/Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/2de73110cb25/Qwen3.8-27B-UD-Q5_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 0.00.099.630 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.099.687 I srv llama_server: initializing ... 0.00.099.692 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.100.210 I srv init_listene: The UI is disabled 0.00.100.212 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.100.266 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) 0.00.101.932 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/2de73110cb25/Qwen3.8-27B-UD-Q5_K_M.gguf' 0.00.634.759 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.634.767 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.634.774 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.634.777 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.634.779 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.634.787 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.634.789 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.634.791 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.634.793 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.634.795 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.634.798 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.634.801 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.634.803 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.634.805 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.634.812 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.599.435 I cmn init: llama threadpool init, n_threads = 8 0.02.044.157 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.02.049.129 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.049.249 I srv llama_server: model loaded 0.02.049.253 I srv llama_server: listening on http://127.0.0.1:8091 0.33.494.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.33.495.048 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.33.495.051 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.33.495.066 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.33.495.067 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.33.495.080 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.33.495.080 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.33.495.092 I slot launch_slot_: id 3 | task 2 | processing task, is_child = 0 0.39.051.157 I slot print_timing: id 0 | task 1 | prompt processing, n_tokens = 118, progress = 0.97, t = 5.56 s / 21.24 tokens per second 0.39.458.636 I slot print_timing: id 1 | task 0 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.56 s / 19.98 tokens per second 0.39.470.195 I slot print_timing: id 2 | task 3 | prompt processing, n_tokens = 126, progress = 0.97, t = 5.56 s / 22.68 tokens per second 0.39.481.617 I slot print_timing: id 3 | task 2 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.56 s / 19.98 tokens per second 0.40.383.054 I slot print_timing: id 0 | task 1 | prompt eval time = 6656.23 ms / 122 tokens ( 54.56 ms per token, 18.33 tokens per second) 0.40.383.057 I slot print_timing: id 0 | task 1 | eval time = 231.72 ms / 2 tokens ( 231.72 ms per token, 4.32 tokens per second) 0.40.383.057 I slot print_timing: id 0 | task 1 | total time = 6887.95 ms / 124 tokens 0.40.383.058 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.40.383.058 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.383.078 I slot release: id 0 | task 1 | stop processing: n_tokens = 123, truncated = 0 0.40.383.232 I slot print_timing: id 1 | task 0 | prompt eval time = 6656.53 ms / 115 tokens ( 57.88 ms per token, 17.28 tokens per second) 0.40.383.234 I slot print_timing: id 1 | task 0 | eval time = 231.59 ms / 2 tokens ( 231.59 ms per token, 4.32 tokens per second) 0.40.383.235 I slot print_timing: id 1 | task 0 | total time = 6888.12 ms / 117 tokens 0.40.383.235 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.40.383.235 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.383.245 I slot release: id 1 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.40.383.414 I slot print_timing: id 2 | task 3 | prompt eval time = 6656.85 ms / 130 tokens ( 51.21 ms per token, 19.53 tokens per second) 0.40.383.415 I slot print_timing: id 2 | task 3 | eval time = 231.45 ms / 2 tokens ( 231.45 ms per token, 4.32 tokens per second) 0.40.383.416 I slot print_timing: id 2 | task 3 | total time = 6888.30 ms / 132 tokens 0.40.383.416 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.40.383.416 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.383.427 I slot release: id 2 | task 3 | stop processing: n_tokens = 131, truncated = 0 0.40.383.595 I slot print_timing: id 3 | task 2 | prompt eval time = 6657.38 ms / 115 tokens ( 57.89 ms per token, 17.27 tokens per second) 0.40.383.597 I slot print_timing: id 3 | task 2 | eval time = 231.10 ms / 2 tokens ( 231.10 ms per token, 4.33 tokens per second) 0.40.383.597 I slot print_timing: id 3 | task 2 | total time = 6888.48 ms / 117 tokens 0.40.383.598 I slot print_timing: id 3 | task 2 | graphs reused = 1 0.40.383.598 I slot print_timing: id 3 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.383.609 I slot release: id 3 | task 2 | stop processing: n_tokens = 116, truncated = 0 0.40.392.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.236 0.40.414.393 I slot launch_slot_: id 0 | task 7 | processing task, is_child = 0 0.40.482.303 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.221 0.40.482.377 I slot launch_slot_: id 2 | task 8 | processing task, is_child = 0 0.40.482.411 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.40.482.453 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.40.482.471 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.241 0.40.482.502 I slot launch_slot_: id 3 | task 10 | processing task, is_child = 0 0.47.582.496 I slot print_timing: id 0 | task 7 | prompt processing, n_tokens = 104, progress = 0.96, t = 7.10 s / 14.65 tokens per second 0.48.386.552 I slot print_timing: id 1 | task 9 | prompt processing, n_tokens = 156, progress = 0.97, t = 7.10 s / 21.97 tokens per second 0.48.391.218 I slot print_timing: id 2 | task 8 | prompt processing, n_tokens = 148, progress = 0.97, t = 7.10 s / 20.85 tokens per second 0.48.396.068 I slot print_timing: id 3 | task 10 | prompt processing, n_tokens = 196, progress = 0.98, t = 7.10 s / 27.61 tokens per second 0.49.096.727 I slot print_timing: id 0 | task 7 | prompt eval time = 8385.60 ms / 108 tokens ( 77.64 ms per token, 12.88 tokens per second) 0.49.096.730 I slot print_timing: id 0 | task 7 | eval time = 228.61 ms / 2 tokens ( 228.61 ms per token, 4.37 tokens per second) 0.49.096.731 I slot print_timing: id 0 | task 7 | total time = 8614.22 ms / 110 tokens 0.49.096.732 I slot print_timing: id 0 | task 7 | graphs reused = 1 0.49.096.732 I slot print_timing: id 0 | task 7 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.096.756 I slot release: id 0 | task 7 | stop processing: n_tokens = 109, truncated = 0 0.49.096.909 I slot print_timing: id 1 | task 9 | prompt eval time = 8385.75 ms / 160 tokens ( 52.41 ms per token, 19.08 tokens per second) 0.49.096.910 I slot print_timing: id 1 | task 9 | eval time = 228.63 ms / 2 tokens ( 228.63 ms per token, 4.37 tokens per second) 0.49.096.911 I slot print_timing: id 1 | task 9 | total time = 8614.39 ms / 162 tokens 0.49.096.911 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.49.096.911 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.096.924 I slot release: id 1 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.49.097.095 I slot print_timing: id 2 | task 8 | prompt eval time = 8385.92 ms / 152 tokens ( 55.17 ms per token, 18.13 tokens per second) 0.49.097.101 I slot print_timing: id 2 | task 8 | eval time = 228.64 ms / 2 tokens ( 228.64 ms per token, 4.37 tokens per second) 0.49.097.102 I slot print_timing: id 2 | task 8 | total time = 8614.56 ms / 154 tokens 0.49.097.102 I slot print_timing: id 2 | task 8 | graphs reused = 1 0.49.097.102 I slot print_timing: id 2 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.097.113 I slot release: id 2 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.49.097.275 I slot print_timing: id 3 | task 10 | prompt eval time = 8386.08 ms / 200 tokens ( 41.93 ms per token, 23.85 tokens per second) 0.49.097.277 I slot print_timing: id 3 | task 10 | eval time = 228.66 ms / 2 tokens ( 228.66 ms per token, 4.37 tokens per second) 0.49.097.278 I slot print_timing: id 3 | task 10 | total time = 8614.73 ms / 202 tokens 0.49.097.278 I slot print_timing: id 3 | task 10 | graphs reused = 1 0.49.097.278 I slot print_timing: id 3 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.097.295 I slot release: id 3 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.49.103.240 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.257 0.49.128.670 I slot launch_slot_: id 0 | task 14 | processing task, is_child = 0 0.49.201.873 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.190 0.49.201.947 I slot launch_slot_: id 2 | task 15 | processing task, is_child = 0 0.49.201.985 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.174 0.49.202.019 I slot launch_slot_: id 1 | task 16 | processing task, is_child = 0 0.49.202.039 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.139 0.49.202.072 I slot launch_slot_: id 3 | task 17 | processing task, is_child = 0 0.55.285.254 I slot print_timing: id 0 | task 14 | prompt processing, n_tokens = 113, progress = 0.97, t = 6.08 s / 18.58 tokens per second 0.55.738.892 I slot print_timing: id 1 | task 16 | prompt processing, n_tokens = 121, progress = 0.97, t = 6.08 s / 19.89 tokens per second 0.55.743.576 I slot print_timing: id 2 | task 15 | prompt processing, n_tokens = 114, progress = 0.97, t = 6.08 s / 18.74 tokens per second 0.55.748.395 I slot print_timing: id 3 | task 17 | prompt processing, n_tokens = 146, progress = 0.97, t = 6.08 s / 24.00 tokens per second 0.56.449.756 I slot print_timing: id 0 | task 14 | prompt eval time = 7017.81 ms / 117 tokens ( 59.98 ms per token, 16.67 tokens per second) 0.56.449.758 I slot print_timing: id 0 | task 14 | eval time = 229.86 ms / 2 tokens ( 229.86 ms per token, 4.35 tokens per second) 0.56.449.759 I slot print_timing: id 0 | task 14 | total time = 7247.67 ms / 119 tokens 0.56.449.759 I slot print_timing: id 0 | task 14 | graphs reused = 1 0.56.449.760 I slot print_timing: id 0 | task 14 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.449.782 I slot release: id 0 | task 14 | stop processing: n_tokens = 118, truncated = 0 0.56.449.928 I slot print_timing: id 1 | task 16 | prompt eval time = 7018.00 ms / 125 tokens ( 56.14 ms per token, 17.81 tokens per second) 0.56.449.930 I slot print_timing: id 1 | task 16 | eval time = 229.84 ms / 2 tokens ( 229.84 ms per token, 4.35 tokens per second) 0.56.449.930 I slot print_timing: id 1 | task 16 | total time = 7247.84 ms / 127 tokens 0.56.449.930 I slot print_timing: id 1 | task 16 | graphs reused = 1 0.56.449.931 I slot print_timing: id 1 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.449.942 I slot release: id 1 | task 16 | stop processing: n_tokens = 126, truncated = 0 0.56.450.126 I slot print_timing: id 2 | task 15 | prompt eval time = 7018.18 ms / 118 tokens ( 59.48 ms per token, 16.81 tokens per second) 0.56.450.128 I slot print_timing: id 2 | task 15 | eval time = 229.84 ms / 2 tokens ( 229.84 ms per token, 4.35 tokens per second) 0.56.450.129 I slot print_timing: id 2 | task 15 | total time = 7248.02 ms / 120 tokens 0.56.450.129 I slot print_timing: id 2 | task 15 | graphs reused = 1 0.56.450.129 I slot print_timing: id 2 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.450.137 I slot release: id 2 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.56.450.316 I slot print_timing: id 3 | task 17 | prompt eval time = 7018.39 ms / 150 tokens ( 46.79 ms per token, 21.37 tokens per second) 0.56.450.320 I slot print_timing: id 3 | task 17 | eval time = 229.80 ms / 2 tokens ( 229.80 ms per token, 4.35 tokens per second) 0.56.450.321 I slot print_timing: id 3 | task 17 | total time = 7248.19 ms / 152 tokens 0.56.450.321 I slot print_timing: id 3 | task 17 | graphs reused = 1 0.56.450.321 I slot print_timing: id 3 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.450.329 I slot release: id 3 | task 17 | stop processing: n_tokens = 151, truncated = 0 0.56.456.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.237 0.56.482.475 I slot launch_slot_: id 0 | task 21 | processing task, is_child = 0 0.56.556.014 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.222 0.56.556.096 I slot launch_slot_: id 1 | task 22 | processing task, is_child = 0 0.56.556.132 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.235 0.56.556.167 I slot launch_slot_: id 2 | task 23 | processing task, is_child = 0 0.56.556.187 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.185 0.56.556.221 I slot launch_slot_: id 3 | task 24 | processing task, is_child = 0 1.03.285.553 I slot print_timing: id 0 | task 21 | prompt processing, n_tokens = 115, progress = 0.97, t = 6.73 s / 17.09 tokens per second 1.04.086.422 I slot print_timing: id 1 | task 22 | prompt processing, n_tokens = 139, progress = 0.97, t = 6.73 s / 20.66 tokens per second 1.04.091.235 I slot print_timing: id 2 | task 23 | prompt processing, n_tokens = 132, progress = 0.97, t = 6.73 s / 19.62 tokens per second 1.04.095.653 I slot print_timing: id 3 | task 24 | prompt processing, n_tokens = 177, progress = 0.98, t = 6.73 s / 26.30 tokens per second 1.04.796.687 I slot print_timing: id 0 | task 21 | prompt eval time = 8010.90 ms / 119 tokens ( 67.32 ms per token, 14.85 tokens per second) 1.04.796.693 I slot print_timing: id 0 | task 21 | eval time = 229.55 ms / 2 tokens ( 229.55 ms per token, 4.36 tokens per second) 1.04.796.695 I slot print_timing: id 0 | task 21 | total time = 8240.44 ms / 121 tokens 1.04.796.695 I slot print_timing: id 0 | task 21 | graphs reused = 1 1.04.796.695 I slot print_timing: id 0 | task 21 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.796.716 I slot release: id 0 | task 21 | stop processing: n_tokens = 120, truncated = 0 1.04.796.868 I slot print_timing: id 1 | task 22 | prompt eval time = 8011.04 ms / 143 tokens ( 56.02 ms per token, 17.85 tokens per second) 1.04.796.871 I slot print_timing: id 1 | task 22 | eval time = 229.57 ms / 2 tokens ( 229.57 ms per token, 4.36 tokens per second) 1.04.796.871 I slot print_timing: id 1 | task 22 | total time = 8240.62 ms / 145 tokens 1.04.796.872 I slot print_timing: id 1 | task 22 | graphs reused = 1 1.04.796.872 I slot print_timing: id 1 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.796.882 I slot release: id 1 | task 22 | stop processing: n_tokens = 144, truncated = 0 1.04.797.049 I slot print_timing: id 2 | task 23 | prompt eval time = 8011.19 ms / 136 tokens ( 58.91 ms per token, 16.98 tokens per second) 1.04.797.051 I slot print_timing: id 2 | task 23 | eval time = 229.59 ms / 2 tokens ( 229.59 ms per token, 4.36 tokens per second) 1.04.797.051 I slot print_timing: id 2 | task 23 | total time = 8240.78 ms / 138 tokens 1.04.797.051 I slot print_timing: id 2 | task 23 | graphs reused = 1 1.04.797.052 I slot print_timing: id 2 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.797.066 I slot release: id 2 | task 23 | stop processing: n_tokens = 137, truncated = 0 1.04.797.236 I slot print_timing: id 3 | task 24 | prompt eval time = 8011.34 ms / 181 tokens ( 44.26 ms per token, 22.59 tokens per second) 1.04.797.237 I slot print_timing: id 3 | task 24 | eval time = 229.62 ms / 2 tokens ( 229.62 ms per token, 4.36 tokens per second) 1.04.797.237 I slot print_timing: id 3 | task 24 | total time = 8240.96 ms / 183 tokens 1.04.797.237 I slot print_timing: id 3 | task 24 | graphs reused = 1 1.04.797.238 I slot print_timing: id 3 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.797.246 I slot release: id 3 | task 24 | stop processing: n_tokens = 182, truncated = 0 1.04.802.834 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.233 1.04.831.659 I slot launch_slot_: id 0 | task 28 | processing task, is_child = 0 1.04.894.585 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.194 1.04.894.678 I slot launch_slot_: id 1 | task 29 | processing task, is_child = 0 1.04.894.729 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.204 1.04.894.766 I slot launch_slot_: id 2 | task 30 | processing task, is_child = 0 1.04.894.792 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.154 1.04.898.324 I slot launch_slot_: id 3 | task 31 | processing task, is_child = 0 1.11.531.513 I slot print_timing: id 0 | task 28 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.63 s / 19.15 tokens per second 1.12.324.008 I slot print_timing: id 1 | task 29 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.63 s / 21.11 tokens per second 1.12.328.439 I slot print_timing: id 2 | task 30 | prompt processing, n_tokens = 174, progress = 0.98, t = 6.63 s / 26.23 tokens per second 1.12.332.881 I slot print_timing: id 3 | task 31 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.63 s / 17.79 tokens per second 1.13.036.692 I slot print_timing: id 0 | task 28 | prompt eval time = 7908.84 ms / 131 tokens ( 60.37 ms per token, 16.56 tokens per second) 1.13.036.694 I slot print_timing: id 0 | task 28 | eval time = 229.52 ms / 2 tokens ( 229.52 ms per token, 4.36 tokens per second) 1.13.036.695 I slot print_timing: id 0 | task 28 | total time = 8138.36 ms / 133 tokens 1.13.036.695 I slot print_timing: id 0 | task 28 | graphs reused = 1 1.13.036.696 I slot print_timing: id 0 | task 28 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.036.718 I slot release: id 0 | task 28 | stop processing: n_tokens = 132, truncated = 0 1.13.036.879 I slot print_timing: id 1 | task 29 | prompt eval time = 7908.98 ms / 144 tokens ( 54.92 ms per token, 18.21 tokens per second) 1.13.036.880 I slot print_timing: id 1 | task 29 | eval time = 229.55 ms / 2 tokens ( 229.55 ms per token, 4.36 tokens per second) 1.13.036.881 I slot print_timing: id 1 | task 29 | total time = 8138.53 ms / 146 tokens 1.13.036.881 I slot print_timing: id 1 | task 29 | graphs reused = 1 1.13.036.881 I slot print_timing: id 1 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.036.892 I slot release: id 1 | task 29 | stop processing: n_tokens = 145, truncated = 0 1.13.037.060 I slot print_timing: id 2 | task 30 | prompt eval time = 7909.13 ms / 178 tokens ( 44.43 ms per token, 22.51 tokens per second) 1.13.037.062 I slot print_timing: id 2 | task 30 | eval time = 229.57 ms / 2 tokens ( 229.57 ms per token, 4.36 tokens per second) 1.13.037.062 I slot print_timing: id 2 | task 30 | total time = 8138.69 ms / 180 tokens 1.13.037.062 I slot print_timing: id 2 | task 30 | graphs reused = 1 1.13.037.063 I slot print_timing: id 2 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.037.073 I slot release: id 2 | task 30 | stop processing: n_tokens = 179, truncated = 0 1.13.037.247 I slot print_timing: id 3 | task 31 | prompt eval time = 7909.27 ms / 122 tokens ( 64.83 ms per token, 15.42 tokens per second) 1.13.037.249 I slot print_timing: id 3 | task 31 | eval time = 229.59 ms / 2 tokens ( 229.59 ms per token, 4.36 tokens per second) 1.13.037.249 I slot print_timing: id 3 | task 31 | total time = 8138.86 ms / 124 tokens 1.13.037.249 I slot print_timing: id 3 | task 31 | graphs reused = 1 1.13.037.249 I slot print_timing: id 3 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.037.259 I slot release: id 3 | task 31 | stop processing: n_tokens = 123, truncated = 0 1.13.043.276 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.212 1.13.069.710 I slot launch_slot_: id 0 | task 35 | processing task, is_child = 0 1.13.589.290 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 1.13.592.137 I slot launch_slot_: id 3 | task 36 | processing task, is_child = 0 1.13.592.181 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 1.13.592.228 I slot launch_slot_: id 2 | task 37 | processing task, is_child = 0 1.13.592.247 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.193 1.13.592.282 I slot launch_slot_: id 1 | task 38 | processing task, is_child = 0 1.20.236.053 I slot print_timing: id 0 | task 35 | prompt processing, n_tokens = 109, progress = 0.96, t = 6.64 s / 16.41 tokens per second 1.20.423.573 I slot print_timing: id 1 | task 38 | prompt processing, n_tokens = 138, progress = 0.97, t = 6.64 s / 20.78 tokens per second 1.20.432.615 I slot print_timing: id 2 | task 37 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.64 s / 21.08 tokens per second 1.20.437.028 I slot print_timing: id 3 | task 36 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.64 s / 17.47 tokens per second 1.21.156.366 I slot print_timing: id 0 | task 35 | prompt eval time = 7331.75 ms / 113 tokens ( 64.88 ms per token, 15.41 tokens per second) 1.21.156.371 I slot print_timing: id 0 | task 35 | eval time = 231.80 ms / 2 tokens ( 231.80 ms per token, 4.31 tokens per second) 1.21.156.372 I slot print_timing: id 0 | task 35 | total time = 7563.55 ms / 115 tokens 1.21.156.372 I slot print_timing: id 0 | task 35 | graphs reused = 1 1.21.156.373 I slot print_timing: id 0 | task 35 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.157.880 I slot release: id 0 | task 35 | stop processing: n_tokens = 114, truncated = 0 1.21.158.687 I slot print_timing: id 1 | task 38 | prompt eval time = 7331.92 ms / 142 tokens ( 51.63 ms per token, 19.37 tokens per second) 1.21.158.693 I slot print_timing: id 1 | task 38 | eval time = 233.23 ms / 2 tokens ( 233.23 ms per token, 4.29 tokens per second) 1.21.158.694 I slot print_timing: id 1 | task 38 | total time = 7565.15 ms / 144 tokens 1.21.158.694 I slot print_timing: id 1 | task 38 | graphs reused = 1 1.21.158.695 I slot print_timing: id 1 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.158.720 I slot release: id 1 | task 38 | stop processing: n_tokens = 143, truncated = 0 1.21.159.082 I slot print_timing: id 2 | task 37 | prompt eval time = 7332.99 ms / 144 tokens ( 50.92 ms per token, 19.64 tokens per second) 1.21.159.083 I slot print_timing: id 2 | task 37 | eval time = 232.54 ms / 2 tokens ( 232.54 ms per token, 4.30 tokens per second) 1.21.159.084 I slot print_timing: id 2 | task 37 | total time = 7565.53 ms / 146 tokens 1.21.159.084 I slot print_timing: id 2 | task 37 | graphs reused = 1 1.21.159.084 I slot print_timing: id 2 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.159.107 I slot release: id 2 | task 37 | stop processing: n_tokens = 145, truncated = 0 1.21.159.408 I slot print_timing: id 3 | task 36 | prompt eval time = 7333.58 ms / 120 tokens ( 61.11 ms per token, 16.36 tokens per second) 1.21.159.412 I slot print_timing: id 3 | task 36 | eval time = 232.26 ms / 2 tokens ( 232.26 ms per token, 4.31 tokens per second) 1.21.159.413 I slot print_timing: id 3 | task 36 | total time = 7565.84 ms / 122 tokens 1.21.159.414 I slot print_timing: id 3 | task 36 | graphs reused = 1 1.21.159.414 I slot print_timing: id 3 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.159.437 I slot release: id 3 | task 36 | stop processing: n_tokens = 121, truncated = 0 1.21.179.853 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.246 1.21.308.053 I slot launch_slot_: id 0 | task 45 | processing task, is_child = 0 1.21.599.463 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.196 1.21.599.884 I slot launch_slot_: id 1 | task 44 | processing task, is_child = 0 1.21.599.926 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.193 1.21.599.968 I slot launch_slot_: id 2 | task 42 | processing task, is_child = 0 1.21.599.988 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 1.21.600.031 I slot launch_slot_: id 3 | task 43 | processing task, is_child = 0 1.27.835.913 I slot print_timing: id 0 | task 45 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.24 s / 19.08 tokens per second 1.28.026.067 I slot print_timing: id 1 | task 44 | prompt processing, n_tokens = 139, progress = 0.97, t = 6.24 s / 22.29 tokens per second 1.28.074.884 I slot print_timing: id 2 | task 42 | prompt processing, n_tokens = 105, progress = 0.96, t = 6.24 s / 16.84 tokens per second 1.28.082.697 I slot print_timing: id 3 | task 43 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.24 s / 17.32 tokens per second 1.28.785.093 I slot print_timing: id 0 | task 45 | prompt eval time = 6954.74 ms / 123 tokens ( 56.54 ms per token, 17.69 tokens per second) 1.28.785.096 I slot print_timing: id 0 | task 45 | eval time = 230.31 ms / 2 tokens ( 230.31 ms per token, 4.34 tokens per second) 1.28.785.099 I slot print_timing: id 0 | task 45 | total time = 7185.05 ms / 125 tokens 1.28.785.100 I slot print_timing: id 0 | task 45 | graphs reused = 1 1.28.785.100 I slot print_timing: id 0 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.785.290 I slot release: id 0 | task 45 | stop processing: n_tokens = 124, truncated = 0 1.28.785.520 I slot print_timing: id 1 | task 44 | prompt eval time = 6955.28 ms / 143 tokens ( 48.64 ms per token, 20.56 tokens per second) 1.28.785.523 I slot print_timing: id 1 | task 44 | eval time = 230.17 ms / 2 tokens ( 230.17 ms per token, 4.34 tokens per second) 1.28.785.523 I slot print_timing: id 1 | task 44 | total time = 7185.45 ms / 145 tokens 1.28.785.524 I slot print_timing: id 1 | task 44 | graphs reused = 1 1.28.785.524 I slot print_timing: id 1 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.785.569 I slot release: id 1 | task 44 | stop processing: n_tokens = 144, truncated = 0 1.28.785.750 I slot print_timing: id 2 | task 42 | prompt eval time = 6955.47 ms / 109 tokens ( 63.81 ms per token, 15.67 tokens per second) 1.28.785.752 I slot print_timing: id 2 | task 42 | eval time = 230.19 ms / 2 tokens ( 230.19 ms per token, 4.34 tokens per second) 1.28.785.752 I slot print_timing: id 2 | task 42 | total time = 7185.66 ms / 111 tokens 1.28.785.752 I slot print_timing: id 2 | task 42 | graphs reused = 1 1.28.785.753 I slot print_timing: id 2 | task 42 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.785.798 I slot release: id 2 | task 42 | stop processing: n_tokens = 110, truncated = 0 1.28.785.963 I slot print_timing: id 3 | task 43 | prompt eval time = 6955.82 ms / 112 tokens ( 62.11 ms per token, 16.10 tokens per second) 1.28.785.964 I slot print_timing: id 3 | task 43 | eval time = 230.04 ms / 2 tokens ( 230.04 ms per token, 4.35 tokens per second) 1.28.785.964 I slot print_timing: id 3 | task 43 | total time = 7185.86 ms / 114 tokens 1.28.785.965 I slot print_timing: id 3 | task 43 | graphs reused = 1 1.28.785.965 I slot print_timing: id 3 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.786.032 I slot release: id 3 | task 43 | stop processing: n_tokens = 113, truncated = 0 1.28.801.153 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.283 1.28.883.715 I slot launch_slot_: id 3 | task 49 | processing task, is_child = 0 1.29.152.889 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.226 1.29.158.651 I slot launch_slot_: id 0 | task 51 | processing task, is_child = 0 1.29.158.690 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.194 1.29.158.728 I slot launch_slot_: id 1 | task 50 | processing task, is_child = 0 1.29.158.746 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.255 1.29.158.778 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 1.35.414.897 I slot print_timing: id 0 | task 51 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.26 s / 17.26 tokens per second 1.35.610.949 I slot print_timing: id 1 | task 50 | prompt processing, n_tokens = 98, progress = 0.96, t = 6.26 s / 15.66 tokens per second 1.35.640.522 I slot print_timing: id 2 | task 52 | prompt processing, n_tokens = 132, progress = 0.97, t = 6.26 s / 21.10 tokens per second 1.35.654.629 I slot print_timing: id 3 | task 49 | prompt processing, n_tokens = 125, progress = 0.97, t = 6.26 s / 19.98 tokens per second 1.36.366.924 I slot print_timing: id 0 | task 51 | prompt eval time = 6977.45 ms / 112 tokens ( 62.30 ms per token, 16.05 tokens per second) 1.36.366.927 I slot print_timing: id 0 | task 51 | eval time = 230.68 ms / 2 tokens ( 230.68 ms per token, 4.34 tokens per second) 1.36.366.928 I slot print_timing: id 0 | task 51 | total time = 7208.13 ms / 114 tokens 1.36.366.928 I slot print_timing: id 0 | task 51 | graphs reused = 1 1.36.366.929 I slot print_timing: id 0 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.367.064 I slot release: id 0 | task 51 | stop processing: n_tokens = 113, truncated = 0 1.36.367.251 I slot print_timing: id 1 | task 50 | prompt eval time = 6977.84 ms / 102 tokens ( 68.41 ms per token, 14.62 tokens per second) 1.36.367.253 I slot print_timing: id 1 | task 50 | eval time = 230.61 ms / 2 tokens ( 230.61 ms per token, 4.34 tokens per second) 1.36.367.254 I slot print_timing: id 1 | task 50 | total time = 7208.45 ms / 104 tokens 1.36.367.254 I slot print_timing: id 1 | task 50 | graphs reused = 1 1.36.367.255 I slot print_timing: id 1 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.367.315 I slot release: id 1 | task 50 | stop processing: n_tokens = 103, truncated = 0 1.36.367.566 I slot print_timing: id 2 | task 52 | prompt eval time = 6978.46 ms / 136 tokens ( 51.31 ms per token, 19.49 tokens per second) 1.36.367.570 I slot print_timing: id 2 | task 52 | eval time = 230.28 ms / 2 tokens ( 230.28 ms per token, 4.34 tokens per second) 1.36.367.570 I slot print_timing: id 2 | task 52 | total time = 7208.74 ms / 138 tokens 1.36.367.570 I slot print_timing: id 2 | task 52 | graphs reused = 1 1.36.367.571 I slot print_timing: id 2 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.367.625 I slot release: id 2 | task 52 | stop processing: n_tokens = 137, truncated = 0 1.36.367.809 I slot print_timing: id 3 | task 49 | prompt eval time = 6979.15 ms / 129 tokens ( 54.10 ms per token, 18.48 tokens per second) 1.36.367.812 I slot print_timing: id 3 | task 49 | eval time = 229.83 ms / 2 tokens ( 229.83 ms per token, 4.35 tokens per second) 1.36.367.813 I slot print_timing: id 3 | task 49 | total time = 7208.98 ms / 131 tokens 1.36.367.813 I slot print_timing: id 3 | task 49 | graphs reused = 1 1.36.367.813 I slot print_timing: id 3 | task 49 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.367.917 I slot release: id 3 | task 49 | stop processing: n_tokens = 130, truncated = 0 1.36.377.529 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.248 1.36.406.507 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 1.36.406.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 1.36.463.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 1.36.642.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 1.36.767.823 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.272 1.36.768.161 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 1.36.768.198 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.204 1.36.768.240 I slot launch_slot_: id 2 | task 57 | processing task, is_child = 0 1.36.768.257 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.215 1.36.768.291 I slot launch_slot_: id 3 | task 59 | processing task, is_child = 0 1.44.895.928 I slot print_timing: id 0 | task 56 | prompt processing, n_tokens = 128, progress = 0.97, t = 8.13 s / 15.75 tokens per second 1.45.088.410 I slot print_timing: id 1 | task 58 | prompt processing, n_tokens = 162, progress = 0.98, t = 8.13 s / 19.93 tokens per second 1.45.097.851 I slot print_timing: id 2 | task 57 | prompt processing, n_tokens = 178, progress = 0.98, t = 8.13 s / 21.90 tokens per second 1.45.114.477 I slot print_timing: id 3 | task 59 | prompt processing, n_tokens = 173, progress = 0.98, t = 8.13 s / 21.29 tokens per second 1.45.819.604 I slot print_timing: id 0 | task 56 | prompt eval time = 8819.76 ms / 132 tokens ( 66.82 ms per token, 14.97 tokens per second) 1.45.819.607 I slot print_timing: id 0 | task 56 | eval time = 231.53 ms / 2 tokens ( 231.53 ms per token, 4.32 tokens per second) 1.45.819.609 I slot print_timing: id 0 | task 56 | total time = 9051.30 ms / 134 tokens 1.45.819.609 I slot print_timing: id 0 | task 56 | graphs reused = 1 1.45.819.609 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.819.756 I slot release: id 0 | task 56 | stop processing: n_tokens = 133, truncated = 0 1.45.820.033 I slot print_timing: id 1 | task 58 | prompt eval time = 8820.20 ms / 166 tokens ( 53.13 ms per token, 18.82 tokens per second) 1.45.820.037 I slot print_timing: id 1 | task 58 | eval time = 231.50 ms / 2 tokens ( 231.50 ms per token, 4.32 tokens per second) 1.45.820.037 I slot print_timing: id 1 | task 58 | total time = 9051.70 ms / 168 tokens 1.45.820.038 I slot print_timing: id 1 | task 58 | graphs reused = 1 1.45.820.043 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.820.112 I slot release: id 1 | task 58 | stop processing: n_tokens = 167, truncated = 0 1.45.820.457 I slot print_timing: id 2 | task 57 | prompt eval time = 8821.15 ms / 182 tokens ( 48.47 ms per token, 20.63 tokens per second) 1.45.820.460 I slot print_timing: id 2 | task 57 | eval time = 230.97 ms / 2 tokens ( 230.97 ms per token, 4.33 tokens per second) 1.45.820.460 I slot print_timing: id 2 | task 57 | total time = 9052.11 ms / 184 tokens 1.45.820.460 I slot print_timing: id 2 | task 57 | graphs reused = 1 1.45.820.461 I slot print_timing: id 2 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.820.581 I slot release: id 2 | task 57 | stop processing: n_tokens = 183, truncated = 0 1.45.820.923 I slot print_timing: id 3 | task 59 | prompt eval time = 8821.92 ms / 177 tokens ( 49.84 ms per token, 20.06 tokens per second) 1.45.820.926 I slot print_timing: id 3 | task 59 | eval time = 230.65 ms / 2 tokens ( 230.65 ms per token, 4.34 tokens per second) 1.45.820.926 I slot print_timing: id 3 | task 59 | total time = 9052.56 ms / 179 tokens 1.45.820.926 I slot print_timing: id 3 | task 59 | graphs reused = 1 1.45.820.927 I slot print_timing: id 3 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.821.108 I slot release: id 3 | task 59 | stop processing: n_tokens = 178, truncated = 0 1.45.830.282 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 1.45.830.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 1.45.963.342 I slot launch_slot_: id 0 | task 65 | processing task, is_child = 0 1.45.963.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 1.46.217.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.820 MiB) 1.46.457.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.630 MiB) 1.46.750.636 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.168 1.46.750.840 I slot launch_slot_: id 1 | task 66 | processing task, is_child = 0 1.46.750.888 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.153 1.46.750.968 I slot launch_slot_: id 2 | task 64 | processing task, is_child = 0 1.46.750.988 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.157 1.46.785.859 I slot launch_slot_: id 3 | task 63 | processing task, is_child = 0 1.53.825.357 I slot print_timing: id 0 | task 65 | prompt processing, n_tokens = 119, progress = 0.97, t = 7.04 s / 16.90 tokens per second 1.54.272.817 I slot print_timing: id 1 | task 66 | prompt processing, n_tokens = 165, progress = 0.98, t = 7.04 s / 23.44 tokens per second 1.54.291.518 I slot print_timing: id 2 | task 64 | prompt processing, n_tokens = 145, progress = 0.97, t = 7.04 s / 20.60 tokens per second 1.54.296.064 I slot print_timing: id 3 | task 63 | prompt processing, n_tokens = 136, progress = 0.97, t = 7.04 s / 19.32 tokens per second 1.55.023.028 I slot print_timing: id 0 | task 65 | prompt eval time = 8006.68 ms / 123 tokens ( 65.09 ms per token, 15.36 tokens per second) 1.55.023.032 I slot print_timing: id 0 | task 65 | eval time = 230.47 ms / 2 tokens ( 230.47 ms per token, 4.34 tokens per second) 1.55.023.033 I slot print_timing: id 0 | task 65 | total time = 8237.15 ms / 125 tokens 1.55.023.033 I slot print_timing: id 0 | task 65 | graphs reused = 1 1.55.023.033 I slot print_timing: id 0 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.023.170 I slot release: id 0 | task 65 | stop processing: n_tokens = 124, truncated = 0 1.55.023.333 I slot print_timing: id 1 | task 66 | prompt eval time = 8006.86 ms / 169 tokens ( 47.38 ms per token, 21.11 tokens per second) 1.55.023.335 I slot print_timing: id 1 | task 66 | eval time = 230.57 ms / 2 tokens ( 230.57 ms per token, 4.34 tokens per second) 1.55.023.336 I slot print_timing: id 1 | task 66 | total time = 8237.43 ms / 171 tokens 1.55.023.336 I slot print_timing: id 1 | task 66 | graphs reused = 1 1.55.023.336 I slot print_timing: id 1 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.023.395 I slot release: id 1 | task 66 | stop processing: n_tokens = 170, truncated = 0 1.55.023.647 I slot print_timing: id 2 | task 64 | prompt eval time = 8007.28 ms / 149 tokens ( 53.74 ms per token, 18.61 tokens per second) 1.55.023.649 I slot print_timing: id 2 | task 64 | eval time = 230.45 ms / 2 tokens ( 230.45 ms per token, 4.34 tokens per second) 1.55.023.650 I slot print_timing: id 2 | task 64 | total time = 8237.73 ms / 151 tokens 1.55.023.652 I slot print_timing: id 2 | task 64 | graphs reused = 1 1.55.023.652 I slot print_timing: id 2 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.023.703 I slot release: id 2 | task 64 | stop processing: n_tokens = 150, truncated = 0 1.55.023.884 I slot print_timing: id 3 | task 63 | prompt eval time = 8007.99 ms / 140 tokens ( 57.20 ms per token, 17.48 tokens per second) 1.55.023.887 I slot print_timing: id 3 | task 63 | eval time = 229.97 ms / 2 tokens ( 229.97 ms per token, 4.35 tokens per second) 1.55.023.888 I slot print_timing: id 3 | task 63 | total time = 8237.95 ms / 142 tokens 1.55.023.888 I slot print_timing: id 3 | task 63 | graphs reused = 1 1.55.023.889 I slot print_timing: id 3 | task 63 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.023.929 I slot release: id 3 | task 63 | stop processing: n_tokens = 141, truncated = 0 1.55.032.698 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 1.55.060.137 I slot launch_slot_: id 3 | task 71 | processing task, is_child = 0 1.55.060.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 1.55.200.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 1.55.311.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.694 MiB) 1.55.590.672 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.234 1.55.590.759 I slot launch_slot_: id 0 | task 70 | processing task, is_child = 0 1.55.590.796 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.165 1.55.590.829 I slot launch_slot_: id 1 | task 72 | processing task, is_child = 0 1.55.590.847 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.187 1.55.590.883 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 2.02.573.644 I slot print_timing: id 0 | task 70 | prompt processing, n_tokens = 159, progress = 0.98, t = 6.98 s / 22.77 tokens per second 2.03.365.213 I slot print_timing: id 1 | task 72 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.98 s / 17.76 tokens per second 2.03.379.174 I slot print_timing: id 2 | task 73 | prompt processing, n_tokens = 157, progress = 0.98, t = 6.98 s / 22.48 tokens per second 2.03.403.215 I slot print_timing: id 3 | task 71 | prompt processing, n_tokens = 107, progress = 0.96, t = 6.98 s / 15.32 tokens per second 2.04.135.647 I slot print_timing: id 0 | task 70 | prompt eval time = 8314.41 ms / 163 tokens ( 51.01 ms per token, 19.60 tokens per second) 2.04.135.652 I slot print_timing: id 0 | task 70 | eval time = 230.34 ms / 2 tokens ( 230.34 ms per token, 4.34 tokens per second) 2.04.135.652 I slot print_timing: id 0 | task 70 | total time = 8544.76 ms / 165 tokens 2.04.135.653 I slot print_timing: id 0 | task 70 | graphs reused = 1 2.04.135.653 I slot print_timing: id 0 | task 70 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.135.791 I slot release: id 0 | task 70 | stop processing: n_tokens = 164, truncated = 0 2.04.135.947 I slot print_timing: id 1 | task 72 | prompt eval time = 8314.76 ms / 128 tokens ( 64.96 ms per token, 15.39 tokens per second) 2.04.135.949 I slot print_timing: id 1 | task 72 | eval time = 230.28 ms / 2 tokens ( 230.28 ms per token, 4.34 tokens per second) 2.04.135.949 I slot print_timing: id 1 | task 72 | total time = 8545.04 ms / 130 tokens 2.04.135.950 I slot print_timing: id 1 | task 72 | graphs reused = 1 2.04.135.950 I slot print_timing: id 1 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.135.982 I slot release: id 1 | task 72 | stop processing: n_tokens = 129, truncated = 0 2.04.136.306 I slot print_timing: id 2 | task 73 | prompt eval time = 8315.12 ms / 161 tokens ( 51.65 ms per token, 19.36 tokens per second) 2.04.136.309 I slot print_timing: id 2 | task 73 | eval time = 230.26 ms / 2 tokens ( 230.26 ms per token, 4.34 tokens per second) 2.04.136.309 I slot print_timing: id 2 | task 73 | total time = 8545.38 ms / 163 tokens 2.04.136.310 I slot print_timing: id 2 | task 73 | graphs reused = 1 2.04.136.310 I slot print_timing: id 2 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.136.378 I slot release: id 2 | task 73 | stop processing: n_tokens = 162, truncated = 0 2.04.136.572 I slot print_timing: id 3 | task 71 | prompt eval time = 8315.72 ms / 111 tokens ( 74.92 ms per token, 13.35 tokens per second) 2.04.136.573 I slot print_timing: id 3 | task 71 | eval time = 229.91 ms / 2 tokens ( 229.91 ms per token, 4.35 tokens per second) 2.04.136.573 I slot print_timing: id 3 | task 71 | total time = 8545.63 ms / 113 tokens 2.04.136.573 I slot print_timing: id 3 | task 71 | graphs reused = 1 2.04.136.573 I slot print_timing: id 3 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.136.663 I slot release: id 3 | task 71 | stop processing: n_tokens = 112, truncated = 0 2.04.147.122 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.171 2.04.147.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.755 MiB) 2.04.604.547 I slot launch_slot_: id 0 | task 77 | processing task, is_child = 0 2.04.604.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 2.04.991.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 2.05.134.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.632 MiB) 2.05.799.919 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.217 2.05.800.106 I slot launch_slot_: id 1 | task 78 | processing task, is_child = 0 2.05.800.145 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.179 2.05.800.191 I slot launch_slot_: id 2 | task 79 | processing task, is_child = 0 2.05.800.211 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.250 2.05.800.248 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 2.12.207.347 I slot print_timing: id 0 | task 77 | prompt processing, n_tokens = 163, progress = 0.98, t = 6.41 s / 25.44 tokens per second 2.13.018.241 I slot print_timing: id 1 | task 78 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.41 s / 16.86 tokens per second 2.13.027.032 I slot print_timing: id 2 | task 79 | prompt processing, n_tokens = 105, progress = 0.96, t = 6.41 s / 16.39 tokens per second 2.13.079.723 I slot print_timing: id 3 | task 80 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.41 s / 24.97 tokens per second 2.13.792.926 I slot print_timing: id 0 | task 77 | prompt eval time = 7762.09 ms / 167 tokens ( 46.48 ms per token, 21.51 tokens per second) 2.13.792.929 I slot print_timing: id 0 | task 77 | eval time = 230.57 ms / 2 tokens ( 230.57 ms per token, 4.34 tokens per second) 2.13.792.929 I slot print_timing: id 0 | task 77 | total time = 7992.66 ms / 169 tokens 2.13.792.929 I slot print_timing: id 0 | task 77 | graphs reused = 1 2.13.792.930 I slot print_timing: id 0 | task 77 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.793.122 I slot release: id 0 | task 77 | stop processing: n_tokens = 168, truncated = 0 2.13.793.280 I slot print_timing: id 1 | task 78 | prompt eval time = 7762.40 ms / 112 tokens ( 69.31 ms per token, 14.43 tokens per second) 2.13.793.284 I slot print_timing: id 1 | task 78 | eval time = 230.60 ms / 2 tokens ( 230.60 ms per token, 4.34 tokens per second) 2.13.793.285 I slot print_timing: id 1 | task 78 | total time = 7993.00 ms / 114 tokens 2.13.793.285 I slot print_timing: id 1 | task 78 | graphs reused = 1 2.13.793.285 I slot print_timing: id 1 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.793.332 I slot release: id 1 | task 78 | stop processing: n_tokens = 113, truncated = 0 2.13.793.494 I slot print_timing: id 2 | task 79 | prompt eval time = 7763.13 ms / 109 tokens ( 71.22 ms per token, 14.04 tokens per second) 2.13.793.495 I slot print_timing: id 2 | task 79 | eval time = 230.07 ms / 2 tokens ( 230.07 ms per token, 4.35 tokens per second) 2.13.793.496 I slot print_timing: id 2 | task 79 | total time = 7993.20 ms / 111 tokens 2.13.793.496 I slot print_timing: id 2 | task 79 | graphs reused = 1 2.13.793.496 I slot print_timing: id 2 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.793.538 I slot release: id 2 | task 79 | stop processing: n_tokens = 110, truncated = 0 2.13.793.706 I slot print_timing: id 3 | task 80 | prompt eval time = 7763.50 ms / 164 tokens ( 47.34 ms per token, 21.12 tokens per second) 2.13.793.708 I slot print_timing: id 3 | task 80 | eval time = 229.90 ms / 2 tokens ( 229.90 ms per token, 4.35 tokens per second) 2.13.793.709 I slot print_timing: id 3 | task 80 | total time = 7993.40 ms / 166 tokens 2.13.793.709 I slot print_timing: id 3 | task 80 | graphs reused = 1 2.13.793.709 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.793.775 I slot release: id 3 | task 80 | stop processing: n_tokens = 165, truncated = 0 2.13.804.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.167 2.13.804.899 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 2.14.110.838 I slot launch_slot_: id 0 | task 84 | processing task, is_child = 0 2.14.110.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.14.679.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.444 MiB) 2.15.340.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 2.15.997.707 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.248 2.16.005.627 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 2.16.005.678 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.255 2.16.005.725 I slot launch_slot_: id 2 | task 86 | processing task, is_child = 0 2.16.005.747 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.170 2.16.005.786 I slot launch_slot_: id 3 | task 87 | processing task, is_child = 0 2.22.476.657 I slot print_timing: id 0 | task 84 | prompt processing, n_tokens = 143, progress = 0.97, t = 6.47 s / 22.10 tokens per second 2.22.869.243 I slot print_timing: id 1 | task 85 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.47 s / 18.24 tokens per second 2.22.897.361 I slot print_timing: id 2 | task 86 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.47 s / 19.63 tokens per second 2.22.904.727 I slot print_timing: id 3 | task 87 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.47 s / 17.93 tokens per second 2.23.818.519 I slot print_timing: id 0 | task 84 | prompt eval time = 7581.81 ms / 147 tokens ( 51.58 ms per token, 19.39 tokens per second) 2.23.818.522 I slot print_timing: id 0 | task 84 | eval time = 230.91 ms / 2 tokens ( 230.91 ms per token, 4.33 tokens per second) 2.23.818.522 I slot print_timing: id 0 | task 84 | total time = 7812.72 ms / 149 tokens 2.23.818.523 I slot print_timing: id 0 | task 84 | graphs reused = 1 2.23.818.523 I slot print_timing: id 0 | task 84 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.818.666 I slot release: id 0 | task 84 | stop processing: n_tokens = 148, truncated = 0 2.23.818.869 I slot print_timing: id 1 | task 85 | prompt eval time = 7582.10 ms / 122 tokens ( 62.15 ms per token, 16.09 tokens per second) 2.23.818.872 I slot print_timing: id 1 | task 85 | eval time = 230.94 ms / 2 tokens ( 230.94 ms per token, 4.33 tokens per second) 2.23.818.877 I slot print_timing: id 1 | task 85 | total time = 7813.03 ms / 124 tokens 2.23.818.877 I slot print_timing: id 1 | task 85 | graphs reused = 1 2.23.818.878 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.822.644 I slot release: id 1 | task 85 | stop processing: n_tokens = 123, truncated = 0 2.23.822.812 I slot print_timing: id 2 | task 86 | prompt eval time = 7582.66 ms / 131 tokens ( 57.88 ms per token, 17.28 tokens per second) 2.23.822.814 I slot print_timing: id 2 | task 86 | eval time = 234.30 ms / 2 tokens ( 234.30 ms per token, 4.27 tokens per second) 2.23.822.815 I slot print_timing: id 2 | task 86 | total time = 7816.96 ms / 133 tokens 2.23.822.815 I slot print_timing: id 2 | task 86 | graphs reused = 1 2.23.822.816 I slot print_timing: id 2 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.823.669 I slot release: id 2 | task 86 | stop processing: n_tokens = 132, truncated = 0 2.23.823.891 I slot print_timing: id 3 | task 87 | prompt eval time = 7583.34 ms / 120 tokens ( 63.19 ms per token, 15.82 tokens per second) 2.23.823.894 I slot print_timing: id 3 | task 87 | eval time = 234.69 ms / 2 tokens ( 234.69 ms per token, 4.26 tokens per second) 2.23.823.894 I slot print_timing: id 3 | task 87 | total time = 7818.03 ms / 122 tokens 2.23.823.894 I slot print_timing: id 3 | task 87 | graphs reused = 1 2.23.823.900 I slot print_timing: id 3 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.824.511 I slot release: id 3 | task 87 | stop processing: n_tokens = 121, truncated = 0 2.23.833.266 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.236 2.23.859.318 I slot launch_slot_: id 1 | task 91 | processing task, is_child = 0 2.23.859.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.380 MiB) 2.24.295.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 2.24.653.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 2.25.068.177 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.189 2.25.074.589 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 2.25.074.634 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.212 2.25.074.676 I slot launch_slot_: id 2 | task 93 | processing task, is_child = 0 2.25.074.696 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.231 2.25.074.734 I slot launch_slot_: id 3 | task 94 | processing task, is_child = 0 2.31.632.401 I slot print_timing: id 0 | task 92 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.56 s / 20.89 tokens per second 2.32.037.157 I slot print_timing: id 1 | task 91 | prompt processing, n_tokens = 127, progress = 0.97, t = 6.56 s / 19.37 tokens per second 2.32.069.275 I slot print_timing: id 2 | task 93 | prompt processing, n_tokens = 140, progress = 0.97, t = 6.56 s / 21.35 tokens per second 2.32.073.657 I slot print_timing: id 3 | task 94 | prompt processing, n_tokens = 120, progress = 0.97, t = 6.56 s / 18.30 tokens per second 2.33.216.559 I slot print_timing: id 0 | task 92 | prompt eval time = 7910.94 ms / 141 tokens ( 56.11 ms per token, 17.82 tokens per second) 2.33.216.561 I slot print_timing: id 0 | task 92 | eval time = 230.86 ms / 2 tokens ( 230.86 ms per token, 4.33 tokens per second) 2.33.216.562 I slot print_timing: id 0 | task 92 | total time = 8141.81 ms / 143 tokens 2.33.216.562 I slot print_timing: id 0 | task 92 | graphs reused = 1 2.33.216.563 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.216.738 I slot release: id 0 | task 92 | stop processing: n_tokens = 142, truncated = 0 2.33.216.928 I slot print_timing: id 1 | task 91 | prompt eval time = 7911.42 ms / 131 tokens ( 60.39 ms per token, 16.56 tokens per second) 2.33.216.930 I slot print_timing: id 1 | task 91 | eval time = 230.75 ms / 2 tokens ( 230.75 ms per token, 4.33 tokens per second) 2.33.216.930 I slot print_timing: id 1 | task 91 | total time = 8142.17 ms / 133 tokens 2.33.216.931 I slot print_timing: id 1 | task 91 | graphs reused = 1 2.33.216.931 I slot print_timing: id 1 | task 91 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.217.457 I slot release: id 1 | task 91 | stop processing: n_tokens = 132, truncated = 0 2.33.217.765 I slot print_timing: id 2 | task 93 | prompt eval time = 7912.06 ms / 144 tokens ( 54.94 ms per token, 18.20 tokens per second) 2.33.217.769 I slot print_timing: id 2 | task 93 | eval time = 230.93 ms / 2 tokens ( 230.93 ms per token, 4.33 tokens per second) 2.33.217.769 I slot print_timing: id 2 | task 93 | total time = 8142.98 ms / 146 tokens 2.33.217.769 I slot print_timing: id 2 | task 93 | graphs reused = 1 2.33.217.770 I slot print_timing: id 2 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.218.612 I slot release: id 2 | task 93 | stop processing: n_tokens = 145, truncated = 0 2.33.218.917 I slot print_timing: id 3 | task 94 | prompt eval time = 7912.52 ms / 124 tokens ( 63.81 ms per token, 15.67 tokens per second) 2.33.218.920 I slot print_timing: id 3 | task 94 | eval time = 231.60 ms / 2 tokens ( 231.60 ms per token, 4.32 tokens per second) 2.33.218.920 I slot print_timing: id 3 | task 94 | total time = 8144.12 ms / 126 tokens 2.33.218.920 I slot print_timing: id 3 | task 94 | graphs reused = 1 2.33.218.921 I slot print_timing: id 3 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.219.087 I slot release: id 3 | task 94 | stop processing: n_tokens = 125, truncated = 0 2.33.228.134 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.197 2.33.276.976 I slot launch_slot_: id 0 | task 99 | processing task, is_child = 0 2.33.277.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 2.33.672.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 2.34.289.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.256 MiB) 2.34.709.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.212 2.34.709.142 I slot launch_slot_: id 1 | task 98 | processing task, is_child = 0 2.34.709.180 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 2.34.709.222 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 2.34.709.243 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.224 2.34.709.280 I slot launch_slot_: id 3 | task 101 | processing task, is_child = 0 2.40.738.335 I slot print_timing: id 0 | task 99 | prompt processing, n_tokens = 117, progress = 0.97, t = 6.03 s / 19.41 tokens per second 2.41.543.285 I slot print_timing: id 1 | task 98 | prompt processing, n_tokens = 168, progress = 0.98, t = 6.03 s / 27.87 tokens per second 2.41.583.991 I slot print_timing: id 2 | task 100 | prompt processing, n_tokens = 114, progress = 0.97, t = 6.03 s / 18.91 tokens per second 2.41.595.354 I slot print_timing: id 3 | task 101 | prompt processing, n_tokens = 103, progress = 0.96, t = 6.03 s / 17.08 tokens per second 2.42.308.311 I slot print_timing: id 0 | task 99 | prompt eval time = 7367.60 ms / 121 tokens ( 60.89 ms per token, 16.42 tokens per second) 2.42.308.314 I slot print_timing: id 0 | task 99 | eval time = 231.40 ms / 2 tokens ( 231.40 ms per token, 4.32 tokens per second) 2.42.308.315 I slot print_timing: id 0 | task 99 | total time = 7599.01 ms / 123 tokens 2.42.308.315 I slot print_timing: id 0 | task 99 | graphs reused = 1 2.42.308.315 I slot print_timing: id 0 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.308.447 I slot release: id 0 | task 99 | stop processing: n_tokens = 122, truncated = 0 2.42.308.681 I slot print_timing: id 1 | task 98 | prompt eval time = 7367.95 ms / 172 tokens ( 42.84 ms per token, 23.34 tokens per second) 2.42.308.685 I slot print_timing: id 1 | task 98 | eval time = 231.40 ms / 2 tokens ( 231.40 ms per token, 4.32 tokens per second) 2.42.308.686 I slot print_timing: id 1 | task 98 | total time = 7599.35 ms / 174 tokens 2.42.308.686 I slot print_timing: id 1 | task 98 | graphs reused = 1 2.42.309.716 I slot print_timing: id 1 | task 98 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.309.824 I slot release: id 1 | task 98 | stop processing: n_tokens = 173, truncated = 0 2.42.310.417 I slot print_timing: id 2 | task 100 | prompt eval time = 7368.68 ms / 118 tokens ( 62.45 ms per token, 16.01 tokens per second) 2.42.310.421 I slot print_timing: id 2 | task 100 | eval time = 232.39 ms / 2 tokens ( 232.39 ms per token, 4.30 tokens per second) 2.42.310.421 I slot print_timing: id 2 | task 100 | total time = 7601.07 ms / 120 tokens 2.42.310.421 I slot print_timing: id 2 | task 100 | graphs reused = 1 2.42.310.422 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.311.248 I slot release: id 2 | task 100 | stop processing: n_tokens = 119, truncated = 0 2.42.311.672 I slot print_timing: id 3 | task 101 | prompt eval time = 7369.43 ms / 107 tokens ( 68.87 ms per token, 14.52 tokens per second) 2.42.311.675 I slot print_timing: id 3 | task 101 | eval time = 232.88 ms / 2 tokens ( 232.88 ms per token, 4.29 tokens per second) 2.42.311.675 I slot print_timing: id 3 | task 101 | total time = 7602.31 ms / 109 tokens 2.42.311.675 I slot print_timing: id 3 | task 101 | graphs reused = 1 2.42.311.676 I slot print_timing: id 3 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.312.323 I slot release: id 3 | task 101 | stop processing: n_tokens = 108, truncated = 0 2.42.325.151 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 2.42.325.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.130 MiB) 2.42.666.458 I slot launch_slot_: id 0 | task 105 | processing task, is_child = 0 2.42.666.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.693 MiB) 2.42.972.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 2.43.778.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 2.44.162.659 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.244 2.44.162.788 I slot launch_slot_: id 2 | task 106 | processing task, is_child = 0 2.44.162.825 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.269 2.44.162.863 I slot launch_slot_: id 3 | task 107 | processing task, is_child = 0 2.44.162.890 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.162 2.44.162.924 I slot launch_slot_: id 1 | task 108 | processing task, is_child = 0 2.51.905.018 I slot print_timing: id 0 | task 105 | prompt processing, n_tokens = 236, progress = 0.98, t = 7.74 s / 30.48 tokens per second 2.52.352.900 I slot print_timing: id 1 | task 108 | prompt processing, n_tokens = 173, progress = 0.98, t = 7.74 s / 22.35 tokens per second 2.52.372.646 I slot print_timing: id 2 | task 106 | prompt processing, n_tokens = 112, progress = 0.97, t = 7.74 s / 14.47 tokens per second 2.52.384.459 I slot print_timing: id 3 | task 107 | prompt processing, n_tokens = 132, progress = 0.97, t = 7.74 s / 17.05 tokens per second 2.53.086.903 I slot print_timing: id 0 | task 105 | prompt eval time = 8693.48 ms / 240 tokens ( 36.22 ms per token, 27.61 tokens per second) 2.53.086.905 I slot print_timing: id 0 | task 105 | eval time = 230.48 ms / 2 tokens ( 230.48 ms per token, 4.34 tokens per second) 2.53.086.907 I slot print_timing: id 0 | task 105 | total time = 8923.97 ms / 242 tokens 2.53.086.908 I slot print_timing: id 0 | task 105 | graphs reused = 1 2.53.086.908 I slot print_timing: id 0 | task 105 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.089.906 I slot release: id 0 | task 105 | stop processing: n_tokens = 241, truncated = 0 2.53.090.211 I slot print_timing: id 1 | task 108 | prompt eval time = 8693.97 ms / 177 tokens ( 49.12 ms per token, 20.36 tokens per second) 2.53.090.218 I slot print_timing: id 1 | task 108 | eval time = 233.29 ms / 2 tokens ( 233.29 ms per token, 4.29 tokens per second) 2.53.090.218 I slot print_timing: id 1 | task 108 | total time = 8927.26 ms / 179 tokens 2.53.090.219 I slot print_timing: id 1 | task 108 | graphs reused = 1 2.53.090.219 I slot print_timing: id 1 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.091.324 I slot release: id 1 | task 108 | stop processing: n_tokens = 178, truncated = 0 2.53.091.642 I slot print_timing: id 2 | task 106 | prompt eval time = 8694.16 ms / 116 tokens ( 74.95 ms per token, 13.34 tokens per second) 2.53.091.644 I slot print_timing: id 2 | task 106 | eval time = 234.51 ms / 2 tokens ( 234.51 ms per token, 4.26 tokens per second) 2.53.091.645 I slot print_timing: id 2 | task 106 | total time = 8928.67 ms / 118 tokens 2.53.091.645 I slot print_timing: id 2 | task 106 | graphs reused = 1 2.53.091.645 I slot print_timing: id 2 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.091.744 I slot release: id 2 | task 106 | stop processing: n_tokens = 117, truncated = 0 2.53.092.071 I slot print_timing: id 3 | task 107 | prompt eval time = 8694.55 ms / 136 tokens ( 63.93 ms per token, 15.64 tokens per second) 2.53.092.078 I slot print_timing: id 3 | task 107 | eval time = 234.54 ms / 2 tokens ( 234.54 ms per token, 4.26 tokens per second) 2.53.092.078 I slot print_timing: id 3 | task 107 | total time = 8929.08 ms / 138 tokens 2.53.092.078 I slot print_timing: id 3 | task 107 | graphs reused = 1 2.53.092.079 I slot print_timing: id 3 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.093.147 I slot release: id 3 | task 107 | stop processing: n_tokens = 137, truncated = 0 2.53.104.626 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 2.53.104.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.568 MiB) 2.53.493.614 I slot launch_slot_: id 2 | task 112 | processing task, is_child = 0 2.53.493.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 2.53.991.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 2.54.646.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 2.55.176.721 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.212 2.55.192.269 I slot launch_slot_: id 3 | task 113 | processing task, is_child = 0 2.55.192.330 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 2.55.192.372 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 2.55.192.398 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.157 2.55.192.439 I slot launch_slot_: id 1 | task 115 | processing task, is_child = 0 3.04.170.725 I slot print_timing: id 0 | task 114 | prompt processing, n_tokens = 156, progress = 0.97, t = 8.98 s / 17.38 tokens per second 3.04.575.700 I slot print_timing: id 1 | task 115 | prompt processing, n_tokens = 222, progress = 0.98, t = 8.98 s / 24.73 tokens per second 3.04.580.460 I slot print_timing: id 2 | task 112 | prompt processing, n_tokens = 138, progress = 0.97, t = 8.98 s / 15.37 tokens per second 3.04.596.285 I slot print_timing: id 3 | task 113 | prompt processing, n_tokens = 151, progress = 0.97, t = 8.98 s / 16.82 tokens per second 3.05.324.881 I slot print_timing: id 0 | task 114 | prompt eval time = 9901.66 ms / 160 tokens ( 61.89 ms per token, 16.16 tokens per second) 3.05.324.886 I slot print_timing: id 0 | task 114 | eval time = 230.77 ms / 2 tokens ( 230.77 ms per token, 4.33 tokens per second) 3.05.324.887 I slot print_timing: id 0 | task 114 | total time = 10132.43 ms / 162 tokens 3.05.324.887 I slot print_timing: id 0 | task 114 | graphs reused = 1 3.05.324.888 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.326.181 I slot release: id 0 | task 114 | stop processing: n_tokens = 161, truncated = 0 3.05.326.628 I slot print_timing: id 1 | task 115 | prompt eval time = 9902.03 ms / 226 tokens ( 43.81 ms per token, 22.82 tokens per second) 3.05.326.634 I slot print_timing: id 1 | task 115 | eval time = 232.12 ms / 2 tokens ( 232.12 ms per token, 4.31 tokens per second) 3.05.326.634 I slot print_timing: id 1 | task 115 | total time = 10134.15 ms / 228 tokens 3.05.326.635 I slot print_timing: id 1 | task 115 | graphs reused = 1 3.05.326.635 I slot print_timing: id 1 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.326.846 I slot release: id 1 | task 115 | stop processing: n_tokens = 227, truncated = 0 3.05.327.393 I slot print_timing: id 2 | task 112 | prompt eval time = 9902.56 ms / 142 tokens ( 69.74 ms per token, 14.34 tokens per second) 3.05.327.398 I slot print_timing: id 2 | task 112 | eval time = 232.34 ms / 2 tokens ( 232.34 ms per token, 4.30 tokens per second) 3.05.327.399 I slot print_timing: id 2 | task 112 | total time = 10134.90 ms / 144 tokens 3.05.327.399 I slot print_timing: id 2 | task 112 | graphs reused = 1 3.05.327.400 I slot print_timing: id 2 | task 112 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.327.884 I slot release: id 2 | task 112 | stop processing: n_tokens = 143, truncated = 0 3.05.328.251 I slot print_timing: id 3 | task 113 | prompt eval time = 9903.25 ms / 155 tokens ( 63.89 ms per token, 15.65 tokens per second) 3.05.328.255 I slot print_timing: id 3 | task 113 | eval time = 232.50 ms / 2 tokens ( 232.50 ms per token, 4.30 tokens per second) 3.05.328.256 I slot print_timing: id 3 | task 113 | total time = 10135.75 ms / 157 tokens 3.05.328.256 I slot print_timing: id 3 | task 113 | graphs reused = 1 3.05.328.256 I slot print_timing: id 3 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.328.321 I slot release: id 3 | task 113 | stop processing: n_tokens = 156, truncated = 0 3.05.341.550 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 3.05.368.716 I slot launch_slot_: id 2 | task 119 | processing task, is_child = 0 3.05.368.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 3.05.688.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 3.06.001.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.882 MiB) 3.06.755.048 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 3.06.755.207 I slot launch_slot_: id 3 | task 120 | processing task, is_child = 0 3.06.755.250 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 3.06.755.291 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 3.06.755.312 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 3.06.788.527 I slot launch_slot_: id 1 | task 122 | processing task, is_child = 0 3.13.813.465 I slot print_timing: id 0 | task 121 | prompt processing, n_tokens = 137, progress = 0.97, t = 7.02 s / 19.50 tokens per second 3.14.207.175 I slot print_timing: id 1 | task 122 | prompt processing, n_tokens = 188, progress = 0.98, t = 7.02 s / 26.76 tokens per second 3.14.236.772 I slot print_timing: id 2 | task 119 | prompt processing, n_tokens = 101, progress = 0.96, t = 7.02 s / 14.38 tokens per second 3.14.243.642 I slot print_timing: id 3 | task 120 | prompt processing, n_tokens = 110, progress = 0.96, t = 7.02 s / 15.66 tokens per second 3.14.955.787 I slot print_timing: id 0 | task 121 | prompt eval time = 7936.48 ms / 141 tokens ( 56.29 ms per token, 17.77 tokens per second) 3.14.955.789 I slot print_timing: id 0 | task 121 | eval time = 230.76 ms / 2 tokens ( 230.76 ms per token, 4.33 tokens per second) 3.14.955.791 I slot print_timing: id 0 | task 121 | total time = 8167.24 ms / 143 tokens 3.14.955.791 I slot print_timing: id 0 | task 121 | graphs reused = 1 3.14.955.792 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.957.481 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 3.14.957.811 I slot print_timing: id 1 | task 122 | prompt eval time = 7936.82 ms / 192 tokens ( 41.34 ms per token, 24.19 tokens per second) 3.14.957.815 I slot print_timing: id 1 | task 122 | eval time = 232.43 ms / 2 tokens ( 232.43 ms per token, 4.30 tokens per second) 3.14.957.815 I slot print_timing: id 1 | task 122 | total time = 8169.25 ms / 194 tokens 3.14.957.816 I slot print_timing: id 1 | task 122 | graphs reused = 1 3.14.957.816 I slot print_timing: id 1 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.960.987 I slot release: id 1 | task 122 | stop processing: n_tokens = 193, truncated = 0 3.14.961.262 I slot print_timing: id 2 | task 119 | prompt eval time = 7937.34 ms / 105 tokens ( 75.59 ms per token, 13.23 tokens per second) 3.14.961.266 I slot print_timing: id 2 | task 119 | eval time = 235.35 ms / 2 tokens ( 235.35 ms per token, 4.25 tokens per second) 3.14.961.266 I slot print_timing: id 2 | task 119 | total time = 8172.68 ms / 107 tokens 3.14.961.267 I slot print_timing: id 2 | task 119 | graphs reused = 1 3.14.961.267 I slot print_timing: id 2 | task 119 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.961.321 I slot release: id 2 | task 119 | stop processing: n_tokens = 106, truncated = 0 3.14.961.565 I slot print_timing: id 3 | task 120 | prompt eval time = 7938.00 ms / 114 tokens ( 69.63 ms per token, 14.36 tokens per second) 3.14.961.576 I slot print_timing: id 3 | task 120 | eval time = 234.98 ms / 2 tokens ( 234.98 ms per token, 4.26 tokens per second) 3.14.961.581 I slot print_timing: id 3 | task 120 | total time = 8172.98 ms / 116 tokens 3.14.961.581 I slot print_timing: id 3 | task 120 | graphs reused = 1 3.14.961.581 I slot print_timing: id 3 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.962.475 I slot release: id 3 | task 120 | stop processing: n_tokens = 115, truncated = 0 3.14.971.142 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.274 3.14.997.820 I slot launch_slot_: id 2 | task 126 | processing task, is_child = 0 3.14.997.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 3.15.630.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.506 MiB) 3.16.252.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 3.16.706.119 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 3.16.706.225 I slot launch_slot_: id 0 | task 127 | processing task, is_child = 0 3.16.706.267 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.145 3.16.706.303 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 3.16.706.320 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.252 3.16.706.356 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 3.23.345.422 I slot print_timing: id 0 | task 127 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.64 s / 19.73 tokens per second 3.23.752.128 I slot print_timing: id 1 | task 128 | prompt processing, n_tokens = 168, progress = 0.98, t = 6.64 s / 25.30 tokens per second 3.23.756.900 I slot print_timing: id 2 | task 126 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.64 s / 15.67 tokens per second 3.23.761.404 I slot print_timing: id 3 | task 129 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.64 s / 17.77 tokens per second 3.24.472.617 I slot print_timing: id 0 | task 127 | prompt eval time = 7534.96 ms / 135 tokens ( 55.81 ms per token, 17.92 tokens per second) 3.24.472.623 I slot print_timing: id 0 | task 127 | eval time = 231.29 ms / 2 tokens ( 231.29 ms per token, 4.32 tokens per second) 3.24.472.623 I slot print_timing: id 0 | task 127 | total time = 7766.25 ms / 137 tokens 3.24.472.624 I slot print_timing: id 0 | task 127 | graphs reused = 1 3.24.472.624 I slot print_timing: id 0 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.476.266 I slot release: id 0 | task 127 | stop processing: n_tokens = 136, truncated = 0 3.24.476.710 I slot print_timing: id 1 | task 128 | prompt eval time = 7535.57 ms / 172 tokens ( 43.81 ms per token, 22.83 tokens per second) 3.24.476.713 I slot print_timing: id 1 | task 128 | eval time = 234.76 ms / 2 tokens ( 234.76 ms per token, 4.26 tokens per second) 3.24.476.713 I slot print_timing: id 1 | task 128 | total time = 7770.33 ms / 174 tokens 3.24.476.714 I slot print_timing: id 1 | task 128 | graphs reused = 1 3.24.476.714 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.477.653 I slot release: id 1 | task 128 | stop processing: n_tokens = 173, truncated = 0 3.24.478.088 I slot print_timing: id 2 | task 126 | prompt eval time = 7536.33 ms / 108 tokens ( 69.78 ms per token, 14.33 tokens per second) 3.24.478.096 I slot print_timing: id 2 | task 126 | eval time = 235.35 ms / 2 tokens ( 235.35 ms per token, 4.25 tokens per second) 3.24.478.096 I slot print_timing: id 2 | task 126 | total time = 7771.69 ms / 110 tokens 3.24.478.097 I slot print_timing: id 2 | task 126 | graphs reused = 1 3.24.478.097 I slot print_timing: id 2 | task 126 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.478.218 I slot release: id 2 | task 126 | stop processing: n_tokens = 109, truncated = 0 3.24.478.544 I slot print_timing: id 3 | task 129 | prompt eval time = 7537.18 ms / 122 tokens ( 61.78 ms per token, 16.19 tokens per second) 3.24.478.547 I slot print_timing: id 3 | task 129 | eval time = 234.96 ms / 2 tokens ( 234.96 ms per token, 4.26 tokens per second) 3.24.478.548 I slot print_timing: id 3 | task 129 | total time = 7772.14 ms / 124 tokens 3.24.478.548 I slot print_timing: id 3 | task 129 | graphs reused = 1 3.24.478.548 I slot print_timing: id 3 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.479.257 I slot release: id 3 | task 129 | stop processing: n_tokens = 123, truncated = 0 3.24.490.406 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.206 3.24.490.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 3.24.949.867 I slot launch_slot_: id 0 | task 133 | processing task, is_child = 0 3.24.949.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.756 MiB) 3.25.571.678 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 3.26.064.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 3.26.200.478 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.162 3.26.200.580 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 3.26.200.615 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.266 3.26.226.578 I slot launch_slot_: id 2 | task 135 | processing task, is_child = 0 3.26.226.608 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.228 3.26.226.643 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 3.32.586.296 I slot print_timing: id 0 | task 133 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.36 s / 20.60 tokens per second 3.33.383.107 I slot print_timing: id 1 | task 134 | prompt processing, n_tokens = 130, progress = 0.97, t = 6.36 s / 20.44 tokens per second 3.33.387.606 I slot print_timing: id 2 | task 135 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.36 s / 18.24 tokens per second 3.33.407.932 I slot print_timing: id 3 | task 136 | prompt processing, n_tokens = 155, progress = 0.97, t = 6.36 s / 24.37 tokens per second 3.34.111.282 I slot print_timing: id 0 | task 133 | prompt eval time = 7653.32 ms / 135 tokens ( 56.69 ms per token, 17.64 tokens per second) 3.34.111.285 I slot print_timing: id 0 | task 133 | eval time = 231.30 ms / 2 tokens ( 231.30 ms per token, 4.32 tokens per second) 3.34.111.285 I slot print_timing: id 0 | task 133 | total time = 7884.62 ms / 137 tokens 3.34.111.286 I slot print_timing: id 0 | task 133 | graphs reused = 1 3.34.111.845 I slot print_timing: id 0 | task 133 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.112.766 I slot release: id 0 | task 133 | stop processing: n_tokens = 136, truncated = 0 3.34.113.072 I slot print_timing: id 1 | task 134 | prompt eval time = 7653.54 ms / 134 tokens ( 57.12 ms per token, 17.51 tokens per second) 3.34.113.076 I slot print_timing: id 1 | task 134 | eval time = 232.84 ms / 2 tokens ( 232.84 ms per token, 4.29 tokens per second) 3.34.113.077 I slot print_timing: id 1 | task 134 | total time = 7886.38 ms / 136 tokens 3.34.113.077 I slot print_timing: id 1 | task 134 | graphs reused = 1 3.34.113.077 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.113.217 I slot release: id 1 | task 134 | stop processing: n_tokens = 135, truncated = 0 3.34.113.536 I slot print_timing: id 2 | task 135 | prompt eval time = 7654.05 ms / 120 tokens ( 63.78 ms per token, 15.68 tokens per second) 3.34.113.543 I slot print_timing: id 2 | task 135 | eval time = 232.78 ms / 2 tokens ( 232.78 ms per token, 4.30 tokens per second) 3.34.113.544 I slot print_timing: id 2 | task 135 | total time = 7886.82 ms / 122 tokens 3.34.113.544 I slot print_timing: id 2 | task 135 | graphs reused = 1 3.34.113.545 I slot print_timing: id 2 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.115.618 I slot release: id 2 | task 135 | stop processing: n_tokens = 121, truncated = 0 3.34.115.877 I slot print_timing: id 3 | task 136 | prompt eval time = 7654.88 ms / 159 tokens ( 48.14 ms per token, 20.77 tokens per second) 3.34.115.880 I slot print_timing: id 3 | task 136 | eval time = 234.25 ms / 2 tokens ( 234.25 ms per token, 4.27 tokens per second) 3.34.115.880 I slot print_timing: id 3 | task 136 | total time = 7889.13 ms / 161 tokens 3.34.115.881 I slot print_timing: id 3 | task 136 | graphs reused = 1 3.34.115.881 I slot print_timing: id 3 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.117.829 I slot release: id 3 | task 136 | stop processing: n_tokens = 160, truncated = 0 3.34.126.677 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 3.34.156.358 I slot launch_slot_: id 0 | task 140 | processing task, is_child = 0 3.34.156.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.506 MiB) 3.34.833.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.35.483.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 3.35.968.011 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.207 3.35.968.377 I slot launch_slot_: id 1 | task 141 | processing task, is_child = 0 3.35.968.414 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.231 3.35.968.451 I slot launch_slot_: id 2 | task 142 | processing task, is_child = 0 3.35.968.470 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.175 3.35.968.505 I slot launch_slot_: id 3 | task 143 | processing task, is_child = 0 3.43.893.778 I slot print_timing: id 0 | task 140 | prompt processing, n_tokens = 126, progress = 0.97, t = 7.93 s / 15.90 tokens per second 3.44.087.045 I slot print_timing: id 1 | task 141 | prompt processing, n_tokens = 176, progress = 0.98, t = 7.93 s / 22.21 tokens per second 3.44.110.774 I slot print_timing: id 2 | task 142 | prompt processing, n_tokens = 171, progress = 0.98, t = 7.93 s / 21.58 tokens per second 3.44.137.532 I slot print_timing: id 3 | task 143 | prompt processing, n_tokens = 168, progress = 0.98, t = 7.93 s / 21.20 tokens per second 3.44.840.627 I slot print_timing: id 0 | task 140 | prompt eval time = 8641.20 ms / 130 tokens ( 66.47 ms per token, 15.04 tokens per second) 3.44.840.632 I slot print_timing: id 0 | task 140 | eval time = 230.91 ms / 2 tokens ( 230.91 ms per token, 4.33 tokens per second) 3.44.840.633 I slot print_timing: id 0 | task 140 | total time = 8872.11 ms / 132 tokens 3.44.840.633 I slot print_timing: id 0 | task 140 | graphs reused = 1 3.44.840.633 I slot print_timing: id 0 | task 140 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.843.899 I slot release: id 0 | task 140 | stop processing: n_tokens = 131, truncated = 0 3.44.844.220 I slot print_timing: id 1 | task 141 | prompt eval time = 8641.62 ms / 180 tokens ( 48.01 ms per token, 20.83 tokens per second) 3.44.844.223 I slot print_timing: id 1 | task 141 | eval time = 234.06 ms / 2 tokens ( 234.06 ms per token, 4.27 tokens per second) 3.44.844.223 I slot print_timing: id 1 | task 141 | total time = 8875.68 ms / 182 tokens 3.44.844.224 I slot print_timing: id 1 | task 141 | graphs reused = 1 3.44.844.224 I slot print_timing: id 1 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.844.360 I slot release: id 1 | task 141 | stop processing: n_tokens = 181, truncated = 0 3.44.844.681 I slot print_timing: id 2 | task 142 | prompt eval time = 8642.05 ms / 175 tokens ( 49.38 ms per token, 20.25 tokens per second) 3.44.844.683 I slot print_timing: id 2 | task 142 | eval time = 234.07 ms / 2 tokens ( 234.07 ms per token, 4.27 tokens per second) 3.44.844.683 I slot print_timing: id 2 | task 142 | total time = 8876.12 ms / 177 tokens 3.44.844.683 I slot print_timing: id 2 | task 142 | graphs reused = 1 3.44.844.691 I slot print_timing: id 2 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.845.101 I slot release: id 2 | task 142 | stop processing: n_tokens = 176, truncated = 0 3.44.845.404 I slot print_timing: id 3 | task 143 | prompt eval time = 8642.63 ms / 172 tokens ( 50.25 ms per token, 19.90 tokens per second) 3.44.845.413 I slot print_timing: id 3 | task 143 | eval time = 234.20 ms / 2 tokens ( 234.20 ms per token, 4.27 tokens per second) 3.44.845.413 I slot print_timing: id 3 | task 143 | total time = 8876.83 ms / 174 tokens 3.44.845.413 I slot print_timing: id 3 | task 143 | graphs reused = 1 3.44.845.413 I slot print_timing: id 3 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.846.259 I slot release: id 3 | task 143 | stop processing: n_tokens = 173, truncated = 0 3.44.856.865 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 3.44.856.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 3.45.092.168 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 3.45.092.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.506 MiB) 3.45.502.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 3.46.068.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 3.46.473.880 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 3.46.474.244 I slot launch_slot_: id 1 | task 147 | processing task, is_child = 0 3.46.474.294 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 3.46.508.729 I slot launch_slot_: id 2 | task 149 | processing task, is_child = 0 3.46.508.764 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 3.46.512.319 I slot launch_slot_: id 3 | task 150 | processing task, is_child = 0 3.52.093.398 I slot print_timing: id 0 | task 148 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.58 s / 21.32 tokens per second 3.52.290.961 I slot print_timing: id 1 | task 147 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.58 s / 19.89 tokens per second 3.52.577.144 I slot print_timing: id 2 | task 149 | prompt processing, n_tokens = 111, progress = 0.97, t = 5.58 s / 19.89 tokens per second 3.52.595.171 I slot print_timing: id 3 | task 150 | prompt processing, n_tokens = 119, progress = 0.97, t = 5.58 s / 21.32 tokens per second 3.53.331.462 I slot print_timing: id 0 | task 148 | prompt eval time = 6589.86 ms / 123 tokens ( 53.58 ms per token, 18.67 tokens per second) 3.53.331.467 I slot print_timing: id 0 | task 148 | eval time = 229.27 ms / 2 tokens ( 229.27 ms per token, 4.36 tokens per second) 3.53.331.467 I slot print_timing: id 0 | task 148 | total time = 6819.13 ms / 125 tokens 3.53.331.468 I slot print_timing: id 0 | task 148 | graphs reused = 1 3.53.331.468 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.331.598 I slot release: id 0 | task 148 | stop processing: n_tokens = 124, truncated = 0 3.53.331.761 I slot print_timing: id 1 | task 147 | prompt eval time = 6590.23 ms / 115 tokens ( 57.31 ms per token, 17.45 tokens per second) 3.53.331.763 I slot print_timing: id 1 | task 147 | eval time = 229.17 ms / 2 tokens ( 229.17 ms per token, 4.36 tokens per second) 3.53.331.771 I slot print_timing: id 1 | task 147 | total time = 6819.40 ms / 117 tokens 3.53.331.774 I slot print_timing: id 1 | task 147 | graphs reused = 1 3.53.331.774 I slot print_timing: id 1 | task 147 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.332.994 I slot release: id 1 | task 147 | stop processing: n_tokens = 116, truncated = 0 3.53.333.280 I slot print_timing: id 2 | task 149 | prompt eval time = 6590.59 ms / 115 tokens ( 57.31 ms per token, 17.45 tokens per second) 3.53.333.284 I slot print_timing: id 2 | task 149 | eval time = 230.31 ms / 2 tokens ( 230.31 ms per token, 4.34 tokens per second) 3.53.333.284 I slot print_timing: id 2 | task 149 | total time = 6820.90 ms / 117 tokens 3.53.333.285 I slot print_timing: id 2 | task 149 | graphs reused = 1 3.53.333.285 I slot print_timing: id 2 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.334.313 I slot release: id 2 | task 149 | stop processing: n_tokens = 116, truncated = 0 3.53.334.594 I slot print_timing: id 3 | task 150 | prompt eval time = 6590.93 ms / 123 tokens ( 53.58 ms per token, 18.66 tokens per second) 3.53.334.603 I slot print_timing: id 3 | task 150 | eval time = 231.28 ms / 2 tokens ( 231.28 ms per token, 4.32 tokens per second) 3.53.334.604 I slot print_timing: id 3 | task 150 | total time = 6822.20 ms / 125 tokens 3.53.334.604 I slot print_timing: id 3 | task 150 | graphs reused = 1 3.53.334.604 I slot print_timing: id 3 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.335.057 I slot release: id 3 | task 150 | stop processing: n_tokens = 124, truncated = 0 3.53.344.722 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 3.53.373.784 I slot launch_slot_: id 2 | task 154 | processing task, is_child = 0 3.53.399.