slot print_timing: id 0 | task 9730 | prompt processing, n_tokens = 483, progress = 0.48, t = 34.85 s / 13.86 tokens per second 70.29.115.323 I slot print_timing: id 1 | task 9731 | prompt processing, n_tokens = 1039, progress = 0.67, t = 34.85 s / 29.82 tokens per second 70.29.130.033 I slot print_timing: id 2 | task 9732 | prompt processing, n_tokens = 1161, progress = 0.69, t = 34.85 s / 33.32 tokens per second 70.36.159.706 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 98596332853 70.36.159.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 883.618 MiB) 70.38.012.487 I slot launch_slot_: id 3 | task 9737 | processing task, is_child = 0 70.38.012.501 I slot print_timing: id 0 | task 9730 | prompt processing, n_tokens = 853, progress = 0.85, t = 41.91 s / 20.35 tokens per second 70.38.026.984 I slot print_timing: id 1 | task 9731 | prompt processing, n_tokens = 1275, progress = 0.82, t = 41.91 s / 30.42 tokens per second 70.38.041.318 I slot print_timing: id 2 | task 9732 | prompt processing, n_tokens = 1275, progress = 0.76, t = 41.91 s / 30.42 tokens per second 70.49.549.592 I slot print_timing: id 0 | task 9730 | prompt processing, n_tokens = 995, progress = 1.00, t = 55.30 s / 17.99 tokens per second 70.51.066.629 I slot print_timing: id 1 | task 9731 | prompt processing, n_tokens = 1551, progress = 1.00, t = 55.30 s / 28.05 tokens per second 70.51.071.589 I slot print_timing: id 2 | task 9732 | prompt processing, n_tokens = 1673, progress = 1.00, t = 55.30 s / 30.25 tokens per second 70.51.078.378 I slot print_timing: id 3 | task 9737 | prompt processing, n_tokens = 261, progress = 0.26, t = 11.49 s / 22.71 tokens per second 70.53.312.203 I slot print_timing: id 3 | task 9737 | prompt processing, n_tokens = 409, progress = 0.41, t = 15.26 s / 26.81 tokens per second 70.54.312.269 I slot print_timing: id 0 | task 9730 | prompt eval time = 59062.67 ms / 999 tokens ( 59.12 ms per token, 16.91 tokens per second) 70.54.312.272 I slot print_timing: id 0 | task 9730 | eval time = 1000.92 ms / 2 tokens ( 1000.92 ms per token, 1.00 tokens per second) 70.54.312.272 I slot print_timing: id 0 | task 9730 | total time = 60063.59 ms / 1001 tokens 70.54.312.273 I slot print_timing: id 0 | task 9730 | graphs reused = 8265 70.54.312.273 I slot print_timing: id 0 | task 9730 | graph reallocs = 0 / 0 (same size) / (changed size) 70.54.312.397 I slot release: id 0 | task 9730 | stop processing: n_tokens = 1000, truncated = 0 70.54.312.815 I slot print_timing: id 1 | task 9731 | prompt eval time = 59062.89 ms / 1555 tokens ( 37.98 ms per token, 26.33 tokens per second) 70.54.312.818 I slot print_timing: id 1 | task 9731 | eval time = 1001.04 ms / 2 tokens ( 1001.04 ms per token, 1.00 tokens per second) 70.54.312.818 I slot print_timing: id 1 | task 9731 | total time = 60063.93 ms / 1557 tokens 70.54.312.818 I slot print_timing: id 1 | task 9731 | graphs reused = 8265 70.54.312.819 I slot print_timing: id 1 | task 9731 | graph reallocs = 0 / 0 (same size) / (changed size) 70.54.314.042 I slot release: id 1 | task 9731 | stop processing: n_tokens = 1556, truncated = 0 70.54.314.623 I slot print_timing: id 2 | task 9732 | prompt eval time = 59063.13 ms / 1677 tokens ( 35.22 ms per token, 28.39 tokens per second) 70.54.314.626 I slot print_timing: id 2 | task 9732 | eval time = 1002.43 ms / 2 tokens ( 1002.43 ms per token, 1.00 tokens per second) 70.54.314.627 I slot print_timing: id 2 | task 9732 | total time = 60065.56 ms / 1679 tokens 70.54.314.627 I slot print_timing: id 2 | task 9732 | graphs reused = 8265 70.54.314.628 I slot print_timing: id 2 | task 9732 | graph reallocs = 0 / 0 (same size) / (changed size) 70.54.315.669 I slot release: id 2 | task 9732 | stop processing: n_tokens = 1678, truncated = 0 70.54.315.696 I slot print_timing: id 3 | task 9737 | prompt processing, n_tokens = 473, progress = 0.48, t = 16.26 s / 29.10 tokens per second 70.54.337.241 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.882 70.54.337.288 I slot launch_slot_: id 0 | task 9742 | processing task, is_child = 0 70.54.337.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.303 MiB) 70.58.715.