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.880 MiB) 3.53.956.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 3.54.576.272 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 3.54.576.367 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 3.54.576.401 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.241 3.54.576.434 I slot launch_slot_: id 1 | task 156 | processing task, is_child = 0 3.54.576.450 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.226 3.54.576.484 I slot launch_slot_: id 3 | task 157 | processing task, is_child = 0 4.01.225.235 I slot print_timing: id 0 | task 155 | prompt processing, n_tokens = 124, progress = 0.97, t = 6.65 s / 18.65 tokens per second 4.01.415.485 I slot print_timing: id 1 | task 156 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.65 s / 20.61 tokens per second 4.01.419.960 I slot print_timing: id 2 | task 154 | prompt processing, n_tokens = 123, progress = 0.97, t = 6.65 s / 18.50 tokens per second 4.01.424.397 I slot print_timing: id 3 | task 157 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.65 s / 18.95 tokens per second 4.02.125.172 I slot print_timing: id 0 | task 155 | prompt eval time = 7318.92 ms / 128 tokens ( 57.18 ms per token, 17.49 tokens per second) 4.02.125.175 I slot print_timing: id 0 | task 155 | eval time = 229.76 ms / 2 tokens ( 229.76 ms per token, 4.35 tokens per second) 4.02.125.175 I slot print_timing: id 0 | task 155 | total time = 7548.68 ms / 130 tokens 4.02.125.176 I slot print_timing: id 0 | task 155 | graphs reused = 1 4.02.125.176 I slot print_timing: id 0 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.126.252 I slot release: id 0 | task 155 | stop processing: n_tokens = 129, truncated = 0 4.02.126.554 I slot print_timing: id 1 | task 156 | prompt eval time = 7319.06 ms / 141 tokens ( 51.91 ms per token, 19.26 tokens per second) 4.02.126.557 I slot print_timing: id 1 | task 156 | eval time = 230.98 ms / 2 tokens ( 230.98 ms per token, 4.33 tokens per second) 4.02.126.559 I slot print_timing: id 1 | task 156 | total time = 7550.05 ms / 143 tokens 4.02.126.564 I slot print_timing: id 1 | task 156 | graphs reused = 1 4.02.126.564 I slot print_timing: id 1 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.126.666 I slot release: id 1 | task 156 | stop processing: n_tokens = 142, truncated = 0 4.02.126.979 I slot print_timing: id 2 | task 154 | prompt eval time = 7319.22 ms / 127 tokens ( 57.63 ms per token, 17.35 tokens per second) 4.02.126.982 I slot print_timing: id 2 | task 154 | eval time = 231.24 ms / 2 tokens ( 231.24 ms per token, 4.32 tokens per second) 4.02.126.982 I slot print_timing: id 2 | task 154 | total time = 7550.46 ms / 129 tokens 4.02.127.000 I slot print_timing: id 2 | task 154 | graphs reused = 1 4.02.127.002 I slot print_timing: id 2 | task 154 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.127.040 I slot release: id 2 | task 154 | stop processing: n_tokens = 128, truncated = 0 4.02.127.371 I slot print_timing: id 3 | task 157 | prompt eval time = 7319.39 ms / 130 tokens ( 56.30 ms per token, 17.76 tokens per second) 4.02.127.375 I slot print_timing: id 3 | task 157 | eval time = 231.46 ms / 2 tokens ( 231.46 ms per token, 4.32 tokens per second) 4.02.127.376 I slot print_timing: id 3 | task 157 | total time = 7550.84 ms / 132 tokens 4.02.127.376 I slot print_timing: id 3 | task 157 | graphs reused = 1 4.02.127.376 I slot print_timing: id 3 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.127.393 I slot release: id 3 | task 157 | stop processing: n_tokens = 131, truncated = 0 4.02.136.773 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 4.02.136.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.693 MiB) 4.02.692.915 I slot launch_slot_: id 2 | task 161 | processing task, is_child = 0 4.02.692.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.321 MiB) 4.03.147.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.382 MiB) 4.03.788.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.818 MiB) 4.04.225.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 4.04.225.563 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 4.04.225.608 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.197 4.04.225.644 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 4.04.225.665 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.214 4.04.225.705 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 4.10.364.444 I slot print_timing: id 0 | task 162 | prompt processing, n_tokens = 125, progress = 0.97, t = 6.14 s / 20.36 tokens per second 4.11.174.144 I slot print_timing: id 1 | task 163 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.14 s / 19.39 tokens per second 4.11.203.109 I slot print_timing: id 2 | task 161 | prompt processing, n_tokens = 101, progress = 0.96, t = 6.14 s / 16.45 tokens per second 4.11.210.350 I slot print_timing: id 3 | task 164 | prompt processing, n_tokens = 157, progress = 0.98, t = 6.14 s / 25.58 tokens per second 4.11.915.007 I slot print_timing: id 0 | task 162 | prompt eval time = 7457.22 ms / 129 tokens ( 57.81 ms per token, 17.30 tokens per second) 4.11.915.010 I slot print_timing: id 0 | task 162 | eval time = 232.07 ms / 2 tokens ( 232.07 ms per token, 4.31 tokens per second) 4.11.915.011 I slot print_timing: id 0 | task 162 | total time = 7689.29 ms / 131 tokens 4.11.915.011 I slot print_timing: id 0 | task 162 | graphs reused = 1 4.11.915.012 I slot print_timing: id 0 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.917.287 I slot release: id 0 | task 162 | stop processing: n_tokens = 130, truncated = 0 4.11.917.727 I slot print_timing: id 1 | task 163 | prompt eval time = 7458.07 ms / 123 tokens ( 60.63 ms per token, 16.49 tokens per second) 4.11.917.733 I slot print_timing: id 1 | task 163 | eval time = 233.92 ms / 2 tokens ( 233.92 ms per token, 4.27 tokens per second) 4.11.917.733 I slot print_timing: id 1 | task 163 | total time = 7691.99 ms / 125 tokens 4.11.917.734 I slot print_timing: id 1 | task 163 | graphs reused = 1 4.11.917.734 I slot print_timing: id 1 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.917.783 I slot release: id 1 | task 163 | stop processing: n_tokens = 124, truncated = 0 4.11.918.096 I slot print_timing: id 2 | task 161 | prompt eval time = 7459.09 ms / 105 tokens ( 71.04 ms per token, 14.08 tokens per second) 4.11.918.099 I slot print_timing: id 2 | task 161 | eval time = 233.25 ms / 2 tokens ( 233.25 ms per token, 4.29 tokens per second) 4.11.918.100 I slot print_timing: id 2 | task 161 | total time = 7692.35 ms / 107 tokens 4.11.918.100 I slot print_timing: id 2 | task 161 | graphs reused = 1 4.11.918.100 I slot print_timing: id 2 | task 161 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.919.069 I slot release: id 2 | task 161 | stop processing: n_tokens = 106, truncated = 0 4.11.919.361 I slot print_timing: id 3 | task 164 | prompt eval time = 7460.01 ms / 161 tokens ( 46.34 ms per token, 21.58 tokens per second) 4.11.919.365 I slot print_timing: id 3 | task 164 | eval time = 233.59 ms / 2 tokens ( 233.59 ms per token, 4.28 tokens per second) 4.11.919.365 I slot print_timing: id 3 | task 164 | total time = 7693.59 ms / 163 tokens 4.11.919.365 I slot print_timing: id 3 | task 164 | graphs reused = 1 4.11.919.366 I slot print_timing: id 3 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.922.295 I slot release: id 3 | task 164 | stop processing: n_tokens = 162, truncated = 0 4.11.933.206 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 4.11.933.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.193 MiB) 4.12.397.397 I slot launch_slot_: id 2 | task 168 | processing task, is_child = 0 4.12.397.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 4.12.869.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.445 MiB) 4.13.698.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 4.14.461.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.215 4.14.461.463 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 4.14.461.498 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 4.14.461.531 I slot launch_slot_: id 1 | task 170 | processing task, is_child = 0 4.14.461.549 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.173 4.14.461.587 I slot launch_slot_: id 3 | task 171 | processing task, is_child = 0 4.21.083.239 I slot print_timing: id 0 | task 169 | prompt processing, n_tokens = 150, progress = 0.97, t = 6.62 s / 22.65 tokens per second 4.21.892.307 I slot print_timing: id 1 | task 170 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.62 s / 20.69 tokens per second 4.21.898.385 I slot print_timing: id 2 | task 168 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.62 s / 16.01 tokens per second 4.21.924.330 I slot print_timing: id 3 | task 171 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.62 s / 24.16 tokens per second 4.22.638.158 I slot print_timing: id 0 | task 169 | prompt eval time = 7945.07 ms / 154 tokens ( 51.59 ms per token, 19.38 tokens per second) 4.22.638.161 I slot print_timing: id 0 | task 169 | eval time = 231.49 ms / 2 tokens ( 231.49 ms per token, 4.32 tokens per second) 4.22.638.161 I slot print_timing: id 0 | task 169 | total time = 8176.56 ms / 156 tokens 4.22.638.162 I slot print_timing: id 0 | task 169 | graphs reused = 1 4.22.638.162 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.639.949 I slot release: id 0 | task 169 | stop processing: n_tokens = 155, truncated = 0 4.22.640.317 I slot print_timing: id 1 | task 170 | prompt eval time = 7945.53 ms / 141 tokens ( 56.35 ms per token, 17.75 tokens per second) 4.22.640.321 I slot print_timing: id 1 | task 170 | eval time = 233.17 ms / 2 tokens ( 233.17 ms per token, 4.29 tokens per second) 4.22.640.322 I slot print_timing: id 1 | task 170 | total time = 8178.70 ms / 143 tokens 4.22.640.323 I slot print_timing: id 1 | task 170 | graphs reused = 1 4.22.640.323 I slot print_timing: id 1 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.641.705 I slot release: id 1 | task 170 | stop processing: n_tokens = 142, truncated = 0 4.22.642.011 I slot print_timing: id 2 | task 168 | prompt eval time = 7946.36 ms / 110 tokens ( 72.24 ms per token, 13.84 tokens per second) 4.22.642.015 I slot print_timing: id 2 | task 168 | eval time = 234.01 ms / 2 tokens ( 234.01 ms per token, 4.27 tokens per second) 4.22.642.016 I slot print_timing: id 2 | task 168 | total time = 8180.38 ms / 112 tokens 4.22.642.016 I slot print_timing: id 2 | task 168 | graphs reused = 1 4.22.642.017 I slot print_timing: id 2 | task 168 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.643.665 I slot release: id 2 | task 168 | stop processing: n_tokens = 111, truncated = 0 4.22.643.942 I slot print_timing: id 3 | task 171 | prompt eval time = 7947.37 ms / 164 tokens ( 48.46 ms per token, 20.64 tokens per second) 4.22.643.947 I slot print_timing: id 3 | task 171 | eval time = 234.92 ms / 2 tokens ( 234.92 ms per token, 4.26 tokens per second) 4.22.643.948 I slot print_timing: id 3 | task 171 | total time = 8182.30 ms / 166 tokens 4.22.643.948 I slot print_timing: id 3 | task 171 | graphs reused = 1 4.22.643.948 I slot print_timing: id 3 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.645.459 I slot release: id 3 | task 171 | stop processing: n_tokens = 165, truncated = 0 4.22.653.655 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 4.22.653.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 4.23.161.107 I slot launch_slot_: id 2 | task 175 | processing task, is_child = 0 4.23.161.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 311.320 MiB) 4.23.860.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 4.24.156.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 4.24.320.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.181 4.24.320.656 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 4.24.320.694 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.197 4.24.320.730 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 4.24.320.748 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 4.24.320.781 I slot launch_slot_: id 3 | task 178 | processing task, is_child = 0 4.30.591.624 I slot print_timing: id 0 | task 176 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.27 s / 16.90 tokens per second 4.31.043.932 I slot print_timing: id 1 | task 177 | prompt processing, n_tokens = 144, progress = 0.97, t = 6.27 s / 22.96 tokens per second 4.31.052.786 I slot print_timing: id 2 | task 175 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.27 s / 16.90 tokens per second 4.31.058.268 I slot print_timing: id 3 | task 178 | prompt processing, n_tokens = 133, progress = 0.97, t = 6.27 s / 21.21 tokens per second 4.31.762.346 I slot print_timing: id 0 | task 176 | prompt eval time = 7210.47 ms / 110 tokens ( 65.55 ms per token, 15.26 tokens per second) 4.31.762.349 I slot print_timing: id 0 | task 176 | eval time = 231.09 ms / 2 tokens ( 231.09 ms per token, 4.33 tokens per second) 4.31.762.350 I slot print_timing: id 0 | task 176 | total time = 7441.55 ms / 112 tokens 4.31.762.350 I slot print_timing: id 0 | task 176 | graphs reused = 1 4.31.762.350 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.763.710 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 4.31.764.167 I slot print_timing: id 1 | task 177 | prompt eval time = 7210.85 ms / 148 tokens ( 48.72 ms per token, 20.52 tokens per second) 4.31.764.170 I slot print_timing: id 1 | task 177 | eval time = 232.51 ms / 2 tokens ( 232.51 ms per token, 4.30 tokens per second) 4.31.764.170 I slot print_timing: id 1 | task 177 | total time = 7443.36 ms / 150 tokens 4.31.764.171 I slot print_timing: id 1 | task 177 | graphs reused = 1 4.31.764.172 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.764.846 I slot release: id 1 | task 177 | stop processing: n_tokens = 149, truncated = 0 4.31.765.160 I slot print_timing: id 2 | task 175 | prompt eval time = 7211.58 ms / 110 tokens ( 65.56 ms per token, 15.25 tokens per second) 4.31.765.165 I slot print_timing: id 2 | task 175 | eval time = 232.76 ms / 2 tokens ( 232.76 ms per token, 4.30 tokens per second) 4.31.765.165 I slot print_timing: id 2 | task 175 | total time = 7444.34 ms / 112 tokens 4.31.765.165 I slot print_timing: id 2 | task 175 | graphs reused = 1 4.31.765.166 I slot print_timing: id 2 | task 175 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.765.238 I slot release: id 2 | task 175 | stop processing: n_tokens = 111, truncated = 0 4.31.765.540 I slot print_timing: id 3 | task 178 | prompt eval time = 7212.41 ms / 137 tokens ( 52.65 ms per token, 19.00 tokens per second) 4.31.765.544 I slot print_timing: id 3 | task 178 | eval time = 232.29 ms / 2 tokens ( 232.29 ms per token, 4.31 tokens per second) 4.31.765.544 I slot print_timing: id 3 | task 178 | total time = 7444.70 ms / 139 tokens 4.31.765.561 I slot print_timing: id 3 | task 178 | graphs reused = 1 4.31.765.565 I slot print_timing: id 3 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.766.762 I slot release: id 3 | task 178 | stop processing: n_tokens = 138, truncated = 0 4.31.777.366 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.252 4.31.777.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 4.32.253.532 I slot launch_slot_: id 0 | task 182 | processing task, is_child = 0 4.32.253.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 4.33.052.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 4.33.354.929 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 4.33.748.151 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.188 4.33.748.252 I slot launch_slot_: id 1 | task 183 | processing task, is_child = 0 4.33.748.297 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 4.33.748.330 I slot launch_slot_: id 2 | task 184 | processing task, is_child = 0 4.33.748.348 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.203 4.33.748.383 I slot launch_slot_: id 3 | task 185 | processing task, is_child = 0 4.40.068.987 I slot print_timing: id 0 | task 182 | prompt processing, n_tokens = 148, progress = 0.97, t = 6.32 s / 23.42 tokens per second 4.40.517.316 I slot print_timing: id 1 | task 183 | prompt processing, n_tokens = 119, progress = 0.97, t = 6.32 s / 18.83 tokens per second 4.40.521.790 I slot print_timing: id 2 | task 184 | prompt processing, n_tokens = 108, progress = 0.96, t = 6.32 s / 17.09 tokens per second 4.40.535.768 I slot print_timing: id 3 | task 185 | prompt processing, n_tokens = 126, progress = 0.97, t = 6.32 s / 19.94 tokens per second 4.41.238.769 I slot print_timing: id 0 | task 182 | prompt eval time = 7259.26 ms / 152 tokens ( 47.76 ms per token, 20.94 tokens per second) 4.41.238.772 I slot print_timing: id 0 | task 182 | eval time = 231.11 ms / 2 tokens ( 231.11 ms per token, 4.33 tokens per second) 4.41.238.772 I slot print_timing: id 0 | task 182 | total time = 7490.37 ms / 154 tokens 4.41.238.773 I slot print_timing: id 0 | task 182 | graphs reused = 1 4.41.238.773 I slot print_timing: id 0 | task 182 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.238.907 I slot release: id 0 | task 182 | stop processing: n_tokens = 153, truncated = 0 4.41.239.064 I slot print_timing: id 1 | task 183 | prompt eval time = 7259.67 ms / 123 tokens ( 59.02 ms per token, 16.94 tokens per second) 4.41.239.066 I slot print_timing: id 1 | task 183 | eval time = 230.98 ms / 2 tokens ( 230.98 ms per token, 4.33 tokens per second) 4.41.239.067 I slot print_timing: id 1 | task 183 | total time = 7490.65 ms / 125 tokens 4.41.239.067 I slot print_timing: id 1 | task 183 | graphs reused = 1 4.41.239.067 I slot print_timing: id 1 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.239.112 I slot release: id 1 | task 183 | stop processing: n_tokens = 124, truncated = 0 4.41.239.278 I slot print_timing: id 2 | task 184 | prompt eval time = 7260.10 ms / 112 tokens ( 64.82 ms per token, 15.43 tokens per second) 4.41.239.279 I slot print_timing: id 2 | task 184 | eval time = 230.75 ms / 2 tokens ( 230.75 ms per token, 4.33 tokens per second) 4.41.239.279 I slot print_timing: id 2 | task 184 | total time = 7490.85 ms / 114 tokens 4.41.239.280 I slot print_timing: id 2 | task 184 | graphs reused = 1 4.41.239.280 I slot print_timing: id 2 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.239.337 I slot release: id 2 | task 184 | stop processing: n_tokens = 113, truncated = 0 4.41.239.491 I slot print_timing: id 3 | task 185 | prompt eval time = 7260.99 ms / 130 tokens ( 55.85 ms per token, 17.90 tokens per second) 4.41.239.492 I slot print_timing: id 3 | task 185 | eval time = 230.06 ms / 2 tokens ( 230.06 ms per token, 4.35 tokens per second) 4.41.239.493 I slot print_timing: id 3 | task 185 | total time = 7491.05 ms / 132 tokens 4.41.239.493 I slot print_timing: id 3 | task 185 | graphs reused = 1 4.41.239.493 I slot print_timing: id 3 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 4.41.242.688 I slot release: id 3 | task 185 | stop processing: n_tokens = 131, truncated = 0 4.41.253.376 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 4.41.253.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 4.41.729.152 I slot launch_slot_: id 3 | task 189 | processing task, is_child = 0 4.41.729.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.256 MiB) 4.42.400.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 4.42.557.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.569 MiB) 4.42.845.115 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.183 4.42.845.216 I slot launch_slot_: id 0 | task 190 | processing task, is_child = 0 4.42.845.257 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.226 4.42.845.297 I slot launch_slot_: id 1 | task 191 | processing task, is_child = 0 4.42.845.317 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 4.42.845.349 I slot launch_slot_: id 2 | task 192 | processing task, is_child = 0 4.49.854.361 I slot print_timing: id 0 | task 190 | prompt processing, n_tokens = 153, progress = 0.97, t = 7.01 s / 21.83 tokens per second 4.50.261.310 I slot print_timing: id 1 | task 191 | prompt processing, n_tokens = 162, progress = 0.98, t = 7.01 s / 23.11 tokens per second 4.50.267.170 I slot print_timing: id 2 | task 192 | prompt processing, n_tokens = 110, progress = 0.96, t = 7.01 s / 15.69 tokens per second 4.50.280.183 I slot print_timing: id 3 | task 189 | prompt processing, n_tokens = 124, progress = 0.97, t = 7.01 s / 17.69 tokens per second 4.50.984.507 I slot print_timing: id 0 | task 190 | prompt eval time = 7907.63 ms / 157 tokens ( 50.37 ms per token, 19.85 tokens per second) 4.50.984.512 I slot print_timing: id 0 | task 190 | eval time = 231.52 ms / 2 tokens ( 231.52 ms per token, 4.32 tokens per second) 4.50.984.512 I slot print_timing: id 0 | task 190 | total time = 8139.15 ms / 159 tokens 4.50.984.512 I slot print_timing: id 0 | task 190 | graphs reused = 1 4.50.984.513 I slot print_timing: id 0 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.986.780 I slot release: id 0 | task 190 | stop processing: n_tokens = 158, truncated = 0 4.50.987.153 I slot print_timing: id 1 | task 191 | prompt eval time = 7908.14 ms / 166 tokens ( 47.64 ms per token, 20.99 tokens per second) 4.50.987.680 I slot print_timing: id 1 | task 191 | eval time = 233.63 ms / 2 tokens ( 233.63 ms per token, 4.28 tokens per second) 4.50.987.684 I slot print_timing: id 1 | task 191 | total time = 8141.77 ms / 168 tokens 4.50.987.684 I slot print_timing: id 1 | task 191 | graphs reused = 1 4.50.987.685 I slot print_timing: id 1 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.989.226 I slot release: id 1 | task 191 | stop processing: n_tokens = 167, truncated = 0 4.50.989.518 I slot print_timing: id 2 | task 192 | prompt eval time = 7908.97 ms / 114 tokens ( 69.38 ms per token, 14.41 tokens per second) 4.50.989.522 I slot print_timing: id 2 | task 192 | eval time = 235.15 ms / 2 tokens ( 235.15 ms per token, 4.25 tokens per second) 4.50.989.522 I slot print_timing: id 2 | task 192 | total time = 8144.12 ms / 116 tokens 4.50.989.523 I slot print_timing: id 2 | task 192 | graphs reused = 1 4.50.989.523 I slot print_timing: id 2 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.990.398 I slot release: id 2 | task 192 | stop processing: n_tokens = 115, truncated = 0 4.50.990.694 I slot print_timing: id 3 | task 189 | prompt eval time = 7909.81 ms / 128 tokens ( 61.80 ms per token, 16.18 tokens per second) 4.50.990.697 I slot print_timing: id 3 | task 189 | eval time = 235.47 ms / 2 tokens ( 235.47 ms per token, 4.25 tokens per second) 4.50.990.697 I slot print_timing: id 3 | task 189 | total time = 8145.28 ms / 130 tokens 4.50.990.698 I slot print_timing: id 3 | task 189 | graphs reused = 1 4.50.990.698 I slot print_timing: id 3 | task 189 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.991.213 I slot release: id 3 | task 189 | stop processing: n_tokens = 129, truncated = 0 4.51.001.821 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.177 4.51.001.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.257 MiB) 4.51.409.136 I slot launch_slot_: id 0 | task 196 | processing task, is_child = 0 4.51.409.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.069 MiB) 4.51.831.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.505 MiB) 4.52.024.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 4.52.297.226 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.168 4.52.297.516 I slot launch_slot_: id 1 | task 197 | processing task, is_child = 0 4.52.297.555 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.243 4.52.392.520 I slot launch_slot_: id 2 | task 198 | processing task, is_child = 0 4.52.392.558 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.217 4.52.392.594 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 4.59.379.560 I slot print_timing: id 0 | task 196 | prompt processing, n_tokens = 104, progress = 0.96, t = 6.99 s / 14.88 tokens per second 5.00.173.912 I slot print_timing: id 1 | task 197 | prompt processing, n_tokens = 149, progress = 0.97, t = 6.99 s / 21.33 tokens per second 5.00.557.105 I slot print_timing: id 2 | task 198 | prompt processing, n_tokens = 137, progress = 0.97, t = 6.99 s / 19.61 tokens per second 5.00.571.456 I slot print_timing: id 3 | task 199 | prompt processing, n_tokens = 175, progress = 0.98, t = 6.99 s / 25.05 tokens per second 5.01.298.710 I slot print_timing: id 0 | task 196 | prompt eval time = 8675.39 ms / 108 tokens ( 80.33 ms per token, 12.45 tokens per second) 5.01.298.713 I slot print_timing: id 0 | task 196 | eval time = 230.72 ms / 2 tokens ( 230.72 ms per token, 4.33 tokens per second) 5.01.298.714 I slot print_timing: id 0 | task 196 | total time = 8906.11 ms / 110 tokens 5.01.298.714 I slot print_timing: id 0 | task 196 | graphs reused = 1 5.01.298.714 I slot print_timing: id 0 | task 196 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.299.221 I slot release: id 0 | task 196 | stop processing: n_tokens = 109, truncated = 0 5.01.299.429 I slot print_timing: id 1 | task 197 | prompt eval time = 8675.74 ms / 153 tokens ( 56.70 ms per token, 17.64 tokens per second) 5.01.299.431 I slot print_timing: id 1 | task 197 | eval time = 231.07 ms / 2 tokens ( 231.07 ms per token, 4.33 tokens per second) 5.01.299.431 I slot print_timing: id 1 | task 197 | total time = 8906.81 ms / 155 tokens 5.01.299.432 I slot print_timing: id 1 | task 197 | graphs reused = 1 5.01.299.432 I slot print_timing: id 1 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.299.527 I slot release: id 1 | task 197 | stop processing: n_tokens = 154, truncated = 0 5.01.300.155 I slot print_timing: id 2 | task 198 | prompt eval time = 8676.16 ms / 141 tokens ( 61.53 ms per token, 16.25 tokens per second) 5.01.300.158 I slot print_timing: id 2 | task 198 | eval time = 231.36 ms / 2 tokens ( 231.36 ms per token, 4.32 tokens per second) 5.01.300.158 I slot print_timing: id 2 | task 198 | total time = 8907.52 ms / 143 tokens 5.01.300.158 I slot print_timing: id 2 | task 198 | graphs reused = 1 5.01.300.159 I slot print_timing: id 2 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.300.226 I slot release: id 2 | task 198 | stop processing: n_tokens = 142, truncated = 0 5.01.300.540 I slot print_timing: id 3 | task 199 | prompt eval time = 8676.84 ms / 179 tokens ( 48.47 ms per token, 20.63 tokens per second) 5.01.300.542 I slot print_timing: id 3 | task 199 | eval time = 231.05 ms / 2 tokens ( 231.05 ms per token, 4.33 tokens per second) 5.01.300.542 I slot print_timing: id 3 | task 199 | total time = 8907.88 ms / 181 tokens 5.01.300.542 I slot print_timing: id 3 | task 199 | graphs reused = 1 5.01.300.543 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 5.01.303.864 I slot release: id 3 | task 199 | stop processing: n_tokens = 180, truncated = 0 5.01.315.489 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 5.01.358.347 I slot launch_slot_: id 0 | task 203 | processing task, is_child = 0 5.01.358.373 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 5.02.301.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.256 MiB) 5.02.953.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 5.03.399.201 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.182 5.03.431.004 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 5.03.431.406 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.197 5.03.431.464 I slot launch_slot_: id 2 | task 205 | processing task, is_child = 0 5.03.431.484 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 5.03.431.531 I slot launch_slot_: id 3 | task 206 | processing task, is_child = 0 5.10.083.965 I slot print_timing: id 0 | task 203 | prompt processing, n_tokens = 130, progress = 0.97, t = 6.65 s / 19.54 tokens per second 5.10.532.501 I slot print_timing: id 1 | task 204 | prompt processing, n_tokens = 112, progress = 0.97, t = 6.65 s / 16.84 tokens per second 5.10.585.382 I slot print_timing: id 2 | task 205 | prompt processing, n_tokens = 131, progress = 0.97, t = 6.65 s / 19.69 tokens per second 5.10.732.101 I slot print_timing: id 3 | task 206 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.65 s / 23.15 tokens per second 5.11.458.629 I slot print_timing: id 0 | task 203 | prompt eval time = 7795.30 ms / 134 tokens ( 58.17 ms per token, 17.19 tokens per second) 5.11.458.635 I slot print_timing: id 0 | task 203 | eval time = 231.79 ms / 2 tokens ( 231.79 ms per token, 4.31 tokens per second) 5.11.458.635 I slot print_timing: id 0 | task 203 | total time = 8027.09 ms / 136 tokens 5.11.458.636 I slot print_timing: id 0 | task 203 | graphs reused = 1 5.11.458.636 I slot print_timing: id 0 | task 203 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.458.748 I slot release: id 0 | task 203 | stop processing: n_tokens = 135, truncated = 0 5.11.458.959 I slot print_timing: id 1 | task 204 | prompt eval time = 7795.60 ms / 116 tokens ( 67.20 ms per token, 14.88 tokens per second) 5.11.458.959 I slot print_timing: id 1 | task 204 | eval time = 231.80 ms / 2 tokens ( 231.80 ms per token, 4.31 tokens per second) 5.11.458.960 I slot print_timing: id 1 | task 204 | total time = 8027.40 ms / 118 tokens 5.11.458.960 I slot print_timing: id 1 | task 204 | graphs reused = 1 5.11.458.960 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.462.624 I slot release: id 1 | task 204 | stop processing: n_tokens = 117, truncated = 0 5.11.463.376 I slot print_timing: id 2 | task 205 | prompt eval time = 7796.63 ms / 135 tokens ( 57.75 ms per token, 17.32 tokens per second) 5.11.463.380 I slot print_timing: id 2 | task 205 | eval time = 235.16 ms / 2 tokens ( 235.16 ms per token, 4.25 tokens per second) 5.11.463.381 I slot print_timing: id 2 | task 205 | total time = 8031.79 ms / 137 tokens 5.11.463.382 I slot print_timing: id 2 | task 205 | graphs reused = 1 5.11.463.382 I slot print_timing: id 2 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.464.498 I slot release: id 2 | task 205 | stop processing: n_tokens = 136, truncated = 0 5.11.464.686 I slot print_timing: id 3 | task 206 | prompt eval time = 7797.47 ms / 158 tokens ( 49.35 ms per token, 20.26 tokens per second) 5.11.464.692 I slot print_timing: id 3 | task 206 | eval time = 235.62 ms / 2 tokens ( 235.62 ms per token, 4.24 tokens per second) 5.11.464.692 I slot print_timing: id 3 | task 206 | total time = 8033.09 ms / 160 tokens 5.11.464.693 I slot print_timing: id 3 | task 206 | graphs reused = 1 5.11.464.693 I slot print_timing: id 3 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.465.348 I slot release: id 3 | task 206 | stop processing: n_tokens = 159, truncated = 0 5.11.475.143 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.207 5.11.582.920 I slot launch_slot_: id 0 | task 210 | processing task, is_child = 0 5.11.582.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 5.12.032.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 5.12.468.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.381 MiB) 5.13.015.455 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.248 5.13.015.576 I slot launch_slot_: id 1 | task 211 | processing task, is_child = 0 5.13.015.613 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.206 5.13.047.497 I slot launch_slot_: id 2 | task 212 | processing task, is_child = 0 5.13.047.528 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 5.13.047.562 I slot launch_slot_: id 3 | task 213 | processing task, is_child = 0 5.19.640.731 I slot print_timing: id 0 | task 210 | prompt processing, n_tokens = 145, progress = 0.97, t = 6.59 s / 21.99 tokens per second 5.20.436.340 I slot print_timing: id 1 | task 211 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.59 s / 17.90 tokens per second 5.20.536.421 I slot print_timing: id 2 | task 212 | prompt processing, n_tokens = 113, progress = 0.97, t = 6.59 s / 17.14 tokens per second 5.20.551.439 I slot print_timing: id 3 | task 213 | prompt processing, n_tokens = 153, progress = 0.97, t = 6.59 s / 23.21 tokens per second 5.21.266.844 I slot print_timing: id 0 | task 210 | prompt eval time = 7988.40 ms / 149 tokens ( 53.61 ms per token, 18.65 tokens per second) 5.21.266.849 I slot print_timing: id 0 | task 210 | eval time = 230.86 ms / 2 tokens ( 230.86 ms per token, 4.33 tokens per second) 5.21.266.850 I slot print_timing: id 0 | task 210 | total time = 8219.26 ms / 151 tokens 5.21.266.850 I slot print_timing: id 0 | task 210 | graphs reused = 1 5.21.266.851 I slot print_timing: id 0 | task 210 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.268.504 I slot release: id 0 | task 210 | stop processing: n_tokens = 150, truncated = 0 5.21.268.833 I slot print_timing: id 1 | task 211 | prompt eval time = 7988.56 ms / 122 tokens ( 65.48 ms per token, 15.27 tokens per second) 5.21.268.836 I slot print_timing: id 1 | task 211 | eval time = 232.65 ms / 2 tokens ( 232.65 ms per token, 4.30 tokens per second) 5.21.268.836 I slot print_timing: id 1 | task 211 | total time = 8221.21 ms / 124 tokens 5.21.268.837 I slot print_timing: id 1 | task 211 | graphs reused = 1 5.21.268.837 I slot print_timing: id 1 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.268.908 I slot release: id 1 | task 211 | stop processing: n_tokens = 123, truncated = 0 5.21.269.227 I slot print_timing: id 2 | task 212 | prompt eval time = 7988.78 ms / 117 tokens ( 68.28 ms per token, 14.65 tokens per second) 5.21.269.235 I slot print_timing: id 2 | task 212 | eval time = 232.81 ms / 2 tokens ( 232.81 ms per token, 4.30 tokens per second) 5.21.269.236 I slot print_timing: id 2 | task 212 | total time = 8221.59 ms / 119 tokens 5.21.269.236 I slot print_timing: id 2 | task 212 | graphs reused = 1 5.21.269.237 I slot print_timing: id 2 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.269.272 I slot release: id 2 | task 212 | stop processing: n_tokens = 118, truncated = 0 5.21.269.574 I slot print_timing: id 3 | task 213 | prompt eval time = 7989.57 ms / 157 tokens ( 50.89 ms per token, 19.65 tokens per second) 5.21.269.578 I slot print_timing: id 3 | task 213 | eval time = 232.35 ms / 2 tokens ( 232.35 ms per token, 4.30 tokens per second) 5.21.269.578 I slot print_timing: id 3 | task 213 | total time = 8221.92 ms / 159 tokens 5.21.269.579 I slot print_timing: id 3 | task 213 | graphs reused = 1 5.21.269.579 I slot print_timing: id 3 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.271.834 I slot release: id 3 | task 213 | stop processing: n_tokens = 158, truncated = 0 5.21.284.709 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.187 5.21.366.443 I slot launch_slot_: id 0 | task 217 | processing task, is_child = 0 5.21.366.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 5.22.139.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.381 MiB) 5.22.656.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 5.23.192.963 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.228 5.23.193.304 I slot launch_slot_: id 1 | task 218 | processing task, is_child = 0 5.23.193.339 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.237 5.23.193.376 I slot launch_slot_: id 2 | task 219 | processing task, is_child = 0 5.23.193.403 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.177 5.23.193.454 I slot launch_slot_: id 3 | task 220 | processing task, is_child = 0 5.31.205.049 I slot print_timing: id 0 | task 217 | prompt processing, n_tokens = 145, progress = 0.97, t = 8.01 s / 18.10 tokens per second 5.31.397.369 I slot print_timing: id 1 | task 218 | prompt processing, n_tokens = 156, progress = 0.97, t = 8.01 s / 19.47 tokens per second 5.31.418.054 I slot print_timing: id 2 | task 219 | prompt processing, n_tokens = 151, progress = 0.97, t = 8.01 s / 18.85 tokens per second 5.31.422.951 I slot print_timing: id 3 | task 220 | prompt processing, n_tokens = 150, progress = 0.97, t = 8.01 s / 18.72 tokens per second 5.32.131.332 I slot print_timing: id 0 | task 217 | prompt eval time = 8706.63 ms / 149 tokens ( 58.43 ms per token, 17.11 tokens per second) 5.32.131.335 I slot print_timing: id 0 | task 217 | eval time = 231.24 ms / 2 tokens ( 231.24 ms per token, 4.32 tokens per second) 5.32.131.336 I slot print_timing: id 0 | task 217 | total time = 8937.87 ms / 151 tokens 5.32.131.336 I slot print_timing: id 0 | task 217 | graphs reused = 1 5.32.131.337 I slot print_timing: id 0 | task 217 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.131.531 I slot release: id 0 | task 217 | stop processing: n_tokens = 150, truncated = 0 5.32.131.689 I slot print_timing: id 1 | task 218 | prompt eval time = 8707.14 ms / 160 tokens ( 54.42 ms per token, 18.38 tokens per second) 5.32.131.694 I slot print_timing: id 1 | task 218 | eval time = 231.07 ms / 2 tokens ( 231.07 ms per token, 4.33 tokens per second) 5.32.131.695 I slot print_timing: id 1 | task 218 | total time = 8938.20 ms / 162 tokens 5.32.131.695 I slot print_timing: id 1 | task 218 | graphs reused = 1 5.32.131.695 I slot print_timing: id 1 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.133.045 I slot release: id 1 | task 218 | stop processing: n_tokens = 161, truncated = 0 5.32.133.381 I slot print_timing: id 2 | task 219 | prompt eval time = 8707.59 ms / 155 tokens ( 56.18 ms per token, 17.80 tokens per second) 5.32.133.386 I slot print_timing: id 2 | task 219 | eval time = 232.29 ms / 2 tokens ( 232.29 ms per token, 4.31 tokens per second) 5.32.133.386 I slot print_timing: id 2 | task 219 | total time = 8939.87 ms / 157 tokens 5.32.133.386 I slot print_timing: id 2 | task 219 | graphs reused = 1 5.32.133.387 I slot print_timing: id 2 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.134.840 I slot release: id 2 | task 219 | stop processing: n_tokens = 156, truncated = 0 5.32.135.249 I slot print_timing: id 3 | task 220 | prompt eval time = 8708.69 ms / 154 tokens ( 56.55 ms per token, 17.68 tokens per second) 5.32.135.255 I slot print_timing: id 3 | task 220 | eval time = 233.04 ms / 2 tokens ( 233.04 ms per token, 4.29 tokens per second) 5.32.135.255 I slot print_timing: id 3 | task 220 | total time = 8941.73 ms / 156 tokens 5.32.135.256 I slot print_timing: id 3 | task 220 | graphs reused = 1 5.32.135.256 I slot print_timing: id 3 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.136.608 I slot release: id 3 | task 220 | stop processing: n_tokens = 155, truncated = 0 5.32.145.258 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.187 5.32.145.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 5.32.775.827 I slot launch_slot_: id 0 | task 224 | processing task, is_child = 0 5.32.775.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 5.33.143.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 5.33.765.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.569 MiB) 5.34.290.201 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.174 5.34.312.959 I slot launch_slot_: id 1 | task 225 | processing task, is_child = 0 5.34.313.009 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.179 5.34.313.056 I slot launch_slot_: id 2 | task 226 | processing task, is_child = 0 5.34.313.077 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.181 5.34.313.116 I slot launch_slot_: id 3 | task 227 | processing task, is_child = 0 5.40.057.421 I slot print_timing: id 0 | task 224 | prompt processing, n_tokens = 103, progress = 0.96, t = 5.74 s / 17.93 tokens per second 5.41.242.150 I slot print_timing: id 1 | task 225 | prompt processing, n_tokens = 98, progress = 0.96, t = 5.74 s / 17.06 tokens per second 5.41.246.596 I slot print_timing: id 2 | task 226 | prompt processing, n_tokens = 110, progress = 0.96, t = 5.74 s / 19.15 tokens per second 5.41.278.616 I slot print_timing: id 3 | task 227 | prompt processing, n_tokens = 181, progress = 0.98, t = 5.74 s / 31.51 tokens per second 5.41.994.258 I slot print_timing: id 0 | task 224 | prompt eval time = 7450.14 ms / 107 tokens ( 69.63 ms per token, 14.36 tokens per second) 5.41.994.265 I slot print_timing: id 0 | task 224 | eval time = 231.00 ms / 2 tokens ( 231.00 ms per token, 4.33 tokens per second) 5.41.995.310 I slot print_timing: id 0 | task 224 | total time = 7681.13 ms / 109 tokens 5.41.995.313 I slot print_timing: id 0 | task 224 | graphs reused = 1 5.41.995.313 I slot print_timing: id 0 | task 224 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.995.458 I slot release: id 0 | task 224 | stop processing: n_tokens = 108, truncated = 0 5.41.995.790 I slot print_timing: id 1 | task 225 | prompt eval time = 7450.52 ms / 102 tokens ( 73.04 ms per token, 13.69 tokens per second) 5.41.995.793 I slot print_timing: id 1 | task 225 | eval time = 232.12 ms / 2 tokens ( 232.12 ms per token, 4.31 tokens per second) 5.41.995.794 I slot print_timing: id 1 | task 225 | total time = 7682.65 ms / 104 tokens 5.41.995.794 I slot print_timing: id 1 | task 225 | graphs reused = 1 5.41.995.795 I slot print_timing: id 1 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.997.085 I slot release: id 1 | task 225 | stop processing: n_tokens = 103, truncated = 0 5.41.997.426 I slot print_timing: id 2 | task 226 | prompt eval time = 7451.49 ms / 114 tokens ( 65.36 ms per token, 15.30 tokens per second) 5.41.997.431 I slot print_timing: id 2 | task 226 | eval time = 232.78 ms / 2 tokens ( 232.78 ms per token, 4.30 tokens per second) 5.41.997.431 I slot print_timing: id 2 | task 226 | total time = 7684.27 ms / 116 tokens 5.41.997.431 I slot print_timing: id 2 | task 226 | graphs reused = 1 5.41.997.431 I slot print_timing: id 2 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.999.012 I slot release: id 2 | task 226 | stop processing: n_tokens = 115, truncated = 0 5.41.999.337 I slot print_timing: id 3 | task 227 | prompt eval time = 7452.11 ms / 185 tokens ( 40.28 ms per token, 24.83 tokens per second) 5.41.999.345 I slot print_timing: id 3 | task 227 | eval time = 234.05 ms / 2 tokens ( 234.05 ms per token, 4.27 tokens per second) 5.41.999.345 I slot print_timing: id 3 | task 227 | total time = 7686.16 ms / 187 tokens 5.41.999.345 I slot print_timing: id 3 | task 227 | graphs reused = 1 5.41.999.346 I slot print_timing: id 3 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.999.486 I slot release: id 3 | task 227 | stop processing: n_tokens = 186, truncated = 0 5.42.009.033 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.259 5.42.043.276 I slot launch_slot_: id 0 | task 231 | processing task, is_child = 0 5.42.043.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.193 MiB) 5.42.507.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 5.42.885.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.443 MiB) 5.43.531.611 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 5.43.531.737 I slot launch_slot_: id 1 | task 232 | processing task, is_child = 0 5.43.531.784 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 5.43.531.824 I slot launch_slot_: id 2 | task 233 | processing task, is_child = 0 5.43.531.847 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 5.43.531.887 I slot launch_slot_: id 3 | task 234 | processing task, is_child = 0 5.49.779.158 I slot print_timing: id 0 | task 231 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.25 s / 18.89 tokens per second 5.50.576.154 I slot print_timing: id 1 | task 232 | prompt processing, n_tokens = 106, progress = 0.96, t = 6.25 s / 16.97 tokens per second 5.50.600.641 I slot print_timing: id 2 | task 233 | prompt processing, n_tokens = 122, progress = 0.97, t = 6.25 s / 19.53 tokens per second 5.50.605.154 I slot print_timing: id 3 | task 234 | prompt processing, n_tokens = 160, progress = 0.98, t = 6.25 s / 25.61 tokens per second 5.51.307.910 I slot print_timing: id 0 | task 231 | prompt eval time = 7545.61 ms / 122 tokens ( 61.85 ms per token, 16.17 tokens per second) 5.51.307.913 I slot print_timing: id 0 | task 231 | eval time = 230.40 ms / 2 tokens ( 230.40 ms per token, 4.34 tokens per second) 5.51.307.913 I slot print_timing: id 0 | task 231 | total time = 7776.01 ms / 124 tokens 5.51.307.914 I slot print_timing: id 0 | task 231 | graphs reused = 1 5.51.307.914 I slot print_timing: id 0 | task 231 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.307.999 I slot release: id 0 | task 231 | stop processing: n_tokens = 123, truncated = 0 5.51.308.153 I slot print_timing: id 1 | task 232 | prompt eval time = 7546.10 ms / 110 tokens ( 68.60 ms per token, 14.58 tokens per second) 5.51.308.157 I slot print_timing: id 1 | task 232 | eval time = 230.13 ms / 2 tokens ( 230.13 ms per token, 4.35 tokens per second) 5.51.308.158 I slot print_timing: id 1 | task 232 | total time = 7776.23 ms / 112 tokens 5.51.308.158 I slot print_timing: id 1 | task 232 | graphs reused = 1 5.51.308.158 I slot print_timing: id 1 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.309.215 I slot release: id 1 | task 232 | stop processing: n_tokens = 111, truncated = 0 5.51.309.562 I slot print_timing: id 2 | task 233 | prompt eval time = 7546.47 ms / 126 tokens ( 59.89 ms per token, 16.70 tokens per second) 5.51.309.568 I slot print_timing: id 2 | task 233 | eval time = 231.15 ms / 2 tokens ( 231.15 ms per token, 4.33 tokens per second) 5.51.309.568 I slot print_timing: id 2 | task 233 | total time = 7777.62 ms / 128 tokens 5.51.309.569 I slot print_timing: id 2 | task 233 | graphs reused = 1 5.51.309.569 I slot print_timing: id 2 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.310.125 I slot release: id 2 | task 233 | stop processing: n_tokens = 127, truncated = 0 5.51.310.459 I slot print_timing: id 3 | task 234 | prompt eval time = 7547.06 ms / 164 tokens ( 46.02 ms per token, 21.73 tokens per second) 5.51.310.463 I slot print_timing: id 3 | task 234 | eval time = 231.45 ms / 2 tokens ( 231.45 ms per token, 4.32 tokens per second) 5.51.310.464 I slot print_timing: id 3 | task 234 | total time = 7778.51 ms / 166 tokens 5.51.310.464 I slot print_timing: id 3 | task 234 | graphs reused = 1 5.51.310.465 I slot print_timing: id 3 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.310.538 I slot release: id 3 | task 234 | stop processing: n_tokens = 165, truncated = 0 5.51.340.039 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.228 5.51.340.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.819 MiB) 5.52.095.230 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 5.52.095.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.005 MiB) 5.52.767.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.318 MiB) 5.53.126.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 5.53.639.822 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.252 5.53.639.919 I slot launch_slot_: id 1 | task 239 | processing task, is_child = 0 5.53.639.965 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.220 5.53.671.515 I slot launch_slot_: id 2 | task 240 | processing task, is_child = 0 5.53.671.549 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.170 5.53.698.308 I slot launch_slot_: id 3 | task 241 | processing task, is_child = 0 6.00.253.572 I slot print_timing: id 0 | task 238 | prompt processing, n_tokens = 121, progress = 0.97, t = 6.56 s / 18.46 tokens per second 6.00.647.150 I slot print_timing: id 1 | task 239 | prompt processing, n_tokens = 118, progress = 0.97, t = 6.56 s / 18.00 tokens per second 6.00.675.761 I slot print_timing: id 2 | task 240 | prompt processing, n_tokens = 133, progress = 0.97, t = 6.56 s / 20.29 tokens per second 6.00.681.704 I slot print_timing: id 3 | task 241 | prompt processing, n_tokens = 134, progress = 0.97, t = 6.56 s / 20.44 tokens per second 6.01.399.304 I slot print_timing: id 0 | task 238 | prompt eval time = 7469.97 ms / 125 tokens ( 59.76 ms per token, 16.73 tokens per second) 6.01.399.307 I slot print_timing: id 0 | task 238 | eval time = 231.01 ms / 2 tokens ( 231.01 ms per token, 4.33 tokens per second) 6.01.399.308 I slot print_timing: id 0 | task 238 | total time = 7700.98 ms / 127 tokens 6.01.399.309 I slot print_timing: id 0 | task 238 | graphs reused = 1 6.01.399.309 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.399.403 I slot release: id 0 | task 238 | stop processing: n_tokens = 126, truncated = 0 6.01.400.331 I slot print_timing: id 1 | task 239 | prompt eval time = 7470.31 ms / 122 tokens ( 61.23 ms per token, 16.33 tokens per second) 6.01.400.333 I slot print_timing: id 1 | task 239 | eval time = 230.93 ms / 2 tokens ( 230.93 ms per token, 4.33 tokens per second) 6.01.400.334 I slot print_timing: id 1 | task 239 | total time = 7701.24 ms / 124 tokens 6.01.400.334 I slot print_timing: id 1 | task 239 | graphs reused = 1 6.01.400.335 I slot print_timing: id 1 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.400.409 I slot release: id 1 | task 239 | stop processing: n_tokens = 123, truncated = 0 6.01.400.917 I slot print_timing: id 2 | task 240 | prompt eval time = 7470.70 ms / 137 tokens ( 54.53 ms per token, 18.34 tokens per second) 6.01.400.922 I slot print_timing: id 2 | task 240 | eval time = 231.86 ms / 2 tokens ( 231.86 ms per token, 4.31 tokens per second) 6.01.400.923 I slot print_timing: id 2 | task 240 | total time = 7702.56 ms / 139 tokens 6.01.400.923 I slot print_timing: id 2 | task 240 | graphs reused = 1 6.01.400.923 I slot print_timing: id 2 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.401.886 I slot release: id 2 | task 240 | stop processing: n_tokens = 138, truncated = 0 6.01.402.083 I slot print_timing: id 3 | task 241 | prompt eval time = 7471.43 ms / 138 tokens ( 54.14 ms per token, 18.47 tokens per second) 6.01.402.087 I slot print_timing: id 3 | task 241 | eval time = 232.28 ms / 2 tokens ( 232.28 ms per token, 4.31 tokens per second) 6.01.402.087 I slot print_timing: id 3 | task 241 | total time = 7703.71 ms / 140 tokens 6.01.402.087 I slot print_timing: id 3 | task 241 | graphs reused = 1 6.01.402.088 I slot print_timing: id 3 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.403.094 I slot release: id 3 | task 241 | stop processing: n_tokens = 139, truncated = 0 6.01.411.226 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.222 6.01.500.952 I slot launch_slot_: id 0 | task 245 | processing task, is_child = 0 6.01.530.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.694 MiB) 6.01.904.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.318 MiB) 6.02.226.291 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 6.02.244.006 I slot launch_slot_: id 1 | task 246 | processing task, is_child = 0 6.02.244.055 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.203 6.02.244.095 I slot launch_slot_: id 2 | task 247 | processing task, is_child = 0 6.02.244.115 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.201 6.02.244.147 I slot launch_slot_: id 3 | task 248 | processing task, is_child = 0 6.09.185.821 I slot print_timing: id 0 | task 245 | prompt processing, n_tokens = 136, progress = 0.97, t = 6.94 s / 19.59 tokens per second 6.09.988.273 I slot print_timing: id 1 | task 246 | prompt processing, n_tokens = 154, progress = 0.97, t = 6.94 s / 22.19 tokens per second 6.09.992.704 I slot print_timing: id 2 | task 247 | prompt processing, n_tokens = 116, progress = 0.97, t = 6.94 s / 16.71 tokens per second 6.10.003.073 I slot print_timing: id 3 | task 248 | prompt processing, n_tokens = 164, progress = 0.98, t = 6.94 s / 23.63 tokens per second 6.10.704.467 I slot print_timing: id 0 | task 245 | prompt eval time = 8230.51 ms / 140 tokens ( 58.79 ms per token, 17.01 tokens per second) 6.10.704.472 I slot print_timing: id 0 | task 245 | eval time = 229.80 ms / 2 tokens ( 229.80 ms per token, 4.35 tokens per second) 6.10.704.472 I slot print_timing: id 0 | task 245 | total time = 8460.31 ms / 142 tokens 6.10.704.473 I slot print_timing: id 0 | task 245 | graphs reused = 1 6.10.704.473 I slot print_timing: id 0 | task 245 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.705.977 I slot release: id 0 | task 245 | stop processing: n_tokens = 141, truncated = 0 6.10.706.288 I slot print_timing: id 1 | task 246 | prompt eval time = 8230.64 ms / 158 tokens ( 52.09 ms per token, 19.20 tokens per second) 6.10.706.292 I slot print_timing: id 1 | task 246 | eval time = 231.46 ms / 2 tokens ( 231.46 ms per token, 4.32 tokens per second) 6.10.706.292 I slot print_timing: id 1 | task 246 | total time = 8462.10 ms / 160 tokens 6.10.706.293 I slot print_timing: id 1 | task 246 | graphs reused = 1 6.10.706.293 I slot print_timing: id 1 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.707.279 I slot release: id 1 | task 246 | stop processing: n_tokens = 159, truncated = 0 6.10.707.600 I slot print_timing: id 2 | task 247 | prompt eval time = 8230.80 ms / 120 tokens ( 68.59 ms per token, 14.58 tokens per second) 6.10.707.612 I slot print_timing: id 2 | task 247 | eval time = 232.60 ms / 2 tokens ( 232.60 ms per token, 4.30 tokens per second) 6.10.707.613 I slot print_timing: id 2 | task 247 | total time = 8463.39 ms / 122 tokens 6.10.707.614 I slot print_timing: id 2 | task 247 | graphs reused = 1 6.10.707.614 I slot print_timing: id 2 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.707.993 I slot release: id 2 | task 247 | stop processing: n_tokens = 121, truncated = 0 6.10.708.335 I slot print_timing: id 3 | task 248 | prompt eval time = 8230.95 ms / 168 tokens ( 48.99 ms per token, 20.41 tokens per second) 6.10.708.342 I slot print_timing: id 3 | task 248 | eval time = 233.17 ms / 2 tokens ( 233.17 ms per token, 4.29 tokens per second) 6.10.708.342 I slot print_timing: id 3 | task 248 | total time = 8464.11 ms / 170 tokens 6.10.708.342 I slot print_timing: id 3 | task 248 | graphs reused = 1 6.10.708.343 I slot print_timing: id 3 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.710.154 I slot release: id 3 | task 248 | stop processing: n_tokens = 169, truncated = 0 6.10.714.156 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.199 6.10.732.061 I slot launch_slot_: id 0 | task 252 | processing task, is_child = 0 6.10.732.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.068 MiB) 6.11.222.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.881 MiB) 6.11.815.994 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.131 MiB) 6.12.354.107 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 6.12.360.163 I slot launch_slot_: id 1 | task 253 | processing task, is_child = 0 6.12.360.208 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.248 6.12.360.249 I slot launch_slot_: id 2 | task 254 | processing task, is_child = 0 6.12.360.271 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 6.12.360.318 I slot launch_slot_: id 3 | task 255 | processing task, is_child = 0 6.19.377.899 I slot print_timing: id 0 | task 252 | prompt processing, n_tokens = 99, progress = 0.96, t = 7.02 s / 14.11 tokens per second 6.19.829.552 I slot print_timing: id 1 | task 253 | prompt processing, n_tokens = 129, progress = 0.97, t = 7.02 s / 18.38 tokens per second 6.19.846.148 I slot print_timing: id 2 | task 254 | prompt processing, n_tokens = 178, progress = 0.98, t = 7.02 s / 25.37 tokens per second 6.19.854.614 I slot print_timing: id 3 | task 255 | prompt processing, n_tokens = 151, progress = 0.97, t = 7.02 s / 21.52 tokens per second 6.20.580.025 I slot print_timing: id 0 | task 252 | prompt eval time = 7988.31 ms / 103 tokens ( 77.56 ms per token, 12.89 tokens per second) 6.20.580.030 I slot print_timing: id 0 | task 252 | eval time = 231.38 ms / 2 tokens ( 231.38 ms per token, 4.32 tokens per second) 6.20.580.031 I slot print_timing: id 0 | task 252 | total time = 8219.70 ms / 105 tokens 6.20.580.031 I slot print_timing: id 0 | task 252 | graphs reused = 1 6.20.580.032 I slot print_timing: id 0 | task 252 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.580.163 I slot release: id 0 | task 252 | stop processing: n_tokens = 104, truncated = 0 6.20.580.319 I slot print_timing: id 1 | task 253 | prompt eval time = 7988.93 ms / 133 tokens ( 60.07 ms per token, 16.65 tokens per second) 6.20.580.324 I slot print_timing: id 1 | task 253 | eval time = 231.05 ms / 2 tokens ( 231.05 ms per token, 4.33 tokens per second) 6.20.580.324 I slot print_timing: id 1 | task 253 | total time = 8219.98 ms / 135 tokens 6.20.580.325 I slot print_timing: id 1 | task 253 | graphs reused = 1 6.20.580.325 I slot print_timing: id 1 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.580.398 I slot release: id 1 | task 253 | stop processing: n_tokens = 134, truncated = 0 6.20.580.576 I slot print_timing: id 2 | task 254 | prompt eval time = 7989.98 ms / 182 tokens ( 43.90 ms per token, 22.78 tokens per second) 6.20.580.584 I slot print_timing: id 2 | task 254 | eval time = 230.23 ms / 2 tokens ( 230.23 ms per token, 4.34 tokens per second) 6.20.580.585 I slot print_timing: id 2 | task 254 | total time = 8220.22 ms / 184 tokens 6.20.580.585 I slot print_timing: id 2 | task 254 | graphs reused = 1 6.20.580.585 I slot print_timing: id 2 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.580.676 I slot release: id 2 | task 254 | stop processing: n_tokens = 183, truncated = 0 6.20.580.884 I slot print_timing: id 3 | task 255 | prompt eval time = 7990.64 ms / 155 tokens ( 51.55 ms per token, 19.40 tokens per second) 6.20.580.888 I slot print_timing: id 3 | task 255 | eval time = 229.86 ms / 2 tokens ( 229.86 ms per token, 4.35 tokens per second) 6.20.580.889 I slot print_timing: id 3 | task 255 | total time = 8220.50 ms / 157 tokens 6.20.580.894 I slot print_timing: id 3 | task 255 | graphs reused = 1 6.20.580.894 I slot print_timing: id 3 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 6.20.583.740 I slot release: id 3 | task 255 | stop processing: n_tokens = 156, truncated = 0 6.20.593.443 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.269 6.20.619.902 I slot launch_slot_: id 0 | task 259 | processing task, is_child = 0 6.20.619.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.507 MiB) 6.20.976.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.693 MiB) 6.21.024.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.568 MiB) 6.21.571.468 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.209 6.21.571.741 I slot launch_slot_: id 1 | task 260 | processing task, is_child = 0 6.24.637.249 I slot print_timing: id 0 | task 259 | prompt processing, n_tokens = 120, progress = 0.97, t = 3.07 s / 39.15 tokens per second 6.25.085.768 I slot print_timing: id 1 | task 260 | prompt processing, n_tokens = 140, progress = 0.97, t = 3.07 s / 45.67 tokens per second 6.25.517.432 I slot print_timing: id 0 | task 259 | prompt eval time = 3742.18 ms / 124 tokens ( 30.18 ms per token, 33.14 tokens per second) 6.25.517.434 I slot print_timing: id 0 | task 259 | eval time = 203.46 ms / 2 tokens ( 203.46 ms per token, 4.91 tokens per second) 6.25.517.435 I slot print_timing: id 0 | task 259 | total time = 3945.64 ms / 126 tokens 6.25.517.435 I slot print_timing: id 0 | task 259 | graphs reused = 1 6.25.517.436 I slot print_timing: id 0 | task 259 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.519.532 I slot release: id 0 | task 259 | stop processing: n_tokens = 125, truncated = 0 6.25.519.758 I slot print_timing: id 1 | task 260 | prompt eval time = 3742.45 ms / 144 tokens ( 25.99 ms per token, 38.48 tokens per second) 6.25.519.760 I slot print_timing: id 1 | task 260 | eval time = 205.50 ms / 2 tokens ( 205.50 ms per token, 4.87 tokens per second) 6.25.519.761 I slot print_timing: id 1 | task 260 | total time = 3947.95 ms / 146 tokens 6.25.519.761 I slot print_timing: id 1 | task 260 | graphs reused = 1 6.25.519.761 I slot print_timing: id 1 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.520.135 I slot release: id 1 | task 260 | stop processing: n_tokens = 145, truncated = 0 6.25.641.412 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 103455518300 6.25.641.482 I slot launch_slot_: id 2 | task 264 | processing task, is_child = 0 6.25.641.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.756 MiB) 6.26.023.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 6.26.578.960 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 103455521363 6.26.579.034 I slot launch_slot_: id 3 | task 265 | processing task, is_child = 0 6.26.579.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 103460457156 6.26.579.113 I slot launch_slot_: id 0 | task 266 | processing task, is_child = 0 6.26.579.135 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 103460457758 6.26.579.180 I slot launch_slot_: id 1 | task 267 | processing task, is_child = 0 6.32.627.379 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 146, progress = 0.12, t = 6.05 s / 24.14 tokens per second 6.33.856.126 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 146, progress = 0.12, t = 6.05 s / 24.14 tokens per second 6.33.879.041 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 146, progress = 0.12, t = 6.05 s / 24.14 tokens per second 6.33.891.288 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 146, progress = 0.12, t = 6.05 s / 24.14 tokens per second 6.33.912.053 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 257, progress = 0.21, t = 7.33 s / 35.05 tokens per second 6.33.912.070 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 257, progress = 0.21, t = 7.33 s / 35.05 tokens per second 6.33.912.088 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 257, progress = 0.21, t = 7.33 s / 35.05 tokens per second 6.33.912.102 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 257, progress = 0.21, t = 7.33 s / 35.05 tokens per second 7.01.078.140 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 718, progress = 0.58, t = 34.50 s / 20.81 tokens per second 7.01.536.854 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 714, progress = 0.58, t = 34.50 s / 20.70 tokens per second 7.01.551.990 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 699, progress = 0.58, t = 34.50 s / 20.26 tokens per second 7.01.669.283 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 727, progress = 0.58, t = 34.50 s / 21.07 tokens per second 7.21.552.978 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 54.97 s / 20.46 tokens per second 7.21.969.011 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 54.97 s / 20.46 tokens per second 7.22.029.903 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1125, progress = 0.93, t = 54.97 s / 20.46 tokens per second 7.22.071.841 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1125, progress = 0.91, t = 54.97 s / 20.46 tokens per second 7.27.078.441 I slot print_timing: id 0 | task 266 | prompt processing, n_tokens = 1230, progress = 1.00, t = 60.50 s / 20.33 tokens per second 7.27.540.195 I slot print_timing: id 1 | task 267 | prompt processing, n_tokens = 1226, progress = 1.00, t = 60.50 s / 20.26 tokens per second 7.27.593.268 I slot print_timing: id 2 | task 264 | prompt processing, n_tokens = 1211, progress = 1.00, t = 60.50 s / 20.02 tokens per second 7.27.655.878 I slot print_timing: id 3 | task 265 | prompt processing, n_tokens = 1239, progress = 1.00, t = 60.50 s / 20.48 tokens per second 7.43.376.118 I slot print_timing: id 2 | task 264 | prompt eval time = 61636.55 ms / 1215 tokens ( 50.73 ms per token, 19.71 tokens per second) 7.43.376.120 I slot print_timing: id 2 | task 264 | eval time = 15160.34 ms / 67 tokens ( 229.70 ms per token, 4.35 tokens per second) 7.43.376.121 I slot print_timing: id 2 | task 264 | total time = 76796.89 ms / 1282 tokens 7.43.376.121 I slot print_timing: id 2 | task 264 | graphs reused = 67 7.43.376.122 I slot print_timing: id 2 | task 264 | graph reallocs = 0 / 0 (same size) / (changed size) 7.43.380.565 I slot release: id 2 | task 264 | stop processing: n_tokens = 1281, truncated = 0 7.43.709.105 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 7.43.709.139 I slot launch_slot_: id 2 | task 341 | processing task, is_child = 0 7.46.888.012 I slot print_timing: id 1 | task 267 | prompt eval time = 61635.24 ms / 1230 tokens ( 50.11 ms per token, 19.96 tokens per second) 7.46.888.014 I slot print_timing: id 1 | task 267 | eval time = 18673.56 ms / 73 tokens ( 259.36 ms per token, 3.86 tokens per second) 7.46.888.015 I slot print_timing: id 1 | task 267 | total time = 80308.80 ms / 1303 tokens 7.46.888.015 I slot print_timing: id 1 | task 267 | graphs reused = 69 7.46.888.016 I slot print_timing: id 1 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 7.46.888.067 I slot release: id 1 | task 267 | stop processing: n_tokens = 1302, truncated = 0 7.47.216.758 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.880 7.47.216.789 I slot launch_slot_: id 1 | task 348 | processing task, is_child = 0 7.55.697.805 I slot print_timing: id 0 | task 266 | n_gen = 100, tg = 3.60 t/s, tg_3s = 3.64 t/s 7.55.698.213 I slot print_timing: id 3 | task 265 | n_gen = 100, tg = 3.60 t/s, tg_3s = 3.64 t/s 7.58.913.678 I slot print_timing: id 0 | task 266 | n_gen = 114, tg = 3.68 t/s, tg_3s = 4.35 t/s 7.58.914.095 I slot print_timing: id 3 | task 265 | n_gen = 114, tg = 3.68 t/s, tg_3s = 4.35 t/s 8.02.133.167 I slot print_timing: id 0 | task 266 | n_gen = 128, tg = 3.74 t/s, tg_3s = 4.35 t/s 8.02.133.583 I slot print_timing: id 3 | task 265 | n_gen = 128, tg = 3.74 t/s, tg_3s = 4.35 t/s 8.05.352.792 I slot print_timing: id 0 | task 266 | n_gen = 142, tg = 3.80 t/s, tg_3s = 4.35 t/s 8.05.353.194 I slot print_timing: id 3 | task 265 | n_gen = 142, tg = 3.80 t/s, tg_3s = 4.35 t/s 8.08.572.299 I slot print_timing: id 0 | task 266 | n_gen = 156, tg = 3.84 t/s, tg_3s = 4.35 t/s 8.08.572.725 I slot print_timing: id 3 | task 265 | n_gen = 156, tg = 3.84 t/s, tg_3s = 4.35 t/s 8.11.558.905 I slot print_timing: id 2 | task 341 | n_gen = 100, tg = 3.90 t/s, tg_3s = 3.94 t/s 8.11.789.102 I slot print_timing: id 0 | task 266 | n_gen = 170, tg = 3.88 t/s, tg_3s = 4.35 t/s 8.11.789.558 I slot print_timing: id 3 | task 265 | n_gen = 170, tg = 3.88 t/s, tg_3s = 4.35 t/s 8.12.939.447 I slot print_timing: id 1 | task 348 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 8.14.777.097 I slot print_timing: id 2 | task 341 | n_gen = 114, tg = 3.95 t/s, tg_3s = 4.35 t/s 8.15.006.638 I slot print_timing: id 0 | task 266 | n_gen = 184, tg = 3.91 t/s, tg_3s = 4.35 t/s 8.15.007.054 I slot print_timing: id 3 | task 265 | n_gen = 184, tg = 3.91 t/s, tg_3s = 4.35 t/s 8.15.466.188 I slot print_timing: id 1 | task 348 | prompt eval time = 2966.25 ms / 139 tokens ( 21.34 ms per token, 46.86 tokens per second) 8.15.466.193 I slot print_timing: id 1 | task 348 | eval time = 25283.15 ms / 111 tokens ( 229.85 ms per token, 4.35 tokens per second) 8.15.466.194 I slot print_timing: id 1 | task 348 | total time = 28249.39 ms / 250 tokens 8.15.466.194 I slot print_timing: id 1 | task 348 | graphs reused = 178 8.15.466.195 I slot print_timing: id 1 | task 348 | graph reallocs = 0 / 0 (same size) / (changed size) 8.15.466.265 I slot release: id 1 | task 348 | stop processing: n_tokens = 1374, truncated = 0 8.15.796.218 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.834 8.15.796.254 I slot launch_slot_: id 1 | task 462 | processing task, is_child = 0 8.18.131.866 I slot print_timing: id 0 | task 266 | n_gen = 188, tg = 3.75 t/s, tg_3s = 1.28 t/s 8.18.132.034 I slot print_timing: id 2 | task 341 | n_gen = 119, tg = 3.69 t/s, tg_3s = 1.49 t/s 8.18.132.240 I slot print_timing: id 3 | task 265 | n_gen = 188, tg = 3.75 t/s, tg_3s = 1.28 t/s 8.21.268.112 I slot print_timing: id 0 | task 266 | n_gen = 200, tg = 3.75 t/s, tg_3s = 3.83 t/s 8.21.268.401 I slot print_timing: id 2 | task 341 | n_gen = 131, tg = 3.71 t/s, tg_3s = 3.83 t/s 8.21.268.547 I slot print_timing: id 3 | task 265 | n_gen = 200, tg = 3.75 t/s, tg_3s = 3.83 t/s 8.24.486.328 I slot print_timing: id 0 | task 266 | n_gen = 214, tg = 3.79 t/s, tg_3s = 4.35 t/s 8.24.486.601 I slot print_timing: id 2 | task 341 | n_gen = 145, tg = 3.76 t/s, tg_3s = 4.35 t/s 8.24.486.742 I slot print_timing: id 3 | task 265 | n_gen = 214, tg = 3.79 t/s, tg_3s = 4.35 t/s 8.27.703.823 I slot print_timing: id 0 | task 266 | n_gen = 228, tg = 3.82 t/s, tg_3s = 4.35 t/s 8.27.704.131 I slot print_timing: id 2 | task 341 | n_gen = 159, tg = 3.81 t/s, tg_3s = 4.35 t/s 8.27.704.295 I slot print_timing: id 3 | task 265 | n_gen = 228, tg = 3.82 t/s, tg_3s = 4.35 t/s 8.30.919.931 I slot print_timing: id 0 | task 266 | n_gen = 242, tg = 3.84 t/s, tg_3s = 4.35 t/s 8.30.920.232 I slot print_timing: id 2 | task 341 | n_gen = 173, tg = 3.85 t/s, tg_3s = 4.35 t/s 8.30.920.380 I slot print_timing: id 3 | task 265 | n_gen = 242, tg = 3.84 t/s, tg_3s = 4.35 t/s 8.34.140.708 I slot print_timing: id 0 | task 266 | n_gen = 256, tg = 3.87 t/s, tg_3s = 4.35 t/s 8.34.140.987 I slot print_timing: id 2 | task 341 | n_gen = 187, tg = 3.88 t/s, tg_3s = 4.35 t/s 8.34.141.131 I slot print_timing: id 3 | task 265 | n_gen = 256, tg = 3.87 t/s, tg_3s = 4.35 t/s 8.37.357.497 I slot print_timing: id 0 | task 266 | n_gen = 270, tg = 3.89 t/s, tg_3s = 4.35 t/s 8.37.357.778 I slot print_timing: id 2 | task 341 | n_gen = 201, tg = 3.91 t/s, tg_3s = 4.35 t/s 8.37.357.923 I slot print_timing: id 3 | task 265 | n_gen = 270, tg = 3.89 t/s, tg_3s = 4.35 t/s 8.40.579.503 I slot print_timing: id 0 | task 266 | n_gen = 284, tg = 3.91 t/s, tg_3s = 4.35 t/s 8.40.579.773 I slot print_timing: id 2 | task 341 | n_gen = 215, tg = 3.94 t/s, tg_3s = 4.35 t/s 8.40.579.923 I slot print_timing: id 3 | task 265 | n_gen = 284, tg = 3.91 t/s, tg_3s = 4.35 t/s 8.41.500.193 I slot print_timing: id 1 | task 462 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 8.42.880.411 I slot print_timing: id 2 | task 341 | prompt eval time = 2487.74 ms / 132 tokens ( 18.85 ms per token, 53.06 tokens per second) 8.42.880.416 I slot print_timing: id 2 | task 341 | eval time = 56683.51 ms / 225 tokens ( 253.05 ms per token, 3.95 tokens per second) 8.42.880.416 I slot print_timing: id 2 | task 341 | total time = 59171.26 ms / 357 tokens 8.42.880.417 I slot print_timing: id 2 | task 341 | graphs reused = 282 8.42.880.421 I slot print_timing: id 2 | task 341 | graph reallocs = 0 / 0 (same size) / (changed size) 8.42.880.498 I slot release: id 2 | task 341 | stop processing: n_tokens = 1481, truncated = 0 8.43.209.462 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.774 8.43.209.503 I slot launch_slot_: id 2 | task 571 | processing task, is_child = 0 8.45.109.600 I slot print_timing: id 0 | task 266 | n_gen = 296, tg = 3.84 t/s, tg_3s = 2.65 t/s 8.45.109.777 I slot print_timing: id 1 | task 462 | n_gen = 108, tg = 4.06 t/s, tg_3s = 2.22 t/s 8.45.109.957 I slot print_timing: id 3 | task 265 | n_gen = 296, tg = 3.84 t/s, tg_3s = 2.65 t/s 8.48.183.164 I slot print_timing: id 0 | task 266 | n_gen = 308, tg = 3.84 t/s, tg_3s = 3.90 t/s 8.48.183.307 I slot print_timing: id 1 | task 462 | n_gen = 120, tg = 4.04 t/s, tg_3s = 3.90 t/s 8.48.183.592 I slot print_timing: id 3 | task 265 | n_gen = 308, tg = 3.84 t/s, tg_3s = 3.90 t/s 8.51.401.931 I slot print_timing: id 0 | task 266 | n_gen = 322, tg = 3.86 t/s, tg_3s = 4.35 t/s 8.51.402.076 I slot print_timing: id 1 | task 462 | n_gen = 134, tg = 4.07 t/s, tg_3s = 4.35 t/s 8.51.402.351 I slot print_timing: id 3 | task 265 | n_gen = 322, tg = 3.86 t/s, tg_3s = 4.35 t/s 8.54.620.699 I slot print_timing: id 0 | task 266 | n_gen = 336, tg = 3.88 t/s, tg_3s = 4.35 t/s 8.54.620.843 I slot print_timing: id 1 | task 462 | n_gen = 148, tg = 4.10 t/s, tg_3s = 4.35 t/s 8.54.621.120 I slot print_timing: id 3 | task 265 | n_gen = 336, tg = 3.88 t/s, tg_3s = 4.35 t/s 8.57.839.964 I slot print_timing: id 0 | task 266 | n_gen = 350, tg = 3.89 t/s, tg_3s = 4.35 t/s 8.57.840.114 I slot print_timing: id 1 | task 462 | n_gen = 162, tg = 4.12 t/s, tg_3s = 4.35 t/s 8.57.840.403 I slot print_timing: id 3 | task 265 | n_gen = 350, tg = 3.89 t/s, tg_3s = 4.35 t/s 9.01.057.654 I slot print_timing: id 0 | task 266 | n_gen = 364, tg = 3.91 t/s, tg_3s = 4.35 t/s 9.01.057.803 I slot print_timing: id 1 | task 462 | n_gen = 176, tg = 4.14 t/s, tg_3s = 4.35 t/s 9.01.058.098 I slot print_timing: id 3 | task 265 | n_gen = 364, tg = 3.91 t/s, tg_3s = 4.35 t/s 9.01.287.383 I slot print_timing: id 0 | task 266 | prompt eval time = 61634.86 ms / 1234 tokens ( 49.95 ms per token, 20.02 tokens per second) 9.01.287.389 I slot print_timing: id 0 | task 266 | eval time = 93073.34 ms / 365 tokens ( 255.70 ms per token, 3.91 tokens per second) 9.01.287.390 I slot print_timing: id 0 | task 266 | total time = 154708.20 ms / 1599 tokens 9.01.287.390 I slot print_timing: id 0 | task 266 | graphs reused = 349 9.01.287.391 I slot print_timing: id 0 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 9.01.288.996 I slot release: id 0 | task 266 | stop processing: n_tokens = 1598, truncated = 0 9.01.508.314 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.717 9.01.508.349 I slot launch_slot_: id 0 | task 643 | processing task, is_child = 0 9.04.120.785 I slot print_timing: id 1 | task 462 | n_gen = 180, tg = 3.94 t/s, tg_3s = 1.31 t/s 9.04.121.080 I slot print_timing: id 3 | task 265 | n_gen = 368, tg = 3.83 t/s, tg_3s = 1.31 t/s 9.07.340.703 I slot print_timing: id 1 | task 462 | n_gen = 194, tg = 3.97 t/s, tg_3s = 4.35 t/s 9.07.340.981 I slot print_timing: id 3 | task 265 | n_gen = 382, tg = 3.84 t/s, tg_3s = 4.35 t/s 9.10.557.791 I slot print_timing: id 1 | task 462 | n_gen = 208, tg = 3.99 t/s, tg_3s = 4.35 t/s 9.10.557.933 I slot print_timing: id 2 | task 571 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 9.10.558.073 I slot print_timing: id 3 | task 265 | n_gen = 396, tg = 3.86 t/s, tg_3s = 4.35 t/s 9.11.247.312 I slot print_timing: id 3 | task 265 | prompt eval time = 61637.67 ms / 1243 tokens ( 49.59 ms per token, 20.17 tokens per second) 9.11.247.318 I slot print_timing: id 3 | task 265 | eval time = 103030.39 ms / 399 tokens ( 258.87 ms per token, 3.86 tokens per second) 9.11.247.318 I slot print_timing: id 3 | task 265 | total time = 164668.06 ms / 1642 tokens 9.11.247.319 I slot print_timing: id 3 | task 265 | graphs reused = 380 9.11.247.319 I slot print_timing: id 3 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 9.11.247.367 I slot release: id 3 | task 265 | stop processing: n_tokens = 1641, truncated = 0 9.11.465.393 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.698 9.11.465.420 I slot launch_slot_: id 3 | task 678 | processing task, is_child = 0 9.14.005.954 I slot print_timing: id 1 | task 462 | n_gen = 213, tg = 3.84 t/s, tg_3s = 1.45 t/s 9.14.006.176 I slot print_timing: id 2 | task 571 | n_gen = 105, tg = 3.67 t/s, tg_3s = 1.45 t/s 9.17.199.795 I slot print_timing: id 1 | task 462 | n_gen = 226, tg = 3.85 t/s, tg_3s = 4.07 t/s 9.17.199.946 I slot print_timing: id 2 | task 571 | n_gen = 118, tg = 3.71 t/s, tg_3s = 4.07 t/s 9.20.417.778 I slot print_timing: id 1 | task 462 | n_gen = 240, tg = 3.87 t/s, tg_3s = 4.35 t/s 9.20.417.926 I slot print_timing: id 2 | task 571 | n_gen = 132, tg = 3.77 t/s, tg_3s = 4.35 t/s 9.23.635.374 I slot print_timing: id 1 | task 462 | n_gen = 254, tg = 3.90 t/s, tg_3s = 4.35 t/s 9.23.635.520 I slot print_timing: id 2 | task 571 | n_gen = 146, tg = 3.82 t/s, tg_3s = 4.35 t/s 9.26.851.244 I slot print_timing: id 1 | task 462 | n_gen = 268, tg = 3.92 t/s, tg_3s = 4.35 t/s 9.26.851.400 I slot print_timing: id 2 | task 571 | n_gen = 160, tg = 3.86 t/s, tg_3s = 4.35 t/s 9.29.383.222 I slot print_timing: id 0 | task 643 | n_gen = 100, tg = 3.92 t/s, tg_3s = 3.96 t/s 9.30.073.486 I slot print_timing: id 1 | task 462 | n_gen = 282, tg = 3.94 t/s, tg_3s = 4.34 t/s 9.30.073.637 I slot print_timing: id 2 | task 571 | n_gen = 174, tg = 3.89 t/s, tg_3s = 4.34 t/s 9.32.605.668 I slot print_timing: id 0 | task 643 | n_gen = 114, tg = 3.97 t/s, tg_3s = 4.34 t/s 9.33.295.472 I slot print_timing: id 1 | task 462 | n_gen = 296, tg = 3.96 t/s, tg_3s = 4.35 t/s 9.33.295.622 I slot print_timing: id 2 | task 571 | n_gen = 188, tg = 3.93 t/s, tg_3s = 4.35 t/s 9.35.822.999 I slot print_timing: id 0 | task 643 | n_gen = 128, tg = 4.01 t/s, tg_3s = 4.35 t/s 9.36.512.163 I slot print_timing: id 1 | task 462 | n_gen = 310, tg = 3.97 t/s, tg_3s = 4.35 t/s 9.36.512.312 I slot print_timing: id 2 | task 571 | n_gen = 202, tg = 3.95 t/s, tg_3s = 4.35 t/s 9.37.201.193 I slot print_timing: id 3 | task 678 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 9.39.041.152 I slot print_timing: id 0 | task 643 | n_gen = 142, tg = 4.04 t/s, tg_3s = 4.35 t/s 9.39.731.082 I slot print_timing: id 1 | task 462 | n_gen = 324, tg = 3.99 t/s, tg_3s = 4.35 t/s 9.39.731.238 I slot print_timing: id 2 | task 571 | n_gen = 216, tg = 3.98 t/s, tg_3s = 4.35 t/s 9.40.420.801 I slot print_timing: id 3 | task 678 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 9.42.259.249 I slot print_timing: id 0 | task 643 | n_gen = 156, tg = 4.06 t/s, tg_3s = 4.35 t/s 9.42.720.198 I slot print_timing: id 1 | task 462 | prompt eval time = 2941.80 ms / 139 tokens ( 21.16 ms per token, 47.25 tokens per second) 9.42.720.200 I slot print_timing: id 1 | task 462 | eval time = 83982.14 ms / 337 tokens ( 249.95 ms per token, 4.00 tokens per second) 9.42.720.200 I slot print_timing: id 1 | task 462 | total time = 86923.94 ms / 476 tokens 9.42.720.201 I slot print_timing: id 1 | task 462 | graphs reused = 501 9.42.720.201 I slot print_timing: id 1 | task 462 | graph reallocs = 0 / 0 (same size) / (changed size) 9.42.720.267 I slot release: id 1 | task 462 | stop processing: n_tokens = 1600, truncated = 0 9.43.049.247 I slot print_timing: id 2 | task 571 | n_gen = 230, tg = 3.99 t/s, tg_3s = 4.22 t/s 9.43.049.433 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.716 9.43.049.465 I slot launch_slot_: id 1 | task 805 | processing task, is_child = 0 9.45.019.823 I slot print_timing: id 3 | task 678 | n_gen = 126, tg = 4.09 t/s, tg_3s = 2.61 t/s 9.45.623.679 I slot print_timing: id 0 | task 643 | n_gen = 161, tg = 3.86 t/s, tg_3s = 1.49 t/s 9.46.087.705 I slot print_timing: id 2 | task 571 | n_gen = 234, tg = 3.86 t/s, tg_3s = 1.32 t/s 9.48.154.791 I slot print_timing: id 3 | task 678 | n_gen = 138, tg = 4.06 t/s, tg_3s = 3.83 t/s 9.48.843.365 I slot print_timing: id 0 | task 643 | n_gen = 175, tg = 3.89 t/s, tg_3s = 4.35 t/s 9.49.302.792 I slot print_timing: id 2 | task 571 | n_gen = 248, tg = 3.88 t/s, tg_3s = 4.35 t/s 9.51.371.604 I slot print_timing: id 3 | task 678 | n_gen = 152, tg = 4.09 t/s, tg_3s = 4.35 t/s 9.52.059.881 I slot print_timing: id 0 | task 643 | n_gen = 189, tg = 3.92 t/s, tg_3s = 4.35 t/s 9.52.289.932 I slot print_timing: id 2 | task 571 | prompt eval time = 2443.98 ms / 114 tokens ( 21.44 ms per token, 46.65 tokens per second) 9.52.289.938 I slot print_timing: id 2 | task 571 | eval time = 66636.44 ms / 261 tokens ( 256.29 ms per token, 3.90 tokens per second) 9.52.289.938 I slot print_timing: id 2 | task 571 | total time = 69080.42 ms / 375 tokens 9.52.289.939 I slot print_timing: id 2 | task 571 | graphs reused = 529 9.52.289.939 I slot print_timing: id 2 | task 571 | graph reallocs = 0 / 0 (same size) / (changed size) 9.52.290.014 I slot release: id 2 | task 571 | stop processing: n_tokens = 1499, truncated = 0 9.52.618.984 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.765 9.52.619.018 I slot launch_slot_: id 2 | task 838 | processing task, is_child = 0 9.54.722.451 I slot print_timing: id 3 | task 678 | n_gen = 159, tg = 3.92 t/s, tg_3s = 2.09 t/s 9.55.184.896 I slot print_timing: id 0 | task 643 | n_gen = 195, tg = 3.80 t/s, tg_3s = 1.92 t/s 9.57.943.232 I slot print_timing: id 3 | task 678 | n_gen = 173, tg = 3.95 t/s, tg_3s = 4.35 t/s 9.58.402.020 I slot print_timing: id 0 | task 643 | n_gen = 209, tg = 3.83 t/s, tg_3s = 4.35 t/s 10.01.159.508 I slot print_timing: id 3 | task 678 | n_gen = 187, tg = 3.98 t/s, tg_3s = 4.35 t/s 10.01.618.726 I slot print_timing: id 0 | task 643 | n_gen = 223, tg = 3.86 t/s, tg_3s = 4.35 t/s 10.02.766.172 I slot print_timing: id 0 | task 643 | prompt eval time = 2612.29 ms / 141 tokens ( 18.53 ms per token, 53.98 tokens per second) 10.02.766.177 I slot print_timing: id 0 | task 643 | eval time = 58645.53 ms / 228 tokens ( 258.35 ms per token, 3.87 tokens per second) 10.02.766.178 I slot print_timing: id 0 | task 643 | total time = 61257.82 ms / 369 tokens 10.02.766.178 I slot print_timing: id 0 | task 643 | graphs reused = 563 10.02.766.179 I slot print_timing: id 0 | task 643 | graph reallocs = 0 / 0 (same size) / (changed size) 10.02.766.244 I slot release: id 0 | task 643 | stop processing: n_tokens = 1493, truncated = 0 10.02.985.199 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.768 10.02.985.232 I slot launch_slot_: id 0 | task 877 | processing task, is_child = 0 10.04.749.254 I slot print_timing: id 3 | task 678 | n_gen = 196, tg = 3.88 t/s, tg_3s = 2.51 t/s 10.07.931.930 I slot print_timing: id 3 | task 678 | n_gen = 209, tg = 3.89 t/s, tg_3s = 4.08 t/s 10.11.146.763 I slot print_timing: id 3 | task 678 | n_gen = 223, tg = 3.92 t/s, tg_3s = 4.35 t/s 10.11.835.996 I slot print_timing: id 1 | task 805 | n_gen = 100, tg = 3.78 t/s, tg_3s = 3.82 t/s 10.12.295.267 I slot print_timing: id 1 | task 805 | prompt eval time = 2574.44 ms / 125 tokens ( 20.60 ms per token, 48.55 tokens per second) 10.12.295.270 I slot print_timing: id 1 | task 805 | eval time = 26671.35 ms / 102 tokens ( 264.07 ms per token, 3.79 tokens per second) 10.12.295.270 I slot print_timing: id 1 | task 805 | total time = 29245.79 ms / 227 tokens 10.12.295.270 I slot print_timing: id 1 | task 805 | graphs reused = 594 10.12.295.271 I slot print_timing: id 1 | task 805 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.295.318 I slot release: id 1 | task 805 | stop processing: n_tokens = 1351, truncated = 0 10.12.624.626 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.848 10.12.624.662 I slot launch_slot_: id 1 | task 912 | processing task, is_child = 0 10.14.246.399 I slot print_timing: id 3 | task 678 | n_gen = 230, tg = 3.83 t/s, tg_3s = 2.26 t/s 10.17.380.243 I slot print_timing: id 3 | task 678 | n_gen = 242, tg = 3.83 t/s, tg_3s = 3.83 t/s 10.20.600.766 I slot print_timing: id 3 | task 678 | n_gen = 256, tg = 3.85 t/s, tg_3s = 4.35 t/s 10.21.059.744 I slot print_timing: id 2 | task 838 | n_gen = 100, tg = 3.76 t/s, tg_3s = 3.80 t/s 10.21.290.411 I slot print_timing: id 2 | task 838 | prompt eval time = 2103.28 ms / 101 tokens ( 20.82 ms per token, 48.02 tokens per second) 10.21.290.414 I slot print_timing: id 2 | task 838 | eval time = 26568.11 ms / 101 tokens ( 265.68 ms per token, 3.76 tokens per second) 10.21.290.415 I slot print_timing: id 2 | task 838 | total time = 28671.39 ms / 202 tokens 10.21.290.415 I slot print_timing: id 2 | task 838 | graphs reused = 620 10.21.290.416 I slot print_timing: id 2 | task 838 | graph reallocs = 0 / 0 (same size) / (changed size) 10.21.290.458 I slot release: id 2 | task 838 | stop processing: n_tokens = 1326, truncated = 0 10.21.619.824 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.864 10.21.619.862 I slot launch_slot_: id 2 | task 944 | processing task, is_child = 0 10.24.074.031 I slot print_timing: id 3 | task 678 | n_gen = 262, tg = 3.75 t/s, tg_3s = 1.73 t/s 10.24.306.203 I slot print_timing: id 3 | task 678 | prompt eval time = 2976.53 ms / 169 tokens ( 17.61 ms per token, 56.78 tokens per second) 10.24.306.206 I slot print_timing: id 3 | task 678 | eval time = 69864.25 ms / 263 tokens ( 266.66 ms per token, 3.75 tokens per second) 10.24.306.207 I slot print_timing: id 3 | task 678 | total time = 72840.77 ms / 432 tokens 10.24.306.207 I slot print_timing: id 3 | task 678 | graphs reused = 620 10.24.306.208 I slot print_timing: id 3 | task 678 | graph reallocs = 0 / 0 (same size) / (changed size) 10.24.306.262 I slot release: id 3 | task 678 | stop processing: n_tokens = 1556, truncated = 0 10.24.524.170 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.737 10.24.524.203 I slot launch_slot_: id 3 | task 949 | processing task, is_child = 0 10.34.022.141 I slot print_timing: id 0 | task 877 | n_gen = 100, tg = 3.43 t/s, tg_3s = 3.47 t/s 10.37.239.781 I slot print_timing: id 0 | task 877 | n_gen = 114, tg = 3.52 t/s, tg_3s = 4.35 t/s 10.40.458.056 I slot print_timing: id 0 | task 877 | n_gen = 128, tg = 3.60 t/s, tg_3s = 4.35 t/s 10.41.837.333 I slot print_timing: id 1 | task 912 | n_gen = 100, tg = 3.67 t/s, tg_3s = 3.71 t/s 10.43.674.543 I slot print_timing: id 0 | task 877 | n_gen = 142, tg = 3.66 t/s, tg_3s = 4.35 t/s 10.44.823.203 I slot print_timing: id 2 | task 944 | prompt eval time = 2453.95 ms / 120 tokens ( 20.45 ms per token, 48.90 tokens per second) 10.44.823.209 I slot print_timing: id 2 | task 944 | eval time = 20749.39 ms / 82 tokens ( 256.17 ms per token, 3.90 tokens per second) 10.44.823.219 I slot print_timing: id 2 | task 944 | total time = 23203.33 ms / 202 tokens 10.44.823.222 I slot print_timing: id 2 | task 944 | graphs reused = 696 10.44.823.222 I slot print_timing: id 2 | task 944 | graph reallocs = 0 / 0 (same size) / (changed size) 10.44.823.273 I slot release: id 2 | task 944 | stop processing: n_tokens = 1326, truncated = 0 10.45.152.319 I slot print_timing: id 1 | task 912 | n_gen = 114, tg = 3.73 t/s, tg_3s = 4.22 t/s 10.45.152.472 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.864 10.45.152.502 I slot launch_slot_: id 2 | task 1030 | processing task, is_child = 0 10.46.702.990 I slot print_timing: id 0 | task 877 | n_gen = 149, tg = 3.56 t/s, tg_3s = 2.31 t/s 10.48.169.181 I slot print_timing: id 1 | task 912 | n_gen = 120, tg = 3.57 t/s, tg_3s = 1.99 t/s 10.49.777.188 I slot print_timing: id 0 | task 877 | n_gen = 161, tg = 3.59 t/s, tg_3s = 3.90 t/s 10.49.777.346 I slot print_timing: id 1 | task 912 | prompt eval time = 2225.99 ms / 95 tokens ( 23.43 ms per token, 42.68 tokens per second) 10.49.777.348 I slot print_timing: id 1 | task 912 | eval time = 34926.69 ms / 127 tokens ( 277.20 ms per token, 3.61 tokens per second) 10.49.777.348 I slot print_timing: id 1 | task 912 | total time = 37152.68 ms / 222 tokens 10.49.777.349 I slot print_timing: id 1 | task 912 | graphs reused = 706 10.49.777.349 I slot print_timing: id 1 | task 912 | graph reallocs = 0 / 0 (same size) / (changed size) 10.49.777.394 I slot release: id 1 | task 912 | stop processing: n_tokens = 1346, truncated = 0 10.50.107.072 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.851 10.50.107.104 I slot launch_slot_: id 1 | task 1045 | processing task, is_child = 0 10.52.919.647 I slot print_timing: id 0 | task 877 | n_gen = 165, tg = 3.43 t/s, tg_3s = 1.27 t/s 10.53.839.867 I slot print_timing: id 3 | task 949 | n_gen = 100, tg = 3.71 t/s, tg_3s = 3.74 t/s 10.56.138.675 I slot print_timing: id 0 | task 877 | n_gen = 179, tg = 3.49 t/s, tg_3s = 4.35 t/s 10.57.057.794 I slot print_timing: id 3 | task 949 | n_gen = 114, tg = 3.78 t/s, tg_3s = 4.35 t/s 10.59.354.691 I slot print_timing: id 0 | task 877 | n_gen = 193, tg = 3.54 t/s, tg_3s = 4.35 t/s 11.00.274.675 I slot print_timing: id 3 | task 949 | n_gen = 128, tg = 3.83 t/s, tg_3s = 4.35 t/s 11.02.573.389 I slot print_timing: id 0 | task 877 | n_gen = 207, tg = 3.59 t/s, tg_3s = 4.35 t/s 11.03.493.845 I slot print_timing: id 3 | task 949 | n_gen = 142, tg = 3.88 t/s, tg_3s = 4.35 t/s 11.05.791.443 I slot print_timing: id 0 | task 877 | n_gen = 221, tg = 3.63 t/s, tg_3s = 4.35 t/s 11.06.710.548 I slot print_timing: id 3 | task 949 | n_gen = 156, tg = 3.92 t/s, tg_3s = 4.35 t/s 11.09.007.013 I slot print_timing: id 0 | task 877 | n_gen = 235, tg = 3.67 t/s, tg_3s = 4.35 t/s 11.09.926.324 I slot print_timing: id 3 | task 949 | n_gen = 170, tg = 3.95 t/s, tg_3s = 4.35 t/s 11.12.223.458 I slot print_timing: id 0 | task 877 | n_gen = 249, tg = 3.70 t/s, tg_3s = 4.35 t/s 11.12.223.738 I slot print_timing: id 2 | task 1030 | n_gen = 100, tg = 3.96 t/s, tg_3s = 4.00 t/s 11.13.142.991 I slot print_timing: id 3 | task 949 | n_gen = 184, tg = 3.98 t/s, tg_3s = 4.35 t/s 11.15.442.725 I slot print_timing: id 0 | task 877 | n_gen = 263, tg = 3.73 t/s, tg_3s = 4.35 t/s 11.15.442.874 I slot print_timing: id 1 | task 1045 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 11.15.443.016 I slot print_timing: id 2 | task 1030 | n_gen = 114, tg = 4.01 t/s, tg_3s = 4.35 t/s 11.16.362.180 I slot print_timing: id 3 | task 949 | n_gen = 198, tg = 4.00 t/s, tg_3s = 4.35 t/s 11.18.664.024 I slot print_timing: id 0 | task 877 | n_gen = 277, tg = 3.76 t/s, tg_3s = 4.35 t/s 11.18.664.171 I slot print_timing: id 1 | task 1045 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 11.18.664.306 I slot print_timing: id 2 | task 1030 | n_gen = 128, tg = 4.04 t/s, tg_3s = 4.35 t/s 11.19.585.860 I slot print_timing: id 3 | task 949 | n_gen = 212, tg = 4.02 t/s, tg_3s = 4.34 t/s 11.20.274.962 I slot print_timing: id 2 | task 1030 | prompt eval time = 2095.57 ms / 86 tokens ( 24.37 ms per token, 41.04 tokens per second) 11.20.274.967 I slot print_timing: id 2 | task 1030 | eval time = 33026.88 ms / 135 tokens ( 246.47 ms per token, 4.06 tokens per second) 11.20.274.968 I slot print_timing: id 2 | task 1030 | total time = 35122.45 ms / 221 tokens 11.20.274.968 I slot print_timing: id 2 | task 1030 | graphs reused = 825 11.20.274.969 I slot print_timing: id 2 | task 1030 | graph reallocs = 0 / 0 (same size) / (changed size) 11.20.275.011 I slot release: id 2 | task 1030 | stop processing: n_tokens = 1345, truncated = 0 11.20.604.459 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.852 11.20.604.493 I slot launch_slot_: id 2 | task 1169 | processing task, is_child = 0 11.22.167.038 I slot print_timing: id 0 | task 877 | n_gen = 286, tg = 3.70 t/s, tg_3s = 2.57 t/s 11.22.167.208 I slot print_timing: id 1 | task 1045 | n_gen = 123, tg = 4.14 t/s, tg_3s = 2.57 t/s 11.22.711.526 I slot print_timing: id 3 | task 949 | n_gen = 218, tg = 3.90 t/s, tg_3s = 1.92 t/s 11.25.240.320 I slot print_timing: id 0 | task 877 | n_gen = 298, tg = 3.71 t/s, tg_3s = 3.90 t/s 11.25.240.466 I slot print_timing: id 1 | task 1045 | n_gen = 135, tg = 4.12 t/s, tg_3s = 3.90 t/s 11.25.929.675 I slot print_timing: id 3 | task 949 | n_gen = 232, tg = 3.93 t/s, tg_3s = 4.35 t/s 11.28.460.156 I slot print_timing: id 0 | task 877 | n_gen = 312, tg = 3.73 t/s, tg_3s = 4.35 t/s 11.28.460.299 I slot print_timing: id 1 | task 1045 | n_gen = 149, tg = 4.14 t/s, tg_3s = 4.35 t/s 11.29.149.985 I slot print_timing: id 3 | task 949 | n_gen = 246, tg = 3.95 t/s, tg_3s = 4.35 t/s 11.31.677.514 I slot print_timing: id 0 | task 877 | n_gen = 326, tg = 3.76 t/s, tg_3s = 4.35 t/s 11.31.677.654 I slot print_timing: id 1 | task 1045 | n_gen = 163, tg = 4.15 t/s, tg_3s = 4.35 t/s 11.31.907.134 I slot print_timing: id 1 | task 1045 | prompt eval time = 2579.41 ms / 133 tokens ( 19.39 ms per token, 51.56 tokens per second) 11.31.907.136 I slot print_timing: id 1 | task 1045 | eval time = 39220.61 ms / 164 tokens ( 240.62 ms per token, 4.16 tokens per second) 11.31.907.137 I slot print_timing: id 1 | task 1045 | total time = 41800.02 ms / 297 tokens 11.31.907.137 I slot print_timing: id 1 | task 1045 | graphs reused = 863 11.31.907.146 I slot print_timing: id 1 | task 1045 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.908.542 I slot release: id 1 | task 1045 | stop processing: n_tokens = 1421, truncated = 0 11.32.238.293 I slot print_timing: id 3 | task 949 | n_gen = 259, tg = 3.96 t/s, tg_3s = 4.21 t/s 11.32.238.301 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.806 11.32.238.334 I slot launch_slot_: id 1 | task 1213 | processing task, is_child = 0 11.34.684.792 I slot print_timing: id 0 | task 877 | n_gen = 331, tg = 3.69 t/s, tg_3s = 1.66 t/s 11.35.376.669 I slot print_timing: id 3 | task 949 | n_gen = 265, tg = 3.87 t/s, tg_3s = 1.91 t/s 11.37.904.110 I slot print_timing: id 0 | task 877 | n_gen = 345, tg = 3.71 t/s, tg_3s = 4.35 t/s 11.38.593.947 I slot print_timing: id 3 | task 949 | n_gen = 279, tg = 3.89 t/s, tg_3s = 4.35 t/s 11.39.513.167 I slot print_timing: id 2 | task 1169 | prompt eval time = 2106.89 ms / 97 tokens ( 21.72 ms per token, 46.04 tokens per second) 11.39.513.173 I slot print_timing: id 2 | task 1169 | eval time = 16801.78 ms / 66 tokens ( 258.49 ms per token, 3.87 tokens per second) 11.39.513.175 I slot print_timing: id 2 | task 1169 | total time = 18908.66 ms / 163 tokens 11.39.513.175 I slot print_timing: id 2 | task 1169 | graphs reused = 884 11.39.513.176 I slot print_timing: id 2 | task 1169 | graph reallocs = 0 / 0 (same size) / (changed size) 11.39.513.227 I slot release: id 2 | task 1169 | stop processing: n_tokens = 1287, truncated = 0 11.39.841.508 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.890 11.39.841.548 I slot launch_slot_: id 2 | task 1239 | processing task, is_child = 0 11.41.399.760 I slot print_timing: id 0 | task 877 | n_gen = 354, tg = 3.67 t/s, tg_3s = 2.57 t/s 11.41.944.276 I slot print_timing: id 3 | task 949 | n_gen = 286, tg = 3.81 t/s, tg_3s = 2.09 t/s 11.44.475.784 I slot print_timing: id 0 | task 877 | n_gen = 366, tg = 3.68 t/s, tg_3s = 3.90 t/s 11.45.166.582 I slot print_timing: id 3 | task 949 | n_gen = 300, tg = 3.83 t/s, tg_3s = 4.34 t/s 11.47.693.848 I slot print_timing: id 0 | task 877 | n_gen = 380, tg = 3.70 t/s, tg_3s = 4.35 t/s 11.48.384.258 I slot print_timing: id 3 | task 949 | n_gen = 314, tg = 3.85 t/s, tg_3s = 4.35 t/s 11.50.915.116 I slot print_timing: id 0 | task 877 | n_gen = 394, tg = 3.72 t/s, tg_3s = 4.35 t/s 11.51.605.118 I slot print_timing: id 3 | task 949 | n_gen = 328, tg = 3.87 t/s, tg_3s = 4.35 t/s 11.54.136.114 I slot print_timing: id 0 | task 877 | n_gen = 408, tg = 3.74 t/s, tg_3s = 4.35 t/s 11.54.366.046 I slot print_timing: id 1 | task 1213 | prompt eval time = 2214.42 ms / 84 tokens ( 26.36 ms per token, 37.93 tokens per second) 11.54.366.049 I slot print_timing: id 1 | task 1213 | eval time = 19913.28 ms / 80 tokens ( 252.07 ms per token, 3.97 tokens per second) 11.54.366.049 I slot print_timing: id 1 | task 1213 | total time = 22127.71 ms / 164 tokens 11.54.366.050 I slot print_timing: id 1 | task 1213 | graphs reused = 937 11.54.366.050 I slot print_timing: id 1 | task 1213 | graph reallocs = 0 / 0 (same size) / (changed size) 11.54.366.096 I slot release: id 1 | task 1213 | stop processing: n_tokens = 1288, truncated = 0 11.54.695.583 I slot print_timing: id 3 | task 949 | n_gen = 341, tg = 3.88 t/s, tg_3s = 4.21 t/s 11.54.695.591 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.890 11.54.695.621 I slot launch_slot_: id 1 | task 1297 | processing task, is_child = 0 11.57.153.002 I slot print_timing: id 0 | task 877 | n_gen = 413, tg = 3.68 t/s, tg_3s = 1.66 t/s 11.57.843.847 I slot print_timing: id 3 | task 949 | n_gen = 347, tg = 3.81 t/s, tg_3s = 1.91 t/s 12.00.371.539 I slot print_timing: id 0 | task 877 | n_gen = 427, tg = 3.70 t/s, tg_3s = 4.35 t/s 12.01.061.722 I slot print_timing: id 3 | task 949 | n_gen = 361, tg = 3.83 t/s, tg_3s = 4.35 t/s 12.03.589.926 I slot print_timing: id 0 | task 877 | n_gen = 441, tg = 3.72 t/s, tg_3s = 4.35 t/s 12.04.280.463 I slot print_timing: id 3 | task 949 | n_gen = 375, tg = 3.85 t/s, tg_3s = 4.35 t/s 12.06.580.736 I slot print_timing: id 2 | task 1239 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 12.06.810.551 I slot print_timing: id 0 | task 877 | n_gen = 455, tg = 3.73 t/s, tg_3s = 4.35 t/s 12.07.502.803 I slot print_timing: id 3 | task 949 | n_gen = 389, tg = 3.87 t/s, tg_3s = 4.34 t/s 12.09.804.484 I slot print_timing: id 2 | task 1239 | n_gen = 114, tg = 4.06 t/s, tg_3s = 4.34 t/s 12.10.034.136 I slot print_timing: id 0 | task 877 | n_gen = 469, tg = 3.75 t/s, tg_3s = 4.34 t/s 12.10.724.494 I slot print_timing: id 3 | task 949 | n_gen = 403, tg = 3.88 t/s, tg_3s = 4.35 t/s 12.11.874.458 I slot print_timing: id 1 | task 1297 | prompt eval time = 2224.08 ms / 95 tokens ( 23.41 ms per token, 42.71 tokens per second) 12.11.874.463 I slot print_timing: id 1 | task 1297 | eval time = 14954.75 ms / 66 tokens ( 230.07 ms per token, 4.35 tokens per second) 12.11.874.464 I slot print_timing: id 1 | task 1297 | total time = 17178.83 ms / 161 tokens 12.11.874.464 I slot print_timing: id 1 | task 1297 | graphs reused = 1001 12.11.874.465 I slot print_timing: id 1 | task 1297 | graph reallocs = 0 / 0 (same size) / (changed size) 12.11.874.511 I slot release: id 1 | task 1297 | stop processing: n_tokens = 1285, truncated = 0 12.12.204.095 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.892 12.12.204.136 I slot launch_slot_: id 1 | task 1366 | processing task, is_child = 0 12.14.185.863 I slot print_timing: id 0 | task 877 | n_gen = 479, tg = 3.71 t/s, tg_3s = 2.41 t/s 12.14.186.020 I slot print_timing: id 2 | task 1239 | n_gen = 125, tg = 3.85 t/s, tg_3s = 2.51 t/s 12.14.186.175 I slot print_timing: id 3 | task 949 | n_gen = 410, tg = 3.82 t/s, tg_3s = 2.02 t/s 12.17.325.556 I slot print_timing: id 0 | task 877 | n_gen = 491, tg = 3.71 t/s, tg_3s = 3.82 t/s 12.17.325.828 I slot print_timing: id 2 | task 1239 | n_gen = 137, tg = 3.84 t/s, tg_3s = 3.82 t/s 12.17.325.969 I slot print_timing: id 3 | task 949 | n_gen = 422, tg = 3.82 t/s, tg_3s = 3.82 t/s 12.20.546.812 I slot print_timing: id 0 | task 877 | n_gen = 505, tg = 3.72 t/s, tg_3s = 4.35 t/s 12.20.547.100 I slot print_timing: id 2 | task 1239 | n_gen = 151, tg = 3.89 t/s, tg_3s = 4.35 t/s 12.20.547.241 I slot print_timing: id 3 | task 949 | n_gen = 436, tg = 3.84 t/s, tg_3s = 4.35 t/s 12.22.388.029 I slot print_timing: id 3 | task 949 | prompt eval time = 2608.27 ms / 148 tokens ( 17.62 ms per token, 56.74 tokens per second) 12.22.388.035 I slot print_timing: id 3 | task 949 | eval time = 115255.54 ms / 444 tokens ( 260.17 ms per token, 3.84 tokens per second) 12.22.388.036 I slot print_timing: id 3 | task 949 | total time = 117863.81 ms / 592 tokens 12.22.388.036 I slot print_timing: id 3 | task 949 | graphs reused = 1033 12.22.388.037 I slot print_timing: id 3 | task 949 | graph reallocs = 0 / 0 (same size) / (changed size) 12.22.388.083 I slot release: id 3 | task 949 | stop processing: n_tokens = 1716, truncated = 0 12.22.606.758 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.668 12.22.606.793 I slot launch_slot_: id 3 | task 1403 | processing task, is_child = 0 12.24.053.323 I slot print_timing: id 0 | task 877 | n_gen = 515, tg = 3.70 t/s, tg_3s = 2.85 t/s 12.24.053.639 I slot print_timing: id 2 | task 1239 | n_gen = 161, tg = 3.80 t/s, tg_3s = 2.85 t/s 12.24.949.946 I slot print_timing: id 2 | task 1239 | prompt eval time = 2102.58 ms / 101 tokens ( 20.82 ms per token, 48.04 tokens per second) 12.24.949.952 I slot print_timing: id 2 | task 1239 | eval time = 43005.81 ms / 164 tokens ( 263.84 ms per token, 3.79 tokens per second) 12.24.949.953 I slot print_timing: id 2 | task 1239 | total time = 45108.39 ms / 265 tokens 12.24.949.953 I slot print_timing: id 2 | task 1239 | graphs reused = 1034 12.24.949.953 I slot print_timing: id 2 | task 1239 | graph reallocs = 0 / 0 (same size) / (changed size) 12.24.950.000 I slot release: id 2 | task 1239 | stop processing: n_tokens = 1389, truncated = 0 12.25.279.017 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.825 12.25.279.062 I slot launch_slot_: id 2 | task 1409 | processing task, is_child = 0 12.27.383.609 I slot print_timing: id 0 | task 877 | n_gen = 521, tg = 3.66 t/s, tg_3s = 1.80 t/s 12.30.604.643 I slot print_timing: id 0 | task 877 | n_gen = 535, tg = 3.67 t/s, tg_3s = 4.35 t/s 12.33.822.783 I slot print_timing: id 0 | task 877 | n_gen = 549, tg = 3.69 t/s, tg_3s = 4.35 t/s 12.37.039.626 I slot print_timing: id 0 | task 877 | n_gen = 563, tg = 3.70 t/s, tg_3s = 4.35 t/s 12.40.261.452 I slot print_timing: id 0 | task 877 | n_gen = 577, tg = 3.71 t/s, tg_3s = 4.35 t/s 12.40.721.092 I slot print_timing: id 1 | task 1366 | n_gen = 100, tg = 3.82 t/s, tg_3s = 3.86 t/s 12.43.479.460 I slot print_timing: id 0 | task 877 | n_gen = 591, tg = 3.73 t/s, tg_3s = 4.35 t/s 12.43.939.310 I slot print_timing: id 1 | task 1366 | n_gen = 114, tg = 3.88 t/s, tg_3s = 4.35 t/s 12.46.698.223 I slot print_timing: id 0 | task 877 | n_gen = 605, tg = 3.74 t/s, tg_3s = 4.35 t/s 12.47.158.038 I slot print_timing: id 1 | task 1366 | n_gen = 128, tg = 3.92 t/s, tg_3s = 4.35 t/s 12.48.997.904 I slot print_timing: id 3 | task 1403 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 12.49.917.158 I slot print_timing: id 0 | task 877 | n_gen = 619, tg = 3.75 t/s, tg_3s = 4.35 t/s 12.50.147.439 I slot print_timing: id 2 | task 1409 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 12.50.377.173 I slot print_timing: id 1 | task 1366 | n_gen = 142, tg = 3.96 t/s, tg_3s = 4.35 t/s 12.52.218.510 I slot print_timing: id 3 | task 1403 | n_gen = 114, tg = 4.07 t/s, tg_3s = 4.35 t/s 12.53.137.582 I slot print_timing: id 0 | task 877 | n_gen = 633, tg = 3.76 t/s, tg_3s = 4.35 t/s 12.53.367.808 I slot print_timing: id 2 | task 1409 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 12.53.597.754 I slot print_timing: id 1 | task 1366 | n_gen = 156, tg = 3.99 t/s, tg_3s = 4.35 t/s 12.54.057.902 I slot print_timing: id 3 | task 1403 | prompt eval time = 1881.60 ms / 90 tokens ( 20.91 ms per token, 47.83 tokens per second) 12.54.057.908 I slot print_timing: id 3 | task 1403 | eval time = 29569.50 ms / 122 tokens ( 244.38 ms per token, 4.09 tokens per second) 12.54.057.909 I slot print_timing: id 3 | task 1403 | total time = 31451.10 ms / 212 tokens 12.54.057.909 I slot print_timing: id 3 | task 1403 | graphs reused = 1148 12.54.057.910 I slot print_timing: id 3 | task 1403 | graph reallocs = 0 / 0 (same size) / (changed size) 12.54.057.957 I slot release: id 3 | task 1403 | stop processing: n_tokens = 1336, truncated = 0 12.54.276.019 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.858 12.54.276.053 I slot launch_slot_: id 3 | task 1529 | processing task, is_child = 0 12.56.153.616 I slot print_timing: id 0 | task 877 | n_gen = 640, tg = 3.74 t/s, tg_3s = 2.32 t/s 12.56.385.769 I slot print_timing: id 2 | task 1409 | n_gen = 121, tg = 4.14 t/s, tg_3s = 2.32 t/s 12.56.615.634 I slot print_timing: id 1 | task 1366 | n_gen = 163, tg = 3.87 t/s, tg_3s = 2.32 t/s 12.59.374.109 I slot print_timing: id 0 | task 877 | n_gen = 654, tg = 3.75 t/s, tg_3s = 4.35 t/s 12.59.604.451 I slot print_timing: id 2 | task 1409 | n_gen = 135, tg = 4.16 t/s, tg_3s = 4.35 t/s 12.59.834.286 I slot print_timing: id 1 | task 1366 | n_gen = 177, tg = 3.91 t/s, tg_3s = 4.35 t/s 13.02.593.943 I slot print_timing: id 0 | task 877 | n_gen = 668, tg = 3.76 t/s, tg_3s = 4.35 t/s 13.02.824.213 I slot print_timing: id 2 | task 1409 | n_gen = 149, tg = 4.18 t/s, tg_3s = 4.35 t/s 13.03.053.935 I slot print_timing: id 1 | task 1366 | n_gen = 191, tg = 3.94 t/s, tg_3s = 4.35 t/s 13.05.815.111 I slot print_timing: id 0 | task 877 | n_gen = 682, tg = 3.77 t/s, tg_3s = 4.35 t/s 13.06.045.327 I slot print_timing: id 2 | task 1409 | n_gen = 163, tg = 4.19 t/s, tg_3s = 4.35 t/s 13.06.275.117 I slot print_timing: id 1 | task 1366 | n_gen = 205, tg = 3.96 t/s, tg_3s = 4.35 t/s 13.08.118.396 I slot print_timing: id 2 | task 1409 | prompt eval time = 2104.85 ms / 96 tokens ( 21.93 ms per token, 45.61 tokens per second) 13.08.118.402 I slot print_timing: id 2 | task 1409 | eval time = 40734.47 ms / 172 tokens ( 238.21 ms per token, 4.20 tokens per second) 13.08.118.402 I slot print_timing: id 2 | task 1409 | total time = 42839.32 ms / 268 tokens 13.08.118.403 I slot print_timing: id 2 | task 1409 | graphs reused = 1199 13.08.118.403 I slot print_timing: id 2 | task 1409 | graph reallocs = 0 / 0 (same size) / (changed size) 13.08.118.456 I slot release: id 2 | task 1409 | stop processing: n_tokens = 1392, truncated = 0 13.08.447.736 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.823 13.08.447.767 I slot launch_slot_: id 2 | task 1585 | processing task, is_child = 0 13.10.371.682 I slot print_timing: id 0 | task 877 | n_gen = 694, tg = 3.74 t/s, tg_3s = 2.63 t/s 13.10.371.841 I slot print_timing: id 1 | task 1366 | n_gen = 215, tg = 3.85 t/s, tg_3s = 2.44 t/s 13.13.449.464 I slot print_timing: id 0 | task 877 | n_gen = 706, tg = 3.74 t/s, tg_3s = 3.90 t/s 13.13.449.612 I slot print_timing: id 1 | task 1366 | n_gen = 227, tg = 3.85 t/s, tg_3s = 3.90 t/s 13.16.669.332 I slot print_timing: id 0 | task 877 | n_gen = 720, tg = 3.75 t/s, tg_3s = 4.35 t/s 13.16.669.475 I slot print_timing: id 1 | task 1366 | n_gen = 241, tg = 3.88 t/s, tg_3s = 4.35 t/s 13.19.886.931 I slot print_timing: id 0 | task 877 | n_gen = 734, tg = 3.76 t/s, tg_3s = 4.35 t/s 13.19.887.086 I slot print_timing: id 1 | task 1366 | n_gen = 255, tg = 3.90 t/s, tg_3s = 4.35 t/s 13.21.037.999 I slot print_timing: id 3 | task 1529 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 13.23.108.125 I slot print_timing: id 0 | task 877 | n_gen = 748, tg = 3.77 t/s, tg_3s = 4.35 t/s 13.23.108.268 I slot print_timing: id 1 | task 1366 | n_gen = 269, tg = 3.92 t/s, tg_3s = 4.35 t/s 13.24.259.462 I slot print_timing: id 3 | task 1529 | n_gen = 114, tg = 4.02 t/s, tg_3s = 4.35 t/s 13.26.329.243 I slot print_timing: id 0 | task 877 | n_gen = 762, tg = 3.78 t/s, tg_3s = 4.35 t/s 13.26.329.393 I slot print_timing: id 1 | task 1366 | n_gen = 283, tg = 3.94 t/s, tg_3s = 4.35 t/s 13.27.479.565 I slot print_timing: id 3 | task 1529 | n_gen = 128, tg = 4.05 t/s, tg_3s = 4.35 t/s 13.27.939.397 I slot print_timing: id 3 | task 1529 | prompt eval time = 1878.04 ms / 87 tokens ( 21.59 ms per token, 46.32 tokens per second) 13.27.939.402 I slot print_timing: id 3 | task 1529 | eval time = 31785.29 ms / 130 tokens ( 246.40 ms per token, 4.06 tokens per second) 13.27.939.403 I slot print_timing: id 3 | task 1529 | total time = 33663.34 ms / 217 tokens 13.27.939.403 I slot print_timing: id 3 | task 1529 | graphs reused = 1272 13.27.939.404 I slot print_timing: id 3 | task 1529 | graph reallocs = 0 / 0 (same size) / (changed size) 13.27.939.449 I slot release: id 3 | task 1529 | stop processing: n_tokens = 1341, truncated = 0 13.28.157.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.855 13.28.157.572 I slot launch_slot_: id 3 | task 1663 | processing task, is_child = 0 13.30.322.023 I slot print_timing: id 0 | task 877 | n_gen = 771, tg = 3.75 t/s, tg_3s = 2.25 t/s 13.30.322.189 I slot print_timing: id 1 | task 1366 | n_gen = 292, tg = 3.85 t/s, tg_3s = 2.25 t/s 13.32.830.340 I slot print_timing: id 1 | task 1366 | prompt eval time = 2588.74 ms / 130 tokens ( 19.91 ms per token, 50.22 tokens per second) 13.32.830.345 I slot print_timing: id 1 | task 1366 | eval time = 78037.46 ms / 302 tokens ( 259.26 ms per token, 3.86 tokens per second) 13.32.830.346 I slot print_timing: id 1 | task 1366 | total time = 80626.20 ms / 432 tokens 13.32.830.346 I slot print_timing: id 1 | task 1366 | graphs reused = 1280 13.32.830.347 I slot print_timing: id 1 | task 1366 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.830.391 I slot release: id 1 | task 1366 | stop processing: n_tokens = 1556, truncated = 0 13.33.160.190 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.737 13.33.160.226 I slot launch_slot_: id 1 | task 1676 | processing task, is_child = 0 13.35.509.611 I slot print_timing: id 0 | task 877 | n_gen = 783, tg = 3.72 t/s, tg_3s = 2.31 t/s 13.38.418.275 I slot print_timing: id 2 | task 1585 | n_gen = 100, tg = 3.60 t/s, tg_3s = 3.64 t/s 13.38.647.980 I slot print_timing: id 0 | task 877 | n_gen = 795, tg = 3.72 t/s, tg_3s = 3.82 t/s 13.41.641.389 I slot print_timing: id 2 | task 1585 | n_gen = 114, tg = 3.68 t/s, tg_3s = 4.34 t/s 13.41.871.319 I slot print_timing: id 0 | task 877 | n_gen = 809, tg = 3.73 t/s, tg_3s = 4.34 t/s 13.44.862.507 I slot print_timing: id 2 | task 1585 | n_gen = 128, tg = 3.74 t/s, tg_3s = 4.35 t/s 13.45.092.234 I slot print_timing: id 0 | task 877 | n_gen = 823, tg = 3.74 t/s, tg_3s = 4.35 t/s 13.47.869.250 I slot print_timing: id 2 | task 1585 | n_gen = 141, tg = 3.79 t/s, tg_3s = 4.32 t/s 13.48.099.797 I slot print_timing: id 0 | task 877 | n_gen = 836, tg = 3.75 t/s, tg_3s = 4.32 t/s 13.50.872.412 I slot print_timing: id 2 | task 1585 | n_gen = 154, tg = 3.83 t/s, tg_3s = 4.33 t/s 13.51.102.993 I slot print_timing: id 0 | task 877 | n_gen = 849, tg = 3.75 t/s, tg_3s = 4.33 t/s 13.53.872.764 I slot print_timing: id 2 | task 1585 | n_gen = 167, tg = 3.86 t/s, tg_3s = 4.33 t/s 13.54.103.357 I slot print_timing: id 0 | task 877 | n_gen = 862, tg = 3.76 t/s, tg_3s = 4.33 t/s 13.56.180.913 I slot print_timing: id 3 | task 1663 | n_gen = 100, tg = 3.89 t/s, tg_3s = 3.93 t/s 13.56.873.157 I slot print_timing: id 2 | task 1585 | n_gen = 180, tg = 3.89 t/s, tg_3s = 4.33 t/s 13.57.104.669 I slot print_timing: id 0 | task 877 | n_gen = 875, tg = 3.77 t/s, tg_3s = 4.33 t/s 13.58.950.786 I slot print_timing: id 1 | task 1676 | n_gen = 100, tg = 4.34 t/s, tg_3s = 4.38 t/s 13.59.181.763 I slot print_timing: id 3 | task 1663 | n_gen = 113, tg = 3.94 t/s, tg_3s = 4.33 t/s 13.59.873.598 I slot print_timing: id 2 | task 1585 | n_gen = 193, tg = 3.92 t/s, tg_3s = 4.33 t/s 14.00.334.992 I slot print_timing: id 0 | task 877 | n_gen = 889, tg = 3.78 t/s, tg_3s = 4.33 t/s 14.02.180.905 I slot print_timing: id 1 | task 1676 | n_gen = 114, tg = 4.34 t/s, tg_3s = 4.33 t/s 14.02.411.734 I slot print_timing: id 3 | task 1663 | n_gen = 127, tg = 3.98 t/s, tg_3s = 4.33 t/s 14.03.103.942 I slot print_timing: id 2 | task 1585 | n_gen = 207, tg = 3.95 t/s, tg_3s = 4.33 t/s 14.03.565.122 I slot print_timing: id 0 | task 877 | n_gen = 903, tg = 3.78 t/s, tg_3s = 4.33 t/s 14.05.409.402 I slot print_timing: id 1 | task 1676 | n_gen = 128, tg = 4.34 t/s, tg_3s = 4.34 t/s 14.05.640.599 I slot print_timing: id 3 | task 1663 | n_gen = 141, tg = 4.01 t/s, tg_3s = 4.34 t/s 14.06.333.197 I slot print_timing: id 2 | task 1585 | n_gen = 221, tg = 3.97 t/s, tg_3s = 4.34 t/s 14.06.793.922 I slot print_timing: id 0 | task 877 | n_gen = 917, tg = 3.79 t/s, tg_3s = 4.34 t/s 14.08.416.452 I slot print_timing: id 1 | task 1676 | n_gen = 141, tg = 4.33 t/s, tg_3s = 4.32 t/s 14.08.649.063 I slot print_timing: id 3 | task 1663 | n_gen = 154, tg = 4.04 t/s, tg_3s = 4.32 t/s 14.09.344.446 I slot print_timing: id 2 | task 1585 | n_gen = 234, tg = 3.99 t/s, tg_3s = 4.32 t/s 14.09.806.358 I slot print_timing: id 0 | task 877 | n_gen = 930, tg = 3.80 t/s, tg_3s = 4.32 t/s 14.11.423.491 I slot print_timing: id 1 | task 1676 | n_gen = 154, tg = 4.33 t/s, tg_3s = 4.32 t/s 14.11.654.970 I slot print_timing: id 3 | task 1663 | n_gen = 167, tg = 4.06 t/s, tg_3s = 4.32 t/s 14.12.347.647 I slot print_timing: id 2 | task 1585 | n_gen = 247, tg = 4.00 t/s, tg_3s = 4.33 t/s 14.12.809.211 I slot print_timing: id 0 | task 877 | n_gen = 943, tg = 3.80 t/s, tg_3s = 4.33 t/s 14.14.425.649 I slot print_timing: id 1 | task 1676 | n_gen = 167, tg = 4.33 t/s, tg_3s = 4.33 t/s 14.14.656.799 I slot print_timing: id 3 | task 1663 | n_gen = 180, tg = 4.08 t/s, tg_3s = 4.33 t/s 14.15.348.927 I slot print_timing: id 2 | task 1585 | n_gen = 260, tg = 4.02 t/s, tg_3s = 4.33 t/s 14.15.810.364 I slot print_timing: id 0 | task 877 | n_gen = 956, tg = 3.81 t/s, tg_3s = 4.33 t/s 14.17.426.877 I slot print_timing: id 1 | task 1676 | n_gen = 180, tg = 4.33 t/s, tg_3s = 4.33 t/s 14.17.657.968 I slot print_timing: id 3 | task 1663 | n_gen = 193, tg = 4.09 t/s, tg_3s = 4.33 t/s 14.18.350.054 I slot print_timing: id 2 | task 1585 | n_gen = 273, tg = 4.03 t/s, tg_3s = 4.33 t/s 14.18.811.696 I slot print_timing: id 0 | task 877 | n_gen = 969, tg = 3.82 t/s, tg_3s = 4.33 t/s 14.20.428.802 I slot print_timing: id 1 | task 1676 | n_gen = 193, tg = 4.33 t/s, tg_3s = 4.33 t/s 14.20.662.337 I slot print_timing: id 3 | task 1663 | n_gen = 206, tg = 4.11 t/s, tg_3s = 4.33 t/s 14.21.356.588 I slot print_timing: id 2 | task 1585 | n_gen = 286, tg = 4.05 t/s, tg_3s = 4.32 t/s 14.21.818.366 I slot print_timing: id 0 | task 877 | n_gen = 982, tg = 3.82 t/s, tg_3s = 4.32 t/s 14.23.435.516 I slot print_timing: id 1 | task 1676 | n_gen = 206, tg = 4.33 t/s, tg_3s = 4.32 t/s 14.23.666.825 I slot print_timing: id 3 | task 1663 | n_gen = 219, tg = 4.12 t/s, tg_3s = 4.33 t/s 14.24.359.433 I slot print_timing: id 2 | task 1585 | n_gen = 299, tg = 4.06 t/s, tg_3s = 4.33 t/s 14.24.822.100 I slot print_timing: id 0 | task 877 | n_gen = 995, tg = 3.83 t/s, tg_3s = 4.33 t/s 14.26.440.545 I slot print_timing: id 1 | task 1676 | n_gen = 219, tg = 4.33 t/s, tg_3s = 4.33 t/s 14.26.672.040 I slot print_timing: id 3 | task 1663 | n_gen = 232, tg = 4.13 t/s, tg_3s = 4.33 t/s 14.27.365.073 I slot print_timing: id 2 | task 1585 | n_gen = 312, tg = 4.07 t/s, tg_3s = 4.33 t/s 14.27.828.282 I slot print_timing: id 0 | task 877 | n_gen = 1008, tg = 3.83 t/s, tg_3s = 4.32 t/s 14.29.444.378 I slot print_timing: id 1 | task 1676 | n_gen = 232, tg = 4.33 t/s, tg_3s = 4.33 t/s 14.29.675.673 I slot print_timing: id 3 | task 1663 | n_gen = 245, tg = 4.14 t/s, tg_3s = 4.33 t/s 14.30.368.473 I slot print_timing: id 2 | task 1585 | n_gen = 325, tg = 4.08 t/s, tg_3s = 4.33 t/s 14.30.829.705 I slot print_timing: id 0 | task 877 | n_gen = 1021, tg = 3.84 t/s, tg_3s = 4.33 t/s 14.31.522.114 I slot print_timing: id 0 | task 877 | prompt eval time = 2188.54 ms / 101 tokens ( 21.67 ms per token, 46.15 tokens per second) 14.31.522.120 I slot print_timing: id 0 | task 877 | eval time = 266348.33 ms / 1024 tokens ( 260.36 ms per token, 3.84 tokens per second) 14.31.522.120 I slot print_timing: id 0 | task 877 | total time = 268536.88 ms / 1125 tokens 14.31.522.121 I slot print_timing: id 0 | task 877 | graphs reused = 1518 14.31.522.121 I slot print_timing: id 0 | task 877 | graph reallocs = 0 / 0 (same size) / (changed size) 14.31.522.248 I slot release: id 0 | task 877 | stop processing: n_tokens = 2249, truncated = 0 14.31.741.427 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.510 14.31.741.466 I slot launch_slot_: id 0 | task 1920 | processing task, is_child = 0 14.33.192.064 I slot print_timing: id 1 | task 1676 | n_gen = 243, tg = 4.24 t/s, tg_3s = 2.94 t/s 14.33.192.515 I slot print_timing: id 3 | task 1663 | n_gen = 255, tg = 4.07 t/s, tg_3s = 2.84 t/s 14.33.622.104 I slot print_timing: id 2 | task 1585 | n_gen = 333, tg = 4.01 t/s, tg_3s = 2.46 t/s 14.36.382.404 I slot print_timing: id 1 | task 1676 | n_gen = 256, tg = 4.23 t/s, tg_3s = 4.07 t/s 14.36.382.693 I slot print_timing: id 3 | task 1663 | n_gen = 268, tg = 4.07 t/s, tg_3s = 4.08 t/s 14.36.842.055 I slot print_timing: id 2 | task 1585 | n_gen = 347, tg = 4.03 t/s, tg_3s = 4.35 t/s 14.39.602.159 I slot print_timing: id 1 | task 1676 | n_gen = 270, tg = 4.24 t/s, tg_3s = 4.35 t/s 14.39.602.442 I slot print_timing: id 3 | task 1663 | n_gen = 282, tg = 4.08 t/s, tg_3s = 4.35 t/s 14.40.062.069 I slot print_timing: id 2 | task 1585 | n_gen = 361, tg = 4.04 t/s, tg_3s = 4.35 t/s 14.42.822.870 I slot print_timing: id 1 | task 1676 | n_gen = 284, tg = 4.24 t/s, tg_3s = 4.35 t/s 14.42.823.171 I slot print_timing: id 3 | task 1663 | n_gen = 296, tg = 4.09 t/s, tg_3s = 4.35 t/s 14.43.283.792 I slot print_timing: id 2 | task 1585 | n_gen = 375, tg = 4.05 t/s, tg_3s = 4.35 t/s 14.46.044.814 I slot print_timing: id 1 | task 1676 | n_gen = 298, tg = 4.25 t/s, tg_3s = 4.35 t/s 14.46.045.107 I slot print_timing: id 3 | task 1663 | n_gen = 310, tg = 4.10 t/s, tg_3s = 4.35 t/s 14.46.504.932 I slot print_timing: id 2 | task 1585 | n_gen = 389, tg = 4.06 t/s, tg_3s = 4.35 t/s 14.49.266.526 I slot print_timing: id 1 | task 1676 | n_gen = 312, tg = 4.25 t/s, tg_3s = 4.35 t/s 14.49.266.808 I slot print_timing: id 3 | task 1663 | n_gen = 324, tg = 4.11 t/s, tg_3s = 4.35 t/s 14.49.727.508 I slot print_timing: id 2 | task 1585 | n_gen = 403, tg = 4.07 t/s, tg_3s = 4.34 t/s 14.52.488.180 I slot print_timing: id 1 | task 1676 | n_gen = 326, tg = 4.26 t/s, tg_3s = 4.35 t/s 14.52.488.453 I slot print_timing: id 3 | task 1663 | n_gen = 338, tg = 4.12 t/s, tg_3s = 4.35 t/s 14.52.949.479 I slot print_timing: id 2 | task 1585 | n_gen = 417, tg = 4.08 t/s, tg_3s = 4.35 t/s 14.55.709.112 I slot print_timing: id 1 | task 1676 | n_gen = 340, tg = 4.26 t/s, tg_3s = 4.35 t/s 14.55.709.390 I slot print_timing: id 3 | task 1663 | n_gen = 352, tg = 4.13 t/s, tg_3s = 4.35 t/s 14.56.169.166 I slot print_timing: id 2 | task 1585 | n_gen = 431, tg = 4.09 t/s, tg_3s = 4.35 t/s 14.56.398.955 I slot print_timing: id 0 | task 1920 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 14.58.932.332 I slot print_timing: id 1 | task 1676 | n_gen = 354, tg = 4.26 t/s, tg_3s = 4.34 t/s 14.58.932.622 I slot print_timing: id 3 | task 1663 | n_gen = 366, tg = 4.14 t/s, tg_3s = 4.34 t/s 14.59.392.548 I slot print_timing: id 2 | task 1585 | n_gen = 445, tg = 4.09 t/s, tg_3s = 4.34 t/s 14.59.622.247 I slot print_timing: id 0 | task 1920 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.34 t/s 15.02.154.594 I slot print_timing: id 1 | task 1676 | n_gen = 368, tg = 4.27 t/s, tg_3s = 4.34 t/s 15.02.154.878 I slot print_timing: id 3 | task 1663 | n_gen = 380, tg = 4.15 t/s, tg_3s = 4.34 t/s 15.02.615.114 I slot print_timing: id 2 | task 1585 | n_gen = 459, tg = 4.10 t/s, tg_3s = 4.34 t/s 15.02.845.037 I slot print_timing: id 0 | task 1920 | n_gen = 128, tg = 4.35 t/s, tg_3s = 4.34 t/s 15.03.996.286 I slot print_timing: id 3 | task 1663 | prompt eval time = 2599.62 ms / 137 tokens ( 18.98 ms per token, 52.70 tokens per second) 15.03.996.289 I slot print_timing: id 3 | task 1663 | eval time = 93239.08 ms / 388 tokens ( 240.93 ms per token, 4.15 tokens per second) 15.03.996.290 I slot print_timing: id 3 | task 1663 | total time = 95838.70 ms / 525 tokens 15.03.996.291 I slot print_timing: id 3 | task 1663 | graphs reused = 1650 15.03.996.291 I slot print_timing: id 3 | task 1663 | graph reallocs = 0 / 0 (same size) / (changed size) 15.03.996.425 I slot release: id 3 | task 1663 | stop processing: n_tokens = 1649, truncated = 0 15.04.214.760 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.695 15.04.214.792 I slot launch_slot_: id 3 | task 2056 | processing task, is_child = 0 15.05.658.339 I slot print_timing: id 1 | task 1676 | n_gen = 378, tg = 4.21 t/s, tg_3s = 2.85 t/s 15.05.658.558 I slot print_timing: id 2 | task 1585 | n_gen = 467, tg = 4.06 t/s, tg_3s = 2.63 t/s 15.06.094.476 I slot print_timing: id 0 | task 1920 | n_gen = 136, tg = 4.16 t/s, tg_3s = 2.46 t/s 15.08.857.062 I slot print_timing: id 1 | task 1676 | n_gen = 391, tg = 4.21 t/s, tg_3s = 4.06 t/s 15.08.857.215 I slot print_timing: id 2 | task 1585 | n_gen = 480, tg = 4.06 t/s, tg_3s = 4.06 t/s 15.09.316.940 I slot print_timing: id 0 | task 1920 | n_gen = 150, tg = 4.17 t/s, tg_3s = 4.34 t/s 15.12.076.423 I slot print_timing: id 1 | task 1676 | n_gen = 405, tg = 4.21 t/s, tg_3s = 4.35 t/s 15.12.076.573 I slot print_timing: id 2 | task 1585 | n_gen = 494, tg = 4.07 t/s, tg_3s = 4.35 t/s 15.12.536.007 I slot print_timing: id 0 | task 1920 | n_gen = 164, tg = 4.19 t/s, tg_3s = 4.35 t/s 15.15.296.122 I slot print_timing: id 1 | task 1676 | n_gen = 419, tg = 4.21 t/s, tg_3s = 4.35 t/s 15.15.296.270 I slot print_timing: id 2 | task 1585 | prompt eval time = 2467.66 ms / 131 tokens ( 18.84 ms per token, 53.09 tokens per second) 15.15.296.275 I slot print_timing: id 2 | task 1585 | eval time = 124380.84 ms / 508 tokens ( 245.33 ms per token, 4.08 tokens per second) 15.15.296.275 I slot print_timing: id 2 | task 1585 | total time = 126848.50 ms / 639 tokens 15.15.296.276 I slot print_timing: id 2 | task 1585 | graphs reused = 1689 15.15.296.276 I slot print_timing: id 2 | task 1585 | graph reallocs = 0 / 0 (same size) / (changed size) 15.15.296.363 I slot release: id 2 | task 1585 | stop processing: n_tokens = 1763, truncated = 0 15.15.625.263 I slot print_timing: id 0 | task 1920 | n_gen = 177, tg = 4.19 t/s, tg_3s = 4.21 t/s 15.15.625.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.650 15.15.625.589 I slot launch_slot_: id 2 | task 2100 | processing task, is_child = 0 15.17.983.096 I slot print_timing: id 0 | task 1920 | prompt eval time = 1880.35 ms / 93 tokens ( 20.22 ms per token, 49.46 tokens per second) 15.17.983.101 I slot print_timing: id 0 | task 1920 | eval time = 44361.27 ms / 180 tokens ( 247.83 ms per token, 4.04 tokens per second) 15.17.983.102 I slot print_timing: id 0 | task 1920 | total time = 46241.62 ms / 273 tokens 15.17.983.102 I slot print_timing: id 0 | task 1920 | graphs reused = 1689 15.17.983.103 I slot print_timing: id 0 | task 1920 | graph reallocs = 0 / 0 (same size) / (changed size) 15.17.983.145 I slot release: id 0 | task 1920 | stop processing: n_tokens = 1397, truncated = 0 15.18.201.299 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.820 15.18.201.328 I slot launch_slot_: id 0 | task 2105 | processing task, is_child = 0 15.19.974.180 I slot print_timing: id 1 | task 1676 | n_gen = 425, tg = 4.08 t/s, tg_3s = 1.28 t/s 15.21.090.723 I slot print_timing: id 1 | task 1676 | prompt eval time = 2955.27 ms / 153 tokens ( 19.32 ms per token, 51.77 tokens per second) 15.21.090.730 I slot print_timing: id 1 | task 1676 | eval time = 104975.21 ms / 429 tokens ( 245.27 ms per token, 4.08 tokens per second) 15.21.090.730 I slot print_timing: id 1 | task 1676 | total time = 107930.49 ms / 582 tokens 15.21.090.731 I slot print_timing: id 1 | task 1676 | graphs reused = 1692 15.21.090.731 I slot print_timing: id 1 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 15.21.090.785 I slot release: id 1 | task 1676 | stop processing: n_tokens = 1706, truncated = 0 15.21.419.162 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.672 15.21.419.202 I slot launch_slot_: id 1 | task 2112 | processing task, is_child = 0 15.25.147.801 I slot print_timing: id 3 | task 2056 | prompt eval time = 1880.19 ms / 87 tokens ( 21.61 ms per token, 46.27 tokens per second) 15.25.147.804 I slot print_timing: id 3 | task 2056 | eval time = 19052.80 ms / 59 tokens ( 328.50 ms per token, 3.04 tokens per second) 15.25.147.804 I slot print_timing: id 3 | task 2056 | total time = 20933.00 ms / 146 tokens 15.25.147.805 I slot print_timing: id 3 | task 2056 | graphs reused = 1696 15.25.147.805 I slot print_timing: id 3 | task 2056 | graph reallocs = 0 / 0 (same size) / (changed size) 15.25.147.853 I slot release: id 3 | task 2056 | stop processing: n_tokens = 1270, truncated = 0 15.25.365.858 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.902 15.25.365.887 I slot launch_slot_: id 3 | task 2121 | processing task, is_child = 0 15.46.201.877 I slot print_timing: id 2 | task 2100 | n_gen = 100, tg = 3.48 t/s, tg_3s = 3.51 t/s 15.47.120.131 I slot print_timing: id 0 | task 2105 | n_gen = 100, tg = 3.70 t/s, tg_3s = 3.74 t/s 15.47.350.062 I slot print_timing: id 2 | task 2100 | prompt eval time = 2125.68 ms / 98 tokens ( 21.69 ms per token, 46.10 tokens per second) 15.47.350.065 I slot print_timing: id 2 | task 2100 | eval time = 29598.78 ms / 105 tokens ( 284.60 ms per token, 3.51 tokens per second) 15.47.350.065 I slot print_timing: id 2 | task 2100 | total time = 31724.46 ms / 203 tokens 15.47.350.066 I slot print_timing: id 2 | task 2100 | graphs reused = 1780 15.47.350.066 I slot print_timing: id 2 | task 2100 | graph reallocs = 0 / 0 (same size) / (changed size) 15.47.350.114 I slot release: id 2 | task 2100 | stop processing: n_tokens = 1327, truncated = 0 15.47.678.613 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.864 15.47.678.650 I slot launch_slot_: id 2 | task 2211 | processing task, is_child = 0 15.50.251.461 I slot print_timing: id 0 | task 2105 | n_gen = 106, tg = 3.52 t/s, tg_3s = 1.92 t/s 15.50.251.604 I slot print_timing: id 1 | task 2112 | n_gen = 100, tg = 3.77 t/s, tg_3s = 3.81 t/s 15.52.091.061 I slot print_timing: id 3 | task 2121 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 15.53.469.394 I slot print_timing: id 0 | task 2105 | n_gen = 120, tg = 3.60 t/s, tg_3s = 4.35 t/s 15.53.469.533 I slot print_timing: id 1 | task 2112 | n_gen = 114, tg = 3.83 t/s, tg_3s = 4.35 t/s 15.55.308.513 I slot print_timing: id 3 | task 2121 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 15.56.686.702 I slot print_timing: id 0 | task 2105 | n_gen = 134, tg = 3.67 t/s, tg_3s = 4.35 t/s 15.56.686.853 I slot print_timing: id 1 | task 2112 | n_gen = 128, tg = 3.89 t/s, tg_3s = 4.35 t/s 15.58.525.379 I slot print_timing: id 3 | task 2121 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 15.59.904.366 I slot print_timing: id 0 | task 2105 | n_gen = 148, tg = 3.72 t/s, tg_3s = 4.35 t/s 15.59.904.513 I slot print_timing: id 1 | task 2112 | n_gen = 142, tg = 3.93 t/s, tg_3s = 4.35 t/s 16.01.742.079 I slot print_timing: id 3 | task 2121 | n_gen = 142, tg = 4.13 t/s, tg_3s = 4.35 t/s 16.03.119.759 I slot print_timing: id 0 | task 2105 | n_gen = 162, tg = 3.77 t/s, tg_3s = 4.35 t/s 16.03.119.908 I slot print_timing: id 1 | task 2112 | n_gen = 156, tg = 3.96 t/s, tg_3s = 4.35 t/s 16.04.728.700 I slot print_timing: id 0 | task 2105 | prompt eval time = 2196.89 ms / 105 tokens ( 20.92 ms per token, 47.79 tokens per second) 16.04.728.705 I slot print_timing: id 0 | task 2105 | eval time = 44330.48 ms / 169 tokens ( 263.87 ms per token, 3.79 tokens per second) 16.04.728.706 I slot print_timing: id 0 | task 2105 | total time = 46527.37 ms / 274 tokens 16.04.728.707 I slot print_timing: id 0 | task 2105 | graphs reused = 1844 16.04.728.707 I slot print_timing: id 0 | task 2105 | graph reallocs = 0 / 0 (same size) / (changed size) 16.04.728.753 I slot release: id 0 | task 2105 | stop processing: n_tokens = 1398, truncated = 0 16.04.946.756 I slot print_timing: id 3 | task 2121 | n_gen = 156, tg = 4.15 t/s, tg_3s = 4.37 t/s 16.04.946.761 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.820 16.04.946.793 I slot launch_slot_: id 0 | task 2280 | processing task, is_child = 0 16.06.723.237 I slot print_timing: id 1 | task 2112 | n_gen = 165, tg = 3.84 t/s, tg_3s = 2.50 t/s 16.08.066.601 I slot print_timing: id 3 | task 2121 | n_gen = 162, tg = 3.98 t/s, tg_3s = 1.92 t/s 16.09.904.171 I slot print_timing: id 1 | task 2112 | n_gen = 178, tg = 3.86 t/s, tg_3s = 4.09 t/s 16.11.284.129 I slot print_timing: id 3 | task 2121 | n_gen = 176, tg = 4.01 t/s, tg_3s = 4.35 t/s 16.12.432.140 I slot print_timing: id 3 | task 2121 | prompt eval time = 2234.84 ms / 122 tokens ( 18.32 ms per token, 54.59 tokens per second) 16.12.432.143 I slot print_timing: id 3 | task 2121 | eval time = 44831.41 ms / 181 tokens ( 249.06 ms per token, 4.02 tokens per second) 16.12.432.143 I slot print_timing: id 3 | task 2121 | total time = 47066.24 ms / 303 tokens 16.12.432.144 I slot print_timing: id 3 | task 2121 | graphs reused = 1867 16.12.432.144 I slot print_timing: id 3 | task 2121 | graph reallocs = 0 / 0 (same size) / (changed size) 16.12.432.202 I slot release: id 3 | task 2121 | stop processing: n_tokens = 1427, truncated = 0 16.12.650.560 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.803 16.12.650.592 I slot launch_slot_: id 3 | task 2307 | processing task, is_child = 0 16.14.825.047 I slot print_timing: id 1 | task 2112 | n_gen = 191, tg = 3.74 t/s, tg_3s = 2.64 t/s 16.16.410.492 I slot print_timing: id 2 | task 2211 | n_gen = 100, tg = 3.72 t/s, tg_3s = 3.76 t/s 16.18.017.650 I slot print_timing: id 1 | task 2112 | n_gen = 204, tg = 3.76 t/s, tg_3s = 4.07 t/s 16.19.626.219 I slot print_timing: id 2 | task 2211 | n_gen = 114, tg = 3.79 t/s, tg_3s = 4.35 t/s 16.21.234.485 I slot print_timing: id 1 | task 2112 | n_gen = 218, tg = 3.79 t/s, tg_3s = 4.35 t/s 16.22.841.613 I slot print_timing: id 2 | task 2211 | n_gen = 128, tg = 3.84 t/s, tg_3s = 4.35 t/s 16.23.530.534 I slot print_timing: id 1 | task 2112 | prompt eval time = 2579.04 ms / 113 tokens ( 22.82 ms per token, 43.81 tokens per second) 16.23.530.541 I slot print_timing: id 1 | task 2112 | eval time = 59532.29 ms / 228 tokens ( 262.26 ms per token, 3.81 tokens per second) 16.23.530.543 I slot print_timing: id 1 | task 2112 | total time = 62111.32 ms / 341 tokens 16.23.530.543 I slot print_timing: id 1 | task 2112 | graphs reused = 1902 16.23.530.544 I slot print_timing: id 1 | task 2112 | graph reallocs = 0 / 0 (same size) / (changed size) 16.23.530.588 I slot release: id 1 | task 2112 | stop processing: n_tokens = 1465, truncated = 0 16.23.858.269 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.782 16.23.858.320 I slot launch_slot_: id 1 | task 2347 | processing task, is_child = 0 16.25.843.977 I slot print_timing: id 2 | task 2211 | n_gen = 133, tg = 3.66 t/s, tg_3s = 1.67 t/s 16.28.980.515 I slot print_timing: id 2 | task 2211 | n_gen = 145, tg = 3.67 t/s, tg_3s = 3.83 t/s 16.32.196.860 I slot print_timing: id 2 | task 2211 | n_gen = 159, tg = 3.73 t/s, tg_3s = 4.35 t/s 16.34.263.518 I slot print_timing: id 0 | task 2280 | n_gen = 100, tg = 3.65 t/s, tg_3s = 3.69 t/s 16.35.412.861 I slot print_timing: id 2 | task 2211 | n_gen = 173, tg = 3.77 t/s, tg_3s = 4.35 t/s 16.37.481.799 I slot print_timing: id 0 | task 2280 | n_gen = 114, tg = 3.72 t/s, tg_3s = 4.35 t/s 16.38.633.456 I slot print_timing: id 2 | task 2211 | n_gen = 187, tg = 3.81 t/s, tg_3s = 4.35 t/s 16.40.239.998 I slot print_timing: id 3 | task 2307 | n_gen = 100, tg = 3.96 t/s, tg_3s = 4.00 t/s 16.40.698.972 I slot print_timing: id 0 | task 2280 | n_gen = 128, tg = 3.79 t/s, tg_3s = 4.35 t/s 16.41.848.542 I slot print_timing: id 2 | task 2211 | n_gen = 201, tg = 3.84 t/s, tg_3s = 4.35 t/s 16.43.456.763 I slot print_timing: id 3 | task 2307 | n_gen = 114, tg = 4.01 t/s, tg_3s = 4.35 t/s 16.43.915.640 I slot print_timing: id 0 | task 2280 | n_gen = 142, tg = 3.83 t/s, tg_3s = 4.35 t/s 16.45.063.935 I slot print_timing: id 2 | task 2211 | n_gen = 215, tg = 3.87 t/s, tg_3s = 4.35 t/s 16.45.293.544 I slot print_timing: id 2 | task 2211 | prompt eval time = 2111.13 ms / 96 tokens ( 21.99 ms per token, 45.47 tokens per second) 16.45.293.549 I slot print_timing: id 2 | task 2211 | eval time = 55503.76 ms / 216 tokens ( 258.16 ms per token, 3.87 tokens per second) 16.45.293.549 I slot print_timing: id 2 | task 2211 | total time = 57614.89 ms / 312 tokens 16.45.293.550 I slot print_timing: id 2 | task 2211 | graphs reused = 1983 16.45.293.550 I slot print_timing: id 2 | task 2211 | graph reallocs = 0 / 0 (same size) / (changed size) 16.45.293.599 I slot release: id 2 | task 2211 | stop processing: n_tokens = 1436, truncated = 0 16.45.622.592 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.798 16.45.622.621 I slot launch_slot_: id 2 | task 2433 | processing task, is_child = 0 16.47.525.472 I slot print_timing: id 0 | task 2280 | n_gen = 150, tg = 3.69 t/s, tg_3s = 2.22 t/s 16.47.525.837 I slot print_timing: id 3 | task 2307 | n_gen = 124, tg = 3.81 t/s, tg_3s = 2.46 t/s 16.50.600.127 I slot print_timing: id 0 | task 2280 | n_gen = 162, tg = 3.71 t/s, tg_3s = 3.90 t/s 16.50.600.551 I slot print_timing: id 3 | task 2307 | n_gen = 136, tg = 3.82 t/s, tg_3s = 3.90 t/s 16.51.289.336 I slot print_timing: id 1 | task 2347 | n_gen = 100, tg = 3.99 t/s, tg_3s = 4.03 t/s 16.53.817.661 I slot print_timing: id 0 | task 2280 | n_gen = 176, tg = 3.75 t/s, tg_3s = 4.35 t/s 16.53.818.108 I slot print_timing: id 3 | task 2307 | n_gen = 150, tg = 3.86 t/s, tg_3s = 4.35 t/s 16.54.507.032 I slot print_timing: id 1 | task 2347 | n_gen = 114, tg = 4.03 t/s, tg_3s = 4.35 t/s 16.57.033.694 I slot print_timing: id 0 | task 2280 | n_gen = 190, tg = 3.79 t/s, tg_3s = 4.35 t/s 16.57.034.105 I slot print_timing: id 3 | task 2307 | n_gen = 164, tg = 3.90 t/s, tg_3s = 4.35 t/s 16.57.723.262 I slot print_timing: id 1 | task 2347 | n_gen = 128, tg = 4.06 t/s, tg_3s = 4.35 t/s 17.00.251.026 I slot print_timing: id 0 | task 2280 | n_gen = 204, tg = 3.82 t/s, tg_3s = 4.35 t/s 17.00.251.452 I slot print_timing: id 3 | task 2307 | n_gen = 178, tg = 3.93 t/s, tg_3s = 4.35 t/s 17.00.940.377 I slot print_timing: id 1 | task 2347 | n_gen = 142, tg = 4.09 t/s, tg_3s = 4.35 t/s 17.03.468.701 I slot print_timing: id 0 | task 2280 | n_gen = 218, tg = 3.85 t/s, tg_3s = 4.35 t/s 17.03.469.126 I slot print_timing: id 3 | task 2307 | n_gen = 192, tg = 3.96 t/s, tg_3s = 4.35 t/s 17.04.158.204 I slot print_timing: id 1 | task 2347 | n_gen = 156, tg = 4.11 t/s, tg_3s = 4.35 t/s 17.06.684.685 I slot print_timing: id 0 | task 2280 | n_gen = 232, tg = 3.88 t/s, tg_3s = 4.35 t/s 17.06.685.104 I slot print_timing: id 3 | task 2307 | n_gen = 206, tg = 3.99 t/s, tg_3s = 4.35 t/s 17.07.376.020 I slot print_timing: id 1 | task 2347 | n_gen = 170, tg = 4.13 t/s, tg_3s = 4.35 t/s 17.09.903.952 I slot print_timing: id 0 | task 2280 | n_gen = 246, tg = 3.90 t/s, tg_3s = 4.35 t/s 17.09.904.356 I slot print_timing: id 3 | task 2307 | n_gen = 220, tg = 4.01 t/s, tg_3s = 4.35 t/s 17.10.594.574 I slot print_timing: id 1 | task 2347 | n_gen = 184, tg = 4.15 t/s, tg_3s = 4.35 t/s 17.10.824.555 I slot print_timing: id 2 | task 2433 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 17.13.122.956 I slot print_timing: id 0 | task 2280 | n_gen = 260, tg = 3.93 t/s, tg_3s = 4.35 t/s 17.13.123.350 I slot print_timing: id 3 | task 2307 | n_gen = 234, tg = 4.03 t/s, tg_3s = 4.35 t/s 17.13.352.845 I slot print_timing: id 0 | task 2280 | prompt eval time = 2198.69 ms / 113 tokens ( 19.46 ms per token, 51.39 tokens per second) 17.13.352.850 I slot print_timing: id 0 | task 2280 | eval time = 66207.36 ms / 261 tokens ( 254.64 ms per token, 3.93 tokens per second) 17.13.352.851 I slot print_timing: id 0 | task 2280 | total time = 68406.05 ms / 374 tokens 17.13.352.851 I slot print_timing: id 0 | task 2280 | graphs reused = 2092 17.13.352.852 I slot print_timing: id 0 | task 2280 | graph reallocs = 0 / 0 (same size) / (changed size) 17.13.354.552 I slot release: id 0 | task 2280 | stop processing: n_tokens = 1498, truncated = 0 17.13.573.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.765 17.13.573.586 I slot launch_slot_: id 0 | task 2547 | processing task, is_child = 0 17.15.362.553 I slot print_timing: id 1 | task 2347 | n_gen = 198, tg = 4.03 t/s, tg_3s = 2.94 t/s 17.15.362.701 I slot print_timing: id 2 | task 2433 | n_gen = 113, tg = 4.10 t/s, tg_3s = 2.86 t/s 17.16.246.713 I slot print_timing: id 3 | task 2307 | n_gen = 240, tg = 3.92 t/s, tg_3s = 1.92 t/s 17.18.543.264 I slot print_timing: id 1 | task 2347 | n_gen = 211, tg = 4.03 t/s, tg_3s = 4.09 t/s 17.18.543.406 I slot print_timing: id 2 | task 2433 | n_gen = 126, tg = 4.10 t/s, tg_3s = 4.09 t/s 17.19.462.705 I slot print_timing: id 3 | task 2307 | n_gen = 254, tg = 3.94 t/s, tg_3s = 4.35 t/s 17.21.762.048 I slot print_timing: id 1 | task 2347 | n_gen = 225, tg = 4.05 t/s, tg_3s = 4.35 t/s 17.21.762.203 I slot print_timing: id 2 | task 2433 | n_gen = 140, tg = 4.13 t/s, tg_3s = 4.35 t/s 17.22.681.331 I slot print_timing: id 3 | task 2307 | n_gen = 268, tg = 3.96 t/s, tg_3s = 4.35 t/s 17.24.977.825 I slot print_timing: id 1 | task 2347 | n_gen = 239, tg = 4.07 t/s, tg_3s = 4.35 t/s 17.24.977.972 I slot print_timing: id 2 | task 2433 | n_gen = 154, tg = 4.15 t/s, tg_3s = 4.35 t/s 17.25.895.492 I slot print_timing: id 3 | task 2307 | n_gen = 282, tg = 3.98 t/s, tg_3s = 4.36 t/s 17.28.193.500 I slot print_timing: id 1 | task 2347 | n_gen = 253, tg = 4.08 t/s, tg_3s = 4.35 t/s 17.28.193.638 I slot print_timing: id 2 | task 2433 | n_gen = 168, tg = 4.16 t/s, tg_3s = 4.35 t/s 17.29.113.204 I slot print_timing: id 3 | task 2307 | n_gen = 296, tg = 3.99 t/s, tg_3s = 4.35 t/s 17.31.412.074 I slot print_timing: id 1 | task 2347 | n_gen = 267, tg = 4.09 t/s, tg_3s = 4.35 t/s 17.31.412.225 I slot print_timing: id 2 | task 2433 | n_gen = 182, tg = 4.18 t/s, tg_3s = 4.35 t/s 17.32.331.751 I slot print_timing: id 3 | task 2307 | n_gen = 310, tg = 4.01 t/s, tg_3s = 4.35 t/s 17.34.632.568 I slot print_timing: id 1 | task 2347 | n_gen = 281, tg = 4.11 t/s, tg_3s = 4.35 t/s 17.34.632.721 I slot print_timing: id 2 | task 2433 | n_gen = 196, tg = 4.19 t/s, tg_3s = 4.35 t/s 17.35.551.771 I slot print_timing: id 3 | task 2307 | n_gen = 324, tg = 4.02 t/s, tg_3s = 4.35 t/s 17.37.849.122 I slot print_timing: id 1 | task 2347 | n_gen = 295, tg = 4.12 t/s, tg_3s = 4.35 t/s 17.37.849.278 I slot print_timing: id 2 | task 2433 | n_gen = 210, tg = 4.20 t/s, tg_3s = 4.35 t/s 17.38.539.942 I slot print_timing: id 0 | task 2547 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 17.38.770.088 I slot print_timing: id 3 | task 2307 | n_gen = 338, tg = 4.04 t/s, tg_3s = 4.35 t/s 17.41.069.325 I slot print_timing: id 1 | task 2347 | n_gen = 309, tg = 4.13 t/s, tg_3s = 4.35 t/s 17.41.069.470 I slot print_timing: id 2 | task 2433 | n_gen = 224, tg = 4.21 t/s, tg_3s = 4.35 t/s 17.41.758.798 I slot print_timing: id 0 | task 2547 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 17.41.988.901 I slot print_timing: id 3 | task 2307 | n_gen = 352, tg = 4.05 t/s, tg_3s = 4.35 t/s 17.44.287.682 I slot print_timing: id 1 | task 2347 | n_gen = 323, tg = 4.14 t/s, tg_3s = 4.35 t/s 17.44.287.833 I slot print_timing: id 2 | task 2433 | n_gen = 238, tg = 4.22 t/s, tg_3s = 4.35 t/s 17.44.977.147 I slot print_timing: id 0 | task 2547 | n_gen = 128, tg = 4.35 t/s, tg_3s = 4.35 t/s 17.45.207.380 I slot print_timing: id 3 | task 2307 | n_gen = 366, tg = 4.06 t/s, tg_3s = 4.35 t/s 17.45.668.201 I slot print_timing: id 3 | task 2307 | prompt eval time = 2608.34 ms / 149 tokens ( 17.51 ms per token, 57.12 tokens per second) 17.45.668.204 I slot print_timing: id 3 | task 2307 | eval time = 90409.27 ms / 368 tokens ( 246.35 ms per token, 4.06 tokens per second) 17.45.668.205 I slot print_timing: id 3 | task 2307 | total time = 93017.61 ms / 517 tokens 17.45.668.206 I slot print_timing: id 3 | task 2307 | graphs reused = 2221 17.45.668.206 I slot print_timing: id 3 | task 2307 | graph reallocs = 0 / 0 (same size) / (changed size) 17.45.669.101 I slot release: id 3 | task 2307 | stop processing: n_tokens = 1641, truncated = 0 17.45.886.270 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.698 17.45.886.302 I slot launch_slot_: id 3 | task 2681 | processing task, is_child = 0 17.48.051.168 I slot print_timing: id 0 | task 2547 | n_gen = 133, tg = 4.09 t/s, tg_3s = 1.63 t/s 17.48.051.320 I slot print_timing: id 1 | task 2347 | n_gen = 331, tg = 4.04 t/s, tg_3s = 2.13 t/s 17.48.051.480 I slot print_timing: id 2 | task 2433 | n_gen = 246, tg = 4.08 t/s, tg_3s = 2.13 t/s 17.51.247.403 I slot print_timing: id 0 | task 2547 | n_gen = 146, tg = 4.09 t/s, tg_3s = 4.07 t/s 17.51.247.544 I slot print_timing: id 1 | task 2347 | n_gen = 344, tg = 4.05 t/s, tg_3s = 4.07 t/s 17.51.247.682 I slot print_timing: id 2 | task 2433 | n_gen = 259, tg = 4.08 t/s, tg_3s = 4.07 t/s 17.54.466.229 I slot print_timing: id 0 | task 2547 | n_gen = 160, tg = 4.11 t/s, tg_3s = 4.35 t/s 17.54.466.374 I slot print_timing: id 1 | task 2347 | n_gen = 358, tg = 4.06 t/s, tg_3s = 4.35 t/s 17.54.466.518 I slot print_timing: id 2 | task 2433 | n_gen = 273, tg = 4.10 t/s, tg_3s = 4.35 t/s 17.57.684.118 I slot print_timing: id 0 | task 2547 | n_gen = 174, tg = 4.13 t/s, tg_3s = 4.35 t/s 17.57.684.269 I slot print_timing: id 1 | task 2347 | n_gen = 372, tg = 4.07 t/s, tg_3s = 4.35 t/s 17.57.684.413 I slot print_timing: id 2 | task 2433 | n_gen = 287, tg = 4.11 t/s, tg_3s = 4.35 t/s 17.58.832.953 I slot print_timing: id 2 | task 2433 | prompt eval time = 2448.05 ms / 117 tokens ( 20.92 ms per token, 47.79 tokens per second) 17.58.832.956 I slot print_timing: id 2 | task 2433 | eval time = 70762.27 ms / 292 tokens ( 243.17 ms per token, 4.11 tokens per second) 17.58.832.957 I slot print_timing: id 2 | task 2433 | total time = 73210.32 ms / 409 tokens 17.58.832.957 I slot print_timing: id 2 | task 2433 | graphs reused = 2265 17.58.832.958 I slot print_timing: id 2 | task 2433 | graph reallocs = 0 / 0 (same size) / (changed size) 17.58.834.144 I slot release: id 2 | task 2433 | stop processing: n_tokens = 1533, truncated = 0 17.59.163.483 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.748 17.59.163.514 I slot launch_slot_: id 2 | task 2730 | processing task, is_child = 0 18.00.721.866 I slot print_timing: id 0 | task 2547 | n_gen = 181, tg = 4.01 t/s, tg_3s = 2.30 t/s 18.00.722.037 I slot print_timing: id 1 | task 2347 | n_gen = 379, tg = 4.01 t/s, tg_3s = 2.30 t/s 18.03.794.047 I slot print_timing: id 0 | task 2547 | n_gen = 193, tg = 4.00 t/s, tg_3s = 3.91 t/s 18.03.794.200 I slot print_timing: id 1 | task 2347 | n_gen = 391, tg = 4.01 t/s, tg_3s = 3.91 t/s 18.04.714.662 I slot print_timing: id 1 | task 2347 | prompt eval time = 2593.29 ms / 131 tokens ( 19.80 ms per token, 50.52 tokens per second) 18.04.714.665 I slot print_timing: id 1 | task 2347 | eval time = 98263.04 ms / 395 tokens ( 249.40 ms per token, 4.01 tokens per second) 18.04.714.665 I slot print_timing: id 1 | task 2347 | total time = 100856.33 ms / 526 tokens 18.04.714.666 I slot print_timing: id 1 | task 2347 | graphs reused = 2279 18.04.714.666 I slot print_timing: id 1 | task 2347 | graph reallocs = 0 / 0 (same size) / (changed size) 18.04.714.718 I slot release: id 1 | task 2347 | stop processing: n_tokens = 1650, truncated = 0 18.05.044.371 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.695 18.05.044.402 I slot launch_slot_: id 1 | task 2749 | processing task, is_child = 0 18.06.994.592 I slot print_timing: id 0 | task 2547 | n_gen = 199, tg = 3.87 t/s, tg_3s = 1.87 t/s 18.10.131.191 I slot print_timing: id 0 | task 2547 | n_gen = 211, tg = 3.86 t/s, tg_3s = 3.83 t/s 18.13.347.141 I slot print_timing: id 0 | task 2547 | n_gen = 225, tg = 3.89 t/s, tg_3s = 4.35 t/s 18.15.184.102 I slot print_timing: id 3 | task 2681 | n_gen = 100, tg = 3.71 t/s, tg_3s = 3.75 t/s 18.16.561.599 I slot print_timing: id 0 | task 2547 | n_gen = 239, tg = 3.92 t/s, tg_3s = 4.36 t/s 18.18.398.901 I slot print_timing: id 3 | task 2681 | n_gen = 114, tg = 3.78 t/s, tg_3s = 4.35 t/s 18.19.775.177 I slot print_timing: id 0 | task 2547 | n_gen = 253, tg = 3.94 t/s, tg_3s = 4.36 t/s 18.21.613.108 I slot print_timing: id 3 | task 2681 | n_gen = 128, tg = 3.83 t/s, tg_3s = 4.36 t/s 18.22.992.653 I slot print_timing: id 0 | task 2547 | n_gen = 267, tg = 3.96 t/s, tg_3s = 4.35 t/s 18.24.830.362 I slot print_timing: id 3 | task 2681 | n_gen = 142, tg = 3.88 t/s, tg_3s = 4.35 t/s 18.26.207.011 I slot print_timing: id 0 | task 2547 | n_gen = 281, tg = 3.98 t/s, tg_3s = 4.36 t/s 18.26.207.301 I slot print_timing: id 2 | task 2730 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 18.28.047.513 I slot print_timing: id 3 | task 2681 | n_gen = 156, tg = 3.92 t/s, tg_3s = 4.35 t/s 18.28.506.682 I slot print_timing: id 1 | task 2749 | prompt eval time = 2555.98 ms / 104 tokens ( 24.58 ms per token, 40.69 tokens per second) 18.28.506.686 I slot print_timing: id 1 | task 2749 | eval time = 20906.29 ms / 92 tokens ( 229.74 ms per token, 4.35 tokens per second) 18.28.506.687 I slot print_timing: id 1 | task 2749 | total time = 23462.27 ms / 196 tokens 18.28.506.687 I slot print_timing: id 1 | task 2749 | graphs reused = 2368 18.28.506.688 I slot print_timing: id 1 | task 2749 | graph reallocs = 0 / 0 (same size) / (changed size) 18.28.506.736 I slot release: id 1 | task 2749 | stop processing: n_tokens = 1320, truncated = 0 18.28.835.751 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.868 18.28.835.793 I slot launch_slot_: id 1 | task 2844 | processing task, is_child = 0 18.30.458.055 I slot print_timing: id 0 | task 2547 | n_gen = 293, tg = 3.91 t/s, tg_3s = 2.82 t/s 18.30.458.219 I slot print_timing: id 2 | task 2730 | n_gen = 112, tg = 3.80 t/s, tg_3s = 2.82 t/s 18.31.063.822 I slot print_timing: id 3 | task 2681 | n_gen = 161, tg = 3.76 t/s, tg_3s = 1.66 t/s 18.33.592.130 I slot print_timing: id 0 | task 2547 | n_gen = 305, tg = 3.91 t/s, tg_3s = 3.83 t/s 18.33.592.423 I slot print_timing: id 2 | task 2730 | n_gen = 124, tg = 3.80 t/s, tg_3s = 3.83 t/s 18.34.051.151 I slot print_timing: id 0 | task 2547 | prompt eval time = 2210.60 ms / 127 tokens ( 17.41 ms per token, 57.45 tokens per second) 18.34.051.157 I slot print_timing: id 0 | task 2547 | eval time = 78266.96 ms / 307 tokens ( 255.77 ms per token, 3.91 tokens per second) 18.34.051.157 I slot print_timing: id 0 | task 2547 | total time = 80477.56 ms / 434 tokens 18.34.051.158 I slot print_timing: id 0 | task 2547 | graphs reused = 2380 18.34.051.158 I slot print_timing: id 0 | task 2547 | graph reallocs = 0 / 0 (same size) / (changed size) 18.34.051.204 I slot release: id 0 | task 2547 | stop processing: n_tokens = 1558, truncated = 0 18.34.269.417 I slot print_timing: id 3 | task 2681 | n_gen = 175, tg = 3.80 t/s, tg_3s = 4.37 t/s 18.34.269.422 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.736 18.34.269.449 I slot launch_slot_: id 0 | task 2861 | processing task, is_child = 0 18.36.688.408 I slot print_timing: id 2 | task 2730 | n_gen = 130, tg = 3.64 t/s, tg_3s = 1.94 t/s 18.37.376.424 I slot print_timing: id 3 | task 2681 | n_gen = 181, tg = 3.68 t/s, tg_3s = 1.93 t/s 18.39.902.114 I slot print_timing: id 2 | task 2730 | n_gen = 144, tg = 3.70 t/s, tg_3s = 4.36 t/s 18.40.591.152 I slot print_timing: id 3 | task 2681 | n_gen = 195, tg = 3.72 t/s, tg_3s = 4.35 t/s 18.43.116.254 I slot print_timing: id 2 | task 2730 | n_gen = 158, tg = 3.75 t/s, tg_3s = 4.36 t/s 18.43.804.936 I slot print_timing: id 3 | task 2681 | n_gen = 209, tg = 3.76 t/s, tg_3s = 4.36 t/s 18.46.332.064 I slot print_timing: id 2 | task 2730 | n_gen = 172, tg = 3.79 t/s, tg_3s = 4.35 t/s 18.47.019.486 I slot print_timing: id 3 | task 2681 | n_gen = 223, tg = 3.79 t/s, tg_3s = 4.36 t/s 18.49.545.288 I slot print_timing: id 2 | task 2730 | n_gen = 186, tg = 3.83 t/s, tg_3s = 4.36 t/s 18.50.234.590 I slot print_timing: id 3 | task 2681 | n_gen = 237, tg = 3.82 t/s, tg_3s = 4.35 t/s 18.52.301.240 I slot print_timing: id 2 | task 2730 | prompt eval time = 2100.62 ms / 96 tokens ( 21.88 ms per token, 45.70 tokens per second) 18.52.301.245 I slot print_timing: id 2 | task 2730 | eval time = 51037.09 ms / 198 tokens ( 259.07 ms per token, 3.86 tokens per second) 18.52.301.245 I slot print_timing: id 2 | task 2730 | total time = 53137.72 ms / 294 tokens 18.52.301.246 I slot print_timing: id 2 | task 2730 | graphs reused = 2449 18.52.301.246 I slot print_timing: id 2 | task 2730 | graph reallocs = 0 / 0 (same size) / (changed size) 18.52.301.290 I slot release: id 2 | task 2730 | stop processing: n_tokens = 1418, truncated = 0 18.52.629.791 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.808 18.52.629.822 I slot launch_slot_: id 2 | task 2934 | processing task, is_child = 0 18.54.523.328 I slot print_timing: id 3 | task 2681 | n_gen = 248, tg = 3.74 t/s, tg_3s = 2.56 t/s 18.55.299.595 I slot print_timing: id 0 | task 2861 | prompt eval time = 2185.58 ms / 102 tokens ( 21.43 ms per token, 46.67 tokens per second) 18.55.299.601 I slot print_timing: id 0 | task 2861 | eval time = 18844.56 ms / 74 tokens ( 258.14 ms per token, 3.87 tokens per second) 18.55.299.602 I slot print_timing: id 0 | task 2861 | total time = 21030.14 ms / 176 tokens 18.55.299.602 I slot print_timing: id 0 | task 2861 | graphs reused = 2449 18.55.299.603 I slot print_timing: id 0 | task 2861 | graph reallocs = 0 / 0 (same size) / (changed size) 18.55.299.644 I slot release: id 0 | task 2861 | stop processing: n_tokens = 1300, truncated = 0 18.55.517.796 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 18.55.517.822 I slot launch_slot_: id 0 | task 2939 | processing task, is_child = 0 18.57.722.332 I slot print_timing: id 3 | task 2681 | n_gen = 253, tg = 3.64 t/s, tg_3s = 1.56 t/s 18.57.953.341 I slot print_timing: id 1 | task 2844 | prompt eval time = 2227.74 ms / 98 tokens ( 22.73 ms per token, 43.99 tokens per second) 18.57.953.346 I slot print_timing: id 1 | task 2844 | eval time = 26889.80 ms / 94 tokens ( 289.14 ms per token, 3.46 tokens per second) 18.57.953.346 I slot print_timing: id 1 | task 2844 | total time = 29117.54 ms / 192 tokens 18.57.953.347 I slot print_timing: id 1 | task 2844 | graphs reused = 2450 18.57.953.347 I slot print_timing: id 1 | task 2844 | graph reallocs = 0 / 0 (same size) / (changed size) 18.57.953.396 I slot release: id 1 | task 2844 | stop processing: n_tokens = 1316, truncated = 0 18.58.282.522 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.871 18.58.282.549 I slot launch_slot_: id 1 | task 2944 | processing task, is_child = 0 19.00.857.177 I slot print_timing: id 3 | task 2681 | n_gen = 257, tg = 3.54 t/s, tg_3s = 1.28 t/s 19.04.075.906 I slot print_timing: id 3 | task 2681 | n_gen = 271, tg = 3.57 t/s, tg_3s = 4.35 t/s 19.07.292.001 I slot print_timing: id 3 | task 2681 | n_gen = 285, tg = 3.60 t/s, tg_3s = 4.35 t/s 19.10.504.941 I slot print_timing: id 3 | task 2681 | n_gen = 299, tg = 3.63 t/s, tg_3s = 4.36 t/s 19.13.723.981 I slot print_timing: id 3 | task 2681 | n_gen = 313, tg = 3.66 t/s, tg_3s = 4.35 t/s 19.16.940.267 I slot print_timing: id 3 | task 2681 | n_gen = 327, tg = 3.69 t/s, tg_3s = 4.35 t/s 19.19.236.932 I slot print_timing: id 3 | task 2681 | prompt eval time = 2600.53 ms / 137 tokens ( 18.98 ms per token, 52.68 tokens per second) 19.19.236.934 I slot print_timing: id 3 | task 2681 | eval time = 90750.09 ms / 337 tokens ( 270.09 ms per token, 3.70 tokens per second) 19.19.236.935 I slot print_timing: id 3 | task 2681 | total time = 93350.62 ms / 474 tokens 19.19.236.936 I slot print_timing: id 3 | task 2681 | graphs reused = 2528 19.19.236.936 I slot print_timing: id 3 | task 2681 | graph reallocs = 0 / 0 (same size) / (changed size) 19.19.236.980 I slot release: id 3 | task 2681 | stop processing: n_tokens = 1598, truncated = 0 19.19.454.962 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.717 19.19.454.999 I slot launch_slot_: id 3 | task 3028 | processing task, is_child = 0 19.23.514.370 I slot print_timing: id 2 | task 2934 | n_gen = 100, tg = 3.48 t/s, tg_3s = 3.52 t/s 19.24.202.650 I slot print_timing: id 1 | task 2944 | prompt eval time = 2574.33 ms / 124 tokens ( 20.76 ms per token, 48.17 tokens per second) 19.24.202.656 I slot print_timing: id 1 | task 2944 | eval time = 23345.76 ms / 95 tokens ( 248.36 ms per token, 4.03 tokens per second) 19.24.202.656 I slot print_timing: id 1 | task 2944 | total time = 25920.09 ms / 219 tokens 19.24.202.657 I slot print_timing: id 1 | task 2944 | graphs reused = 2538 19.24.202.657 I slot print_timing: id 1 | task 2944 | graph reallocs = 0 / 0 (same size) / (changed size) 19.24.202.705 I slot release: id 1 | task 2944 | stop processing: n_tokens = 1343, truncated = 0 19.24.531.824 I slot print_timing: id 0 | task 2939 | n_gen = 100, tg = 3.69 t/s, tg_3s = 3.73 t/s 19.24.532.115 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.853 19.24.532.152 I slot launch_slot_: id 1 | task 3043 | processing task, is_child = 0 19.26.749.477 I slot print_timing: id 2 | task 2934 | n_gen = 106, tg = 3.31 t/s, tg_3s = 1.85 t/s 19.27.210.741 I slot print_timing: id 2 | task 2934 | prompt eval time = 2436.95 ms / 108 tokens ( 22.56 ms per token, 44.32 tokens per second) 19.27.210.748 I slot print_timing: id 2 | task 2934 | eval time = 32143.97 ms / 108 tokens ( 300.41 ms per token, 3.33 tokens per second) 19.27.210.748 I slot print_timing: id 2 | task 2934 | total time = 34580.91 ms / 216 tokens 19.27.210.749 I slot print_timing: id 2 | task 2934 | graphs reused = 2539 19.27.210.749 I slot print_timing: id 2 | task 2934 | graph reallocs = 0 / 0 (same size) / (changed size) 19.27.210.796 I slot release: id 2 | task 2934 | stop processing: n_tokens = 1340, truncated = 0 19.27.538.795 I slot print_timing: id 0 | task 2939 | n_gen = 105, tg = 3.49 t/s, tg_3s = 1.66 t/s 19.27.539.082 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.855 19.27.539.112 I slot launch_slot_: id 2 | task 3049 | processing task, is_child = 0 19.30.668.930 I slot print_timing: id 0 | task 2939 | prompt eval time = 2204.09 ms / 122 tokens ( 18.07 ms per token, 55.35 tokens per second) 19.30.668.935 I slot print_timing: id 0 | task 2939 | eval time = 32947.00 ms / 110 tokens ( 302.27 ms per token, 3.31 tokens per second) 19.30.668.935 I slot print_timing: id 0 | task 2939 | total time = 35151.10 ms / 232 tokens 19.30.668.936 I slot print_timing: id 0 | task 2939 | graphs reused = 2541 19.30.668.936 I slot print_timing: id 0 | task 2939 | graph reallocs = 0 / 0 (same size) / (changed size) 19.30.668.982 I slot release: id 0 | task 2939 | stop processing: n_tokens = 1356, truncated = 0 19.30.887.040 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.845 19.30.887.076 I slot launch_slot_: id 0 | task 3056 | processing task, is_child = 0 19.49.739.366 I slot print_timing: id 3 | task 3028 | n_gen = 100, tg = 3.53 t/s, tg_3s = 3.56 t/s 19.52.953.204 I slot print_timing: id 1 | task 3043 | n_gen = 100, tg = 3.78 t/s, tg_3s = 3.82 t/s 19.52.953.506 I slot print_timing: id 3 | task 3028 | n_gen = 114, tg = 3.61 t/s, tg_3s = 4.36 t/s 19.54.101.890 I slot print_timing: id 2 | task 3049 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.15 t/s 19.55.480.882 I slot print_timing: id 0 | task 3056 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 19.56.169.115 I slot print_timing: id 1 | task 3043 | n_gen = 114, tg = 3.84 t/s, tg_3s = 4.35 t/s 19.56.169.430 I slot print_timing: id 3 | task 3028 | n_gen = 128, tg = 3.68 t/s, tg_3s = 4.35 t/s 19.57.317.314 I slot print_timing: id 2 | task 3049 | n_gen = 114, tg = 4.13 t/s, tg_3s = 4.35 t/s 19.57.776.497 I slot print_timing: id 1 | task 3043 | prompt eval time = 2217.18 ms / 86 tokens ( 25.78 ms per token, 38.79 tokens per second) 19.57.776.503 I slot print_timing: id 1 | task 3043 | eval time = 31027.16 ms / 121 tokens ( 258.56 ms per token, 3.87 tokens per second) 19.57.776.503 I slot print_timing: id 1 | task 3043 | total time = 33244.34 ms / 207 tokens 19.57.776.504 I slot print_timing: id 1 | task 3043 | graphs reused = 2649 19.57.776.504 I slot print_timing: id 1 | task 3043 | graph reallocs = 0 / 0 (same size) / (changed size) 19.57.776.548 I slot release: id 1 | task 3043 | stop processing: n_tokens = 1331, truncated = 0 19.58.105.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.861 19.58.105.845 I slot launch_slot_: id 1 | task 3169 | processing task, is_child = 0 19.59.723.615 I slot print_timing: id 0 | task 3056 | n_gen = 112, tg = 4.11 t/s, tg_3s = 2.83 t/s 19.59.723.905 I slot print_timing: id 3 | task 3028 | n_gen = 137, tg = 3.57 t/s, tg_3s = 2.53 t/s 20.00.328.204 I slot print_timing: id 2 | task 3049 | n_gen = 119, tg = 3.89 t/s, tg_3s = 1.66 t/s 20.02.167.539 I slot print_timing: id 3 | task 3028 | prompt eval time = 2219.35 ms / 111 tokens ( 19.99 ms per token, 50.01 tokens per second) 20.02.167.545 I slot print_timing: id 3 | task 3028 | eval time = 40493.18 ms / 146 tokens ( 279.26 ms per token, 3.58 tokens per second) 20.02.167.545 I slot print_timing: id 3 | task 3028 | total time = 42712.53 ms / 257 tokens 20.02.167.546 I slot print_timing: id 3 | task 3028 | graphs reused = 2656 20.02.167.546 I slot print_timing: id 3 | task 3028 | graph reallocs = 0 / 0 (same size) / (changed size) 20.02.167.592 I slot release: id 3 | task 3028 | stop processing: n_tokens = 1381, truncated = 0 20.02.385.312 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.830 20.02.385.340 I slot launch_slot_: id 3 | task 3181 | processing task, is_child = 0 20.04.184.683 I slot print_timing: id 0 | task 3056 | n_gen = 123, tg = 3.88 t/s, tg_3s = 2.47 t/s 20.04.184.989 I slot print_timing: id 2 | task 3049 | n_gen = 129, tg = 3.74 t/s, tg_3s = 2.59 t/s 20.05.768.481 I slot print_timing: id 0 | task 3056 | prompt eval time = 1860.56 ms / 98 tokens ( 18.99 ms per token, 52.67 tokens per second) 20.05.768.486 I slot print_timing: id 0 | task 3056 | eval time = 33020.83 ms / 129 tokens ( 257.98 ms per token, 3.88 tokens per second) 20.05.768.487 I slot print_timing: id 0 | task 3056 | total time = 34881.39 ms / 227 tokens 20.05.768.487 I slot print_timing: id 0 | task 3056 | graphs reused = 2660 20.05.768.488 I slot print_timing: id 0 | task 3056 | graph reallocs = 0 / 0 (same size) / (changed size) 20.05.768.535 I slot release: id 0 | task 3056 | stop processing: n_tokens = 1351, truncated = 0 20.05.986.676 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.848 20.05.986.708 I slot launch_slot_: id 0 | task 3190 | processing task, is_child = 0 20.07.750.373 I slot print_timing: id 2 | task 3049 | n_gen = 137, tg = 3.60 t/s, tg_3s = 2.24 t/s 20.10.928.463 I slot print_timing: id 2 | task 3049 | n_gen = 150, tg = 3.64 t/s, tg_3s = 4.09 t/s 20.14.142.214 I slot print_timing: id 2 | task 3049 | n_gen = 164, tg = 3.69 t/s, tg_3s = 4.36 t/s 20.17.356.634 I slot print_timing: id 2 | task 3049 | n_gen = 178, tg = 3.74 t/s, tg_3s = 4.36 t/s 20.20.571.039 I slot print_timing: id 2 | task 3049 | n_gen = 192, tg = 3.78 t/s, tg_3s = 4.36 t/s 20.22.638.486 I slot print_timing: id 3 | task 3181 | prompt eval time = 2233.42 ms / 121 tokens ( 18.46 ms per token, 54.18 tokens per second) 20.22.638.491 I slot print_timing: id 3 | task 3181 | eval time = 18019.72 ms / 72 tokens ( 253.80 ms per token, 3.94 tokens per second) 20.22.638.492 I slot print_timing: id 3 | task 3181 | total time = 20253.14 ms / 193 tokens 20.22.638.492 I slot print_timing: id 3 | task 3181 | graphs reused = 2723 20.22.638.493 I slot print_timing: id 3 | task 3181 | graph reallocs = 0 / 0 (same size) / (changed size) 20.22.639.783 I slot release: id 3 | task 3181 | stop processing: n_tokens = 1317, truncated = 0 20.22.857.700 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.870 20.22.857.728 I slot launch_slot_: id 3 | task 3257 | processing task, is_child = 0 20.24.308.161 I slot print_timing: id 2 | task 3049 | n_gen = 203, tg = 3.72 t/s, tg_3s = 2.94 t/s 20.25.664.331 I slot print_timing: id 2 | task 3049 | prompt eval time = 2438.56 ms / 106 tokens ( 23.01 ms per token, 43.47 tokens per second) 20.25.664.336 I slot print_timing: id 2 | task 3049 | eval time = 55686.65 ms / 208 tokens ( 269.02 ms per token, 3.72 tokens per second) 20.25.664.336 I slot print_timing: id 2 | task 3049 | total time = 58125.21 ms / 314 tokens 20.25.664.337 I slot print_timing: id 2 | task 3049 | graphs reused = 2726 20.25.664.337 I slot print_timing: id 2 | task 3049 | graph reallocs = 0 / 0 (same size) / (changed size) 20.25.664.394 I slot release: id 2 | task 3049 | stop processing: n_tokens = 1438, truncated = 0 20.25.993.097 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.797 20.25.993.137 I slot launch_slot_: id 2 | task 3265 | processing task, is_child = 0 20.30.426.206 I slot print_timing: id 1 | task 3169 | n_gen = 100, tg = 3.29 t/s, tg_3s = 3.32 t/s 20.31.344.083 I slot print_timing: id 0 | task 3190 | prompt eval time = 2184.99 ms / 105 tokens ( 20.81 ms per token, 48.06 tokens per second) 20.31.344.088 I slot print_timing: id 0 | task 3190 | eval time = 23172.38 ms / 85 tokens ( 275.86 ms per token, 3.63 tokens per second) 20.31.344.088 I slot print_timing: id 0 | task 3190 | total time = 25357.37 ms / 190 tokens 20.31.344.089 I slot print_timing: id 0 | task 3190 | graphs reused = 2736 20.31.344.089 I slot print_timing: id 0 | task 3190 | graph reallocs = 0 / 0 (same size) / (changed size) 20.31.344.150 I slot release: id 0 | task 3190 | stop processing: n_tokens = 1314, truncated = 0 20.31.562.563 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.872 20.31.562.596 I slot launch_slot_: id 0 | task 3280 | processing task, is_child = 0 20.33.755.103 I slot print_timing: id 1 | task 3169 | n_gen = 107, tg = 3.17 t/s, tg_3s = 2.10 t/s 20.33.987.044 I slot print_timing: id 1 | task 3169 | prompt eval time = 2222.21 ms / 91 tokens ( 24.42 ms per token, 40.95 tokens per second) 20.33.987.050 I slot print_timing: id 1 | task 3169 | eval time = 33658.98 ms / 108 tokens ( 314.57 ms per token, 3.18 tokens per second) 20.33.987.050 I slot print_timing: id 1 | task 3169 | total time = 35881.19 ms / 199 tokens 20.33.987.051 I slot print_timing: id 1 | task 3169 | graphs reused = 2737 20.33.987.051 I slot print_timing: id 1 | task 3169 | graph reallocs = 0 / 0 (same size) / (changed size) 20.33.987.099 I slot release: id 1 | task 3169 | stop processing: n_tokens = 1323, truncated = 0 20.34.315.180 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.866 20.34.315.220 I slot launch_slot_: id 1 | task 3285 | processing task, is_child = 0 20.54.039.760 I slot print_timing: id 3 | task 3257 | prompt eval time = 1885.18 ms / 95 tokens ( 19.84 ms per token, 50.39 tokens per second) 20.54.039.765 I slot print_timing: id 3 | task 3257 | eval time = 29296.84 ms / 99 tokens ( 298.95 ms per token, 3.35 tokens per second) 20.54.039.766 I slot print_timing: id 3 | task 3257 | total time = 31182.03 ms / 194 tokens 20.54.039.766 I slot print_timing: id 3 | task 3257 | graphs reused = 2809 20.54.039.767 I slot print_timing: id 3 | task 3257 | graph reallocs = 0 / 0 (same size) / (changed size) 20.54.039.815 I slot release: id 3 | task 3257 | stop processing: n_tokens = 1318, truncated = 0 20.54.258.259 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.869 20.54.258.294 I slot launch_slot_: id 3 | task 3362 | processing task, is_child = 0 20.57.637.008 I slot print_timing: id 2 | task 3265 | n_gen = 100, tg = 3.44 t/s, tg_3s = 3.47 t/s 21.00.854.915 I slot print_timing: id 0 | task 3280 | n_gen = 100, tg = 3.65 t/s, tg_3s = 3.69 t/s 21.00.855.195 I slot print_timing: id 2 | task 3265 | n_gen = 114, tg = 3.53 t/s, tg_3s = 4.35 t/s 21.01.773.508 I slot print_timing: id 1 | task 3285 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 21.04.071.775 I slot print_timing: id 0 | task 3280 | n_gen = 114, tg = 3.73 t/s, tg_3s = 4.35 t/s 21.04.072.067 I slot print_timing: id 2 | task 3265 | n_gen = 128, tg = 3.60 t/s, tg_3s = 4.35 t/s 21.04.990.394 I slot print_timing: id 1 | task 3285 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 21.07.286.937 I slot print_timing: id 0 | task 3280 | n_gen = 128, tg = 3.79 t/s, tg_3s = 4.35 t/s 21.07.287.219 I slot print_timing: id 2 | task 3265 | n_gen = 142, tg = 3.67 t/s, tg_3s = 4.35 t/s 21.08.206.169 I slot print_timing: id 1 | task 3285 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 21.10.502.537 I slot print_timing: id 0 | task 3280 | n_gen = 142, tg = 3.84 t/s, tg_3s = 4.35 t/s 21.10.502.818 I slot print_timing: id 2 | task 3265 | n_gen = 156, tg = 3.72 t/s, tg_3s = 4.35 t/s 21.11.421.647 I slot print_timing: id 1 | task 3285 | n_gen = 142, tg = 4.13 t/s, tg_3s = 4.35 t/s 21.13.488.582 I slot print_timing: id 0 | task 3280 | prompt eval time = 2192.36 ms / 110 tokens ( 19.93 ms per token, 50.17 tokens per second) 21.13.488.587 I slot print_timing: id 0 | task 3280 | eval time = 39733.62 ms / 155 tokens ( 258.01 ms per token, 3.88 tokens per second) 21.13.488.588 I slot print_timing: id 0 | task 3280 | total time = 41925.98 ms / 265 tokens 21.13.488.588 I slot print_timing: id 0 | task 3280 | graphs reused = 2882 21.13.488.589 I slot print_timing: id 0 | task 3280 | graph reallocs = 0 / 0 (same size) / (changed size) 21.13.488.641 I slot release: id 0 | task 3280 | stop processing: n_tokens = 1389, truncated = 0 21.13.706.996 I slot print_timing: id 2 | task 3265 | n_gen = 170, tg = 3.76 t/s, tg_3s = 4.37 t/s 21.13.707.147 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.825 21.13.707.176 I slot launch_slot_: id 0 | task 3440 | processing task, is_child = 0 21.15.496.925 I slot print_timing: id 1 | task 3285 | n_gen = 153, tg = 3.98 t/s, tg_3s = 2.70 t/s 21.16.840.705 I slot print_timing: id 2 | task 3265 | n_gen = 176, tg = 3.64 t/s, tg_3s = 1.91 t/s 21.18.677.888 I slot print_timing: id 1 | task 3285 | n_gen = 166, tg = 3.99 t/s, tg_3s = 4.09 t/s 21.20.055.993 I slot print_timing: id 2 | task 3265 | n_gen = 190, tg = 3.69 t/s, tg_3s = 4.35 t/s 21.20.974.783 I slot print_timing: id 3 | task 3362 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 21.21.893.257 I slot print_timing: id 1 | task 3285 | n_gen = 180, tg = 4.01 t/s, tg_3s = 4.35 t/s 21.23.272.591 I slot print_timing: id 2 | task 3265 | n_gen = 204, tg = 3.73 t/s, tg_3s = 4.35 t/s 21.24.191.309 I slot print_timing: id 3 | task 3362 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 21.25.109.697 I slot print_timing: id 1 | task 3285 | n_gen = 194, tg = 4.03 t/s, tg_3s = 4.35 t/s 21.26.488.088 I slot print_timing: id 2 | task 3265 | n_gen = 218, tg = 3.76 t/s, tg_3s = 4.35 t/s 21.27.406.650 I slot print_timing: id 3 | task 3362 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 21.28.325.391 I slot print_timing: id 1 | task 3285 | n_gen = 208, tg = 4.05 t/s, tg_3s = 4.35 t/s 21.29.705.421 I slot print_timing: id 2 | task 3265 | n_gen = 232, tg = 3.79 t/s, tg_3s = 4.35 t/s 21.30.626.788 I slot print_timing: id 3 | task 3362 | n_gen = 142, tg = 4.13 t/s, tg_3s = 4.35 t/s 21.31.545.765 I slot print_timing: id 1 | task 3285 | n_gen = 222, tg = 4.07 t/s, tg_3s = 4.35 t/s 21.32.924.906 I slot print_timing: id 2 | task 3265 | n_gen = 246, tg = 3.82 t/s, tg_3s = 4.35 t/s 21.33.844.513 I slot print_timing: id 3 | task 3362 | n_gen = 156, tg = 4.15 t/s, tg_3s = 4.35 t/s 21.34.763.758 I slot print_timing: id 1 | task 3285 | n_gen = 236, tg = 4.09 t/s, tg_3s = 4.35 t/s 21.36.143.189 I slot print_timing: id 2 | task 3265 | n_gen = 260, tg = 3.85 t/s, tg_3s = 4.35 t/s 21.37.062.464 I slot print_timing: id 3 | task 3362 | n_gen = 170, tg = 4.17 t/s, tg_3s = 4.35 t/s 21.37.981.979 I slot print_timing: id 1 | task 3285 | n_gen = 250, tg = 4.10 t/s, tg_3s = 4.35 t/s 21.38.674.112 I slot print_timing: id 0 | task 3440 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 21.39.364.095 I slot print_timing: id 2 | task 3265 | n_gen = 274, tg = 3.87 t/s, tg_3s = 4.35 t/s 21.40.283.546 I slot print_timing: id 3 | task 3362 | n_gen = 184, tg = 4.18 t/s, tg_3s = 4.35 t/s 21.41.202.598 I slot print_timing: id 1 | task 3285 | n_gen = 264, tg = 4.11 t/s, tg_3s = 4.35 t/s 21.41.892.155 I slot print_timing: id 0 | task 3440 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 21.42.122.253 I slot print_timing: id 2 | task 3265 | prompt eval time = 2824.52 ms / 144 tokens ( 19.61 ms per token, 50.98 tokens per second) 21.42.122.256 I slot print_timing: id 2 | task 3265 | eval time = 73304.59 ms / 286 tokens ( 257.21 ms per token, 3.89 tokens per second) 21.42.122.256 I slot print_timing: id 2 | task 3265 | total time = 76129.11 ms / 430 tokens 21.42.122.257 I slot print_timing: id 2 | task 3265 | graphs reused = 2995 21.42.122.257 I slot print_timing: id 2 | task 3265 | graph reallocs = 0 / 0 (same size) / (changed size) 21.42.122.303 I slot release: id 2 | task 3265 | stop processing: n_tokens = 1554, truncated = 0 21.42.450.696 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.737 21.42.450.734 I slot launch_slot_: id 2 | task 3558 | processing task, is_child = 0 21.43.998.011 I slot print_timing: id 3 | task 3362 | n_gen = 194, tg = 4.06 t/s, tg_3s = 2.69 t/s 21.44.542.730 I slot print_timing: id 1 | task 3285 | n_gen = 271, tg = 4.01 t/s, tg_3s = 2.10 t/s 21.44.775.443 I slot print_timing: id 3 | task 3362 | prompt eval time = 2228.11 ms / 115 tokens ( 19.37 ms per token, 51.61 tokens per second) 21.44.775.449 I slot print_timing: id 3 | task 3362 | eval time = 48289.04 ms / 196 tokens ( 247.64 ms per token, 4.04 tokens per second) 21.44.775.450 I slot print_timing: id 3 | task 3362 | total time = 50517.14 ms / 311 tokens 21.44.775.450 I slot print_timing: id 3 | task 3362 | graphs reused = 2995 21.44.775.451 I slot print_timing: id 3 | task 3362 | graph reallocs = 0 / 0 (same size) / (changed size) 21.44.776.593 I slot release: id 3 | task 3362 | stop processing: n_tokens = 1435, truncated = 0 21.44.994.544 I slot print_timing: id 0 | task 3440 | n_gen = 120, tg = 4.09 t/s, tg_3s = 1.93 t/s 21.44.994.837 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.799 21.44.994.871 I slot launch_slot_: id 3 | task 3563 | processing task, is_child = 0 21.47.674.767 I slot print_timing: id 1 | task 3285 | n_gen = 277, tg = 3.92 t/s, tg_3s = 1.92 t/s 21.48.134.180 I slot print_timing: id 0 | task 3440 | n_gen = 126, tg = 3.88 t/s, tg_3s = 1.91 t/s 21.50.891.046 I slot print_timing: id 1 | task 3285 | n_gen = 291, tg = 3.94 t/s, tg_3s = 4.35 t/s 21.51.350.537 I slot print_timing: id 0 | task 3440 | n_gen = 140, tg = 3.92 t/s, tg_3s = 4.35 t/s 21.54.107.119 I slot print_timing: id 1 | task 3285 | n_gen = 305, tg = 3.96 t/s, tg_3s = 4.35 t/s 21.54.566.585 I slot print_timing: id 0 | task 3440 | n_gen = 154, tg = 3.96 t/s, tg_3s = 4.35 t/s 21.57.322.791 I slot print_timing: id 1 | task 3285 | n_gen = 319, tg = 3.97 t/s, tg_3s = 4.35 t/s 21.57.782.083 I slot print_timing: id 0 | task 3440 | n_gen = 168, tg = 3.99 t/s, tg_3s = 4.35 t/s 21.59.160.733 I slot print_timing: id 2 | task 3558 | prompt eval time = 2092.17 ms / 81 tokens ( 25.83 ms per token, 38.72 tokens per second) 21.59.160.738 I slot print_timing: id 2 | task 3558 | eval time = 14617.82 ms / 57 tokens ( 261.03 ms per token, 3.83 tokens per second) 21.59.160.739 I slot print_timing: id 2 | task 3558 | total time = 16709.99 ms / 138 tokens 21.59.160.739 I slot print_timing: id 2 | task 3558 | graphs reused = 3046 21.59.160.740 I slot print_timing: id 2 | task 3558 | graph reallocs = 0 / 0 (same size) / (changed size) 21.59.160.795 I slot release: id 2 | task 3558 | stop processing: n_tokens = 1262, truncated = 0 21.59.488.713 I slot print_timing: id 3 | task 3563 | prompt eval time = 2218.92 ms / 104 tokens ( 21.34 ms per token, 46.87 tokens per second) 21.59.488.716 I slot print_timing: id 3 | task 3563 | eval time = 12274.91 ms / 54 tokens ( 231.60 ms per token, 4.32 tokens per second) 21.59.488.717 I slot print_timing: id 3 | task 3563 | total time = 14493.83 ms / 158 tokens 21.59.488.717 I slot print_timing: id 3 | task 3563 | graphs reused = 3046 21.59.488.717 I slot print_timing: id 3 | task 3563 | graph reallocs = 0 / 0 (same size) / (changed size) 21.59.488.763 I slot release: id 3 | task 3563 | stop processing: n_tokens = 1282, truncated = 0 21.59.488.773 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.908 21.59.488.801 I slot launch_slot_: id 2 | task 3619 | processing task, is_child = 0 21.59.488.