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 880.367 MiB) 70.58.887.298 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 98621547600 70.58.887.445 I slot launch_slot_: id 1 | task 9743 | processing task, is_child = 0 70.58.887.519 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 98621549231 70.58.887.609 I slot launch_slot_: id 2 | task 9744 | processing task, is_child = 0 70.58.895.469 I slot print_timing: id 3 | task 9737 | prompt processing, n_tokens = 853, progress = 0.86, t = 16.28 s / 52.39 tokens per second 71.04.898.991 I slot print_timing: id 0 | task 9742 | prompt processing, n_tokens = 103, progress = 1.00, t = 6.01 s / 17.13 tokens per second 71.08.198.732 I slot print_timing: id 1 | task 9743 | prompt processing, n_tokens = 261, progress = 0.27, t = 6.00 s / 43.47 tokens per second 71.08.203.537 I slot print_timing: id 2 | task 9744 | prompt processing, n_tokens = 261, progress = 0.27, t = 6.00 s / 43.47 tokens per second 71.08.207.944 I slot print_timing: id 3 | task 9737 | prompt processing, n_tokens = 985, progress = 1.00, t = 26.84 s / 36.69 tokens per second 71.11.881.594 I slot print_timing: id 1 | task 9743 | prompt processing, n_tokens = 409, progress = 0.42, t = 12.99 s / 31.50 tokens per second 71.11.881.608 I slot print_timing: id 2 | task 9744 | prompt processing, n_tokens = 409, progress = 0.42, t = 12.99 s / 31.50 tokens per second 71.13.825.100 I slot print_timing: id 0 | task 9742 | prompt eval time = 12993.74 ms / 107 tokens ( 121.44 ms per token, 8.23 tokens per second) 71.13.825.102 I slot print_timing: id 0 | task 9742 | eval time = 1943.74 ms / 2 tokens ( 1943.74 ms per token, 0.51 tokens per second) 71.13.825.103 I slot print_timing: id 0 | task 9742 | total time = 14937.48 ms / 109 tokens 71.13.825.103 I slot print_timing: id 0 | task 9742 | graphs reused = 8265 71.13.825.104 I slot print_timing: id 0 | task 9742 | graph reallocs = 0 / 0 (same size) / (changed size) 71.13.825.167 I slot release: id 0 | task 9742 | stop processing: n_tokens = 961, truncated = 0 71.13.825.395 I slot print_timing: id 3 | task 9737 | prompt eval time = 33826.06 ms / 989 tokens ( 34.20 ms per token, 29.24 tokens per second) 71.13.825.397 I slot print_timing: id 3 | task 9737 | eval time = 1943.81 ms / 2 tokens ( 1943.81 ms per token, 0.51 tokens per second) 71.13.825.398 I slot print_timing: id 3 | task 9737 | total time = 35769.87 ms / 991 tokens 71.13.825.398 I slot print_timing: id 3 | task 9737 | graphs reused = 8265 71.13.825.398 I slot print_timing: id 3 | task 9737 | graph reallocs = 0 / 0 (same size) / (changed size) 71.13.827.141 I slot release: id 3 | task 9737 | stop processing: n_tokens = 990, truncated = 0 71.13.827.163 I slot print_timing: id 1 | task 9743 | prompt processing, n_tokens = 467, progress = 0.48, t = 14.93 s / 31.28 tokens per second 71.13.832.785 I slot print_timing: id 2 | task 9744 | prompt processing, n_tokens = 461, progress = 0.47, t = 14.93 s / 30.88 tokens per second 71.22.946.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.917 71.22.946.458 I slot launch_slot_: id 0 | task 9749 | processing task, is_child = 0 71.22.946.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 875.303 MiB) 71.23.122.562 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.890 71.23.122.642 I slot launch_slot_: id 3 | task 9750 | processing task, is_child = 0 71.23.130.442 I slot print_timing: id 1 | task 9743 | prompt processing, n_tokens = 853, progress = 0.87, t = 24.05 s / 35.47 tokens per second 71.23.135.282 I slot print_timing: id 2 | task 9744 | prompt processing, n_tokens = 853, progress = 0.87, t = 24.05 s / 35.47 tokens per second 71.29.184.251 I slot print_timing: id 0 | task 9749 | prompt processing, n_tokens = 119, progress = 1.00, t = 6.06 s / 19.63 tokens per second 71.29.358.904 I slot print_timing: id 1 | task 9743 | prompt processing, n_tokens = 979, progress = 1.00, t = 30.29 s / 32.32 tokens per second 71.29.363.499 I slot print_timing: id 2 | task 9744 | prompt processing, n_tokens = 973, progress = 1.00, t = 30.29 s / 32.12 tokens per second 71.29.377.971 I slot print_timing: id 3 | task 9750 | prompt processing, n_tokens = 115, progress = 1.00, t = 6.04 s / 19.03 tokens per second 71.29.995.099 I slot print_timing: id 0 | task 9749 | prompt eval time = 6659.36 ms / 