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 21.59.489.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 21.59.489.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.131 MiB) 22.01.401.084 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.894 22.01.401.179 I slot launch_slot_: id 3 | task 3620 | processing task, is_child = 0 22.04.881.193 I slot print_timing: id 0 | task 3440 | n_gen = 176, tg = 3.57 t/s, tg_3s = 1.13 t/s 22.04.881.404 I slot print_timing: id 1 | task 3285 | n_gen = 329, tg = 3.74 t/s, tg_3s = 1.32 t/s 22.04.881.414 I slot print_timing: id 2 | task 3619 | prompt processing, n_tokens = 121, progress = 1.00, t = 3.48 s / 34.77 tokens per second 22.04.889.564 I slot print_timing: id 3 | task 3620 | prompt processing, n_tokens = 99, progress = 1.00, t = 3.43 s / 28.85 tokens per second 22.08.103.300 I slot print_timing: id 0 | task 3440 | n_gen = 189, tg = 3.60 t/s, tg_3s = 4.03 t/s 22.08.103.447 I slot print_timing: id 1 | task 3285 | n_gen = 342, tg = 3.75 t/s, tg_3s = 4.03 t/s 22.11.319.349 I slot print_timing: id 0 | task 3440 | n_gen = 203, tg = 3.65 t/s, tg_3s = 4.35 t/s 22.11.319.490 I slot print_timing: id 1 | task 3285 | n_gen = 356, tg = 3.77 t/s, tg_3s = 4.35 t/s 22.14.535.706 I slot print_timing: id 0 | task 3440 | n_gen = 217, tg = 3.68 t/s, tg_3s = 4.35 t/s 22.14.535.853 I slot print_timing: id 1 | task 3285 | n_gen = 370, tg = 3.79 t/s, tg_3s = 4.35 t/s 22.17.753.153 I slot print_timing: id 0 | task 3440 | n_gen = 231, tg = 3.72 t/s, tg_3s = 4.35 t/s 22.17.753.300 I slot print_timing: id 1 | task 3285 | n_gen = 384, tg = 3.81 t/s, tg_3s = 4.35 t/s 22.20.973.604 I slot print_timing: id 0 | task 3440 | n_gen = 245, tg = 3.75 t/s, tg_3s = 4.35 t/s 22.20.973.751 I slot print_timing: id 1 | task 3285 | n_gen = 398, tg = 3.83 t/s, tg_3s = 4.35 t/s 22.24.191.022 I slot print_timing: id 0 | task 3440 | n_gen = 259, tg = 3.78 t/s, tg_3s = 4.35 t/s 22.24.191.181 I slot print_timing: id 1 | task 3285 | n_gen = 412, tg = 3.84 t/s, tg_3s = 4.35 t/s 22.27.409.397 I slot print_timing: id 0 | task 3440 | n_gen = 273, tg = 3.80 t/s, tg_3s = 4.35 t/s 22.27.409.732 I slot print_timing: id 1 | task 3285 | n_gen = 426, tg = 3.86 t/s, tg_3s = 4.35 t/s 22.28.100.291 I slot print_timing: id 2 | task 3619 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 22.28.100.442 I slot print_timing: id 3 | task 3620 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 22.29.708.884 I slot print_timing: id 1 | task 3285 | prompt eval time = 2958.73 ms / 158 tokens ( 18.73 ms per token, 53.40 tokens per second) 22.29.708.889 I slot print_timing: id 1 | task 3285 | eval time = 112434.92 ms / 436 tokens ( 258.47 ms per token, 3.87 tokens per second) 22.29.708.890 I slot print_timing: id 1 | task 3285 | total time = 115393.65 ms / 594 tokens 22.29.708.890 I slot print_timing: id 1 | task 3285 | graphs reused = 3151 22.29.708.891 I slot print_timing: id 1 | task 3285 | graph reallocs = 0 / 0 (same size) / (changed size) 22.29.708.948 I slot release: id 1 | task 3285 | stop processing: n_tokens = 1718, truncated = 0 22.30.037.740 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.667 22.30.037.781 I slot launch_slot_: id 1 | task 3730 | processing task, is_child = 0 22.32.025.229 I slot print_timing: id 0 | task 3440 | n_gen = 285, tg = 3.73 t/s, tg_3s = 2.60 t/s 22.32.025.452 I slot print_timing: id 2 | task 3619 | n_gen = 109, tg = 4.05 t/s, tg_3s = 2.29 t/s 22.32.025.668 I slot print_timing: id 3 | task 3620 | n_gen = 109, tg = 4.05 t/s, tg_3s = 2.29 t/s 22.35.161.065 I slot print_timing: id 0 | task 3440 | n_gen = 297, tg = 3.74 t/s, tg_3s = 3.83 t/s 22.35.161.356 I slot print_timing: id 2 | task 3619 | n_gen = 121, tg = 4.02 t/s, tg_3s = 3.83 t/s 22.35.161.503 I slot print_timing: id 3 | task 3620 | n_gen = 121, tg = 4.02 t/s, tg_3s = 3.83 t/s 22.38.378.015 I slot print_timing: id 0 | task 3440 | n_gen = 311, tg = 3.76 t/s, tg_3s = 4.35 t/s 22.38.378.282 I slot print_timing: id 2 | task 3619 | n_gen = 135, tg = 4.06 t/s, tg_3s = 4.35 t/s 22.38.378.444 I slot print_timing: id 3 | task 3620 | n_gen = 135, tg = 4.06 t/s, tg_3s = 4.35 t/s 22.40.906.954 I slot print_timing: id 2 | task 3619 | prompt eval time = 3943.80 ms / 125 tokens ( 31.55 ms per token, 31.70 tokens per second) 22.40.906.960 I slot print_timing: id 2 | task 3619 | eval time = 35561.96 ms / 146 tokens ( 245.25 ms per token, 4.08 tokens per second) 22.40.906.961 I slot print_timing: id 2 | task 3619 | total time = 39505.76 ms / 271 tokens 22.40.906.961 I slot print_timing: id 2 | task 3619 | graphs reused = 3186 22.40.906.962 I slot print_timing: id 2 | task 3619 | graph reallocs = 0 / 0 (same size) / (changed size) 22.40.907.013 I slot release: id 2 | task 3619 | stop processing: n_tokens = 1395, truncated = 0 22.41.236.291 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.822 22.41.236.324 I slot launch_slot_: id 2 | task 3770 | processing task, is_child = 0 22.43.158.711 I slot print_timing: id 0 | task 3440 | n_gen = 324, tg = 3.70 t/s, tg_3s = 2.72 t/s 22.43.159.102 I slot print_timing: id 3 | task 3620 | n_gen = 148, tg = 3.89 t/s, tg_3s = 2.72 t/s 22.46.232.198 I slot print_timing: id 0 | task 3440 | n_gen = 336, tg = 3.71 t/s, tg_3s = 3.90 t/s 22.46.232.662 I slot print_timing: id 3 | task 3620 | n_gen = 160, tg = 3.89 t/s, tg_3s = 3.90 t/s 22.49.453.016 I slot print_timing: id 0 | task 3440 | n_gen = 350, tg = 3.73 t/s, tg_3s = 4.35 t/s 22.49.453.454 I slot print_timing: id 3 | task 3620 | n_gen = 174, tg = 3.92 t/s, tg_3s = 4.35 t/s 22.52.671.612 I slot print_timing: id 0 | task 3440 | n_gen = 364, tg = 3.75 t/s, tg_3s = 4.35 t/s 22.52.672.004 I slot print_timing: id 3 | task 3620 | n_gen = 188, tg = 3.95 t/s, tg_3s = 4.35 t/s 22.55.887.967 I slot print_timing: id 0 | task 3440 | n_gen = 378, tg = 3.77 t/s, tg_3s = 4.35 t/s 22.55.888.384 I slot print_timing: id 3 | task 3620 | n_gen = 202, tg = 3.98 t/s, tg_3s = 4.35 t/s 22.57.497.511 I slot print_timing: id 1 | task 3730 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 22.59.108.141 I slot print_timing: id 0 | task 3440 | n_gen = 392, tg = 3.79 t/s, tg_3s = 4.35 t/s 22.59.108.565 I slot print_timing: id 3 | task 3620 | n_gen = 216, tg = 4.00 t/s, tg_3s = 4.35 t/s 23.00.257.258 I slot print_timing: id 1 | task 3730 | prompt eval time = 2594.88 ms / 126 tokens ( 20.59 ms per token, 48.56 tokens per second) 23.00.257.262 I slot print_timing: id 1 | task 3730 | eval time = 27624.60 ms / 112 tokens ( 248.87 ms per token, 4.02 tokens per second) 23.00.257.262 I slot print_timing: id 1 | task 3730 | total time = 30219.47 ms / 238 tokens 23.00.257.263 I slot print_timing: id 1 | task 3730 | graphs reused = 3257 23.00.257.263 I slot print_timing: id 1 | task 3730 | graph reallocs = 0 / 0 (same size) / (changed size) 23.00.257.319 I slot release: id 1 | task 3730 | stop processing: n_tokens = 1362, truncated = 0 23.00.585.551 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.841 23.00.585.588 I slot launch_slot_: id 1 | task 3846 | processing task, is_child = 0 23.02.541.638 I slot print_timing: id 0 | task 3440 | n_gen = 399, tg = 3.73 t/s, tg_3s = 2.04 t/s 23.02.542.038 I slot print_timing: id 3 | task 3620 | n_gen = 223, tg = 3.88 t/s, tg_3s = 2.04 t/s 23.05.677.562 I slot print_timing: id 0 | task 3440 | n_gen = 411, tg = 3.74 t/s, tg_3s = 3.83 t/s 23.05.677.954 I slot print_timing: id 3 | task 3620 | n_gen = 235, tg = 3.88 t/s, tg_3s = 3.83 t/s 23.08.665.391 I slot print_timing: id 2 | task 3770 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 23.08.894.931 I slot print_timing: id 0 | task 3440 | n_gen = 425, tg = 3.75 t/s, tg_3s = 4.35 t/s 23.08.895.349 I slot print_timing: id 3 | task 3620 | n_gen = 249, tg = 3.90 t/s, tg_3s = 4.35 t/s 23.11.884.364 I slot print_timing: id 2 | task 3770 | n_gen = 114, tg = 4.01 t/s, tg_3s = 4.35 t/s 23.12.113.885 I slot print_timing: id 0 | task 3440 | n_gen = 439, tg = 3.77 t/s, tg_3s = 4.35 t/s 23.12.114.284 I slot print_timing: id 3 | task 3620 | n_gen = 263, tg = 3.92 t/s, tg_3s = 4.35 t/s 23.15.105.234 I slot print_timing: id 2 | task 3770 | n_gen = 128, tg = 4.04 t/s, tg_3s = 4.35 t/s 23.15.334.923 I slot print_timing: id 0 | task 3440 | n_gen = 453, tg = 3.79 t/s, tg_3s = 4.35 t/s 23.15.335.344 I slot print_timing: id 3 | task 3620 | n_gen = 277, tg = 3.94 t/s, tg_3s = 4.35 t/s 23.18.324.892 I slot print_timing: id 2 | task 3770 | n_gen = 142, tg = 4.07 t/s, tg_3s = 4.35 t/s 23.18.554.341 I slot print_timing: id 0 | task 3440 | n_gen = 467, tg = 3.80 t/s, tg_3s = 4.35 t/s 23.18.554.738 I slot print_timing: id 3 | task 3620 | n_gen = 291, tg = 3.96 t/s, tg_3s = 4.35 t/s 23.21.544.637 I slot print_timing: id 2 | task 3770 | n_gen = 156, tg = 4.10 t/s, tg_3s = 4.35 t/s 23.21.774.561 I slot print_timing: id 0 | task 3440 | n_gen = 481, tg = 3.81 t/s, tg_3s = 4.35 t/s 23.21.774.995 I slot print_timing: id 3 | task 3620 | n_gen = 305, tg = 3.98 t/s, tg_3s = 4.35 t/s 23.24.765.796 I slot print_timing: id 2 | task 3770 | n_gen = 170, tg = 4.12 t/s, tg_3s = 4.35 t/s 23.24.995.922 I slot print_timing: id 0 | task 3440 | n_gen = 495, tg = 3.83 t/s, tg_3s = 4.35 t/s 23.24.996.343 I slot print_timing: id 3 | task 3620 | n_gen = 319, tg = 3.99 t/s, tg_3s = 4.35 t/s 23.25.915.700 I slot print_timing: id 1 | task 3846 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 23.27.985.922 I slot print_timing: id 2 | task 3770 | n_gen = 184, tg = 4.13 t/s, tg_3s = 4.35 t/s 23.28.217.254 I slot print_timing: id 0 | task 3440 | n_gen = 509, tg = 3.84 t/s, tg_3s = 4.35 t/s 23.28.217.666 I slot print_timing: id 3 | task 3620 | n_gen = 333, tg = 4.01 t/s, tg_3s = 4.35 t/s 23.29.138.464 I slot print_timing: id 1 | task 3846 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.34 t/s 23.31.207.376 I slot print_timing: id 2 | task 3770 | n_gen = 198, tg = 4.15 t/s, tg_3s = 4.35 t/s 23.31.436.935 I slot print_timing: id 0 | task 3440 | n_gen = 523, tg = 3.85 t/s, tg_3s = 4.35 t/s 23.31.437.352 I slot print_timing: id 3 | task 3620 | n_gen = 347, tg = 4.02 t/s, tg_3s = 4.35 t/s 23.32.357.319 I slot print_timing: id 1 | task 3846 | n_gen = 128, tg = 4.35 t/s, tg_3s = 4.35 t/s 23.34.426.794 I slot print_timing: id 2 | task 3770 | n_gen = 212, tg = 4.16 t/s, tg_3s = 4.35 t/s 23.34.656.589 I slot print_timing: id 0 | task 3440 | n_gen = 537, tg = 3.86 t/s, tg_3s = 4.35 t/s 23.34.656.976 I slot print_timing: id 3 | task 3620 | n_gen = 361, tg = 4.03 t/s, tg_3s = 4.35 t/s 23.35.579.191 I slot print_timing: id 1 | task 3846 | n_gen = 142, tg = 4.35 t/s, tg_3s = 4.35 t/s 23.37.649.909 I slot print_timing: id 2 | task 3770 | n_gen = 226, tg = 4.17 t/s, tg_3s = 4.34 t/s 23.37.879.876 I slot print_timing: id 0 | task 3440 | n_gen = 551, tg = 3.87 t/s, tg_3s = 4.34 t/s 23.37.880.294 I slot print_timing: id 3 | task 3620 | n_gen = 375, tg = 4.04 t/s, tg_3s = 4.34 t/s 23.38.800.160 I slot print_timing: id 1 | task 3846 | n_gen = 156, tg = 4.35 t/s, tg_3s = 4.35 t/s 23.40.870.621 I slot print_timing: id 2 | task 3770 | n_gen = 240, tg = 4.18 t/s, tg_3s = 4.35 t/s 23.41.100.524 I slot print_timing: id 0 | task 3440 | n_gen = 565, tg = 3.88 t/s, tg_3s = 4.35 t/s 23.41.100.934 I slot print_timing: id 3 | task 3620 | n_gen = 389, tg = 4.05 t/s, tg_3s = 4.35 t/s 23.42.021.471 I slot print_timing: id 1 | task 3846 | n_gen = 170, tg = 4.35 t/s, tg_3s = 4.35 t/s 23.44.092.313 I slot print_timing: id 2 | task 3770 | n_gen = 254, tg = 4.19 t/s, tg_3s = 4.35 t/s 23.44.322.176 I slot print_timing: id 0 | task 3440 | n_gen = 579, tg = 3.89 t/s, tg_3s = 4.35 t/s 23.44.322.610 I slot print_timing: id 3 | task 3620 | n_gen = 403, tg = 4.06 t/s, tg_3s = 4.35 t/s 23.45.242.672 I slot print_timing: id 1 | task 3846 | n_gen = 184, tg = 4.35 t/s, tg_3s = 4.35 t/s 23.47.314.052 I slot print_timing: id 2 | task 3770 | n_gen = 268, tg = 4.20 t/s, tg_3s = 4.35 t/s 23.47.543.971 I slot print_timing: id 0 | task 3440 | n_gen = 593, tg = 3.90 t/s, tg_3s = 4.35 t/s 23.47.544.386 I slot print_timing: id 3 | task 3620 | n_gen = 417, tg = 4.07 t/s, tg_3s = 4.35 t/s 23.48.465.544 I slot print_timing: id 1 | task 3846 | n_gen = 198, tg = 4.35 t/s, tg_3s = 4.34 t/s 23.50.536.298 I slot print_timing: id 2 | task 3770 | n_gen = 282, tg = 4.20 t/s, tg_3s = 4.34 t/s 23.50.766.318 I slot print_timing: id 0 | task 3440 | n_gen = 607, tg = 3.91 t/s, tg_3s = 4.34 t/s 23.50.766.741 I slot print_timing: id 3 | task 3620 | n_gen = 431, tg = 4.08 t/s, tg_3s = 4.34 t/s 23.51.687.017 I slot print_timing: id 1 | task 3846 | n_gen = 212, tg = 4.35 t/s, tg_3s = 4.35 t/s 23.52.147.412 I slot print_timing: id 1 | task 3846 | prompt eval time = 2561.36 ms / 108 tokens ( 23.72 ms per token, 42.17 tokens per second) 23.52.147.417 I slot print_timing: id 1 | task 3846 | eval time = 49000.45 ms / 214 tokens ( 230.05 ms per token, 4.35 tokens per second) 23.52.147.418 I slot print_timing: id 1 | task 3846 | total time = 51561.81 ms / 322 tokens 23.52.147.418 I slot print_timing: id 1 | task 3846 | graphs reused = 3468 23.52.147.419 I slot print_timing: id 1 | task 3846 | graph reallocs = 0 / 0 (same size) / (changed size) 23.52.147.468 I slot release: id 1 | task 3846 | stop processing: n_tokens = 1446, truncated = 0 23.52.477.023 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.793 23.52.477.051 I slot launch_slot_: id 1 | task 4063 | processing task, is_child = 0 23.54.103.315 I slot print_timing: id 0 | task 3440 | n_gen = 615, tg = 3.88 t/s, tg_3s = 2.40 t/s 23.54.103.476 I slot print_timing: id 2 | task 3770 | n_gen = 291, tg = 4.12 t/s, tg_3s = 2.52 t/s 23.54.103.631 I slot print_timing: id 3 | task 3620 | n_gen = 439, tg = 4.03 t/s, tg_3s = 2.40 t/s 23.57.245.095 I slot print_timing: id 0 | task 3440 | n_gen = 627, tg = 3.88 t/s, tg_3s = 3.82 t/s 23.57.245.393 I slot print_timing: id 2 | task 3770 | n_gen = 303, tg = 4.11 t/s, tg_3s = 3.82 t/s 23.57.245.540 I slot print_timing: id 3 | task 3620 | n_gen = 451, tg = 4.02 t/s, tg_3s = 3.82 t/s 24.00.471.960 I slot print_timing: id 0 | task 3440 | n_gen = 641, tg = 3.89 t/s, tg_3s = 4.34 t/s 24.00.472.239 I slot print_timing: id 2 | task 3770 | n_gen = 317, tg = 4.12 t/s, tg_3s = 4.34 t/s 24.00.472.380 I slot print_timing: id 3 | task 3620 | n_gen = 465, tg = 4.03 t/s, tg_3s = 4.34 t/s 24.03.694.353 I slot print_timing: id 0 | task 3440 | n_gen = 655, tg = 3.90 t/s, tg_3s = 4.34 t/s 24.03.694.623 I slot print_timing: id 2 | task 3770 | n_gen = 331, tg = 4.13 t/s, tg_3s = 4.34 t/s 24.03.694.766 I slot print_timing: id 3 | task 3620 | n_gen = 479, tg = 4.04 t/s, tg_3s = 4.34 t/s 24.06.916.068 I slot print_timing: id 0 | task 3440 | n_gen = 669, tg = 3.91 t/s, tg_3s = 4.35 t/s 24.06.916.362 I slot print_timing: id 2 | task 3770 | n_gen = 345, tg = 4.13 t/s, tg_3s = 4.35 t/s 24.06.916.532 I slot print_timing: id 3 | task 3620 | n_gen = 493, tg = 4.05 t/s, tg_3s = 4.35 t/s 24.07.376.339 I slot print_timing: id 2 | task 3770 | prompt eval time = 2467.15 ms / 125 tokens ( 19.74 ms per token, 50.67 tokens per second) 24.07.376.344 I slot print_timing: id 2 | task 3770 | eval time = 83672.86 ms / 347 tokens ( 241.83 ms per token, 4.14 tokens per second) 24.07.376.345 I slot print_timing: id 2 | task 3770 | total time = 86140.01 ms / 472 tokens 24.07.376.345 I slot print_timing: id 2 | task 3770 | graphs reused = 3522 24.07.376.346 I slot print_timing: id 2 | task 3770 | graph reallocs = 0 / 0 (same size) / (changed size) 24.07.376.392 I slot release: id 2 | task 3770 | stop processing: n_tokens = 1596, truncated = 0 24.07.705.460 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.718 24.07.705.499 I slot launch_slot_: id 2 | task 4122 | processing task, is_child = 0 24.10.354.612 I slot print_timing: id 0 | task 3440 | n_gen = 673, tg = 3.85 t/s, tg_3s = 1.16 t/s 24.10.354.935 I slot print_timing: id 3 | task 3620 | n_gen = 497, tg = 3.97 t/s, tg_3s = 1.16 t/s 24.13.432.691 I slot print_timing: id 0 | task 3440 | n_gen = 685, tg = 3.85 t/s, tg_3s = 3.90 t/s 24.13.433.109 I slot print_timing: id 3 | task 3620 | n_gen = 509, tg = 3.97 t/s, tg_3s = 3.90 t/s 24.16.654.228 I slot print_timing: id 0 | task 3440 | n_gen = 699, tg = 3.86 t/s, tg_3s = 4.35 t/s 24.16.654.639 I slot print_timing: id 3 | task 3620 | n_gen = 523, tg = 3.98 t/s, tg_3s = 4.35 t/s 24.19.876.113 I slot print_timing: id 0 | task 3440 | n_gen = 713, tg = 3.87 t/s, tg_3s = 4.35 t/s 24.19.876.543 I slot print_timing: id 3 | task 3620 | n_gen = 537, tg = 3.98 t/s, tg_3s = 4.35 t/s 24.20.336.537 I slot print_timing: id 1 | task 4063 | n_gen = 100, tg = 3.86 t/s, tg_3s = 3.90 t/s 24.23.096.376 I slot print_timing: id 0 | task 3440 | n_gen = 727, tg = 3.88 t/s, tg_3s = 4.35 t/s 24.23.096.781 I slot print_timing: id 3 | task 3620 | n_gen = 551, tg = 3.99 t/s, tg_3s = 4.35 t/s 24.23.556.718 I slot print_timing: id 1 | task 4063 | n_gen = 114, tg = 3.92 t/s, tg_3s = 4.35 t/s 24.26.320.304 I slot print_timing: id 0 | task 3440 | n_gen = 741, tg = 3.89 t/s, tg_3s = 4.34 t/s 24.26.320.734 I slot print_timing: id 3 | task 3620 | n_gen = 565, tg = 4.00 t/s, tg_3s = 4.34 t/s 24.26.780.711 I slot print_timing: id 1 | task 4063 | n_gen = 128, tg = 3.96 t/s, tg_3s = 4.34 t/s 24.29.542.537 I slot print_timing: id 0 | task 3440 | n_gen = 755, tg = 3.89 t/s, tg_3s = 4.34 t/s 24.29.542.955 I slot print_timing: id 3 | task 3620 | n_gen = 579, tg = 4.01 t/s, tg_3s = 4.34 t/s 24.29.773.045 I slot print_timing: id 2 | task 4122 | prompt eval time = 3193.95 ms / 171 tokens ( 18.68 ms per token, 53.54 tokens per second) 24.29.773.050 I slot print_timing: id 2 | task 4122 | eval time = 18873.59 ms / 83 tokens ( 230.17 ms per token, 4.34 tokens per second) 24.29.773.051 I slot print_timing: id 2 | task 4122 | total time = 22067.54 ms / 254 tokens 24.29.773.051 I slot print_timing: id 2 | task 4122 | graphs reused = 3603 24.29.773.052 I slot print_timing: id 2 | task 4122 | graph reallocs = 0 / 0 (same size) / (changed size) 24.29.773.107 I slot release: id 2 | task 4122 | stop processing: n_tokens = 1378, truncated = 0 24.30.102.089 I slot print_timing: id 1 | task 4063 | n_gen = 142, tg = 3.98 t/s, tg_3s = 4.22 t/s 24.30.102.244 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.832 24.30.102.274 I slot launch_slot_: id 2 | task 4208 | processing task, is_child = 0 24.32.660.405 I slot print_timing: id 0 | task 3440 | n_gen = 761, tg = 3.86 t/s, tg_3s = 1.92 t/s 24.32.660.841 I slot print_timing: id 3 | task 3620 | n_gen = 585, tg = 3.96 t/s, tg_3s = 1.92 t/s 24.33.121.978 I slot print_timing: id 1 | task 4063 | n_gen = 148, tg = 3.83 t/s, tg_3s = 1.99 t/s 24.34.964.233 I slot print_timing: id 1 | task 4063 | prompt eval time = 2232.32 ms / 100 tokens ( 22.32 ms per token, 44.80 tokens per second) 24.34.964.237 I slot print_timing: id 1 | task 4063 | eval time = 40254.85 ms / 156 tokens ( 259.71 ms per token, 3.85 tokens per second) 24.34.964.238 I slot print_timing: id 1 | task 4063 | total time = 42487.17 ms / 256 tokens 24.34.964.238 I slot print_timing: id 1 | task 4063 | graphs reused = 3614 24.34.964.239 I slot print_timing: id 1 | task 4063 | graph reallocs = 0 / 0 (same size) / (changed size) 24.34.964.283 I slot release: id 1 | task 4063 | stop processing: n_tokens = 1380, truncated = 0 24.35.294.470 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 24.35.294.501 I slot launch_slot_: id 1 | task 4224 | processing task, is_child = 0 24.36.901.597 I slot print_timing: id 0 | task 3440 | n_gen = 773, tg = 3.84 t/s, tg_3s = 2.83 t/s 24.36.901.904 I slot print_timing: id 3 | task 3620 | n_gen = 597, tg = 3.93 t/s, tg_3s = 2.83 t/s 24.40.040.268 I slot print_timing: id 0 | task 3440 | n_gen = 785, tg = 3.84 t/s, tg_3s = 3.82 t/s 24.40.040.690 I slot print_timing: id 3 | task 3620 | n_gen = 609, tg = 3.93 t/s, tg_3s = 3.82 t/s 24.43.268.453 I slot print_timing: id 0 | task 3440 | n_gen = 799, tg = 3.85 t/s, tg_3s = 4.34 t/s 24.43.268.852 I slot print_timing: id 3 | task 3620 | n_gen = 623, tg = 3.94 t/s, tg_3s = 4.34 t/s 24.46.269.616 I slot print_timing: id 0 | task 3440 | n_gen = 812, tg = 3.86 t/s, tg_3s = 4.33 t/s 24.46.270.041 I slot print_timing: id 3 | task 3620 | n_gen = 636, tg = 3.95 t/s, tg_3s = 4.33 t/s 24.49.270.962 I slot print_timing: id 0 | task 3440 | n_gen = 825, tg = 3.86 t/s, tg_3s = 4.33 t/s 24.49.271.356 I slot print_timing: id 3 | task 3620 | n_gen = 649, tg = 3.95 t/s, tg_3s = 4.33 t/s 24.52.271.803 I slot print_timing: id 0 | task 3440 | n_gen = 838, tg = 3.87 t/s, tg_3s = 4.33 t/s 24.52.272.206 I slot print_timing: id 3 | task 3620 | n_gen = 662, tg = 3.96 t/s, tg_3s = 4.33 t/s 24.53.656.411 I slot print_timing: id 2 | task 4208 | prompt eval time = 2096.00 ms / 89 tokens ( 23.55 ms per token, 42.46 tokens per second) 24.53.656.416 I slot print_timing: id 2 | task 4208 | eval time = 21458.12 ms / 86 tokens ( 252.45 ms per token, 3.96 tokens per second) 24.53.656.417 I slot print_timing: id 2 | task 4208 | total time = 23554.13 ms / 175 tokens 24.53.656.417 I slot print_timing: id 2 | task 4208 | graphs reused = 3682 24.53.656.417 I slot print_timing: id 2 | task 4208 | graph reallocs = 0 / 0 (same size) / (changed size) 24.53.656.466 I slot release: id 2 | task 4208 | stop processing: n_tokens = 1299, truncated = 0 24.53.985.571 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.882 24.53.985.606 I slot launch_slot_: id 2 | task 4298 | processing task, is_child = 0 24.55.891.789 I slot print_timing: id 0 | task 3440 | n_gen = 846, tg = 3.84 t/s, tg_3s = 2.21 t/s 24.55.892.108 I slot print_timing: id 3 | task 3620 | n_gen = 670, tg = 3.92 t/s, tg_3s = 2.21 t/s 24.58.982.605 I slot print_timing: id 0 | task 3440 | n_gen = 858, tg = 3.84 t/s, tg_3s = 3.88 t/s 24.58.983.011 I slot print_timing: id 3 | task 3620 | n_gen = 682, tg = 3.92 t/s, tg_3s = 3.88 t/s 25.01.983.352 I slot print_timing: id 0 | task 3440 | n_gen = 871, tg = 3.85 t/s, tg_3s = 4.33 t/s 25.01.983.763 I slot print_timing: id 3 | task 3620 | n_gen = 695, tg = 3.93 t/s, tg_3s = 4.33 t/s 25.02.444.864 I slot print_timing: id 1 | task 4224 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 25.03.830.621 I slot print_timing: id 1 | task 4224 | prompt eval time = 2212.64 ms / 82 tokens ( 26.98 ms per token, 37.06 tokens per second) 25.03.830.626 I slot print_timing: id 1 | task 4224 | eval time = 26323.48 ms / 106 tokens ( 250.70 ms per token, 3.99 tokens per second) 25.03.830.627 I slot print_timing: id 1 | task 4224 | total time = 28536.11 ms / 188 tokens 25.03.830.627 I slot print_timing: id 1 | task 4224 | graphs reused = 3713 25.03.830.628 I slot print_timing: id 1 | task 4224 | graph reallocs = 0 / 0 (same size) / (changed size) 25.03.830.672 I slot release: id 1 | task 4224 | stop processing: n_tokens = 1312, truncated = 0 25.04.160.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.873 25.04.160.271 I slot launch_slot_: id 1 | task 4334 | processing task, is_child = 0 25.05.783.166 I slot print_timing: id 0 | task 3440 | n_gen = 881, tg = 3.83 t/s, tg_3s = 2.63 t/s 25.05.783.480 I slot print_timing: id 3 | task 3620 | n_gen = 705, tg = 3.90 t/s, tg_3s = 2.63 t/s 25.08.932.091 I slot print_timing: id 0 | task 3440 | n_gen = 893, tg = 3.83 t/s, tg_3s = 3.81 t/s 25.08.932.528 I slot print_timing: id 3 | task 3620 | n_gen = 717, tg = 3.90 t/s, tg_3s = 3.81 t/s 25.11.933.004 I slot print_timing: id 0 | task 3440 | n_gen = 906, tg = 3.83 t/s, tg_3s = 4.33 t/s 25.11.933.428 I slot print_timing: id 3 | task 3620 | n_gen = 730, tg = 3.91 t/s, tg_3s = 4.33 t/s 25.15.163.310 I slot print_timing: id 0 | task 3440 | n_gen = 920, tg = 3.84 t/s, tg_3s = 4.33 t/s 25.15.163.711 I slot print_timing: id 3 | task 3620 | n_gen = 744, tg = 3.91 t/s, tg_3s = 4.33 t/s 25.17.471.721 I slot print_timing: id 3 | task 3620 | prompt eval time = 3895.95 ms / 103 tokens ( 37.82 ms per token, 26.44 tokens per second) 25.17.471.727 I slot print_timing: id 3 | task 3620 | eval time = 192126.52 ms / 754 tokens ( 255.15 ms per token, 3.92 tokens per second) 25.17.471.727 I slot print_timing: id 3 | task 3620 | total time = 196022.47 ms / 857 tokens 25.17.471.728 I slot print_timing: id 3 | task 3620 | graphs reused = 3760 25.17.471.728 I slot print_timing: id 3 | task 3620 | graph reallocs = 0 / 0 (same size) / (changed size) 25.17.471.773 I slot release: id 3 | task 3620 | stop processing: n_tokens = 1981, truncated = 0 25.17.689.874 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.578 25.17.689.909 I slot launch_slot_: id 3 | task 4386 | processing task, is_child = 0 25.19.481.940 I slot print_timing: id 0 | task 3440 | n_gen = 932, tg = 3.82 t/s, tg_3s = 2.78 t/s 25.22.228.526 I slot print_timing: id 2 | task 4298 | prompt eval time = 2452.05 ms / 114 tokens ( 21.51 ms per token, 46.49 tokens per second) 25.22.228.528 I slot print_timing: id 2 | task 4298 | eval time = 25790.85 ms / 97 tokens ( 268.65 ms per token, 3.72 tokens per second) 25.22.228.529 I slot print_timing: id 2 | task 4298 | total time = 28242.91 ms / 211 tokens 25.22.228.530 I slot print_timing: id 2 | task 4298 | graphs reused = 3769 25.22.228.530 I slot print_timing: id 2 | task 4298 | graph reallocs = 0 / 0 (same size) / (changed size) 25.22.228.577 I slot release: id 2 | task 4298 | stop processing: n_tokens = 1335, truncated = 0 25.22.557.950 I slot print_timing: id 0 | task 3440 | n_gen = 944, tg = 3.82 t/s, tg_3s = 3.90 t/s 25.22.558.355 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.858 25.22.558.389 I slot launch_slot_: id 2 | task 4400 | processing task, is_child = 0 25.25.593.379 I slot print_timing: id 0 | task 3440 | n_gen = 950, tg = 3.80 t/s, tg_3s = 1.98 t/s 25.26.747.334 I slot print_timing: id 1 | task 4334 | prompt eval time = 2228.87 ms / 98 tokens ( 22.74 ms per token, 43.97 tokens per second) 25.26.747.340 I slot print_timing: id 1 | task 4334 | eval time = 20358.18 ms / 74 tokens ( 278.88 ms per token, 3.59 tokens per second) 25.26.747.340 I slot print_timing: id 1 | task 4334 | total time = 22587.06 ms / 172 tokens 25.26.747.341 I slot print_timing: id 1 | task 4334 | graphs reused = 3777 25.26.747.341 I slot print_timing: id 1 | task 4334 | graph reallocs = 0 / 0 (same size) / (changed size) 25.26.747.388 I slot release: id 1 | task 4334 | stop processing: n_tokens = 1296, truncated = 0 25.27.075.821 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.884 25.27.075.857 I slot launch_slot_: id 1 | task 4413 | processing task, is_child = 0 25.29.035.192 I slot print_timing: id 0 | task 3440 | n_gen = 957, tg = 3.78 t/s, tg_3s = 2.03 t/s 25.32.180.473 I slot print_timing: id 0 | task 3440 | n_gen = 969, tg = 3.78 t/s, tg_3s = 3.82 t/s 25.35.410.118 I slot print_timing: id 0 | task 3440 | n_gen = 983, tg = 3.78 t/s, tg_3s = 4.33 t/s 25.38.639.358 I slot print_timing: id 0 | task 3440 | n_gen = 997, tg = 3.79 t/s, tg_3s = 4.34 t/s 25.41.869.711 I slot print_timing: id 0 | task 3440 | n_gen = 1011, tg = 3.80 t/s, tg_3s = 4.33 t/s 25.44.871.389 I slot print_timing: id 0 | task 3440 | prompt eval time = 2211.93 ms / 128 tokens ( 17.28 ms per token, 57.87 tokens per second) 25.44.871.394 I slot print_timing: id 0 | task 3440 | eval time = 268952.27 ms / 1024 tokens ( 262.91 ms per token, 3.80 tokens per second) 25.44.871.395 I slot print_timing: id 0 | task 3440 | total time = 271164.21 ms / 1152 tokens 25.44.871.396 I slot print_timing: id 0 | task 3440 | graphs reused = 3842 25.44.871.396 I slot print_timing: id 0 | task 3440 | graph reallocs = 0 / 0 (same size) / (changed size) 25.44.871.441 I slot release: id 0 | task 3440 | stop processing: n_tokens = 2276, truncated = 0 25.45.089.463 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.504 25.45.089.504 I slot launch_slot_: id 0 | task 4483 | processing task, is_child = 0 25.48.447.043 I slot print_timing: id 3 | task 4386 | n_gen = 100, tg = 3.47 t/s, tg_3s = 3.51 t/s 25.51.431.645 I slot print_timing: id 2 | task 4400 | n_gen = 100, tg = 3.70 t/s, tg_3s = 3.74 t/s 25.51.662.361 I slot print_timing: id 3 | task 4386 | n_gen = 114, tg = 3.56 t/s, tg_3s = 4.35 t/s 25.54.186.860 I slot print_timing: id 1 | task 4413 | n_gen = 100, tg = 4.03 t/s, tg_3s = 4.07 t/s 25.54.646.031 I slot print_timing: id 2 | task 4400 | n_gen = 114, tg = 3.77 t/s, tg_3s = 4.36 t/s 25.54.875.937 I slot print_timing: id 3 | task 4386 | n_gen = 128, tg = 3.63 t/s, tg_3s = 4.36 t/s 25.57.401.976 I slot print_timing: id 1 | task 4413 | n_gen = 114, tg = 4.07 t/s, tg_3s = 4.35 t/s 25.57.860.884 I slot print_timing: id 2 | task 4400 | n_gen = 128, tg = 3.83 t/s, tg_3s = 4.35 t/s 25.58.090.756 I slot print_timing: id 3 | task 4386 | n_gen = 142, tg = 3.69 t/s, tg_3s = 4.35 t/s 26.00.616.373 I slot print_timing: id 1 | task 4413 | n_gen = 128, tg = 4.10 t/s, tg_3s = 4.36 t/s 26.01.076.670 I slot print_timing: id 2 | task 4400 | n_gen = 142, tg = 3.87 t/s, tg_3s = 4.35 t/s 26.01.306.421 I slot print_timing: id 3 | task 4386 | n_gen = 156, tg = 3.75 t/s, tg_3s = 4.35 t/s 26.03.831.301 I slot print_timing: id 1 | task 4413 | n_gen = 142, tg = 4.12 t/s, tg_3s = 4.35 t/s 26.04.290.843 I slot print_timing: id 2 | task 4400 | n_gen = 156, tg = 3.91 t/s, tg_3s = 4.36 t/s 26.04.520.703 I slot print_timing: id 3 | task 4386 | n_gen = 170, tg = 3.79 t/s, tg_3s = 4.36 t/s 26.07.045.853 I slot print_timing: id 1 | task 4413 | n_gen = 156, tg = 4.14 t/s, tg_3s = 4.36 t/s 26.07.505.344 I slot print_timing: id 2 | task 4400 | n_gen = 170, tg = 3.95 t/s, tg_3s = 4.36 t/s 26.07.735.238 I slot print_timing: id 3 | task 4386 | n_gen = 184, tg = 3.83 t/s, tg_3s = 4.36 t/s 26.10.031.852 I slot print_timing: id 0 | task 4483 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 26.10.261.643 I slot print_timing: id 1 | task 4413 | n_gen = 170, tg = 4.16 t/s, tg_3s = 4.35 t/s 26.10.721.365 I slot print_timing: id 2 | task 4400 | n_gen = 184, tg = 3.97 t/s, tg_3s = 4.35 t/s 26.10.951.371 I slot print_timing: id 3 | task 4386 | n_gen = 198, tg = 3.86 t/s, tg_3s = 4.35 t/s 26.13.248.781 I slot print_timing: id 0 | task 4483 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 26.13.478.650 I slot print_timing: id 1 | task 4413 | n_gen = 184, tg = 4.17 t/s, tg_3s = 4.35 t/s 26.13.938.365 I slot print_timing: id 2 | task 4400 | n_gen = 198, tg = 4.00 t/s, tg_3s = 4.35 t/s 26.14.168.500 I slot print_timing: id 3 | task 4386 | n_gen = 212, tg = 3.89 t/s, tg_3s = 4.35 t/s 26.16.466.318 I slot print_timing: id 0 | task 4483 | n_gen = 128, tg = 4.35 t/s, tg_3s = 4.35 t/s 26.16.696.310 I slot print_timing: id 1 | task 4413 | n_gen = 198, tg = 4.19 t/s, tg_3s = 4.35 t/s 26.17.156.126 I slot print_timing: id 2 | task 4400 | n_gen = 212, tg = 4.02 t/s, tg_3s = 4.35 t/s 26.17.385.990 I slot print_timing: id 3 | task 4386 | n_gen = 226, tg = 3.92 t/s, tg_3s = 4.35 t/s 26.19.683.504 I slot print_timing: id 0 | task 4483 | prompt eval time = 2207.12 ms / 119 tokens ( 18.55 ms per token, 53.92 tokens per second) 26.19.683.509 I slot print_timing: id 0 | task 4483 | eval time = 32386.87 ms / 142 tokens ( 229.69 ms per token, 4.35 tokens per second) 26.19.683.510 I slot print_timing: id 0 | task 4483 | total time = 34593.99 ms / 261 tokens 26.19.683.510 I slot print_timing: id 0 | task 4483 | graphs reused = 3983 26.19.683.511 I slot print_timing: id 0 | task 4483 | graph reallocs = 0 / 0 (same size) / (changed size) 26.19.683.554 I slot release: id 0 | task 4483 | stop processing: n_tokens = 1385, truncated = 0 26.19.901.830 I slot print_timing: id 1 | task 4413 | n_gen = 212, tg = 4.20 t/s, tg_3s = 4.37 t/s 26.19.902.121 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.827 26.19.902.153 I slot launch_slot_: id 0 | task 4628 | processing task, is_child = 0 26.22.049.645 I slot print_timing: id 2 | task 4400 | n_gen = 225, tg = 3.90 t/s, tg_3s = 2.66 t/s 26.22.049.858 I slot print_timing: id 3 | task 4386 | n_gen = 238, tg = 3.81 t/s, tg_3s = 2.57 t/s 26.22.934.329 I slot print_timing: id 1 | task 4413 | n_gen = 216, tg = 4.03 t/s, tg_3s = 1.32 t/s 26.24.313.214 I slot print_timing: id 1 | task 4413 | prompt eval time = 2565.65 ms / 113 tokens ( 22.70 ms per token, 44.04 tokens per second) 26.24.313.219 I slot print_timing: id 1 | task 4413 | eval time = 54671.70 ms / 222 tokens ( 247.38 ms per token, 4.04 tokens per second) 26.24.313.220 I slot print_timing: id 1 | task 4413 | total time = 57237.35 ms / 335 tokens 26.24.313.221 I slot print_timing: id 1 | task 4413 | graphs reused = 3991 26.24.313.221 I slot print_timing: id 1 | task 4413 | graph reallocs = 0 / 0 (same size) / (changed size) 26.24.313.264 I slot release: id 1 | task 4413 | stop processing: n_tokens = 1459, truncated = 0 26.24.313.409 I slot print_timing: id 2 | task 4400 | prompt eval time = 2108.95 ms / 97 tokens ( 21.74 ms per token, 45.99 tokens per second) 26.24.313.411 I slot print_timing: id 2 | task 4400 | eval time = 59646.07 ms / 234 tokens ( 255.99 ms per token, 3.91 tokens per second) 26.24.313.412 I slot print_timing: id 2 | task 4400 | total time = 61755.01 ms / 331 tokens 26.24.313.413 I slot print_timing: id 2 | task 4400 | graphs reused = 3991 26.24.313.413 I slot print_timing: id 2 | task 4400 | graph reallocs = 0 / 0 (same size) / (changed size) 26.24.313.442 I slot release: id 2 | task 4400 | stop processing: n_tokens = 1455, truncated = 0 26.24.564.797 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.785 26.24.564.834 I slot launch_slot_: id 1 | task 4640 | processing task, is_child = 0 26.24.564.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.631 MiB) 26.24.565.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.319 MiB) 26.26.344.290 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.788 26.26.344.468 I slot launch_slot_: id 2 | task 4641 | processing task, is_child = 0 26.29.664.370 I slot print_timing: id 3 | task 4386 | n_gen = 249, tg = 3.56 t/s, tg_3s = 1.44 t/s 26.29.664.401 I slot print_timing: id 1 | task 4640 | prompt processing, n_tokens = 105, progress = 1.00, t = 3.32 s / 31.64 tokens per second 26.29.673.755 I slot print_timing: id 2 | task 4641 | prompt processing, n_tokens = 108, progress = 1.00, t = 3.29 s / 32.84 tokens per second 26.32.766.269 I slot print_timing: id 3 | task 4386 | n_gen = 261, tg = 3.57 t/s, tg_3s = 3.87 t/s 26.35.978.843 I slot print_timing: id 3 | task 4386 | n_gen = 275, tg = 3.60 t/s, tg_3s = 4.36 t/s 26.39.193.843 I slot print_timing: id 3 | task 4386 | n_gen = 289, tg = 3.63 t/s, tg_3s = 4.35 t/s 26.42.408.899 I slot print_timing: id 3 | task 4386 | n_gen = 303, tg = 3.66 t/s, tg_3s = 4.35 t/s 26.45.628.190 I slot print_timing: id 3 | task 4386 | n_gen = 317, tg = 3.69 t/s, tg_3s = 4.35 t/s 26.48.842.909 I slot print_timing: id 3 | task 4386 | n_gen = 331, tg = 3.71 t/s, tg_3s = 4.35 t/s 26.50.450.386 I slot print_timing: id 0 | task 4628 | n_gen = 100, tg = 3.54 t/s, tg_3s = 3.57 t/s 26.52.060.742 I slot print_timing: id 3 | task 4386 | n_gen = 345, tg = 3.73 t/s, tg_3s = 4.35 t/s 26.52.979.384 I slot print_timing: id 1 | task 4640 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 26.52.979.521 I slot print_timing: id 2 | task 4641 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 26.53.668.281 I slot print_timing: id 0 | task 4628 | n_gen = 114, tg = 3.62 t/s, tg_3s = 4.35 t/s 26.54.818.661 I slot print_timing: id 3 | task 4386 | prompt eval time = 2229.41 ms / 109 tokens ( 20.45 ms per token, 48.89 tokens per second) 26.54.818.667 I slot print_timing: id 3 | task 4386 | eval time = 94899.33 ms / 357 tokens ( 266.57 ms per token, 3.75 tokens per second) 26.54.818.670 I slot print_timing: id 3 | task 4386 | total time = 97128.74 ms / 466 tokens 26.54.818.671 I slot print_timing: id 3 | task 4386 | graphs reused = 4096 26.54.818.671 I slot print_timing: id 3 | task 4386 | graph reallocs = 0 / 0 (same size) / (changed size) 26.54.818.725 I slot release: id 3 | task 4386 | stop processing: n_tokens = 1590, truncated = 0 26.55.036.438 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.721 26.55.036.479 I slot launch_slot_: id 3 | task 4752 | processing task, is_child = 0 26.56.488.438 I slot print_timing: id 1 | task 4640 | n_gen = 110, tg = 4.15 t/s, tg_3s = 2.85 t/s 26.56.488.652 I slot print_timing: id 2 | task 4641 | n_gen = 110, tg = 4.15 t/s, tg_3s = 2.85 t/s 26.56.930.508 I slot print_timing: id 0 | task 4628 | n_gen = 122, tg = 3.51 t/s, tg_3s = 2.45 t/s 26.59.687.844 I slot print_timing: id 1 | task 4640 | n_gen = 123, tg = 4.14 t/s, tg_3s = 4.06 t/s 26.59.687.992 I slot print_timing: id 2 | task 4641 | n_gen = 123, tg = 4.14 t/s, tg_3s = 4.06 t/s 27.00.146.875 I slot print_timing: id 0 | task 4628 | n_gen = 136, tg = 3.58 t/s, tg_3s = 4.35 t/s 27.02.902.131 I slot print_timing: id 1 | task 4640 | n_gen = 137, tg = 4.16 t/s, tg_3s = 4.36 t/s 27.02.902.288 I slot print_timing: id 2 | task 4641 | n_gen = 137, tg = 4.16 t/s, tg_3s = 4.36 t/s 27.03.361.285 I slot print_timing: id 0 | task 4628 | n_gen = 150, tg = 3.64 t/s, tg_3s = 4.36 t/s 27.06.115.559 I slot print_timing: id 1 | task 4640 | n_gen = 151, tg = 4.18 t/s, tg_3s = 4.36 t/s 27.06.115.714 I slot print_timing: id 2 | task 4641 | n_gen = 151, tg = 4.18 t/s, tg_3s = 4.36 t/s 27.06.574.967 I slot print_timing: id 0 | task 4628 | n_gen = 164, tg = 3.70 t/s, tg_3s = 4.36 t/s 27.09.329.902 I slot print_timing: id 1 | task 4640 | n_gen = 165, tg = 4.20 t/s, tg_3s = 4.36 t/s 27.09.330.047 I slot print_timing: id 2 | task 4641 | n_gen = 165, tg = 4.20 t/s, tg_3s = 4.36 t/s 27.09.789.099 I slot print_timing: id 0 | task 4628 | n_gen = 178, tg = 3.74 t/s, tg_3s = 4.36 t/s 27.12.545.772 I slot print_timing: id 1 | task 4640 | n_gen = 179, tg = 4.21 t/s, tg_3s = 4.35 t/s 27.12.545.912 I slot print_timing: id 2 | task 4641 | n_gen = 179, tg = 4.21 t/s, tg_3s = 4.35 t/s 27.13.004.685 I slot print_timing: id 0 | task 4628 | n_gen = 192, tg = 3.78 t/s, tg_3s = 4.35 t/s 27.15.763.793 I slot print_timing: id 1 | task 4640 | n_gen = 193, tg = 4.22 t/s, tg_3s = 4.35 t/s 27.15.763.952 I slot print_timing: id 2 | task 4641 | n_gen = 193, tg = 4.22 t/s, tg_3s = 4.35 t/s 27.16.222.565 I slot print_timing: id 0 | task 4628 | n_gen = 206, tg = 3.81 t/s, tg_3s = 4.35 t/s 27.18.977.448 I slot print_timing: id 1 | task 4640 | n_gen = 207, tg = 4.23 t/s, tg_3s = 4.36 t/s 27.18.977.600 I slot print_timing: id 2 | task 4641 | n_gen = 207, tg = 4.23 t/s, tg_3s = 4.36 t/s 27.19.437.058 I slot print_timing: id 0 | task 4628 | n_gen = 220, tg = 3.84 t/s, tg_3s = 4.36 t/s 27.19.667.184 I slot print_timing: id 3 | task 4752 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 27.22.191.461 I slot print_timing: id 1 | task 4640 | n_gen = 221, tg = 4.23 t/s, tg_3s = 4.36 t/s 27.22.191.610 I slot print_timing: id 2 | task 4641 | n_gen = 221, tg = 4.23 t/s, tg_3s = 4.36 t/s 27.22.651.047 I slot print_timing: id 0 | task 4628 | n_gen = 234, tg = 3.87 t/s, tg_3s = 4.36 t/s 27.22.651.184 I slot print_timing: id 1 | task 4640 | prompt eval time = 3892.86 ms / 109 tokens ( 35.71 ms per token, 28.00 tokens per second) 27.22.651.186 I slot print_timing: id 1 | task 4640 | eval time = 52413.85 ms / 223 tokens ( 236.10 ms per token, 4.24 tokens per second) 27.22.651.187 I slot print_timing: id 1 | task 4640 | total time = 56306.71 ms / 332 tokens 27.22.651.188 I slot print_timing: id 1 | task 4640 | graphs reused = 4207 27.22.651.188 I slot print_timing: id 1 | task 4640 | graph reallocs = 0 / 0 (same size) / (changed size) 27.22.651.240 I slot release: id 1 | task 4640 | stop processing: n_tokens = 1456, truncated = 0 27.22.979.222 I slot print_timing: id 3 | task 4752 | n_gen = 114, tg = 4.34 t/s, tg_3s = 4.23 t/s 27.22.979.236 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.787 27.22.979.269 I slot launch_slot_: id 1 | task 4868 | processing task, is_child = 0 27.25.204.310 I slot print_timing: id 2 | task 4641 | n_gen = 226, tg = 4.09 t/s, tg_3s = 1.66 t/s 27.25.665.769 I slot print_timing: id 0 | task 4628 | n_gen = 239, tg = 3.77 t/s, tg_3s = 1.66 t/s 27.26.125.229 I slot print_timing: id 3 | task 4752 | n_gen = 120, tg = 4.08 t/s, tg_3s = 1.91 t/s 27.28.422.291 I slot print_timing: id 2 | task 4641 | n_gen = 240, tg = 4.11 t/s, tg_3s = 4.35 t/s 27.28.881.570 I slot print_timing: id 0 | task 4628 | n_gen = 253, tg = 3.79 t/s, tg_3s = 4.35 t/s 27.29.341.259 I slot print_timing: id 3 | task 4752 | n_gen = 134, tg = 4.10 t/s, tg_3s = 4.35 t/s 27.30.489.134 I slot print_timing: id 3 | task 4752 | prompt eval time = 1894.49 ms / 95 tokens ( 19.94 ms per token, 50.15 tokens per second) 27.30.489.140 I slot print_timing: id 3 | task 4752 | eval time = 33558.16 ms / 139 tokens ( 243.18 ms per token, 4.11 tokens per second) 27.30.489.141 I slot print_timing: id 3 | task 4752 | total time = 35452.65 ms / 234 tokens 27.30.489.141 I slot print_timing: id 3 | task 4752 | graphs reused = 4229 27.30.489.142 I slot print_timing: id 3 | task 4752 | graph reallocs = 0 / 0 (same size) / (changed size) 27.30.489.187 I slot release: id 3 | task 4752 | stop processing: n_tokens = 1358, truncated = 0 27.30.707.538 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.844 27.30.707.569 I slot launch_slot_: id 3 | task 4895 | processing task, is_child = 0 27.32.507.164 I slot print_timing: id 0 | task 4628 | n_gen = 262, tg = 3.73 t/s, tg_3s = 2.48 t/s 27.32.507.544 I slot print_timing: id 2 | task 4641 | n_gen = 251, tg = 4.01 t/s, tg_3s = 2.69 t/s 27.35.701.409 I slot print_timing: id 0 | task 4628 | n_gen = 275, tg = 3.74 t/s, tg_3s = 4.07 t/s 27.35.701.704 I slot print_timing: id 2 | task 4641 | n_gen = 264, tg = 4.02 t/s, tg_3s = 4.07 t/s 27.38.918.574 I slot print_timing: id 0 | task 4628 | n_gen = 289, tg = 3.77 t/s, tg_3s = 4.35 t/s 27.38.918.873 I slot print_timing: id 2 | task 4641 | n_gen = 278, tg = 4.03 t/s, tg_3s = 4.35 t/s 27.41.215.795 I slot print_timing: id 2 | task 4641 | prompt eval time = 3863.87 ms / 112 tokens ( 34.50 ms per token, 28.99 tokens per second) 27.41.215.798 I slot print_timing: id 2 | task 4641 | eval time = 70977.40 ms / 288 tokens ( 247.31 ms per token, 4.04 tokens per second) 27.41.215.799 I slot print_timing: id 2 | task 4641 | total time = 74841.26 ms / 400 tokens 27.41.215.799 I slot print_timing: id 2 | task 4641 | graphs reused = 4263 27.41.215.800 I slot print_timing: id 2 | task 4641 | graph reallocs = 0 / 0 (same size) / (changed size) 27.41.215.854 I slot release: id 2 | task 4641 | stop processing: n_tokens = 1524, truncated = 0 27.41.545.792 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.752 27.41.545.826 I slot launch_slot_: id 2 | task 4935 | processing task, is_child = 0 27.44.192.466 I slot print_timing: id 0 | task 4628 | n_gen = 301, tg = 3.67 t/s, tg_3s = 2.28 t/s 27.47.269.164 I slot print_timing: id 0 | task 4628 | n_gen = 313, tg = 3.68 t/s, tg_3s = 3.90 t/s 27.50.485.905 I slot print_timing: id 0 | task 4628 | n_gen = 327, tg = 3.70 t/s, tg_3s = 4.35 t/s 27.52.556.114 I slot print_timing: id 1 | task 4868 | n_gen = 100, tg = 3.62 t/s, tg_3s = 3.66 t/s 27.53.705.740 I slot print_timing: id 0 | task 4628 | n_gen = 341, tg = 3.73 t/s, tg_3s = 4.35 t/s 27.55.084.573 I slot print_timing: id 1 | task 4868 | prompt eval time = 2224.86 ms / 96 tokens ( 23.18 ms per token, 43.15 tokens per second) 27.55.084.575 I slot print_timing: id 1 | task 4868 | eval time = 29880.43 ms / 111 tokens ( 271.64 ms per token, 3.68 tokens per second) 27.55.084.577 I slot print_timing: id 1 | task 4868 | total time = 32105.30 ms / 207 tokens 27.55.084.577 I slot print_timing: id 1 | task 4868 | graphs reused = 4307 27.55.084.578 I slot print_timing: id 1 | task 4868 | graph reallocs = 0 / 0 (same size) / (changed size) 27.55.084.620 I slot release: id 1 | task 4868 | stop processing: n_tokens = 1331, truncated = 0 27.55.413.530 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.861 27.55.413.562 I slot launch_slot_: id 1 | task 4984 | processing task, is_child = 0 27.57.374.461 I slot print_timing: id 0 | task 4628 | prompt eval time = 2569.95 ms / 134 tokens ( 19.18 ms per token, 52.14 tokens per second) 27.57.374.466 I slot print_timing: id 0 | task 4628 | eval time = 94902.35 ms / 349 tokens ( 272.71 ms per token, 3.67 tokens per second) 27.57.374.467 I slot print_timing: id 0 | task 4628 | total time = 97472.30 ms / 483 tokens 27.57.374.467 I slot print_timing: id 0 | task 4628 | graphs reused = 4307 27.57.374.468 I slot print_timing: id 0 | task 4628 | graph reallocs = 0 / 0 (same size) / (changed size) 27.57.374.529 I slot release: id 0 | task 4628 | stop processing: n_tokens = 1607, truncated = 0 27.57.784.487 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.713 27.57.784.527 I slot launch_slot_: id 0 | task 4987 | processing task, is_child = 0 28.02.283.467 I slot print_timing: id 3 | task 4895 | n_gen = 100, tg = 3.37 t/s, tg_3s = 3.41 t/s 28.05.496.731 I slot print_timing: id 3 | task 4895 | n_gen = 114, tg = 3.47 t/s, tg_3s = 4.36 t/s 28.08.711.819 I slot print_timing: id 3 | task 4895 | n_gen = 128, tg = 3.55 t/s, tg_3s = 4.35 t/s 28.11.237.094 I slot print_timing: id 2 | task 4935 | n_gen = 100, tg = 3.74 t/s, tg_3s = 3.77 t/s 28.11.926.306 I slot print_timing: id 3 | task 4895 | n_gen = 142, tg = 3.62 t/s, tg_3s = 4.36 t/s 28.14.451.655 I slot print_timing: id 2 | task 4935 | n_gen = 114, tg = 3.80 t/s, tg_3s = 4.36 t/s 28.15.140.457 I slot print_timing: id 3 | task 4895 | n_gen = 156, tg = 3.67 t/s, tg_3s = 4.36 t/s 28.17.667.503 I slot print_timing: id 2 | task 4935 | n_gen = 128, tg = 3.86 t/s, tg_3s = 4.35 t/s 28.18.354.874 I slot print_timing: id 3 | task 4895 | n_gen = 170, tg = 3.72 t/s, tg_3s = 4.36 t/s 28.20.880.863 I slot print_timing: id 2 | task 4935 | n_gen = 142, tg = 3.90 t/s, tg_3s = 4.36 t/s 28.21.570.103 I slot print_timing: id 3 | task 4895 | n_gen = 184, tg = 3.76 t/s, tg_3s = 4.35 t/s 28.22.258.492 I slot print_timing: id 1 | task 4984 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 28.22.717.868 I slot print_timing: id 0 | task 4987 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 28.24.095.857 I slot print_timing: id 2 | task 4935 | n_gen = 156, tg = 3.94 t/s, tg_3s = 4.35 t/s 28.24.785.364 I slot print_timing: id 3 | task 4895 | n_gen = 198, tg = 3.80 t/s, tg_3s = 4.35 t/s 28.25.474.041 I slot print_timing: id 1 | task 4984 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 28.25.933.111 I slot print_timing: id 0 | task 4987 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 28.27.312.201 I slot print_timing: id 2 | task 4935 | n_gen = 170, tg = 3.97 t/s, tg_3s = 4.35 t/s 28.28.003.139 I slot print_timing: id 3 | task 4895 | n_gen = 212, tg = 3.83 t/s, tg_3s = 4.35 t/s 28.28.691.459 I slot print_timing: id 1 | task 4984 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 28.28.920.950 I slot print_timing: id 0 | task 4987 | prompt eval time = 2199.11 ms / 104 tokens ( 21.15 ms per token, 47.29 tokens per second) 28.28.920.957 I slot print_timing: id 0 | task 4987 | eval time = 28937.31 ms / 127 tokens ( 229.66 ms per token, 4.35 tokens per second) 28.28.920.957 I slot print_timing: id 0 | task 4987 | total time = 31136.41 ms / 231 tokens 28.28.920.958 I slot print_timing: id 0 | task 4987 | graphs reused = 4432 28.28.920.958 I slot print_timing: id 0 | task 4987 | graph reallocs = 0 / 0 (same size) / (changed size) 28.28.921.015 I slot release: id 0 | task 4987 | stop processing: n_tokens = 1355, truncated = 0 28.29.141.023 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.846 28.29.141.072 I slot launch_slot_: id 0 | task 5117 | processing task, is_child = 0 28.30.910.409 I slot print_timing: id 2 | task 4935 | n_gen = 179, tg = 3.86 t/s, tg_3s = 2.50 t/s 28.31.333.009 I slot print_timing: id 3 | task 4895 | n_gen = 219, tg = 3.73 t/s, tg_3s = 2.10 t/s 28.31.794.398 I slot print_timing: id 1 | task 4984 | n_gen = 134, tg = 3.91 t/s, tg_3s = 1.93 t/s 28.34.091.254 I slot print_timing: id 2 | task 4935 | n_gen = 192, tg = 3.87 t/s, tg_3s = 4.09 t/s 28.34.550.850 I slot print_timing: id 3 | task 4895 | n_gen = 233, tg = 3.77 t/s, tg_3s = 4.35 t/s 28.35.010.067 I slot print_timing: id 1 | task 4984 | n_gen = 148, tg = 3.95 t/s, tg_3s = 4.35 t/s 28.37.308.091 I slot print_timing: id 2 | task 4935 | n_gen = 206, tg = 3.90 t/s, tg_3s = 4.35 t/s 28.37.768.004 I slot print_timing: id 3 | task 4895 | n_gen = 247, tg = 3.79 t/s, tg_3s = 4.35 t/s 28.38.227.240 I slot print_timing: id 1 | task 4984 | n_gen = 162, tg = 3.98 t/s, tg_3s = 4.35 t/s 28.40.523.826 I slot print_timing: id 2 | task 4935 | n_gen = 220, tg = 3.93 t/s, tg_3s = 4.35 t/s 28.40.983.493 I slot print_timing: id 3 | task 4895 | n_gen = 261, tg = 3.82 t/s, tg_3s = 4.35 t/s 28.41.443.189 I slot print_timing: id 1 | task 4984 | n_gen = 176, tg = 4.01 t/s, tg_3s = 4.35 t/s 28.43.739.302 I slot print_timing: id 2 | task 4935 | n_gen = 234, tg = 3.95 t/s, tg_3s = 4.35 t/s 28.44.199.021 I slot print_timing: id 3 | task 4895 | n_gen = 275, tg = 3.85 t/s, tg_3s = 4.35 t/s 28.44.658.129 I slot print_timing: id 1 | task 4984 | n_gen = 190, tg = 4.03 t/s, tg_3s = 4.35 t/s 28.46.956.797 I slot print_timing: id 2 | task 4935 | n_gen = 248, tg = 3.97 t/s, tg_3s = 4.35 t/s 28.47.416.616 I slot print_timing: id 3 | task 4895 | n_gen = 289, tg = 3.87 t/s, tg_3s = 4.35 t/s 28.47.876.042 I slot print_timing: id 1 | task 4984 | n_gen = 204, tg = 4.05 t/s, tg_3s = 4.35 t/s 28.50.173.799 I slot print_timing: id 2 | task 4935 | n_gen = 262, tg = 3.99 t/s, tg_3s = 4.35 t/s 28.50.633.587 I slot print_timing: id 3 | task 4895 | n_gen = 303, tg = 3.89 t/s, tg_3s = 4.35 t/s 28.51.092.829 I slot print_timing: id 1 | task 4984 | n_gen = 218, tg = 4.07 t/s, tg_3s = 4.35 t/s 28.53.392.090 I slot print_timing: id 2 | task 4935 | n_gen = 276, tg = 4.01 t/s, tg_3s = 4.35 t/s 28.53.852.132 I slot print_timing: id 3 | task 4895 | n_gen = 317, tg = 3.91 t/s, tg_3s = 4.35 t/s 28.54.081.533 I slot print_timing: id 0 | task 5117 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 28.54.311.472 I slot print_timing: id 1 | task 4984 | n_gen = 232, tg = 4.09 t/s, tg_3s = 4.35 t/s 28.56.610.510 I slot print_timing: id 2 | task 4935 | n_gen = 290, tg = 4.02 t/s, tg_3s = 4.35 t/s 28.57.070.359 I slot print_timing: id 3 | task 4895 | n_gen = 331, tg = 3.92 t/s, tg_3s = 4.35 t/s 28.57.300.824 I slot print_timing: id 0 | task 5117 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 28.57.530.941 I slot print_timing: id 1 | task 4984 | n_gen = 246, tg = 4.10 t/s, tg_3s = 4.35 t/s 28.59.829.431 I slot print_timing: id 2 | task 4935 | n_gen = 304, tg = 4.04 t/s, tg_3s = 4.35 t/s 29.00.289.287 I slot print_timing: id 3 | task 4895 | n_gen = 345, tg = 3.94 t/s, tg_3s = 4.35 t/s 29.00.518.728 I slot print_timing: id 0 | task 5117 | n_gen = 128, tg = 4.35 t/s, tg_3s = 4.35 t/s 29.00.748.897 I slot print_timing: id 1 | task 4984 | n_gen = 260, tg = 4.11 t/s, tg_3s = 4.35 t/s 29.03.049.473 I slot print_timing: id 2 | task 4935 | n_gen = 318, tg = 4.05 t/s, tg_3s = 4.35 t/s 29.03.509.582 I slot print_timing: id 3 | task 4895 | n_gen = 359, tg = 3.95 t/s, tg_3s = 4.35 t/s 29.03.739.236 I slot print_timing: id 0 | task 5117 | n_gen = 142, tg = 4.35 t/s, tg_3s = 4.35 t/s 29.03.739.678 I slot print_timing: id 3 | task 4895 | prompt eval time = 2235.74 ms / 122 tokens ( 18.33 ms per token, 54.57 tokens per second) 29.03.739.681 I slot print_timing: id 3 | task 4895 | eval time = 90796.37 ms / 360 tokens ( 252.91 ms per token, 3.95 tokens per second) 29.03.739.682 I slot print_timing: id 3 | task 4895 | total time = 93032.10 ms / 482 tokens 29.03.739.682 I slot print_timing: id 3 | task 4895 | graphs reused = 4572 29.03.739.682 I slot print_timing: id 3 | task 4895 | graph reallocs = 0 / 0 (same size) / (changed size) 29.03.739.732 I slot release: id 3 | task 4895 | stop processing: n_tokens = 1606, truncated = 0 29.03.957.481 I slot print_timing: id 1 | task 4984 | n_gen = 274, tg = 4.13 t/s, tg_3s = 4.36 t/s 29.03.957.639 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.714 29.03.957.670 I slot launch_slot_: id 3 | task 5262 | processing task, is_child = 0 29.06.193.594 I slot print_timing: id 2 | task 4935 | n_gen = 324, tg = 3.97 t/s, tg_3s = 1.91 t/s 29.06.886.808 I slot print_timing: id 0 | task 5117 | n_gen = 148, tg = 4.13 t/s, tg_3s = 1.91 t/s 29.07.116.699 I slot print_timing: id 1 | task 4984 | n_gen = 280, tg = 4.02 t/s, tg_3s = 1.90 t/s 29.09.414.585 I slot print_timing: id 2 | task 4935 | n_gen = 338, tg = 3.98 t/s, tg_3s = 4.35 t/s 29.10.102.752 I slot print_timing: id 0 | task 5117 | n_gen = 162, tg = 4.15 t/s, tg_3s = 4.35 t/s 29.10.332.742 I slot print_timing: id 1 | task 4984 | n_gen = 294, tg = 4.04 t/s, tg_3s = 4.35 t/s 29.12.631.565 I slot print_timing: id 2 | task 4935 | n_gen = 352, tg = 3.99 t/s, tg_3s = 4.35 t/s 29.13.321.974 I slot print_timing: id 0 | task 5117 | n_gen = 176, tg = 4.17 t/s, tg_3s = 4.35 t/s 29.13.551.849 I slot print_timing: id 1 | task 4984 | n_gen = 308, tg = 4.05 t/s, tg_3s = 4.35 t/s 29.15.850.775 I slot print_timing: id 2 | task 4935 | n_gen = 366, tg = 4.01 t/s, tg_3s = 4.35 t/s 29.16.540.240 I slot print_timing: id 0 | task 5117 | n_gen = 190, tg = 4.18 t/s, tg_3s = 4.35 t/s 29.16.770.197 I slot print_timing: id 1 | task 4984 | n_gen = 322, tg = 4.06 t/s, tg_3s = 4.35 t/s 29.19.071.402 I slot print_timing: id 2 | task 4935 | n_gen = 380, tg = 4.02 t/s, tg_3s = 4.35 t/s 29.19.761.916 I slot print_timing: id 0 | task 5117 | n_gen = 204, tg = 4.19 t/s, tg_3s = 4.35 t/s 29.19.991.739 I slot print_timing: id 1 | task 4984 | n_gen = 336, tg = 4.08 t/s, tg_3s = 4.35 t/s 29.22.292.789 I slot print_timing: id 2 | task 4935 | n_gen = 394, tg = 4.03 t/s, tg_3s = 4.35 t/s 29.22.522.552 I slot print_timing: id 1 | task 4984 | prompt eval time = 2370.63 ms / 117 tokens ( 20.26 ms per token, 49.35 tokens per second) 29.22.522.557 I slot print_timing: id 1 | task 4984 | eval time = 84738.35 ms / 347 tokens ( 244.91 ms per token, 4.08 tokens per second) 29.22.522.557 I slot print_timing: id 1 | task 4984 | total time = 87108.98 ms / 464 tokens 29.22.522.558 I slot print_timing: id 1 | task 4984 | graphs reused = 4642 29.22.522.558 I slot print_timing: id 1 | task 4984 | graph reallocs = 0 / 0 (same size) / (changed size) 29.22.522.604 I slot release: id 1 | task 4984 | stop processing: n_tokens = 1588, truncated = 0 29.22.851.164 I slot print_timing: id 0 | task 5117 | n_gen = 217, tg = 4.19 t/s, tg_3s = 4.21 t/s 29.22.851.471 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.722 29.22.851.507 I slot launch_slot_: id 1 | task 5337 | processing task, is_child = 0 29.25.417.307 I slot print_timing: id 2 | task 4935 | n_gen = 398, tg = 3.94 t/s, tg_3s = 1.28 t/s 29.25.879.094 I slot print_timing: id 0 | task 5117 | n_gen = 221, tg = 4.03 t/s, tg_3s = 1.32 t/s 29.28.638.871 I slot print_timing: id 2 | task 4935 | n_gen = 412, tg = 3.96 t/s, tg_3s = 4.35 t/s 29.29.098.255 I slot print_timing: id 0 | task 5117 | n_gen = 235, tg = 4.05 t/s, tg_3s = 4.35 t/s 29.29.557.998 I slot print_timing: id 0 | task 5117 | prompt eval time = 2191.48 ms / 108 tokens ( 20.29 ms per token, 49.28 tokens per second) 29.29.558.003 I slot print_timing: id 0 | task 5117 | eval time = 58225.44 ms / 237 tokens ( 246.72 ms per token, 4.05 tokens per second) 29.29.558.004 I slot print_timing: id 0 | task 5117 | total time = 60416.92 ms / 345 tokens 29.29.558.004 I slot print_timing: id 0 | task 5117 | graphs reused = 4659 29.29.558.005 I slot print_timing: id 0 | task 5117 | graph reallocs = 0 / 0 (same size) / (changed size) 29.29.558.051 I slot release: id 0 | task 5117 | stop processing: n_tokens = 1469, truncated = 0 29.29.776.430 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.780 29.29.776.466 I slot launch_slot_: id 0 | task 5359 | processing task, is_child = 0 29.31.973.931 I slot print_timing: id 2 | task 4935 | n_gen = 419, tg = 3.90 t/s, tg_3s = 2.10 t/s 29.32.895.439 I slot print_timing: id 3 | task 5262 | n_gen = 100, tg = 3.71 t/s, tg_3s = 3.75 t/s 29.35.191.779 I slot print_timing: id 2 | task 4935 | n_gen = 433, tg = 3.91 t/s, tg_3s = 4.35 t/s 29.35.651.106 I slot print_timing: id 2 | task 4935 | prompt eval time = 3192.56 ms / 166 tokens ( 19.23 ms per token, 52.00 tokens per second) 29.35.651.111 I slot print_timing: id 2 | task 4935 | eval time = 110912.72 ms / 435 tokens ( 255.56 ms per token, 3.91 tokens per second) 29.35.651.112 I slot print_timing: id 2 | task 4935 | total time = 114105.27 ms / 601 tokens 29.35.651.113 I slot print_timing: id 2 | task 4935 | graphs reused = 4675 29.35.651.113 I slot print_timing: id 2 | task 4935 | graph reallocs = 0 / 0 (same size) / (changed size) 29.35.651.164 I slot release: id 2 | task 4935 | stop processing: n_tokens = 1725, truncated = 0 29.35.979.538 I slot print_timing: id 3 | task 5262 | n_gen = 113, tg = 3.76 t/s, tg_3s = 4.22 t/s 29.35.979.543 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.664 29.35.979.579 I slot launch_slot_: id 2 | task 5379 | processing task, is_child = 0 29.39.120.126 I slot print_timing: id 3 | task 5262 | n_gen = 118, tg = 3.55 t/s, tg_3s = 1.59 t/s 29.42.334.401 I slot print_timing: id 3 | task 5262 | n_gen = 132, tg = 3.62 t/s, tg_3s = 4.36 t/s 29.45.550.411 I slot print_timing: id 3 | task 5262 | n_gen = 146, tg = 3.68 t/s, tg_3s = 4.35 t/s 29.48.766.560 I slot print_timing: id 3 | task 5262 | n_gen = 160, tg = 3.73 t/s, tg_3s = 4.35 t/s 29.51.983.376 I slot print_timing: id 1 | task 5337 | n_gen = 100, tg = 3.73 t/s, tg_3s = 3.76 t/s 29.51.983.665 I slot print_timing: id 3 | task 5262 | n_gen = 174, tg = 3.78 t/s, tg_3s = 4.35 t/s 29.55.198.066 I slot print_timing: id 1 | task 5337 | n_gen = 114, tg = 3.79 t/s, tg_3s = 4.36 t/s 29.55.198.351 I slot print_timing: id 3 | task 5262 | n_gen = 188, tg = 3.82 t/s, tg_3s = 4.36 t/s 29.55.887.137 I slot print_timing: id 0 | task 5359 | prompt eval time = 2197.18 ms / 116 tokens ( 18.94 ms per token, 52.79 tokens per second) 29.55.887.142 I slot print_timing: id 0 | task 5359 | eval time = 23913.48 ms / 96 tokens ( 251.72 ms per token, 3.97 tokens per second) 29.55.887.142 I slot print_timing: id 0 | task 5359 | total time = 26110.66 ms / 212 tokens 29.55.887.143 I slot print_timing: id 0 | task 5359 | graphs reused = 4750 29.55.887.143 I slot print_timing: id 0 | task 5359 | graph reallocs = 0 / 0 (same size) / (changed size) 29.55.887.200 I slot release: id 0 | task 5359 | stop processing: n_tokens = 1336, truncated = 0 29.56.106.051 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.858 29.56.106.081 I slot launch_slot_: id 0 | task 5459 | processing task, is_child = 0 29.58.309.545 I slot print_timing: id 1 | task 5337 | n_gen = 120, tg = 3.62 t/s, tg_3s = 1.93 t/s 29.58.309.830 I slot print_timing: id 3 | task 5262 | n_gen = 194, tg = 3.70 t/s, tg_3s = 1.93 t/s 30.01.528.437 I slot print_timing: id 1 | task 5337 | n_gen = 134, tg = 3.68 t/s, tg_3s = 4.35 t/s 30.01.528.702 I slot print_timing: id 3 | task 5262 | n_gen = 208, tg = 3.74 t/s, tg_3s = 4.35 t/s 30.02.906.343 I slot print_timing: id 2 | task 5379 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.09 t/s 30.04.743.040 I slot print_timing: id 1 | task 5337 | n_gen = 148, tg = 3.74 t/s, tg_3s = 4.36 t/s 30.04.743.339 I slot print_timing: id 3 | task 5262 | n_gen = 222, tg = 3.77 t/s, tg_3s = 4.36 t/s 30.05.431.883 I slot print_timing: id 1 | task 5337 | prompt eval time = 2565.65 ms / 112 tokens ( 22.91 ms per token, 43.65 tokens per second) 30.05.431.886 I slot print_timing: id 1 | task 5337 | eval time = 40014.72 ms / 151 tokens ( 266.76 ms per token, 3.75 tokens per second) 30.05.431.887 I slot print_timing: id 1 | task 5337 | total time = 42580.37 ms / 263 tokens 30.05.431.887 I slot print_timing: id 1 | task 5337 | graphs reused = 4781 30.05.431.888 I slot print_timing: id 1 | task 5337 | graph reallocs = 0 / 0 (same size) / (changed size) 30.05.431.943 I slot release: id 1 | task 5337 | stop processing: n_tokens = 1387, truncated = 0 30.05.760.551 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.826 30.05.760.591 I slot launch_slot_: id 1 | task 5494 | processing task, is_child = 0 30.07.711.621 I slot print_timing: id 2 | task 5379 | n_gen = 113, tg = 3.82 t/s, tg_3s = 2.71 t/s 30.08.316.996 I slot print_timing: id 3 | task 5262 | n_gen = 228, tg = 3.65 t/s, tg_3s = 1.68 t/s 30.10.844.498 I slot print_timing: id 2 | task 5379 | n_gen = 125, tg = 3.83 t/s, tg_3s = 3.83 t/s 30.11.534.037 I slot print_timing: id 3 | task 5262 | n_gen = 242, tg = 3.69 t/s, tg_3s = 4.35 t/s 30.14.061.584 I slot print_timing: id 2 | task 5379 | n_gen = 139, tg = 3.87 t/s, tg_3s = 4.35 t/s 30.14.750.501 I slot print_timing: id 3 | task 5262 | n_gen = 256, tg = 3.72 t/s, tg_3s = 4.35 t/s 30.17.278.155 I slot print_timing: id 2 | task 5379 | n_gen = 153, tg = 3.91 t/s, tg_3s = 4.35 t/s 30.17.967.044 I slot print_timing: id 3 | task 5262 | n_gen = 270, tg = 3.75 t/s, tg_3s = 4.35 t/s 30.20.495.724 I slot print_timing: id 2 | task 5379 | n_gen = 167, tg = 3.95 t/s, tg_3s = 4.35 t/s 30.21.184.956 I slot print_timing: id 3 | task 5262 | n_gen = 284, tg = 3.77 t/s, tg_3s = 4.35 t/s 30.23.252.038 I slot print_timing: id 0 | task 5459 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 30.23.252.433 I slot print_timing: id 3 | task 5262 | prompt eval time = 2236.10 ms / 133 tokens ( 16.81 ms per token, 59.48 tokens per second) 30.23.252.437 I slot print_timing: id 3 | task 5262 | eval time = 77058.66 ms / 293 tokens ( 263.90 ms per token, 3.79 tokens per second) 30.23.252.438 I slot print_timing: id 3 | task 5262 | total time = 79294.76 ms / 426 tokens 30.23.252.438 I slot print_timing: id 3 | task 5262 | graphs reused = 4844 30.23.252.439 I slot print_timing: id 3 | task 5262 | graph reallocs = 0 / 0 (same size) / (changed size) 30.23.252.482 I slot release: id 3 | task 5262 | stop processing: n_tokens = 1550, truncated = 0 30.23.470.354 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.739 30.23.470.383 I slot launch_slot_: id 3 | task 5563 | processing task, is_child = 0 30.25.268.825 I slot print_timing: id 2 | task 5379 | n_gen = 181, tg = 3.84 t/s, tg_3s = 2.93 t/s 30.26.393.697 I slot print_timing: id 0 | task 5459 | n_gen = 106, tg = 3.74 t/s, tg_3s = 1.91 t/s 30.28.460.383 I slot print_timing: id 2 | task 5379 | n_gen = 194, tg = 3.86 t/s, tg_3s = 4.07 t/s 30.29.608.449 I slot print_timing: id 0 | task 5459 | n_gen = 120, tg = 3.80 t/s, tg_3s = 4.35 t/s 30.30.756.870 I slot print_timing: id 1 | task 5494 | prompt eval time = 2556.12 ms / 103 tokens ( 24.82 ms per token, 40.30 tokens per second) 30.30.756.876 I slot print_timing: id 1 | task 5494 | eval time = 22440.15 ms / 91 tokens ( 249.34 ms per token, 4.01 tokens per second) 30.30.756.876 I slot print_timing: id 1 | task 5494 | total time = 24996.27 ms / 194 tokens 30.30.756.877 I slot print_timing: id 1 | task 5494 | graphs reused = 4865 30.30.756.877 I slot print_timing: id 1 | task 5494 | graph reallocs = 0 / 0 (same size) / (changed size) 30.30.756.922 I slot release: id 1 | task 5494 | stop processing: n_tokens = 1318, truncated = 0 30.31.085.439 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.869 30.31.085.474 I slot launch_slot_: id 1 | task 5589 | processing task, is_child = 0 30.33.036.952 I slot print_timing: id 0 | task 5459 | n_gen = 127, tg = 3.63 t/s, tg_3s = 2.04 t/s 30.33.037.107 I slot print_timing: id 2 | task 5379 | n_gen = 206, tg = 3.75 t/s, tg_3s = 2.62 t/s 30.36.170.589 I slot print_timing: id 0 | task 5459 | n_gen = 139, tg = 3.64 t/s, tg_3s = 3.83 t/s 30.36.170.876 I slot print_timing: id 2 | task 5379 | n_gen = 218, tg = 3.76 t/s, tg_3s = 3.83 t/s 30.39.385.271 I slot print_timing: id 0 | task 5459 | n_gen = 153, tg = 3.70 t/s, tg_3s = 4.36 t/s 30.39.385.535 I slot print_timing: id 2 | task 5379 | n_gen = 232, tg = 3.79 t/s, tg_3s = 4.36 t/s 30.42.600.323 I slot print_timing: id 0 | task 5459 | n_gen = 167, tg = 3.75 t/s, tg_3s = 4.35 t/s 30.42.600.593 I slot print_timing: id 2 | task 5379 | n_gen = 246, tg = 3.82 t/s, tg_3s = 4.35 t/s 30.43.060.143 I slot print_timing: id 2 | task 5379 | prompt eval time = 2449.57 ms / 119 tokens ( 20.58 ms per token, 48.58 tokens per second) 30.43.060.148 I slot print_timing: id 2 | task 5379 | eval time = 64630.99 ms / 248 tokens ( 261.66 ms per token, 3.82 tokens per second) 30.43.060.148 I slot print_timing: id 2 | task 5379 | total time = 67080.56 ms / 367 tokens 30.43.060.149 I slot print_timing: id 2 | task 5379 | graphs reused = 4905 30.43.060.149 I slot print_timing: id 2 | task 5379 | graph reallocs = 0 / 0 (same size) / (changed size) 30.43.060.880 I slot release: id 2 | task 5379 | stop processing: n_tokens = 1491, truncated = 0 30.43.389.819 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.769 30.43.389.850 I slot launch_slot_: id 2 | task 5634 | processing task, is_child = 0 30.45.725.769 I slot print_timing: id 0 | task 5459 | n_gen = 173, tg = 3.63 t/s, tg_3s = 1.92 t/s 30.48.940.285 I slot print_timing: id 0 | task 5459 | n_gen = 187, tg = 3.67 t/s, tg_3s = 4.36 t/s 30.51.466.565 I slot print_timing: id 3 | task 5563 | prompt eval time = 2232.52 ms / 120 tokens ( 18.60 ms per token, 53.75 tokens per second) 30.51.466.571 I slot print_timing: id 3 | task 5563 | eval time = 25763.65 ms / 96 tokens ( 271.20 ms per token, 3.69 tokens per second) 30.51.466.572 I slot print_timing: id 3 | task 5563 | total time = 27996.18 ms / 216 tokens 30.51.466.572 I slot print_timing: id 3 | task 5563 | graphs reused = 4930 30.51.466.573 I slot print_timing: id 3 | task 5563 | graph reallocs = 0 / 0 (same size) / (changed size) 30.51.466.678 I slot release: id 3 | task 5563 | stop processing: n_tokens = 1340, truncated = 0 30.51.684.495 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.855 30.51.684.529 I slot launch_slot_: id 3 | task 5664 | processing task, is_child = 0 30.53.139.646 I slot print_timing: id 0 | task 5459 | n_gen = 200, tg = 3.63 t/s, tg_3s = 3.10 t/s 30.56.334.611 I slot print_timing: id 0 | task 5459 | n_gen = 213, tg = 3.65 t/s, tg_3s = 4.07 t/s 30.57.711.934 I slot print_timing: id 0 | task 5459 | prompt eval time = 2203.33 ms / 119 tokens ( 18.52 ms per token, 54.01 tokens per second) 30.57.711.936 I slot print_timing: id 0 | task 5459 | eval time = 59402.52 ms / 219 tokens ( 272.49 ms per token, 3.67 tokens per second) 30.57.711.937 I slot print_timing: id 0 | task 5459 | total time = 61605.85 ms / 338 tokens 30.57.711.937 I slot print_timing: id 0 | task 5459 | graphs reused = 4947 30.57.711.938 I slot print_timing: id 0 | task 5459 | graph reallocs = 0 / 0 (same size) / (changed size) 30.57.711.980 I slot release: id 0 | task 5459 | stop processing: n_tokens = 1462, truncated = 0 30.57.930.866 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.784 30.57.930.896 I slot launch_slot_: id 0 | task 5686 | processing task, is_child = 0 31.02.026.319 I slot print_timing: id 1 | task 5589 | n_gen = 100, tg = 3.49 t/s, tg_3s = 3.52 t/s 31.05.240.077 I slot print_timing: id 1 | task 5589 | n_gen = 114, tg = 3.58 t/s, tg_3s = 4.36 t/s 31.08.455.799 I slot print_timing: id 1 | task 5589 | n_gen = 128, tg = 3.65 t/s, tg_3s = 4.35 t/s 31.11.671.624 I slot print_timing: id 1 | task 5589 | n_gen = 142, tg = 3.71 t/s, tg_3s = 4.35 t/s 31.12.131.225 I slot print_timing: id 2 | task 5634 | n_gen = 100, tg = 3.72 t/s, tg_3s = 3.75 t/s 31.13.969.589 I slot print_timing: id 3 | task 5664 | prompt eval time = 1890.79 ms / 100 tokens ( 18.91 ms per token, 52.89 tokens per second) 31.13.969.592 I slot print_timing: id 3 | task 5664 | eval time = 20394.26 ms / 79 tokens ( 261.46 ms per token, 3.82 tokens per second) 31.13.969.594 I slot print_timing: id 3 | task 5664 | total time = 22285.06 ms / 179 tokens 31.13.969.594 I slot print_timing: id 3 | task 5664 | graphs reused = 5004 31.13.969.595 I slot print_timing: id 3 | task 5664 | graph reallocs = 0 / 0 (same size) / (changed size) 31.13.969.643 I slot release: id 3 | task 5664 | stop processing: n_tokens = 1303, truncated = 0 31.14.187.916 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.880 31.14.187.946 I slot launch_slot_: id 3 | task 5747 | processing task, is_child = 0 31.15.983.898 I slot print_timing: id 1 | task 5589 | n_gen = 154, tg = 3.61 t/s, tg_3s = 2.78 t/s 31.15.984.064 I slot print_timing: id 2 | task 5634 | n_gen = 110, tg = 3.57 t/s, tg_3s = 2.60 t/s 31.19.175.750 I slot print_timing: id 1 | task 5589 | n_gen = 167, tg = 3.65 t/s, tg_3s = 4.07 t/s 31.19.175.912 I slot print_timing: id 2 | task 5634 | n_gen = 123, tg = 3.62 t/s, tg_3s = 4.07 t/s 31.22.391.090 I slot print_timing: id 1 | task 5589 | n_gen = 181, tg = 3.69 t/s, tg_3s = 4.35 t/s 31.22.391.245 I slot print_timing: id 2 | task 5634 | n_gen = 137, tg = 3.69 t/s, tg_3s = 4.35 t/s 31.25.376.728 I slot print_timing: id 0 | task 5686 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 31.25.606.778 I slot print_timing: id 1 | task 5589 | n_gen = 195, tg = 3.73 t/s, tg_3s = 4.35 t/s 31.25.606.925 I slot print_timing: id 2 | task 5634 | n_gen = 151, tg = 3.74 t/s, tg_3s = 4.35 t/s 31.28.593.962 I slot print_timing: id 0 | task 5686 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 31.28.823.895 I slot print_timing: id 1 | task 5589 | n_gen = 209, tg = 3.77 t/s, tg_3s = 4.35 t/s 31.28.824.046 I slot print_timing: id 2 | task 5634 | n_gen = 165, tg = 3.78 t/s, tg_3s = 4.35 t/s 31.31.811.624 I slot print_timing: id 0 | task 5686 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 31.32.041.939 I slot print_timing: id 1 | task 5589 | n_gen = 223, tg = 3.80 t/s, tg_3s = 4.35 t/s 31.32.042.082 I slot print_timing: id 2 | task 5634 | n_gen = 179, tg = 3.82 t/s, tg_3s = 4.35 t/s 31.33.879.111 I slot print_timing: id 2 | task 5634 | prompt eval time = 2104.27 ms / 97 tokens ( 21.69 ms per token, 46.10 tokens per second) 31.33.879.114 I slot print_timing: id 2 | task 5634 | eval time = 48384.98 ms / 187 tokens ( 260.13 ms per token, 3.84 tokens per second) 31.33.879.115 I slot print_timing: id 2 | task 5634 | total time = 50489.25 ms / 284 tokens 31.33.879.116 I slot print_timing: id 2 | task 5634 | graphs reused = 5079 31.33.879.116 I slot print_timing: id 2 | task 5634 | graph reallocs = 0 / 0 (same size) / (changed size) 31.33.879.161 I slot release: id 2 | task 5634 | stop processing: n_tokens = 1408, truncated = 0 31.34.207.852 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.814 31.34.207.890 I slot launch_slot_: id 2 | task 5827 | processing task, is_child = 0 31.36.105.625 I slot print_timing: id 0 | task 5686 | n_gen = 139, tg = 3.92 t/s, tg_3s = 2.56 t/s 31.36.105.812 I slot print_timing: id 1 | task 5589 | n_gen = 233, tg = 3.71 t/s, tg_3s = 2.46 t/s 31.39.184.015 I slot print_timing: id 0 | task 5686 | n_gen = 151, tg = 3.92 t/s, tg_3s = 3.90 t/s 31.39.184.177 I slot print_timing: id 1 | task 5589 | n_gen = 245, tg = 3.72 t/s, tg_3s = 3.90 t/s 31.39.643.110 I slot print_timing: id 1 | task 5589 | prompt eval time = 2557.05 ms / 108 tokens ( 23.68 ms per token, 42.24 tokens per second) 31.39.643.114 I slot print_timing: id 1 | task 5589 | eval time = 66000.58 ms / 247 tokens ( 268.30 ms per token, 3.73 tokens per second) 31.39.643.115 I slot print_timing: id 1 | task 5589 | total time = 68557.63 ms / 355 tokens 31.39.643.115 I slot print_timing: id 1 | task 5589 | graphs reused = 5091 31.39.643.115 I slot print_timing: id 1 | task 5589 | graph reallocs = 0 / 0 (same size) / (changed size) 31.39.643.162 I slot release: id 1 | task 5589 | stop processing: n_tokens = 1479, truncated = 0 31.39.971.591 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.775 31.39.971.629 I slot launch_slot_: id 1 | task 5844 | processing task, is_child = 0 31.42.527.948 I slot print_timing: id 0 | task 5686 | n_gen = 156, tg = 3.72 t/s, tg_3s = 1.50 t/s 31.43.447.894 I slot print_timing: id 3 | task 5747 | n_gen = 100, tg = 3.66 t/s, tg_3s = 3.70 t/s 31.45.742.547 I slot print_timing: id 0 | task 5686 | n_gen = 170, tg = 3.77 t/s, tg_3s = 4.36 t/s 31.46.661.338 I slot print_timing: id 3 | task 5747 | n_gen = 114, tg = 3.74 t/s, tg_3s = 4.36 t/s 31.48.958.260 I slot print_timing: id 0 | task 5686 | n_gen = 184, tg = 3.81 t/s, tg_3s = 4.35 t/s 31.49.876.890 I slot print_timing: id 3 | task 5747 | n_gen = 128, tg = 3.80 t/s, tg_3s = 4.35 t/s 31.52.172.853 I slot print_timing: id 0 | task 5686 | n_gen = 198, tg = 3.84 t/s, tg_3s = 4.36 t/s 31.53.091.717 I slot print_timing: id 3 | task 5747 | n_gen = 142, tg = 3.84 t/s, tg_3s = 4.35 t/s 31.55.388.140 I slot print_timing: id 0 | task 5686 | n_gen = 212, tg = 3.87 t/s, tg_3s = 4.35 t/s 31.56.307.377 I slot print_timing: id 3 | task 5747 | n_gen = 156, tg = 3.89 t/s, tg_3s = 4.35 t/s 31.58.603.964 I slot print_timing: id 0 | task 5686 | n_gen = 226, tg = 3.90 t/s, tg_3s = 4.35 t/s 31.59.523.201 I slot print_timing: id 3 | task 5747 | n_gen = 170, tg = 3.92 t/s, tg_3s = 4.35 t/s 32.01.591.474 I slot print_timing: id 2 | task 5827 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 32.01.821.033 I slot print_timing: id 0 | task 5686 | n_gen = 240, tg = 3.92 t/s, tg_3s = 4.35 t/s 32.02.743.207 I slot print_timing: id 3 | task 5747 | n_gen = 184, tg = 3.95 t/s, tg_3s = 4.35 t/s 32.03.203.506 I slot print_timing: id 3 | task 5747 | prompt eval time = 2229.66 ms / 119 tokens ( 18.74 ms per token, 53.37 tokens per second) 32.03.203.509 I slot print_timing: id 3 | task 5747 | eval time = 46785.90 ms / 186 tokens ( 252.90 ms per token, 3.95 tokens per second) 32.03.203.509 I slot print_timing: id 3 | task 5747 | total time = 49015.55 ms / 305 tokens 32.03.203.510 I slot print_timing: id 3 | task 5747 | graphs reused = 5179 32.03.203.510 I slot print_timing: id 3 | task 5747 | graph reallocs = 0 / 0 (same size) / (changed size) 32.03.203.568 I slot release: id 3 | task 5747 | stop processing: n_tokens = 1429, truncated = 0 32.03.421.287 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.802 32.03.421.321 I slot launch_slot_: id 3 | task 5938 | processing task, is_child = 0 32.05.211.981 I slot print_timing: id 0 | task 5686 | n_gen = 248, tg = 3.84 t/s, tg_3s = 2.36 t/s 32.05.212.459 I slot print_timing: id 2 | task 5827 | n_gen = 109, tg = 3.78 t/s, tg_3s = 2.49 t/s 32.07.027.529 I slot print_timing: id 1 | task 5844 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 32.08.405.660 I slot print_timing: id 0 | task 5686 | n_gen = 261, tg = 3.85 t/s, tg_3s = 4.07 t/s 32.08.405.926 I slot print_timing: id 2 | task 5827 | n_gen = 122, tg = 3.81 t/s, tg_3s = 4.07 t/s 32.10.244.476 I slot print_timing: id 1 | task 5844 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 32.11.624.257 I slot print_timing: id 0 | task 5686 | n_gen = 275, tg = 3.87 t/s, tg_3s = 4.35 t/s 32.11.624.536 I slot print_timing: id 2 | task 5827 | n_gen = 136, tg = 3.86 t/s, tg_3s = 4.35 t/s 32.13.462.462 I slot print_timing: id 1 | task 5844 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 32.14.841.310 I slot print_timing: id 0 | task 5686 | n_gen = 289, tg = 3.89 t/s, tg_3s = 4.35 t/s 32.14.841.598 I slot print_timing: id 2 | task 5827 | n_gen = 150, tg = 3.90 t/s, tg_3s = 4.35 t/s 32.15.301.139 I slot print_timing: id 2 | task 5827 | prompt eval time = 2441.49 ms / 114 tokens ( 21.42 ms per token, 46.69 tokens per second) 32.15.301.146 I slot print_timing: id 2 | task 5827 | eval time = 38651.75 ms / 152 tokens ( 255.97 ms per token, 3.91 tokens per second) 32.15.301.146 I slot print_timing: id 2 | task 5827 | total time = 41093.24 ms / 266 tokens 32.15.301.147 I slot print_timing: id 2 | task 5827 | graphs reused = 5220 32.15.301.147 I slot print_timing: id 2 | task 5827 | graph reallocs = 0 / 0 (same size) / (changed size) 32.15.301.198 I slot release: id 2 | task 5827 | stop processing: n_tokens = 1390, truncated = 0 32.15.630.440 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.824 32.15.630.475 I slot launch_slot_: id 2 | task 5984 | processing task, is_child = 0 32.17.183.212 I slot print_timing: id 1 | task 5844 | n_gen = 138, tg = 3.95 t/s, tg_3s = 2.69 t/s 32.17.959.084 I slot print_timing: id 0 | task 5686 | n_gen = 295, tg = 3.81 t/s, tg_3s = 1.92 t/s 32.20.256.413 I slot print_timing: id 1 | task 5844 | n_gen = 150, tg = 3.95 t/s, tg_3s = 3.90 t/s 32.21.176.436 I slot print_timing: id 0 | task 5686 | n_gen = 309, tg = 3.84 t/s, tg_3s = 4.35 t/s 32.23.474.036 I slot print_timing: id 1 | task 5844 | n_gen = 164, tg = 3.98 t/s, tg_3s = 4.35 t/s 32.24.392.982 I slot print_timing: id 0 | task 5686 | n_gen = 323, tg = 3.86 t/s, tg_3s = 4.35 t/s 32.26.690.653 I slot print_timing: id 1 | task 5844 | n_gen = 178, tg = 4.01 t/s, tg_3s = 4.35 t/s 32.27.609.525 I slot print_timing: id 0 | task 5686 | n_gen = 337, tg = 3.87 t/s, tg_3s = 4.35 t/s 32.29.907.354 I slot print_timing: id 1 | task 5844 | n_gen = 192, tg = 4.03 t/s, tg_3s = 4.35 t/s 32.30.137.665 I slot print_timing: id 3 | task 5938 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 32.30.826.585 I slot print_timing: id 0 | task 5686 | n_gen = 351, tg = 3.89 t/s, tg_3s = 4.35 t/s 32.33.126.501 I slot print_timing: id 1 | task 5844 | n_gen = 206, tg = 4.05 t/s, tg_3s = 4.35 t/s 32.33.356.558 I slot print_timing: id 3 | task 5938 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 32.34.045.562 I slot print_timing: id 0 | task 5686 | n_gen = 365, tg = 3.91 t/s, tg_3s = 4.35 t/s 32.36.343.171 I slot print_timing: id 1 | task 5844 | n_gen = 220, tg = 4.07 t/s, tg_3s = 4.35 t/s 32.36.573.401 I slot print_timing: id 3 | task 5938 | n_gen = 128, tg = 4.11 t/s, tg_3s = 4.35 t/s 32.36.803.440 I slot print_timing: id 3 | task 5938 | prompt eval time = 2226.04 ms / 117 tokens ( 19.03 ms per token, 52.56 tokens per second) 32.36.803.446 I slot print_timing: id 3 | task 5938 | eval time = 31156.07 ms / 129 tokens ( 243.41 ms per token, 4.11 tokens per second) 32.36.803.446 I slot print_timing: id 3 | task 5938 | total time = 33382.11 ms / 246 tokens 32.36.803.447 I slot print_timing: id 3 | task 5938 | graphs reused = 5302 32.36.803.447 I slot print_timing: id 3 | task 5938 | graph reallocs = 0 / 0 (same size) / (changed size) 32.36.803.504 I slot release: id 3 | task 5938 | stop processing: n_tokens = 1370, truncated = 0 32.37.021.858 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.836 32.37.021.893 I slot launch_slot_: id 3 | task 6071 | processing task, is_child = 0 32.38.825.964 I slot print_timing: id 0 | task 5686 | n_gen = 379, tg = 3.86 t/s, tg_3s = 2.93 t/s 32.39.491.695 I slot print_timing: id 1 | task 5844 | n_gen = 226, tg = 3.95 t/s, tg_3s = 1.91 t/s 32.41.331.619 I slot print_timing: id 2 | task 5984 | prompt eval time = 2096.59 ms / 88 tokens ( 23.82 ms per token, 41.97 tokens per second) 32.41.331.622 I slot print_timing: id 2 | task 5984 | eval time = 23604.54 ms / 96 tokens ( 248.47 ms per token, 4.02 tokens per second) 32.41.331.623 I slot print_timing: id 2 | task 5984 | total time = 25701.14 ms / 184 tokens 32.41.331.623 I slot print_timing: id 2 | task 5984 | graphs reused = 5310 32.41.331.624 I slot print_timing: id 2 | task 5984 | graph reallocs = 0 / 0 (same size) / (changed size) 32.41.331.667 I slot release: id 2 | task 5984 | stop processing: n_tokens = 1308, truncated = 0 32.41.660.330 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.876 32.41.660.363 I slot launch_slot_: id 2 | task 6084 | processing task, is_child = 0 32.43.213.676 I slot print_timing: id 0 | task 5686 | n_gen = 391, tg = 3.81 t/s, tg_3s = 2.73 t/s 32.43.213.821 I slot print_timing: id 1 | task 5844 | n_gen = 236, tg = 3.87 t/s, tg_3s = 2.69 t/s 32.44.679.939 I slot print_timing: id 1 | task 5844 | prompt eval time = 2556.50 ms / 104 tokens ( 24.58 ms per token, 40.68 tokens per second) 32.44.679.944 I slot print_timing: id 1 | task 5844 | eval time = 62151.79 ms / 241 tokens ( 258.97 ms per token, 3.86 tokens per second) 32.44.679.945 I slot print_timing: id 1 | task 5844 | total time = 64708.30 ms / 345 tokens 32.44.679.945 I slot print_timing: id 1 | task 5844 | graphs reused = 5313 32.44.679.946 I slot print_timing: id 1 | task 5844 | graph reallocs = 0 / 0 (same size) / (changed size) 32.44.679.988 I slot release: id 1 | task 5844 | stop processing: n_tokens = 1469, truncated = 0 32.45.008.848 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.780 32.45.008.884 I slot launch_slot_: id 1 | task 6092 | processing task, is_child = 0 32.47.357.501 I slot print_timing: id 0 | task 5686 | n_gen = 398, tg = 3.73 t/s, tg_3s = 1.69 t/s 32.49.342.009 I slot print_timing: id 0 | task 5686 | prompt eval time = 2945.80 ms / 172 tokens ( 17.13 ms per token, 58.39 tokens per second) 32.49.342.014 I slot print_timing: id 0 | task 5686 | eval time = 108465.30 ms / 405 tokens ( 268.48 ms per token, 3.72 tokens per second) 32.49.342.015 I slot print_timing: id 0 | task 5686 | total time = 111411.11 ms / 577 tokens 32.49.342.015 I slot print_timing: id 0 | task 5686 | graphs reused = 5318 32.49.342.016 I slot print_timing: id 0 | task 5686 | graph reallocs = 0 / 0 (same size) / (changed size) 32.49.342.078 I slot release: id 0 | task 5686 | stop processing: n_tokens = 1701, truncated = 0 32.49.561.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.674 32.49.561.168 I slot launch_slot_: id 0 | task 6102 | processing task, is_child = 0 33.06.001.437 I slot print_timing: id 2 | task 6084 | prompt eval time = 2097.79 ms / 87 tokens ( 24.11 ms per token, 41.47 tokens per second) 33.06.001.442 I slot print_timing: id 2 | task 6084 | eval time = 22243.28 ms / 79 tokens ( 285.17 ms per token, 3.51 tokens per second) 33.06.001.442 I slot print_timing: id 2 | task 6084 | total time = 24341.07 ms / 166 tokens 33.06.001.443 I slot print_timing: id 2 | task 6084 | graphs reused = 5380 33.06.001.443 I slot print_timing: id 2 | task 6084 | graph reallocs = 0 / 0 (same size) / (changed size) 33.06.001.495 I slot release: id 2 | task 6084 | stop processing: n_tokens = 1290, truncated = 0 33.06.330.282 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.888 33.06.330.318 I slot launch_slot_: id 2 | task 6168 | processing task, is_child = 0 33.10.152.893 I slot print_timing: id 3 | task 6071 | n_gen = 100, tg = 3.20 t/s, tg_3s = 3.24 t/s 33.13.367.255 I slot print_timing: id 3 | task 6071 | n_gen = 114, tg = 3.31 t/s, tg_3s = 4.36 t/s 33.14.055.698 I slot print_timing: id 0 | task 6102 | prompt eval time = 2205.20 ms / 118 tokens ( 18.69 ms per token, 53.51 tokens per second) 33.14.055.704 I slot print_timing: id 0 | task 6102 | eval time = 22289.33 ms / 89 tokens ( 253.29 ms per token, 3.95 tokens per second) 33.14.055.704 I slot print_timing: id 0 | task 6102 | total time = 24494.52 ms / 207 tokens 33.14.055.705 I slot print_timing: id 0 | task 6102 | graphs reused = 5402 33.14.055.705 I slot print_timing: id 0 | task 6102 | graph reallocs = 0 / 0 (same size) / (changed size) 33.14.055.753 I slot release: id 0 | task 6102 | stop processing: n_tokens = 1331, truncated = 0 33.14.274.005 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.861 33.14.274.039 I slot launch_slot_: id 0 | task 6195 | processing task, is_child = 0 33.16.421.137 I slot print_timing: id 1 | task 6092 | n_gen = 100, tg = 3.48 t/s, tg_3s = 3.51 t/s 33.16.421.541 I slot print_timing: id 3 | task 6071 | n_gen = 119, tg = 3.18 t/s, tg_3s = 1.64 t/s 33.18.914.394 I slot print_timing: id 3 | task 6071 | prompt eval time = 2237.73 ms / 129 tokens ( 17.35 ms per token, 57.65 tokens per second) 33.18.914.399 I slot print_timing: id 3 | task 6071 | eval time = 39654.76 ms / 129 tokens ( 309.80 ms per token, 3.23 tokens per second) 33.18.914.400 I slot print_timing: id 3 | task 6071 | total time = 41892.49 ms / 258 tokens 33.18.914.401 I slot print_timing: id 3 | task 6071 | graphs reused = 5411 33.18.914.401 I slot print_timing: id 3 | task 6071 | graph reallocs = 0 / 0 (same size) / (changed size) 33.18.914.450 I slot release: id 3 | task 6071 | stop processing: n_tokens = 1382, truncated = 0 33.19.132.348 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.829 33.19.132.377 I slot launch_slot_: id 3 | task 6208 | processing task, is_child = 0 33.20.578.664 I slot print_timing: id 1 | task 6092 | n_gen = 112, tg = 3.40 t/s, tg_3s = 2.89 t/s 33.23.771.571 I slot print_timing: id 1 | task 6092 | n_gen = 125, tg = 3.46 t/s, tg_3s = 4.07 t/s 33.26.985.202 I slot print_timing: id 1 | task 6092 | n_gen = 139, tg = 3.54 t/s, tg_3s = 4.36 t/s 33.30.198.901 I slot print_timing: id 1 | task 6092 | n_gen = 153, tg = 3.60 t/s, tg_3s = 4.36 t/s 33.33.412.768 I slot print_timing: id 1 | task 6092 | n_gen = 167, tg = 3.65 t/s, tg_3s = 4.36 t/s 33.35.020.340 I slot print_timing: id 2 | task 6168 | n_gen = 100, tg = 3.77 t/s, tg_3s = 3.81 t/s 33.36.626.934 I slot print_timing: id 1 | task 6092 | n_gen = 181, tg = 3.70 t/s, tg_3s = 4.36 t/s 33.38.233.516 I slot print_timing: id 2 | task 6168 | n_gen = 114, tg = 3.84 t/s, tg_3s = 4.36 t/s 33.39.840.426 I slot print_timing: id 1 | task 6092 | n_gen = 195, tg = 3.74 t/s, tg_3s = 4.36 t/s 33.40.989.797 I slot print_timing: id 0 | task 6195 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 33.41.449.566 I slot print_timing: id 2 | task 6168 | n_gen = 128, tg = 3.89 t/s, tg_3s = 4.35 t/s 33.43.057.639 I slot print_timing: id 1 | task 6092 | n_gen = 209, tg = 3.78 t/s, tg_3s = 4.35 t/s 33.43.746.988 I slot print_timing: id 3 | task 6208 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 33.44.206.028 I slot print_timing: id 0 | task 6195 | n_gen = 114, tg = 4.13 t/s, tg_3s = 4.35 t/s 33.44.665.827 I slot print_timing: id 2 | task 6168 | n_gen = 142, tg = 3.93 t/s, tg_3s = 4.35 t/s 33.46.273.670 I slot print_timing: id 1 | task 6092 | n_gen = 223, tg = 3.81 t/s, tg_3s = 4.35 t/s 33.46.963.002 I slot print_timing: id 3 | task 6208 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 33.47.422.187 I slot print_timing: id 0 | task 6195 | n_gen = 128, tg = 4.15 t/s, tg_3s = 4.35 t/s 33.47.882.025 I slot print_timing: id 2 | task 6168 | n_gen = 156, tg = 3.96 t/s, tg_3s = 4.35 t/s 33.49.491.283 I slot print_timing: id 1 | task 6092 | n_gen = 237, tg = 3.84 t/s, tg_3s = 4.35 t/s 33.49.491.558 I slot print_timing: id 3 | task 6208 | prompt eval time = 1881.82 ms / 92 tokens ( 20.45 ms per token, 48.89 tokens per second) 33.49.491.562 I slot print_timing: id 3 | task 6208 | eval time = 28477.36 ms / 125 tokens ( 229.66 ms per token, 4.35 tokens per second) 33.49.491.562 I slot print_timing: id 3 | task 6208 | total time = 30359.18 ms / 217 tokens 33.49.491.563 I slot print_timing: id 3 | task 6208 | graphs reused = 5534 33.49.491.563 I slot print_timing: id 3 | task 6208 | graph reallocs = 0 / 0 (same size) / (changed size) 33.49.491.609 I slot release: id 3 | task 6208 | stop processing: n_tokens = 1341, truncated = 0 33.49.710.201 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.855 33.49.710.231 I slot launch_slot_: id 3 | task 6336 | processing task, is_child = 0 33.51.510.820 I slot print_timing: id 0 | task 6195 | n_gen = 139, tg = 3.98 t/s, tg_3s = 2.69 t/s 33.51.511.218 I slot print_timing: id 2 | task 6168 | n_gen = 165, tg = 3.84 t/s, tg_3s = 2.48 t/s 33.52.638.416 I slot print_timing: id 1 | task 6092 | n_gen = 243, tg = 3.74 t/s, tg_3s = 1.91 t/s 33.54.707.651 I slot print_timing: id 0 | task 6195 | n_gen = 152, tg = 3.99 t/s, tg_3s = 4.07 t/s 33.54.707.931 I slot print_timing: id 2 | task 6168 | n_gen = 178, tg = 3.85 t/s, tg_3s = 4.07 t/s 33.55.856.830 I slot print_timing: id 1 | task 6092 | n_gen = 257, tg = 3.77 t/s, tg_3s = 4.35 t/s 33.57.927.402 I slot print_timing: id 0 | task 6195 | n_gen = 166, tg = 4.02 t/s, tg_3s = 4.35 t/s 33.57.927.698 I slot print_timing: id 2 | task 6168 | n_gen = 192, tg = 3.89 t/s, tg_3s = 4.35 t/s 33.59.077.447 I slot print_timing: id 1 | task 6092 | n_gen = 271, tg = 3.80 t/s, tg_3s = 4.35 t/s 34.00.456.990 I slot print_timing: id 1 | task 6092 | prompt eval time = 2953.03 ms / 152 tokens ( 19.43 ms per token, 51.47 tokens per second) 34.00.456.995 I slot print_timing: id 1 | task 6092 | eval time = 72495.06 ms / 277 tokens ( 262.66 ms per token, 3.81 tokens per second) 34.00.456.996 I slot print_timing: id 1 | task 6092 | total time = 75448.10 ms / 429 tokens 34.00.456.996 I slot print_timing: id 1 | task 6092 | graphs reused = 5569 34.00.456.997 I slot print_timing: id 1 | task 6092 | graph reallocs = 0 / 0 (same size) / (changed size) 34.00.457.057 I slot release: id 1 | task 6092 | stop processing: n_tokens = 1553, truncated = 0 34.00.786.411 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.738 34.00.786.444 I slot launch_slot_: id 1 | task 6377 | processing task, is_child = 0 34.02.767.697 I slot print_timing: id 0 | task 6195 | n_gen = 179, tg = 3.88 t/s, tg_3s = 2.69 t/s 34.02.767.862 I slot print_timing: id 2 | task 6168 | n_gen = 205, tg = 3.78 t/s, tg_3s = 2.69 t/s 34.05.902.959 I slot print_timing: id 0 | task 6195 | n_gen = 191, tg = 3.87 t/s, tg_3s = 3.83 t/s 34.05.903.239 I slot print_timing: id 2 | task 6168 | n_gen = 217, tg = 3.78 t/s, tg_3s = 3.83 t/s 34.09.119.051 I slot print_timing: id 0 | task 6195 | n_gen = 205, tg = 3.90 t/s, tg_3s = 4.35 t/s 34.09.119.326 I slot print_timing: id 2 | task 6168 | n_gen = 231, tg = 3.81 t/s, tg_3s = 4.35 t/s 34.12.337.493 I slot print_timing: id 0 | task 6195 | n_gen = 219, tg = 3.93 t/s, tg_3s = 4.35 t/s 34.12.337.771 I slot print_timing: id 2 | task 6168 | n_gen = 245, tg = 3.84 t/s, tg_3s = 4.35 t/s 34.14.634.186 I slot print_timing: id 0 | task 6195 | prompt eval time = 2570.59 ms / 135 tokens ( 19.04 ms per token, 52.52 tokens per second) 34.14.634.191 I slot print_timing: id 0 | task 6195 | eval time = 57789.55 ms / 229 tokens ( 253.46 ms per token, 3.95 tokens per second) 34.14.634.191 I slot print_timing: id 0 | task 6195 | total time = 60360.14 ms / 364 tokens 34.14.634.192 I slot print_timing: id 0 | task 6195 | graphs reused = 5617 34.14.634.192 I slot print_timing: id 0 | task 6195 | graph reallocs = 0 / 0 (same size) / (changed size) 34.14.634.235 I slot release: id 0 | task 6195 | stop processing: n_tokens = 1488, truncated = 0 34.14.852.346 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.770 34.14.852.379 I slot launch_slot_: id 0 | task 6430 | processing task, is_child = 0 34.16.288.043 I slot print_timing: id 2 | task 6168 | n_gen = 257, tg = 3.79 t/s, tg_3s = 3.04 t/s 34.18.321.063 I slot print_timing: id 3 | task 6336 | n_gen = 100, tg = 3.75 t/s, tg_3s = 3.79 t/s 34.19.469.529 I slot print_timing: id 2 | task 6168 | n_gen = 270, tg = 3.80 t/s, tg_3s = 4.09 t/s 34.21.536.437 I slot print_timing: id 3 | task 6336 | n_gen = 114, tg = 3.82 t/s, tg_3s = 4.35 t/s 34.22.684.350 I slot print_timing: id 2 | task 6168 | n_gen = 284, tg = 3.83 t/s, tg_3s = 4.35 t/s 34.24.751.749 I slot print_timing: id 3 | task 6336 | n_gen = 128, tg = 3.87 t/s, tg_3s = 4.35 t/s 34.25.899.671 I slot print_timing: id 2 | task 6168 | n_gen = 298, tg = 3.85 t/s, tg_3s = 4.35 t/s 34.27.509.964 I slot print_timing: id 1 | task 6377 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 34.27.969.690 I slot print_timing: id 3 | task 6336 | n_gen = 142, tg = 3.91 t/s, tg_3s = 4.35 t/s 34.29.117.293 I slot print_timing: id 2 | task 6168 | n_gen = 312, tg = 3.87 t/s, tg_3s = 4.35 t/s 34.30.724.855 I slot print_timing: id 1 | task 6377 | n_gen = 114, tg = 4.13 t/s, tg_3s = 4.35 t/s 34.31.184.419 I slot print_timing: id 3 | task 6336 | n_gen = 156, tg = 3.95 t/s, tg_3s = 4.35 t/s 34.32.332.894 I slot print_timing: id 2 | task 6168 | n_gen = 326, tg = 3.89 t/s, tg_3s = 4.35 t/s 34.33.940.860 I slot print_timing: id 1 | task 6377 | n_gen = 128, tg = 4.15 t/s, tg_3s = 4.35 t/s 34.34.400.988 I slot print_timing: id 3 | task 6336 | n_gen = 170, tg = 3.98 t/s, tg_3s = 4.35 t/s 34.35.549.402 I slot print_timing: id 2 | task 6168 | n_gen = 340, tg = 3.91 t/s, tg_3s = 4.35 t/s 34.37.157.800 I slot print_timing: id 1 | task 6377 | n_gen = 142, tg = 4.17 t/s, tg_3s = 4.35 t/s 34.37.617.616 I slot print_timing: id 3 | task 6336 | n_gen = 184, tg = 4.01 t/s, tg_3s = 4.35 t/s 34.38.766.323 I slot print_timing: id 2 | task 6168 | prompt eval time = 2442.26 ms / 110 tokens ( 22.20 ms per token, 45.04 tokens per second) 34.38.766.329 I slot print_timing: id 2 | task 6168 | eval time = 89993.74 ms / 354 tokens ( 254.94 ms per token, 3.92 tokens per second) 34.38.766.329 I slot print_timing: id 2 | task 6168 | total time = 92436.00 ms / 464 tokens 34.38.766.330 I slot print_timing: id 2 | task 6168 | graphs reused = 5712 34.38.766.330 I slot print_timing: id 2 | task 6168 | graph reallocs = 0 / 0 (same size) / (changed size) 34.38.766.395 I slot release: id 2 | task 6168 | stop processing: n_tokens = 1588, truncated = 0 34.39.095.497 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.722 34.39.095.549 I slot launch_slot_: id 2 | task 6530 | processing task, is_child = 0 34.40.657.599 I slot print_timing: id 1 | task 6377 | n_gen = 151, tg = 4.02 t/s, tg_3s = 2.57 t/s 34.40.657.755 I slot print_timing: id 3 | task 6336 | n_gen = 191, tg = 3.90 t/s, tg_3s = 2.30 t/s 34.41.202.240 I slot print_timing: id 0 | task 6430 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 34.43.731.844 I slot print_timing: id 1 | task 6377 | n_gen = 163, tg = 4.01 t/s, tg_3s = 3.90 t/s 34.43.732.128 I slot print_timing: id 3 | task 6336 | n_gen = 203, tg = 3.90 t/s, tg_3s = 3.90 t/s 34.44.420.930 I slot print_timing: id 0 | task 6430 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 34.46.488.799 I slot print_timing: id 3 | task 6336 | prompt eval time = 2237.01 ms / 120 tokens ( 18.64 ms per token, 53.64 tokens per second) 34.46.488.802 I slot print_timing: id 3 | task 6336 | eval time = 54541.55 ms / 215 tokens ( 254.87 ms per token, 3.92 tokens per second) 34.46.488.802 I slot print_timing: id 3 | task 6336 | total time = 56778.56 ms / 335 tokens 34.46.488.803 I slot print_timing: id 3 | task 6336 | graphs reused = 5734 34.46.488.803 I slot print_timing: id 3 | task 6336 | graph reallocs = 0 / 0 (same size) / (changed size) 34.46.488.855 I slot release: id 3 | task 6336 | stop processing: n_tokens = 1459, truncated = 0 34.46.706.367 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 34.46.706.399 I slot launch_slot_: id 3 | task 6557 | processing task, is_child = 0 34.48.501.008 I slot print_timing: id 0 | task 6430 | n_gen = 125, tg = 3.90 t/s, tg_3s = 2.70 t/s 34.48.501.169 I slot print_timing: id 1 | task 6377 | n_gen = 177, tg = 3.90 t/s, tg_3s = 2.94 t/s 34.51.692.978 I slot print_timing: id 0 | task 6430 | n_gen = 138, tg = 3.92 t/s, tg_3s = 4.07 t/s 34.51.693.132 I slot print_timing: id 1 | task 6377 | n_gen = 190, tg = 3.91 t/s, tg_3s = 4.07 t/s 34.54.906.006 I slot print_timing: id 0 | task 6430 | n_gen = 152, tg = 3.95 t/s, tg_3s = 4.36 t/s 34.54.906.150 I slot print_timing: id 1 | task 6377 | n_gen = 204, tg = 3.94 t/s, tg_3s = 4.36 t/s 34.58.121.138 I slot print_timing: id 0 | task 6430 | n_gen = 166, tg = 3.98 t/s, tg_3s = 4.35 t/s 34.58.121.276 I slot print_timing: id 1 | task 6377 | n_gen = 218, tg = 3.96 t/s, tg_3s = 4.35 t/s 35.01.337.981 I slot print_timing: id 0 | task 6430 | n_gen = 180, tg = 4.01 t/s, tg_3s = 4.35 t/s 35.01.338.117 I slot print_timing: id 1 | task 6377 | n_gen = 232, tg = 3.99 t/s, tg_3s = 4.35 t/s 35.04.555.883 I slot print_timing: id 0 | task 6430 | n_gen = 194, tg = 4.03 t/s, tg_3s = 4.35 t/s 35.04.556.031 I slot print_timing: id 1 | task 6377 | n_gen = 246, tg = 4.00 t/s, tg_3s = 4.35 t/s 35.05.706.269 I slot print_timing: id 2 | task 6530 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 35.06.855.884 I slot print_timing: id 2 | task 6530 | prompt eval time = 2107.08 ms / 98 tokens ( 21.50 ms per token, 46.51 tokens per second) 35.06.855.890 I slot print_timing: id 2 | task 6530 | eval time = 25653.25 ms / 105 tokens ( 246.67 ms per token, 4.05 tokens per second) 35.06.855.891 I slot print_timing: id 2 | task 6530 | total time = 27760.33 ms / 203 tokens 35.06.855.892 I slot print_timing: id 2 | task 6530 | graphs reused = 5811 35.06.855.892 I slot print_timing: id 2 | task 6530 | graph reallocs = 0 / 0 (same size) / (changed size) 35.06.855.937 I slot release: id 2 | task 6530 | stop processing: n_tokens = 1327, truncated = 0 35.07.185.548 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.864 35.07.185.580 I slot launch_slot_: id 2 | task 6639 | processing task, is_child = 0 35.09.102.444 I slot print_timing: id 0 | task 6430 | n_gen = 206, tg = 3.91 t/s, tg_3s = 2.64 t/s 35.09.102.659 I slot print_timing: id 1 | task 6377 | n_gen = 258, tg = 3.91 t/s, tg_3s = 2.64 t/s 35.12.179.368 I slot print_timing: id 0 | task 6430 | n_gen = 218, tg = 3.91 t/s, tg_3s = 3.90 t/s 35.12.179.513 I slot print_timing: id 1 | task 6377 | n_gen = 270, tg = 3.91 t/s, tg_3s = 3.90 t/s 35.13.787.354 I slot print_timing: id 3 | task 6557 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 35.15.398.470 I slot print_timing: id 0 | task 6430 | n_gen = 232, tg = 3.94 t/s, tg_3s = 4.35 t/s 35.15.398.609 I slot print_timing: id 1 | task 6377 | n_gen = 284, tg = 3.93 t/s, tg_3s = 4.35 t/s 35.15.857.745 I slot print_timing: id 0 | task 6430 | prompt eval time = 1858.40 ms / 95 tokens ( 19.56 ms per token, 51.12 tokens per second) 35.15.857.750 I slot print_timing: id 0 | task 6430 | eval time = 59146.96 ms / 234 tokens ( 253.85 ms per token, 3.94 tokens per second) 35.15.857.750 I slot print_timing: id 0 | task 6430 | total time = 61005.36 ms / 329 tokens 35.15.857.751 I slot print_timing: id 0 | task 6430 | graphs reused = 5836 35.15.857.751 I slot print_timing: id 0 | task 6430 | graph reallocs = 0 / 0 (same size) / (changed size) 35.15.857.795 I slot release: id 0 | task 6430 | stop processing: n_tokens = 1453, truncated = 0 35.16.076.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.789 35.16.076.633 I slot launch_slot_: id 0 | task 6670 | processing task, is_child = 0 35.17.841.584 I slot print_timing: id 3 | task 6557 | n_gen = 111, tg = 3.81 t/s, tg_3s = 2.71 t/s 35.18.496.923 I slot print_timing: id 1 | task 6377 | n_gen = 290, tg = 3.85 t/s, tg_3s = 1.94 t/s 35.21.022.191 I slot print_timing: id 3 | task 6557 | n_gen = 124, tg = 3.83 t/s, tg_3s = 4.09 t/s 35.21.710.679 I slot print_timing: id 1 | task 6377 | n_gen = 304, tg = 3.87 t/s, tg_3s = 4.36 t/s 35.24.239.532 I slot print_timing: id 3 | task 6557 | n_gen = 138, tg = 3.88 t/s, tg_3s = 4.35 t/s 35.24.929.319 I slot print_timing: id 1 | task 6377 | n_gen = 318, tg = 3.89 t/s, tg_3s = 4.35 t/s 35.27.456.984 I slot print_timing: id 3 | task 6557 | n_gen = 152, tg = 3.92 t/s, tg_3s = 4.35 t/s 35.28.146.652 I slot print_timing: id 1 | task 6377 | n_gen = 332, tg = 3.90 t/s, tg_3s = 4.35 t/s 35.30.674.144 I slot print_timing: id 3 | task 6557 | n_gen = 166, tg = 3.95 t/s, tg_3s = 4.35 t/s 35.31.363.232 I slot print_timing: id 1 | task 6377 | n_gen = 346, tg = 3.92 t/s, tg_3s = 4.35 t/s 35.33.890.506 I slot print_timing: id 3 | task 6557 | n_gen = 180, tg = 3.98 t/s, tg_3s = 4.35 t/s 35.34.120.109 I slot print_timing: id 2 | task 6639 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 35.34.579.345 I slot print_timing: id 1 | task 6377 | n_gen = 360, tg = 3.94 t/s, tg_3s = 4.35 t/s 35.37.109.691 I slot print_timing: id 3 | task 6557 | n_gen = 194, tg = 4.01 t/s, tg_3s = 4.35 t/s 35.37.339.307 I slot print_timing: id 2 | task 6639 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 35.37.568.940 I slot print_timing: id 1 | task 6377 | prompt eval time = 2585.80 ms / 131 tokens ( 19.74 ms per token, 50.66 tokens per second) 35.37.568.946 I slot print_timing: id 1 | task 6377 | eval time = 94196.69 ms / 373 tokens ( 253.22 ms per token, 3.95 tokens per second) 35.37.568.947 I slot print_timing: id 1 | task 6377 | total time = 96782.49 ms / 504 tokens 35.37.568.947 I slot print_timing: id 1 | task 6377 | graphs reused = 5920 35.37.568.948 I slot print_timing: id 1 | task 6377 | graph reallocs = 0 / 0 (same size) / (changed size) 35.37.568.993 I slot release: id 1 | task 6377 | stop processing: n_tokens = 1628, truncated = 0 35.37.898.060 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.704 35.37.898.095 I slot launch_slot_: id 1 | task 6758 | processing task, is_child = 0 35.40.474.289 I slot print_timing: id 2 | task 6639 | n_gen = 118, tg = 3.80 t/s, tg_3s = 1.28 t/s 35.40.474.448 I slot print_timing: id 3 | task 6557 | n_gen = 199, tg = 3.84 t/s, tg_3s = 1.49 t/s 35.43.232.260 I slot print_timing: id 0 | task 6670 | n_gen = 100, tg = 3.97 t/s, tg_3s = 4.01 t/s 35.43.691.429 I slot print_timing: id 2 | task 6639 | n_gen = 132, tg = 3.85 t/s, tg_3s = 4.35 t/s 35.43.691.580 I slot print_timing: id 3 | task 6557 | n_gen = 213, tg = 3.87 t/s, tg_3s = 4.35 t/s 35.46.447.499 I slot print_timing: id 0 | task 6670 | n_gen = 114, tg = 4.01 t/s, tg_3s = 4.35 t/s 35.46.906.945 I slot print_timing: id 2 | task 6639 | n_gen = 146, tg = 3.89 t/s, tg_3s = 4.35 t/s 35.46.907.099 I slot print_timing: id 3 | task 6557 | n_gen = 227, tg = 3.90 t/s, tg_3s = 4.35 t/s 35.49.665.697 I slot print_timing: id 0 | task 6670 | n_gen = 128, tg = 4.04 t/s, tg_3s = 4.35 t/s 35.50.125.668 I slot print_timing: id 2 | task 6639 | n_gen = 160, tg = 3.93 t/s, tg_3s = 4.35 t/s 35.50.125.824 I slot print_timing: id 3 | task 6557 | n_gen = 241, tg = 3.92 t/s, tg_3s = 4.35 t/s 35.51.734.722 I slot print_timing: id 2 | task 6639 | prompt eval time = 2462.40 ms / 130 tokens ( 18.94 ms per token, 52.79 tokens per second) 35.51.734.728 I slot print_timing: id 2 | task 6639 | eval time = 42086.74 ms / 167 tokens ( 253.53 ms per token, 3.94 tokens per second) 35.51.734.728 I slot print_timing: id 2 | task 6639 | total time = 44549.13 ms / 297 tokens 35.51.734.729 I slot print_timing: id 2 | task 6639 | graphs reused = 5968 35.51.734.729 I slot print_timing: id 2 | task 6639 | graph reallocs = 0 / 0 (same size) / (changed size) 35.51.735.818 I slot release: id 2 | task 6639 | stop processing: n_tokens = 1421, truncated = 0 35.52.064.322 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.806 35.52.064.354 I slot launch_slot_: id 2 | task 6811 | processing task, is_child = 0 35.53.975.755 I slot print_timing: id 0 | task 6670 | n_gen = 139, tg = 3.86 t/s, tg_3s = 2.55 t/s 35.53.976.125 I slot print_timing: id 3 | task 6557 | n_gen = 250, tg = 3.83 t/s, tg_3s = 2.34 t/s 35.57.049.404 I slot print_timing: id 0 | task 6670 | n_gen = 151, tg = 3.87 t/s, tg_3s = 3.90 t/s 35.57.049.809 I slot print_timing: id 3 | task 6557 | n_gen = 262, tg = 3.83 t/s, tg_3s = 3.90 t/s 36.00.264.762 I slot print_timing: id 0 | task 6670 | n_gen = 165, tg = 3.90 t/s, tg_3s = 4.35 t/s 36.00.265.181 I slot print_timing: id 3 | task 6557 | n_gen = 276, tg = 3.86 t/s, tg_3s = 4.35 t/s 36.03.479.947 I slot print_timing: id 0 | task 6670 | n_gen = 179, tg = 3.94 t/s, tg_3s = 4.35 t/s 36.03.480.336 I slot print_timing: id 3 | task 6557 | n_gen = 290, tg = 3.88 t/s, tg_3s = 4.35 t/s 36.05.320.139 I slot print_timing: id 1 | task 6758 | n_gen = 100, tg = 3.98 t/s, tg_3s = 4.02 t/s 36.06.698.233 I slot print_timing: id 0 | task 6670 | n_gen = 193, tg = 3.96 t/s, tg_3s = 4.35 t/s 36.06.698.655 I slot print_timing: id 3 | task 6557 | n_gen = 304, tg = 3.90 t/s, tg_3s = 4.35 t/s 36.08.536.815 I slot print_timing: id 1 | task 6758 | n_gen = 114, tg = 4.03 t/s, tg_3s = 4.35 t/s 36.09.915.145 I slot print_timing: id 0 | task 6670 | n_gen = 207, tg = 3.99 t/s, tg_3s = 4.35 t/s 36.09.915.571 I slot print_timing: id 3 | task 6557 | n_gen = 318, tg = 3.91 t/s, tg_3s = 4.35 t/s 36.11.064.561 I slot print_timing: id 3 | task 6557 | prompt eval time = 2229.01 ms / 116 tokens ( 19.22 ms per token, 52.04 tokens per second) 36.11.064.566 I slot print_timing: id 3 | task 6557 | eval time = 82129.14 ms / 323 tokens ( 255.06 ms per token, 3.92 tokens per second) 36.11.064.567 I slot print_timing: id 3 | task 6557 | total time = 84358.16 ms / 439 tokens 36.11.064.568 I slot print_timing: id 3 | task 6557 | graphs reused = 6038 36.11.064.568 I slot print_timing: id 3 | task 6557 | graph reallocs = 0 / 0 (same size) / (changed size) 36.11.064.613 I slot release: id 3 | task 6557 | stop processing: n_tokens = 1563, truncated = 0 36.11.282.338 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.733 36.11.282.372 I slot launch_slot_: id 3 | task 6887 | processing task, is_child = 0 36.13.078.995 I slot print_timing: id 0 | task 6670 | n_gen = 214, tg = 3.89 t/s, tg_3s = 2.21 t/s 36.13.079.234 I slot print_timing: id 1 | task 6758 | n_gen = 127, tg = 3.86 t/s, tg_3s = 2.86 t/s 36.16.272.279 I slot print_timing: id 0 | task 6670 | n_gen = 227, tg = 3.90 t/s, tg_3s = 4.07 t/s 36.16.272.426 I slot print_timing: id 1 | task 6758 | n_gen = 140, tg = 3.88 t/s, tg_3s = 4.07 t/s 36.19.028.761 I slot print_timing: id 2 | task 6811 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 36.19.487.666 I slot print_timing: id 0 | task 6670 | n_gen = 241, tg = 3.92 t/s, tg_3s = 4.35 t/s 36.19.487.807 I slot print_timing: id 1 | task 6758 | n_gen = 154, tg = 3.92 t/s, tg_3s = 4.35 t/s 36.22.246.280 I slot print_timing: id 2 | task 6811 | n_gen = 114, tg = 4.08 t/s, tg_3s = 4.35 t/s 36.22.705.543 I slot print_timing: id 0 | task 6670 | prompt eval time = 2188.26 ms / 103 tokens ( 21.25 ms per token, 47.07 tokens per second) 36.22.705.545 I slot print_timing: id 0 | task 6670 | eval time = 64440.64 ms / 255 tokens ( 253.70 ms per token, 3.94 tokens per second) 36.22.705.545 I slot print_timing: id 0 | task 6670 | total time = 66628.90 ms / 358 tokens 36.22.705.546 I slot print_timing: id 0 | task 6670 | graphs reused = 6077 36.22.705.546 I slot print_timing: id 0 | task 6670 | graph reallocs = 0 / 0 (same size) / (changed size) 36.22.705.595 I slot release: id 0 | task 6670 | stop processing: n_tokens = 1482, truncated = 0 36.22.705.751 I slot print_timing: id 1 | task 6758 | n_gen = 168, tg = 3.95 t/s, tg_3s = 4.35 t/s 36.22.924.228 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 36.22.924.260 I slot launch_slot_: id 0 | task 6931 | processing task, is_child = 0 36.25.358.177 I slot print_timing: id 2 | task 6811 | n_gen = 120, tg = 3.86 t/s, tg_3s = 1.93 t/s 36.25.817.224 I slot print_timing: id 1 | task 6758 | n_gen = 174, tg = 3.82 t/s, tg_3s = 1.93 t/s 36.28.572.836 I slot print_timing: id 2 | task 6811 | n_gen = 134, tg = 3.91 t/s, tg_3s = 4.36 t/s 36.29.031.047 I slot print_timing: id 1 | task 6758 | n_gen = 188, tg = 3.85 t/s, tg_3s = 4.36 t/s 36.31.786.627 I slot print_timing: id 2 | task 6811 | n_gen = 148, tg = 3.94 t/s, tg_3s = 4.36 t/s 36.32.245.661 I slot print_timing: id 1 | task 6758 | n_gen = 202, tg = 3.88 t/s, tg_3s = 4.36 t/s 36.34.999.445 I slot print_timing: id 2 | task 6811 | n_gen = 162, tg = 3.98 t/s, tg_3s = 4.36 t/s 36.35.458.841 I slot print_timing: id 1 | task 6758 | n_gen = 216, tg = 3.91 t/s, tg_3s = 4.36 t/s 36.37.984.188 I slot print_timing: id 3 | task 6887 | n_gen = 100, tg = 4.05 t/s, tg_3s = 4.09 t/s 36.38.214.874 I slot print_timing: id 2 | task 6811 | n_gen = 176, tg = 4.01 t/s, tg_3s = 4.35 t/s 36.38.674.132 I slot print_timing: id 1 | task 6758 | n_gen = 230, tg = 3.93 t/s, tg_3s = 4.35 t/s 36.39.133.360 I slot print_timing: id 1 | task 6758 | prompt eval time = 2576.05 ms / 122 tokens ( 21.12 ms per token, 47.36 tokens per second) 36.39.133.365 I slot print_timing: id 1 | task 6758 | eval time = 58659.21 ms / 232 tokens ( 253.94 ms per token, 3.94 tokens per second) 36.39.133.365 I slot print_timing: id 1 | task 6758 | total time = 61235.26 ms / 354 tokens 36.39.133.366 I slot print_timing: id 1 | task 6758 | graphs reused = 6138 36.39.133.366 I slot print_timing: id 1 | task 6758 | graph reallocs = 0 / 0 (same size) / (changed size) 36.39.133.410 I slot release: id 1 | task 6758 | stop processing: n_tokens = 1478, truncated = 0 36.39.462.748 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.775 36.39.462.780 I slot launch_slot_: id 1 | task 6996 | processing task, is_child = 0 36.41.079.942 I slot print_timing: id 3 | task 6887 | n_gen = 107, tg = 3.85 t/s, tg_3s = 2.26 t/s 36.41.684.548 I slot print_timing: id 2 | task 6811 | n_gen = 183, tg = 3.86 t/s, tg_3s = 2.02 t/s 36.44.212.881 I slot print_timing: id 3 | task 6887 | n_gen = 119, tg = 3.84 t/s, tg_3s = 3.83 t/s 36.44.900.617 I slot print_timing: id 2 | task 6811 | n_gen = 197, tg = 3.89 t/s, tg_3s = 4.35 t/s 36.47.427.391 I slot print_timing: id 3 | task 6887 | n_gen = 133, tg = 3.89 t/s, tg_3s = 4.36 t/s 36.48.115.384 I slot print_timing: id 2 | task 6811 | n_gen = 211, tg = 3.92 t/s, tg_3s = 4.35 t/s 36.49.722.096 I slot print_timing: id 0 | task 6931 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.07 t/s 36.50.640.992 I slot print_timing: id 3 | task 6887 | n_gen = 147, tg = 3.93 t/s, tg_3s = 4.36 t/s 36.51.330.020 I slot print_timing: id 2 | task 6811 | n_gen = 225, tg = 3.94 t/s, tg_3s = 4.36 t/s 36.52.936.450 I slot print_timing: id 0 | task 6931 | n_gen = 114, tg = 4.06 t/s, tg_3s = 4.36 t/s 36.53.854.719 I slot print_timing: id 3 | task 6887 | n_gen = 161, tg = 3.97 t/s, tg_3s = 4.36 t/s 36.54.544.041 I slot print_timing: id 2 | task 6811 | n_gen = 239, tg = 3.97 t/s, tg_3s = 4.36 t/s 36.56.150.979 I slot print_timing: id 0 | task 6931 | n_gen = 128, tg = 4.09 t/s, tg_3s = 4.36 t/s 36.57.070.050 I slot print_timing: id 3 | task 6887 | n_gen = 175, tg = 3.99 t/s, tg_3s = 4.35 t/s 36.57.758.820 I slot print_timing: id 2 | task 6811 | n_gen = 253, tg = 3.98 t/s, tg_3s = 4.35 t/s 36.59.366.122 I slot print_timing: id 0 | task 6931 | n_gen = 142, tg = 4.12 t/s, tg_3s = 4.35 t/s 37.00.286.040 I slot print_timing: id 3 | task 6887 | n_gen = 189, tg = 4.02 t/s, tg_3s = 4.35 t/s 37.00.974.746 I slot print_timing: id 2 | task 6811 | n_gen = 267, tg = 4.00 t/s, tg_3s = 4.35 t/s 37.02.582.249 I slot print_timing: id 0 | task 6931 | n_gen = 156, tg = 4.14 t/s, tg_3s = 4.35 t/s 37.03.502.569 I slot print_timing: id 3 | task 6887 | n_gen = 203, tg = 4.04 t/s, tg_3s = 4.35 t/s 37.04.193.595 I slot print_timing: id 2 | task 6811 | n_gen = 281, tg = 4.02 t/s, tg_3s = 4.35 t/s 37.04.423.274 I slot print_timing: id 1 | task 6996 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.40 t/s 37.05.800.886 I slot print_timing: id 0 | task 6931 | n_gen = 170, tg = 4.15 t/s, tg_3s = 4.35 t/s 37.06.720.670 I slot print_timing: id 3 | task 6887 | n_gen = 217, tg = 4.06 t/s, tg_3s = 4.35 t/s 37.07.409.638 I slot print_timing: id 2 | task 6811 | n_gen = 295, tg = 4.03 t/s, tg_3s = 4.35 t/s 37.07.640.299 I slot print_timing: id 1 | task 6996 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 37.08.329.468 I slot print_timing: id 1 | task 6996 | prompt eval time = 2221.61 ms / 101 tokens ( 22.00 ms per token, 45.46 tokens per second) 37.08.329.473 I slot print_timing: id 1 | task 6996 | eval time = 26645.07 ms / 117 tokens ( 229.70 ms per token, 4.35 tokens per second) 37.08.329.474 I slot print_timing: id 1 | task 6996 | total time = 28866.68 ms / 218 tokens 37.08.329.475 I slot print_timing: id 1 | task 6996 | graphs reused = 6252 37.08.329.475 I slot print_timing: id 1 | task 6996 | graph reallocs = 0 / 0 (same size) / (changed size) 37.08.329.517 I slot release: id 1 | task 6996 | stop processing: n_tokens = 1342, truncated = 0 37.08.658.721 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.854 37.08.658.752 I slot launch_slot_: id 1 | task 7116 | processing task, is_child = 0 37.10.277.288 I slot print_timing: id 0 | task 6931 | n_gen = 183, tg = 4.03 t/s, tg_3s = 2.90 t/s 37.10.277.649 I slot print_timing: id 3 | task 6887 | n_gen = 226, tg = 3.96 t/s, tg_3s = 2.53 t/s 37.10.881.632 I slot print_timing: id 2 | task 6811 | n_gen = 302, tg = 3.94 t/s, tg_3s = 2.02 t/s 37.13.413.611 I slot print_timing: id 0 | task 6931 | n_gen = 195, tg = 4.02 t/s, tg_3s = 3.83 t/s 37.13.414.030 I slot print_timing: id 3 | task 6887 | n_gen = 238, tg = 3.96 t/s, tg_3s = 3.83 t/s 37.14.102.527 I slot print_timing: id 2 | task 6811 | n_gen = 316, tg = 3.96 t/s, tg_3s = 4.35 t/s 37.16.630.618 I slot print_timing: id 0 | task 6931 | n_gen = 209, tg = 4.04 t/s, tg_3s = 4.35 t/s 37.16.631.026 I slot print_timing: id 3 | task 6887 | n_gen = 252, tg = 3.98 t/s, tg_3s = 4.35 t/s 37.17.319.874 I slot print_timing: id 2 | task 6811 | n_gen = 330, tg = 3.97 t/s, tg_3s = 4.35 t/s 37.19.157.739 I slot print_timing: id 3 | task 6887 | prompt eval time = 2231.87 ms / 123 tokens ( 18.15 ms per token, 55.11 tokens per second) 37.19.157.745 I slot print_timing: id 3 | task 6887 | eval time = 65643.49 ms / 263 tokens ( 250.55 ms per token, 3.99 tokens per second) 37.19.157.745 I slot print_timing: id 3 | task 6887 | total time = 67875.36 ms / 386 tokens 37.19.157.746 I slot print_timing: id 3 | task 6887 | graphs reused = 6287 37.19.157.746 I slot print_timing: id 3 | task 6887 | graph reallocs = 0 / 0 (same size) / (changed size) 37.19.157.794 I slot release: id 3 | task 6887 | stop processing: n_tokens = 1510, truncated = 0 37.19.375.596 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.759 37.19.375.623 I slot launch_slot_: id 3 | task 7156 | processing task, is_child = 0 37.21.552.536 I slot print_timing: id 0 | task 6931 | n_gen = 222, tg = 3.92 t/s, tg_3s = 2.64 t/s 37.21.552.941 I slot print_timing: id 2 | task 6811 | n_gen = 340, tg = 3.90 t/s, tg_3s = 2.36 t/s 37.24.746.160 I slot print_timing: id 0 | task 6931 | n_gen = 235, tg = 3.92 t/s, tg_3s = 4.07 t/s 37.24.746.473 I slot print_timing: id 2 | task 6811 | n_gen = 353, tg = 3.90 t/s, tg_3s = 4.07 t/s 37.27.966.399 I slot print_timing: id 0 | task 6931 | n_gen = 249, tg = 3.95 t/s, tg_3s = 4.35 t/s 37.27.966.680 I slot print_timing: id 2 | task 6811 | n_gen = 367, tg = 3.92 t/s, tg_3s = 4.35 t/s 37.31.186.352 I slot print_timing: id 0 | task 6931 | n_gen = 263, tg = 3.97 t/s, tg_3s = 4.35 t/s 37.31.186.622 I slot print_timing: id 2 | task 6811 | n_gen = 381, tg = 3.93 t/s, tg_3s = 4.35 t/s 37.31.875.602 I slot print_timing: id 1 | task 7116 | prompt eval time = 2222.73 ms / 95 tokens ( 23.40 ms per token, 42.74 tokens per second) 37.31.875.608 I slot print_timing: id 1 | task 7116 | eval time = 20994.11 ms / 83 tokens ( 256.03 ms per token, 3.91 tokens per second) 37.31.875.608 I slot print_timing: id 1 | task 7116 | total time = 23216.84 ms / 178 tokens 37.31.875.609 I slot print_timing: id 1 | task 7116 | graphs reused = 6329 37.31.875.609 I slot print_timing: id 1 | task 7116 | graph reallocs = 0 / 0 (same size) / (changed size) 37.31.875.661 I slot release: id 1 | task 7116 | stop processing: n_tokens = 1302, truncated = 0 37.32.205.465 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.880 37.32.205.495 I slot launch_slot_: id 1 | task 7203 | processing task, is_child = 0 37.34.422.287 I slot print_timing: id 0 | task 6931 | n_gen = 269, tg = 3.87 t/s, tg_3s = 1.85 t/s 37.34.422.614 I slot print_timing: id 2 | task 6811 | n_gen = 387, tg = 3.86 t/s, tg_3s = 1.85 t/s 37.37.643.789 I slot print_timing: id 0 | task 6931 | n_gen = 283, tg = 3.89 t/s, tg_3s = 4.35 t/s 37.37.644.051 I slot print_timing: id 2 | task 6811 | n_gen = 401, tg = 3.88 t/s, tg_3s = 4.35 t/s 37.40.860.852 I slot print_timing: id 0 | task 6931 | n_gen = 297, tg = 3.91 t/s, tg_3s = 4.35 t/s 37.40.861.144 I slot print_timing: id 2 | task 6811 | n_gen = 415, tg = 3.89 t/s, tg_3s = 4.35 t/s 37.44.077.737 I slot print_timing: id 0 | task 6931 | n_gen = 311, tg = 3.93 t/s, tg_3s = 4.35 t/s 37.44.078.030 I slot print_timing: id 2 | task 6811 | n_gen = 429, tg = 3.91 t/s, tg_3s = 4.35 t/s 37.46.606.047 I slot print_timing: id 3 | task 7156 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 37.47.295.074 I slot print_timing: id 0 | task 6931 | n_gen = 325, tg = 3.94 t/s, tg_3s = 4.35 t/s 37.47.295.347 I slot print_timing: id 2 | task 6811 | n_gen = 443, tg = 3.92 t/s, tg_3s = 4.35 t/s 37.48.904.228 I slot print_timing: id 1 | task 7203 | prompt eval time = 2216.97 ms / 89 tokens ( 24.91 ms per token, 40.14 tokens per second) 37.48.904.233 I slot print_timing: id 1 | task 7203 | eval time = 14481.75 ms / 64 tokens ( 229.87 ms per token, 4.35 tokens per second) 37.48.904.234 I slot print_timing: id 1 | task 7203 | total time = 16698.72 ms / 153 tokens 37.48.904.235 I slot print_timing: id 1 | task 7203 | graphs reused = 6391 37.48.904.235 I slot print_timing: id 1 | task 7203 | graph reallocs = 0 / 0 (same size) / (changed size) 37.48.905.498 I slot release: id 1 | task 7203 | stop processing: n_tokens = 1277, truncated = 0 37.49.235.594 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.897 37.49.235.626 I slot launch_slot_: id 1 | task 7270 | processing task, is_child = 0 37.50.860.511 I slot print_timing: id 0 | task 6931 | n_gen = 334, tg = 3.88 t/s, tg_3s = 2.52 t/s 37.50.860.734 I slot print_timing: id 2 | task 6811 | n_gen = 452, tg = 3.88 t/s, tg_3s = 2.52 t/s 37.50.860.959 I slot print_timing: id 3 | task 7156 | n_gen = 112, tg = 3.84 t/s, tg_3s = 2.82 t/s 37.53.996.720 I slot print_timing: id 0 | task 6931 | n_gen = 346, tg = 3.88 t/s, tg_3s = 3.83 t/s 37.53.997.026 I slot print_timing: id 2 | task 6811 | n_gen = 464, tg = 3.88 t/s, tg_3s = 3.83 t/s 37.53.997.199 I slot print_timing: id 3 | task 7156 | n_gen = 124, tg = 3.84 t/s, tg_3s = 3.83 t/s 37.57.214.981 I slot print_timing: id 0 | task 6931 | n_gen = 360, tg = 3.90 t/s, tg_3s = 4.35 t/s 37.57.215.263 I slot print_timing: id 2 | task 6811 | n_gen = 478, tg = 3.89 t/s, tg_3s = 4.35 t/s 37.57.215.411 I slot print_timing: id 3 | task 7156 | n_gen = 138, tg = 3.89 t/s, tg_3s = 4.35 t/s 38.00.434.701 I slot print_timing: id 0 | task 6931 | n_gen = 374, tg = 3.91 t/s, tg_3s = 4.35 t/s 38.00.434.976 I slot print_timing: id 2 | task 6811 | n_gen = 492, tg = 3.90 t/s, tg_3s = 4.35 t/s 38.00.435.125 I slot print_timing: id 3 | task 7156 | n_gen = 152, tg = 3.93 t/s, tg_3s = 4.35 t/s 38.03.653.301 I slot print_timing: id 0 | task 6931 | n_gen = 388, tg = 3.93 t/s, tg_3s = 4.35 t/s 38.03.653.562 I slot print_timing: id 2 | task 6811 | n_gen = 506, tg = 3.91 t/s, tg_3s = 4.35 t/s 38.03.653.706 I slot print_timing: id 3 | task 7156 | n_gen = 166, tg = 3.96 t/s, tg_3s = 4.35 t/s 38.06.871.881 I slot print_timing: id 0 | task 6931 | n_gen = 402, tg = 3.94 t/s, tg_3s = 4.35 t/s 38.06.872.178 I slot print_timing: id 2 | task 6811 | n_gen = 520, tg = 3.92 t/s, tg_3s = 4.35 t/s 38.06.872.333 I slot print_timing: id 3 | task 7156 | n_gen = 180, tg = 3.99 t/s, tg_3s = 4.35 t/s 38.07.103.320 I slot print_timing: id 2 | task 6811 | prompt eval time = 2456.35 ms / 133 tokens ( 18.47 ms per token, 54.15 tokens per second) 38.07.103.325 I slot print_timing: id 2 | task 6811 | eval time = 132582.61 ms / 521 tokens ( 254.97 ms per token, 3.92 tokens per second) 38.07.103.326 I slot print_timing: id 2 | task 6811 | total time = 135038.96 ms / 654 tokens 38.07.103.326 I slot print_timing: id 2 | task 6811 | graphs reused = 6458 38.07.103.327 I slot print_timing: id 2 | task 6811 | graph reallocs = 0 / 0 (same size) / (changed size) 38.07.103.372 I slot release: id 2 | task 6811 | stop processing: n_tokens = 1778, truncated = 0 38.07.432.161 I slot print_timing: id 0 | task 6931 | prompt eval time = 2201.49 ms / 118 tokens ( 18.66 ms per token, 53.60 tokens per second) 38.07.432.165 I slot print_timing: id 0 | task 6931 | eval time = 102306.40 ms / 404 tokens ( 253.86 ms per token, 3.94 tokens per second) 38.07.432.166 I slot print_timing: id 0 | task 6931 | total time = 104507.89 ms / 522 tokens 38.07.432.166 I slot print_timing: id 0 | task 6931 | graphs reused = 6458 38.07.432.166 I slot print_timing: id 0 | task 6931 | graph reallocs = 0 / 0 (same size) / (changed size) 38.07.432.206 I slot release: id 0 | task 6931 | stop processing: n_tokens = 1646, truncated = 0 38.07.432.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.696 38.07.432.664 I slot launch_slot_: id 0 | task 7342 | processing task, is_child = 0 38.07.432.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 38.07.433.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.944 MiB) 38.07.434.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.443 MiB) 38.09.159.171 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.645 38.09.159.458 I slot launch_slot_: id 2 | task 7343 | processing task, is_child = 0 38.12.309.750 I slot print_timing: id 3 | task 7156 | n_gen = 183, tg = 3.62 t/s, tg_3s = 0.55 t/s 38.12.309.768 I slot print_timing: id 0 | task 7342 | prompt processing, n_tokens = 88, progress = 1.00, t = 3.15 s / 27.94 tokens per second 38.12.321.310 I slot print_timing: id 2 | task 7343 | prompt processing, n_tokens = 109, progress = 1.00, t = 3.12 s / 34.94 tokens per second 38.15.348.164 I slot print_timing: id 3 | task 7156 | n_gen = 194, tg = 3.62 t/s, tg_3s = 3.62 t/s 38.18.562.500 I slot print_timing: id 3 | task 7156 | n_gen = 208, tg = 3.66 t/s, tg_3s = 4.36 t/s 38.19.484.168 I slot print_timing: id 1 | task 7270 | n_gen = 100, tg = 3.53 t/s, tg_3s = 3.57 t/s 38.21.781.090 I slot print_timing: id 3 | task 7156 | n_gen = 222, tg = 3.70 t/s, tg_3s = 4.35 t/s 38.22.700.010 I slot print_timing: id 1 | task 7270 | n_gen = 114, tg = 3.62 t/s, tg_3s = 4.35 t/s 38.24.996.076 I slot print_timing: id 3 | task 7156 | n_gen = 236, tg = 3.73 t/s, tg_3s = 4.35 t/s 38.25.914.223 I slot print_timing: id 1 | task 7270 | n_gen = 128, tg = 3.69 t/s, tg_3s = 4.36 t/s 38.28.210.470 I slot print_timing: id 3 | task 7156 | n_gen = 250, tg = 3.76 t/s, tg_3s = 4.36 t/s 38.29.128.864 I slot print_timing: id 1 | task 7270 | n_gen = 142, tg = 3.74 t/s, tg_3s = 4.36 t/s 38.31.428.595 I slot print_timing: id 3 | task 7156 | n_gen = 264, tg = 3.79 t/s, tg_3s = 4.35 t/s 38.32.346.955 I slot print_timing: id 1 | task 7270 | n_gen = 156, tg = 3.79 t/s, tg_3s = 4.35 t/s 38.33.725.119 I slot print_timing: id 0 | task 7342 | prompt eval time = 3891.24 ms / 92 tokens ( 42.30 ms per token, 23.64 tokens per second) 38.33.725.121 I slot print_timing: id 0 | task 7342 | eval time = 20674.40 ms / 91 tokens ( 229.72 ms per token, 4.35 tokens per second) 38.33.725.122 I slot print_timing: id 0 | task 7342 | total time = 24565.64 ms / 183 tokens 38.33.725.122 I slot print_timing: id 0 | task 7342 | graphs reused = 6546 38.33.725.123 I slot print_timing: id 0 | task 7342 | graph reallocs = 0 / 0 (same size) / (changed size) 38.33.725.279 I slot release: id 0 | task 7342 | stop processing: n_tokens = 1307, truncated = 0 38.33.943.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.877 38.33.943.585 I slot launch_slot_: id 0 | task 7437 | processing task, is_child = 0 38.35.728.299 I slot print_timing: id 1 | task 7270 | n_gen = 164, tg = 3.68 t/s, tg_3s = 2.37 t/s 38.35.728.757 I slot print_timing: id 3 | task 7156 | n_gen = 276, tg = 3.73 t/s, tg_3s = 2.79 t/s 38.37.534.043 I slot print_timing: id 2 | task 7343 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 38.38.912.812 I slot print_timing: id 1 | task 7270 | n_gen = 177, tg = 3.71 t/s, tg_3s = 4.08 t/s 38.38.913.113 I slot print_timing: id 3 | task 7156 | n_gen = 289, tg = 3.74 t/s, tg_3s = 4.08 t/s 38.39.831.810 I slot print_timing: id 1 | task 7270 | prompt eval time = 2230.97 ms / 99 tokens ( 22.54 ms per token, 44.38 tokens per second) 38.39.831.813 I slot print_timing: id 1 | task 7270 | eval time = 48365.21 ms / 181 tokens ( 268.70 ms per token, 3.72 tokens per second) 38.39.831.813 I slot print_timing: id 1 | task 7270 | total time = 50596.18 ms / 280 tokens 38.39.831.814 I slot print_timing: id 1 | task 7270 | graphs reused = 6562 38.39.831.814 I slot print_timing: id 1 | task 7270 | graph reallocs = 0 / 0 (same size) / (changed size) 38.39.831.898 I slot release: id 1 | task 7270 | stop processing: n_tokens = 1404, truncated = 0 38.40.161.912 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.816 38.40.161.959 I slot launch_slot_: id 1 | task 7457 | processing task, is_child = 0 38.41.779.908 I slot print_timing: id 2 | task 7343 | n_gen = 112, tg = 3.86 t/s, tg_3s = 2.83 t/s 38.42.387.556 I slot print_timing: id 3 | task 7156 | n_gen = 296, tg = 3.67 t/s, tg_3s = 2.01 t/s 38.44.920.854 I slot print_timing: id 2 | task 7343 | n_gen = 124, tg = 3.86 t/s, tg_3s = 3.82 t/s 38.45.612.334 I slot print_timing: id 3 | task 7156 | n_gen = 310, tg = 3.70 t/s, tg_3s = 4.34 t/s 38.48.138.360 I slot print_timing: id 2 | task 7343 | n_gen = 138, tg = 3.90 t/s, tg_3s = 4.35 t/s 38.48.827.567 I slot print_timing: id 3 | task 7156 | n_gen = 324, tg = 3.72 t/s, tg_3s = 4.35 t/s 38.51.354.554 I slot print_timing: id 2 | task 7343 | n_gen = 152, tg = 3.94 t/s, tg_3s = 4.35 t/s 38.52.043.845 I slot print_timing: id 3 | task 7156 | n_gen = 338, tg = 3.74 t/s, tg_3s = 4.35 t/s 38.54.570.697 I slot print_timing: id 2 | task 7343 | n_gen = 166, tg = 3.97 t/s, tg_3s = 4.35 t/s 38.55.260.250 I slot print_timing: id 3 | task 7156 | n_gen = 352, tg = 3.76 t/s, tg_3s = 4.35 t/s 38.57.786.836 I slot print_timing: id 2 | task 7343 | n_gen = 180, tg = 4.00 t/s, tg_3s = 4.35 t/s 38.58.476.307 I slot print_timing: id 3 | task 7156 | n_gen = 366, tg = 3.78 t/s, tg_3s = 4.35 t/s 39.00.773.675 I slot print_timing: id 0 | task 7437 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 39.01.003.849 I slot print_timing: id 2 | task 7343 | n_gen = 194, tg = 4.02 t/s, tg_3s = 4.35 t/s 39.01.234.700 I slot print_timing: id 1 | task 7457 | prompt eval time = 2225.25 ms / 90 tokens ( 24.73 ms per token, 40.44 tokens per second) 39.01.234.703 I slot print_timing: id 1 | task 7457 | eval time = 18847.48 ms / 83 tokens ( 229.85 ms per token, 4.35 tokens per second) 39.01.234.704 I slot print_timing: id 1 | task 7457 | total time = 21072.73 ms / 173 tokens 39.01.234.704 I slot print_timing: id 1 | task 7457 | graphs reused = 6643 39.01.234.704 I slot print_timing: id 1 | task 7457 | graph reallocs = 0 / 0 (same size) / (changed size) 39.01.234.747 I slot release: id 1 | task 7457 | stop processing: n_tokens = 1297, truncated = 0 39.01.564.293 I slot print_timing: id 3 | task 7156 | n_gen = 379, tg = 3.80 t/s, tg_3s = 4.21 t/s 39.01.564.298 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.884 39.01.564.326 I slot launch_slot_: id 1 | task 7543 | processing task, is_child = 0 39.04.275.934 I slot print_timing: id 0 | task 7437 | n_gen = 104, tg = 3.66 t/s, tg_3s = 1.14 t/s 39.04.276.103 I slot print_timing: id 2 | task 7343 | n_gen = 197, tg = 3.83 t/s, tg_3s = 0.92 t/s 39.04.882.381 I slot print_timing: id 3 | task 7156 | n_gen = 381, tg = 3.69 t/s, tg_3s = 0.60 t/s 39.07.183.020 I slot print_timing: id 2 | task 7343 | prompt eval time = 3861.61 ms / 113 tokens ( 34.17 ms per token, 29.26 tokens per second) 39.07.183.026 I slot print_timing: id 2 | task 7343 | eval time = 54131.90 ms / 208 tokens ( 261.51 ms per token, 3.82 tokens per second) 39.07.183.026 I slot print_timing: id 2 | task 7343 | total time = 57993.52 ms / 321 tokens 39.07.183.027 I slot print_timing: id 2 | task 7343 | graphs reused = 6652 39.07.183.027 I slot print_timing: id 2 | task 7343 | graph reallocs = 0 / 0 (same size) / (changed size) 39.07.183.077 I slot release: id 2 | task 7343 | stop processing: n_tokens = 1445, truncated = 0 39.07.511.705 I slot print_timing: id 0 | task 7437 | n_gen = 116, tg = 3.67 t/s, tg_3s = 3.71 t/s 39.07.512.096 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.793 39.07.512.155 I slot launch_slot_: id 2 | task 7557 | processing task, is_child = 0 39.09.407.740 I slot print_timing: id 3 | task 7156 | n_gen = 393, tg = 3.65 t/s, tg_3s = 2.65 t/s 39.10.645.304 I slot print_timing: id 0 | task 7437 | n_gen = 121, tg = 3.48 t/s, tg_3s = 1.60 t/s 39.12.484.439 I slot print_timing: id 3 | task 7156 | n_gen = 405, tg = 3.66 t/s, tg_3s = 3.90 t/s 39.13.862.472 I slot print_timing: id 0 | task 7437 | n_gen = 135, tg = 3.55 t/s, tg_3s = 4.35 t/s 39.15.701.931 I slot print_timing: id 3 | task 7156 | n_gen = 419, tg = 3.68 t/s, tg_3s = 4.35 t/s 39.17.080.579 I slot print_timing: id 0 | task 7437 | n_gen = 149, tg = 3.62 t/s, tg_3s = 4.35 t/s 39.18.919.439 I slot print_timing: id 3 | task 7156 | n_gen = 433, tg = 3.69 t/s, tg_3s = 4.35 t/s 39.20.298.334 I slot print_timing: id 0 | task 7437 | n_gen = 163, tg = 3.67 t/s, tg_3s = 4.35 t/s 39.22.137.600 I slot print_timing: id 3 | task 7156 | n_gen = 447, tg = 3.71 t/s, tg_3s = 4.35 t/s 39.23.516.372 I slot print_timing: id 0 | task 7437 | n_gen = 177, tg = 3.72 t/s, tg_3s = 4.35 t/s 39.25.356.549 I slot print_timing: id 3 | task 7156 | n_gen = 461, tg = 3.73 t/s, tg_3s = 4.35 t/s 39.26.735.246 I slot print_timing: id 0 | task 7437 | n_gen = 191, tg = 3.76 t/s, tg_3s = 4.35 t/s 39.28.574.334 I slot print_timing: id 3 | task 7156 | n_gen = 475, tg = 3.74 t/s, tg_3s = 4.35 t/s 39.29.723.295 I slot print_timing: id 1 | task 7543 | n_gen = 100, tg = 3.99 t/s, tg_3s = 4.03 t/s 39.29.953.054 I slot print_timing: id 0 | task 7437 | n_gen = 205, tg = 3.79 t/s, tg_3s = 4.35 t/s 39.31.792.800 I slot print_timing: id 3 | task 7156 | n_gen = 489, tg = 3.76 t/s, tg_3s = 4.35 t/s 39.32.712.154 I slot print_timing: id 2 | task 7557 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 39.32.942.064 I slot print_timing: id 1 | task 7543 | n_gen = 114, tg = 4.03 t/s, tg_3s = 4.35 t/s 39.33.171.897 I slot print_timing: id 0 | task 7437 | n_gen = 219, tg = 3.82 t/s, tg_3s = 4.35 t/s 39.33.172.302 I slot print_timing: id 3 | task 7156 | prompt eval time = 2612.47 ms / 152 tokens ( 17.19 ms per token, 58.18 tokens per second) 39.33.172.304 I slot print_timing: id 3 | task 7156 | eval time = 131184.20 ms / 495 tokens ( 265.56 ms per token, 3.77 tokens per second) 39.33.172.306 I slot print_timing: id 3 | task 7156 | total time = 133796.67 ms / 647 tokens 39.33.172.306 I slot print_timing: id 3 | task 7156 | graphs reused = 6752 39.33.172.307 I slot print_timing: id 3 | task 7156 | graph reallocs = 0 / 0 (same size) / (changed size) 39.33.172.352 I slot release: id 3 | task 7156 | stop processing: n_tokens = 1771, truncated = 0 39.33.390.758 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.647 39.33.390.791 I slot launch_slot_: id 3 | task 7662 | processing task, is_child = 0 39.36.005.207 I slot print_timing: id 1 | task 7543 | n_gen = 118, tg = 3.76 t/s, tg_3s = 1.31 t/s 39.36.005.390 I slot print_timing: id 2 | task 7557 | n_gen = 105, tg = 3.99 t/s, tg_3s = 1.52 t/s 39.36.237.513 I slot print_timing: id 0 | task 7437 | n_gen = 223, tg = 3.69 t/s, tg_3s = 1.30 t/s 39.39.225.362 I slot print_timing: id 1 | task 7543 | n_gen = 132, tg = 3.81 t/s, tg_3s = 4.35 t/s 39.39.225.520 I slot print_timing: id 2 | task 7557 | n_gen = 119, tg = 4.03 t/s, tg_3s = 4.35 t/s 39.39.454.935 I slot print_timing: id 0 | task 7437 | n_gen = 237, tg = 3.73 t/s, tg_3s = 4.35 t/s 39.42.441.965 I slot print_timing: id 1 | task 7543 | n_gen = 146, tg = 3.86 t/s, tg_3s = 4.35 t/s 39.42.442.108 I slot print_timing: id 2 | task 7557 | n_gen = 133, tg = 4.06 t/s, tg_3s = 4.35 t/s 39.42.671.586 I slot print_timing: id 0 | task 7437 | n_gen = 251, tg = 3.76 t/s, tg_3s = 4.35 t/s 39.45.659.050 I slot print_timing: id 1 | task 7543 | n_gen = 160, tg = 3.90 t/s, tg_3s = 4.35 t/s 39.45.659.201 I slot print_timing: id 2 | task 7557 | n_gen = 147, tg = 4.09 t/s, tg_3s = 4.35 t/s 39.45.888.844 I slot print_timing: id 0 | task 7437 | n_gen = 265, tg = 3.79 t/s, tg_3s = 4.35 t/s 39.48.876.923 I slot print_timing: id 1 | task 7543 | n_gen = 174, tg = 3.93 t/s, tg_3s = 4.35 t/s 39.48.877.086 I slot print_timing: id 2 | task 7557 | n_gen = 161, tg = 4.11 t/s, tg_3s = 4.35 t/s 39.49.106.631 I slot print_timing: id 0 | task 7437 | n_gen = 279, tg = 3.81 t/s, tg_3s = 4.35 t/s 39.52.094.114 I slot print_timing: id 1 | task 7543 | n_gen = 188, tg = 3.96 t/s, tg_3s = 4.35 t/s 39.52.094.263 I slot print_timing: id 2 | task 7557 | n_gen = 175, tg = 4.13 t/s, tg_3s = 4.35 t/s 39.52.323.859 I slot print_timing: id 0 | task 7437 | n_gen = 293, tg = 3.83 t/s, tg_3s = 4.35 t/s 39.55.317.008 I slot print_timing: id 1 | task 7543 | n_gen = 202, tg = 3.99 t/s, tg_3s = 4.34 t/s 39.55.317.155 I slot print_timing: id 2 | task 7557 | n_gen = 189, tg = 4.14 t/s, tg_3s = 4.34 t/s 39.55.546.800 I slot print_timing: id 0 | task 7437 | n_gen = 307, tg = 3.85 t/s, tg_3s = 4.34 t/s 39.58.534.644 I slot print_timing: id 1 | task 7543 | n_gen = 216, tg = 4.01 t/s, tg_3s = 4.35 t/s 39.58.534.793 I slot print_timing: id 2 | task 7557 | n_gen = 203, tg = 4.16 t/s, tg_3s = 4.35 t/s 39.58.764.511 I slot print_timing: id 0 | task 7437 | n_gen = 321, tg = 3.87 t/s, tg_3s = 4.35 t/s 39.58.764.951 I slot print_timing: id 3 | task 7662 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 40.00.143.467 I slot print_timing: id 0 | task 7437 | prompt eval time = 2208.58 ms / 118 tokens ( 18.72 ms per token, 53.43 tokens per second) 40.00.143.473 I slot print_timing: id 0 | task 7437 | eval time = 83991.29 ms / 327 tokens ( 257.64 ms per token, 3.88 tokens per second) 40.00.143.474 I slot print_timing: id 0 | task 7437 | total time = 86199.88 ms / 445 tokens 40.00.143.475 I slot print_timing: id 0 | task 7437 | graphs reused = 6855 40.00.143.475 I slot print_timing: id 0 | task 7437 | graph reallocs = 0 / 0 (same size) / (changed size) 40.00.143.523 I slot release: id 0 | task 7437 | stop processing: n_tokens = 1569, truncated = 0 40.00.362.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.730 40.00.362.246 I slot launch_slot_: id 0 | task 7771 | processing task, is_child = 0 40.02.133.019 I slot print_timing: id 1 | task 7543 | n_gen = 225, tg = 3.91 t/s, tg_3s = 2.50 t/s 40.02.133.172 I slot print_timing: id 2 | task 7557 | n_gen = 212, tg = 4.04 t/s, tg_3s = 2.50 t/s 40.02.133.338 I slot print_timing: id 3 | task 7662 | n_gen = 108, tg = 4.10 t/s, tg_3s = 2.38 t/s 40.05.314.580 I slot print_timing: id 1 | task 7543 | n_gen = 238, tg = 3.92 t/s, tg_3s = 4.09 t/s 40.05.314.727 I slot print_timing: id 2 | task 7557 | n_gen = 225, tg = 4.05 t/s, tg_3s = 4.09 t/s 40.05.314.869 I slot print_timing: id 3 | task 7662 | n_gen = 121, tg = 4.09 t/s, tg_3s = 4.09 t/s 40.08.075.277 I slot print_timing: id 2 | task 7557 | prompt eval time = 2441.89 ms / 107 tokens ( 22.82 ms per token, 43.82 tokens per second) 40.08.075.280 I slot print_timing: id 2 | task 7557 | eval time = 58121.23 ms / 237 tokens ( 246.28 ms per token, 4.06 tokens per second) 40.08.075.281 I slot print_timing: id 2 | task 7557 | total time = 60563.12 ms / 344 tokens 40.08.075.281 I slot print_timing: id 2 | task 7557 | graphs reused = 6878 40.08.075.282 I slot print_timing: id 2 | task 7557 | graph reallocs = 0 / 0 (same size) / (changed size) 40.08.075.341 I slot release: id 2 | task 7557 | stop processing: n_tokens = 1468, truncated = 0 40.08.403.505 I slot print_timing: id 1 | task 7543 | n_gen = 251, tg = 3.94 t/s, tg_3s = 4.21 t/s 40.08.403.670 I slot print_timing: id 3 | task 7662 | n_gen = 134, tg = 4.11 t/s, tg_3s = 4.21 t/s 40.08.403.676 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.781 40.08.403.705 I slot launch_slot_: id 2 | task 7799 | processing task, is_child = 0 40.11.459.142 I slot print_timing: id 1 | task 7543 | n_gen = 254, tg = 3.80 t/s, tg_3s = 0.98 t/s 40.11.459.427 I slot print_timing: id 3 | task 7662 | n_gen = 137, tg = 3.84 t/s, tg_3s = 0.98 t/s 40.14.674.931 I slot print_timing: id 1 | task 7543 | n_gen = 268, tg = 3.83 t/s, tg_3s = 4.35 t/s 40.14.675.207 I slot print_timing: id 3 | task 7662 | n_gen = 151, tg = 3.88 t/s, tg_3s = 4.35 t/s 40.17.892.974 I slot print_timing: id 1 | task 7543 | n_gen = 282, tg = 3.85 t/s, tg_3s = 4.35 t/s 40.17.893.266 I slot print_timing: id 3 | task 7662 | n_gen = 165, tg = 3.92 t/s, tg_3s = 4.35 t/s 40.21.109.659 I slot print_timing: id 1 | task 7543 | n_gen = 296, tg = 3.87 t/s, tg_3s = 4.35 t/s 40.21.109.974 I slot print_timing: id 3 | task 7662 | n_gen = 179, tg = 3.95 t/s, tg_3s = 4.35 t/s 40.24.328.016 I slot print_timing: id 1 | task 7543 | n_gen = 310, tg = 3.89 t/s, tg_3s = 4.35 t/s 40.24.328.293 I slot print_timing: id 3 | task 7662 | n_gen = 193, tg = 3.97 t/s, tg_3s = 4.35 t/s 40.27.544.860 I slot print_timing: id 1 | task 7543 | n_gen = 324, tg = 3.91 t/s, tg_3s = 4.35 t/s 40.27.545.158 I slot print_timing: id 3 | task 7662 | n_gen = 207, tg = 4.00 t/s, tg_3s = 4.35 t/s 40.27.774.460 I slot print_timing: id 0 | task 7771 | n_gen = 100, tg = 3.93 t/s, tg_3s = 3.97 t/s 40.30.762.329 I slot print_timing: id 1 | task 7543 | n_gen = 338, tg = 3.92 t/s, tg_3s = 4.35 t/s 40.30.762.618 I slot print_timing: id 3 | task 7662 | n_gen = 221, tg = 4.02 t/s, tg_3s = 4.35 t/s 40.30.992.134 I slot print_timing: id 0 | task 7771 | n_gen = 114, tg = 3.97 t/s, tg_3s = 4.35 t/s 40.33.980.717 I slot print_timing: id 1 | task 7543 | n_gen = 352, tg = 3.94 t/s, tg_3s = 4.35 t/s 40.33.980.864 I slot print_timing: id 2 | task 7799 | n_gen = 100, tg = 4.35 t/s, tg_3s = 4.39 t/s 40.33.981.010 I slot print_timing: id 3 | task 7662 | n_gen = 235, tg = 4.04 t/s, tg_3s = 4.35 t/s 40.34.210.440 I slot print_timing: id 0 | task 7771 | n_gen = 128, tg = 4.01 t/s, tg_3s = 4.35 t/s 40.37.200.604 I slot print_timing: id 1 | task 7543 | n_gen = 366, tg = 3.95 t/s, tg_3s = 4.35 t/s 40.37.200.760 I slot print_timing: id 2 | task 7799 | n_gen = 114, tg = 4.35 t/s, tg_3s = 4.35 t/s 40.37.200.924 I slot print_timing: id 3 | task 7662 | n_gen = 249, tg = 4.05 t/s, tg_3s = 4.35 t/s 40.37.431.126 I slot print_timing: id 0 | task 7771 | n_gen = 142, tg = 4.04 t/s, tg_3s = 4.35 t/s 40.40.421.756 I slot print_timing: id 1 | task 7543 | n_gen = 380, tg = 3.97 t/s, tg_3s = 4.35 t/s 40.40.421.903 I slot print_timing: id 2 | task 7799 | n_gen = 128, tg = 4.35 t/s, tg_3s = 4.35 t/s 40.40.422.048 I slot print_timing: id 3 | task 7662 | n_gen = 263, tg = 4.07 t/s, tg_3s = 4.35 t/s 40.40.651.562 I slot print_timing: id 0 | task 7771 | n_gen = 156, tg = 4.07 t/s, tg_3s = 4.35 t/s 40.42.722.955 I slot print_timing: id 1 | task 7543 | prompt eval time = 3317.74 ms / 170 tokens ( 19.52 ms per token, 51.24 tokens per second) 40.42.722.960 I slot print_timing: id 1 | task 7543 | eval time = 97840.88 ms / 390 tokens ( 251.52 ms per token, 3.98 tokens per second) 40.42.722.961 I slot print_timing: id 1 | task 7543 | total time = 101158.62 ms / 560 tokens 40.42.722.961 I slot print_timing: id 1 | task 7543 | graphs reused = 7014 40.42.722.962 I slot print_timing: id 1 | task 7543 | graph reallocs = 0 / 0 (same size) / (changed size) 40.42.723.023 I slot release: id 1 | task 7543 | stop processing: n_tokens = 1684, truncated = 0 40.43.051.950 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.681 40.43.051.977 I slot launch_slot_: id 1 | task 7940 | processing task, is_child = 0 40.45.004.524 I slot print_timing: id 0 | task 7771 | n_gen = 167, tg = 3.91 t/s, tg_3s = 2.53 t/s 40.45.004.683 I slot print_timing: id 2 | task 7799 | n_gen = 140, tg = 4.12 t/s, tg_3s = 2.62 t/s 40.45.004.846 I slot print_timing: id 3 | task 7662 | n_gen = 275, tg = 3.97 t/s, tg_3s = 2.62 t/s 40.48.140.800 I slot print_timing: id 0 | task 7771 | n_gen = 179, tg = 3.90 t/s, tg_3s = 3.83 t/s 40.48.141.090 I slot print_timing: id 2 | task 7799 | n_gen = 152, tg = 4.09 t/s, tg_3s = 3.83 t/s 40.48.141.232 I slot print_timing: id 3 | task 7662 | n_gen = 287, tg = 3.96 t/s, tg_3s = 3.83 t/s 40.51.357.791 I slot print_timing: id 0 | task 7771 | n_gen = 193, tg = 3.93 t/s, tg_3s = 4.35 t/s 40.51.358.060 I slot print_timing: id 2 | task 7799 | n_gen = 166, tg = 4.11 t/s, tg_3s = 4.35 t/s 40.51.358.203 I slot print_timing: id 3 | task 7662 | n_gen = 301, tg = 3.98 t/s, tg_3s = 4.35 t/s 40.52.506.766 I slot print_timing: id 0 | task 7771 | prompt eval time = 2193.00 ms / 109 tokens ( 20.12 ms per token, 49.70 tokens per second) 40.52.506.771 I slot print_timing: id 0 | task 7771 | eval time = 49951.52 ms / 198 tokens ( 253.56 ms per token, 3.94 tokens per second) 40.52.506.772 I slot print_timing: id 0 | task 7771 | total time = 52144.51 ms / 307 tokens 40.52.506.773 I slot print_timing: id 0 | task 7771 | graphs reused = 7043 40.52.506.773 I slot print_timing: id 0 | task 7771 | graph reallocs = 0 / 0 (same size) / (changed size) 40.52.506.819 I slot release: id 0 | task 7771 | stop processing: n_tokens = 1431, truncated = 0 40.52.725.499 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.801 40.52.725.537 I slot launch_slot_: id 0 | task 7974 | processing task, is_child = 0 40.54.873.378 I slot print_timing: id 2 | task 7799 | n_gen = 173, tg = 3.94 t/s, tg_3s = 1.99 t/s 40.54.873.545 I slot print_timing: id 3 | task 7662 | n_gen = 308, tg = 3.89 t/s, tg_3s = 1.99 t/s 40.56.217.996 I slot print_timing: id 3 | task 7662 | prompt eval time = 2614.81 ms / 147 tokens ( 17.79 ms per token, 56.22 tokens per second) 40.56.217.999 I slot print_timing: id 3 | task 7662 | eval time = 80212.38 ms / 313 tokens ( 257.09 ms per token, 3.89 tokens per second) 40.56.218.000 I slot print_timing: id 3 | task 7662 | total time = 82827.20 ms / 460 tokens 40.56.218.000 I slot print_timing: id 3 | task 7662 | graphs reused = 7047 40.56.218.001 I slot print_timing: id 3 | task 7662 | graph reallocs = 0 / 0 (same size) / (changed size) 40.56.218.054 I slot release: id 3 | task 7662 | stop processing: n_tokens = 1584, truncated = 0 40.56.435.511 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.723 40.56.435.544 I slot launch_slot_: id 3 | task 7982 | processing task, is_child = 0 40.58.233.322 I slot print_timing: id 2 | task 7799 | n_gen = 180, tg = 3.81 t/s, tg_3s = 2.08 t/s 41.01.426.066 I slot print_timing: id 2 | task 7799 | n_gen = 193, tg = 3.82 t/s, tg_3s = 4.07 t/s 41.04.639.901 I slot print_timing: id 2 | task 7799 | n_gen = 207, tg = 3.86 t/s, tg_3s = 4.36 t/s 41.07.854.573 I slot print_timing: id 2 | task 7799 | n_gen = 221, tg = 3.89 t/s, tg_3s = 4.36 t/s 41.11.069.669 I slot print_timing: id 2 | task 7799 | n_gen = 235, tg = 3.91 t/s, tg_3s = 4.35 t/s 41.12.218.657 I slot print_timing: id 1 | task 7940 | n_gen = 100, tg = 3.72 t/s, tg_3s = 3.76 t/s 41.14.285.455 I slot print_timing: id 2 | task 7799 | n_gen = 249, tg = 3.93 t/s, tg_3s = 4.35 t/s 41.15.434.964 I slot print_timing: id 1 | task 7940 | n_gen = 114, tg = 3.79 t/s, tg_3s = 4.35 t/s 41.16.813.599 I slot print_timing: id 1 | task 7940 | prompt eval time = 2557.84 ms / 110 tokens ( 23.25 ms per token, 43.00 tokens per second) 41.16.813.602 I slot print_timing: id 1 | task 7940 | eval time = 31203.77 ms / 120 tokens ( 262.22 ms per token, 3.81 tokens per second) 41.16.813.602 I slot print_timing: id 1 | task 7940 | total time = 33761.61 ms / 230 tokens 41.16.813.603 I slot print_timing: id 1 | task 7940 | graphs reused = 7125 41.16.813.603 I slot print_timing: id 1 | task 7940 | graph reallocs = 0 / 0 (same size) / (changed size) 41.16.813.661 I slot release: id 1 | task 7940 | stop processing: n_tokens = 1354, truncated = 0 41.17.142.460 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.846 41.17.142.488 I slot launch_slot_: id 1 | task 8065 | processing task, is_child = 0 41.18.763.871 I slot print_timing: id 2 | task 7799 | n_gen = 262, tg = 3.86 t/s, tg_3s = 2.90 t/s 41.21.667.461 I slot print_timing: id 0 | task 7974 | n_gen = 100, tg = 3.75 t/s, tg_3s = 3.79 t/s 41.21.899.995 I slot print_timing: id 2 | task 7799 | n_gen = 274, tg = 3.86 t/s, tg_3s = 3.83 t/s 41.23.277.936 I slot print_timing: id 3 | task 7982 | n_gen = 100, tg = 4.02 t/s, tg_3s = 4.06 t/s 41.24.885.217 I slot print_timing: id 0 | task 7974 | n_gen = 114, tg = 3.82 t/s, tg_3s = 4.35 t/s 41.25.115.203 I slot print_timing: id 2 | task 7799 | n_gen = 288, tg = 3.88 t/s, tg_3s = 4.35 t/s 41.26.494.692 I slot print_timing: id 3 | task 7982 | n_gen = 114, tg = 4.06 t/s, tg_3s = 4.35 t/s 41.28.102.283 I slot print_timing: id 0 | task 7974 | n_gen = 128, tg = 3.87 t/s, tg_3s = 4.35 t/s 41.28.332.152 I slot print_timing: id 2 | task 7799 | n_gen = 302, tg = 3.90 t/s, tg_3s = 4.35 t/s 41.29.710.405 I slot print_timing: id 3 | task 7982 | n_gen = 128, tg = 4.09 t/s, tg_3s = 4.35 t/s 41.31.317.598 I slot print_timing: id 0 | task 7974 | n_gen = 142, tg = 3.91 t/s, tg_3s = 4.35 t/s 41.31.547.593 I slot print_timing: id 2 | task 7799 | n_gen = 316, tg = 3.92 t/s, tg_3s = 4.35 t/s 41.32.007.233 I slot print_timing: id 3 | task 7982 | prompt eval time = 2231.91 ms / 122 tokens ( 18.29 ms per token, 54.66 tokens per second) 41.32.007.239 I slot print_timing: id 3 | task 7982 | eval time = 33339.77 ms / 138 tokens ( 243.36 ms per token, 4.11 tokens per second) 41.32.007.240 I slot print_timing: id 3 | task 7982 | total time = 35571.68 ms / 260 tokens 41.32.007.240 I slot print_timing: id 3 | task 7982 | graphs reused = 7178 41.32.007.241 I slot print_timing: id 3 | task 7982 | graph reallocs = 0 / 0 (same size) / (changed size) 41.32.007.287 I slot release: id 3 | task 7982 | stop processing: n_tokens = 1384, truncated = 0 41.32.225.520 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.828 41.32.225.551 I slot launch_slot_: id 3 | task 8124 | processing task, is_child = 0 41.34.446.869 I slot print_timing: id 0 | task 7974 | n_gen = 148, tg = 3.75 t/s, tg_3s = 1.92 t/s 41.34.680.572 I slot print_timing: id 2 | task 7799 | n_gen = 322, tg = 3.85 t/s, tg_3s = 1.92 t/s 41.34.910.141 I slot print_timing: id 0 | task 7974 | prompt eval time = 2570.84 ms / 134 tokens ( 19.19 ms per token, 52.12 tokens per second) 41.34.910.143 I slot print_timing: id 0 | task 7974 | eval time = 39613.76 ms / 150 tokens ( 265.86 ms per token, 3.76 tokens per second) 41.34.910.143 I slot print_timing: id 0 | task 7974 | total time = 42184.60 ms / 284 tokens 41.34.910.144 I slot print_timing: id 0 | task 7974 | graphs reused = 7179 41.34.910.144 I slot print_timing: id 0 | task 7974 | graph reallocs = 0 / 0 (same size) / (changed size) 41.34.910.200 I slot release: id 0 | task 7974 | stop processing: n_tokens = 1408, truncated = 0 41.35.128.266 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.814 41.35.128.308 I slot launch_slot_: id 0 | task 8130 | processing task, is_child = 0 41.37.778.826 I slot print_timing: id 2 | task 7799 | n_gen = 328, tg = 3.78 t/s, tg_3s = 1.94 t/s 41.40.992.243 I slot print_timing: id 2 | task 7799 | n_gen = 342, tg = 3.80 t/s, tg_3s = 4.36 t/s 41.41.681.876 I slot print_timing: id 2 | task 7799 | prompt eval time = 2823.05 ms / 139 tokens ( 20.31 ms per token, 49.24 tokens per second) 41.41.681.882 I slot print_timing: id 2 | task 7799 | eval time = 90455.11 ms / 345 tokens ( 262.95 ms per token, 3.80 tokens per second) 41.41.681.882 I slot print_timing: id 2 | task 7799 | total time = 93278.16 ms / 484 tokens 41.41.681.883 I slot print_timing: id 2 | task 7799 | graphs reused = 7198 41.41.681.883 I slot print_timing: id 2 | task 7799 | graph reallocs = 0 / 0 (same size) / (changed size) 41.41.681.930 I slot release: id 2 | task 7799 | stop processing: n_tokens = 1608, truncated = 0 41.42.010.227 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.713 41.42.010.267 I slot launch_slot_: id 2 | task 8153 | processing task, is_child = 0 41.47.664.518 I slot print_timing: id 1 | task 8065 | n_gen = 100, tg = 3.50 t/s, tg_3s = 3.53 t/s 41.50.880.721 I slot print_timing: id 1 | task 8065 | n_gen = 114, tg = 3.59 t/s, tg_3s = 4.35 t/s 41.52.947.079 I slot print_timing: id 1 | task 8065 | prompt eval time = 2225.79 ms / 96 tokens ( 23.19 ms per token, 43.13 tokens per second) 41.52.947.083 I slot print_timing: id 1 | task 8065 | eval time = 33578.79 ms / 123 tokens ( 275.24 ms per token, 3.63 tokens per second) 41.52.947.084 I slot print_timing: id 1 | task 8065 | total time = 35804.58 ms / 219 tokens 41.52.947.084 I slot print_timing: id 1 | task 8065 | graphs reused = 7234 41.52.947.085 I slot print_timing: id 1 | task 8065 | graph reallocs = 0 / 0 (same size) / (changed size) 41.52.947.148 I slot release: id 1 | task 8065 | stop processing: n_tokens = 1343, truncated = 0 41.53.276.088 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.853 41.53.276.123 I slot launch_slot_: id 1 | task 8194 | processing task, is_child = 0 42.03.938.923 I slot print_timing: id 3 | task 8124 | n_gen = 100, tg = 3.36 t/s, tg_3s = 3.39 t/s 42.05.086.995 I slot print_timing: id 0 | task 8130 | n_gen = 100, tg = 3.56 t/s, tg_3s = 3.60 t/s 42.06.005.938 I slot print_timing: id 3 | task 8124 | prompt eval time = 2221.80 ms / 111 tokens ( 20.02 ms per token, 49.96 tokens per second) 42.06.005.943 I slot print_timing: id 3 | task 8124 | eval time = 31558.58 ms / 109 tokens ( 292.21 ms per token, 3.42 tokens per second) 42.06.005.944 I slot print_timing: id 3 | task 8124 | total time = 33780.38 ms / 220 tokens 42.06.005.944 I slot print_timing: id 3 | task 8124 | graphs reused = 7274 42.06.005.945 I slot print_timing: id 3 | task 8124 | graph reallocs = 0 / 0 (same size) / (changed size) 42.06.005.994 I slot release: id 3 | task 8124 | stop processing: n_tokens = 1344, truncated = 0 42.06.223.659 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.853 42.06.223.697 I slot launch_slot_: id 3 | task 8239 | processing task, is_child = 0 42.08.442.586 I slot print_timing: id 0 | task 8130 | n_gen = 107, tg = 3.41 t/s, tg_3s = 2.09 t/s 42.11.659.930 I slot print_timing: id 0 | task 8130 | n_gen = 121, tg = 3.49 t/s, tg_3s = 4.35 t/s 42.11.889.900 I slot print_timing: id 2 | task 8153 | n_gen = 100, tg = 3.61 t/s, tg_3s = 3.64 t/s 42.12.348.836 I slot print_timing: id 0 | task 8130 | prompt eval time = 2187.77 ms / 101 tokens ( 21.66 ms per token, 46.17 tokens per second) 42.12.348.841 I slot print_timing: id 0 | task 8130 | eval time = 35032.75 ms / 124 tokens ( 284.82 ms per token, 3.51 tokens per second) 42.12.348.841 I slot print_timing: id 0 | task 8130 | total time = 37220.52 ms / 225 tokens 42.12.348.842 I slot print_timing: id 0 | task 8130 | graphs reused = 7290 42.12.348.842 I slot print_timing: id 0 | task 8130 | graph reallocs = 0 / 0 (same size) / (changed size) 42.12.348.887 I slot release: id 0 | task 8130 | stop processing: n_tokens = 1349, truncated = 0 42.12.567.648 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.850 42.12.567.683 I slot launch_slot_: id 0 | task 8260 | processing task, is_child = 0 42.15.014.831 I slot print_timing: id 2 | task 8153 | n_gen = 106, tg = 3.44 t/s, tg_3s = 1.92 t/s 42.18.229.036 I slot print_timing: id 2 | task 8153 | n_gen = 120, tg = 3.52 t/s, tg_3s = 4.36 t/s 42.21.443.325 I slot print_timing: id 2 | task 8153 | n_gen = 134, tg = 3.60 t/s, tg_3s = 4.36 t/s 42.22.132.322 I slot print_timing: id 2 | task 8153 | prompt eval time = 2438.18 ms / 108 tokens ( 22.58 ms per token, 44.30 tokens per second) 42.22.132.327 I slot print_timing: id 2 | task 8153 | eval time = 37683.87 ms / 137 tokens ( 277.09 ms per token, 3.61 tokens per second) 42.22.132.327 I slot print_timing: id 2 | task 8153 | total time = 40122.05 ms / 245 tokens 42.22.132.328 I slot print_timing: id 2 | task 8153 | graphs reused = 7322 42.22.132.328 I slot print_timing: id 2 | task 8153 | graph reallocs = 0 / 0 (same size) / (changed size) 42.22.132.371 I slot release: id 2 | task 8153 | stop processing: n_tokens = 1369, truncated = 0 42.22.461.134 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.837 42.22.461.169 I slot launch_slot_: id 2 | task 8296 | processing task, is_child = 0 42.24.566.460 I slot print_timing: id 1 | task 8194 | n_gen = 100, tg = 3.54 t/s, tg_3s = 3.57 t/s 42.27.783.463 I slot print_timing: id 1 | task 8194 | n_gen = 114, tg = 3.62 t/s, tg_3s = 4.35 t/s 42.30.997.774 I slot print_timing: id 1 | task 8194 | n_gen = 128, tg = 3.69 t/s, tg_3s = 4.36 t/s 42.34.212.324 I slot print_timing: id 1 | task 8194 | n_gen = 142, tg = 3.75 t/s, tg_3s = 4.36 t/s 42.34.671.458 I slot print_timing: id 3 | task 8239 | n_gen = 100, tg = 3.77 t/s, tg_3s = 3.81 t/s 42.37.426.685 I slot print_timing: id 1 | task 8194 | n_gen = 156, tg = 3.80 t/s, tg_3s = 4.36 t/s 42.37.886.307 I slot print_timing: id 3 | task 8239 | n_gen = 114, tg = 3.84 t/s, tg_3s = 4.35 t/s 42.39.263.663 I slot print_timing: id 0 | task 8260 | n_gen = 100, tg = 4.04 t/s, tg_3s = 4.08 t/s 42.40.642.823 I slot print_timing: id 1 | task 8194 | n_gen = 170, tg = 3.84 t/s, tg_3s = 4.35 t/s 42.40.872.749 I slot print_timing: id 2 | task 8296 | prompt eval time = 2105.47 ms / 95 tokens ( 22.16 ms per token, 45.12 tokens per second) 42.40.872.752 I slot print_timing: id 2 | task 8296 | eval time = 16306.10 ms / 72 tokens ( 229.66 ms per token, 4.35 tokens per second) 42.40.872.753 I slot print_timing: id 2 | task 8296 | total time = 18411.57 ms / 167 tokens 42.40.872.754 I slot print_timing: id 2 | task 8296 | graphs reused = 7392 42.40.872.754 I slot print_timing: id 2 | task 8296 | graph reallocs = 0 / 0 (same size) / (changed size) 42.40.872.807 I slot release: id 2 | task 8296 | stop processing: n_tokens = 1291, truncated = 0 42.41.201.672 I slot print_timing: id 3 | task 8239 | n_gen = 128, tg = 3.88 t/s, tg_3s = 4.22 t/s 42.41.201.677 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.888 42.41.201.708 I slot launch_slot_: id 2 | task 8371 | processing task, is_child = 0 42.43.480.302 I slot print_timing: id 0 | task 8260 | n_gen = 109, tg = 3.76 t/s, tg_3s = 2.13 t/s 42.44.025.161 I slot print_timing: id 1 | task 8194 | n_gen = 174, tg = 3.65 t/s, tg_3s = 1.18 t/s 42.44.257.605 I slot print_timing: id 3 | task 8239 | n_gen = 131, tg = 3.63 t/s, tg_3s = 0.98 t/s 42.44.486.651 I slot print_timing: id 3 | task 8239 | prompt eval time = 2219.46 ms / 110 tokens ( 20.18 ms per token, 49.56 tokens per second) 42.44.486.653 I slot print_timing: id 3 | task 8239 | eval time = 36043.49 ms / 132 tokens ( 275.14 ms per token, 3.63 tokens per second) 42.44.486.654 I slot print_timing: id 3 | task 8239 | total time = 38262.95 ms / 242 tokens 42.44.486.654 I slot print_timing: id 3 | task 8239 | graphs reused = 7393 42.44.486.655 I slot print_timing: id 3 | task 8239 | graph reallocs = 0 / 0 (same size) / (changed size) 42.44.488.049 I slot release: id 3 | task 8239 | stop processing: n_tokens = 1366, truncated = 0 42.44.706.281 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.839 42.44.706.314 I slot launch_slot_: id 3 | task 8377 | processing task, is_child = 0 42.46.590.805 I slot print_timing: id 0 | task 8260 | n_gen = 115, tg = 3.58 t/s, tg_3s = 1.93 t/s 42.47.052.565 I slot print_timing: id 1 | task 8194 | n_gen = 181, tg = 3.57 t/s, tg_3s = 2.31 t/s 42.49.808.810 I slot print_timing: id 0 | task 8260 | n_gen = 129, tg = 3.65 t/s, tg_3s = 4.35 t/s 42.50.268.324 I slot print_timing: id 1 | task 8194 | n_gen = 195, tg = 3.61 t/s, tg_3s = 4.35 t/s 42.53.022.611 I slot print_timing: id 0 | task 8260 | n_gen = 143, tg = 3.71 t/s, tg_3s = 4.36 t/s 42.53.483.327 I slot print_timing: id 1 | task 8194 | n_gen = 209, tg = 3.66 t/s, tg_3s = 4.35 t/s 42.56.239.745 I slot print_timing: id 0 | task 8260 | n_gen = 157, tg = 3.76 t/s, tg_3s = 4.35 t/s 42.56.699.213 I slot print_timing: id 1 | task 8194 | n_gen = 223, tg = 3.69 t/s, tg_3s = 4.35 t/s 42.59.455.181 I slot print_timing: id 0 | task 8260 | n_gen = 171, tg = 3.81 t/s, tg_3s = 4.35 t/s 42.59.914.630 I slot print_timing: id 1 | task 8194 | n_gen = 237, tg = 3.73 t/s, tg_3s = 4.35 t/s 43.02.675.071 I slot print_timing: id 0 | task 8260 | n_gen = 185, tg = 3.84 t/s, tg_3s = 4.35 t/s 43.03.134.730 I slot print_timing: id 1 | task 8194 | n_gen = 251, tg = 3.76 t/s, tg_3s = 4.35 t/s 43.05.891.917 I slot print_timing: id 0 | task 8260 | n_gen = 199, tg = 3.87 t/s, tg_3s = 4.35 t/s 43.06.351.607 I slot print_timing: id 1 | task 8194 | n_gen = 265, tg = 3.78 t/s, tg_3s = 4.35 t/s 43.08.189.715 I slot print_timing: id 2 | task 8371 | n_gen = 100, tg = 4.10 t/s, tg_3s = 4.14 t/s 43.09.106.615 I slot print_timing: id 0 | task 8260 | n_gen = 213, tg = 3.90 t/s, tg_3s = 4.35 t/s 43.09.107.021 I slot print_timing: id 3 | task 8377 | prompt eval time = 1884.95 ms / 96 tokens ( 19.63 ms per token, 50.93 tokens per second) 43.09.107.025 I slot print_timing: id 3 | task 8377 | eval time = 22515.76 ms / 99 tokens ( 229.75 ms per token, 4.35 tokens per second) 43.09.107.026 I slot print_timing: id 3 | task 8377 | total time = 24400.70 ms / 195 tokens 43.09.107.026 I slot print_timing: id 3 | task 8377 | graphs reused = 7489 43.09.107.027 I slot print_timing: id 3 | task 8377 | graph reallocs = 0 / 0 (same size) / (changed size) 43.09.107.069 I slot release: id 3 | task 8377 | stop processing: n_tokens = 1319, truncated = 0 43.09.541.022 I slot print_timing: id 1 | task 8194 | n_gen = 279, tg = 3.81 t/s, tg_3s = 4.39 t/s 43.11.266.319 I slot print_timing: id 2 | task 8371 | n_gen = 114, tg = 4.15 t/s, tg_3s = 4.55 t/s 43.12.129.155 I slot print_timing: id 0 | task 8260 | n_gen = 227, tg = 3.94 t/s, tg_3s = 4.63 t/s 43.12.560.549 I slot print_timing: id 1 | task 8194 | n_gen = 293, tg = 3.84 t/s, tg_3s = 4.64 t/s 43.14.285.899 I slot print_timing: id 2 | task 8371 | n_gen = 128, tg = 4.20 t/s, tg_3s = 4.64 t/s 43.15.148.724 I slot print_timing: id 0 | task 8260 | n_gen = 241, tg = 3.98 t/s, tg_3s = 4.64 t/s 43.15.579.650 I slot print_timing: id 1 | task 8194 | n_gen = 307, tg = 3.87 t/s, tg_3s = 4.64 t/s 43.16.873.121 I slot print_timing: id 1 | task 8194 | prompt eval time = 3310.98 ms / 166 tokens ( 19.95 ms per token, 50.14 tokens per second) 43.16.873.127 I slot print_timing: id 1 | task 8194 | eval time = 80286.01 ms / 313 tokens ( 257.33 ms per token, 3.89 tokens per second) 43.16.873.128 I slot print_timing: id 1 | task 8194 | total time = 83596.99 ms / 479 tokens 43.16.873.128 I slot print_timing: id 1 | task 8194 | graphs reused = 7524 43.16.873.129 I slot print_timing: id 1 | task 8194 | graph reallocs = 0 / 0 (same size) / (changed size) 43.16.873.177 I slot release: id 1 | task 8194 | stop processing: n_tokens = 1603, truncated = 0 43.17.376.030 I slot print_timing: id 2 | task 8371 | n_gen = 142, tg = 4.23 t/s, tg_3s = 4.53 t/s 43.18.380.576 I slot print_timing: id 0 | task 8260 | n_gen = 255, tg = 3.99 t/s, tg_3s = 4.33 t/s 43.19.888.160 I slot print_timing: id 0 | task 8260 | prompt eval time = 2214.84 ms / 128 tokens ( 17.30 ms per token, 57.79 tokens per second) 43.19.888.168 I slot print_timing: id 0 | task 8260 | eval time = 65105.63 ms / 261 tokens ( 250.41 ms per token, 3.99 tokens per second) 43.19.888.169 I slot print_timing: id 0 | task 8260 | total time = 67320.47 ms / 389 tokens 43.19.888.169 I slot print_timing: id 0 | task 8260 | graphs reused = 7524 43.19.888.170 I slot print_timing: id 0 | task 8260 | graph reallocs = 0 / 0 (same size) / (changed size) 43.19.888.212 I slot release: id 0 | task 8260 | stop processing: n_tokens = 1513, truncated = 0 43.20.385.257 I slot print_timing: id 2 | task 8371 | n_gen = 156, tg = 4.26 t/s, tg_3s = 4.65 t/s 43.23.491.000 I slot print_timing: id 2 | task 8371 | n_gen = 181, tg = 4.56 t/s, tg_3s = 8.05 t/s 43.26.598.943 I slot print_timing: id 2 | task 8371 | n_gen = 206, tg = 4.82 t/s, tg_3s = 8.04 t/s 43.29.706.427 I slot print_timing: id 2 | task 8371 | n_gen = 231, tg = 5.03 t/s, tg_3s = 8.05 t/s 43.32.816.500 I slot print_timing: id 2 | task 8371 | n_gen = 256, tg = 5.23 t/s, tg_3s = 8.04 t/s 43.35.927.862 I slot print_timing: id 2 | task 8371 | n_gen = 281, tg = 5.39 t/s, tg_3s = 8.04 t/s 43.39.035.658 I slot print_timing: id 2 | task 8371 | n_gen = 306, tg = 5.54 t/s, tg_3s = 8.04 t/s 43.42.145.732 I slot print_timing: id 2 | task 8371 | n_gen = 331, tg = 5.68 t/s, tg_3s = 8.04 t/s 43.45.254.790 I slot print_timing: id 2 | task 8371 | n_gen = 356, tg = 5.80 t/s, tg_3s = 8.04 t/s 43.46.249.094 I slot print_timing: id 2 | task 8371 | prompt eval time = 2823.63 ms / 142 tokens ( 19.88 ms per token, 50.29 tokens per second) 43.46.249.097 I slot print_timing: id 2 | task 8371 | eval time = 62223.75 ms / 364 tokens ( 171.42 ms per token, 5.83 tokens per second) 43.46.249.097 I slot print_timing: id 2 | task 8371 | total time = 65047.38 ms / 506 tokens 43.46.249.097 I slot print_timing: id 2 | task 8371 | graphs reused = 7735 43.46.249.098 I slot print_timing: id 2 | task 8371 | graph reallocs = 0 / 0 (same size) / (changed size) 43.46.249.142 I slot release: id 2 | task 8371 | stop processing: n_tokens = 1630, truncated = 0 43.46.290.544 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1319, t_last = 105664044691 43.46.290.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.882 MiB) 43.46.290.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 43.46.290.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.193 MiB) 43.47.816.596 I slot launch_slot_: id 3 | task 8738 | processing task, is_child = 0 43.47.816.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.569 MiB) 43.47.816.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.131 MiB) 43.47.816.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.943 MiB) 43.49.513.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.881 MiB) 43.49.513.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.943 MiB) 43.51.247.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.068 MiB) 43.51.247.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.194 MiB) 43.51.247.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.818 MiB) 43.53.478.305 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1603, t_last = 105671810799 43.53.478.571 I slot launch_slot_: id 1 | task 8739 | processing task, is_child = 0 43.53.478.