123 tokens ( 54.14 ms per token, 18.47 tokens per second) 71.29.995.101 I slot print_timing: id 0 | task 9749 | eval time = 213.08 ms / 2 tokens ( 213.08 ms per token, 4.69 tokens per second) 71.29.995.102 I slot print_timing: id 0 | task 9749 | total time = 6872.44 ms / 125 tokens 71.29.995.102 I slot print_timing: id 0 | task 9749 | graphs reused = 8265 71.29.995.103 I slot print_timing: id 0 | task 9749 | graph reallocs = 0 / 0 (same size) / (changed size) 71.29.995.149 I slot release: id 0 | task 9749 | stop processing: n_tokens = 977, truncated = 0 71.29.995.300 I slot print_timing: id 1 | task 9743 | prompt eval time = 30886.97 ms / 983 tokens ( 31.42 ms per token, 31.83 tokens per second) 71.29.995.302 I slot print_timing: id 1 | task 9743 | eval time = 213.08 ms / 2 tokens ( 213.08 ms per token, 4.69 tokens per second) 71.29.995.303 I slot print_timing: id 1 | task 9743 | total time = 31100.05 ms / 985 tokens 71.29.995.303 I slot print_timing: id 1 | task 9743 | graphs reused = 8265 71.29.995.304 I slot print_timing: id 1 | task 9743 | graph reallocs = 0 / 0 (same size) / (changed size) 71.29.995.330 I slot release: id 1 | task 9743 | stop processing: n_tokens = 984, truncated = 0 71.29.995.510 I slot print_timing: id 2 | task 9744 | prompt eval time = 30887.03 ms / 977 tokens ( 31.61 ms per token, 31.63 tokens per second) 71.29.995.511 I slot print_timing: id 2 | task 9744 | eval time = 213.12 ms / 2 tokens ( 213.12 ms per token, 4.69 tokens per second) 71.29.995.511 I slot print_timing: id 2 | task 9744 | total time = 31100.15 ms / 979 tokens 71.29.995.511 I slot print_timing: id 2 | task 9744 | graphs reused = 8265 71.29.995.512 I slot print_timing: id 2 | task 9744 | graph reallocs = 0 / 0 (same size) / (changed size) 71.29.995.562 I slot release: id 2 | task 9744 | stop processing: n_tokens = 978, truncated = 0 71.29.995.734 I slot print_timing: id 3 | task 9750 | prompt eval time = 6642.57 ms / 119 tokens ( 55.82 ms per token, 17.91 tokens per second) 71.29.995.736 I slot print_timing: id 3 | task 9750 | eval time = 212.93 ms / 2 tokens ( 212.93 ms per token, 4.70 tokens per second) 71.29.995.736 I slot print_timing: id 3 | task 9750 | total time = 6855.50 ms / 121 tokens 71.29.995.736 I slot print_timing: id 3 | task 9750 | graphs reused = 8265 71.29.995.737 I slot print_timing: id 3 | task 9750 | graph reallocs = 0 / 0 (same size) / (changed size) 71.29.995.767 I slot release: id 3 | task 9750 | stop processing: n_tokens = 973, truncated = 0 71.30.006.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 98657228706 71.30.006.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 873.052 MiB) 71.30.139.497 I slot launch_slot_: id 0 | task 9754 | processing task, is_child = 0 71.30.139.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.802 MiB) 71.30.273.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.551 MiB) 71.30.419.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 867.612 MiB) 71.30.499.976 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 98657228887 71.30.500.092 I slot launch_slot_: id 1 | task 9755 | processing task, is_child = 0 71.30.500.190 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 98657229119 71.30.500.258 I slot launch_slot_: id 2 | task 9756 | processing task, is_child = 0 71.30.500.307 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 98657229324 71.30.500.370 I slot launch_slot_: id 3 | task 9757 | processing task, is_child = 0 71.44.080.912 I slot print_timing: id 0 | task 9754 | prompt processing, n_tokens = 166, progress = 0.20, t = 13.58 s / 12.22 tokens per second 71.44.877.028 I slot print_timing: id 1 | task 9755 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.58 s / 25.92 tokens per second 71.44.881.467 I slot print_timing: id 2 | task 9756 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.58 s / 25.92 tokens per second 71.44.885.900 I slot print_timing: id 3 | task 9757 | prompt processing, n_tokens = 352, progress = 0.22, t = 13.58 s / 25.92 tokens per second 71.51.500.865 I slot print_timing: id 0 | task 9754 | prompt processing, n_tokens = 309, progress = 0.37, t = 21.00 s / 14.71 tokens per second 71.53.044.314 I slot print_timing: id 1 | task 9755 | prompt processing, n_tokens = 533, progress = 0.34, t = 21.00 s / 25.38 tokens per second 71.53.044.335 I slot print_timing: id 2 | task 9756 | prompt processing, n_tokens = 533, progress = 0.33, t = 21.00 s / 25.38 tokens per second 71.53.044.358 I slot print_timing: id 3 | task 9757 | prompt processing, n_tokens = 533, progress = 0.33, t = 21.00 s / 25.38 tokens per second 72.16.848.560 I slot print_timing: id 0 | task 9754 | prompt processing, n_tokens = 706, progress = 0.86, t = 46.35 s / 15.23 tokens per second 72.17.286.182 I slot print_timing: id 1 | task 9755 | prompt processing, n_tokens = 1071, progress = 0.67, t = 46.35 s / 23.11 tokens per second 72.17.291.005 I slot print_timing: id 2 | task 9756 | prompt processing, n_tokens = 1099, progress = 0.68, t = 46.35 s / 23.71 tokens per second 72.17.295.463 I slot print_timing: id 3 | task 9757 | prompt processing, n_tokens = 1080, progress = 0.66, t = 46.35 s / 23.30 tokens per second 72.25.862.204 I slot print_timing: id 0 | task 9754 | prompt processing, n_tokens = 821, progress = 1.00, t = 55.36 s / 14.83 tokens per second 72.26.306.124 I slot print_timing: id 1 | task 9755 | prompt processing, n_tokens = 1374, progress = 0.87, t = 55.36 s / 24.82 tokens per second 72.26.310.667 I slot print_timing: id 2 | task 9756 | prompt processing, n_tokens = 1374, progress = 0.85, t = 55.36 s / 24.82 tokens per second 72.26.315.098 I slot print_timing: id 3 | task 9757 | prompt processing, n_tokens = 1113, progress = 0.68, t = 55.36 s / 20.10 tokens per second 72.35.432.675 I slot print_timing: id 1 | task 9755 | prompt processing, n_tokens = 1583, progress = 1.00, t = 64.93 s / 24.38 tokens per second 72.35.441.211 I slot print_timing: id 2 | task 9756 | prompt processing, n_tokens = 1611, progress = 1.00, t = 64.93 s / 24.81 tokens per second 72.35.445.988 I slot print_timing: id 3 | task 9757 | prompt processing, n_tokens = 1374, progress = 0.84, t = 64.93 s / 21.16 tokens per second 72.38.957.883 I slot print_timing: id 0 | task 9754 | prompt eval time = 64932.28 ms / 825 tokens ( 78.71 ms per token, 12.71 tokens per second) 72.38.957.885 I slot print_timing: id 0 | task 9754 | eval time = 3525.22 ms / 2 tokens ( 3525.22 ms per token, 0.28 tokens per second) 72.38.957.886 I slot print_timing: id 0 | task 9754 | total time = 68457.50 ms / 827 tokens 72.38.957.887 I slot print_timing: id 0 | task 9754 | graphs reused = 8266 72.38.957.887 I slot print_timing: id 0 | task 9754 | graph reallocs = 0 / 0 (same size) / (changed size) 72.38.957.938 I slot release: id 0 | task 9754 | stop processing: n_tokens = 826, truncated = 0 72.38.958.457 I slot print_timing: id 3 | task 9757 | prompt processing, n_tokens = 1625, progress = 1.00, t = 68.46 s / 23.74 tokens per second 72.39.338.747 I slot print_timing: id 1 | task 9755 | prompt eval time = 68457.73 ms / 1587 tokens ( 43.14 ms per token, 23.18 tokens per second) 72.39.338.757 I slot print_timing: id 1 | task 9755 | eval time = 380.55 ms / 2 tokens ( 380.55 ms per token, 2.63 tokens per second) 72.39.338.759 I slot print_timing: id 1 | task 9755 | total time = 68838.28 ms / 1589 tokens 72.39.338.760 I slot print_timing: id 1 | task 9755 | graphs reused = 8266 72.39.338.760 I slot print_timing: id 1 | task 9755 | graph reallocs = 0 / 0 (same size) / (changed size) 72.39.340.981 I slot release: id 1 | task 9755 | stop processing: n_tokens = 1588, truncated = 0 72.39.341.264 I slot print_timing: id 2 | task 9756 | prompt eval time = 68457.90 ms / 1615 tokens ( 42.39 ms per token, 23.59 tokens per second) 72.39.341.267 I slot print_timing: id 2 | task 9756 | eval time = 382.81 ms / 2 tokens ( 382.81 ms per token, 2.61 tokens per second) 72.39.341.268 I slot print_timing: id 2 | task 9756 | total time = 68840.71 ms / 1617 tokens 72.39.341.268 I slot print_timing: id 2 | task 9756 | graphs reused = 8266 72.39.341.268 I slot print_timing: id 2 | task 9756 | graph reallocs = 0 / 0 (same size) / (changed size) 72.39.341.358 I slot release: id 2 | task 9756 | stop processing: n_tokens = 1616, truncated = 0 72.39.341.770 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.883 72.39.341.876 I slot launch_slot_: id 1 | task 9765 | processing task, is_child = 0 72.39.341.