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1513, t_last = 105674825834 43.53.478.829 I slot launch_slot_: id 0 | task 8740 | processing task, is_child = 0 43.53.478.904 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 105701186764 43.53.479.007 I slot launch_slot_: id 2 | task 8741 | processing task, is_child = 0 44.00.955.543 I slot print_timing: id 0 | task 8740 | prompt processing, n_tokens = 154, progress = 0.16, t = 7.48 s / 20.60 tokens per second 44.01.409.952 I slot print_timing: id 1 | task 8739 | prompt processing, n_tokens = 137, progress = 0.17, t = 7.47 s / 18.33 tokens per second 44.01.424.432 I slot print_timing: id 2 | task 8741 | prompt processing, n_tokens = 168, progress = 0.17, t = 7.47 s / 22.49 tokens per second 44.01.488.106 I slot print_timing: id 3 | task 8738 | prompt processing, n_tokens = 124, progress = 0.16, t = 7.47 s / 16.61 tokens per second 44.08.194.632 I slot print_timing: id 0 | task 8740 | prompt processing, n_tokens = 279, progress = 0.29, t = 14.72 s / 18.96 tokens per second 44.08.194.650 I slot print_timing: id 1 | task 8739 | prompt processing, n_tokens = 261, progress = 0.32, t = 14.71 s / 17.74 tokens per second 44.08.194.656 I slot print_timing: id 2 | task 8741 | prompt processing, n_tokens = 387, progress = 0.39, t = 14.71 s / 26.31 tokens per second 44.08.194.662 I slot print_timing: id 3 | task 8738 | prompt processing, n_tokens = 263, progress = 0.34, t = 14.70 s / 17.89 tokens per second 44.14.034.242 I slot print_timing: id 0 | task 8740 | prompt processing, n_tokens = 436, progress = 0.46, t = 20.56 s / 21.21 tokens per second 44.17.831.356 I slot print_timing: id 1 | task 8739 | prompt processing, n_tokens = 290, progress = 0.36, t = 20.55 s / 14.11 tokens per second 44.17.845.799 I slot print_timing: id 2 | task 8741 | prompt processing, n_tokens = 471, progress = 0.48, t = 20.55 s / 22.92 tokens per second 44.17.860.399 I slot print_timing: id 3 | task 8738 | prompt processing, n_tokens = 656, progress = 0.84, t = 20.54 s / 31.93 tokens per second 44.32.851.319 I slot print_timing: id 0 | task 8740 | prompt processing, n_tokens = 835, progress = 0.88, t = 39.37 s / 21.21 tokens per second 44.33.665.824 I slot print_timing: id 1 | task 8739 | prompt processing, n_tokens = 642, progress = 0.80, t = 39.37 s / 16.31 tokens per second 44.33.680.039 I slot print_timing: id 2 | task 8741 | prompt processing, n_tokens = 877, progress = 0.89, t = 39.37 s / 22.28 tokens per second 44.33.693.692 I slot print_timing: id 3 | task 8738 | prompt processing, n_tokens = 775, progress = 0.99, t = 39.36 s / 19.69 tokens per second 44.39.248.394 I slot print_timing: id 0 | task 8740 | prompt processing, n_tokens = 948, progress = 1.00, t = 45.77 s / 20.71 tokens per second 44.39.264.898 I slot print_timing: id 1 | task 8739 | prompt processing, n_tokens = 802, progress = 1.00, t = 45.76 s / 17.52 tokens per second 44.39.278.800 I slot print_timing: id 2 | task 8741 | prompt processing, n_tokens = 983, progress = 1.00, t = 45.76 s / 21.48 tokens per second 44.39.861.681 I slot print_timing: id 3 | task 8738 | prompt eval time = 45758.13 ms / 779 tokens ( 58.74 ms per token, 17.02 tokens per second) 44.39.861.687 I slot print_timing: id 3 | task 8738 | eval time = 613.31 ms / 2 tokens ( 613.31 ms per token, 1.63 tokens per second) 44.39.861.688 I slot print_timing: id 3 | task 8738 | total time = 46371.44 ms / 781 tokens 44.39.861.689 I slot print_timing: id 3 | task 8738 | graphs reused = 7735 44.39.861.689 I slot print_timing: id 3 | task 8738 | graph reallocs = 0 / 0 (same size) / (changed size) 44.39.864.347 I slot release: id 3 | task 8738 | stop processing: n_tokens = 780, truncated = 0 44.40.080.918 I slot print_timing: id 0 | task 8740 | prompt eval time = 46381.28 ms / 952 tokens ( 48.72 ms per token, 20.53 tokens per second) 44.40.080.922 I slot print_timing: id 0 | task 8740 | eval time = 220.62 ms / 2 tokens ( 220.62 ms per token, 4.53 tokens per second) 44.40.080.923 I slot print_timing: id 0 | task 8740 | total time = 46601.90 ms / 954 tokens 44.40.080.924 I slot print_timing: id 0 | task 8740 | graphs reused = 7735 44.40.080.924 I slot print_timing: id 0 | task 8740 | graph reallocs = 0 / 0 (same size) / (changed size) 44.40.083.871 I slot release: id 0 | task 8740 | stop processing: n_tokens = 953, truncated = 0 44.40.084.231 I slot print_timing: id 1 | task 8739 | prompt eval time = 46377.75 ms / 806 tokens ( 57.54 ms per token, 17.38 tokens per second) 44.40.084.238 I slot print_timing: id 1 | task 8739 | eval time = 223.56 ms / 2 tokens ( 223.56 ms per token, 4.47 tokens per second) 44.40.084.239 I slot print_timing: id 1 | task 8739 | total time = 46601.30 ms / 808 tokens 44.40.084.239 I slot print_timing: id 1 | task 8739 | graphs reused = 7735 44.40.084.240 I slot print_timing: id 1 | task 8739 | graph reallocs = 0 / 0 (same size) / (changed size) 44.40.084.736 I slot release: id 1 | task 8739 | stop processing: n_tokens = 807, truncated = 0 44.40.085.098 I slot print_timing: id 2 | task 8741 | prompt eval time = 46374.83 ms / 987 tokens ( 46.99 ms per token, 21.28 tokens per second) 44.40.085.103 I slot print_timing: id 2 | task 8741 | eval time = 223.99 ms / 2 tokens ( 223.99 ms per token, 4.46 tokens per second) 44.40.085.107 I slot print_timing: id 2 | task 8741 | total time = 46598.82 ms / 989 tokens 44.40.085.107 I slot print_timing: id 2 | task 8741 | graphs reused = 7735 44.40.085.109 I slot print_timing: id 2 | task 8741 | graph reallocs = 0 / 0 (same size) / (changed size) 44.40.085.538 I slot release: id 2 | task 8741 | stop processing: n_tokens = 988, truncated = 0 44.40.085.552 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 105754801971 44.40.085.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.819 MiB) 44.40.086.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 305.755 MiB) 44.40.086.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.631 MiB) 44.41.838.242 I slot launch_slot_: id 3 | task 8749 | processing task, is_child = 0 44.41.838.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 310.694 MiB) 44.41.842.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.006 MiB) 44.43.644.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 307.068 MiB) 44.43.644.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.318 MiB) 44.43.644.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 828.285 MiB) 44.46.004.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 839.102 MiB) 44.48.639.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 105755021495 44.48.640.149 I slot launch_slot_: id 0 | task 8750 | processing task, is_child = 0 44.48.640.241 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 105755022359 44.48.640.301 I slot launch_slot_: id 1 | task 8751 | processing task, is_child = 0 44.48.640.382 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 105755023163 44.48.640.446 I slot launch_slot_: id 2 | task 8752 | processing task, is_child = 0 45.00.772.998 I slot print_timing: id 0 | task 8750 | prompt processing, n_tokens = 260, progress = 0.32, t = 12.13 s / 21.43 tokens per second 45.00.773.010 I slot print_timing: id 1 | task 8751 | prompt processing, n_tokens = 260, progress = 0.30, t = 12.13 s / 21.43 tokens per second 45.00.773.019 I slot print_timing: id 2 | task 8752 | prompt processing, n_tokens = 260, progress = 0.31, t = 12.13 s / 21.43 tokens per second 45.00.773.024 I slot print_timing: id 3 | task 8749 | prompt processing, n_tokens = 260, progress = 0.32, t = 12.13 s / 21.43 tokens per second 45.04.807.533 I slot print_timing: id 0 | task 8750 | prompt processing, n_tokens = 288, progress = 0.36, t = 16.17 s / 17.81 tokens per second 45.05.202.135 I slot print_timing: id 1 | task 8751 | prompt processing, n_tokens = 339, progress = 0.40, t = 16.17 s / 20.97 tokens per second 45.05.215.675 I slot print_timing: id 2 | task 8752 | prompt processing, n_tokens = 330, progress = 0.39, t = 16.17 s / 20.41 tokens per second 45.05.229.367 I slot print_timing: id 3 | task 8749 | prompt processing, n_tokens = 285, progress = 0.36, t = 16.17 s / 17.63 tokens per second 45.23.598.898 I slot print_timing: id 0 | task 8750 | prompt processing, n_tokens = 696, progress = 0.87, t = 34.96 s / 19.91 tokens per second 45.24.405.496 I slot print_timing: id 1 | task 8751 | prompt processing, n_tokens = 696, progress = 0.81, t = 34.96 s / 19.91 tokens per second 45.24.419.901 I slot print_timing: id 2 | task 8752 | prompt processing, n_tokens = 696, progress = 0.82, t = 34.96 s / 19.91 tokens per second 45.24.433.666 I slot print_timing: id 3 | task 8749 | prompt processing, n_tokens = 696, progress = 0.87, t = 34.96 s / 19.91 tokens per second 45.31.109.238 I slot print_timing: id 0 | task 8750 | prompt processing, n_tokens = 800, progress = 1.00, t = 42.47 s / 18.84 tokens per second 45.31.507.177 I slot print_timing: id 1 | task 8751 | prompt processing, n_tokens = 851, progress = 1.00, t = 42.47 s / 20.04 tokens per second 45.31.522.188 I slot print_timing: id 2 | task 8752 | prompt processing, n_tokens = 842, progress = 1.00, t = 42.47 s / 19.83 tokens per second 45.31.543.466 I slot print_timing: id 3 | task 8749 | prompt processing, n_tokens = 797, progress = 1.00, t = 42.47 s / 18.77 tokens per second 45.32.287.467 I slot print_timing: id 0 | task 8750 | prompt eval time = 43413.40 ms / 804 tokens ( 54.00 ms per token, 18.52 tokens per second) 45.32.287.471 I slot print_timing: id 0 | task 8750 | eval time = 233.60 ms / 2 tokens ( 233.60 ms per token, 4.28 tokens per second) 45.32.287.471 I slot print_timing: id 0 | task 8750 | total time = 43647.00 ms / 806 tokens 45.32.287.472 I slot print_timing: id 0 | task 8750 | graphs reused = 7735 45.32.287.472 I slot print_timing: id 0 | task 8750 | graph reallocs = 0 / 0 (same size) / (changed size) 45.32.290.447 I slot release: id 0 | task 8750 | stop processing: n_tokens = 805, truncated = 0 45.32.291.155 I slot print_timing: id 1 | task 8751 | prompt eval time = 43413.76 ms / 855 tokens ( 50.78 ms per token, 19.69 tokens per second) 45.32.291.159 I slot print_timing: id 1 | task 8751 | eval time = 236.83 ms / 2 tokens ( 236.83 ms per token, 4.22 tokens per second) 45.32.291.160 I slot print_timing: id 1 | task 8751 | total time = 43650.60 ms / 857 tokens 45.32.291.160 I slot print_timing: id 1 | task 8751 | graphs reused = 7735 45.32.291.161 I slot print_timing: id 1 | task 8751 | graph reallocs = 0 / 0 (same size) / (changed size) 45.32.291.239 I slot release: id 1 | task 8751 | stop processing: n_tokens = 856, truncated = 0 45.32.291.998 I slot print_timing: id 2 | task 8752 | prompt eval time = 43414.43 ms / 846 tokens ( 51.32 ms per token, 19.49 tokens per second) 45.32.292.001 I slot print_timing: id 2 | task 8752 | eval time = 236.96 ms / 2 tokens ( 236.96 ms per token, 4.22 tokens per second) 45.32.292.002 I slot print_timing: id 2 | task 8752 | total time = 43651.39 ms / 848 tokens 45.32.292.002 I slot print_timing: id 2 | task 8752 | graphs reused = 7735 45.32.292.002 I slot print_timing: id 2 | task 8752 | graph reallocs = 0 / 0 (same size) / (changed size) 45.32.293.090 I slot release: id 2 | task 8752 | stop processing: n_tokens = 847, truncated = 0 45.32.293.742 I slot print_timing: id 3 | task 8749 | prompt eval time = 43415.19 ms / 801 tokens ( 54.20 ms per token, 18.45 tokens per second) 45.32.293.746 I slot print_timing: id 3 | task 8749 | eval time = 237.88 ms / 2 tokens ( 237.88 ms per token, 4.20 tokens per second) 45.32.293.746 I slot print_timing: id 3 | task 8749 | total time = 43653.07 ms / 803 tokens 45.32.293.746 I slot print_timing: id 3 | task 8749 | graphs reused = 7735 45.32.293.747 I slot print_timing: id 3 | task 8749 | graph reallocs = 0 / 0 (same size) / (changed size) 45.32.293.928 I slot release: id 3 | task 8749 | stop processing: n_tokens = 802, truncated = 0 45.32.312.427 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 45.32.312.470 I slot launch_slot_: id 0 | task 8760 | processing task, is_child = 0 45.32.312.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.297 MiB) 45.34.512.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 830.599 MiB) 45.37.634.144 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 105807228861 45.37.634.815 I slot launch_slot_: id 1 | task 8761 | processing task, is_child = 0 45.37.634.913 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 105807230714 45.37.634.979 I slot launch_slot_: id 2 | task 8762 | processing task, is_child = 0 45.37.635.021 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 802, t_last = 105807231552 45.37.635.092 I slot launch_slot_: id 3 | task 8763 | processing task, is_child = 0 45.45.491.233 I slot print_timing: id 0 | task 8760 | prompt processing, n_tokens = 125, progress = 1.00, t = 7.86 s / 15.91 tokens per second 45.45.888.710 I slot print_timing: id 1 | task 8761 | prompt processing, n_tokens = 171, progress = 0.18, t = 7.81 s / 21.90 tokens per second 45.45.901.051 I slot print_timing: id 2 | task 8762 | prompt processing, n_tokens = 160, progress = 0.18, t = 7.81 s / 20.49 tokens per second 45.45.913.413 I slot print_timing: id 3 | task 8763 | prompt processing, n_tokens = 160, progress = 0.18, t = 7.81 s / 20.49 tokens per second 45.52.939.130 I slot print_timing: id 1 | task 8761 | prompt processing, n_tokens = 340, progress = 0.35, t = 15.26 s / 22.29 tokens per second 45.52.939.144 I slot print_timing: id 2 | task 8762 | prompt processing, n_tokens = 342, progress = 0.38, t = 15.26 s / 22.42 tokens per second 45.52.939.150 I slot print_timing: id 3 | task 8763 | prompt processing, n_tokens = 342, progress = 0.39, t = 15.26 s / 22.42 tokens per second 45.55.665.744 I slot print_timing: id 0 | task 8760 | prompt eval time = 15304.00 ms / 129 tokens ( 118.64 ms per token, 8.43 tokens per second) 45.55.665.746 I slot print_timing: id 0 | task 8760 | eval time = 2726.63 ms / 2 tokens ( 2726.63 ms per token, 0.37 tokens per second) 45.55.665.746 I slot print_timing: id 0 | task 8760 | total time = 18030.63 ms / 131 tokens 45.55.665.747 I slot print_timing: id 0 | task 8760 | graphs reused = 7735 45.55.665.747 I slot print_timing: id 0 | task 8760 | graph reallocs = 0 / 0 (same size) / (changed size) 45.55.667.708 I slot release: id 0 | task 8760 | stop processing: n_tokens = 826, truncated = 0 45.55.667.741 I slot print_timing: id 1 | task 8761 | prompt processing, n_tokens = 447, progress = 0.46, t = 17.98 s / 24.86 tokens per second 45.55.686.684 I slot print_timing: id 2 | task 8762 | prompt processing, n_tokens = 380, progress = 0.42, t = 17.98 s / 21.13 tokens per second 45.55.700.904 I slot print_timing: id 3 | task 8763 | prompt processing, n_tokens = 364, progress = 0.41, t = 17.98 s / 20.24 tokens per second 46.09.959.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 105830605332 46.09.959.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 842.728 MiB) 46.11.618.540 I slot launch_slot_: id 0 | task 8768 | processing task, is_child = 0 46.11.618.628 I slot print_timing: id 1 | task 8761 | prompt processing, n_tokens = 831, progress = 0.86, t = 32.28 s / 25.75 tokens per second 46.11.623.079 I slot print_timing: id 2 | task 8762 | prompt processing, n_tokens = 754, progress = 0.84, t = 32.28 s / 23.36 tokens per second 46.11.627.522 I slot print_timing: id 3 | task 8763 | prompt processing, n_tokens = 754, progress = 0.86, t = 32.28 s / 23.36 tokens per second 46.19.003.073 I slot print_timing: id 0 | task 8768 | prompt processing, n_tokens = 182, progress = 0.18, t = 7.38 s / 24.65 tokens per second 46.19.400.786 I slot print_timing: id 1 | task 8761 | prompt processing, n_tokens = 959, progress = 1.00, t = 41.32 s / 23.21 tokens per second 46.19.443.417 I slot print_timing: id 2 | task 8762 | prompt processing, n_tokens = 892, progress = 1.00, t = 41.32 s / 21.59 tokens per second 46.19.599.353 I slot print_timing: id 3 | task 8763 | prompt processing, n_tokens = 876, progress = 1.00, t = 41.32 s / 21.20 tokens per second 46.22.824.779 I slot print_timing: id 0 | task 8768 | prompt processing, n_tokens = 403, progress = 0.41, t = 11.20 s / 35.97 tokens per second 46.24.221.924 I slot print_timing: id 1 | task 8761 | prompt eval time = 45140.68 ms / 963 tokens ( 46.88 ms per token, 21.33 tokens per second) 46.24.221.929 I slot print_timing: id 1 | task 8761 | eval time = 1398.33 ms / 2 tokens ( 1398.33 ms per token, 0.72 tokens per second) 46.24.221.930 I slot print_timing: id 1 | task 8761 | total time = 46539.01 ms / 965 tokens 46.24.221.930 I slot print_timing: id 1 | task 8761 | graphs reused = 7735 46.24.221.931 I slot print_timing: id 1 | task 8761 | graph reallocs = 0 / 0 (same size) / (changed size) 46.24.227.188 I slot release: id 1 | task 8761 | stop processing: n_tokens = 964, truncated = 0 46.24.227.999 I slot print_timing: id 2 | task 8762 | prompt eval time = 45141.01 ms / 896 tokens ( 50.38 ms per token, 19.85 tokens per second) 46.24.228.006 I slot print_timing: id 2 | task 8762 | eval time = 1404.00 ms / 2 tokens ( 1404.00 ms per token, 0.71 tokens per second) 46.24.228.007 I slot print_timing: id 2 | task 8762 | total time = 46545.00 ms / 898 tokens 46.24.228.007 I slot print_timing: id 2 | task 8762 | graphs reused = 7735 46.24.228.007 I slot print_timing: id 2 | task 8762 | graph reallocs = 0 / 0 (same size) / (changed size) 46.24.232.165 I slot release: id 2 | task 8762 | stop processing: n_tokens = 897, truncated = 0 46.24.232.441 I slot print_timing: id 3 | task 8763 | prompt eval time = 45141.70 ms / 880 tokens ( 51.30 ms per token, 19.49 tokens per second) 46.24.232.444 I slot print_timing: id 3 | task 8763 | eval time = 1407.70 ms / 2 tokens ( 1407.70 ms per token, 0.71 tokens per second) 46.24.232.445 I slot print_timing: id 3 | task 8763 | total time = 46549.40 ms / 882 tokens 46.24.232.445 I slot print_timing: id 3 | task 8763 | graphs reused = 7735 46.24.232.445 I slot print_timing: id 3 | task 8763 | graph reallocs = 0 / 0 (same size) / (changed size) 46.24.232.565 I slot release: id 3 | task 8763 | stop processing: n_tokens = 881, truncated = 0 46.24.232.572 I slot print_timing: id 0 | task 8768 | prompt processing, n_tokens = 471, progress = 0.48, t = 12.60 s / 37.37 tokens per second 46.24.255.542 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 105859164812 46.24.255.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 848.355 MiB) 46.29.236.140 I slot launch_slot_: id 1 | task 8773 | processing task, is_child = 0 46.29.236.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 850.043 MiB) 46.31.915.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.899 MiB) 46.33.749.726 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 105859169790 46.33.749.861 I slot launch_slot_: id 2 | task 8774 | processing task, is_child = 0 46.33.749.914 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 105859170187 46.33.749.981 I slot launch_slot_: id 3 | task 8775 | processing task, is_child = 0 46.33.749.989 I slot print_timing: id 0 | task 8768 | prompt processing, n_tokens = 872, progress = 0.88, t = 12.64 s / 69.00 tokens per second 46.40.574.113 I slot print_timing: id 0 | task 8768 | prompt processing, n_tokens = 983, progress = 1.00, t = 28.96 s / 33.95 tokens per second 46.41.379.894 I slot print_timing: id 1 | task 8773 | prompt processing, n_tokens = 182, progress = 0.18, t = 6.36 s / 28.64 tokens per second 46.41.392.143 I slot print_timing: id 2 | task 8774 | prompt processing, n_tokens = 129, progress = 0.14, t = 6.36 s / 20.30 tokens per second 46.41.404.736 I slot print_timing: id 3 | task 8775 | prompt processing, n_tokens = 129, progress = 0.07, t = 6.36 s / 20.30 tokens per second 46.48.710.402 I slot print_timing: id 1 | task 8773 | prompt processing, n_tokens = 403, progress = 0.39, t = 14.49 s / 27.81 tokens per second 46.48.710.416 I slot print_timing: id 2 | task 8774 | prompt processing, n_tokens = 283, progress = 0.31, t = 14.49 s / 19.53 tokens per second 46.48.710.423 I slot print_timing: id 3 | task 8775 | prompt processing, n_tokens = 283, progress = 0.16, t = 14.49 s / 19.53 tokens per second 46.57.754.666 I slot print_timing: id 0 | task 8768 | prompt eval time = 37091.82 ms / 987 tokens ( 37.58 ms per token, 26.61 tokens per second) 46.57.754.670 I slot print_timing: id 0 | task 8768 | eval time = 9044.28 ms / 2 tokens ( 9044.28 ms per token, 0.11 tokens per second) 46.57.754.672 I slot print_timing: id 0 | task 8768 | total time = 46136.11 ms / 989 tokens 46.57.754.672 I slot print_timing: id 0 | task 8768 | graphs reused = 7735 46.57.754.673 I slot print_timing: id 0 | task 8768 | graph reallocs = 0 / 0 (same size) / (changed size) 46.57.757.374 I slot release: id 0 | task 8768 | stop processing: n_tokens = 988, truncated = 0 46.57.757.410 I slot print_timing: id 1 | task 8773 | prompt processing, n_tokens = 506, progress = 0.50, t = 23.54 s / 21.50 tokens per second 46.57.775.797 I slot print_timing: id 2 | task 8774 | prompt processing, n_tokens = 408, progress = 0.44, t = 23.54 s / 17.34 tokens per second 46.57.789.887 I slot print_timing: id 3 | task 8775 | prompt processing, n_tokens = 753, progress = 0.42, t = 23.54 s / 31.99 tokens per second 47.10.969.255 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 105892694998 47.10.969.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 47.13.274.832 I slot launch_slot_: id 0 | task 8780 | processing task, is_child = 0 47.13.274.932 I slot print_timing: id 1 | task 8773 | prompt processing, n_tokens = 872, progress = 0.85, t = 36.75 s / 23.73 tokens per second 47.13.279.370 I slot print_timing: id 2 | task 8774 | prompt processing, n_tokens = 753, progress = 0.81, t = 36.75 s / 20.49 tokens per second 47.13.290.449 I slot print_timing: id 3 | task 8775 | prompt processing, n_tokens = 1264, progress = 0.71, t = 36.75 s / 34.39 tokens per second 47.21.266.991 I slot print_timing: id 0 | task 8780 | prompt processing, n_tokens = 129, progress = 0.14, t = 7.99 s / 16.14 tokens per second 47.25.501.887 I slot print_timing: id 1 | task 8773 | prompt processing, n_tokens = 1018, progress = 1.00, t = 47.05 s / 21.64 tokens per second 47.25.864.528 I slot print_timing: id 2 | task 8774 | prompt processing, n_tokens = 920, progress = 1.00, t = 47.05 s / 19.55 tokens per second 47.25.935.916 I slot print_timing: id 3 | task 8775 | prompt processing, n_tokens = 1776, progress = 1.00, t = 47.05 s / 37.75 tokens per second 47.28.399.690 I slot print_timing: id 0 | task 8780 | prompt processing, n_tokens = 283, progress = 0.30, t = 15.12 s / 18.71 tokens per second 47.30.528.850 I slot print_timing: id 1 | task 8773 | prompt eval time = 54179.86 ms / 1022 tokens ( 53.01 ms per token, 18.86 tokens per second) 47.30.528.853 I slot print_timing: id 1 | task 8773 | eval time = 2130.10 ms / 2 tokens ( 2130.10 ms per token, 0.47 tokens per second) 47.30.528.853 I slot print_timing: id 1 | task 8773 | total time = 56309.96 ms / 1024 tokens 47.30.528.854 I slot print_timing: id 1 | task 8773 | graphs reused = 7735 47.30.528.854 I slot print_timing: id 1 | task 8773 | graph reallocs = 0 / 0 (same size) / (changed size) 47.30.530.409 I slot release: id 1 | task 8773 | stop processing: n_tokens = 1023, truncated = 0 47.30.531.055 I slot print_timing: id 2 | task 8774 | prompt eval time = 54180.20 ms / 924 tokens ( 58.64 ms per token, 17.05 tokens per second) 47.30.531.060 I slot print_timing: id 2 | task 8774 | eval time = 2131.88 ms / 2 tokens ( 2131.88 ms per token, 0.47 tokens per second) 47.30.531.061 I slot print_timing: id 2 | task 8774 | total time = 56312.08 ms / 926 tokens 47.30.531.061 I slot print_timing: id 2 | task 8774 | graphs reused = 7735 47.30.531.061 I slot print_timing: id 2 | task 8774 | graph reallocs = 0 / 0 (same size) / (changed size) 47.30.535.182 I slot release: id 2 | task 8774 | stop processing: n_tokens = 925, truncated = 0 47.30.535.565 I slot print_timing: id 3 | task 8775 | prompt eval time = 54180.62 ms / 1780 tokens ( 30.44 ms per token, 32.85 tokens per second) 47.30.535.570 I slot print_timing: id 3 | task 8775 | eval time = 2135.92 ms / 2 tokens ( 2135.92 ms per token, 0.47 tokens per second) 47.30.535.570 I slot print_timing: id 3 | task 8775 | total time = 56316.54 ms / 1782 tokens 47.30.535.571 I slot print_timing: id 3 | task 8775 | graphs reused = 7735 47.30.535.571 I slot print_timing: id 3 | task 8775 | graph reallocs = 0 / 0 (same size) / (changed size) 47.30.540.885 I slot release: id 3 | task 8775 | stop processing: n_tokens = 1781, truncated = 0 47.30.540.906 I slot print_timing: id 0 | task 8780 | prompt processing, n_tokens = 421, progress = 0.45, t = 17.25 s / 24.40 tokens per second 47.30.567.362 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 105925468034 47.30.567.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.587 MiB) 47.34.809.245 I slot launch_slot_: id 1 | task 8785 | processing task, is_child = 0 47.34.809.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 47.37.283.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 47.39.480.203 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 105925472805 47.39.480.439 I slot launch_slot_: id 2 | task 8786 | processing task, is_child = 0 47.39.480.529 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 105925478509 47.39.480.636 I slot launch_slot_: id 3 | task 8787 | processing task, is_child = 0 47.39.480.643 I slot print_timing: id 0 | task 8780 | prompt processing, n_tokens = 753, progress = 0.80, t = 17.29 s / 43.54 tokens per second 47.46.796.431 I slot print_timing: id 0 | task 8780 | prompt processing, n_tokens = 933, progress = 1.00, t = 33.52 s / 27.83 tokens per second 47.47.243.131 I slot print_timing: id 1 | task 8785 | prompt processing, n_tokens = 118, progress = 0.17, t = 6.67 s / 17.69 tokens per second 47.47.355.128 I slot print_timing: id 2 | task 8786 | prompt processing, n_tokens = 118, progress = 0.16, t = 6.67 s / 17.69 tokens per second 47.47.421.175 I slot print_timing: id 3 | task 8787 | prompt processing, n_tokens = 140, progress = 0.16, t = 6.67 s / 20.99 tokens per second 47.52.242.668 I slot print_timing: id 1 | task 8785 | prompt processing, n_tokens = 197, progress = 0.28, t = 12.12 s / 16.26 tokens per second 47.52.259.766 I slot print_timing: id 2 | task 8786 | prompt processing, n_tokens = 225, progress = 0.30, t = 12.12 s / 18.57 tokens per second 47.52.299.091 I slot print_timing: id 3 | task 8787 | prompt processing, n_tokens = 268, progress = 0.30, t = 12.12 s / 22.12 tokens per second 48.03.270.009 I slot print_timing: id 0 | task 8780 | prompt eval time = 38967.79 ms / 937 tokens ( 41.59 ms per token, 24.05 tokens per second) 48.03.270.015 I slot print_timing: id 0 | task 8780 | eval time = 11027.36 ms / 2 tokens (11027.36 ms per token, 0.09 tokens per second) 48.03.270.015 I slot print_timing: id 0 | task 8780 | total time = 49995.15 ms / 939 tokens 48.03.270.016 I slot print_timing: id 0 | task 8780 | graphs reused = 7735 48.03.270.016 I slot print_timing: id 0 | task 8780 | graph reallocs = 0 / 0 (same size) / (changed size) 48.03.272.675 I slot release: id 0 | task 8780 | stop processing: n_tokens = 938, truncated = 0 48.03.272.719 I slot print_timing: id 1 | task 8785 | prompt processing, n_tokens = 603, progress = 0.85, t = 23.14 s / 26.06 tokens per second 48.03.342.968 I slot print_timing: id 2 | task 8786 | prompt processing, n_tokens = 603, progress = 0.81, t = 23.14 s / 26.06 tokens per second 48.03.357.295 I slot print_timing: id 3 | task 8787 | prompt processing, n_tokens = 364, progress = 0.41, t = 23.14 s / 15.73 tokens per second 48.08.062.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 105958210299 48.08.062.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.088 MiB) 48.11.496.874 I slot launch_slot_: id 0 | task 8792 | processing task, is_child = 0 48.11.496.961 I slot print_timing: id 1 | task 8785 | prompt processing, n_tokens = 709, progress = 0.99, t = 27.94 s / 25.38 tokens per second 48.11.501.489 I slot print_timing: id 2 | task 8786 | prompt processing, n_tokens = 737, progress = 0.99, t = 27.94 s / 26.38 tokens per second 48.11.509.913 I slot print_timing: id 3 | task 8787 | prompt processing, n_tokens = 769, progress = 0.87, t = 27.94 s / 27.53 tokens per second 48.15.059.713 I slot print_timing: id 0 | task 8792 | prompt processing, n_tokens = 118, progress = 0.16, t = 3.56 s / 33.13 tokens per second 48.15.388.408 I slot print_timing: id 3 | task 8787 | prompt processing, n_tokens = 876, progress = 1.00, t = 34.93 s / 25.08 tokens per second 48.17.005.089 I slot print_timing: id 1 | task 8785 | prompt eval time = 34932.33 ms / 713 tokens ( 48.99 ms per token, 20.41 tokens per second) 48.17.005.103 I slot print_timing: id 1 | task 8785 | eval time = 1944.74 ms / 2 tokens ( 1944.74 ms per token, 0.51 tokens per second) 48.17.005.106 I slot print_timing: id 1 | task 8785 | total time = 36877.07 ms / 715 tokens 48.17.005.107 I slot print_timing: id 1 | task 8785 | graphs reused = 7735 48.17.005.108 I slot print_timing: id 1 | task 8785 | graph reallocs = 0 / 0 (same size) / (changed size) 48.17.008.634 I slot release: id 1 | task 8785 | stop processing: n_tokens = 714, truncated = 0 48.17.009.921 I slot print_timing: id 2 | task 8786 | prompt eval time = 34932.63 ms / 741 tokens ( 47.14 ms per token, 21.21 tokens per second) 48.17.009.925 I slot print_timing: id 2 | task 8786 | eval time = 1950.22 ms / 2 tokens ( 1950.22 ms per token, 0.51 tokens per second) 48.17.009.926 I slot print_timing: id 2 | task 8786 | total time = 36882.85 ms / 743 tokens 48.17.009.926 I slot print_timing: id 2 | task 8786 | graphs reused = 7735 48.17.009.926 I slot print_timing: id 2 | task 8786 | graph reallocs = 0 / 0 (same size) / (changed size) 48.17.010.971 I slot release: id 2 | task 8786 | stop processing: n_tokens = 742, truncated = 0 48.17.011.466 I slot print_timing: id 0 | task 8792 | prompt processing, n_tokens = 200, progress = 0.28, t = 5.51 s / 36.32 tokens per second 48.22.138.790 I slot print_timing: id 3 | task 8787 | prompt eval time = 36884.32 ms / 880 tokens ( 41.91 ms per token, 23.86 tokens per second) 48.22.138.793 I slot print_timing: id 3 | task 8787 | eval time = 5127.33 ms / 2 tokens ( 5127.33 ms per token, 0.20 tokens per second) 48.22.138.798 I slot print_timing: id 3 | task 8787 | total time = 42011.65 ms / 882 tokens 48.22.138.798 I slot print_timing: id 3 | task 8787 | graphs reused = 7735 48.22.138.799 I slot print_timing: id 3 | task 8787 | graph reallocs = 0 / 0 (same size) / (changed size) 48.22.144.328 I slot release: id 3 | task 8787 | stop processing: n_tokens = 881, truncated = 0 48.22.144.351 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.884 48.22.144.478 I slot launch_slot_: id 1 | task 8796 | processing task, is_child = 0 48.22.144.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.274 MiB) 48.24.287.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 48.26.791.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.850 48.26.791.377 I slot launch_slot_: id 2 | task 8797 | processing task, is_child = 0 48.26.791.468 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 105977081953 48.26.791.537 I slot launch_slot_: id 3 | task 8798 | processing task, is_child = 0 48.26.791.545 I slot print_timing: id 0 | task 8792 | prompt processing, n_tokens = 603, progress = 0.84, t = 10.64 s / 56.67 tokens per second 48.33.291.128 I slot print_timing: id 0 | task 8792 | prompt processing, n_tokens = 712, progress = 0.99, t = 21.79 s / 32.67 tokens per second 48.33.699.721 I slot print_timing: id 1 | task 8796 | prompt processing, n_tokens = 112, progress = 0.99, t = 6.41 s / 17.48 tokens per second 48.33.762.995 I slot print_timing: id 2 | task 8797 | prompt processing, n_tokens = 118, progress = 0.99, t = 6.36 s / 18.56 tokens per second 48.33.788.816 I slot print_timing: id 3 | task 8798 | prompt processing, n_tokens = 133, progress = 0.15, t = 6.29 s / 21.14 tokens per second 48.36.183.087 I slot print_timing: id 3 | task 8798 | prompt processing, n_tokens = 277, progress = 0.32, t = 9.18 s / 30.17 tokens per second 48.37.604.997 I slot print_timing: id 0 | task 8792 | prompt eval time = 24685.22 ms / 716 tokens ( 34.48 ms per token, 29.01 tokens per second) 48.37.605.002 I slot print_timing: id 0 | task 8792 | eval time = 1422.89 ms / 2 tokens ( 1422.89 ms per token, 0.70 tokens per second) 48.37.605.003 I slot print_timing: id 0 | task 8792 | total time = 26108.11 ms / 718 tokens 48.37.605.003 I slot print_timing: id 0 | task 8792 | graphs reused = 7735 48.37.605.004 I slot print_timing: id 0 | task 8792 | graph reallocs = 0 / 0 (same size) / (changed size) 48.37.605.089 I slot release: id 0 | task 8792 | stop processing: n_tokens = 717, truncated = 0 48.37.605.335 I slot print_timing: id 1 | task 8796 | prompt eval time = 9299.90 ms / 116 tokens ( 80.17 ms per token, 12.47 tokens per second) 48.37.605.341 I slot print_timing: id 1 | task 8796 | eval time = 1422.54 ms / 2 tokens ( 1422.54 ms per token, 0.70 tokens per second) 48.37.605.342 I slot print_timing: id 1 | task 8796 | total time = 10722.44 ms / 118 tokens 48.37.605.342 I slot print_timing: id 1 | task 8796 | graphs reused = 7735 48.37.605.342 I slot print_timing: id 1 | task 8796 | graph reallocs = 0 / 0 (same size) / (changed size) 48.37.605.376 I slot release: id 1 | task 8796 | stop processing: n_tokens = 720, truncated = 0 48.37.606.787 I slot print_timing: id 2 | task 8797 | prompt eval time = 9249.42 ms / 122 tokens ( 75.81 ms per token, 13.19 tokens per second) 48.37.606.789 I slot print_timing: id 2 | task 8797 | eval time = 1422.55 ms / 2 tokens ( 1422.55 ms per token, 0.70 tokens per second) 48.37.606.790 I slot print_timing: id 2 | task 8797 | total time = 10671.98 ms / 124 tokens 48.37.606.790 I slot print_timing: id 2 | task 8797 | graphs reused = 7735 48.37.606.790 I slot print_timing: id 2 | task 8797 | graph reallocs = 0 / 0 (same size) / (changed size) 48.37.606.818 I slot release: id 2 | task 8797 | stop processing: n_tokens = 726, truncated = 0 48.37.606.837 I slot print_timing: id 3 | task 8798 | prompt processing, n_tokens = 360, progress = 0.41, t = 10.61 s / 33.94 tokens per second 48.37.659.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 105992542712 48.37.659.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.403 MiB) 48.42.639.959 I slot launch_slot_: id 0 | task 8803 | processing task, is_child = 0 48.42.640.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 48.44.898.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 48.46.928.835 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 105992542998 48.46.928.976 I slot launch_slot_: id 1 | task 8804 | processing task, is_child = 0 48.46.929.023 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 105992544440 48.46.929.115 I slot launch_slot_: id 2 | task 8805 | processing task, is_child = 0 48.46.929.369 I slot print_timing: id 3 | task 8798 | prompt processing, n_tokens = 766, progress = 0.87, t = 10.66 s / 71.85 tokens per second 48.52.437.840 I slot print_timing: id 0 | task 8803 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.51 s / 25.78 tokens per second 48.54.023.574 I slot print_timing: id 1 | task 8804 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.51 s / 25.78 tokens per second 48.54.154.007 I slot print_timing: id 2 | task 8805 | prompt processing, n_tokens = 142, progress = 0.14, t = 5.51 s / 25.78 tokens per second 48.54.160.300 I slot print_timing: id 3 | task 8798 | prompt processing, n_tokens = 872, progress = 1.00, t = 25.44 s / 34.28 tokens per second 49.01.995.025 I slot print_timing: id 0 | task 8803 | prompt processing, n_tokens = 345, progress = 0.35, t = 15.07 s / 22.90 tokens per second 49.01.995.040 I slot print_timing: id 1 | task 8804 | prompt processing, n_tokens = 345, progress = 0.34, t = 15.07 s / 22.90 tokens per second 49.01.995.047 I slot print_timing: id 2 | task 8805 | prompt processing, n_tokens = 345, progress = 0.33, t = 15.07 s / 22.90 tokens per second 49.07.996.632 I slot print_timing: id 3 | task 8798 | prompt eval time = 34995.95 ms / 876 tokens ( 39.95 ms per token, 25.03 tokens per second) 49.07.996.635 I slot print_timing: id 3 | task 8798 | eval time = 6001.62 ms / 2 tokens ( 6001.62 ms per token, 0.17 tokens per second) 49.07.996.635 I slot print_timing: id 3 | task 8798 | total time = 40997.56 ms / 878 tokens 49.07.996.636 I slot print_timing: id 3 | task 8798 | graphs reused = 7735 49.07.996.636 I slot print_timing: id 3 | task 8798 | graph reallocs = 0 / 0 (same size) / (changed size) 49.08.000.063 I slot release: id 3 | task 8798 | stop processing: n_tokens = 877, truncated = 0 49.08.000.093 I slot print_timing: id 0 | task 8803 | prompt processing, n_tokens = 476, progress = 0.48, t = 21.07 s / 22.59 tokens per second 49.08.014.028 I slot print_timing: id 1 | task 8804 | prompt processing, n_tokens = 490, progress = 0.49, t = 21.07 s / 23.26 tokens per second 49.08.028.874 I slot print_timing: id 2 | task 8805 | prompt processing, n_tokens = 518, progress = 0.50, t = 21.07 s / 24.59 tokens per second 49.21.555.132 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 106022937688 49.21.555.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.904 MiB) 49.23.899.647 I slot launch_slot_: id 3 | task 8810 | processing task, is_child = 0 49.23.899.664 I slot print_timing: id 0 | task 8803 | prompt processing, n_tokens = 861, progress = 0.87, t = 34.63 s / 24.87 tokens per second 49.23.920.062 I slot print_timing: id 1 | task 8804 | prompt processing, n_tokens = 861, progress = 0.86, t = 34.63 s / 24.87 tokens per second 49.23.972.780 I slot print_timing: id 2 | task 8805 | prompt processing, n_tokens = 861, progress = 0.83, t = 34.63 s / 24.87 tokens per second 49.31.188.497 I slot print_timing: id 0 | task 8803 | prompt processing, n_tokens = 988, progress = 1.00, t = 44.26 s / 22.32 tokens per second 49.31.643.759 I slot print_timing: id 1 | task 8804 | prompt processing, n_tokens = 1002, progress = 1.00, t = 44.26 s / 22.64 tokens per second 49.31.649.011 I slot print_timing: id 2 | task 8805 | prompt processing, n_tokens = 1030, progress = 1.00, t = 44.26 s / 23.27 tokens per second 49.31.657.979 I slot print_timing: id 3 | task 8810 | prompt processing, n_tokens = 142, progress = 0.14, t = 7.14 s / 19.88 tokens per second 49.34.825.309 I slot print_timing: id 3 | task 8810 | prompt processing, n_tokens = 345, progress = 0.35, t = 10.78 s / 32.01 tokens per second 49.36.968.973 I slot print_timing: id 0 | task 8803 | prompt eval time = 47895.08 ms / 992 tokens ( 48.28 ms per token, 20.71 tokens per second) 49.36.968.978 I slot print_timing: id 0 | task 8803 | eval time = 2144.76 ms / 2 tokens ( 2144.76 ms per token, 0.47 tokens per second) 49.36.968.979 I slot print_timing: id 0 | task 8803 | total time = 50039.84 ms / 994 tokens 49.36.968.979 I slot print_timing: id 0 | task 8803 | graphs reused = 7735 49.36.968.980 I slot print_timing: id 0 | task 8803 | graph reallocs = 0 / 0 (same size) / (changed size) 49.36.970.881 I slot release: id 0 | task 8803 | stop processing: n_tokens = 993, truncated = 0 49.36.971.496 I slot print_timing: id 1 | task 8804 | prompt eval time = 47895.44 ms / 1006 tokens ( 47.61 ms per token, 21.00 tokens per second) 49.36.971.502 I slot print_timing: id 1 | task 8804 | eval time = 2146.83 ms / 2 tokens ( 2146.83 ms per token, 0.47 tokens per second) 49.36.971.503 I slot print_timing: id 1 | task 8804 | total time = 50042.27 ms / 1008 tokens 49.36.971.503 I slot print_timing: id 1 | task 8804 | graphs reused = 7735 49.36.971.504 I slot print_timing: id 1 | task 8804 | graph reallocs = 0 / 0 (same size) / (changed size) 49.36.971.544 I slot release: id 1 | task 8804 | stop processing: n_tokens = 1007, truncated = 0 49.36.972.237 I slot print_timing: id 2 | task 8805 | prompt eval time = 47895.97 ms / 1034 tokens ( 46.32 ms per token, 21.59 tokens per second) 49.36.972.243 I slot print_timing: id 2 | task 8805 | eval time = 2146.95 ms / 2 tokens ( 2146.95 ms per token, 0.47 tokens per second) 49.36.972.243 I slot print_timing: id 2 | task 8805 | total time = 50042.92 ms / 1036 tokens 49.36.972.244 I slot print_timing: id 2 | task 8805 | graphs reused = 7735 49.36.972.244 I slot print_timing: id 2 | task 8805 | graph reallocs = 0 / 0 (same size) / (changed size) 49.36.973.028 I slot release: id 2 | task 8805 | stop processing: n_tokens = 1035, truncated = 0 49.36.973.050 I slot print_timing: id 3 | task 8810 | prompt processing, n_tokens = 483, progress = 0.48, t = 12.92 s / 37.38 tokens per second 49.37.024.849 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 49.37.027.845 I slot launch_slot_: id 0 | task 8815 | processing task, is_child = 0 49.37.027.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.092 MiB) 49.41.646.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.965 MiB) 49.43.771.015 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 106051909166 49.43.771.172 I slot launch_slot_: id 1 | task 8816 | processing task, is_child = 0 49.43.771.222 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 106051910652 49.43.771.291 I slot launch_slot_: id 2 | task 8817 | processing task, is_child = 0 49.43.780.360 I slot print_timing: id 3 | task 8810 | prompt processing, n_tokens = 861, progress = 0.86, t = 12.98 s / 66.34 tokens per second 49.51.251.350 I slot print_timing: id 0 | task 8815 | prompt processing, n_tokens = 128, progress = 1.00, t = 7.48 s / 17.11 tokens per second 49.51.705.457 I slot print_timing: id 1 | task 8816 | prompt processing, n_tokens = 193, progress = 0.22, t = 7.47 s / 25.83 tokens per second 49.51.774.776 I slot print_timing: id 2 | task 8817 | prompt processing, n_tokens = 115, progress = 0.11, t = 7.47 s / 15.39 tokens per second 49.51.798.504 I slot print_timing: id 3 | task 8810 | prompt processing, n_tokens = 995, progress = 1.00, t = 27.21 s / 36.57 tokens per second 49.56.501.836 I slot print_timing: id 1 | task 8816 | prompt processing, n_tokens = 327, progress = 0.37, t = 12.72 s / 25.71 tokens per second 49.56.501.851 I slot print_timing: id 2 | task 8817 | prompt processing, n_tokens = 293, progress = 0.29, t = 12.72 s / 23.03 tokens per second 50.00.331.667 I slot print_timing: id 0 | task 8815 | prompt eval time = 12730.12 ms / 132 tokens ( 96.44 ms per token, 10.37 tokens per second) 50.00.331.673 I slot print_timing: id 0 | task 8815 | eval time = 3830.24 ms / 2 tokens ( 3830.24 ms per token, 0.26 tokens per second) 50.00.331.673 I slot print_timing: id 0 | task 8815 | total time = 16560.36 ms / 134 tokens 50.00.331.674 I slot print_timing: id 0 | task 8815 | graphs reused = 7735 50.00.331.674 I slot print_timing: id 0 | task 8815 | graph reallocs = 0 / 0 (same size) / (changed size) 50.00.331.932 I slot release: id 0 | task 8815 | stop processing: n_tokens = 994, truncated = 0 50.00.332.122 I slot print_timing: id 3 | task 8810 | prompt eval time = 32455.69 ms / 999 tokens ( 32.49 ms per token, 30.78 tokens per second) 50.00.332.127 I slot print_timing: id 3 | task 8810 | eval time = 3830.30 ms / 2 tokens ( 3830.30 ms per token, 0.26 tokens per second) 50.00.332.128 I slot print_timing: id 3 | task 8810 | total time = 36285.99 ms / 1001 tokens 50.00.332.128 I slot print_timing: id 3 | task 8810 | graphs reused = 7735 50.00.332.129 I slot print_timing: id 3 | task 8810 | graph reallocs = 0 / 0 (same size) / (changed size) 50.00.332.469 I slot release: id 3 | task 8810 | stop processing: n_tokens = 1000, truncated = 0 50.00.332.482 I slot print_timing: id 1 | task 8816 | prompt processing, n_tokens = 363, progress = 0.41, t = 16.55 s / 21.93 tokens per second 50.00.344.865 I slot print_timing: id 2 | task 8817 | prompt processing, n_tokens = 502, progress = 0.49, t = 16.55 s / 30.33 tokens per second 50.06.915.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 106075269556 50.06.915.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.484 MiB) 50.08.756.655 I slot launch_slot_: id 0 | task 8822 | processing task, is_child = 0 50.08.756.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.777 MiB) 50.11.012.385 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 106075270093 50.11.012.548 I slot launch_slot_: id 3 | task 8823 | processing task, is_child = 0 50.11.012.657 I slot print_timing: id 1 | task 8816 | prompt processing, n_tokens = 730, progress = 0.83, t = 23.14 s / 31.55 tokens per second 50.11.022.150 I slot print_timing: id 2 | task 8817 | prompt processing, n_tokens = 773, progress = 0.76, t = 23.13 s / 33.41 tokens per second 50.17.736.717 I slot print_timing: id 0 | task 8822 | prompt processing, n_tokens = 115, progress = 0.13, t = 6.72 s / 17.10 tokens per second 50.18.944.975 I slot print_timing: id 1 | task 8816 | prompt processing, n_tokens = 875, progress = 1.00, t = 33.96 s / 25.77 tokens per second 50.19.074.678 I slot print_timing: id 2 | task 8817 | prompt processing, n_tokens = 1014, progress = 1.00, t = 33.96 s / 29.86 tokens per second 50.19.133.915 I slot print_timing: id 3 | task 8823 | prompt processing, n_tokens = 115, progress = 0.11, t = 6.71 s / 17.15 tokens per second 50.24.190.171 I slot print_timing: id 0 | task 8822 | prompt processing, n_tokens = 293, progress = 0.33, t = 13.18 s / 22.24 tokens per second 50.24.190.186 I slot print_timing: id 3 | task 8823 | prompt processing, n_tokens = 293, progress = 0.29, t = 13.16 s / 22.26 tokens per second 50.28.266.977 I slot print_timing: id 1 | task 8816 | prompt eval time = 40409.54 ms / 879 tokens ( 45.97 ms per token, 21.75 tokens per second) 50.28.266.983 I slot print_timing: id 1 | task 8816 | eval time = 4077.23 ms / 2 tokens ( 4077.23 ms per token, 0.25 tokens per second) 50.28.266.983 I slot print_timing: id 1 | task 8816 | total time = 44486.78 ms / 881 tokens 50.28.266.984 I slot print_timing: id 1 | task 8816 | graphs reused = 7735 50.28.266.984 I slot print_timing: id 1 | task 8816 | graph reallocs = 0 / 0 (same size) / (changed size) 50.28.271.260 I slot release: id 1 | task 8816 | stop processing: n_tokens = 880, truncated = 0 50.28.271.750 I slot print_timing: id 2 | task 8817 | prompt eval time = 40409.87 ms / 1018 tokens ( 39.70 ms per token, 25.19 tokens per second) 50.28.271.754 I slot print_timing: id 2 | task 8817 | eval time = 4081.59 ms / 2 tokens ( 4081.59 ms per token, 0.25 tokens per second) 50.28.271.754 I slot print_timing: id 2 | task 8817 | total time = 44491.46 ms / 1020 tokens 50.28.271.755 I slot print_timing: id 2 | task 8817 | graphs reused = 7735 50.28.271.755 I slot print_timing: id 2 | task 8817 | graph reallocs = 0 / 0 (same size) / (changed size) 50.28.276.858 I slot release: id 2 | task 8817 | stop processing: n_tokens = 1019, truncated = 0 50.28.276.885 I slot print_timing: id 0 | task 8822 | prompt processing, n_tokens = 380, progress = 0.42, t = 17.25 s / 22.02 tokens per second 50.28.292.242 I slot print_timing: id 3 | task 8823 | prompt processing, n_tokens = 493, progress = 0.49, t = 17.24 s / 28.60 tokens per second 50.33.221.506 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.786 50.33.221.584 I slot launch_slot_: id 2 | task 8828 | processing task, is_child = 0 50.33.221.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.523 MiB) 50.36.676.395 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 106103208884 50.36.676.532 I slot launch_slot_: id 1 | task 8829 | processing task, is_child = 0 50.36.676.540 I slot print_timing: id 0 | task 8822 | prompt processing, n_tokens = 773, progress = 0.86, t = 22.21 s / 34.81 tokens per second 50.36.852.805 I slot print_timing: id 3 | task 8823 | prompt processing, n_tokens = 773, progress = 0.77, t = 22.19 s / 34.83 tokens per second 50.43.250.609 I slot print_timing: id 0 | task 8822 | prompt processing, n_tokens = 892, progress = 1.00, t = 32.24 s / 27.67 tokens per second 50.44.798.789 I slot print_timing: id 1 | task 8829 | prompt processing, n_tokens = 115, progress = 0.12, t = 6.44 s / 17.85 tokens per second 50.44.809.601 I slot print_timing: id 2 | task 8828 | prompt processing, n_tokens = 125, progress = 1.00, t = 6.44 s / 19.40 tokens per second 50.44.858.891 I slot print_timing: id 3 | task 8823 | prompt processing, n_tokens = 1005, progress = 1.00, t = 32.22 s / 31.19 tokens per second 50.47.622.171 I slot print_timing: id 1 | task 8829 | prompt processing, n_tokens = 293, progress = 0.30, t = 10.81 s / 27.10 tokens per second 50.50.310.921 I slot print_timing: id 0 | task 8822 | prompt eval time = 36608.35 ms / 896 tokens ( 40.86 ms per token, 24.48 tokens per second) 50.50.310.924 I slot print_timing: id 0 | task 8822 | eval time = 2690.01 ms / 2 tokens ( 2690.01 ms per token, 0.37 tokens per second) 50.50.310.924 I slot print_timing: id 0 | task 8822 | total time = 39298.36 ms / 898 tokens 50.50.310.925 I slot print_timing: id 0 | task 8822 | graphs reused = 7735 50.50.310.925 I slot print_timing: id 0 | task 8822 | graph reallocs = 0 / 0 (same size) / (changed size) 50.50.314.099 I slot release: id 0 | task 8822 | stop processing: n_tokens = 897, truncated = 0 50.50.314.720 I slot print_timing: id 2 | task 8828 | prompt eval time = 10813.87 ms / 129 tokens ( 83.83 ms per token, 11.93 tokens per second) 50.50.314.725 I slot print_timing: id 2 | task 8828 | eval time = 2693.34 ms / 2 tokens ( 2693.34 ms per token, 0.37 tokens per second) 50.50.314.726 I slot print_timing: id 2 | task 8828 | total time = 13507.21 ms / 131 tokens 50.50.314.726 I slot print_timing: id 2 | task 8828 | graphs reused = 7735 50.50.314.726 I slot print_timing: id 2 | task 8828 | graph reallocs = 0 / 0 (same size) / (changed size) 50.50.315.499 I slot release: id 2 | task 8828 | stop processing: n_tokens = 903, truncated = 0 50.50.316.052 I slot print_timing: id 3 | task 8823 | prompt eval time = 36592.89 ms / 1009 tokens ( 36.27 ms per token, 27.57 tokens per second) 50.50.316.055 I slot print_timing: id 3 | task 8823 | eval time = 2693.91 ms / 2 tokens ( 2693.91 ms per token, 0.37 tokens per second) 50.50.316.055 I slot print_timing: id 3 | task 8823 | total time = 39286.80 ms / 1011 tokens 50.50.316.056 I slot print_timing: id 3 | task 8823 | graphs reused = 7735 50.50.316.056 I slot print_timing: id 3 | task 8823 | graph reallocs = 0 / 0 (same size) / (changed size) 50.50.318.115 I slot release: id 3 | task 8823 | stop processing: n_tokens = 1010, truncated = 0 50.50.318.132 I slot print_timing: id 1 | task 8829 | prompt processing, n_tokens = 469, progress = 0.48, t = 13.50 s / 34.73 tokens per second 50.50.372.402 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 50.50.372.447 I slot launch_slot_: id 0 | task 8834 | processing task, is_child = 0 50.50.372.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 50.54.243.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 50.56.607.435 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 106125253124 50.56.607.598 I slot launch_slot_: id 2 | task 8835 | processing task, is_child = 0 50.56.607.648 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 106125255738 50.56.607.735 I slot launch_slot_: id 3 | task 8836 | processing task, is_child = 0 50.56.620.768 I slot print_timing: id 1 | task 8829 | prompt processing, n_tokens = 773, progress = 0.78, t = 13.56 s / 56.99 tokens per second 51.02.583.093 I slot print_timing: id 0 | task 8834 | prompt processing, n_tokens = 104, progress = 1.00, t = 5.97 s / 17.41 tokens per second 51.03.792.159 I slot print_timing: id 1 | task 8829 | prompt processing, n_tokens = 981, progress = 1.00, t = 25.77 s / 38.06 tokens per second 51.03.841.222 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 116, progress = 0.12, t = 5.93 s / 19.56 tokens per second 51.03.888.901 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 116, progress = 0.13, t = 5.93 s / 19.56 tokens per second 51.07.099.850 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 232, progress = 0.24, t = 10.45 s / 22.20 tokens per second 51.07.099.871 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 232, progress = 0.26, t = 10.45 s / 22.20 tokens per second 51.11.923.226 I slot print_timing: id 0 | task 8834 | prompt eval time = 10491.86 ms / 108 tokens ( 97.15 ms per token, 10.29 tokens per second) 51.11.923.231 I slot print_timing: id 0 | task 8834 | eval time = 4823.62 ms / 2 tokens ( 4823.62 ms per token, 0.21 tokens per second) 51.11.923.231 I slot print_timing: id 0 | task 8834 | total time = 15315.48 ms / 110 tokens 51.11.923.232 I slot print_timing: id 0 | task 8834 | graphs reused = 7735 51.11.923.232 I slot print_timing: id 0 | task 8834 | graph reallocs = 0 / 0 (same size) / (changed size) 51.11.925.674 I slot release: id 0 | task 8834 | stop processing: n_tokens = 882, truncated = 0 51.11.926.131 I slot print_timing: id 1 | task 8829 | prompt eval time = 30292.41 ms / 985 tokens ( 30.75 ms per token, 32.52 tokens per second) 51.11.926.134 I slot print_timing: id 1 | task 8829 | eval time = 4826.29 ms / 2 tokens ( 4826.29 ms per token, 0.21 tokens per second) 51.11.926.135 I slot print_timing: id 1 | task 8829 | total time = 35118.70 ms / 987 tokens 51.11.926.135 I slot print_timing: id 1 | task 8829 | graphs reused = 7735 51.11.926.136 I slot print_timing: id 1 | task 8829 | graph reallocs = 0 / 0 (same size) / (changed size) 51.11.927.703 I slot release: id 1 | task 8829 | stop processing: n_tokens = 986, truncated = 0 51.11.927.729 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 436, progress = 0.46, t = 15.27 s / 28.55 tokens per second 51.11.956.857 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 390, progress = 0.43, t = 15.27 s / 25.54 tokens per second 51.20.307.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 106146863299 51.20.307.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 51.22.013.059 I slot launch_slot_: id 0 | task 8841 | processing task, is_child = 0 51.22.013.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 51.23.945.526 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 106146865327 51.23.945.681 I slot launch_slot_: id 1 | task 8842 | processing task, is_child = 0 51.23.945.862 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 774, progress = 0.81, t = 23.66 s / 32.72 tokens per second 51.23.957.854 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 774, progress = 0.85, t = 23.66 s / 32.72 tokens per second 51.31.851.744 I slot print_timing: id 0 | task 8841 | prompt processing, n_tokens = 116, progress = 0.12, t = 7.91 s / 14.67 tokens per second 51.32.040.792 I slot print_timing: id 1 | task 8842 | prompt processing, n_tokens = 176, progress = 0.13, t = 7.91 s / 22.26 tokens per second 51.32.159.333 I slot print_timing: id 2 | task 8835 | prompt processing, n_tokens = 948, progress = 1.00, t = 35.20 s / 26.93 tokens per second 51.32.164.188 I slot print_timing: id 3 | task 8836 | prompt processing, n_tokens = 902, progress = 1.00, t = 35.20 s / 25.62 tokens per second 51.37.264.096 I slot print_timing: id 0 | task 8841 | prompt processing, n_tokens = 232, progress = 0.25, t = 13.32 s / 17.42 tokens per second 51.37.264.116 I slot print_timing: id 1 | task 8842 | prompt processing, n_tokens = 431, progress = 0.32, t = 13.32 s / 32.36 tokens per second 51.44.683.704 I slot print_timing: id 2 | task 8835 | prompt eval time = 40613.01 ms / 952 tokens ( 42.66 ms per token, 23.44 tokens per second) 51.44.683.709 I slot print_timing: id 2 | task 8835 | eval time = 7420.50 ms / 2 tokens ( 7420.50 ms per token, 0.13 tokens per second) 51.44.683.710 I slot print_timing: id 2 | task 8835 | total time = 48033.51 ms / 954 tokens 51.44.683.710 I slot print_timing: id 2 | task 8835 | graphs reused = 7735 51.44.683.710 I slot print_timing: id 2 | task 8835 | graph reallocs = 0 / 0 (same size) / (changed size) 51.44.689.862 I slot release: id 2 | task 8835 | stop processing: n_tokens = 953, truncated = 0 51.44.690.191 I slot print_timing: id 3 | task 8836 | prompt eval time = 40613.32 ms / 906 tokens ( 44.83 ms per token, 22.31 tokens per second) 51.44.690.195 I slot print_timing: id 3 | task 8836 | eval time = 7426.59 ms / 2 tokens ( 7426.59 ms per token, 0.13 tokens per second) 51.44.690.195 I slot print_timing: id 3 | task 8836 | total time = 48039.91 ms / 908 tokens 51.44.690.196 I slot print_timing: id 3 | task 8836 | graphs reused = 7735 51.44.690.196 I slot print_timing: id 3 | task 8836 | graph reallocs = 0 / 0 (same size) / (changed size) 51.44.691.244 I slot release: id 3 | task 8836 | stop processing: n_tokens = 907, truncated = 0 51.44.691.279 I slot print_timing: id 0 | task 8841 | prompt processing, n_tokens = 424, progress = 0.45, t = 20.74 s / 20.45 tokens per second 51.44.709.601 I slot print_timing: id 1 | task 8842 | prompt processing, n_tokens = 840, progress = 0.62, t = 20.74 s / 40.51 tokens per second 51.52.339.137 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 106179627487 51.52.339.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.964 MiB) 51.54.124.652 I slot launch_slot_: id 2 | task 8847 | processing task, is_child = 0 51.54.124.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.092 MiB) 51.56.756.250 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 106179628868 51.56.756.396 I slot launch_slot_: id 3 | task 8848 | processing task, is_child = 0 51.56.756.404 I slot print_timing: id 0 | task 8841 | prompt processing, n_tokens = 774, progress = 0.82, t = 28.39 s / 27.26 tokens per second 51.56.832.995 I slot print_timing: id 1 | task 8842 | prompt processing, n_tokens = 1152, progress = 0.85, t = 28.39 s / 40.57 tokens per second 52.05.912.332 I slot print_timing: id 0 | task 8841 | prompt processing, n_tokens = 936, progress = 1.00, t = 41.97 s / 22.30 tokens per second 52.06.363.211 I slot print_timing: id 1 | task 8842 | prompt processing, n_tokens = 1352, progress = 1.00, t = 41.97 s / 32.22 tokens per second 52.06.401.919 I slot print_timing: id 2 | task 8847 | prompt processing, n_tokens = 176, progress = 0.14, t = 9.01 s / 19.54 tokens per second 52.06.420.088 I slot print_timing: id 3 | task 8848 | prompt processing, n_tokens = 176, progress = 0.13, t = 9.01 s / 19.54 tokens per second 52.12.951.082 I slot print_timing: id 2 | task 8847 | prompt processing, n_tokens = 431, progress = 0.34, t = 16.05 s / 26.86 tokens per second 52.12.951.110 I slot print_timing: id 3 | task 8848 | prompt processing, n_tokens = 431, progress = 0.32, t = 16.05 s / 26.86 tokens per second 52.21.966.201 I slot print_timing: id 0 | task 8841 | prompt eval time = 49004.99 ms / 940 tokens ( 52.13 ms per token, 19.18 tokens per second) 52.21.966.206 I slot print_timing: id 0 | task 8841 | eval time = 9015.51 ms / 2 tokens ( 9015.51 ms per token, 0.11 tokens per second) 52.21.966.208 I slot print_timing: id 0 | task 8841 | total time = 58020.50 ms / 942 tokens 52.21.966.208 I slot print_timing: id 0 | task 8841 | graphs reused = 7735 52.21.966.209 I slot print_timing: id 0 | task 8841 | graph reallocs = 0 / 0 (same size) / (changed size) 52.21.966.420 I slot release: id 0 | task 8841 | stop processing: n_tokens = 941, truncated = 0 52.21.966.819 I slot print_timing: id 1 | task 8842 | prompt eval time = 49005.28 ms / 1356 tokens ( 36.14 ms per token, 27.67 tokens per second) 52.21.966.822 I slot print_timing: id 1 | task 8842 | eval time = 9015.75 ms / 2 tokens ( 9015.75 ms per token, 0.11 tokens per second) 52.21.966.823 I slot print_timing: id 1 | task 8842 | total time = 58021.03 ms / 1358 tokens 52.21.966.823 I slot print_timing: id 1 | task 8842 | graphs reused = 7735 52.21.966.823 I slot print_timing: id 1 | task 8842 | graph reallocs = 0 / 0 (same size) / (changed size) 52.21.970.652 I slot release: id 1 | task 8842 | stop processing: n_tokens = 1357, truncated = 0 52.21.970.666 I slot print_timing: id 2 | task 8847 | prompt processing, n_tokens = 743, progress = 0.59, t = 25.06 s / 29.65 tokens per second 52.21.986.940 I slot print_timing: id 3 | task 8848 | prompt processing, n_tokens = 826, progress = 0.62, t = 25.06 s / 32.96 tokens per second 52.30.025.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 52.30.025.464 I slot launch_slot_: id 1 | task 8853 | processing task, is_child = 0 52.30.025.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.842 MiB) 52.32.094.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 106216904042 52.32.094.274 I slot launch_slot_: id 0 | task 8854 | processing task, is_child = 0 52.32.110.138 I slot print_timing: id 2 | task 8847 | prompt processing, n_tokens = 1152, progress = 0.92, t = 33.12 s / 34.78 tokens per second 52.32.118.822 I slot print_timing: id 3 | task 8848 | prompt processing, n_tokens = 1152, progress = 0.86, t = 33.12 s / 34.78 tokens per second 52.38.575.295 I slot print_timing: id 0 | task 8854 | prompt processing, n_tokens = 139, progress = 0.18, t = 6.48 s / 21.45 tokens per second 52.39.781.503 I slot print_timing: id 1 | task 8853 | prompt processing, n_tokens = 144, progress = 1.00, t = 6.48 s / 22.22 tokens per second 52.39.831.859 I slot print_timing: id 2 | task 8847 | prompt processing, n_tokens = 1255, progress = 1.00, t = 41.67 s / 30.12 tokens per second 52.39.839.301 I slot print_timing: id 3 | task 8848 | prompt processing, n_tokens = 1338, progress = 1.00, t = 41.67 s / 32.11 tokens per second 52.42.304.404 I slot print_timing: id 0 | task 8854 | prompt processing, n_tokens = 276, progress = 0.35, t = 10.21 s / 27.04 tokens per second 52.47.453.408 I slot print_timing: id 1 | task 8853 | prompt eval time = 10208.98 ms / 148 tokens ( 68.98 ms per token, 14.50 tokens per second) 52.47.453.414 I slot print_timing: id 1 | task 8853 | eval time = 5150.05 ms / 2 tokens ( 5150.05 ms per token, 0.19 tokens per second) 52.47.453.414 I slot print_timing: id 1 | task 8853 | total time = 15359.03 ms / 150 tokens 52.47.453.415 I slot print_timing: id 1 | task 8853 | graphs reused = 7735 52.47.453.415 I slot print_timing: id 1 | task 8853 | graph reallocs = 0 / 0 (same size) / (changed size) 52.47.453.634 I slot release: id 1 | task 8853 | stop processing: n_tokens = 1301, truncated = 0 52.47.453.873 I slot print_timing: id 2 | task 8847 | prompt eval time = 45398.96 ms / 1259 tokens ( 36.06 ms per token, 27.73 tokens per second) 52.47.453.875 I slot print_timing: id 2 | task 8847 | eval time = 5150.12 ms / 2 tokens ( 5150.12 ms per token, 0.19 tokens per second) 52.47.453.880 I slot print_timing: id 2 | task 8847 | total time = 50549.08 ms / 1261 tokens 52.47.453.880 I slot print_timing: id 2 | task 8847 | graphs reused = 7735 52.47.453.881 I slot print_timing: id 2 | task 8847 | graph reallocs = 0 / 0 (same size) / (changed size) 52.47.453.915 I slot release: id 2 | task 8847 | stop processing: n_tokens = 1260, truncated = 0 52.47.454.287 I slot print_timing: id 3 | task 8848 | prompt eval time = 45399.48 ms / 1342 tokens ( 33.83 ms per token, 29.56 tokens per second) 52.47.454.291 I slot print_timing: id 3 | task 8848 | eval time = 5149.91 ms / 2 tokens ( 5149.91 ms per token, 0.19 tokens per second) 52.47.454.292 I slot print_timing: id 3 | task 8848 | total time = 50549.40 ms / 1344 tokens 52.47.454.292 I slot print_timing: id 3 | task 8848 | graphs reused = 7735 52.47.454.293 I slot print_timing: id 3 | task 8848 | graph reallocs = 0 / 0 (same size) / (changed size) 52.47.455.784 I slot release: id 3 | task 8848 | stop processing: n_tokens = 1343, truncated = 0 52.47.455.811 I slot print_timing: id 0 | task 8854 | prompt processing, n_tokens = 681, progress = 0.86, t = 15.36 s / 44.34 tokens per second 52.47.523.373 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 106242391258 52.47.523.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.279 MiB) 52.49.835.261 I slot launch_slot_: id 1 | task 8859 | processing task, is_child = 0 52.49.835.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.654 MiB) 52.52.184.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.151 MiB) 52.54.266.756 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 106242391537 52.54.266.943 I slot launch_slot_: id 2 | task 8860 | processing task, is_child = 0 52.54.267.012 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 106242393410 52.54.267.101 I slot launch_slot_: id 3 | task 8861 | processing task, is_child = 0 52.54.267.107 I slot print_timing: id 0 | task 8854 | prompt processing, n_tokens = 788, progress = 0.99, t = 15.43 s / 51.07 tokens per second 53.00.500.110 I slot print_timing: id 1 | task 8859 | prompt processing, n_tokens = 139, progress = 0.17, t = 6.02 s / 23.09 tokens per second 53.00.513.327 I slot print_timing: id 2 | task 8860 | prompt processing, n_tokens = 149, progress = 0.17, t = 6.02 s / 24.75 tokens per second 53.00.568.636 I slot print_timing: id 3 | task 8861 | prompt processing, n_tokens = 149, progress = 0.17, t = 6.02 s / 24.75 tokens per second 53.06.209.049 I slot print_timing: id 0 | task 8854 | prompt eval time = 28405.79 ms / 792 tokens ( 35.87 ms per token, 27.88 tokens per second) 53.06.209.052 I slot print_timing: id 0 | task 8854 | eval time = 5708.97 ms / 2 tokens ( 5708.97 ms per token, 0.18 tokens per second) 53.06.209.053 I slot print_timing: id 0 | task 8854 | total time = 34114.75 ms / 794 tokens 53.06.209.053 I slot print_timing: id 0 | task 8854 | graphs reused = 7735 53.06.209.054 I slot print_timing: id 0 | task 8854 | graph reallocs = 0 / 0 (same size) / (changed size) 53.06.213.537 I slot release: id 0 | task 8854 | stop processing: n_tokens = 793, truncated = 0 53.06.213.583 I slot print_timing: id 1 | task 8859 | prompt processing, n_tokens = 287, progress = 0.36, t = 11.73 s / 24.47 tokens per second 53.06.213.600 I slot print_timing: id 2 | task 8860 | prompt processing, n_tokens = 285, progress = 0.33, t = 11.73 s / 24.30 tokens per second 53.06.213.611 I slot print_timing: id 3 | task 8861 | prompt processing, n_tokens = 285, progress = 0.32, t = 11.73 s / 24.30 tokens per second 53.08.278.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 106261151161 53.08.278.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 53.10.124.842 I slot launch_slot_: id 0 | task 8865 | processing task, is_child = 0 53.10.124.949 I slot print_timing: id 1 | task 8859 | prompt processing, n_tokens = 292, progress = 0.36, t = 13.80 s / 21.16 tokens per second 53.10.129.917 I slot print_timing: id 2 | task 8860 | prompt processing, n_tokens = 343, progress = 0.40, t = 13.80 s / 24.86 tokens per second 53.10.142.859 I slot print_timing: id 3 | task 8861 | prompt processing, n_tokens = 375, progress = 0.42, t = 13.80 s / 27.18 tokens per second 53.26.728.619 I slot print_timing: id 0 | task 8865 | prompt processing, n_tokens = 163, progress = 0.21, t = 16.60 s / 9.82 tokens per second 53.27.123.127 I slot print_timing: id 1 | task 8859 | prompt processing, n_tokens = 681, progress = 0.84, t = 32.25 s / 21.12 tokens per second 53.27.137.375 I slot print_timing: id 2 | task 8860 | prompt processing, n_tokens = 741, progress = 0.86, t = 32.25 s / 22.98 tokens per second 53.27.151.889 I slot print_timing: id 3 | task 8861 | prompt processing, n_tokens = 741, progress = 0.83, t = 32.25 s / 22.98 tokens per second 53.33.376.181 I slot print_timing: id 0 | task 8865 | prompt processing, n_tokens = 274, progress = 0.35, t = 23.25 s / 11.78 tokens per second 53.33.838.783 I slot print_timing: id 1 | task 8859 | prompt processing, n_tokens = 804, progress = 1.00, t = 38.90 s / 20.67 tokens per second 53.33.954.783 I slot print_timing: id 2 | task 8860 | prompt processing, n_tokens = 855, progress = 1.00, t = 38.90 s / 21.98 tokens per second 53.34.021.485 I slot print_timing: id 3 | task 8861 | prompt processing, n_tokens = 887, progress = 1.00, t = 38.90 s / 22.80 tokens per second 53.39.072.051 I slot print_timing: id 0 | task 8865 | prompt processing, n_tokens = 655, progress = 0.83, t = 28.95 s / 22.63 tokens per second 53.41.220.361 I slot print_timing: id 1 | task 8859 | prompt eval time = 44591.71 ms / 808 tokens ( 55.19 ms per token, 18.12 tokens per second) 53.41.220.366 I slot print_timing: id 1 | task 8859 | eval time = 2149.22 ms / 2 tokens ( 2149.22 ms per token, 0.47 tokens per second) 53.41.220.367 I slot print_timing: id 1 | task 8859 | total time = 46740.93 ms / 810 tokens 53.41.220.367 I slot print_timing: id 1 | task 8859 | graphs reused = 7735 53.41.220.368 I slot print_timing: id 1 | task 8859 | graph reallocs = 0 / 0 (same size) / (changed size) 53.41.220.566 I slot release: id 1 | task 8859 | stop processing: n_tokens = 809, truncated = 0 53.41.220.872 I slot print_timing: id 2 | task 8860 | prompt eval time = 44592.03 ms / 859 tokens ( 51.91 ms per token, 19.26 tokens per second) 53.41.220.874 I slot print_timing: id 2 | task 8860 | eval time = 2149.28 ms / 2 tokens ( 2149.28 ms per token, 0.47 tokens per second) 53.41.220.875 I slot print_timing: id 2 | task 8860 | total time = 46741.31 ms / 861 tokens 53.41.220.875 I slot print_timing: id 2 | task 8860 | graphs reused = 7735 53.41.220.875 I slot print_timing: id 2 | task 8860 | graph reallocs = 0 / 0 (same size) / (changed size) 53.41.225.216 I slot release: id 2 | task 8860 | stop processing: n_tokens = 860, truncated = 0 53.41.225.825 I slot print_timing: id 3 | task 8861 | prompt eval time = 44592.37 ms / 891 tokens ( 50.05 ms per token, 19.98 tokens per second) 53.41.225.829 I slot print_timing: id 3 | task 8861 | eval time = 2153.81 ms / 2 tokens ( 2153.81 ms per token, 0.46 tokens per second) 53.41.225.829 I slot print_timing: id 3 | task 8861 | total time = 46746.18 ms / 893 tokens 53.41.225.830 I slot print_timing: id 3 | task 8861 | graphs reused = 7735 53.41.226.120 I slot print_timing: id 3 | task 8861 | graph reallocs = 0 / 0 (same size) / (changed size) 53.41.226.163 I slot release: id 3 | task 8861 | stop processing: n_tokens = 892, truncated = 0 53.41.226.188 I slot print_timing: id 0 | task 8865 | prompt processing, n_tokens = 786, progress = 0.99, t = 31.10 s / 25.28 tokens per second 53.41.448.807 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 106296158189 53.41.448.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.279 MiB) 53.43.932.111 I slot launch_slot_: id 1 | task 8871 | processing task, is_child = 0 53.43.932.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.276 MiB) 53.45.934.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.779 MiB) 53.48.520.594 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 106296162840 53.48.520.765 I slot launch_slot_: id 2 | task 8872 | processing task, is_child = 0 53.48.520.822 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 106296163785 53.48.520.886 I slot launch_slot_: id 3 | task 8873 | processing task, is_child = 0 53.55.008.518 I slot print_timing: id 0 | task 8865 | prompt eval time = 31323.94 ms / 790 tokens ( 39.65 ms per token, 25.22 tokens per second) 53.55.008.521 I slot print_timing: id 0 | task 8865 | eval time = 13559.70 ms / 2 tokens (13559.70 ms per token, 0.07 tokens per second) 53.55.008.521 I slot print_timing: id 0 | task 8865 | total time = 44883.64 ms / 792 tokens 53.55.008.522 I slot print_timing: id 0 | task 8865 | graphs reused = 7735 53.55.008.522 I slot print_timing: id 0 | task 8865 | graph reallocs = 0 / 0 (same size) / (changed size) 53.55.012.342 I slot release: id 0 | task 8865 | stop processing: n_tokens = 791, truncated = 0 53.55.012.384 I slot print_timing: id 1 | task 8871 | prompt processing, n_tokens = 163, progress = 0.21, t = 6.49 s / 25.13 tokens per second 53.55.025.297 I slot print_timing: id 2 | task 8872 | prompt processing, n_tokens = 163, progress = 0.21, t = 6.49 s / 25.13 tokens per second 53.55.031.709 I slot print_timing: id 3 | task 8873 | prompt processing, n_tokens = 163, progress = 0.19, t = 6.49 s / 25.13 tokens per second 53.58.760.005 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 53.58.760.133 I slot launch_slot_: id 0 | task 8876 | processing task, is_child = 0 53.59.239.381 I slot print_timing: id 1 | task 8871 | prompt processing, n_tokens = 258, progress = 0.33, t = 10.24 s / 25.20 tokens per second 53.59.252.531 I slot print_timing: id 2 | task 8872 | prompt processing, n_tokens = 262, progress = 0.34, t = 10.24 s / 25.59 tokens per second 53.59.288.824 I slot print_timing: id 3 | task 8873 | prompt processing, n_tokens = 287, progress = 0.34, t = 10.24 s / 28.03 tokens per second 54.11.505.155 I slot print_timing: id 0 | task 8876 | prompt processing, n_tokens = 143, progress = 1.00, t = 12.74 s / 11.22 tokens per second 54.11.697.157 I slot print_timing: id 1 | task 8871 | prompt processing, n_tokens = 655, progress = 0.85, t = 22.98 s / 28.50 tokens per second 54.11.747.163 I slot print_timing: id 2 | task 8872 | prompt processing, n_tokens = 655, progress = 0.84, t = 22.98 s / 28.50 tokens per second 54.11.796.949 I slot print_timing: id 3 | task 8873 | prompt processing, n_tokens = 339, progress = 0.40, t = 22.98 s / 14.75 tokens per second 54.19.358.269 I slot print_timing: id 1 | task 8871 | prompt processing, n_tokens = 770, progress = 0.99, t = 30.84 s / 24.97 tokens per second 54.19.375.778 I slot print_timing: id 2 | task 8872 | prompt processing, n_tokens = 774, progress = 0.99, t = 30.84 s / 25.10 tokens per second 54.19.390.315 I slot print_timing: id 3 | task 8873 | prompt processing, n_tokens = 655, progress = 0.77, t = 30.84 s / 21.24 tokens per second 54.22.363.324 I slot print_timing: id 0 | task 8876 | prompt eval time = 20598.11 ms / 147 tokens ( 140.12 ms per token, 7.14 tokens per second) 54.22.363.327 I slot print_timing: id 0 | task 8876 | eval time = 3005.06 ms / 2 tokens ( 3005.06 ms per token, 0.33 tokens per second) 54.22.363.328 I slot print_timing: id 0 | task 8876 | total time = 23603.18 ms / 149 tokens 54.22.363.328 I slot print_timing: id 0 | task 8876 | graphs reused = 7735 54.22.363.328 I slot print_timing: id 0 | task 8876 | graph reallocs = 0 / 0 (same size) / (changed size) 54.22.364.996 I slot release: id 0 | task 8876 | stop processing: n_tokens = 803, truncated = 0 54.22.366.714 I slot print_timing: id 3 | task 8873 | prompt processing, n_tokens = 851, progress = 1.00, t = 33.84 s / 25.15 tokens per second 54.22.792.895 I slot print_timing: id 1 | task 8871 | prompt eval time = 33844.89 ms / 774 tokens ( 43.73 ms per token, 22.87 tokens per second) 54.22.792.898 I slot print_timing: id 1 | task 8871 | eval time = 427.10 ms / 2 tokens ( 427.10 ms per token, 2.34 tokens per second) 54.22.792.898 I slot print_timing: id 1 | task 8871 | total time = 34272.00 ms / 776 tokens 54.22.792.899 I slot print_timing: id 1 | task 8871 | graphs reused = 7735 54.22.792.899 I slot print_timing: id 1 | task 8871 | graph reallocs = 0 / 0 (same size) / (changed size) 54.22.792.943 I slot release: id 1 | task 8871 | stop processing: n_tokens = 775, truncated = 0 54.22.793.264 I slot print_timing: id 2 | task 8872 | prompt eval time = 33845.69 ms / 778 tokens ( 43.50 ms per token, 22.99 tokens per second) 54.22.793.267 I slot print_timing: id 2 | task 8872 | eval time = 426.59 ms / 2 tokens ( 426.59 ms per token, 2.34 tokens per second) 54.22.793.267 I slot print_timing: id 2 | task 8872 | total time = 34272.29 ms / 780 tokens 54.22.793.267 I slot print_timing: id 2 | task 8872 | graphs reused = 7735 54.22.793.268 I slot print_timing: id 2 | task 8872 | graph reallocs = 0 / 0 (same size) / (changed size) 54.22.794.348 I slot release: id 2 | task 8872 | stop processing: n_tokens = 779, truncated = 0 54.22.795.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 106337302620 54.22.795.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.715 MiB) 54.24.755.847 I slot launch_slot_: id 0 | task 8881 | processing task, is_child = 0 54.24.755.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.839 MiB) 54.27.404.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 806.965 MiB) 54.29.317.941 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 106337730565 54.29.318.455 I slot launch_slot_: id 1 | task 8882 | processing task, is_child = 0 54.29.318.499 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 106337731971 54.29.318.574 I slot launch_slot_: id 2 | task 8883 | processing task, is_child = 0 54.36.547.550 I slot print_timing: id 3 | task 8873 | prompt eval time = 34274.07 ms / 855 tokens ( 40.09 ms per token, 24.95 tokens per second) 54.36.547.556 I slot print_timing: id 3 | task 8873 | eval time = 13752.42 ms / 2 tokens (13752.42 ms per token, 0.07 tokens per second) 54.36.547.556 I slot print_timing: id 3 | task 8873 | total time = 48026.49 ms / 857 tokens 54.36.548.471 I slot print_timing: id 3 | task 8873 | graphs reused = 7735 54.36.548.474 I slot print_timing: id 3 | task 8873 | graph reallocs = 0 / 0 (same size) / (changed size) 54.36.549.161 I slot release: id 3 | task 8873 | stop processing: n_tokens = 856, truncated = 0 54.36.549.205 I slot print_timing: id 0 | task 8881 | prompt processing, n_tokens = 183, progress = 0.19, t = 7.23 s / 25.32 tokens per second 54.36.604.115 I slot print_timing: id 1 | task 8882 | prompt processing, n_tokens = 183, progress = 0.19, t = 7.23 s / 25.32 tokens per second 54.36.640.382 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 183, progress = 0.19, t = 7.23 s / 25.32 tokens per second 54.36.678.998 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 106351486785 54.36.679.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 829.473 MiB) 54.42.392.192 I slot launch_slot_: id 3 | task 8886 | processing task, is_child = 0 54.42.392.210 I slot print_timing: id 0 | task 8881 | prompt processing, n_tokens = 333, progress = 0.34, t = 7.36 s / 45.24 tokens per second 54.42.392.223 I slot print_timing: id 1 | task 8882 | prompt processing, n_tokens = 333, progress = 0.35, t = 7.36 s / 45.24 tokens per second 54.42.392.230 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 333, progress = 0.35, t = 7.36 s / 45.24 tokens per second 54.48.193.215 I slot print_timing: id 0 | task 8881 | prompt processing, n_tokens = 455, progress = 0.47, t = 18.87 s / 24.11 tokens per second 54.49.372.112 I slot print_timing: id 1 | task 8882 | prompt processing, n_tokens = 428, progress = 0.45, t = 18.87 s / 22.68 tokens per second 54.49.383.426 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 448, progress = 0.46, t = 18.87 s / 23.74 tokens per second 54.49.396.840 I slot print_timing: id 3 | task 8886 | prompt processing, n_tokens = 183, progress = 0.19, t = 5.80 s / 31.55 tokens per second 55.05.558.556 I slot print_timing: id 0 | task 8881 | prompt processing, n_tokens = 836, progress = 0.86, t = 36.24 s / 23.07 tokens per second 55.06.010.619 I slot print_timing: id 1 | task 8882 | prompt processing, n_tokens = 836, progress = 0.89, t = 36.24 s / 23.07 tokens per second 55.06.024.580 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 836, progress = 0.87, t = 36.24 s / 23.07 tokens per second 55.06.038.398 I slot print_timing: id 3 | task 8886 | prompt processing, n_tokens = 333, progress = 0.35, t = 23.17 s / 14.37 tokens per second 55.11.955.303 I slot print_timing: id 0 | task 8881 | prompt processing, n_tokens = 967, progress = 1.00, t = 42.64 s / 22.68 tokens per second 55.12.408.411 I slot print_timing: id 1 | task 8882 | prompt processing, n_tokens = 940, progress = 1.00, t = 42.64 s / 22.05 tokens per second 55.12.436.776 I slot print_timing: id 2 | task 8883 | prompt processing, n_tokens = 960, progress = 1.00, t = 42.64 s / 22.52 tokens per second 55.12.568.945 I slot print_timing: id 3 | task 8886 | prompt processing, n_tokens = 431, progress = 0.46, t = 29.56 s / 14.58 tokens per second 55.18.085.904 I slot print_timing: id 3 | task 8886 | prompt processing, n_tokens = 836, progress = 0.88, t = 35.69 s / 23.42 tokens per second 55.19.908.570 I slot print_timing: id 0 | task 8881 | prompt eval time = 48765.92 ms / 971 tokens ( 50.22 ms per token, 19.91 tokens per second) 55.19.908.579 I slot print_timing: id 0 | task 8881 | eval time = 1824.06 ms / 2 tokens ( 1824.06 ms per token, 0.55 tokens per second) 55.19.908.580 I slot print_timing: id 0 | task 8881 | total time = 50589.97 ms / 973 tokens 55.19.908.580 I slot print_timing: id 0 | task 8881 | graphs reused = 7735 55.19.908.581 I slot print_timing: id 0 | task 8881 | graph reallocs = 0 / 0 (same size) / (changed size) 55.19.912.575 I slot release: id 0 | task 8881 | stop processing: n_tokens = 972, truncated = 0 55.19.913.402 I slot print_timing: id 1 | task 8882 | prompt eval time = 48766.36 ms / 944 tokens ( 51.66 ms per token, 19.36 tokens per second) 55.19.913.406 I slot print_timing: id 1 | task 8882 | eval time = 1828.34 ms / 2 tokens ( 1828.34 ms per token, 0.55 tokens per second) 55.19.913.407 I slot print_timing: id 1 | task 8882 | total time = 50594.70 ms / 946 tokens 55.19.913.407 I slot print_timing: id 1 | task 8882 | graphs reused = 7735 55.19.913.408 I slot print_timing: id 1 | task 8882 | graph reallocs = 0 / 0 (same size) / (changed size) 55.19.913.447 I slot release: id 1 | task 8882 | stop processing: n_tokens = 945, truncated = 0 55.19.914.420 I slot print_timing: id 2 | task 8883 | prompt eval time = 48767.11 ms / 964 tokens ( 50.59 ms per token, 19.77 tokens per second) 55.19.914.423 I slot print_timing: id 2 | task 8883 | eval time = 1828.55 ms / 2 tokens ( 1828.55 ms per token, 0.55 tokens per second) 55.19.914.425 I slot print_timing: id 2 | task 8883 | total time = 50595.67 ms / 966 tokens 55.19.914.425 I slot print_timing: id 2 | task 8883 | graphs reused = 7735 55.19.914.425 I slot print_timing: id 2 | task 8883 | graph reallocs = 0 / 0 (same size) / (changed size) 55.19.914.748 I slot release: id 2 | task 8883 | stop processing: n_tokens = 965, truncated = 0 55.19.914.775 I slot print_timing: id 3 | task 8886 | prompt processing, n_tokens = 943, progress = 1.00, t = 37.52 s / 25.14 tokens per second 55.20.147.643 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 55.20.147.686 I slot launch_slot_: id 0 | task 8893 | processing task, is_child = 0 55.20.147.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 826.910 MiB) 55.22.407.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 832.099 MiB) 55.24.602.511 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 106394851069 55.24.602.701 I slot launch_slot_: id 1 | task 8894 | processing task, is_child = 0 55.24.602.756 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 106394852371 55.24.602.827 I slot launch_slot_: id 2 | task 8895 | processing task, is_child = 0 55.31.127.556 I slot print_timing: id 3 | task 8886 | prompt eval time = 37755.40 ms / 947 tokens ( 39.87 ms per token, 25.08 tokens per second) 55.31.127.561 I slot print_timing: id 3 | task 8886 | eval time = 10979.90 ms / 2 tokens (10979.90 ms per token, 0.09 tokens per second) 55.31.127.562 I slot print_timing: id 3 | task 8886 | total time = 48735.30 ms / 949 tokens 55.31.127.563 I slot print_timing: id 3 | task 8886 | graphs reused = 7735 55.31.127.563 I slot print_timing: id 3 | task 8886 | graph reallocs = 0 / 0 (same size) / (changed size) 55.31.127.788 I slot release: id 3 | task 8886 | stop processing: n_tokens = 948, truncated = 0 55.31.127.822 I slot print_timing: id 0 | task 8893 | prompt processing, n_tokens = 129, progress = 1.00, t = 6.52 s / 19.77 tokens per second 55.31.148.474 I slot print_timing: id 1 | task 8894 | prompt processing, n_tokens = 162, progress = 0.20, t = 6.46 s / 25.09 tokens per second 55.31.215.103 I slot print_timing: id 2 | task 8895 | prompt processing, n_tokens = 162, progress = 0.20, t = 6.46 s / 25.09 tokens per second 55.34.813.775 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 106406065411 55.34.813.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 797.712 MiB) 55.37.183.550 I slot launch_slot_: id 3 | task 8898 | processing task, is_child = 0 55.37.183.573 I slot print_timing: id 1 | task 8894 | prompt processing, n_tokens = 283, progress = 0.35, t = 10.14 s / 27.90 tokens per second 55.37.217.641 I slot print_timing: id 2 | task 8895 | prompt processing, n_tokens = 282, progress = 0.35, t = 10.14 s / 27.80 tokens per second 55.48.894.030 I slot print_timing: id 0 | task 8893 | prompt eval time = 10210.93 ms / 133 tokens ( 76.77 ms per token, 13.03 tokens per second) 55.48.894.033 I slot print_timing: id 0 | task 8893 | eval time = 14080.25 ms / 2 tokens (14080.25 ms per token, 0.07 tokens per second) 55.48.894.033 I slot print_timing: id 0 | task 8893 | total time = 24291.18 ms / 135 tokens 55.48.894.034 I slot print_timing: id 0 | task 8893 | graphs reused = 7735 55.48.894.034 I slot print_timing: id 0 | task 8893 | graph reallocs = 0 / 0 (same size) / (changed size) 55.48.896.303 I slot release: id 0 | task 8893 | stop processing: n_tokens = 970, truncated = 0 55.48.896.351 I slot print_timing: id 1 | task 8894 | prompt processing, n_tokens = 679, progress = 0.85, t = 24.22 s / 28.03 tokens per second 55.48.904.458 I slot print_timing: id 2 | task 8895 | prompt processing, n_tokens = 679, progress = 0.85, t = 24.22 s / 28.03 tokens per second 55.48.916.741 I slot print_timing: id 3 | task 8898 | prompt processing, n_tokens = 137, progress = 0.14, t = 11.61 s / 11.80 tokens per second 55.53.265.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 106423833927 55.53.265.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.712 MiB) 55.54.904.449 I slot launch_slot_: id 0 | task 8901 | processing task, is_child = 0 55.54.904.569 I slot print_timing: id 1 | task 8894 | prompt processing, n_tokens = 795, progress = 0.99, t = 28.60 s / 27.80 tokens per second 55.54.913.020 I slot print_timing: id 2 | task 8895 | prompt processing, n_tokens = 794, progress = 0.99, t = 28.60 s / 27.77 tokens per second 55.54.925.431 I slot print_timing: id 3 | task 8898 | prompt processing, n_tokens = 335, progress = 0.34, t = 15.98 s / 20.96 tokens per second 55.58.851.624 I slot print_timing: id 0 | task 8901 | prompt processing, n_tokens = 137, progress = 0.14, t = 3.95 s / 34.72 tokens per second 55.58.872.131 I slot print_timing: id 3 | task 8898 | prompt processing, n_tokens = 459, progress = 0.47, t = 21.57 s / 21.28 tokens per second 56.06.294.319 I slot print_timing: id 1 | task 8894 | prompt eval time = 34180.58 ms / 799 tokens ( 42.78 ms per token, 23.38 tokens per second) 56.06.294.327 I slot print_timing: id 1 | task 8894 | eval time = 7442.34 ms / 2 tokens ( 7442.34 ms per token, 0.13 tokens per second) 56.06.294.327 I slot print_timing: id 1 | task 8894 | total time = 41622.92 ms / 801 tokens 56.06.294.328 I slot print_timing: id 1 | task 8894 | graphs reused = 7735 56.06.294.328 I slot print_timing: id 1 | task 8894 | graph reallocs = 0 / 0 (same size) / (changed size) 56.06.298.451 I slot release: id 1 | task 8894 | stop processing: n_tokens = 800, truncated = 0 56.06.299.332 I slot print_timing: id 2 | task 8895 | prompt eval time = 34181.16 ms / 798 tokens ( 42.83 ms per token, 23.35 tokens per second) 56.06.299.337 I slot print_timing: id 2 | task 8895 | eval time = 7447.72 ms / 2 tokens ( 7447.72 ms per token, 0.13 tokens per second) 56.06.299.338 I slot print_timing: id 2 | task 8895 | total time = 41628.88 ms / 800 tokens 56.06.299.338 I slot print_timing: id 2 | task 8895 | graphs reused = 7735 56.06.299.339 I slot print_timing: id 2 | task 8895 | graph reallocs = 0 / 0 (same size) / (changed size) 56.06.300.643 I slot release: id 2 | task 8895 | stop processing: n_tokens = 799, truncated = 0 56.06.300.673 I slot print_timing: id 0 | task 8901 | prompt processing, n_tokens = 335, progress = 0.35, t = 11.39 s / 29.42 tokens per second 56.06.300.697 I slot print_timing: id 3 | task 8898 | prompt processing, n_tokens = 826, progress = 0.85, t = 29.01 s / 28.47 tokens per second 56.07.893.803 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 106441236075 56.07.893.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.901 MiB) 56.10.034.159 I slot launch_slot_: id 1 | task 8905 | processing task, is_child = 0 56.10.034.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.901 MiB) 56.11.881.513 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 106441238267 56.11.881.660 I slot launch_slot_: id 2 | task 8906 | processing task, is_child = 0 56.11.881.670 I slot print_timing: id 0 | task 8901 | prompt processing, n_tokens = 437, progress = 0.46, t = 12.99 s / 33.64 tokens per second 56.11.923.439 I slot print_timing: id 3 | task 8898 | prompt processing, n_tokens = 971, progress = 1.00, t = 30.61 s / 31.72 tokens per second 56.20.609.192 I slot print_timing: id 0 | task 8901 | prompt processing, n_tokens = 826, progress = 0.87, t = 25.70 s / 32.13 tokens per second 56.20.618.503 I slot print_timing: id 1 | task 8905 | prompt processing, n_tokens = 137, progress = 0.14, t = 8.69 s / 15.77 tokens per second 56.20.666.403 I slot print_timing: id 2 | task 8906 | prompt processing, n_tokens = 139, progress = 0.15, t = 8.69 s / 16.00 tokens per second 56.27.332.835 I slot print_timing: id 3 | task 8898 | prompt eval time = 43326.63 ms / 975 tokens ( 44.44 ms per token, 22.50 tokens per second) 56.27.332.841 I slot print_timing: id 3 | task 8898 | eval time = 6723.65 ms / 2 tokens ( 6723.65 ms per token, 0.15 tokens per second) 56.27.332.842 I slot print_timing: id 3 | task 8898 | total time = 50050.28 ms / 977 tokens 56.27.332.847 I slot print_timing: id 3 | task 8898 | graphs reused = 7735 56.27.332.847 I slot print_timing: id 3 | task 8898 | graph reallocs = 0 / 0 (same size) / (changed size) 56.27.335.130 I slot release: id 3 | task 8898 | stop processing: n_tokens = 976, truncated = 0 56.27.335.174 I slot print_timing: id 0 | task 8901 | prompt processing, n_tokens = 949, progress = 1.00, t = 32.43 s / 29.26 tokens per second 56.27.395.149 I slot print_timing: id 1 | task 8905 | prompt processing, n_tokens = 335, progress = 0.35, t = 15.41 s / 21.74 tokens per second 56.27.395.165 I slot print_timing: id 2 | task 8906 | prompt processing, n_tokens = 304, progress = 0.33, t = 15.41 s / 19.73 tokens per second 56.30.531.058 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 106462272754 56.30.531.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.337 MiB) 56.32.058.585 I slot launch_slot_: id 3 | task 8910 | processing task, is_child = 0 56.32.058.599 I slot print_timing: id 1 | task 8905 | prompt processing, n_tokens = 445, progress = 0.46, t = 18.61 s / 23.92 tokens per second 56.32.371.088 I slot print_timing: id 2 | task 8906 | prompt processing, n_tokens = 414, progress = 0.45, t = 18.61 s / 22.25 tokens per second 56.43.879.412 I slot print_timing: id 0 | task 8901 | prompt eval time = 35626.58 ms / 953 tokens ( 37.38 ms per token, 26.75 tokens per second) 56.43.879.416 I slot print_timing: id 0 | task 8901 | eval time = 13348.35 ms / 2 tokens (13348.35 ms per token, 0.07 tokens per second) 56.43.879.417 I slot print_timing: id 0 | task 8901 | total time = 48974.93 ms / 955 tokens 56.43.879.417 I slot print_timing: id 0 | task 8901 | graphs reused = 7735 56.43.879.418 I slot print_timing: id 0 | task 8901 | graph reallocs = 0 / 0 (same size) / (changed size) 56.43.880.939 I slot release: id 0 | task 8901 | stop processing: n_tokens = 954, truncated = 0 56.43.881.600 I slot print_timing: id 1 | task 8905 | prompt processing, n_tokens = 826, progress = 0.86, t = 31.96 s / 25.85 tokens per second 56.43.897.793 I slot print_timing: id 2 | task 8906 | prompt processing, n_tokens = 779, progress = 0.84, t = 31.96 s / 24.38 tokens per second 56.43.911.705 I slot print_timing: id 3 | task 8910 | prompt processing, n_tokens = 139, progress = 0.15, t = 11.48 s / 12.10 tokens per second 56.49.371.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 106478818563 56.49.371.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.586 MiB) 56.51.361.400 I slot launch_slot_: id 0 | task 8913 | processing task, is_child = 0 56.51.361.490 I slot print_timing: id 1 | task 8905 | prompt processing, n_tokens = 957, progress = 1.00, t = 37.45 s / 25.56 tokens per second 56.51.379.926 I slot print_timing: id 2 | task 8906 | prompt processing, n_tokens = 926, progress = 1.00, t = 37.45 s / 24.73 tokens per second 56.51.416.074 I slot print_timing: id 3 | task 8910 | prompt processing, n_tokens = 304, progress = 0.34, t = 16.98 s / 17.91 tokens per second 56.55.005.188 I slot print_timing: id 0 | task 8913 | prompt processing, n_tokens = 139, progress = 0.15, t = 3.64 s / 38.16 tokens per second 56.55.046.215 I slot print_timing: id 3 | task 8910 | prompt processing, n_tokens = 382, progress = 0.43, t = 22.61 s / 16.90 tokens per second 57.02.455.505 I slot print_timing: id 1 | task 8905 | prompt eval time = 43081.42 ms / 961 tokens ( 44.83 ms per token, 22.31 tokens per second) 57.02.455.511 I slot print_timing: id 1 | task 8905 | eval time = 7450.82 ms / 2 tokens ( 7450.82 ms per token, 0.13 tokens per second) 57.02.455.512 I slot print_timing: id 1 | task 8905 | total time = 50532.25 ms / 963 tokens 57.02.455.512 I slot print_timing: id 1 | task 8905 | graphs reused = 7735 57.02.455.513 I slot print_timing: id 1 | task 8905 | graph reallocs = 0 / 0 (same size) / (changed size) 57.02.456.719 I slot release: id 1 | task 8905 | stop processing: n_tokens = 962, truncated = 0 57.02.457.313 I slot print_timing: id 2 | task 8906 | prompt eval time = 43081.81 ms / 930 tokens ( 46.32 ms per token, 21.59 tokens per second) 57.02.457.316 I slot print_timing: id 2 | task 8906 | eval time = 7452.14 ms / 2 tokens ( 7452.14 ms per token, 0.13 tokens per second) 57.02.457.317 I slot print_timing: id 2 | task 8906 | total time = 50533.95 ms / 932 tokens 57.02.457.317 I slot print_timing: id 2 | task 8906 | graphs reused = 7735 57.02.457.318 I slot print_timing: id 2 | task 8906 | graph reallocs = 0 / 0 (same size) / (changed size) 57.02.465.395 I slot release: id 2 | task 8906 | stop processing: n_tokens = 931, truncated = 0 57.02.465.427 I slot print_timing: id 0 | task 8913 | prompt processing, n_tokens = 304, progress = 0.34, t = 11.09 s / 27.40 tokens per second 57.02.465.437 I slot print_timing: id 3 | task 8910 | prompt processing, n_tokens = 779, progress = 0.87, t = 30.06 s / 25.91 tokens per second 57.03.674.881 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.867 57.03.674.955 I slot launch_slot_: id 2 | task 8917 | processing task, is_child = 0 57.03.675.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.836 MiB) 57.05.484.427 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 106497394343 57.05.484.618 I slot launch_slot_: id 1 | task 8918 | processing task, is_child = 0 57.05.484.627 I slot print_timing: id 0 | task 8913 | prompt processing, n_tokens = 386, progress = 0.43, t = 12.31 s / 31.35 tokens per second 57.05.596.768 I slot print_timing: id 3 | task 8910 | prompt processing, n_tokens = 894, progress = 1.00, t = 31.28 s / 28.58 tokens per second 57.14.143.726 I slot print_timing: id 0 | task 8913 | prompt processing, n_tokens = 779, progress = 0.86, t = 22.78 s / 34.19 tokens per second 57.14.153.600 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 139, progress = 0.16, t = 8.59 s / 16.17 tokens per second 57.14.204.212 I slot print_timing: id 2 | task 8917 | prompt processing, n_tokens = 116, progress = 1.00, t = 8.59 s / 13.50 tokens per second 57.18.645.849 I slot print_timing: id 3 | task 8910 | prompt eval time = 41748.27 ms / 898 tokens ( 46.49 ms per token, 21.51 tokens per second) 57.18.645.851 I slot print_timing: id 3 | task 8910 | eval time = 4502.14 ms / 2 tokens ( 4502.14 ms per token, 0.22 tokens per second) 57.18.645.852 I slot print_timing: id 3 | task 8910 | total time = 46250.41 ms / 900 tokens 57.18.645.852 I slot print_timing: id 3 | task 8910 | graphs reused = 7735 57.18.645.853 I slot print_timing: id 3 | task 8910 | graph reallocs = 0 / 0 (same size) / (changed size) 57.18.650.513 I slot release: id 3 | task 8910 | stop processing: n_tokens = 899, truncated = 0 57.18.650.545 I slot print_timing: id 0 | task 8913 | prompt processing, n_tokens = 898, progress = 1.00, t = 27.28 s / 32.91 tokens per second 57.18.670.368 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 304, progress = 0.34, t = 13.10 s / 23.21 tokens per second 57.20.193.530 I slot print_timing: id 2 | task 8917 | prompt eval time = 13097.04 ms / 120 tokens ( 109.14 ms per token, 9.16 tokens per second) 57.20.193.533 I slot print_timing: id 2 | task 8917 | eval time = 1547.89 ms / 2 tokens ( 1547.89 ms per token, 0.65 tokens per second) 57.20.193.534 I slot print_timing: id 2 | task 8917 | total time = 14644.93 ms / 122 tokens 57.20.193.534 I slot print_timing: id 2 | task 8917 | graphs reused = 7735 57.20.193.535 I slot print_timing: id 2 | task 8917 | graph reallocs = 0 / 0 (same size) / (changed size) 57.20.194.045 I slot release: id 2 | task 8917 | stop processing: n_tokens = 900, truncated = 0 57.20.194.068 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 106513588138 57.20.194.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.651 MiB) 57.22.604.063 I slot launch_slot_: id 3 | task 8922 | processing task, is_child = 0 57.22.604.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.215 MiB) 57.25.451.656 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 106515131669 57.25.451.884 I slot launch_slot_: id 2 | task 8923 | processing task, is_child = 0 57.25.451.909 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 374, progress = 0.42, t = 14.64 s / 25.54 tokens per second 57.35.543.685 I slot print_timing: id 0 | task 8913 | prompt eval time = 28831.90 ms / 902 tokens ( 31.96 ms per token, 31.28 tokens per second) 57.35.543.687 I slot print_timing: id 0 | task 8913 | eval time = 15350.35 ms / 2 tokens (15350.35 ms per token, 0.07 tokens per second) 57.35.543.689 I slot print_timing: id 0 | task 8913 | total time = 44182.25 ms / 904 tokens 57.35.543.690 I slot print_timing: id 0 | task 8913 | graphs reused = 7735 57.35.543.690 I slot print_timing: id 0 | task 8913 | graph reallocs = 0 / 0 (same size) / (changed size) 57.35.545.051 I slot release: id 0 | task 8913 | stop processing: n_tokens = 903, truncated = 0 57.35.545.092 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 779, progress = 0.88, t = 29.99 s / 25.97 tokens per second 57.35.571.837 I slot print_timing: id 2 | task 8923 | prompt processing, n_tokens = 189, progress = 0.15, t = 10.02 s / 18.87 tokens per second 57.35.624.190 I slot print_timing: id 3 | task 8922 | prompt processing, n_tokens = 189, progress = 0.15, t = 10.02 s / 18.87 tokens per second 57.39.844.806 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 106530482674 57.39.844.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.466 MiB) 57.42.638.200 I slot launch_slot_: id 0 | task 8926 | processing task, is_child = 0 57.42.638.322 I slot print_timing: id 1 | task 8918 | prompt processing, n_tokens = 886, progress = 1.00, t = 34.30 s / 25.83 tokens per second 57.42.644.451 I slot print_timing: id 2 | task 8923 | prompt processing, n_tokens = 402, progress = 0.33, t = 14.32 s / 28.08 tokens per second 57.42.644.468 I slot print_timing: id 3 | task 8922 | prompt processing, n_tokens = 402, progress = 0.33, t = 14.32 s / 28.08 tokens per second 57.53.077.816 I slot print_timing: id 0 | task 8926 | prompt processing, n_tokens = 189, progress = 0.15, t = 10.44 s / 18.10 tokens per second 57.53.085.536 I slot print_timing: id 2 | task 8923 | prompt processing, n_tokens = 720, progress = 0.58, t = 27.55 s / 26.13 tokens per second 57.53.094.161 I slot print_timing: id 3 | task 8922 | prompt processing, n_tokens = 709, progress = 0.58, t = 27.55 s / 25.74 tokens per second 58.04.751.715 I slot print_timing: id 1 | task 8918 | prompt eval time = 47529.27 ms / 890 tokens ( 53.40 ms per token, 18.73 tokens per second) 58.04.751.722 I slot print_timing: id 1 | task 8918 | eval time = 11673.92 ms / 2 tokens (11673.92 ms per token, 0.09 tokens per second) 58.04.751.722 I slot print_timing: id 1 | task 8918 | total time = 59203.19 ms / 892 tokens 58.04.751.723 I slot print_timing: id 1 | task 8918 | graphs reused = 7735 58.04.751.724 I slot print_timing: id 1 | task 8918 | graph reallocs = 0 / 0 (same size) / (changed size) 58.04.751.833 I slot release: id 1 | task 8918 | stop processing: n_tokens = 891, truncated = 0 58.04.751.849 I slot print_timing: id 0 | task 8926 | prompt processing, n_tokens = 402, progress = 0.31, t = 22.11 s / 18.18 tokens per second 58.04.751.864 I slot print_timing: id 2 | task 8923 | prompt processing, n_tokens = 1061, progress = 0.86, t = 39.22 s / 27.05 tokens per second 58.04.821.661 I slot print_timing: id 3 | task 8922 | prompt processing, n_tokens = 1061, progress = 0.87, t = 39.22 s / 27.05 tokens per second 58.13.251.769 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 106559689456 58.13.251.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.403 MiB) 58.15.683.196 I slot launch_slot_: id 1 | task 8930 | processing task, is_child = 0 58.15.683.220 I slot print_timing: id 0 | task 8926 | prompt processing, n_tokens = 774, progress = 0.60, t = 30.61 s / 25.28 tokens per second 58.15.714.928 I slot print_timing: id 2 | task 8923 | prompt processing, n_tokens = 1232, progress = 1.00, t = 47.72 s / 25.81 tokens per second 58.15.727.031 I slot print_timing: id 3 | task 8922 | prompt processing, n_tokens = 1221, progress = 1.00, t = 47.72 s / 25.58 tokens per second 58.24.650.791 I slot print_timing: id 0 | task 8926 | prompt processing, n_tokens = 1061, progress = 0.82, t = 42.01 s / 25.25 tokens per second 58.24.665.069 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 402, progress = 0.16, t = 8.94 s / 44.99 tokens per second 58.34.803.400 I slot print_timing: id 2 | task 8923 | prompt eval time = 59122.75 ms / 1236 tokens ( 47.83 ms per token, 20.91 tokens per second) 58.34.803.403 I slot print_timing: id 2 | task 8923 | eval time = 10153.15 ms / 2 tokens (10153.15 ms per token, 0.10 tokens per second) 58.34.803.403 I slot print_timing: id 2 | task 8923 | total time = 69275.91 ms / 1238 tokens 58.34.803.404 I slot print_timing: id 2 | task 8923 | graphs reused = 7735 58.34.803.404 I slot print_timing: id 2 | task 8923 | graph reallocs = 0 / 0 (same size) / (changed size) 58.34.807.745 I slot release: id 2 | task 8923 | stop processing: n_tokens = 1237, truncated = 0 58.34.808.281 I slot print_timing: id 3 | task 8922 | prompt eval time = 59123.17 ms / 1225 tokens ( 48.26 ms per token, 20.72 tokens per second) 58.34.808.286 I slot print_timing: id 3 | task 8922 | eval time = 10157.50 ms / 2 tokens (10157.50 ms per token, 0.10 tokens per second) 58.34.808.288 I slot print_timing: id 3 | task 8922 | total time = 69280.67 ms / 1227 tokens 58.34.808.288 I slot print_timing: id 3 | task 8922 | graphs reused = 7735 58.34.808.289 I slot print_timing: id 3 | task 8922 | graph reallocs = 0 / 0 (same size) / (changed size) 58.34.808.703 I slot release: id 3 | task 8922 | stop processing: n_tokens = 1226, truncated = 0 58.34.808.735 I slot print_timing: id 0 | task 8926 | prompt processing, n_tokens = 1286, progress = 1.00, t = 52.17 s / 24.65 tokens per second 58.34.834.058 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 961, progress = 0.37, t = 19.09 s / 50.34 tokens per second 58.48.452.441 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 106589745369 58.48.452.521 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.778 MiB) 58.50.410.573 I slot launch_slot_: id 2 | task 8934 | processing task, is_child = 0 58.50.410.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 58.52.950.299 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 106589746327 58.52.950.488 I slot launch_slot_: id 3 | task 8935 | processing task, is_child = 0 58.52.950.517 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 2071, progress = 0.80, t = 32.74 s / 63.26 tokens per second 59.06.047.580 I slot print_timing: id 0 | task 8926 | prompt eval time = 65814.20 ms / 1290 tokens ( 51.02 ms per token, 19.60 tokens per second) 59.06.047.583 I slot print_timing: id 0 | task 8926 | eval time = 17595.13 ms / 2 tokens (17595.13 ms per token, 0.06 tokens per second) 59.06.047.584 I slot print_timing: id 0 | task 8926 | total time = 83409.33 ms / 1292 tokens 59.06.047.584 I slot print_timing: id 0 | task 8926 | graphs reused = 7735 59.06.047.585 I slot print_timing: id 0 | task 8926 | graph reallocs = 0 / 0 (same size) / (changed size) 59.06.050.800 I slot release: id 0 | task 8926 | stop processing: n_tokens = 1291, truncated = 0 59.06.050.840 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 2288, progress = 0.88, t = 50.33 s / 45.46 tokens per second 59.06.073.872 I slot print_timing: id 2 | task 8934 | prompt processing, n_tokens = 402, progress = 0.16, t = 13.03 s / 30.84 tokens per second 59.06.080.503 I slot print_timing: id 3 | task 8935 | prompt processing, n_tokens = 402, progress = 0.15, t = 13.03 s / 30.84 tokens per second 59.22.923.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 106620988423 59.22.923.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 59.24.333.762 I slot launch_slot_: id 0 | task 8938 | processing task, is_child = 0 59.24.333.905 I slot print_timing: id 1 | task 8930 | prompt processing, n_tokens = 2583, progress = 1.00, t = 67.21 s / 38.43 tokens per second 59.24.348.621 I slot print_timing: id 2 | task 8934 | prompt processing, n_tokens = 961, progress = 0.38, t = 29.91 s / 32.13 tokens per second 59.24.348.655 I slot print_timing: id 3 | task 8935 | prompt processing, n_tokens = 961, progress = 0.35, t = 29.91 s / 32.13 tokens per second 59.49.610.085 I slot print_timing: id 0 | task 8938 | prompt processing, n_tokens = 402, progress = 0.15, t = 25.28 s / 15.90 tokens per second 59.49.651.347 I slot print_timing: id 2 | task 8934 | prompt processing, n_tokens = 1984, progress = 0.79, t = 56.60 s / 35.06 tokens per second 59.49.658.399 I slot print_timing: id 3 | task 8935 | prompt processing, n_tokens = 1580, progress = 0.58, t = 56.60 s / 27.92 tokens per second 60.08.336.667 I slot print_timing: id 1 | task 8930 | prompt eval time = 93895.23 ms / 2587 tokens ( 36.30 ms per token, 27.55 tokens per second) 60.08.336.670 I slot print_timing: id 1 | task 8930 | eval time = 18726.61 ms / 2 tokens (18726.61 ms per token, 0.05 tokens per second) 60.08.336.671 I slot print_timing: id 1 | task 8930 | total time = 112621.83 ms / 2589 tokens 60.08.336.671 I slot print_timing: id 1 | task 8930 | graphs reused = 7735 60.08.336.672 I slot print_timing: id 1 | task 8930 | graph reallocs = 0 / 0 (same size) / (changed size) 60.08.355.966 I slot release: id 1 | task 8930 | stop processing: n_tokens = 2588, truncated = 0 60.08.356.015 I slot print_timing: id 0 | task 8938 | prompt processing, n_tokens = 961, progress = 0.36, t = 44.00 s / 21.84 tokens per second 60.08.356.055 I slot print_timing: id 2 | task 8934 | prompt processing, n_tokens = 2288, progress = 0.92, t = 75.32 s / 30.38 tokens per second 60.08.419.176 I slot print_timing: id 3 | task 8935 | prompt processing, n_tokens = 2226, progress = 0.81, t = 75.32 s / 29.55 tokens per second 60.24.181.468 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 106683293590 60.24.181.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.153 MiB) 60.24.182.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.778 MiB) 60.26.259.039 I slot launch_slot_: id 1 | task 8942 | processing task, is_child = 0 60.26.259.062 I slot print_timing: id 0 | task 8938 | prompt processing, n_tokens = 2139, progress = 0.81, t = 59.85 s / 35.74 tokens per second 60.26.885.317 I slot print_timing: id 2 | task 8934 | prompt processing, n_tokens = 2496, progress = 1.00, t = 91.17 s / 27.38 tokens per second 60.26.890.296 I slot print_timing: id 3 | task 8935 | prompt processing, n_tokens = 2288, progress = 0.83, t = 91.17 s / 25.10 tokens per second 60.37.423.403 I slot print_timing: id 0 | task 8938 | prompt processing, n_tokens = 2288, progress = 0.86, t = 73.09 s / 31.30 tokens per second 60.37.440.117 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 208, progress = 0.12, t = 10.54 s / 19.74 tokens per second 60.37.772.056 I slot print_timing: id 3 | task 8935 | prompt processing, n_tokens = 2738, progress = 1.00, t = 104.41 s / 26.22 tokens per second 60.46.670.800 I slot print_timing: id 2 | task 8934 | prompt eval time = 104409.58 ms / 2500 tokens ( 41.76 ms per token, 23.94 tokens per second) 60.46.670.803 I slot print_timing: id 2 | task 8934 | eval time = 9247.43 ms / 2 tokens ( 9247.43 ms per token, 0.11 tokens per second) 60.46.670.804 I slot print_timing: id 2 | task 8934 | total time = 113657.01 ms / 2502 tokens 60.46.670.804 I slot print_timing: id 2 | task 8934 | graphs reused = 7735 60.46.670.805 I slot print_timing: id 2 | task 8934 | graph reallocs = 0 / 0 (same size) / (changed size) 60.46.673.749 I slot release: id 2 | task 8934 | stop processing: n_tokens = 2501, truncated = 0 60.46.674.510 I slot print_timing: id 0 | task 8938 | prompt processing, n_tokens = 2651, progress = 1.00, t = 82.34 s / 32.20 tokens per second 60.46.746.350 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 520, progress = 0.29, t = 19.79 s / 26.28 tokens per second 60.56.177.354 I slot print_timing: id 3 | task 8935 | prompt eval time = 113660.55 ms / 2742 tokens ( 41.45 ms per token, 24.12 tokens per second) 60.56.177.357 I slot print_timing: id 3 | task 8935 | eval time = 9502.86 ms / 2 tokens ( 9502.86 ms per token, 0.11 tokens per second) 60.56.177.358 I slot print_timing: id 3 | task 8935 | total time = 123163.41 ms / 2744 tokens 60.56.177.358 I slot print_timing: id 3 | task 8935 | graphs reused = 7735 60.56.177.359 I slot print_timing: id 3 | task 8935 | graph reallocs = 0 / 0 (same size) / (changed size) 60.56.179.921 I slot release: id 3 | task 8935 | stop processing: n_tokens = 2743, truncated = 0 60.56.179.941 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 106721611373 60.56.180.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.278 MiB) 60.57.890.593 I slot launch_slot_: id 2 | task 8946 | processing task, is_child = 0 60.57.890.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.339 MiB) 60.59.846.919 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 106731117545 60.59.847.306 I slot launch_slot_: id 3 | task 8947 | processing task, is_child = 0 60.59.847.342 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 1263, progress = 0.71, t = 29.29 s / 43.12 tokens per second 61.08.548.000 I slot print_timing: id 0 | task 8938 | prompt eval time = 91843.13 ms / 2655 tokens ( 34.59 ms per token, 28.91 tokens per second) 61.08.548.002 I slot print_timing: id 0 | task 8938 | eval time = 12371.08 ms / 2 tokens (12371.08 ms per token, 0.08 tokens per second) 61.08.548.003 I slot print_timing: id 0 | task 8938 | total time = 104214.21 ms / 2657 tokens 61.08.548.003 I slot print_timing: id 0 | task 8938 | graphs reused = 7735 61.08.548.004 I slot print_timing: id 0 | task 8938 | graph reallocs = 0 / 0 (same size) / (changed size) 61.08.549.755 I slot release: id 0 | task 8938 | stop processing: n_tokens = 2656, truncated = 0 61.08.549.802 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 1447, progress = 0.81, t = 41.66 s / 34.73 tokens per second 61.08.565.450 I slot print_timing: id 2 | task 8946 | prompt processing, n_tokens = 208, progress = 0.11, t = 8.16 s / 25.48 tokens per second 61.08.578.116 I slot print_timing: id 3 | task 8947 | prompt processing, n_tokens = 208, progress = 0.10, t = 8.16 s / 25.48 tokens per second 61.20.078.207 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 106743487380 61.20.078.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.402 MiB) 61.21.562.759 I slot launch_slot_: id 0 | task 8950 | processing task, is_child = 0 61.21.562.981 I slot print_timing: id 1 | task 8942 | prompt processing, n_tokens = 1775, progress = 1.00, t = 53.19 s / 33.37 tokens per second 61.21.568.625 I slot print_timing: id 2 | task 8946 | prompt processing, n_tokens = 520, progress = 0.28, t = 19.69 s / 26.41 tokens per second 61.21.568.646 I slot print_timing: id 3 | task 8947 | prompt processing, n_tokens = 520, progress = 0.25, t = 19.69 s / 26.41 tokens per second 61.45.685.449 I slot print_timing: id 0 | task 8950 | prompt processing, n_tokens = 208, progress = 0.11, t = 24.12 s / 8.62 tokens per second 61.45.701.120 I slot print_timing: id 2 | task 8946 | prompt processing, n_tokens = 1325, progress = 0.72, t = 45.30 s / 29.25 tokens per second 61.45.723.971 I slot print_timing: id 3 | task 8947 | prompt processing, n_tokens = 1447, progress = 0.71, t = 45.30 s / 31.94 tokens per second 61.52.846.054 I slot print_timing: id 1 | task 8942 | prompt eval time = 78800.31 ms / 1779 tokens ( 44.29 ms per token, 22.58 tokens per second) 61.52.846.059 I slot print_timing: id 1 | task 8942 | eval time = 7160.62 ms / 2 tokens ( 7160.62 ms per token, 0.14 tokens per second) 61.52.846.060 I slot print_timing: id 1 | task 8942 | total time = 85960.93 ms / 1781 tokens 61.52.846.060 I slot print_timing: id 1 | task 8942 | graphs reused = 7735 61.52.846.066 I slot print_timing: id 1 | task 8942 | graph reallocs = 0 / 0 (same size) / (changed size) 61.52.851.456 I slot release: id 1 | task 8942 | stop processing: n_tokens = 1780, truncated = 0 61.52.851.505 I slot print_timing: id 0 | task 8950 | prompt processing, n_tokens = 520, progress = 0.28, t = 31.28 s / 16.62 tokens per second 61.52.851.535 I slot print_timing: id 2 | task 8946 | prompt processing, n_tokens = 1447, progress = 0.79, t = 52.46 s / 27.58 tokens per second 61.53.342.711 I slot print_timing: id 3 | task 8947 | prompt processing, n_tokens = 1532, progress = 0.75, t = 52.46 s / 29.20 tokens per second 62.12.873.300 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 62.12.873.376 I slot launch_slot_: id 1 | task 8954 | processing task, is_child = 0 62.12.873.390 I slot print_timing: id 0 | task 8950 | prompt processing, n_tokens = 1336, progress = 0.72, t = 51.31 s / 26.04 tokens per second 62.14.468.405 I slot print_timing: id 2 | task 8946 | prompt processing, n_tokens = 1837, progress = 1.00, t = 72.49 s / 25.34 tokens per second 62.14.478.399 I slot print_timing: id 3 | task 8947 | prompt processing, n_tokens = 2044, progress = 1.00, t = 72.49 s / 28.20 tokens per second 62.22.719.492 I slot print_timing: id 0 | task 8950 | prompt processing, n_tokens = 1447, progress = 0.78, t = 61.15 s / 23.66 tokens per second 62.22.759.077 I slot print_timing: id 1 | task 8954 | prompt processing, n_tokens = 511, progress = 1.00, t = 8.26 s / 61.89 tokens per second 62.28.195.279 I slot print_timing: id 2 | task 8946 | prompt eval time = 82332.64 ms / 1841 tokens ( 44.72 ms per token, 22.36 tokens per second) 62.28.195.282 I slot print_timing: id 2 | task 8946 | eval time = 5477.27 ms / 2 tokens ( 5477.27 ms per token, 0.18 tokens per second) 62.28.195.283 I slot print_timing: id 2 | task 8946 | total time = 87809.92 ms / 1843 tokens 62.28.195.284 I slot print_timing: id 2 | task 8946 | graphs reused = 7735 62.28.195.284 I slot print_timing: id 2 | task 8946 | graph reallocs = 0 / 0 (same size) / (changed size) 62.28.197.058 I slot release: id 2 | task 8946 | stop processing: n_tokens = 1842, truncated = 0 62.28.197.999 I slot print_timing: id 3 | task 8947 | prompt eval time = 82333.89 ms / 2048 tokens ( 40.20 ms per token, 24.87 tokens per second) 62.28.198.003 I slot print_timing: id 3 | task 8947 | eval time = 5478.54 ms / 2 tokens ( 5478.54 ms per token, 0.18 tokens per second) 62.28.198.003 I slot print_timing: id 3 | task 8947 | total time = 87812.43 ms / 2050 tokens 62.28.198.003 I slot print_timing: id 3 | task 8947 | graphs reused = 7735 62.28.198.004 I slot print_timing: id 3 | task 8947 | graph reallocs = 0 / 0 (same size) / (changed size) 62.28.201.204 I slot release: id 3 | task 8947 | stop processing: n_tokens = 2049, truncated = 0 62.28.201.223 I slot print_timing: id 0 | task 8950 | prompt processing, n_tokens = 1848, progress = 1.00, t = 66.63 s / 27.73 tokens per second 62.28.560.611 I slot print_timing: id 1 | task 8954 | prompt eval time = 13734.30 ms / 515 tokens ( 26.67 ms per token, 37.50 tokens per second) 62.28.560.623 I slot print_timing: id 1 | task 8954 | eval time = 365.74 ms / 2 tokens ( 365.74 ms per token, 2.73 tokens per second) 62.28.560.625 I slot print_timing: id 1 | task 8954 | total time = 14100.04 ms / 517 tokens 62.28.560.626 I slot print_timing: id 1 | task 8954 | graphs reused = 7735 62.28.560.626 I slot print_timing: id 1 | task 8954 | graph reallocs = 0 / 0 (same size) / (changed size) 62.28.565.260 I slot release: id 1 | task 8954 | stop processing: n_tokens = 1963, truncated = 0 62.28.565.300 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 106823134683 62.28.565.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.589 MiB) 62.30.329.621 I slot launch_slot_: id 2 | task 8958 | processing task, is_child = 0 62.30.329.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.839 MiB) 62.32.331.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 825.472 MiB) 62.34.321.751 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.756 62.34.322.090 I slot launch_slot_: id 1 | task 8959 | processing task, is_child = 0 62.34.322.216 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 106823138827 62.34.322.337 I slot launch_slot_: id 3 | task 8960 | processing task, is_child = 0 62.42.538.665 I slot print_timing: id 0 | task 8950 | prompt eval time = 66997.26 ms / 1852 tokens ( 36.18 ms per token, 27.64 tokens per second) 62.42.538.669 I slot print_timing: id 0 | task 8950 | eval time = 13977.96 ms / 2 tokens (13977.96 ms per token, 0.07 tokens per second) 62.42.538.677 I slot print_timing: id 0 | task 8950 | total time = 80975.21 ms / 1854 tokens 62.42.538.680 I slot print_timing: id 0 | task 8950 | graphs reused = 7735 62.42.538.680 I slot print_timing: id 0 | task 8950 | graph reallocs = 0 / 0 (same size) / (changed size) 62.42.541.442 I slot release: id 0 | task 8950 | stop processing: n_tokens = 1853, truncated = 0 62.42.542.083 I slot print_timing: id 1 | task 8959 | prompt processing, n_tokens = 330, progress = 1.00, t = 8.21 s / 40.18 tokens per second 62.42.559.620 I slot print_timing: id 2 | task 8958 | prompt processing, n_tokens = 130, progress = 0.18, t = 8.13 s / 15.98 tokens per second 62.42.574.331 I slot print_timing: id 3 | task 8960 | prompt processing, n_tokens = 130, progress = 0.17, t = 8.13 s / 15.98 tokens per second 62.45.415.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 106837479066 62.45.415.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 824.784 MiB) 62.46.875.937 I slot launch_slot_: id 0 | task 8963 | processing task, is_child = 0 62.46.876.103 I slot print_timing: id 2 | task 8958 | prompt processing, n_tokens = 210, progress = 0.29, t = 11.01 s / 19.07 tokens per second 62.46.881.212 I slot print_timing: id 3 | task 8960 | prompt processing, n_tokens = 232, progress = 0.31, t = 11.01 s / 21.07 tokens per second 62.58.547.809 I slot print_timing: id 1 | task 8959 | prompt eval time = 11092.70 ms / 334 tokens ( 33.21 ms per token, 30.11 tokens per second) 62.58.547.811 I slot print_timing: id 1 | task 8959 | eval time = 13132.75 ms / 2 tokens (13132.75 ms per token, 0.08 tokens per second) 62.58.547.811 I slot print_timing: id 1 | task 8959 | total time = 24225.45 ms / 336 tokens 62.58.547.812 I slot print_timing: id 1 | task 8959 | graphs reused = 7735 62.58.547.812 I slot print_timing: id 1 | task 8959 | graph reallocs = 0 / 0 (same size) / (changed size) 62.58.548.051 I slot release: id 1 | task 8959 | stop processing: n_tokens = 1782, truncated = 0 62.58.548.066 I slot print_timing: id 0 | task 8963 | prompt processing, n_tokens = 130, progress = 0.17, t = 11.67 s / 11.14 tokens per second 62.58.558.512 I slot print_timing: id 2 | task 8958 | prompt processing, n_tokens = 615, progress = 0.85, t = 24.15 s / 25.47 tokens per second 62.58.574.007 I slot print_timing: id 3 | task 8960 | prompt processing, n_tokens = 615, progress = 0.82, t = 24.15 s / 25.47 tokens per second 63.02.877.151 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 106853485674 63.02.878.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 828.848 MiB) 63.04.897.898 I slot launch_slot_: id 1 | task 8966 | processing task, is_child = 0 63.04.897.917 I slot print_timing: id 0 | task 8963 | prompt processing, n_tokens = 245, progress = 0.32, t = 16.00 s / 15.31 tokens per second 63.05.159.925 I slot print_timing: id 2 | task 8958 | prompt processing, n_tokens = 722, progress = 0.99, t = 28.48 s / 25.36 tokens per second 63.05.169.029 I slot print_timing: id 3 | task 8960 | prompt processing, n_tokens = 744, progress = 0.99, t = 28.48 s / 26.13 tokens per second 63.11.795.020 I slot print_timing: id 0 | task 8963 | prompt processing, n_tokens = 615, progress = 0.81, t = 24.92 s / 24.68 tokens per second 63.11.869.908 I slot print_timing: id 1 | task 8966 | prompt processing, n_tokens = 130, progress = 0.18, t = 6.63 s / 19.60 tokens per second 63.14.921.858 I slot print_timing: id 2 | task 8958 | prompt eval time = 37392.77 ms / 726 tokens ( 51.51 ms per token, 19.42 tokens per second) 63.14.921.863 I slot print_timing: id 2 | task 8958 | eval time = 3127.43 ms / 2 tokens ( 3127.43 ms per token, 0.32 tokens per second) 63.14.921.864 I slot print_timing: id 2 | task 8958 | total time = 40520.20 ms / 728 tokens 63.14.921.864 I slot print_timing: id 2 | task 8958 | graphs reused = 7735 63.14.921.865 I slot print_timing: id 2 | task 8958 | graph reallocs = 0 / 0 (same size) / (changed size) 63.14.921.993 I slot release: id 2 | task 8958 | stop processing: n_tokens = 727, truncated = 0 63.14.922.253 I slot print_timing: id 3 | task 8960 | prompt eval time = 37393.13 ms / 748 tokens ( 49.99 ms per token, 20.00 tokens per second) 63.14.922.257 I slot print_timing: id 3 | task 8960 | eval time = 3127.28 ms / 2 tokens ( 3127.28 ms per token, 0.32 tokens per second) 63.14.922.257 I slot print_timing: id 3 | task 8960 | total time = 40520.41 ms / 750 tokens 63.14.922.258 I slot print_timing: id 3 | task 8960 | graphs reused = 7735 63.14.922.258 I slot print_timing: id 3 | task 8960 | graph reallocs = 0 / 0 (same size) / (changed size) 63.14.922.282 I slot release: id 3 | task 8960 | stop processing: n_tokens = 749, truncated = 0 63.14.922.291 I slot print_timing: id 0 | task 8963 | prompt processing, n_tokens = 757, progress = 0.99, t = 28.05 s / 26.99 tokens per second 63.14.999.424 I slot print_timing: id 1 | task 8966 | prompt processing, n_tokens = 209, progress = 0.29, t = 9.76 s / 21.41 tokens per second 63.20.193.661 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 63.20.193.741 I slot launch_slot_: id 2 | task 8970 | processing task, is_child = 0 63.20.193.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 909.940 MiB) 63.22.235.888 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 106869859904 63.22.236.037 I slot launch_slot_: id 3 | task 8971 | processing task, is_child = 0 63.22.236.057 I slot print_timing: id 1 | task 8966 | prompt processing, n_tokens = 615, progress = 0.85, t = 15.03 s / 40.91 tokens per second 63.27.201.272 I slot print_timing: id 0 | task 8963 | prompt eval time = 33317.70 ms / 761 tokens ( 43.78 ms per token, 22.84 tokens per second) 63.27.201.279 I slot print_timing: id 0 | task 8963 | eval time = 7007.62 ms / 2 tokens ( 7007.62 ms per token, 0.14 tokens per second) 63.27.201.279 I slot print_timing: id 0 | task 8963 | total time = 40325.31 ms / 763 tokens 63.27.201.280 I slot print_timing: id 0 | task 8963 | graphs reused = 7735 63.27.201.280 I slot print_timing: id 0 | task 8963 | graph reallocs = 0 / 0 (same size) / (changed size) 63.27.201.439 I slot release: id 0 | task 8963 | stop processing: n_tokens = 762, truncated = 0 63.27.201.457 I slot print_timing: id 1 | task 8966 | prompt processing, n_tokens = 721, progress = 0.99, t = 22.04 s / 32.71 tokens per second 63.27.244.609 I slot print_timing: id 2 | task 8970 | prompt processing, n_tokens = 120, progress = 0.99, t = 4.94 s / 24.31 tokens per second 63.27.277.534 I slot print_timing: id 3 | task 8971 | prompt processing, n_tokens = 117, progress = 0.15, t = 4.87 s / 24.02 tokens per second 63.29.693.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 106882139062 63.29.693.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 904.501 MiB) 63.30.903.921 I slot launch_slot_: id 0 | task 8974 | processing task, is_child = 0 63.30.904.002 I slot print_timing: id 3 | task 8971 | prompt processing, n_tokens = 257, progress = 0.32, t = 7.36 s / 34.91 tokens per second 63.33.860.243 I slot print_timing: id 1 | task 8966 | prompt eval time = 24533.56 ms / 725 tokens ( 33.84 ms per token, 29.55 tokens per second) 63.33.860.249 I slot print_timing: id 1 | task 8966 | eval time = 4166.96 ms / 2 tokens ( 4166.96 ms per token, 0.24 tokens per second) 63.33.860.250 I slot print_timing: id 1 | task 8966 | total time = 28700.52 ms / 727 tokens 63.33.860.250 I slot print_timing: id 1 | task 8966 | graphs reused = 7735 63.33.860.251 I slot print_timing: id 1 | task 8966 | graph reallocs = 0 / 0 (same size) / (changed size) 63.33.860.339 I slot release: id 1 | task 8966 | stop processing: n_tokens = 726, truncated = 0 63.33.860.578 I slot print_timing: id 2 | task 8970 | prompt eval time = 7429.13 ms / 124 tokens ( 59.91 ms per token, 16.69 tokens per second) 63.33.860.580 I slot print_timing: id 2 | task 8970 | eval time = 4166.95 ms / 2 tokens ( 4166.95 ms per token, 0.24 tokens per second) 63.33.860.580 I slot print_timing: id 2 | task 8970 | total time = 11596.08 ms / 126 tokens 63.33.860.581 I slot print_timing: id 2 | task 8970 | graphs reused = 7735 63.33.860.581 I slot print_timing: id 2 | task 8970 | graph reallocs = 0 / 0 (same size) / (changed size) 63.33.860.658 I slot release: id 2 | task 8970 | stop processing: n_tokens = 740, truncated = 0 63.33.867.775 I slot print_timing: id 3 | task 8971 | prompt processing, n_tokens = 282, progress = 0.35, t = 11.53 s / 24.46 tokens per second 63.36.178.568 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 106888797962 63.36.178.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.631 MiB) 63.40.398.133 I slot launch_slot_: id 1 | task 8977 | processing task, is_child = 0 63.40.398.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 914.192 MiB) 63.42.955.751 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 106888798281 63.42.955.870 I slot launch_slot_: id 2 | task 8978 | processing task, is_child = 0 63.42.955.879 I slot print_timing: id 0 | task 8974 | prompt processing, n_tokens = 352, progress = 0.34, t = 5.27 s / 66.73 tokens per second 63.42.956.006 I slot print_timing: id 3 | task 8971 | prompt processing, n_tokens = 631, progress = 0.79, t = 13.85 s / 45.56 tokens per second 63.51.069.507 I slot print_timing: id 0 | task 8974 | prompt processing, n_tokens = 526, progress = 0.50, t = 20.17 s / 26.08 tokens per second 63.51.266.372 I slot print_timing: id 1 | task 8977 | prompt processing, n_tokens = 155, progress = 0.19, t = 8.11 s / 19.10 tokens per second 63.51.320.411 I slot print_timing: id 2 | task 8978 | prompt processing, n_tokens = 155, progress = 0.19, t = 8.11 s / 19.10 tokens per second 63.51.368.601 I slot print_timing: id 3 | task 8971 | prompt processing, n_tokens = 794, progress = 0.99, t = 28.74 s / 27.63 tokens per second 63.59.412.220 I slot print_timing: id 0 | task 8974 | prompt processing, n_tokens = 893, progress = 0.86, t = 28.51 s / 31.32 tokens per second 63.59.428.290 I slot print_timing: id 1 | task 8977 | prompt processing, n_tokens = 277, progress = 0.34, t = 16.46 s / 16.83 tokens per second 63.59.428.298 I slot print_timing: id 2 | task 8978 | prompt processing, n_tokens = 277, progress = 0.35, t = 16.46 s / 16.83 tokens per second 64.02.388.562 I slot print_timing: id 3 | task 8971 | prompt eval time = 37082.07 ms / 798 tokens ( 46.47 ms per token, 21.52 tokens per second) 64.02.388.567 I slot print_timing: id 3 | task 8971 | eval time = 2976.35 ms / 2 tokens ( 2976.35 ms per token, 0.34 tokens per second) 64.02.388.576 I slot print_timing: id 3 | task 8971 | total time = 40058.43 ms / 800 tokens 64.02.388.577 I slot print_timing: id 3 | task 8971 | graphs reused = 7735 64.02.388.577 I slot print_timing: id 3 | task 8971 | graph reallocs = 0 / 0 (same size) / (changed size) 64.02.391.121 I slot release: id 3 | task 8971 | stop processing: n_tokens = 799, truncated = 0 64.02.391.169 I slot print_timing: id 0 | task 8974 | prompt processing, n_tokens = 1038, progress = 1.00, t = 31.48 s / 32.97 tokens per second 64.02.409.599 I slot print_timing: id 1 | task 8977 | prompt processing, n_tokens = 293, progress = 0.36, t = 19.43 s / 15.08 tokens per second 64.02.423.989 I slot print_timing: id 2 | task 8978 | prompt processing, n_tokens = 283, progress = 0.35, t = 19.43 s / 14.56 tokens per second 64.12.353.654 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 106917328750 64.12.353.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.298 MiB) 64.14.770.642 I slot launch_slot_: id 3 | task 8983 | processing task, is_child = 0 64.14.770.658 I slot print_timing: id 1 | task 8977 | prompt processing, n_tokens = 679, progress = 0.84, t = 29.40 s / 23.10 tokens per second 64.14.796.682 I slot print_timing: id 2 | task 8978 | prompt processing, n_tokens = 679, progress = 0.85, t = 29.40 s / 23.10 tokens per second 64.20.240.716 I slot print_timing: id 0 | task 8974 | prompt eval time = 41449.70 ms / 1042 tokens ( 39.78 ms per token, 25.14 tokens per second) 64.20.240.719 I slot print_timing: id 0 | task 8974 | eval time = 7887.06 ms / 2 tokens ( 7887.06 ms per token, 0.13 tokens per second) 64.20.240.719 I slot print_timing: id 0 | task 8974 | total time = 49336.76 ms / 1044 tokens 64.20.240.720 I slot print_timing: id 0 | task 8974 | graphs reused = 7735 64.20.240.720 I slot print_timing: id 0 | task 8974 | graph reallocs = 0 / 0 (same size) / (changed size) 64.20.244.053 I slot release: id 0 | task 8974 | stop processing: n_tokens = 1043, truncated = 0 64.20.244.103 I slot print_timing: id 1 | task 8977 | prompt processing, n_tokens = 805, progress = 1.00, t = 37.28 s / 21.59 tokens per second 64.20.262.164 I slot print_timing: id 2 | task 8978 | prompt processing, n_tokens = 795, progress = 0.99, t = 37.28 s / 21.32 tokens per second 64.20.276.578 I slot print_timing: id 3 | task 8983 | prompt processing, n_tokens = 138, progress = 0.16, t = 5.40 s / 25.55 tokens per second 64.23.019.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 106935181677 64.23.019.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.863 MiB) 64.25.314.930 I slot launch_slot_: id 0 | task 8986 | processing task, is_child = 0 64.25.315.040 I slot print_timing: id 3 | task 8983 | prompt processing, n_tokens = 319, progress = 0.38, t = 8.18 s / 39.00 tokens per second 64.27.906.848 I slot print_timing: id 1 | task 8977 | prompt eval time = 40063.37 ms / 809 tokens ( 49.52 ms per token, 20.19 tokens per second) 64.27.906.850 I slot print_timing: id 1 | task 8977 | eval time = 4887.58 ms / 2 tokens ( 4887.58 ms per token, 0.20 tokens per second) 64.27.906.851 I slot print_timing: id 1 | task 8977 | total time = 44950.95 ms / 811 tokens 64.27.906.851 I slot print_timing: id 1 | task 8977 | graphs reused = 7735 64.27.906.852 I slot print_timing: id 1 | task 8977 | graph reallocs = 0 / 0 (same size) / (changed size) 64.27.910.646 I slot release: id 1 | task 8977 | stop processing: n_tokens = 810, truncated = 0 64.27.911.887 I slot print_timing: id 2 | task 8978 | prompt eval time = 40063.74 ms / 799 tokens ( 50.14 ms per token, 19.94 tokens per second) 64.27.911.889 I slot print_timing: id 2 | task 8978 | eval time = 4892.19 ms / 2 tokens ( 4892.19 ms per token, 0.20 tokens per second) 64.27.911.890 I slot print_timing: id 2 | task 8978 | total time = 44955.93 ms / 801 tokens 64.27.911.890 I slot print_timing: id 2 | task 8978 | graphs reused = 7735 64.27.911.892 I slot print_timing: id 2 | task 8978 | graph reallocs = 0 / 0 (same size) / (changed size) 64.27.912.264 I slot release: id 2 | task 8978 | stop processing: n_tokens = 800, truncated = 0 64.27.930.007 I slot print_timing: id 3 | task 8983 | prompt processing, n_tokens = 329, progress = 0.39, t = 13.07 s / 25.18 tokens per second 64.30.263.384 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 106942848270 64.35.185.350 I slot launch_slot_: id 1 | task 8989 | processing task, is_child = 0 64.35.185.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 876.240 MiB) 64.36.875.450 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 106942849890 64.36.875.601 I slot launch_slot_: id 2 | task 8990 | processing task, is_child = 0 64.36.875.667 I slot print_timing: id 0 | task 8986 | prompt processing, n_tokens = 319, progress = 0.38, t = 4.95 s / 64.46 tokens per second 64.36.875.880 I slot print_timing: id 3 | task 8983 | prompt processing, n_tokens = 723, progress = 0.86, t = 15.42 s / 46.88 tokens per second 64.41.593.255 I slot print_timing: id 0 | task 8986 | prompt processing, n_tokens = 323, progress = 0.38, t = 16.28 s / 19.84 tokens per second 64.42.395.612 I slot print_timing: id 1 | task 8989 | prompt processing, n_tokens = 138, progress = 0.15, t = 4.72 s / 29.25 tokens per second 64.42.454.927 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 138, progress = 0.15, t = 4.72 s / 29.25 tokens per second 64.42.518.780 I slot print_timing: id 3 | task 8983 | prompt processing, n_tokens = 841, progress = 1.00, t = 26.75 s / 31.43 tokens per second 64.52.268.846 I slot print_timing: id 0 | task 8986 | prompt processing, n_tokens = 723, progress = 0.86, t = 26.95 s / 26.82 tokens per second 64.52.283.984 I slot print_timing: id 1 | task 8989 | prompt processing, n_tokens = 319, progress = 0.35, t = 15.39 s / 20.72 tokens per second 64.52.283.995 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 319, progress = 0.35, t = 15.39 s / 20.72 tokens per second 64.56.379.301 I slot print_timing: id 3 | task 8983 | prompt eval time = 37429.23 ms / 845 tokens ( 44.29 ms per token, 22.58 tokens per second) 64.56.379.303 I slot print_timing: id 3 | task 8983 | eval time = 4110.47 ms / 2 tokens ( 4110.47 ms per token, 0.24 tokens per second) 64.56.379.304 I slot print_timing: id 3 | task 8983 | total time = 41539.70 ms / 847 tokens 64.56.379.305 I slot print_timing: id 3 | task 8983 | graphs reused = 7735 64.56.379.305 I slot print_timing: id 3 | task 8983 | graph reallocs = 0 / 0 (same size) / (changed size) 64.56.382.510 I slot release: id 3 | task 8983 | stop processing: n_tokens = 846, truncated = 0 64.56.382.966 I slot print_timing: id 0 | task 8986 | prompt processing, n_tokens = 835, progress = 1.00, t = 31.06 s / 26.88 tokens per second 64.56.409.970 I slot print_timing: id 1 | task 8989 | prompt processing, n_tokens = 394, progress = 0.43, t = 19.50 s / 20.20 tokens per second 64.56.435.267 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 385, progress = 0.43, t = 19.50 s / 19.74 tokens per second 65.05.356.862 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 65.05.356.929 I slot launch_slot_: id 3 | task 8995 | processing task, is_child = 0 65.05.356.937 I slot print_timing: id 1 | task 8989 | prompt processing, n_tokens = 723, progress = 0.79, t = 28.48 s / 25.39 tokens per second 65.05.410.498 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 723, progress = 0.80, t = 28.48 s / 25.39 tokens per second 65.12.283.523 I slot print_timing: id 0 | task 8986 | prompt eval time = 40041.90 ms / 839 tokens ( 47.73 ms per token, 20.95 tokens per second) 65.12.283.529 I slot print_timing: id 0 | task 8986 | eval time = 6926.66 ms / 2 tokens ( 6926.66 ms per token, 0.14 tokens per second) 65.12.283.530 I slot print_timing: id 0 | task 8986 | total time = 46968.56 ms / 841 tokens 65.12.283.530 I slot print_timing: id 0 | task 8986 | graphs reused = 7735 65.12.283.531 I slot print_timing: id 0 | task 8986 | graph reallocs = 0 / 0 (same size) / (changed size) 65.12.284.902 I slot release: id 0 | task 8986 | stop processing: n_tokens = 840, truncated = 0 65.12.284.928 I slot print_timing: id 1 | task 8989 | prompt processing, n_tokens = 906, progress = 1.00, t = 35.41 s / 25.59 tokens per second 65.12.298.217 I slot print_timing: id 2 | task 8990 | prompt processing, n_tokens = 897, progress = 1.00, t = 35.41 s / 25.33 tokens per second 65.12.324.181 I slot print_timing: id 3 | task 8995 | prompt processing, n_tokens = 135, progress = 1.00, t = 6.83 s / 19.75 tokens per second 65.12.816.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 106987222526 65.12.816.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 863.986 MiB) 65.15.016.965 I slot launch_slot_: id 0 | task 8998 | processing task, is_child = 0 65.16.933.636 I slot print_timing: id 1 | task 8989 | prompt eval time = 35939.14 ms / 910 tokens ( 39.49 ms per token, 25.32 tokens per second) 65.16.933.639 I slot print_timing: id 1 | task 8989 | eval time = 4118.80 ms / 2 tokens ( 4118.80 ms per token, 0.24 tokens per second) 65.16.933.639 I slot print_timing: id 1 | task 8989 | total time = 40057.95 ms / 912 tokens 65.16.933.640 I slot print_timing: id 1 | task 8989 | graphs reused = 7735 65.16.933.640 I slot print_timing: id 1 | task 8989 | graph reallocs = 0 / 0 (same size) / (changed size) 65.16.935.374 I slot release: id 1 | task 8989 | stop processing: n_tokens = 911, truncated = 0 65.16.936.623 I slot print_timing: id 2 | task 8990 | prompt eval time = 35939.90 ms / 901 tokens ( 39.89 ms per token, 25.07 tokens per second) 65.16.936.626 I slot print_timing: id 2 | task 8990 | eval time = 4120.89 ms / 2 tokens ( 4120.89 ms per token, 0.24 tokens per second) 65.16.936.626 I slot print_timing: id 2 | task 8990 | total time = 40060.79 ms / 903 tokens 65.16.936.627 I slot print_timing: id 2 | task 8990 | graphs reused = 7735 65.16.936.627 I slot print_timing: id 2 | task 8990 | graph reallocs = 0 / 0 (same size) / (changed size) 65.16.937.065 I slot release: id 2 | task 8990 | stop processing: n_tokens = 902, truncated = 0 65.16.938.253 I slot print_timing: id 3 | task 8995 | prompt eval time = 7368.30 ms / 139 tokens ( 53.01 ms per token, 18.86 tokens per second) 65.16.938.255 I slot print_timing: id 3 | task 8995 | eval time = 4121.80 ms / 2 tokens ( 4121.80 ms per token, 0.24 tokens per second) 65.16.938.256 I slot print_timing: id 3 | task 8995 | total time = 11490.10 ms / 141 tokens 65.16.938.256 I slot print_timing: id 3 | task 8995 | graphs reused = 7735 65.16.938.257 I slot print_timing: id 3 | task 8995 | graph reallocs = 0 / 0 (same size) / (changed size) 65.16.938.899 I slot release: id 3 | task 8995 | stop processing: n_tokens = 863, truncated = 0 65.17.001.525 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 106991872998 65.17.001.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 859.547 MiB) 65.19.112.127 I slot launch_slot_: id 1 | task 9001 | processing task, is_child = 0 65.19.112.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.961 MiB) 65.21.350.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.773 MiB) 65.23.394.863 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 106991874689 65.23.395.013 I slot launch_slot_: id 2 | task 9002 | processing task, is_child = 0 65.23.395.060 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 106991876522 65.23.395.125 I slot launch_slot_: id 3 | task 9003 | processing task, is_child = 0 65.29.540.857 I slot print_timing: id 0 | task 8998 | prompt processing, n_tokens = 583, progress = 0.85, t = 14.52 s / 40.14 tokens per second 65.33.312.859 I slot print_timing: id 1 | task 9001 | prompt processing, n_tokens = 122, progress = 0.16, t = 6.09 s / 20.05 tokens per second 65.33.423.981 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 119, progress = 0.14, t = 6.09 s / 19.56 tokens per second 65.33.486.714 I slot print_timing: id 3 | task 9003 | prompt processing, n_tokens = 119, progress = 0.14, t = 6.09 s / 19.56 tokens per second 65.39.747.328 I slot print_timing: id 0 | task 8998 | prompt processing, n_tokens = 684, progress = 0.99, t = 24.73 s / 27.66 tokens per second 65.39.938.148 I slot print_timing: id 1 | task 9001 | prompt processing, n_tokens = 253, progress = 0.33, t = 16.29 s / 15.53 tokens per second 65.39.948.963 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 246, progress = 0.30, t = 16.29 s / 15.10 tokens per second 65.39.948.972 I slot print_timing: id 3 | task 9003 | prompt processing, n_tokens = 246, progress = 0.29, t = 16.29 s / 15.10 tokens per second 65.46.952.668 I slot print_timing: id 1 | task 9001 | prompt processing, n_tokens = 632, progress = 0.82, t = 23.50 s / 26.90 tokens per second 65.46.964.300 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 309, progress = 0.37, t = 23.50 s / 13.15 tokens per second 65.47.014.945 I slot print_timing: id 3 | task 9003 | prompt processing, n_tokens = 335, progress = 0.39, t = 23.50 s / 14.26 tokens per second 65.58.356.331 I slot print_timing: id 0 | task 8998 | prompt eval time = 31935.67 ms / 688 tokens ( 46.42 ms per token, 21.54 tokens per second) 65.58.356.334 I slot print_timing: id 0 | task 8998 | eval time = 11403.67 ms / 2 tokens (11403.67 ms per token, 0.09 tokens per second) 65.58.356.334 I slot print_timing: id 0 | task 8998 | total time = 43339.34 ms / 690 tokens 65.58.356.335 I slot print_timing: id 0 | task 8998 | graphs reused = 7735 65.58.356.335 I slot print_timing: id 0 | task 8998 | graph reallocs = 0 / 0 (same size) / (changed size) 65.58.360.209 I slot release: id 0 | task 8998 | stop processing: n_tokens = 689, truncated = 0 65.58.360.248 I slot print_timing: id 1 | task 9001 | prompt processing, n_tokens = 765, progress = 0.99, t = 34.90 s / 21.92 tokens per second 65.58.378.973 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 708, progress = 0.86, t = 34.90 s / 20.29 tokens per second 65.58.394.316 I slot print_timing: id 3 | task 9003 | prompt processing, n_tokens = 708, progress = 0.83, t = 34.90 s / 20.29 tokens per second 66.02.016.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 107033297833 66.02.016.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.523 MiB) 66.03.993.049 I slot launch_slot_: id 0 | task 9009 | processing task, is_child = 0 66.03.993.129 I slot print_timing: id 2 | task 9002 | prompt processing, n_tokens = 821, progress = 1.00, t = 38.56 s / 21.29 tokens per second 66.03.999.335 I slot print_timing: id 3 | task 9003 | prompt processing, n_tokens = 847, progress = 1.00, t = 38.56 s / 21.97 tokens per second 66.06.103.309 I slot print_timing: id 1 | task 9001 | prompt eval time = 38560.75 ms / 769 tokens ( 50.14 ms per token, 19.94 tokens per second) 66.06.103.311 I slot print_timing: id 1 | task 9001 | eval time = 4087.02 ms / 2 tokens ( 4087.02 ms per token, 0.24 tokens per second) 66.06.103.313 I slot print_timing: id 1 | task 9001 | total time = 42647.78 ms / 771 tokens 66.06.103.313 I slot print_timing: id 1 | task 9001 | graphs reused = 7735 66.06.103.314 I slot print_timing: id 1 | task 9001 | graph reallocs = 0 / 0 (same size) / (changed size) 66.06.108.612 I slot release: id 1 | task 9001 | stop processing: n_tokens = 770, truncated = 0 66.07.880.499 I slot print_timing: id 2 | task 9002 | prompt eval time = 42654.05 ms / 825 tokens ( 51.70 ms per token, 19.34 tokens per second) 66.07.880.503 I slot print_timing: id 2 | task 9002 | eval time = 1770.83 ms / 2 tokens ( 1770.83 ms per token, 0.56 tokens per second) 66.07.880.503 I slot print_timing: id 2 | task 9002 | total time = 44424.88 ms / 827 tokens 66.07.880.504 I slot print_timing: id 2 | task 9002 | graphs reused = 7735 66.07.880.504 I slot print_timing: id 2 | task 9002 | graph reallocs = 0 / 0 (same size) / (changed size) 66.07.882.944 I slot release: id 2 | task 9002 | stop processing: n_tokens = 826, truncated = 0 66.07.883.369 I slot print_timing: id 3 | task 9003 | prompt eval time = 42654.74 ms / 851 tokens ( 50.12 ms per token, 19.95 tokens per second) 66.07.883.372 I slot print_timing: id 3 | task 9003 | eval time = 1772.94 ms / 2 tokens ( 1772.94 ms per token, 0.56 tokens per second) 66.07.883.372 I slot print_timing: id 3 | task 9003 | total time = 44427.68 ms / 853 tokens 66.07.883.372 I slot print_timing: id 3 | task 9003 | graphs reused = 7735 66.07.883.373 I slot print_timing: id 3 | task 9003 | graph reallocs = 0 / 0 (same size) / (changed size) 66.07.884.231 I slot release: id 3 | task 9003 | stop processing: n_tokens = 852, truncated = 0 66.07.884.242 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 107041046236 66.07.884.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 66.10.685.746 I slot launch_slot_: id 1 | task 9012 | processing task, is_child = 0 66.10.685.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.087 MiB) 66.13.054.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.342 MiB) 66.15.471.782 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 107042820568 66.15.471.941 I slot launch_slot_: id 2 | task 9013 | processing task, is_child = 0 66.15.471.999 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 107042821854 66.15.472.076 I slot launch_slot_: id 3 | task 9014 | processing task, is_child = 0 66.15.472.082 I slot print_timing: id 0 | task 9009 | prompt processing, n_tokens = 236, progress = 0.31, t = 3.89 s / 60.71 tokens per second 66.21.011.927 I slot print_timing: id 0 | task 9009 | prompt processing, n_tokens = 632, progress = 0.84, t = 17.02 s / 37.14 tokens per second 66.24.787.578 I slot print_timing: id 1 | task 9012 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.49 s / 19.13 tokens per second 66.24.936.919 I slot print_timing: id 2 | task 9013 | prompt processing, n_tokens = 105, progress = 0.15, t = 5.49 s / 19.13 tokens per second 66.24.986.658 I slot print_timing: id 3 | task 9014 | prompt processing, n_tokens = 105, progress = 0.14, t = 5.49 s / 19.13 tokens per second 66.30.431.771 I slot print_timing: id 0 | task 9009 | prompt processing, n_tokens = 748, progress = 0.99, t = 26.44 s / 28.29 tokens per second 66.30.880.472 I slot print_timing: id 1 | task 9012 | prompt processing, n_tokens = 197, progress = 0.28, t = 14.91 s / 13.21 tokens per second 66.30.929.857 I slot print_timing: id 2 | task 9013 | prompt processing, n_tokens = 203, progress = 0.28, t = 14.91 s / 13.62 tokens per second 66.30.943.738 I slot print_timing: id 3 | task 9014 | prompt processing, n_tokens = 220, progress = 0.30, t = 14.91 s / 14.76 tokens per second 66.46.244.001 I slot print_timing: id 1 | task 9012 | prompt processing, n_tokens = 603, progress = 0.85, t = 30.72 s / 19.63 tokens per second 66.46.260.552 I slot print_timing: id 2 | task 9013 | prompt processing, n_tokens = 603, progress = 0.84, t = 30.72 s / 19.63 tokens per second 66.46.275.552 I slot print_timing: id 3 | task 9014 | prompt processing, n_tokens = 603, progress = 0.82, t = 30.72 s / 19.63 tokens per second 66.51.225.881 I slot print_timing: id 0 | task 9009 | prompt eval time = 42250.91 ms / 752 tokens ( 56.18 ms per token, 17.80 tokens per second) 66.51.225.887 I slot print_timing: id 0 | task 9009 | eval time = 4981.90 ms / 2 tokens ( 4981.90 ms per token, 0.20 tokens per second) 66.51.225.887 I slot print_timing: id 0 | task 9009 | total time = 47232.81 ms / 754 tokens 66.51.225.888 I slot print_timing: id 0 | task 9009 | graphs reused = 7735 66.51.225.888 I slot print_timing: id 0 | task 9009 | graph reallocs = 0 / 0 (same size) / (changed size) 66.51.227.633 I slot release: id 0 | task 9009 | stop processing: n_tokens = 753, truncated = 0 66.51.227.661 I slot print_timing: id 1 | task 9012 | prompt processing, n_tokens = 709, progress = 0.99, t = 35.70 s / 19.86 tokens per second 66.51.244.194 I slot print_timing: id 2 | task 9013 | prompt processing, n_tokens = 715, progress = 0.99, t = 35.70 s / 20.03 tokens per second 66.51.258.669 I slot print_timing: id 3 | task 9014 | prompt processing, n_tokens = 732, progress = 0.99, t = 35.70 s / 20.50 tokens per second 66.51.717.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 107086165257 66.51.717.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.775 MiB) 66.53.655.247 I slot launch_slot_: id 0 | task 9020 | processing task, is_child = 0 66.55.479.356 I slot print_timing: id 1 | task 9012 | prompt eval time = 36192.38 ms / 713 tokens ( 50.76 ms per token, 19.70 tokens per second) 66.55.479.359 I slot print_timing: id 1 | task 9012 | eval time = 3762.70 ms / 2 tokens ( 3762.70 ms per token, 0.27 tokens per second) 66.55.479.360 I slot print_timing: id 1 | task 9012 | total time = 39955.09 ms / 715 tokens 66.55.479.360 I slot print_timing: id 1 | task 9012 | graphs reused = 7735 66.55.479.361 I slot print_timing: id 1 | task 9012 | graph reallocs = 0 / 0 (same size) / (changed size) 66.55.483.130 I slot release: id 1 | task 9012 | stop processing: n_tokens = 714, truncated = 0 66.55.484.630 I slot print_timing: id 2 | task 9013 | prompt eval time = 36192.64 ms / 719 tokens ( 50.34 ms per token, 19.87 tokens per second) 66.55.484.634 I slot print_timing: id 2 | task 9013 | eval time = 3767.29 ms / 2 tokens ( 3767.29 ms per token, 0.27 tokens per second) 66.55.484.637 I slot print_timing: id 2 | task 9013 | total time = 39959.93 ms / 721 tokens 66.55.484.637 I slot print_timing: id 2 | task 9013 | graphs reused = 7735 66.55.484.638 I slot print_timing: id 2 | task 9013 | graph reallocs = 0 / 0 (same size) / (changed size) 66.55.484.675 I slot release: id 2 | task 9013 | stop processing: n_tokens = 720, truncated = 0 66.55.485.901 I slot print_timing: id 3 | task 9014 | prompt eval time = 36193.08 ms / 736 tokens ( 49.18 ms per token, 20.34 tokens per second) 66.55.485.903 I slot print_timing: id 3 | task 9014 | eval time = 3768.42 ms / 2 tokens ( 3768.42 ms per token, 0.27 tokens per second) 66.55.485.904 I slot print_timing: id 3 | task 9014 | total time = 39961.50 ms / 738 tokens 66.55.485.904 I slot print_timing: id 3 | task 9014 | graphs reused = 7735 66.55.485.904 I slot print_timing: id 3 | task 9014 | graph reallocs = 0 / 0 (same size) / (changed size) 66.55.486.599 I slot release: id 3 | task 9014 | stop processing: n_tokens = 737, truncated = 0 66.56.701.435 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.884 66.56.701.494 I slot launch_slot_: id 1 | task 9024 | processing task, is_child = 0 66.56.701.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.149 MiB) 67.01.651.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 800.650 MiB) 67.04.094.807 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.876 67.04.094.890 I slot launch_slot_: id 2 | task 9025 | processing task, is_child = 0 67.04.094.939 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 67.04.094.960 I slot launch_slot_: id 3 | task 9026 | processing task, is_child = 0 67.04.094.976 I slot print_timing: id 0 | task 9020 | prompt processing, n_tokens = 603, progress = 0.85, t = 3.05 s / 197.95 tokens per second 67.09.836.349 I slot print_timing: id 0 | task 9020 | prompt processing, n_tokens = 706, progress = 0.99, t = 16.18 s / 43.63 tokens per second 67.10.034.818 I slot print_timing: id 1 | task 9024 | prompt processing, n_tokens = 100, progress = 0.99, t = 5.69 s / 17.56 tokens per second 67.10.137.131 I slot print_timing: id 2 | task 9025 | prompt processing, n_tokens = 102, progress = 0.99, t = 5.66 s / 18.02 tokens per second 67.10.161.754 I slot print_timing: id 3 | task 9026 | prompt processing, n_tokens = 108, progress = 0.99, t = 5.60 s / 19.28 tokens per second 67.10.901.576 I slot print_timing: id 0 | task 9020 | prompt eval time = 17013.76 ms / 710 tokens ( 23.96 ms per token, 41.73 tokens per second) 67.10.901.583 I slot print_timing: id 0 | task 9020 | eval time = 232.54 ms / 2 tokens ( 232.54 ms per token, 4.30 tokens per second) 67.10.901.584 I slot print_timing: id 0 | task 9020 | total time = 17246.31 ms / 712 tokens 67.10.901.584 I slot print_timing: id 0 | task 9020 | graphs reused = 7735 67.10.901.585 I slot print_timing: id 0 | task 9020 | graph reallocs = 0 / 0 (same size) / (changed size) 67.10.902.816 I slot release: id 0 | task 9020 | stop processing: n_tokens = 711, truncated = 0 67.10.903.137 I slot print_timing: id 1 | task 9024 | prompt eval time = 6528.47 ms / 104 tokens ( 62.77 ms per token, 15.93 tokens per second) 67.10.903.144 I slot print_timing: id 1 | task 9024 | eval time = 233.32 ms / 2 tokens ( 233.32 ms per token, 4.29 tokens per second) 67.10.903.145 I slot print_timing: id 1 | task 9024 | total time = 6761.78 ms / 106 tokens 67.10.903.145 I slot print_timing: id 1 | task 9024 | graphs reused = 7735 67.10.903.146 I slot print_timing: id 1 | task 9024 | graph reallocs = 0 / 0 (same size) / (changed size) 67.10.903.557 I slot release: id 1 | task 9024 | stop processing: n_tokens = 708, truncated = 0 67.10.904.194 I slot print_timing: id 2 | task 9025 | prompt eval time = 6496.00 ms / 106 tokens ( 61.28 ms per token, 16.32 tokens per second) 67.10.904.198 I slot print_timing: id 2 | task 9025 | eval time = 233.29 ms / 2 tokens ( 233.29 ms per token, 4.29 tokens per second) 67.10.904.199 I slot print_timing: id 2 | task 9025 | total time = 6729.29 ms / 108 tokens 67.10.904.199 I slot print_timing: id 2 | task 9025 | graphs reused = 7735 67.10.904.199 I slot print_timing: id 2 | task 9025 | graph reallocs = 0 / 0 (same size) / (changed size) 67.10.905.079 I slot release: id 2 | task 9025 | stop processing: n_tokens = 710, truncated = 0 67.10.905.389 I slot print_timing: id 3 | task 9026 | prompt eval time = 6435.99 ms / 112 tokens ( 57.46 ms per token, 17.40 tokens per second) 67.10.905.392 I slot print_timing: id 3 | task 9026 | eval time = 233.59 ms / 2 tokens ( 233.59 ms per token, 4.28 tokens per second) 67.10.905.392 I slot print_timing: id 3 | task 9026 | total time = 6669.58 ms / 114 tokens 67.10.905.393 I slot print_timing: id 3 | task 9026 | graphs reused = 7735 67.10.905.393 I slot print_timing: id 3 | task 9026 | graph reallocs = 0 / 0 (same size) / (changed size) 67.10.905.440 I slot release: id 3 | task 9026 | stop processing: n_tokens = 716, truncated = 0 67.10.925.567 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.887 67.10.925.593 I slot launch_slot_: id 0 | task 9030 | processing task, is_child = 0 67.10.925.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 805.089 MiB) 67.13.045.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.527 MiB) 67.15.091.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 802.088 MiB) 67.17.470.301 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 67.17.470.392 I slot launch_slot_: id 1 | task 9031 | processing task, is_child = 0 67.17.470.486 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.889 67.17.470.513 I slot launch_slot_: id 2 | task 9032 | processing task, is_child = 0 67.17.470.551 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.881 67.17.470.569 I slot launch_slot_: id 3 | task 9033 | processing task, is_child = 0 67.23.510.084 I slot print_timing: id 0 | task 9030 | prompt processing, n_tokens = 102, progress = 0.99, t = 6.04 s / 16.89 tokens per second 67.24.305.778 I slot print_timing: id 1 | task 9031 | prompt processing, n_tokens = 109, progress = 0.99, t = 6.00 s / 18.18 tokens per second 67.24.346.284 I slot print_timing: id 2 | task 9032 | prompt processing, n_tokens = 144, progress = 0.99, t = 5.94 s / 24.24 tokens per second 67.24.363.933 I slot print_timing: id 3 | task 9033 | prompt processing, n_tokens = 110, progress = 0.99, t = 5.89 s / 18.67 tokens per second 67.25.082.708 I slot print_timing: id 0 | task 9030 | prompt eval time = 7379.80 ms / 106 tokens ( 69.62 ms per token, 14.36 tokens per second) 67.25.082.710 I slot print_timing: id 0 | task 9030 | eval time = 232.32 ms / 2 tokens ( 232.32 ms per token, 4.30 tokens per second) 67.25.082.711 I slot print_timing: id 0 | task 9030 | total time = 7612.12 ms / 108 tokens 67.25.082.712 I slot print_timing: id 0 | task 9030 | graphs reused = 7735 67.25.082.712 I slot print_timing: id 0 | task 9030 | graph reallocs = 0 / 0 (same size) / (changed size) 67.25.084.868 I slot release: id 0 | task 9030 | stop processing: n_tokens = 710, truncated = 0 67.25.085.240 I slot print_timing: id 1 | task 9031 | prompt eval time = 7335.77 ms / 113 tokens ( 64.92 ms per token, 15.40 tokens per second) 67.25.085.244 I slot print_timing: id 1 | task 9031 | eval time = 234.58 ms / 2 tokens ( 234.58 ms per token, 4.26 tokens per second) 67.25.085.245 I slot print_timing: id 1 | task 9031 | total time = 7570.35 ms / 115 tokens 67.25.085.245 I slot print_timing: id 1 | task 9031 | graphs reused = 7735 67.25.085.246 I slot print_timing: id 1 | task 9031 | graph reallocs = 0 / 0 (same size) / (changed size) 67.25.087.187 I slot release: id 1 | task 9031 | stop processing: n_tokens = 717, truncated = 0 67.25.087.621 I slot print_timing: id 2 | task 9032 | prompt eval time = 7282.74 ms / 148 tokens ( 49.21 ms per token, 20.32 tokens per second) 67.25.087.625 I slot print_timing: id 2 | task 9032 | eval time = 235.97 ms / 2 tokens ( 235.97 ms per token, 4.24 tokens per second) 67.25.087.625 I slot print_timing: id 2 | task 9032 | total time = 7518.71 ms / 150 tokens 67.25.087.626 I slot print_timing: id 2 | task 9032 | graphs reused = 7735 67.25.087.626 I slot print_timing: id 2 | task 9032 | graph reallocs = 0 / 0 (same size) / (changed size) 67.25.088.419 I slot release: id 2 | task 9032 | stop processing: n_tokens = 752, truncated = 0 67.25.088.741 I slot print_timing: id 3 | task 9033 | prompt eval time = 7233.52 ms / 114 tokens ( 63.45 ms per token, 15.76 tokens per second) 67.25.088.744 I slot print_timing: id 3 | task 9033 | eval time = 236.07 ms / 2 tokens ( 236.07 ms per token, 4.24 tokens per second) 67.25.088.745 I slot print_timing: id 3 | task 9033 | total time = 7469.59 ms / 116 tokens 67.25.088.745 I slot print_timing: id 3 | task 9033 | graphs reused = 7735 67.25.088.745 I slot print_timing: id 3 | task 9033 | graph reallocs = 0 / 0 (same size) / (changed size) 67.25.090.772 I slot release: id 3 | task 9033 | stop processing: n_tokens = 718, truncated = 0 67.25.114.738 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 107120022492 67.25.114.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 791.209 MiB) 67.27.190.749 I slot launch_slot_: id 0 | task 9037 | processing task, is_child = 0 67.27.190.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 796.274 MiB) 67.29.893.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 67.32.287.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 801.401 MiB) 67.34.786.296 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 107120024812 67.34.786.425 I slot launch_slot_: id 1 | task 9038 | processing task, is_child = 0 67.34.786.508 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 107120026044 67.34.786.569 I slot launch_slot_: id 2 | task 9039 | processing task, is_child = 0 67.34.786.608 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 107120028396 67.34.786.667 I slot launch_slot_: id 3 | task 9040 | processing task, is_child = 0 67.43.745.497 I slot print_timing: id 0 | task 9037 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.96 s / 20.43 tokens per second 67.43.955.413 I slot print_timing: id 1 | task 9038 | prompt processing, n_tokens = 183, progress = 0.17, t = 8.96 s / 20.43 tokens per second 67.43.968.630 I slot print_timing: id 2 | task 9039 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.95 s / 20.11 tokens per second 67.43.982.597 I slot print_timing: id 3 | task 9040 | prompt processing, n_tokens = 180, progress = 0.20, t = 8.95 s / 20.11 tokens per second 67.49.694.822 I slot print_timing: id 0 | task 9037 | prompt processing, n_tokens = 364, progress = 0.34, t = 14.91 s / 24.42 tokens per second 67.49.694.836 I slot print_timing: id 1 | task 9038 | prompt processing, n_tokens = 364, progress = 0.33, t = 14.91 s / 24.42 tokens per second 67.49.694.845 I slot print_timing: id 2 | task 9039 | prompt processing, n_tokens = 296, progress = 0.34, t = 14.90 s / 19.86 tokens per second 67.49.694.850 I slot print_timing: id 3 | task 9040 | prompt processing, n_tokens = 296, progress = 0.33, t = 14.90 s / 19.86 tokens per second 67.58.949.158 I slot print_timing: id 0 | task 9037 | prompt processing, n_tokens = 566, progress = 0.52, t = 24.16 s / 23.42 tokens per second 67.59.364.757 I slot print_timing: id 1 | task 9038 | prompt processing, n_tokens = 575, progress = 0.53, t = 24.16 s / 23.80 tokens per second 67.59.378.577 I slot print_timing: id 2 | task 9039 | prompt processing, n_tokens = 364, progress = 0.41, t = 24.16 s / 15.07 tokens per second 67.59.393.414 I slot print_timing: id 3 | task 9040 | prompt processing, n_tokens = 380, progress = 0.42, t = 24.16 s / 15.73 tokens per second 68.17.307.710 I slot print_timing: id 0 | task 9037 | prompt processing, n_tokens = 905, progress = 0.84, t = 42.52 s / 21.28 tokens per second 68.17.725.440 I slot print_timing: id 1 | task 9038 | prompt processing, n_tokens = 905, progress = 0.83, t = 42.52 s / 21.28 tokens per second 68.17.739.654 I slot print_timing: id 2 | task 9039 | prompt processing, n_tokens = 762, progress = 0.87, t = 42.51 s / 17.92 tokens per second 68.17.754.226 I slot print_timing: id 3 | task 9040 | prompt processing, n_tokens = 762, progress = 0.85, t = 42.51 s / 17.92 tokens per second 68.25.457.017 I slot print_timing: id 0 | task 9037 | prompt processing, n_tokens = 1078, progress = 1.00, t = 50.67 s / 21.27 tokens per second 68.25.879.718 I slot print_timing: id 1 | task 9038 | prompt processing, n_tokens = 1087, progress = 1.00, t = 50.67 s / 21.45 tokens per second 68.25.918.854 I slot print_timing: id 2 | task 9039 | prompt processing, n_tokens = 876, progress = 1.00, t = 50.66 s / 17.29 tokens per second 68.25.955.085 I slot print_timing: id 3 | task 9040 | prompt processing, n_tokens = 892, progress = 1.00, t = 50.66 s / 17.61 tokens per second 68.26.854.655 I slot print_timing: id 0 | task 9037 | prompt eval time = 51835.35 ms / 1082 tokens ( 47.91 ms per token, 20.87 tokens per second) 68.26.854.658 I slot print_timing: id 0 | task 9037 | eval time = 232.63 ms / 2 tokens ( 232.63 ms per token, 4.30 tokens per second) 68.26.854.659 I slot print_timing: id 0 | task 9037 | total time = 52067.97 ms / 1084 tokens 68.26.854.660 I slot print_timing: id 0 | task 9037 | graphs reused = 7735 68.26.854.660 I slot print_timing: id 0 | task 9037 | graph reallocs = 0 / 0 (same size) / (changed size) 68.26.859.474 I slot release: id 0 | task 9037 | stop processing: n_tokens = 1083, truncated = 0 68.26.860.189 I slot print_timing: id 1 | task 9038 | prompt eval time = 51835.62 ms / 1091 tokens ( 47.51 ms per token, 21.05 tokens per second) 68.26.860.191 I slot print_timing: id 1 | task 9038 | eval time = 237.45 ms / 2 tokens ( 237.45 ms per token, 4.21 tokens per second) 68.26.860.421 I slot print_timing: id 1 | task 9038 | total time = 52073.06 ms / 1093 tokens 68.26.860.423 I slot print_timing: id 1 | task 9038 | graphs reused = 7735 68.26.860.424 I slot print_timing: id 1 | task 9038 | graph reallocs = 0 / 0 (same size) / (changed size) 68.26.862.150 I slot release: id 1 | task 9038 | stop processing: n_tokens = 1092, truncated = 0 68.26.862.529 I slot print_timing: id 2 | task 9039 | prompt eval time = 51829.99 ms / 880 tokens ( 58.90 ms per token, 16.98 tokens per second) 68.26.862.536 I slot print_timing: id 2 | task 9039 | eval time = 239.71 ms / 2 tokens ( 239.71 ms per token, 4.17 tokens per second) 68.26.862.537 I slot print_timing: id 2 | task 9039 | total time = 52069.69 ms / 882 tokens 68.26.862.537 I slot print_timing: id 2 | task 9039 | graphs reused = 7735 68.26.862.538 I slot print_timing: id 2 | task 9039 | graph reallocs = 0 / 0 (same size) / (changed size) 68.26.868.167 I slot release: id 2 | task 9039 | stop processing: n_tokens = 881, truncated = 0 68.26.868.408 I slot print_timing: id 3 | task 9040 | prompt eval time = 51830.60 ms / 896 tokens ( 57.85 ms per token, 17.29 tokens per second) 68.26.868.412 I slot print_timing: id 3 | task 9040 | eval time = 244.92 ms / 2 tokens ( 244.92 ms per token, 4.08 tokens per second) 68.26.868.413 I slot print_timing: id 3 | task 9040 | total time = 52075.51 ms / 898 tokens 68.26.868.413 I slot print_timing: id 3 | task 9040 | graphs reused = 7735 68.26.868.413 I slot print_timing: id 3 | task 9040 | graph reallocs = 0 / 0 (same size) / (changed size) 68.26.868.961 I slot release: id 3 | task 9040 | stop processing: n_tokens = 897, truncated = 0 68.26.875.944 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 68.26.875.975 I slot launch_slot_: id 1 | task 9048 | processing task, is_child = 0 68.26.876.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.211 MiB) 68.28.577.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.148 MiB) 68.31.079.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 68.33.743.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.901 68.33.743.108 I slot launch_slot_: id 0 | task 9049 | processing task, is_child = 0 68.33.743.220 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 107181805793 68.33.811.605 I slot launch_slot_: id 2 | task 9050 | processing task, is_child = 0 68.33.811.668 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 107181806584 68.33.811.735 I slot launch_slot_: id 3 | task 9051 | processing task, is_child = 0 68.43.082.859 I slot print_timing: id 0 | task 9049 | prompt processing, n_tokens = 176, progress = 1.00, t = 9.27 s / 18.98 tokens per second 68.43.486.305 I slot print_timing: id 1 | task 9048 | prompt processing, n_tokens = 162, progress = 1.00, t = 9.21 s / 17.59 tokens per second 68.43.499.152 I slot print_timing: id 2 | task 9050 | prompt processing, n_tokens = 170, progress = 1.00, t = 9.18 s / 18.52 tokens per second 68.43.513.043 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 183, progress = 0.17, t = 9.14 s / 20.03 tokens per second 68.46.285.758 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 364, progress = 0.34, t = 12.34 s / 29.50 tokens per second 68.49.186.111 I slot print_timing: id 0 | task 9049 | prompt eval time = 12473.09 ms / 180 tokens ( 69.29 ms per token, 14.43 tokens per second) 68.49.186.114 I slot print_timing: id 0 | task 9049 | eval time = 2901.28 ms / 2 tokens ( 2901.28 ms per token, 0.34 tokens per second) 68.49.186.114 I slot print_timing: id 0 | task 9049 | total time = 15374.37 ms / 182 tokens 68.49.186.115 I slot print_timing: id 0 | task 9049 | graphs reused = 7735 68.49.186.115 I slot print_timing: id 0 | task 9049 | graph reallocs = 0 / 0 (same size) / (changed size) 68.49.187.214 I slot release: id 0 | task 9049 | stop processing: n_tokens = 1086, truncated = 0 68.49.188.052 I slot print_timing: id 1 | task 9048 | prompt eval time = 12413.61 ms / 166 tokens ( 74.78 ms per token, 13.37 tokens per second) 68.49.188.058 I slot print_timing: id 1 | task 9048 | eval time = 2902.83 ms / 2 tokens ( 2902.83 ms per token, 0.34 tokens per second) 68.49.188.058 I slot print_timing: id 1 | task 9048 | total time = 15316.45 ms / 168 tokens 68.49.188.059 I slot print_timing: id 1 | task 9048 | graphs reused = 7735 68.49.188.059 I slot print_timing: id 1 | task 9048 | graph reallocs = 0 / 0 (same size) / (changed size) 68.49.188.123 I slot release: id 1 | task 9048 | stop processing: n_tokens = 1072, truncated = 0 68.49.188.838 I slot print_timing: id 2 | task 9050 | prompt eval time = 12382.00 ms / 174 tokens ( 71.16 ms per token, 14.05 tokens per second) 68.49.188.844 I slot print_timing: id 2 | task 9050 | eval time = 2903.12 ms / 2 tokens ( 2903.12 ms per token, 0.34 tokens per second) 68.49.188.845 I slot print_timing: id 2 | task 9050 | total time = 15285.12 ms / 176 tokens 68.49.188.845 I slot print_timing: id 2 | task 9050 | graphs reused = 7735 68.49.188.846 I slot print_timing: id 2 | task 9050 | graph reallocs = 0 / 0 (same size) / (changed size) 68.49.188.910 I slot release: id 2 | task 9050 | stop processing: n_tokens = 1080, truncated = 0 68.49.188.933 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 564, progress = 0.52, t = 15.24 s / 37.01 tokens per second 68.49.212.757 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.900 68.49.212.795 I slot launch_slot_: id 0 | task 9056 | processing task, is_child = 0 68.53.407.