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 872.677 MiB) 72.39.421.590 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 840.415 MiB) 72.39.452.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 98726191496 72.39.452.684 I slot launch_slot_: id 0 | task 9766 | processing task, is_child = 0 72.39.452.757 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.868 72.39.452.778 I slot launch_slot_: id 2 | task 9767 | processing task, is_child = 0 72.48.118.803 I slot print_timing: id 3 | task 9757 | prompt eval time = 68841.14 ms / 1629 tokens ( 42.26 ms per token, 23.66 tokens per second) 72.48.118.806 I slot print_timing: id 3 | task 9757 | eval time = 8777.04 ms / 2 tokens ( 8777.04 ms per token, 0.11 tokens per second) 72.48.118.807 I slot print_timing: id 3 | task 9757 | total time = 77618.18 ms / 1631 tokens 72.48.118.807 I slot print_timing: id 3 | task 9757 | graphs reused = 8266 72.48.118.808 I slot print_timing: id 3 | task 9757 | graph reallocs = 0 / 0 (same size) / (changed size) 72.48.118.890 I slot release: id 3 | task 9757 | stop processing: n_tokens = 1630, truncated = 0 72.48.118.904 I slot print_timing: id 0 | task 9766 | prompt processing, n_tokens = 126, progress = 0.15, t = 8.67 s / 14.54 tokens per second 72.48.125.013 I slot print_timing: id 1 | task 9765 | prompt processing, n_tokens = 251, progress = 1.00, t = 8.67 s / 28.96 tokens per second 72.48.130.030 I slot print_timing: id 2 | task 9767 | prompt processing, n_tokens = 340, progress = 1.00, t = 8.66 s / 39.27 tokens per second 72.49.972.323 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 98735352448 72.49.972.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 845.417 MiB) 72.50.005.103 I slot launch_slot_: id 3 | task 9770 | processing task, is_child = 0 72.50.005.115 I slot print_timing: id 0 | task 9766 | prompt processing, n_tokens = 245, progress = 0.29, t = 10.52 s / 23.29 tokens per second 72.52.833.199 I slot print_timing: id 1 | task 9765 | prompt eval time = 10519.23 ms / 255 tokens ( 41.25 ms per token, 24.24 tokens per second) 72.52.833.202 I slot print_timing: id 1 | task 9765 | eval time = 2861.11 ms / 2 tokens ( 2861.11 ms per token, 0.35 tokens per second) 72.52.833.203 I slot print_timing: id 1 | task 9765 | total time = 13380.34 ms / 257 tokens 72.52.833.203 I slot print_timing: id 1 | task 9765 | graphs reused = 8266 72.52.833.204 I slot print_timing: id 1 | task 9765 | graph reallocs = 0 / 0 (same size) / (changed size) 72.52.833.284 I slot release: id 1 | task 9765 | stop processing: n_tokens = 1630, truncated = 0 72.52.833.517 I slot print_timing: id 2 | task 9767 | prompt eval time = 10511.60 ms / 344 tokens ( 30.56 ms per token, 32.73 tokens per second) 72.52.833.520 I slot print_timing: id 2 | task 9767 | eval time = 2861.20 ms / 2 tokens ( 2861.20 ms per token, 0.35 tokens per second) 72.52.833.521 I slot print_timing: id 2 | task 9767 | total time = 13372.80 ms / 346 tokens 72.52.833.521 I slot print_timing: id 2 | task 9767 | graphs reused = 8266 72.52.833.522 I slot print_timing: id 2 | task 9767 | graph reallocs = 0 / 0 (same size) / (changed size) 72.52.833.587 I slot release: id 2 | task 9767 | stop processing: n_tokens = 1719, truncated = 0 72.52.833.609 I slot print_timing: id 0 | task 9766 | prompt processing, n_tokens = 322, progress = 0.38, t = 13.38 s / 24.07 tokens per second 72.57.585.548 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 98740066842 72.57.585.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 853.044 MiB) 72.59.073.673 I slot launch_slot_: id 1 | task 9773 | processing task, is_child = 0 72.59.073.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.029 MiB) 72.59.108.255 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 98740067145 72.59.108.383 I slot launch_slot_: id 2 | task 9774 | processing task, is_child = 0 72.59.108.391 I slot print_timing: id 0 | task 9766 | prompt processing, n_tokens = 725, progress = 0.87, t = 18.13 s / 39.98 tokens per second 72.59.113.044 I slot print_timing: id 3 | task 9770 | prompt processing, n_tokens = 245, progress = 0.28, t = 7.58 s / 32.32 tokens per second 73.04.217.769 I slot print_timing: id 0 | task 9766 | prompt processing, n_tokens = 834, progress = 1.00, t = 24.76 s / 33.68 tokens per second 73.05.388.551 I slot print_timing: id 1 | task 9773 | prompt processing, n_tokens = 149, progress = 0.18, t = 5.10 s / 29.19 tokens per second 73.05.392.936 I slot print_timing: id 2 | task 9774 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.10 s / 29.19 tokens per second 73.05.397.341 I slot print_timing: id 3 | task 9770 | prompt processing, n_tokens = 349, progress = 0.40, t = 14.21 s / 24.56 tokens per second 73.13.051.413 I slot print_timing: id 1 | task 9773 | prompt processing, n_tokens = 277, progress = 0.33, t = 13.94 s / 19.87 tokens per second 73.13.051.426 I slot print_timing: id 2 | task 9774 | prompt processing, n_tokens = 277, progress = 0.32, t = 13.94 s / 19.87 tokens per second 73.13.051.432 I slot print_timing: id 3 | task 9770 | prompt processing, n_tokens = 725, progress = 0.84, t = 23.05 s / 31.46 tokens per second 73.17.063.086 I slot print_timing: id 0 | task 9766 | prompt eval time = 33598.61 ms / 838 tokens ( 40.09 ms per token, 24.94 tokens per second) 73.17.063.091 I slot print_timing: id 0 | task 9766 | eval time = 4011.68 ms / 2 tokens ( 4011.68 ms per token, 0.25 tokens per second) 73.17.063.092 I slot print_timing: id 0 | task 9766 | total time = 37610.30 ms / 840 tokens 73.17.063.092 I slot print_timing: id 0 | task 9766 | graphs reused = 8266 73.17.063.096 I slot print_timing: id 0 | task 9766 | graph reallocs = 0 / 0 (same size) / (changed size) 73.17.063.156 I slot release: id 0 | task 9766 | stop processing: n_tokens = 839, truncated = 0 73.17.063.167 I slot print_timing: id 1 | task 9773 | prompt processing, n_tokens = 326, progress = 0.39, t = 17.95 s / 18.16 tokens per second 73.17.070.090 I slot print_timing: id 2 | task 9774 | prompt processing, n_tokens = 343, progress = 0.40, t = 17.95 s / 19.11 tokens per second 73.17.074.564 I slot print_timing: id 3 | task 9770 | prompt processing, n_tokens = 861, progress = 1.00, t = 27.06 s / 31.82 tokens per second 73.26.540.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 98764296713 73.26.540.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.216 MiB) 73.26.568.254 I slot launch_slot_: id 0 | task 9779 | processing task, is_child = 0 73.26.568.333 I slot print_timing: id 1 | task 9773 | prompt processing, n_tokens = 716, progress = 0.85, t = 27.43 s / 26.11 tokens per second 73.26.572.852 I slot print_timing: id 2 | task 9774 | prompt processing, n_tokens = 716, progress = 0.83, t = 27.43 s / 26.11 tokens per second 73.31.910.700 I slot print_timing: id 3 | task 9770 | prompt eval time = 36535.25 ms / 865 tokens ( 42.24 ms per token, 23.68 tokens per second) 73.31.910.703 I slot print_timing: id 3 | task 9770 | eval time = 5370.32 ms / 2 tokens ( 5370.32 ms per token, 0.19 tokens per second) 73.31.910.704 I slot print_timing: id 3 | task 9770 | total time = 41905.57 ms / 867 tokens 73.31.910.704 I slot print_timing: id 3 | task 9770 | graphs reused = 8266 73.31.910.704 I slot print_timing: id 3 | task 9770 | graph reallocs = 0 / 0 (same size) / (changed size) 73.31.910.763 I slot release: id 3 | task 9770 | stop processing: n_tokens = 866, truncated = 0 73.31.910.779 I slot print_timing: id 0 | task 9779 | prompt processing, n_tokens = 149, progress = 0.17, t = 5.34 s / 27.89 tokens per second 73.31.916.056 I slot print_timing: id 1 | task 9773 | prompt processing, n_tokens = 838, progress = 1.00, t = 32.80 s / 25.55 tokens per second 73.31.921.255 I slot print_timing: id 2 | task 9774 | prompt processing, n_tokens = 855, progress = 1.00, t = 32.80 s / 26.07 tokens per second 73.33.767.529 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 98779144320 73.33.767.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.654 MiB) 73.33.797.612 I slot launch_slot_: id 3 | task 9782 | processing task, is_child = 0 73.33.797.624 I slot print_timing: id 0 | task 9779 | prompt processing, n_tokens = 277, progress = 0.31, t = 7.20 s / 38.48 tokens per second 73.36.639.201 I slot print_timing: id 1 | task 9773 | prompt eval time = 34654.46 ms / 842 tokens ( 41.16 ms per token, 24.30 tokens per second) 73.36.639.205 I slot print_timing: id 1 | task 9773 | eval time = 2871.91 ms / 2 tokens ( 2871.91 ms per token, 0.35 tokens per second) 73.36.639.206 I slot print_timing: id 1 | task 9773 | total time = 37526.37 ms / 844 tokens 73.36.639.206 I slot print_timing: id 1 | task 9773 | graphs reused = 8266 73.36.639.207 I slot print_timing: id 1 | task 9773 | graph reallocs = 0 / 0 (same size) / (changed size) 73.36.639.267 I slot release: id 1 | task 9773 | stop processing: n_tokens = 843, truncated = 0 73.36.639.525 I slot print_timing: id 2 | task 9774 | prompt eval time = 34654.58 ms / 859 tokens ( 40.34 ms per token, 24.79 tokens per second) 73.36.639.528 I slot print_timing: id 2 | task 9774 | eval time = 2872.00 ms / 2 tokens ( 2872.00 ms per token, 0.35 tokens per second) 73.36.639.528 I slot print_timing: id 2 | task 9774 | total time = 37526.59 ms / 861 tokens 73.36.639.528 I slot print_timing: id 2 | task 9774 | graphs reused = 8266 73.36.639.529 I slot print_timing: id 2 | task 9774 | graph reallocs = 0 / 0 (same size) / (changed size) 73.36.639.555 I slot release: id 2 | task 9774 | stop processing: n_tokens = 860, truncated = 0 73.36.639.561 I slot print_timing: id 0 | task 9779 | prompt processing, n_tokens = 370, progress = 0.42, t = 10.07 s / 36.74 tokens per second 73.40.685.301 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 98783872824 73.40.685.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.278 MiB) 73.42.527.475 I slot launch_slot_: id 1 | task 9785 | processing task, is_child = 0 73.42.527.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.966 MiB) 73.42.560.883 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 98783873112 73.42.560.978 I slot launch_slot_: id 2 | task 9786 | processing task, is_child = 0 73.42.560.993 I slot print_timing: id 0 | task 9779 | prompt processing, n_tokens = 716, progress = 0.81, t = 14.12 s / 50.72 tokens per second 73.42.565.605 I slot print_timing: id 3 | task 9782 | prompt processing, n_tokens = 260, progress = 0.33, t = 6.89 s / 37.75 tokens per second 73.47.744.300 I slot print_timing: id 0 | task 9779 | prompt processing, n_tokens = 882, progress = 1.00, t = 21.18 s / 41.65 tokens per second 73.48.054.301 I slot print_timing: id 1 | task 9785 | prompt processing, n_tokens = 113, progress = 0.16, t = 5.18 s / 21.82 tokens per second 73.48.058.690 I slot print_timing: id 2 | task 9786 | prompt processing, n_tokens = 125, progress = 0.17, t = 5.18 s / 24.14 tokens per second 73.48.063.135 I slot print_timing: id 3 | task 9782 | prompt processing, n_tokens = 264, progress = 0.34, t = 13.95 s / 18.93 tokens per second 73.54.725.367 I slot print_timing: id 1 | task 9785 | prompt processing, n_tokens = 175, progress = 0.25, t = 12.16 s / 14.39 tokens per second 73.54.730.957 I slot print_timing: id 2 | task 9786 | prompt processing, n_tokens = 233, progress = 0.31, t = 12.16 s / 19.16 tokens per second 73.54.735.755 I slot print_timing: id 3 | task 9782 | prompt processing, n_tokens = 628, progress = 0.81, t = 20.93 s / 30.01 tokens per second 74.06.000.023 I slot print_timing: id 0 | task 9779 | prompt eval time = 28157.08 ms / 886 tokens ( 31.78 ms per token, 31.47 tokens per second) 74.06.000.029 I slot print_timing: id 0 | task 9779 | eval time = 11274.67 ms / 2 tokens (11274.67 ms per token, 0.09 tokens per second) 74.06.000.030 I slot print_timing: id 0 | task 9779 | total time = 39431.75 ms / 888 tokens 74.06.000.030 I slot print_timing: id 0 | task 9779 | graphs reused = 8266 74.06.000.031 I slot print_timing: id 0 | task 9779 | graph reallocs = 0 / 0 (same size) / (changed size) 74.06.000.076 I slot release: id 0 | task 9779 | stop processing: n_tokens = 887, truncated = 0 74.06.000.090 I slot print_timing: id 1 | task 9785 | prompt processing, n_tokens = 571, progress = 0.83, t = 23.43 s / 24.37 tokens per second 74.06.005.871 I slot print_timing: id 2 | task 9786 | prompt processing, n_tokens = 628, progress = 0.84, t = 23.43 s / 26.80 tokens per second 74.06.010.694 I slot print_timing: id 3 | task 9782 | prompt processing, n_tokens = 776, progress = 0.99, t = 32.20 s / 24.10 tokens per second 74.09.054.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 98813233633 74.09.054.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 74.09.087.582 I slot launch_slot_: id 0 | task 9791 | processing task, is_child = 0 74.09.087.665 I slot print_timing: id 1 | task 9785 | prompt processing, n_tokens = 687, progress = 0.99, t = 26.49 s / 25.94 tokens per second 74.09.092.180 I slot print_timing: id 2 | task 9786 | prompt processing, n_tokens = 745, progress = 0.99, t = 26.49 s / 28.13 tokens per second 74.11.028.616 I slot print_timing: id 3 | task 9782 | prompt eval time = 35256.68 ms / 780 tokens ( 45.20 ms per token, 22.12 tokens per second) 74.11.028.621 I slot print_timing: id 3 | task 9782 | eval time = 1974.29 ms / 2 tokens ( 1974.29 ms per token, 0.51 tokens per second) 74.11.028.621 I slot print_timing: id 3 | task 9782 | total time = 37230.97 ms / 782 tokens 74.11.028.622 I slot print_timing: id 3 | task 9782 | graphs reused = 8266 74.11.028.622 I slot print_timing: id 3 | task 9782 | graph reallocs = 0 / 0 (same size) / (changed size) 74.11.028.685 I slot release: id 3 | task 9782 | stop processing: n_tokens = 781, truncated = 0 74.12.369.024 I slot print_timing: id 1 | task 9785 | prompt eval time = 28462.71 ms / 691 tokens ( 41.19 ms per token, 24.28 tokens per second) 74.12.369.027 I slot print_timing: id 1 | task 9785 | eval time = 1340.84 ms / 2 tokens ( 1340.84 ms per token, 0.75 tokens per second) 74.12.369.028 I slot print_timing: id 1 | task 9785 | total time = 29803.54 ms / 693 tokens 74.12.369.029 I slot print_timing: id 1 | task 9785 | graphs reused = 8266 74.12.369.029 I slot print_timing: id 1 | task 9785 | graph reallocs = 0 / 0 (same size) / (changed size) 74.12.370.761 I slot release: id 1 | task 9785 | stop processing: n_tokens = 692, truncated = 0 74.12.371.186 I slot print_timing: id 2 | task 9786 | prompt eval time = 28462.87 ms / 749 tokens ( 38.00 ms per token, 26.31 tokens per second) 74.12.371.189 I slot print_timing: id 2 | task 9786 | eval time = 1342.78 ms / 2 tokens ( 1342.78 ms per token, 0.74 tokens per second) 74.12.371.189 I slot print_timing: id 2 | task 9786 | total time = 29805.65 ms / 751 tokens 74.12.371.190 I slot print_timing: id 2 | task 9786 | graphs reused = 8266 74.12.371.190 I slot print_timing: id 2 | task 9786 | graph reallocs = 0 / 0 (same size) / (changed size) 74.12.371.233 I slot release: id 2 | task 9786 | stop processing: n_tokens = 750, truncated = 0 74.12.371.244 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 74.12.371.360 I slot launch_slot_: id 1 | task 9794 | processing task, is_child = 0 74.12.371.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 849.168 MiB) 74.13.633.027 I slot print_timing: id 0 | task 9791 | prompt processing, n_tokens = 196, progress = 0.28, t = 3.28 s / 59.73 tokens per second 74.16.375.790 I slot print_timing: id 0 | task 9791 | prompt processing, n_tokens = 571, progress = 0.80, t = 7.29 s / 78.35 tokens per second 74.21.777.707 I slot print_timing: id 0 | task 9791 | prompt processing, n_tokens = 708, progress = 0.99, t = 12.69 s / 55.79 tokens per second 74.22.105.493 I slot print_timing: id 1 | task 9794 | prompt eval time = 8104.28 ms / 107 tokens ( 75.74 ms per token, 13.20 tokens per second) 74.22.105.496 I slot print_timing: id 1 | task 9794 | eval time = 327.80 ms / 2 tokens ( 327.80 ms per token, 3.05 tokens per second) 74.22.105.497 I slot print_timing: id 1 | task 9794 | total time = 8432.08 ms / 109 tokens 74.22.105.497 I slot print_timing: id 1 | task 9794 | graphs reused = 8266 74.22.105.498 I slot print_timing: id 1 | task 9794 | graph reallocs = 0 / 0 (same size) / (changed size) 74.22.105.990 I slot release: id 1 | task 9794 | stop processing: n_tokens = 679, truncated = 0 74.22.214.422 I slot print_timing: id 0 | task 9791 | prompt eval time = 13017.48 ms / 712 tokens ( 18.28 ms per token, 54.70 tokens per second) 74.22.214.424 I slot print_timing: id 0 | task 9791 | eval time = 109.34 ms / 2 tokens ( 109.34 ms per token, 9.15 tokens per second) 74.22.214.424 I slot print_timing: id 0 | task 9791 | total time = 13126.83 ms / 714 tokens 74.22.214.425 I slot print_timing: id 0 | task 9791 | graphs reused = 8266 74.22.214.425 I slot print_timing: id 0 | task 9791 | graph reallocs = 0 / 0 (same size) / (changed size) 74.22.215.481 I slot release: id 0 | task 9791 | stop processing: n_tokens = 713, truncated = 0 74.26.101.242 I srv operator(): operator(): cleaning up before exit...