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.397 MiB) 68.55.741.697 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.911 68.55.741.772 I slot launch_slot_: id 1 | task 9057 | processing task, is_child = 0 68.55.741.830 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.905 68.55.741.851 I slot launch_slot_: id 2 | task 9058 | processing task, is_child = 0 68.55.802.133 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 905, progress = 0.84, t = 15.27 s / 59.28 tokens per second 69.04.595.690 I slot print_timing: id 0 | task 9056 | prompt processing, n_tokens = 164, progress = 1.00, t = 8.85 s / 18.52 tokens per second 69.04.791.221 I slot print_timing: id 1 | task 9057 | prompt processing, n_tokens = 173, progress = 1.00, t = 8.83 s / 19.60 tokens per second 69.04.795.770 I slot print_timing: id 2 | task 9058 | prompt processing, n_tokens = 179, progress = 1.00, t = 8.81 s / 20.31 tokens per second 69.05.092.984 I slot print_timing: id 3 | task 9051 | prompt processing, n_tokens = 1076, progress = 1.00, t = 30.65 s / 35.11 tokens per second 69.05.856.375 I slot print_timing: id 0 | task 9056 | prompt eval time = 9882.15 ms / 168 tokens ( 58.82 ms per token, 17.00 tokens per second) 69.05.856.836 I slot print_timing: id 0 | task 9056 | eval time = 232.35 ms / 2 tokens ( 232.35 ms per token, 4.30 tokens per second) 69.05.856.839 I slot print_timing: id 0 | task 9056 | total time = 10114.50 ms / 170 tokens 69.05.856.839 I slot print_timing: id 0 | task 9056 | graphs reused = 7735 69.05.856.840 I slot print_timing: id 0 | task 9056 | graph reallocs = 0 / 0 (same size) / (changed size) 69.05.857.345 I slot release: id 0 | task 9056 | stop processing: n_tokens = 1074, truncated = 0 69.05.857.673 I slot print_timing: id 1 | task 9057 | prompt eval time = 9856.39 ms / 177 tokens ( 55.69 ms per token, 17.96 tokens per second) 69.05.857.676 I slot print_timing: id 1 | task 9057 | eval time = 233.50 ms / 2 tokens ( 233.50 ms per token, 4.28 tokens per second) 69.05.857.677 I slot print_timing: id 1 | task 9057 | total time = 10089.90 ms / 179 tokens 69.05.857.677 I slot print_timing: id 1 | task 9057 | graphs reused = 7735 69.05.857.678 I slot print_timing: id 1 | task 9057 | graph reallocs = 0 / 0 (same size) / (changed size) 69.05.858.430 I slot release: id 1 | task 9057 | stop processing: n_tokens = 1083, truncated = 0 69.05.858.778 I slot print_timing: id 2 | task 9058 | prompt eval time = 9843.22 ms / 183 tokens ( 53.79 ms per token, 18.59 tokens per second) 69.05.858.782 I slot print_timing: id 2 | task 9058 | eval time = 234.44 ms / 2 tokens ( 234.44 ms per token, 4.27 tokens per second) 69.05.858.782 I slot print_timing: id 2 | task 9058 | total time = 10077.66 ms / 185 tokens 69.05.858.782 I slot print_timing: id 2 | task 9058 | graphs reused = 7735 69.05.858.783 I slot print_timing: id 2 | task 9058 | graph reallocs = 0 / 0 (same size) / (changed size) 69.05.860.284 I slot release: id 2 | task 9058 | stop processing: n_tokens = 1089, truncated = 0 69.05.860.454 I slot print_timing: id 3 | task 9051 | prompt eval time = 31679.82 ms / 1080 tokens ( 29.33 ms per token, 34.09 tokens per second) 69.05.860.458 I slot print_timing: id 3 | task 9051 | eval time = 235.59 ms / 2 tokens ( 235.59 ms per token, 4.24 tokens per second) 69.05.860.459 I slot print_timing: id 3 | task 9051 | total time = 31915.41 ms / 1082 tokens 69.05.860.459 I slot print_timing: id 3 | task 9051 | graphs reused = 7735 69.05.860.459 I slot print_timing: id 3 | task 9051 | graph reallocs = 0 / 0 (same size) / (changed size) 69.05.861.248 I slot release: id 3 | task 9051 | stop processing: n_tokens = 1081, truncated = 0 69.05.877.239 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.910 69.05.877.270 I slot launch_slot_: id 0 | task 9062 | processing task, is_child = 0 69.05.877.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 69.08.205.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.897 MiB) 69.10.738.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.522 MiB) 69.12.952.696 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.902 69.12.952.815 I slot launch_slot_: id 1 | task 9063 | processing task, is_child = 0 69.12.952.928 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.897 69.12.952.955 I slot launch_slot_: id 2 | task 9064 | processing task, is_child = 0 69.12.953.018 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.904 69.12.953.054 I slot launch_slot_: id 3 | task 9065 | processing task, is_child = 0 69.21.889.479 I slot print_timing: id 0 | task 9062 | prompt processing, n_tokens = 167, progress = 1.00, t = 8.94 s / 18.69 tokens per second 69.22.081.993 I slot print_timing: id 1 | task 9063 | prompt processing, n_tokens = 166, progress = 1.00, t = 8.90 s / 18.66 tokens per second 69.22.096.570 I slot print_timing: id 2 | task 9064 | prompt processing, n_tokens = 171, progress = 1.00, t = 8.86 s / 19.31 tokens per second 69.22.111.248 I slot print_timing: id 3 | task 9065 | prompt processing, n_tokens = 174, progress = 1.00, t = 8.85 s / 19.67 tokens per second 69.22.831.215 I slot print_timing: id 0 | task 9062 | prompt eval time = 9645.29 ms / 171 tokens ( 56.41 ms per token, 17.73 tokens per second) 69.22.831.220 I slot print_timing: id 0 | task 9062 | eval time = 232.86 ms / 2 tokens ( 232.86 ms per token, 4.29 tokens per second) 69.22.831.221 I slot print_timing: id 0 | task 9062 | total time = 9878.15 ms / 173 tokens 69.22.831.221 I slot print_timing: id 0 | task 9062 | graphs reused = 7735 69.22.831.221 I slot print_timing: id 0 | task 9062 | graph reallocs = 0 / 0 (same size) / (changed size) 69.22.832.568 I slot release: id 0 | task 9062 | stop processing: n_tokens = 1077, truncated = 0 69.22.832.873 I slot print_timing: id 1 | task 9063 | prompt eval time = 9606.87 ms / 170 tokens ( 56.51 ms per token, 17.70 tokens per second) 69.22.832.875 I slot print_timing: id 1 | task 9063 | eval time = 234.15 ms / 2 tokens ( 234.15 ms per token, 4.27 tokens per second) 69.22.832.876 I slot print_timing: id 1 | task 9063 | total time = 9841.02 ms / 172 tokens 69.22.832.876 I slot print_timing: id 1 | task 9063 | graphs reused = 7735 69.22.832.877 I slot print_timing: id 1 | task 9063 | graph reallocs = 0 / 0 (same size) / (changed size) 69.22.833.742 I slot release: id 1 | task 9063 | stop processing: n_tokens = 1076, truncated = 0 69.22.834.205 I slot print_timing: id 2 | task 9064 | prompt eval time = 9565.91 ms / 175 tokens ( 54.66 ms per token, 18.29 tokens per second) 69.22.834.209 I slot print_timing: id 2 | task 9064 | eval time = 234.97 ms / 2 tokens ( 234.97 ms per token, 4.26 tokens per second) 69.22.834.209 I slot print_timing: id 2 | task 9064 | total time = 9800.88 ms / 177 tokens 69.22.834.210 I slot print_timing: id 2 | task 9064 | graphs reused = 7735 69.22.834.211 I slot print_timing: id 2 | task 9064 | graph reallocs = 0 / 0 (same size) / (changed size) 69.22.835.316 I slot release: id 2 | task 9064 | stop processing: n_tokens = 1081, truncated = 0 69.22.835.568 I slot print_timing: id 3 | task 9065 | prompt eval time = 9557.00 ms / 178 tokens ( 53.69 ms per token, 18.63 tokens per second) 69.22.835.574 I slot print_timing: id 3 | task 9065 | eval time = 235.62 ms / 2 tokens ( 235.62 ms per token, 4.24 tokens per second) 69.22.835.574 I slot print_timing: id 3 | task 9065 | total time = 9792.62 ms / 180 tokens 69.22.835.575 I slot print_timing: id 3 | task 9065 | graphs reused = 7735 69.22.835.575 I slot print_timing: id 3 | task 9065 | graph reallocs = 0 / 0 (same size) / (changed size) 69.22.836.362 I slot release: id 3 | task 9065 | stop processing: n_tokens = 1084, truncated = 0 69.22.851.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.907 69.22.851.417 I slot launch_slot_: id 0 | task 9069 | processing task, is_child = 0 69.22.851.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.960 MiB) 69.25.266.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.148 MiB) 69.27.405.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.022 MiB) 69.29.647.686 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 69.29.647.799 I slot launch_slot_: id 1 | task 9070 | processing task, is_child = 0 69.29.647.920 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 107237772941 69.29.647.994 I slot launch_slot_: id 2 | task 9071 | processing task, is_child = 0 69.29.648.067 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1084, t_last = 107237773986 69.29.648.143 I slot launch_slot_: id 3 | task 9072 | processing task, is_child = 0 69.38.518.047 I slot print_timing: id 0 | task 9069 | prompt processing, n_tokens = 169, progress = 1.00, t = 8.87 s / 19.05 tokens per second 69.39.731.948 I slot print_timing: id 1 | task 9070 | prompt processing, n_tokens = 170, progress = 1.00, t = 8.85 s / 19.21 tokens per second 69.39.818.616 I slot print_timing: id 2 | task 9071 | prompt processing, n_tokens = 210, progress = 0.20, t = 8.81 s / 23.82 tokens per second 69.39.868.019 I slot print_timing: id 3 | task 9072 | prompt processing, n_tokens = 210, progress = 0.21, t = 8.81 s / 23.83 tokens per second 69.44.904.352 I slot print_timing: id 2 | task 9071 | prompt processing, n_tokens = 393, progress = 0.38, t = 15.20 s / 25.86 tokens per second 69.44.904.368 I slot print_timing: id 3 | task 9072 | prompt processing, n_tokens = 393, progress = 0.39, t = 15.20 s / 25.86 tokens per second 69.48.242.409 I slot print_timing: id 0 | task 9069 | prompt eval time = 15255.80 ms / 173 tokens ( 88.18 ms per token, 11.34 tokens per second) 69.48.242.416 I slot print_timing: id 0 | task 9069 | eval time = 3338.45 ms / 2 tokens ( 3338.45 ms per token, 0.30 tokens per second) 69.48.242.424 I slot print_timing: id 0 | task 9069 | total time = 18594.26 ms / 175 tokens 69.48.242.426 I slot print_timing: id 0 | task 9069 | graphs reused = 7735 69.48.242.427 I slot print_timing: id 0 | task 9069 | graph reallocs = 0 / 0 (same size) / (changed size) 69.48.242.630 I slot release: id 0 | task 9069 | stop processing: n_tokens = 1079, truncated = 0 69.48.242.878 I slot print_timing: id 1 | task 9070 | prompt eval time = 15234.60 ms / 174 tokens ( 87.56 ms per token, 11.42 tokens per second) 69.48.242.884 I slot print_timing: id 1 | task 9070 | eval time = 3338.54 ms / 2 tokens ( 3338.54 ms per token, 0.30 tokens per second) 69.48.242.885 I slot print_timing: id 1 | task 9070 | total time = 18573.14 ms / 176 tokens 69.48.242.885 I slot print_timing: id 1 | task 9070 | graphs reused = 7735 69.48.242.886 I slot print_timing: id 1 | task 9070 | graph reallocs = 0 / 0 (same size) / (changed size) 69.48.242.943 I slot release: id 1 | task 9070 | stop processing: n_tokens = 1080, truncated = 0 69.48.242.951 I slot print_timing: id 2 | task 9071 | prompt processing, n_tokens = 515, progress = 0.50, t = 18.54 s / 27.78 tokens per second 69.48.260.738 I slot print_timing: id 3 | task 9072 | prompt processing, n_tokens = 501, progress = 0.49, t = 18.54 s / 27.03 tokens per second 69.57.042.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 107263180253 69.57.042.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 803.214 MiB) 70.00.022.777 I slot launch_slot_: id 0 | task 9077 | processing task, is_child = 0 70.00.022.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 804.214 MiB) 70.02.814.625 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 107263180565 70.02.814.767 I slot launch_slot_: id 1 | task 9078 | processing task, is_child = 0 70.02.814.967 I slot print_timing: id 2 | task 9071 | prompt processing, n_tokens = 878, progress = 0.85, t = 27.34 s / 32.12 tokens per second 70.02.820.172 I slot print_timing: id 3 | task 9072 | prompt processing, n_tokens = 878, progress = 0.86, t = 27.34 s / 32.12 tokens per second 70.10.437.920 I slot print_timing: id 0 | task 9077 | prompt processing, n_tokens = 210, progress = 0.20, t = 7.62 s / 27.55 tokens per second 70.11.993.951 I slot print_timing: id 1 | task 9078 | prompt processing, n_tokens = 210, progress = 0.19, t = 7.62 s / 27.55 tokens per second 70.12.041.950 I slot print_timing: id 2 | task 9071 | prompt processing, n_tokens = 1027, progress = 1.00, t = 40.73 s / 25.21 tokens per second 70.12.047.595 I slot print_timing: id 3 | task 9072 | prompt processing, n_tokens = 1013, progress = 1.00, t = 40.73 s / 24.87 tokens per second 70.17.042.847 I slot print_timing: id 0 | task 9077 | prompt processing, n_tokens = 393, progress = 0.37, t = 14.23 s / 27.62 tokens per second 70.17.042.865 I slot print_timing: id 1 | task 9078 | prompt processing, n_tokens = 393, progress = 0.36, t = 14.23 s / 27.62 tokens per second 70.22.224.986 I slot print_timing: id 2 | task 9071 | prompt eval time = 47338.87 ms / 1031 tokens ( 45.92 ms per token, 21.78 tokens per second) 70.22.224.994 I slot print_timing: id 2 | task 9071 | eval time = 5182.47 ms / 2 tokens ( 5182.47 ms per token, 0.19 tokens per second) 70.22.224.994 I slot print_timing: id 2 | task 9071 | total time = 52521.33 ms / 1033 tokens 70.22.224.995 I slot print_timing: id 2 | task 9071 | graphs reused = 7735 70.22.224.995 I slot print_timing: id 2 | task 9071 | graph reallocs = 0 / 0 (same size) / (changed size) 70.22.234.831 I slot release: id 2 | task 9071 | stop processing: n_tokens = 1032, truncated = 0 70.22.235.193 I slot print_timing: id 3 | task 9072 | prompt eval time = 47339.07 ms / 1017 tokens ( 46.55 ms per token, 21.48 tokens per second) 70.22.235.197 I slot print_timing: id 3 | task 9072 | eval time = 5192.36 ms / 2 tokens ( 5192.36 ms per token, 0.19 tokens per second) 70.22.235.197 I slot print_timing: id 3 | task 9072 | total time = 52531.43 ms / 1019 tokens 70.22.235.198 I slot print_timing: id 3 | task 9072 | graphs reused = 7735 70.22.235.198 I slot print_timing: id 3 | task 9072 | graph reallocs = 0 / 0 (same size) / (changed size) 70.22.235.249 I slot release: id 3 | task 9072 | stop processing: n_tokens = 1018, truncated = 0 70.22.235.266 I slot print_timing: id 0 | task 9077 | prompt processing, n_tokens = 555, progress = 0.52, t = 19.41 s / 28.59 tokens per second 70.22.288.436 I slot print_timing: id 1 | task 9078 | prompt processing, n_tokens = 590, progress = 0.53, t = 19.41 s / 30.40 tokens per second 70.29.241.039 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.878 70.29.241.110 I slot launch_slot_: id 2 | task 9083 | processing task, is_child = 0 70.29.241.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 70.31.050.589 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 70.31.050.697 I slot launch_slot_: id 3 | task 9084 | processing task, is_child = 0 70.31.050.706 I slot print_timing: id 0 | task 9077 | prompt processing, n_tokens = 878, progress = 0.82, t = 26.43 s / 33.22 tokens per second 70.31.110.346 I slot print_timing: id 1 | task 9078 | prompt processing, n_tokens = 878, progress = 0.79, t = 26.43 s / 33.22 tokens per second 70.40.580.288 I slot print_timing: id 0 | task 9077 | prompt processing, n_tokens = 1067, progress = 1.00, t = 37.77 s / 28.25 tokens per second 70.40.994.318 I slot print_timing: id 1 | task 9078 | prompt processing, n_tokens = 1102, progress = 1.00, t = 37.76 s / 29.18 tokens per second 70.40.999.146 I slot print_timing: id 2 | task 9083 | prompt processing, n_tokens = 148, progress = 1.00, t = 9.42 s / 15.71 tokens per second 70.41.041.741 I slot print_timing: id 3 | task 9084 | prompt processing, n_tokens = 163, progress = 1.00, t = 9.39 s / 17.35 tokens per second 70.41.824.655 I slot print_timing: id 0 | task 9077 | prompt eval time = 38776.99 ms / 1071 tokens ( 36.21 ms per token, 27.62 tokens per second) 70.41.824.658 I slot print_timing: id 0 | task 9077 | eval time = 232.88 ms / 2 tokens ( 232.88 ms per token, 4.29 tokens per second) 70.41.824.658 I slot print_timing: id 0 | task 9077 | total time = 39009.87 ms / 1073 tokens 70.41.824.659 I slot print_timing: id 0 | task 9077 | graphs reused = 7735 70.41.824.659 I slot print_timing: id 0 | task 9077 | graph reallocs = 0 / 0 (same size) / (changed size) 70.41.829.084 I slot release: id 0 | task 9077 | stop processing: n_tokens = 1072, truncated = 0 70.41.829.663 I slot print_timing: id 1 | task 9078 | prompt eval time = 38777.39 ms / 1106 tokens ( 35.06 ms per token, 28.52 tokens per second) 70.41.829.670 I slot print_timing: id 1 | task 9078 | eval time = 237.38 ms / 2 tokens ( 237.38 ms per token, 4.21 tokens per second) 70.41.829.671 I slot print_timing: id 1 | task 9078 | total time = 39014.77 ms / 1108 tokens 70.41.829.672 I slot print_timing: id 1 | task 9078 | graphs reused = 7735 70.41.829.672 I slot print_timing: id 1 | task 9078 | graph reallocs = 0 / 0 (same size) / (changed size) 70.41.834.886 I slot release: id 1 | task 9078 | stop processing: n_tokens = 1107, truncated = 0 70.41.835.266 I slot print_timing: id 2 | task 9083 | prompt eval time = 10436.62 ms / 152 tokens ( 68.66 ms per token, 14.56 tokens per second) 70.41.835.268 I slot print_timing: id 2 | task 9083 | eval time = 242.40 ms / 2 tokens ( 242.40 ms per token, 4.13 tokens per second) 70.41.835.269 I slot print_timing: id 2 | task 9083 | total time = 10679.02 ms / 154 tokens 70.41.835.269 I slot print_timing: id 2 | task 9083 | graphs reused = 7735 70.41.835.269 I slot print_timing: id 2 | task 9083 | graph reallocs = 0 / 0 (same size) / (changed size) 70.41.837.472 I slot release: id 2 | task 9083 | stop processing: n_tokens = 1031, truncated = 0 70.41.837.731 I slot print_timing: id 3 | task 9084 | prompt eval time = 10407.17 ms / 167 tokens ( 62.32 ms per token, 16.05 tokens per second) 70.41.837.734 I slot print_timing: id 3 | task 9084 | eval time = 244.21 ms / 2 tokens ( 244.21 ms per token, 4.09 tokens per second) 70.41.837.735 I slot print_timing: id 3 | task 9084 | total time = 10651.38 ms / 169 tokens 70.41.837.735 I slot print_timing: id 3 | task 9084 | graphs reused = 7735 70.41.837.735 I slot print_timing: id 3 | task 9084 | graph reallocs = 0 / 0 (same size) / (changed size) 70.41.838.974 I slot release: id 3 | task 9084 | stop processing: n_tokens = 1046, truncated = 0 70.41.856.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 107316766707 70.41.856.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.656 MiB) 70.43.691.744 I slot launch_slot_: id 0 | task 9088 | processing task, is_child = 0 70.43.691.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.843 MiB) 70.46.081.512 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 816.218 MiB) 70.48.705.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.718 MiB) 70.51.338.520 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 107316772510 70.51.338.670 I slot launch_slot_: id 1 | task 9089 | processing task, is_child = 0 70.51.338.771 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 107316775095 70.51.338.848 I slot launch_slot_: id 2 | task 9090 | processing task, is_child = 0 70.51.338.901 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 107316776597 70.51.338.968 I slot launch_slot_: id 3 | task 9091 | processing task, is_child = 0 70.57.556.199 I slot print_timing: id 0 | task 9088 | prompt processing, n_tokens = 136, progress = 0.19, t = 6.22 s / 21.87 tokens per second 70.58.040.881 I slot print_timing: id 1 | task 9089 | prompt processing, n_tokens = 136, progress = 0.18, t = 6.22 s / 21.88 tokens per second 70.58.053.251 I slot print_timing: id 2 | task 9090 | prompt processing, n_tokens = 136, progress = 0.18, t = 6.22 s / 21.88 tokens per second 70.58.066.118 I slot print_timing: id 3 | task 9091 | prompt processing, n_tokens = 136, progress = 0.17, t = 6.22 s / 21.88 tokens per second 71.03.120.395 I slot print_timing: id 0 | task 9088 | prompt processing, n_tokens = 213, progress = 0.29, t = 11.78 s / 18.08 tokens per second 71.03.916.753 I slot print_timing: id 1 | task 9089 | prompt processing, n_tokens = 237, progress = 0.31, t = 11.78 s / 20.12 tokens per second 71.03.931.043 I slot print_timing: id 2 | task 9090 | prompt processing, n_tokens = 224, progress = 0.30, t = 11.78 s / 19.01 tokens per second 71.03.945.213 I slot print_timing: id 3 | task 9091 | prompt processing, n_tokens = 259, progress = 0.32, t = 11.78 s / 21.98 tokens per second 71.19.049.074 I slot print_timing: id 0 | task 9088 | prompt processing, n_tokens = 623, progress = 0.85, t = 27.71 s / 22.48 tokens per second 71.19.456.859 I slot print_timing: id 1 | task 9089 | prompt processing, n_tokens = 623, progress = 0.83, t = 27.71 s / 22.48 tokens per second 71.19.471.332 I slot print_timing: id 2 | task 9090 | prompt processing, n_tokens = 623, progress = 0.84, t = 27.71 s / 22.48 tokens per second 71.19.485.703 I slot print_timing: id 3 | task 9091 | prompt processing, n_tokens = 281, progress = 0.35, t = 27.71 s / 10.14 tokens per second 71.25.717.986 I slot print_timing: id 0 | task 9088 | prompt processing, n_tokens = 725, progress = 0.99, t = 34.38 s / 21.09 tokens per second 71.28.741.619 I slot print_timing: id 1 | task 9089 | prompt processing, n_tokens = 749, progress = 0.99, t = 34.38 s / 21.79 tokens per second 71.28.756.111 I slot print_timing: id 2 | task 9090 | prompt processing, n_tokens = 736, progress = 0.99, t = 34.38 s / 21.41 tokens per second 71.28.770.497 I slot print_timing: id 3 | task 9091 | prompt processing, n_tokens = 623, progress = 0.78, t = 34.38 s / 18.12 tokens per second 71.31.542.257 I slot print_timing: id 3 | task 9091 | prompt processing, n_tokens = 793, progress = 0.99, t = 40.20 s / 19.73 tokens per second 71.31.984.205 I slot print_timing: id 0 | task 9088 | prompt eval time = 40202.15 ms / 729 tokens ( 55.15 ms per token, 18.13 tokens per second) 71.31.984.211 I slot print_timing: id 0 | task 9088 | eval time = 443.08 ms / 2 tokens ( 443.08 ms per token, 2.26 tokens per second) 71.31.984.213 I slot print_timing: id 0 | task 9088 | total time = 40645.22 ms / 731 tokens 71.31.984.214 I slot print_timing: id 0 | task 9088 | graphs reused = 7735 71.31.984.214 I slot print_timing: id 0 | task 9088 | graph reallocs = 0 / 0 (same size) / (changed size) 71.31.988.489 I slot release: id 0 | task 9088 | stop processing: n_tokens = 730, truncated = 0 71.31.988.927 I slot print_timing: id 1 | task 9089 | prompt eval time = 40202.46 ms / 753 tokens ( 53.39 ms per token, 18.73 tokens per second) 71.31.989.025 I slot print_timing: id 1 | task 9089 | eval time = 447.38 ms / 2 tokens ( 447.38 ms per token, 2.24 tokens per second) 71.31.989.028 I slot print_timing: id 1 | task 9089 | total time = 40649.85 ms / 755 tokens 71.31.989.029 I slot print_timing: id 1 | task 9089 | graphs reused = 7735 71.31.989.029 I slot print_timing: id 1 | task 9089 | graph reallocs = 0 / 0 (same size) / (changed size) 71.31.989.389 I slot release: id 1 | task 9089 | stop processing: n_tokens = 754, truncated = 0 71.31.989.801 I slot print_timing: id 2 | task 9090 | prompt eval time = 40203.08 ms / 740 tokens ( 54.33 ms per token, 18.41 tokens per second) 71.31.989.807 I slot print_timing: id 2 | task 9090 | eval time = 447.56 ms / 2 tokens ( 447.56 ms per token, 2.23 tokens per second) 71.31.989.807 I slot print_timing: id 2 | task 9090 | total time = 40650.65 ms / 742 tokens 71.31.989.809 I slot print_timing: id 2 | task 9090 | graphs reused = 7735 71.31.989.809 I slot print_timing: id 2 | task 9090 | graph reallocs = 0 / 0 (same size) / (changed size) 71.31.990.104 I slot release: id 2 | task 9090 | stop processing: n_tokens = 741, truncated = 0 71.32.117.414 I slot print_timing: id 3 | task 9091 | prompt eval time = 40651.67 ms / 797 tokens ( 51.01 ms per token, 19.61 tokens per second) 71.32.117.416 I slot print_timing: id 3 | task 9091 | eval time = 126.52 ms / 2 tokens ( 126.52 ms per token, 7.90 tokens per second) 71.32.117.417 I slot print_timing: id 3 | task 9091 | total time = 40778.18 ms / 799 tokens 71.32.117.417 I slot print_timing: id 3 | task 9091 | graphs reused = 7735 71.32.117.417 I slot print_timing: id 3 | task 9091 | graph reallocs = 0 / 0 (same size) / (changed size) 71.32.117.478 I slot release: id 3 | task 9091 | stop processing: n_tokens = 798, truncated = 0 71.32.117.486 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.866 71.32.117.513 I slot launch_slot_: id 1 | task 9099 | processing task, is_child = 0 71.32.117.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.406 MiB) 71.34.333.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.718 MiB) 71.36.828.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.906 MiB) 71.39.006.848 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 71.39.006.936 I slot launch_slot_: id 0 | task 9100 | processing task, is_child = 0 71.39.007.029 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.879 71.39.007.049 I slot launch_slot_: id 2 | task 9101 | processing task, is_child = 0 71.39.007.093 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 71.39.007.109 I slot launch_slot_: id 3 | task 9102 | processing task, is_child = 0 71.45.332.857 I slot print_timing: id 0 | task 9100 | prompt processing, n_tokens = 119, progress = 0.99, t = 6.33 s / 18.81 tokens per second 71.45.782.476 I slot print_timing: id 1 | task 9099 | prompt processing, n_tokens = 112, progress = 0.99, t = 6.25 s / 17.93 tokens per second 71.45.834.076 I slot print_timing: id 2 | task 9101 | prompt processing, n_tokens = 106, progress = 0.99, t = 6.21 s / 17.06 tokens per second 71.45.857.456 I slot print_timing: id 3 | task 9102 | prompt processing, n_tokens = 128, progress = 0.99, t = 6.15 s / 20.80 tokens per second 71.46.610.072 I slot print_timing: id 0 | task 9100 | prompt eval time = 7369.65 ms / 123 tokens ( 59.92 ms per token, 16.69 tokens per second) 71.46.610.077 I slot print_timing: id 0 | task 9100 | eval time = 233.31 ms / 2 tokens ( 233.31 ms per token, 4.29 tokens per second) 71.46.610.077 I slot print_timing: id 0 | task 9100 | total time = 7602.95 ms / 125 tokens 71.46.610.078 I slot print_timing: id 0 | task 9100 | graphs reused = 7735 71.46.610.078 I slot print_timing: id 0 | task 9100 | graph reallocs = 0 / 0 (same size) / (changed size) 71.46.612.925 I slot release: id 0 | task 9100 | stop processing: n_tokens = 747, truncated = 0 71.46.613.404 I slot print_timing: id 1 | task 9099 | prompt eval time = 7293.35 ms / 116 tokens ( 62.87 ms per token, 15.90 tokens per second) 71.46.613.408 I slot print_timing: id 1 | task 9099 | eval time = 235.99 ms / 2 tokens ( 235.99 ms per token, 4.24 tokens per second) 71.46.613.408 I slot print_timing: id 1 | task 9099 | total time = 7529.34 ms / 118 tokens 71.46.613.408 I slot print_timing: id 1 | task 9099 | graphs reused = 7735 71.46.613.408 I slot print_timing: id 1 | task 9099 | graph reallocs = 0 / 0 (same size) / (changed size) 71.46.614.037 I slot release: id 1 | task 9099 | stop processing: n_tokens = 740, truncated = 0 71.46.614.434 I slot print_timing: id 2 | task 9101 | prompt eval time = 7260.28 ms / 110 tokens ( 66.00 ms per token, 15.15 tokens per second) 71.46.614.438 I slot print_timing: id 2 | task 9101 | eval time = 235.88 ms / 2 tokens ( 235.88 ms per token, 4.24 tokens per second) 71.46.614.440 I slot print_timing: id 2 | task 9101 | total time = 7496.15 ms / 112 tokens 71.46.614.440 I slot print_timing: id 2 | task 9101 | graphs reused = 7735 71.46.614.440 I slot print_timing: id 2 | task 9101 | graph reallocs = 0 / 0 (same size) / (changed size) 71.46.614.883 I slot release: id 2 | task 9101 | stop processing: n_tokens = 734, truncated = 0 71.46.615.196 I slot print_timing: id 3 | task 9102 | prompt eval time = 7200.63 ms / 132 tokens ( 54.55 ms per token, 18.33 tokens per second) 71.46.615.201 I slot print_timing: id 3 | task 9102 | eval time = 235.60 ms / 2 tokens ( 235.60 ms per token, 4.24 tokens per second) 71.46.615.201 I slot print_timing: id 3 | task 9102 | total time = 7436.23 ms / 134 tokens 71.46.615.201 I slot print_timing: id 3 | task 9102 | graphs reused = 7735 71.46.615.202 I slot print_timing: id 3 | task 9102 | graph reallocs = 0 / 0 (same size) / (changed size) 71.46.616.938 I slot release: id 3 | task 9102 | stop processing: n_tokens = 756, truncated = 0 71.46.637.162 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 71.46.637.193 I slot launch_slot_: id 0 | task 9106 | processing task, is_child = 0 71.46.637.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.593 MiB) 71.48.768.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.656 MiB) 71.50.979.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 811.779 MiB) 71.52.920.844 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 107381551660 71.52.921.299 I slot launch_slot_: id 1 | task 9107 | processing task, is_child = 0 71.52.921.394 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 107381552510 71.52.926.768 I slot launch_slot_: id 2 | task 9108 | processing task, is_child = 0 71.52.926.874 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 107381554562 71.52.931.070 I slot launch_slot_: id 3 | task 9109 | processing task, is_child = 0 71.58.831.910 I slot print_timing: id 0 | task 9106 | prompt processing, n_tokens = 120, progress = 0.99, t = 5.90 s / 20.34 tokens per second 72.00.435.611 I slot print_timing: id 1 | task 9107 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.88 s / 27.56 tokens per second 72.00.498.038 I slot print_timing: id 2 | task 9108 | prompt processing, n_tokens = 162, progress = 0.17, t = 5.88 s / 27.56 tokens per second 72.00.546.069 I slot print_timing: id 3 | task 9109 | prompt processing, n_tokens = 162, progress = 0.16, t = 5.88 s / 27.56 tokens per second 72.07.967.081 I slot print_timing: id 1 | task 9107 | prompt processing, n_tokens = 350, progress = 0.36, t = 15.01 s / 23.31 tokens per second 72.07.967.099 I slot print_timing: id 2 | task 9108 | prompt processing, n_tokens = 350, progress = 0.37, t = 15.01 s / 23.31 tokens per second 72.07.967.106 I slot print_timing: id 3 | task 9109 | prompt processing, n_tokens = 350, progress = 0.35, t = 15.01 s / 23.31 tokens per second 72.12.848.360 I slot print_timing: id 0 | task 9106 | prompt eval time = 15035.96 ms / 124 tokens ( 121.26 ms per token, 8.25 tokens per second) 72.12.848.363 I slot print_timing: id 0 | task 9106 | eval time = 4881.30 ms / 2 tokens ( 4881.30 ms per token, 0.20 tokens per second) 72.12.848.363 I slot print_timing: id 0 | task 9106 | total time = 19917.26 ms / 126 tokens 72.12.848.364 I slot print_timing: id 0 | task 9106 | graphs reused = 7735 72.12.848.364 I slot print_timing: id 0 | task 9106 | graph reallocs = 0 / 0 (same size) / (changed size) 72.12.850.330 I slot release: id 0 | task 9106 | stop processing: n_tokens = 748, truncated = 0 72.12.850.364 I slot print_timing: id 1 | task 9107 | prompt processing, n_tokens = 457, progress = 0.47, t = 19.90 s / 22.97 tokens per second 72.12.859.338 I slot print_timing: id 2 | task 9108 | prompt processing, n_tokens = 439, progress = 0.46, t = 19.90 s / 22.07 tokens per second 72.12.899.362 I slot print_timing: id 3 | task 9109 | prompt processing, n_tokens = 474, progress = 0.48, t = 19.90 s / 23.82 tokens per second 72.26.495.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 107407787954 72.26.495.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 815.156 MiB) 72.28.826.872 I slot launch_slot_: id 0 | task 9114 | processing task, is_child = 0 72.28.826.956 I slot print_timing: id 1 | task 9107 | prompt processing, n_tokens = 820, progress = 0.84, t = 33.54 s / 24.45 tokens per second 72.28.831.338 I slot print_timing: id 2 | task 9108 | prompt processing, n_tokens = 820, progress = 0.86, t = 33.54 s / 24.45 tokens per second 72.28.838.203 I slot print_timing: id 3 | task 9109 | prompt processing, n_tokens = 820, progress = 0.83, t = 33.54 s / 24.45 tokens per second 72.36.586.077 I slot print_timing: id 0 | task 9114 | prompt processing, n_tokens = 162, progress = 0.16, t = 7.76 s / 20.88 tokens per second 72.37.384.732 I slot print_timing: id 1 | task 9107 | prompt processing, n_tokens = 969, progress = 1.00, t = 43.63 s / 22.21 tokens per second 72.37.448.163 I slot print_timing: id 2 | task 9108 | prompt processing, n_tokens = 951, progress = 1.00, t = 43.63 s / 21.80 tokens per second 72.37.505.872 I slot print_timing: id 3 | task 9109 | prompt processing, n_tokens = 986, progress = 1.00, t = 43.63 s / 22.60 tokens per second 72.40.428.065 I slot print_timing: id 0 | task 9114 | prompt processing, n_tokens = 350, progress = 0.34, t = 11.60 s / 30.17 tokens per second 72.42.936.699 I slot print_timing: id 1 | task 9107 | prompt eval time = 47474.14 ms / 973 tokens ( 48.79 ms per token, 20.50 tokens per second) 72.42.936.703 I slot print_timing: id 1 | task 9107 | eval time = 2509.65 ms / 2 tokens ( 2509.65 ms per token, 0.40 tokens per second) 72.42.936.703 I slot print_timing: id 1 | task 9107 | total time = 49983.79 ms / 975 tokens 72.42.936.704 I slot print_timing: id 1 | task 9107 | graphs reused = 7735 72.42.936.704 I slot print_timing: id 1 | task 9107 | graph reallocs = 0 / 0 (same size) / (changed size) 72.42.946.623 I slot release: id 1 | task 9107 | stop processing: n_tokens = 974, truncated = 0 72.42.947.339 I slot print_timing: id 2 | task 9108 | prompt eval time = 47474.50 ms / 955 tokens ( 49.71 ms per token, 20.12 tokens per second) 72.42.947.343 I slot print_timing: id 2 | task 9108 | eval time = 2519.85 ms / 2 tokens ( 2519.85 ms per token, 0.40 tokens per second) 72.42.947.344 I slot print_timing: id 2 | task 9108 | total time = 49994.34 ms / 957 tokens 72.42.947.344 I slot print_timing: id 2 | task 9108 | graphs reused = 7735 72.42.947.345 I slot print_timing: id 2 | task 9108 | graph reallocs = 0 / 0 (same size) / (changed size) 72.42.947.992 I slot release: id 2 | task 9108 | stop processing: n_tokens = 956, truncated = 0 72.42.948.822 I slot print_timing: id 3 | task 9109 | prompt eval time = 47474.98 ms / 990 tokens ( 47.95 ms per token, 20.85 tokens per second) 72.42.948.826 I slot print_timing: id 3 | task 9109 | eval time = 2520.79 ms / 2 tokens ( 2520.79 ms per token, 0.40 tokens per second) 72.42.948.827 I slot print_timing: id 3 | task 9109 | total time = 49995.77 ms / 992 tokens 72.42.948.827 I slot print_timing: id 3 | task 9109 | graphs reused = 7735 72.42.948.827 I slot print_timing: id 3 | task 9109 | graph reallocs = 0 / 0 (same size) / (changed size) 72.42.950.183 I slot release: id 3 | task 9109 | stop processing: n_tokens = 991, truncated = 0 72.42.950.211 I slot print_timing: id 0 | task 9114 | prompt processing, n_tokens = 528, progress = 0.51, t = 14.11 s / 37.42 tokens per second 72.43.004.834 I slot print_timing: id 0 | task 9114 | prompt processing, n_tokens = 820, progress = 0.79, t = 14.18 s / 57.84 tokens per second 72.46.810.487 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 107437884247 72.46.810.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 817.344 MiB) 72.49.590.511 I slot launch_slot_: id 1 | task 9120 | processing task, is_child = 0 72.49.590.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 812.592 MiB) 72.51.824.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.530 MiB) 72.53.907.612 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 107437885616 72.53.907.781 I slot launch_slot_: id 2 | task 9121 | processing task, is_child = 0 72.53.907.841 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 107437887811 72.53.907.912 I slot launch_slot_: id 3 | task 9122 | processing task, is_child = 0 72.53.907.921 I slot print_timing: id 0 | task 9114 | prompt processing, n_tokens = 1040, progress = 1.00, t = 17.98 s / 57.83 tokens per second 73.04.297.884 I slot print_timing: id 1 | task 9120 | prompt processing, n_tokens = 204, progress = 0.18, t = 10.20 s / 20.01 tokens per second 73.04.310.408 I slot print_timing: id 2 | task 9121 | prompt processing, n_tokens = 204, progress = 0.18, t = 10.20 s / 20.01 tokens per second 73.04.375.162 I slot print_timing: id 3 | task 9122 | prompt processing, n_tokens = 372, progress = 0.18, t = 10.20 s / 36.48 tokens per second 73.11.530.317 I slot print_timing: id 0 | task 9114 | prompt eval time = 35470.95 ms / 1044 tokens ( 33.98 ms per token, 29.43 tokens per second) 73.11.530.744 I slot print_timing: id 0 | task 9114 | eval time = 7232.47 ms / 2 tokens ( 7232.47 ms per token, 0.14 tokens per second) 73.11.530.747 I slot print_timing: id 0 | task 9114 | total time = 42703.42 ms / 1046 tokens 73.11.530.748 I slot print_timing: id 0 | task 9114 | graphs reused = 7735 73.11.530.748 I slot print_timing: id 0 | task 9114 | graph reallocs = 0 / 0 (same size) / (changed size) 73.11.533.171 I slot release: id 0 | task 9114 | stop processing: n_tokens = 1045, truncated = 0 73.11.533.202 I slot print_timing: id 1 | task 9120 | prompt processing, n_tokens = 350, progress = 0.30, t = 17.53 s / 19.96 tokens per second 73.11.533.221 I slot print_timing: id 2 | task 9121 | prompt processing, n_tokens = 350, progress = 0.31, t = 17.53 s / 19.96 tokens per second 73.11.533.230 I slot print_timing: id 3 | task 9122 | prompt processing, n_tokens = 640, progress = 0.31, t = 17.53 s / 36.50 tokens per second 73.27.963.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 107466470794 73.27.963.697 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 793.773 MiB) 73.30.278.167 I slot launch_slot_: id 0 | task 9126 | processing task, is_child = 0 73.30.278.288 I slot print_timing: id 1 | task 9120 | prompt processing, n_tokens = 645, progress = 0.56, t = 33.97 s / 18.99 tokens per second 73.30.283.220 I slot print_timing: id 2 | task 9121 | prompt processing, n_tokens = 608, progress = 0.54, t = 33.97 s / 17.90 tokens per second 73.30.287.981 I slot print_timing: id 3 | task 9122 | prompt processing, n_tokens = 1575, progress = 0.75, t = 33.97 s / 46.37 tokens per second 73.45.556.722 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 372, progress = 0.18, t = 15.28 s / 24.35 tokens per second 73.46.354.768 I slot print_timing: id 1 | task 9120 | prompt processing, n_tokens = 977, progress = 0.84, t = 51.56 s / 18.95 tokens per second 73.46.403.774 I slot print_timing: id 2 | task 9121 | prompt processing, n_tokens = 977, progress = 0.87, t = 51.56 s / 18.95 tokens per second 73.46.466.431 I slot print_timing: id 3 | task 9122 | prompt processing, n_tokens = 1761, progress = 0.84, t = 51.56 s / 34.15 tokens per second 73.55.904.865 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 640, progress = 0.31, t = 25.63 s / 24.97 tokens per second 73.55.904.891 I slot print_timing: id 1 | task 9120 | prompt processing, n_tokens = 1157, progress = 1.00, t = 61.91 s / 18.69 tokens per second 73.58.249.435 I slot print_timing: id 2 | task 9121 | prompt processing, n_tokens = 1120, progress = 1.00, t = 61.91 s / 18.09 tokens per second 73.58.323.151 I slot print_timing: id 3 | task 9122 | prompt processing, n_tokens = 2087, progress = 1.00, t = 61.91 s / 33.71 tokens per second 74.10.216.581 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 1578, progress = 0.75, t = 39.94 s / 39.51 tokens per second 74.12.881.201 I slot print_timing: id 1 | task 9120 | prompt eval time = 76220.06 ms / 1161 tokens ( 65.65 ms per token, 15.23 tokens per second) 74.12.881.203 I slot print_timing: id 1 | task 9120 | eval time = 2665.57 ms / 2 tokens ( 2665.57 ms per token, 0.38 tokens per second) 74.12.881.206 I slot print_timing: id 1 | task 9120 | total time = 78885.64 ms / 1163 tokens 74.12.881.206 I slot print_timing: id 1 | task 9120 | graphs reused = 7735 74.12.881.207 I slot print_timing: id 1 | task 9120 | graph reallocs = 0 / 0 (same size) / (changed size) 74.12.886.209 I slot release: id 1 | task 9120 | stop processing: n_tokens = 1162, truncated = 0 74.12.887.082 I slot print_timing: id 2 | task 9121 | prompt eval time = 76220.44 ms / 1124 tokens ( 67.81 ms per token, 14.75 tokens per second) 74.12.887.086 I slot print_timing: id 2 | task 9121 | eval time = 2670.97 ms / 2 tokens ( 2670.97 ms per token, 0.37 tokens per second) 74.12.887.088 I slot print_timing: id 2 | task 9121 | total time = 78891.42 ms / 1126 tokens 74.12.887.088 I slot print_timing: id 2 | task 9121 | graphs reused = 7735 74.12.887.089 I slot print_timing: id 2 | task 9121 | graph reallocs = 0 / 0 (same size) / (changed size) 74.12.887.204 I slot release: id 2 | task 9121 | stop processing: n_tokens = 1125, truncated = 0 74.12.888.155 I slot print_timing: id 3 | task 9122 | prompt eval time = 76220.79 ms / 2091 tokens ( 36.45 ms per token, 27.43 tokens per second) 74.12.888.159 I slot print_timing: id 3 | task 9122 | eval time = 2671.62 ms / 2 tokens ( 2671.62 ms per token, 0.37 tokens per second) 74.12.888.160 I slot print_timing: id 3 | task 9122 | total time = 78892.42 ms / 2093 tokens 74.12.888.160 I slot print_timing: id 3 | task 9122 | graphs reused = 7735 74.12.888.161 I slot print_timing: id 3 | task 9122 | graph reallocs = 0 / 0 (same size) / (changed size) 74.12.893.615 I slot release: id 3 | task 9122 | stop processing: n_tokens = 2092, truncated = 0 74.12.893.626 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 1761, progress = 0.84, t = 42.60 s / 41.34 tokens per second 74.13.002.225 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 74.13.002.295 I slot launch_slot_: id 3 | task 9132 | processing task, is_child = 0 74.13.002.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.460 MiB) 74.17.310.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 798.024 MiB) 74.19.555.331 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 107527823833 74.19.555.721 I slot launch_slot_: id 1 | task 9133 | processing task, is_child = 0 74.19.555.782 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 107527824827 74.19.555.874 I slot launch_slot_: id 2 | task 9134 | processing task, is_child = 0 74.19.555.887 I slot print_timing: id 0 | task 9126 | prompt processing, n_tokens = 2090, progress = 1.00, t = 42.72 s / 48.92 tokens per second 74.32.548.518 I slot print_timing: id 1 | task 9133 | prompt processing, n_tokens = 372, progress = 0.18, t = 12.97 s / 28.68 tokens per second 74.32.557.700 I slot print_timing: id 2 | task 9134 | prompt processing, n_tokens = 372, progress = 0.18, t = 12.97 s / 28.68 tokens per second 74.32.589.596 I slot print_timing: id 3 | task 9132 | prompt processing, n_tokens = 276, progress = 1.00, t = 12.97 s / 21.28 tokens per second 74.39.764.405 I slot print_timing: id 0 | task 9126 | prompt eval time = 62269.36 ms / 2094 tokens ( 29.74 ms per token, 33.63 tokens per second) 74.39.764.407 I slot print_timing: id 0 | task 9126 | eval time = 7216.86 ms / 2 tokens ( 7216.86 ms per token, 0.14 tokens per second) 74.39.764.408 I slot print_timing: id 0 | task 9126 | total time = 69486.21 ms / 2096 tokens 74.39.764.409 I slot print_timing: id 0 | task 9126 | graphs reused = 7735 74.39.764.409 I slot print_timing: id 0 | task 9126 | graph reallocs = 0 / 0 (same size) / (changed size) 74.39.766.549 I slot release: id 0 | task 9126 | stop processing: n_tokens = 2095, truncated = 0 74.39.849.930 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 74.39.850.021 I slot launch_slot_: id 0 | task 9137 | processing task, is_child = 0 74.39.860.788 I slot print_timing: id 1 | task 9133 | prompt processing, n_tokens = 640, progress = 0.30, t = 20.19 s / 31.70 tokens per second 74.39.860.811 I slot print_timing: id 2 | task 9134 | prompt processing, n_tokens = 640, progress = 0.31, t = 20.19 s / 31.70 tokens per second 75.05.064.789 I slot print_timing: id 3 | task 9132 | prompt eval time = 20272.18 ms / 280 tokens ( 72.40 ms per token, 13.81 tokens per second) 75.05.064.793 I slot print_timing: id 3 | task 9132 | eval time = 25213.79 ms / 2 tokens (25213.79 ms per token, 0.04 tokens per second) 75.05.064.794 I slot print_timing: id 3 | task 9132 | total time = 45485.97 ms / 282 tokens 75.05.064.795 I slot print_timing: id 3 | task 9132 | graphs reused = 7735 75.05.064.795 I slot print_timing: id 3 | task 9132 | graph reallocs = 0 / 0 (same size) / (changed size) 75.05.066.413 I slot release: id 3 | task 9132 | stop processing: n_tokens = 2042, truncated = 0 75.05.066.450 I slot print_timing: id 0 | task 9137 | prompt processing, n_tokens = 365, progress = 1.00, t = 25.21 s / 14.48 tokens per second 75.05.081.850 I slot print_timing: id 1 | task 9133 | prompt processing, n_tokens = 1589, progress = 0.75, t = 45.49 s / 34.93 tokens per second 75.05.112.017 I slot print_timing: id 2 | task 9134 | prompt processing, n_tokens = 1373, progress = 0.67, t = 45.49 s / 30.19 tokens per second 75.09.986.039 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 75.09.986.107 I slot launch_slot_: id 3 | task 9140 | processing task, is_child = 0 75.09.986.114 I slot print_timing: id 1 | task 9133 | prompt processing, n_tokens = 1761, progress = 0.84, t = 50.41 s / 34.93 tokens per second 75.10.002.902 I slot print_timing: id 2 | task 9134 | prompt processing, n_tokens = 1541, progress = 0.75, t = 50.41 s / 30.57 tokens per second 75.21.228.515 I slot print_timing: id 0 | task 9137 | prompt eval time = 30136.00 ms / 369 tokens ( 81.67 ms per token, 12.24 tokens per second) 75.21.228.518 I slot print_timing: id 0 | task 9137 | eval time = 11242.48 ms / 2 tokens (11242.48 ms per token, 0.09 tokens per second) 75.21.228.518 I slot print_timing: id 0 | task 9137 | total time = 41378.47 ms / 371 tokens 75.21.228.519 I slot print_timing: id 0 | task 9137 | graphs reused = 7735 75.21.228.519 I slot print_timing: id 0 | task 9137 | graph reallocs = 0 / 0 (same size) / (changed size) 75.21.228.675 I slot release: id 0 | task 9137 | stop processing: n_tokens = 2131, truncated = 0 75.21.228.695 I slot print_timing: id 1 | task 9133 | prompt processing, n_tokens = 2101, progress = 1.00, t = 61.65 s / 34.08 tokens per second 75.21.240.813 I slot print_timing: id 2 | task 9134 | prompt processing, n_tokens = 1761, progress = 0.86, t = 61.65 s / 28.56 tokens per second 75.21.256.022 I slot print_timing: id 3 | task 9140 | prompt processing, n_tokens = 296, progress = 1.00, t = 11.21 s / 26.40 tokens per second 75.25.193.785 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 75.25.193.867 I slot launch_slot_: id 0 | task 9143 | processing task, is_child = 0 75.25.202.984 I slot print_timing: id 2 | task 9134 | prompt processing, n_tokens = 2053, progress = 1.00, t = 65.62 s / 31.29 tokens per second 75.30.328.127 I slot print_timing: id 1 | task 9133 | prompt eval time = 65615.87 ms / 2105 tokens ( 31.17 ms per token, 32.08 tokens per second) 75.30.328.132 I slot print_timing: id 1 | task 9133 | eval time = 5134.77 ms / 2 tokens ( 5134.77 ms per token, 0.19 tokens per second) 75.30.328.133 I slot print_timing: id 1 | task 9133 | total time = 70750.64 ms / 2107 tokens 75.30.328.133 I slot print_timing: id 1 | task 9133 | graphs reused = 7735 75.30.328.133 I slot print_timing: id 1 | task 9133 | graph reallocs = 0 / 0 (same size) / (changed size) 75.30.329.321 I slot release: id 1 | task 9133 | stop processing: n_tokens = 2106, truncated = 0 75.30.330.177 I slot print_timing: id 3 | task 9140 | prompt eval time = 15176.59 ms / 300 tokens ( 50.59 ms per token, 19.77 tokens per second) 75.30.330.181 I slot print_timing: id 3 | task 9140 | eval time = 5136.40 ms / 2 tokens ( 5136.40 ms per token, 0.19 tokens per second) 75.30.330.184 I slot print_timing: id 3 | task 9140 | total time = 20312.99 ms / 302 tokens 75.30.330.187 I slot print_timing: id 3 | task 9140 | graphs reused = 7735 75.30.330.187 I slot print_timing: id 3 | task 9140 | graph reallocs = 0 / 0 (same size) / (changed size) 75.30.331.266 I slot release: id 3 | task 9140 | stop processing: n_tokens = 2062, truncated = 0 75.30.331.296 I slot print_timing: id 0 | task 9143 | prompt processing, n_tokens = 376, progress = 1.00, t = 5.13 s / 73.24 tokens per second 75.30.674.587 I slot print_timing: id 2 | task 9134 | prompt eval time = 70752.07 ms / 2057 tokens ( 34.40 ms per token, 29.07 tokens per second) 75.30.674.590 I slot print_timing: id 2 | task 9134 | eval time = 344.87 ms / 2 tokens ( 344.87 ms per token, 2.90 tokens per second) 75.30.674.591 I slot print_timing: id 2 | task 9134 | total time = 71096.94 ms / 2059 tokens 75.30.674.591 I slot print_timing: id 2 | task 9134 | graphs reused = 7735 75.30.674.592 I slot print_timing: id 2 | task 9134 | graph reallocs = 0 / 0 (same size) / (changed size) 75.30.675.890 I slot release: id 2 | task 9134 | stop processing: n_tokens = 2058, truncated = 0 75.30.675.912 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 75.30.675.981 I slot launch_slot_: id 1 | task 9146 | processing task, is_child = 0 75.30.676.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.398 MiB) 75.32.090.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.023 MiB) 75.32.095.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 795.398 MiB) 75.33.916.704 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.870 75.33.917.094 I slot launch_slot_: id 2 | task 9147 | processing task, is_child = 0 75.33.917.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.868 75.33.917.247 I slot launch_slot_: id 3 | task 9148 | processing task, is_child = 0 75.46.179.506 I slot print_timing: id 0 | task 9143 | prompt eval time = 5480.51 ms / 380 tokens ( 14.42 ms per token, 69.34 tokens per second) 75.46.179.509 I slot print_timing: id 0 | task 9143 | eval time = 15505.11 ms / 2 tokens (15505.11 ms per token, 0.06 tokens per second) 75.46.179.509 I slot print_timing: id 0 | task 9143 | total time = 20985.62 ms / 382 tokens 75.46.179.510 I slot print_timing: id 0 | task 9143 | graphs reused = 7735 75.46.179.510 I slot print_timing: id 0 | task 9143 | graph reallocs = 0 / 0 (same size) / (changed size) 75.46.179.691 I slot release: id 0 | task 9143 | stop processing: n_tokens = 2142, truncated = 0 75.46.179.714 I slot print_timing: id 1 | task 9146 | prompt processing, n_tokens = 206, progress = 1.00, t = 12.26 s / 16.80 tokens per second 75.46.195.263 I slot print_timing: id 2 | task 9147 | prompt processing, n_tokens = 463, progress = 1.00, t = 12.21 s / 37.91 tokens per second 75.46.209.335 I slot print_timing: id 3 | task 9148 | prompt processing, n_tokens = 254, progress = 1.00, t = 12.20 s / 20.81 tokens per second 75.46.674.813 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.835 75.46.674.893 I slot launch_slot_: id 0 | task 9151 | processing task, is_child = 0 75.49.997.200 I slot print_timing: id 1 | task 9146 | prompt eval time = 12756.55 ms / 210 tokens ( 60.75 ms per token, 16.46 tokens per second) 75.49.997.205 I slot print_timing: id 1 | task 9146 | eval time = 3322.21 ms / 2 tokens ( 3322.21 ms per token, 0.30 tokens per second) 75.49.997.206 I slot print_timing: id 1 | task 9146 | total time = 16078.76 ms / 212 tokens 75.49.997.207 I slot print_timing: id 1 | task 9146 | graphs reused = 7735 75.49.997.207 I slot print_timing: id 1 | task 9146 | graph reallocs = 0 / 0 (same size) / (changed size) 75.49.998.247 I slot release: id 1 | task 9146 | stop processing: n_tokens = 1972, truncated = 0 75.49.998.765 I slot print_timing: id 2 | task 9147 | prompt eval time = 12708.48 ms / 467 tokens ( 27.21 ms per token, 36.75 tokens per second) 75.49.998.768 I slot print_timing: id 2 | task 9147 | eval time = 3324.59 ms / 2 tokens ( 3324.59 ms per token, 0.30 tokens per second) 75.49.998.768 I slot print_timing: id 2 | task 9147 | total time = 16033.07 ms / 469 tokens 75.49.998.769 I slot print_timing: id 2 | task 9147 | graphs reused = 7735 75.49.998.769 I slot print_timing: id 2 | task 9147 | graph reallocs = 0 / 0 (same size) / (changed size) 75.49.998.943 I slot release: id 2 | task 9147 | stop processing: n_tokens = 2229, truncated = 0 75.49.999.549 I slot print_timing: id 3 | task 9148 | prompt eval time = 12699.45 ms / 258 tokens ( 49.22 ms per token, 20.32 tokens per second) 75.49.999.553 I slot print_timing: id 3 | task 9148 | eval time = 3324.78 ms / 2 tokens ( 3324.78 ms per token, 0.30 tokens per second) 75.49.999.553 I slot print_timing: id 3 | task 9148 | total time = 16024.23 ms / 260 tokens 75.49.999.554 I slot print_timing: id 3 | task 9148 | graphs reused = 7735 75.49.999.554 I slot print_timing: id 3 | task 9148 | graph reallocs = 0 / 0 (same size) / (changed size) 75.50.000.775 I slot release: id 3 | task 9148 | stop processing: n_tokens = 2020, truncated = 0 75.50.000.785 I slot print_timing: id 0 | task 9151 | prompt processing, n_tokens = 249, progress = 1.00, t = 3.32 s / 74.98 tokens per second 75.50.226.177 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.907 75.50.226.218 I slot launch_slot_: id 1 | task 9154 | processing task, is_child = 0 75.50.226.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.898 MiB) 75.51.736.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.028 MiB) 75.54.434.624 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.803 75.54.434.707 I slot launch_slot_: id 2 | task 9155 | processing task, is_child = 0 75.54.434.812 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.886 75.54.434.834 I slot launch_slot_: id 3 | task 9156 | processing task, is_child = 0 76.05.982.625 I slot print_timing: id 0 | task 9151 | prompt eval time = 3551.26 ms / 253 tokens ( 14.04 ms per token, 71.24 tokens per second) 76.05.982.628 I slot print_timing: id 0 | task 9151 | eval time = 15756.44 ms / 2 tokens (15756.44 ms per token, 0.06 tokens per second) 76.05.982.629 I slot print_timing: id 0 | task 9151 | total time = 19307.70 ms / 255 tokens 76.05.982.629 I slot print_timing: id 0 | task 9151 | graphs reused = 7735 76.05.982.629 I slot print_timing: id 0 | task 9151 | graph reallocs = 0 / 0 (same size) / (changed size) 76.05.983.725 I slot release: id 0 | task 9151 | stop processing: n_tokens = 2015, truncated = 0 76.05.983.769 I slot print_timing: id 1 | task 9154 | prompt processing, n_tokens = 208, progress = 1.00, t = 11.55 s / 18.01 tokens per second 76.06.001.505 I slot print_timing: id 2 | task 9155 | prompt processing, n_tokens = 300, progress = 1.00, t = 11.52 s / 26.03 tokens per second 76.06.015.860 I slot print_timing: id 3 | task 9156 | prompt processing, n_tokens = 341, progress = 1.00, t = 11.51 s / 29.61 tokens per second 76.06.480.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.888 76.06.480.924 I slot launch_slot_: id 0 | task 9159 | processing task, is_child = 0 76.10.557.200 I slot print_timing: id 1 | task 9154 | prompt eval time = 12045.24 ms / 212 tokens ( 56.82 ms per token, 17.60 tokens per second) 76.10.557.203 I slot print_timing: id 1 | task 9154 | eval time = 4077.11 ms / 2 tokens ( 4077.11 ms per token, 0.25 tokens per second) 76.10.557.204 I slot print_timing: id 1 | task 9154 | total time = 16122.35 ms / 214 tokens 76.10.557.204 I slot print_timing: id 1 | task 9154 | graphs reused = 7735 76.10.557.205 I slot print_timing: id 1 | task 9154 | graph reallocs = 0 / 0 (same size) / (changed size) 76.10.558.370 I slot release: id 1 | task 9154 | stop processing: n_tokens = 1974, truncated = 0 76.10.559.181 I slot print_timing: id 2 | task 9155 | prompt eval time = 12022.94 ms / 304 tokens ( 39.55 ms per token, 25.28 tokens per second) 76.10.559.188 I slot print_timing: id 2 | task 9155 | eval time = 4078.73 ms / 2 tokens ( 4078.73 ms per token, 0.25 tokens per second) 76.10.559.189 I slot print_timing: id 2 | task 9155 | total time = 16101.68 ms / 306 tokens 76.10.559.189 I slot print_timing: id 2 | task 9155 | graphs reused = 7735 76.10.559.189 I slot print_timing: id 2 | task 9155 | graph reallocs = 0 / 0 (same size) / (changed size) 76.10.560.805 I slot release: id 2 | task 9155 | stop processing: n_tokens = 2066, truncated = 0 76.10.561.603 I slot print_timing: id 3 | task 9156 | prompt eval time = 12013.19 ms / 345 tokens ( 34.82 ms per token, 28.72 tokens per second) 76.10.561.606 I slot print_timing: id 3 | task 9156 | eval time = 4080.79 ms / 2 tokens ( 4080.79 ms per token, 0.25 tokens per second) 76.10.561.607 I slot print_timing: id 3 | task 9156 | total time = 16093.98 ms / 347 tokens 76.10.561.607 I slot print_timing: id 3 | task 9156 | graphs reused = 7735 76.10.561.607 I slot print_timing: id 3 | task 9156 | graph reallocs = 0 / 0 (same size) / (changed size) 76.10.562.359 I slot release: id 3 | task 9156 | stop processing: n_tokens = 2107, truncated = 0 76.10.562.372 I slot print_timing: id 0 | task 9159 | prompt processing, n_tokens = 300, progress = 1.00, t = 4.08 s / 73.60 tokens per second 76.10.783.346 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.866 76.10.783.415 I slot launch_slot_: id 2 | task 9162 | processing task, is_child = 0 76.10.783.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 807.903 MiB) 76.12.159.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.091 MiB) 76.14.323.568 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.850 76.14.323.639 I slot launch_slot_: id 3 | task 9163 | processing task, is_child = 0 76.14.323.743 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.906 76.14.329.323 I slot launch_slot_: id 1 | task 9164 | processing task, is_child = 0 76.26.965.657 I slot print_timing: id 0 | task 9159 | prompt eval time = 4302.40 ms / 304 tokens ( 14.15 ms per token, 70.66 tokens per second) 76.26.965.664 I slot print_timing: id 0 | task 9159 | eval time = 16182.30 ms / 2 tokens (16182.30 ms per token, 0.06 tokens per second) 76.26.965.664 I slot print_timing: id 0 | task 9159 | total time = 20484.71 ms / 306 tokens 76.26.965.665 I slot print_timing: id 0 | task 9159 | graphs reused = 7735 76.26.965.665 I slot print_timing: id 0 | task 9159 | graph reallocs = 0 / 0 (same size) / (changed size) 76.26.967.277 I slot release: id 0 | task 9159 | stop processing: n_tokens = 2066, truncated = 0 76.26.967.317 I slot print_timing: id 1 | task 9164 | prompt processing, n_tokens = 401, progress = 1.00, t = 12.64 s / 31.73 tokens per second 76.27.008.610 I slot print_timing: id 2 | task 9162 | prompt processing, n_tokens = 349, progress = 1.00, t = 12.63 s / 27.64 tokens per second 76.27.031.598 I slot print_timing: id 3 | task 9163 | prompt processing, n_tokens = 206, progress = 1.00, t = 12.62 s / 16.33 tokens per second 76.27.517.789 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.866 76.27.517.867 I slot launch_slot_: id 0 | task 9167 | processing task, is_child = 0 76.32.746.293 I slot print_timing: id 1 | task 9164 | prompt eval time = 13188.11 ms / 405 tokens ( 32.56 ms per token, 30.71 tokens per second) 76.32.746.296 I slot print_timing: id 1 | task 9164 | eval time = 5228.85 ms / 2 tokens ( 5228.85 ms per token, 0.19 tokens per second) 76.32.746.297 I slot print_timing: id 1 | task 9164 | total time = 18416.96 ms / 407 tokens 76.32.746.298 I slot print_timing: id 1 | task 9164 | graphs reused = 7735 76.32.746.298 I slot print_timing: id 1 | task 9164 | graph reallocs = 0 / 0 (same size) / (changed size) 76.32.749.510 I slot release: id 1 | task 9164 | stop processing: n_tokens = 2167, truncated = 0 76.32.749.967 I slot print_timing: id 2 | task 9162 | prompt eval time = 13178.67 ms / 353 tokens ( 37.33 ms per token, 26.79 tokens per second) 76.32.749.971 I slot print_timing: id 2 | task 9162 | eval time = 5232.36 ms / 2 tokens ( 5232.36 ms per token, 0.19 tokens per second) 76.32.749.971 I slot print_timing: id 2 | task 9162 | total time = 18411.03 ms / 355 tokens 76.32.749.972 I slot print_timing: id 2 | task 9162 | graphs reused = 7735 76.32.749.972 I slot print_timing: id 2 | task 9162 | graph reallocs = 0 / 0 (same size) / (changed size) 76.32.751.322 I slot release: id 2 | task 9162 | stop processing: n_tokens = 2115, truncated = 0 76.32.751.753 I slot print_timing: id 3 | task 9163 | prompt eval time = 13170.03 ms / 210 tokens ( 62.71 ms per token, 15.95 tokens per second) 76.32.751.759 I slot print_timing: id 3 | task 9163 | eval time = 5233.97 ms / 2 tokens ( 5233.97 ms per token, 0.19 tokens per second) 76.32.751.759 I slot print_timing: id 3 | task 9163 | total time = 18404.00 ms / 212 tokens 76.32.751.760 I slot print_timing: id 3 | task 9163 | graphs reused = 7735 76.32.751.760 I slot print_timing: id 3 | task 9163 | graph reallocs = 0 / 0 (same size) / (changed size) 76.32.751.859 I slot release: id 3 | task 9163 | stop processing: n_tokens = 1972, truncated = 0 76.32.751.883 I slot print_timing: id 0 | task 9167 | prompt processing, n_tokens = 409, progress = 1.00, t = 5.23 s / 78.23 tokens per second 76.32.971.908 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.826 76.32.971.951 I slot launch_slot_: id 1 | task 9170 | processing task, is_child = 0 76.32.972.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 813.467 MiB) 76.34.822.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 820.783 MiB) 76.37.237.819 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.846 76.37.237.917 I slot launch_slot_: id 2 | task 9171 | processing task, is_child = 0 76.37.238.113 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.907 76.37.238.167 I slot launch_slot_: id 3 | task 9172 | processing task, is_child = 0 76.47.252.742 I slot print_timing: id 0 | task 9167 | prompt eval time = 5454.02 ms / 413 tokens ( 13.21 ms per token, 75.72 tokens per second) 76.47.252.745 I slot print_timing: id 0 | task 9167 | eval time = 14280.83 ms / 2 tokens (14280.83 ms per token, 0.07 tokens per second) 76.47.252.745 I slot print_timing: id 0 | task 9167 | total time = 19734.86 ms / 415 tokens 76.47.252.746 I slot print_timing: id 0 | task 9167 | graphs reused = 7735 76.47.252.746 I slot print_timing: id 0 | task 9167 | graph reallocs = 0 / 0 (same size) / (changed size) 76.47.254.738 I slot release: id 0 | task 9167 | stop processing: n_tokens = 2175, truncated = 0 76.47.254.781 I slot print_timing: id 1 | task 9170 | prompt processing, n_tokens = 268, progress = 1.00, t = 10.01 s / 26.76 tokens per second 76.47.291.813 I slot print_timing: id 2 | task 9171 | prompt processing, n_tokens = 260, progress = 1.00, t = 9.99 s / 26.02 tokens per second 76.47.306.392 I slot print_timing: id 3 | task 9172 | prompt processing, n_tokens = 232, progress = 1.00, t = 9.96 s / 23.29 tokens per second 76.48.286.809 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.823 76.48.286.879 I slot launch_slot_: id 0 | task 9175 | processing task, is_child = 0 76.50.469.754 I slot print_timing: id 1 | task 9170 | prompt eval time = 11048.12 ms / 272 tokens ( 40.62 ms per token, 24.62 tokens per second) 76.50.469.756 I slot print_timing: id 1 | task 9170 | eval time = 2183.45 ms / 2 tokens ( 2183.45 ms per token, 0.46 tokens per second) 76.50.469.757 I slot print_timing: id 1 | task 9170 | total time = 13231.57 ms / 274 tokens 76.50.469.757 I slot print_timing: id 1 | task 9170 | graphs reused = 7735 76.50.469.757 I slot print_timing: id 1 | task 9170 | graph reallocs = 0 / 0 (same size) / (changed size) 76.50.471.252 I slot release: id 1 | task 9170 | stop processing: n_tokens = 2034, truncated = 0 76.50.471.679 I slot print_timing: id 2 | task 9171 | prompt eval time = 11025.97 ms / 264 tokens ( 41.77 ms per token, 23.94 tokens per second) 76.50.471.687 I slot print_timing: id 2 | task 9171 | eval time = 2185.21 ms / 2 tokens ( 2185.21 ms per token, 0.46 tokens per second) 76.50.471.689 I slot print_timing: id 2 | task 9171 | total time = 13211.17 ms / 266 tokens 76.50.471.690 I slot print_timing: id 2 | task 9171 | graphs reused = 7735 76.50.471.690 I slot print_timing: id 2 | task 9171 | graph reallocs = 0 / 0 (same size) / (changed size) 76.50.471.779 I slot release: id 2 | task 9171 | stop processing: n_tokens = 2026, truncated = 0 76.50.472.260 I slot print_timing: id 3 | task 9172 | prompt eval time = 10995.63 ms / 236 tokens ( 46.59 ms per token, 21.46 tokens per second) 76.50.472.263 I slot print_timing: id 3 | task 9172 | eval time = 2185.46 ms / 2 tokens ( 2185.46 ms per token, 0.46 tokens per second) 76.50.472.571 I slot print_timing: id 3 | task 9172 | total time = 13181.09 ms / 238 tokens 76.50.472.575 I slot print_timing: id 3 | task 9172 | graphs reused = 7735 76.50.472.575 I slot print_timing: id 3 | task 9172 | graph reallocs = 0 / 0 (same size) / (changed size) 76.50.473.954 I slot release: id 3 | task 9172 | stop processing: n_tokens = 1998, truncated = 0 76.50.696.618 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.880 76.50.696.667 I slot launch_slot_: id 1 | task 9178 | processing task, is_child = 0 76.50.696.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 818.469 MiB) 76.52.373.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 876.803 MiB) 76.55.049.838 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.884 76.55.049.949 I slot launch_slot_: id 2 | task 9179 | processing task, is_child = 0 76.55.050.053 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1998, t_last = 107685411577 76.55.050.165 I slot launch_slot_: id 3 | task 9180 | processing task, is_child = 0 77.05.742.681 I slot print_timing: id 0 | task 9175 | prompt eval time = 2409.72 ms / 149 tokens ( 16.17 ms per token, 61.83 tokens per second) 77.05.742.687 I slot print_timing: id 0 | task 9175 | eval time = 15046.07 ms / 2 tokens (15046.07 ms per token, 0.07 tokens per second) 77.05.742.688 I slot print_timing: id 0 | task 9175 | total time = 17455.79 ms / 151 tokens 77.05.742.688 I slot print_timing: id 0 | task 9175 | graphs reused = 7735 77.05.742.689 I slot print_timing: id 0 | task 9175 | graph reallocs = 0 / 0 (same size) / (changed size) 77.05.742.787 I slot release: id 0 | task 9175 | stop processing: n_tokens = 1911, truncated = 0 77.05.742.805 I slot print_timing: id 1 | task 9178 | prompt processing, n_tokens = 192, progress = 1.00, t = 10.69 s / 17.96 tokens per second 77.05.751.832 I slot print_timing: id 2 | task 9179 | prompt processing, n_tokens = 226, progress = 1.00, t = 10.65 s / 21.21 tokens per second 77.05.818.951 I slot print_timing: id 3 | task 9180 | prompt processing, n_tokens = 363, progress = 0.25, t = 10.64 s / 34.13 tokens per second 77.09.055.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 107700680410 77.09.056.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 877.053 MiB) 77.12.578.691 I slot launch_slot_: id 0 | task 9183 | processing task, is_child = 0 77.12.578.868 I slot print_timing: id 3 | task 9180 | prompt processing, n_tokens = 575, progress = 0.39, t = 13.91 s / 41.32 tokens per second 77.21.868.316 I slot print_timing: id 1 | task 9178 | prompt eval time = 14005.32 ms / 196 tokens ( 71.46 ms per token, 13.99 tokens per second) 77.21.868.320 I slot print_timing: id 1 | task 9178 | eval time = 12812.82 ms / 2 tokens (12812.82 ms per token, 0.08 tokens per second) 77.21.868.320 I slot print_timing: id 1 | task 9178 | total time = 26818.14 ms / 198 tokens 77.21.868.321 I slot print_timing: id 1 | task 9178 | graphs reused = 7735 77.21.868.321 I slot print_timing: id 1 | task 9178 | graph reallocs = 0 / 0 (same size) / (changed size) 77.21.868.789 I slot release: id 1 | task 9178 | stop processing: n_tokens = 1958, truncated = 0 77.21.869.042 I slot print_timing: id 2 | task 9179 | prompt eval time = 13968.09 ms / 230 tokens ( 60.73 ms per token, 16.47 tokens per second) 77.21.869.045 I slot print_timing: id 2 | task 9179 | eval time = 12813.11 ms / 2 tokens (12813.11 ms per token, 0.08 tokens per second) 77.21.869.046 I slot print_timing: id 2 | task 9179 | total time = 26781.20 ms / 232 tokens 77.21.869.046 I slot print_timing: id 2 | task 9179 | graphs reused = 7735 77.21.869.046 I slot print_timing: id 2 | task 9179 | graph reallocs = 0 / 0 (same size) / (changed size) 77.21.869.129 I slot release: id 2 | task 9179 | stop processing: n_tokens = 1992, truncated = 0 77.21.869.145 I slot print_timing: id 0 | task 9183 | prompt processing, n_tokens = 363, progress = 0.22, t = 9.29 s / 39.08 tokens per second 77.21.885.526 I slot print_timing: id 3 | task 9180 | prompt processing, n_tokens = 959, progress = 0.65, t = 26.76 s / 35.83 tokens per second 77.24.577.478 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 107716806412 77.24.577.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 887.495 MiB) 77.28.503.993 I slot launch_slot_: id 1 | task 9186 | processing task, is_child = 0 77.28.504.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.427 MiB) 77.31.128.707 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 107716806753 77.31.128.887 I slot launch_slot_: id 2 | task 9187 | processing task, is_child = 0 77.31.128.895 I slot print_timing: id 0 | task 9183 | prompt processing, n_tokens = 575, progress = 0.34, t = 12.00 s / 47.92 tokens per second 77.31.129.318 I slot print_timing: id 3 | task 9180 | prompt processing, n_tokens = 1275, progress = 0.86, t = 29.47 s / 43.26 tokens per second 77.47.695.307 I slot print_timing: id 0 | task 9183 | prompt processing, n_tokens = 1161, progress = 0.69, t = 35.12 s / 33.06 tokens per second 77.49.222.216 I slot print_timing: id 1 | task 9186 | prompt processing, n_tokens = 261, progress = 0.26, t = 16.57 s / 15.75 tokens per second 77.49.263.270 I slot print_timing: id 2 | task 9187 | prompt processing, n_tokens = 363, progress = 0.23, t = 16.57 s / 21.91 tokens per second 77.49.294.018 I slot print_timing: id 3 | task 9180 | prompt processing, n_tokens = 1471, progress = 1.00, t = 52.59 s / 27.97 tokens per second 77.56.040.341 I slot print_timing: id 0 | task 9183 | prompt processing, n_tokens = 1275, progress = 0.76, t = 43.46 s / 29.34 tokens per second 77.56.057.176 I slot print_timing: id 1 | task 9186 | prompt processing, n_tokens = 409, progress = 0.41, t = 24.91 s / 16.42 tokens per second 77.56.057.189 I slot print_timing: id 2 | task 9187 | prompt processing, n_tokens = 575, progress = 0.37, t = 24.91 s / 23.08 tokens per second 78.08.059.493 I slot print_timing: id 3 | task 9180 | prompt eval time = 60933.98 ms / 1475 tokens ( 41.31 ms per token, 24.21 tokens per second) 78.08.059.497 I slot print_timing: id 3 | task 9180 | eval time = 12019.55 ms / 2 tokens (12019.55 ms per token, 0.08 tokens per second) 78.08.059.497 I slot print_timing: id 3 | task 9180 | total time = 72953.53 ms / 1477 tokens 78.08.059.498 I slot print_timing: id 3 | task 9180 | graphs reused = 7735 78.08.059.498 I slot print_timing: id 3 | task 9180 | graph reallocs = 0 / 0 (same size) / (changed size) 78.08.069.194 I slot release: id 3 | task 9180 | stop processing: n_tokens = 1476, truncated = 0 78.08.069.211 I slot print_timing: id 0 | task 9183 | prompt processing, n_tokens = 1673, progress = 1.00, t = 55.48 s / 30.15 tokens per second 78.08.085.510 I slot print_timing: id 1 | task 9186 | prompt processing, n_tokens = 483, progress = 0.48, t = 36.93 s / 13.08 tokens per second 78.08.100.193 I slot print_timing: id 2 | task 9187 | prompt processing, n_tokens = 1039, progress = 0.67, t = 36.93 s / 28.13 tokens per second 78.16.193.449 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 107763006817 78.16.194.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.551 MiB) 78.17.998.129 I slot launch_slot_: id 3 | task 9192 | processing task, is_child = 0 78.17.998.159 I slot print_timing: id 1 | task 9186 | prompt processing, n_tokens = 853, progress = 0.85, t = 45.06 s / 18.93 tokens per second 78.18.026.075 I slot print_timing: id 2 | task 9187 | prompt processing, n_tokens = 1275, progress = 0.82, t = 45.06 s / 28.29 tokens per second 78.27.224.885 I slot print_timing: id 0 | task 9183 | prompt eval time = 63614.72 ms / 1677 tokens ( 37.93 ms per token, 26.36 tokens per second) 78.27.224.892 I slot print_timing: id 0 | task 9183 | eval time = 11031.42 ms / 2 tokens (11031.42 ms per token, 0.09 tokens per second) 78.27.224.893 I slot print_timing: id 0 | task 9183 | total time = 74646.15 ms / 1679 tokens 78.27.224.893 I slot print_timing: id 0 | task 9183 | graphs reused = 7735 78.27.224.894 I slot print_timing: id 0 | task 9183 | graph reallocs = 0 / 0 (same size) / (changed size) 78.27.229.389 I slot release: id 0 | task 9183 | stop processing: n_tokens = 1678, truncated = 0 78.27.229.432 I slot print_timing: id 1 | task 9186 | prompt processing, n_tokens = 995, progress = 1.00, t = 56.10 s / 17.74 tokens per second 78.27.245.387 I slot print_timing: id 2 | task 9187 | prompt processing, n_tokens = 1551, progress = 1.00, t = 56.10 s / 27.65 tokens per second 78.27.259.204 I slot print_timing: id 3 | task 9192 | prompt processing, n_tokens = 261, progress = 0.26, t = 9.15 s / 28.53 tokens per second 78.29.633.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 107782167013 78.29.633.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 879.867 MiB) 78.32.324.736 I slot launch_slot_: id 0 | task 9195 | processing task, is_child = 0 78.32.324.886 I slot print_timing: id 3 | task 9192 | prompt processing, n_tokens = 409, progress = 0.41, t = 11.56 s / 35.39 tokens per second 78.36.853.117 I slot print_timing: id 1 | task 9186 | prompt eval time = 58504.45 ms / 999 tokens ( 58.56 ms per token, 17.08 tokens per second) 78.36.853.120 I slot print_timing: id 1 | task 9186 | eval time = 7219.75 ms / 2 tokens ( 7219.75 ms per token, 0.14 tokens per second) 78.36.853.121 I slot print_timing: id 1 | task 9186 | total time = 65724.20 ms / 1001 tokens 78.36.853.121 I slot print_timing: id 1 | task 9186 | graphs reused = 7735 78.36.853.122 I slot print_timing: id 1 | task 9186 | graph reallocs = 0 / 0 (same size) / (changed size) 78.36.855.997 I slot release: id 1 | task 9186 | stop processing: n_tokens = 1000, truncated = 0 78.36.857.147 I slot print_timing: id 2 | task 9187 | prompt eval time = 58504.58 ms / 1555 tokens ( 37.62 ms per token, 26.58 tokens per second) 78.36.857.151 I slot print_timing: id 2 | task 9187 | eval time = 7223.39 ms / 2 tokens ( 7223.39 ms per token, 0.14 tokens per second) 78.36.857.152 I slot print_timing: id 2 | task 9187 | total time = 65727.96 ms / 1557 tokens 78.36.857.152 I slot print_timing: id 2 | task 9187 | graphs reused = 7735 78.36.857.154 I slot print_timing: id 2 | task 9187 | graph reallocs = 0 / 0 (same size) / (changed size) 78.36.857.976 I slot release: id 2 | task 9187 | stop processing: n_tokens = 1556, truncated = 0 78.36.858.006 I slot print_timing: id 0 | task 9195 | prompt processing, n_tokens = 261, progress = 0.27, t = 4.53 s / 57.64 tokens per second 78.36.895.569 I slot print_timing: id 3 | task 9192 | prompt processing, n_tokens = 473, progress = 0.48, t = 18.78 s / 25.19 tokens per second 78.38.881.499 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.882 78.38.881.581 I slot launch_slot_: id 1 | task 9198 | processing task, is_child = 0 78.38.881.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 880.367 MiB) 78.43.504.306 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 107791795600 78.43.504.533 I slot launch_slot_: id 2 | task 9199 | processing task, is_child = 0 78.43.504.560 I slot print_timing: id 0 | task 9195 | prompt processing, n_tokens = 409, progress = 0.42, t = 6.56 s / 62.38 tokens per second 78.43.516.639 I slot print_timing: id 3 | task 9192 | prompt processing, n_tokens = 853, progress = 0.86, t = 20.81 s / 41.00 tokens per second 78.49.080.729 I slot print_timing: id 0 | task 9195 | prompt processing, n_tokens = 461, progress = 0.47, t = 16.76 s / 27.51 tokens per second 78.50.988.048 I slot print_timing: id 1 | task 9198 | prompt processing, n_tokens = 103, progress = 1.00, t = 5.58 s / 18.47 tokens per second 78.51.044.275 I slot print_timing: id 2 | task 9199 | prompt processing, n_tokens = 261, progress = 0.27, t = 5.56 s / 46.91 tokens per second 78.51.090.354 I slot print_timing: id 3 | task 9192 | prompt processing, n_tokens = 985, progress = 1.00, t = 31.00 s / 31.77 tokens per second 78.58.426.525 I slot print_timing: id 0 | task 9195 | prompt processing, n_tokens = 853, progress = 0.87, t = 26.10 s / 32.68 tokens per second 78.58.435.667 I slot print_timing: id 2 | task 9199 | prompt processing, n_tokens = 409, progress = 0.42, t = 14.91 s / 27.43 tokens per second 79.01.125.123 I slot print_timing: id 1 | task 9198 | prompt eval time = 14921.02 ms / 107 tokens ( 139.45 ms per token, 7.17 tokens per second) 79.01.125.125 I slot print_timing: id 1 | task 9198 | eval time = 2699.52 ms / 2 tokens ( 2699.52 ms per token, 0.37 tokens per second) 79.01.125.126 I slot print_timing: id 1 | task 9198 | total time = 17620.54 ms / 109 tokens 79.01.125.126 I slot print_timing: id 1 | task 9198 | graphs reused = 7735 79.01.125.127 I slot print_timing: id 1 | task 9198 | graph reallocs = 0 / 0 (same size) / (changed size) 79.01.125.262 I slot release: id 1 | task 9198 | stop processing: n_tokens = 961, truncated = 0 79.01.125.500 I slot print_timing: id 3 | task 9192 | prompt eval time = 40350.12 ms / 989 tokens ( 40.80 ms per token, 24.51 tokens per second) 79.01.125.502 I slot print_timing: id 3 | task 9192 | eval time = 2699.00 ms / 2 tokens ( 2699.00 ms per token, 0.37 tokens per second) 79.01.125.503 I slot print_timing: id 3 | task 9192 | total time = 43049.12 ms / 991 tokens 79.01.125.503 I slot print_timing: id 3 | task 9192 | graphs reused = 7735 79.01.125.503 I slot print_timing: id 3 | task 9192 | graph reallocs = 0 / 0 (same size) / (changed size) 79.01.126.387 I slot release: id 3 | task 9192 | stop processing: n_tokens = 990, truncated = 0 79.01.126.411 I slot print_timing: id 0 | task 9195 | prompt processing, n_tokens = 973, progress = 1.00, t = 28.80 s / 33.78 tokens per second 79.01.133.294 I slot print_timing: id 2 | task 9199 | prompt processing, n_tokens = 467, progress = 0.48, t = 17.61 s / 26.52 tokens per second 79.06.309.886 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.917 79.06.310.124 I slot launch_slot_: id 1 | task 9204 | processing task, is_child = 0 79.06.310.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 871.426 MiB) 79.08.842.586 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 79.08.842.729 I slot launch_slot_: id 3 | task 9205 | processing task, is_child = 0 79.08.851.468 I slot print_timing: id 2 | task 9199 | prompt processing, n_tokens = 853, progress = 0.87, t = 22.79 s / 37.42 tokens per second 79.13.847.736 I slot print_timing: id 0 | task 9195 | prompt eval time = 33985.11 ms / 977 tokens ( 34.79 ms per token, 28.75 tokens per second) 79.13.847.742 I slot print_timing: id 0 | task 9195 | eval time = 7536.76 ms / 2 tokens ( 7536.76 ms per token, 0.13 tokens per second) 79.13.847.742 I slot print_timing: id 0 | task 9195 | total time = 41521.87 ms / 979 tokens 79.13.847.743 I slot print_timing: id 0 | task 9195 | graphs reused = 7735 79.13.847.744 I slot print_timing: id 0 | task 9195 | graph reallocs = 0 / 0 (same size) / (changed size) 79.13.848.708 I slot release: id 0 | task 9195 | stop processing: n_tokens = 978, truncated = 0 79.13.848.747 I slot print_timing: id 1 | task 9204 | prompt processing, n_tokens = 119, progress = 1.00, t = 5.00 s / 23.78 tokens per second 79.13.903.130 I slot print_timing: id 2 | task 9199 | prompt processing, n_tokens = 979, progress = 1.00, t = 30.33 s / 32.28 tokens per second 79.13.917.741 I slot print_timing: id 3 | task 9205 | prompt processing, n_tokens = 115, progress = 1.00, t = 4.99 s / 23.05 tokens per second 79.14.377.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 107828786332 79.14.377.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 874.802 MiB) 79.16.691.056 I slot launch_slot_: id 0 | task 9208 | processing task, is_child = 0 79.19.294.820 I slot print_timing: id 1 | task 9204 | prompt eval time = 5533.52 ms / 123 tokens ( 44.99 ms per token, 22.23 tokens per second) 79.19.294.823 I slot print_timing: id 1 | task 9204 | eval time = 4918.54 ms / 2 tokens ( 4918.54 ms per token, 0.20 tokens per second) 79.19.294.823 I slot print_timing: id 1 | task 9204 | total time = 10452.06 ms / 125 tokens 79.19.294.824 I slot print_timing: id 1 | task 9204 | graphs reused = 7735 79.19.294.824 I slot print_timing: id 1 | task 9204 | graph reallocs = 0 / 0 (same size) / (changed size) 79.19.294.967 I slot release: id 1 | task 9204 | stop processing: n_tokens = 977, truncated = 0 79.19.295.557 I slot print_timing: id 2 | task 9199 | prompt eval time = 30860.17 ms / 983 tokens ( 31.39 ms per token, 31.85 tokens per second) 79.19.295.560 I slot print_timing: id 2 | task 9199 | eval time = 4918.87 ms / 2 tokens ( 4918.87 ms per token, 0.20 tokens per second) 79.19.295.561 I slot print_timing: id 2 | task 9199 | total time = 35779.04 ms / 985 tokens 79.19.295.561 I slot print_timing: id 2 | task 9199 | graphs reused = 7735 79.19.295.561 I slot print_timing: id 2 | task 9199 | graph reallocs = 0 / 0 (same size) / (changed size) 79.19.295.604 I slot release: id 2 | task 9199 | stop processing: n_tokens = 984, truncated = 0 79.19.296.771 I slot print_timing: id 3 | task 9205 | prompt eval time = 5520.57 ms / 119 tokens ( 46.39 ms per token, 21.56 tokens per second) 79.19.296.779 I slot print_timing: id 3 | task 9205 | eval time = 4919.54 ms / 2 tokens ( 4919.54 ms per token, 0.20 tokens per second) 79.19.296.779 I slot print_timing: id 3 | task 9205 | total time = 10440.11 ms / 121 tokens 79.19.296.780 I slot print_timing: id 3 | task 9205 | graphs reused = 7735 79.19.296.780 I slot print_timing: id 3 | task 9205 | graph reallocs = 0 / 0 (same size) / (changed size) 79.19.296.834 I slot release: id 3 | task 9205 | stop processing: n_tokens = 973, truncated = 0 79.19.359.215 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 107834232590 79.19.359.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 873.052 MiB) 79.21.454.679 I slot launch_slot_: id 1 | task 9211 | processing task, is_child = 0 79.21.454.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 867.612 MiB) 79.23.705.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 870.551 MiB) 79.26.386.902 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 107834233226 79.26.387.088 I slot launch_slot_: id 2 | task 9212 | processing task, is_child = 0 79.26.387.154 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 107834234456 79.26.387.250 I slot launch_slot_: id 3 | task 9213 | processing task, is_child = 0 79.43.213.852 I slot print_timing: id 0 | task 9208 | prompt processing, n_tokens = 706, progress = 0.86, t = 26.52 s / 26.62 tokens per second 79.44.018.536 I slot print_timing: id 1 | task 9211 | prompt processing, n_tokens = 352, progress = 0.22, t = 16.80 s / 20.95 tokens per second 79.44.030.624 I slot print_timing: id 2 | task 9212 | prompt processing, n_tokens = 352, progress = 0.22, t = 16.80 s / 20.95 tokens per second 79.44.042.527 I slot print_timing: id 3 | task 9213 | prompt processing, n_tokens = 352, progress = 0.22, t = 16.80 s / 20.95 tokens per second 79.49.768.116 I slot print_timing: id 0 | task 9208 | prompt processing, n_tokens = 821, progress = 1.00, t = 33.08 s / 24.82 tokens per second 79.52.490.795 I slot print_timing: id 1 | task 9211 | prompt processing, n_tokens = 533, progress = 0.34, t = 23.36 s / 22.82 tokens per second 79.52.490.818 I slot print_timing: id 2 | task 9212 | prompt processing, n_tokens = 533, progress = 0.33, t = 23.36 s / 22.82 tokens per second 79.52.490.830 I slot print_timing: id 3 | task 9213 | prompt processing, n_tokens = 533, progress = 0.33, t = 23.36 s / 22.82 tokens per second 80.13.810.413 I slot print_timing: id 1 | task 9211 | prompt processing, n_tokens = 1071, progress = 0.67, t = 47.40 s / 22.60 tokens per second 80.13.826.812 I slot print_timing: id 2 | task 9212 | prompt processing, n_tokens = 1113, progress = 0.68, t = 47.40 s / 23.48 tokens per second 80.13.840.578 I slot print_timing: id 3 | task 9213 | prompt processing, n_tokens = 1099, progress = 0.68, t = 47.40 s / 23.19 tokens per second 80.24.922.104 I slot print_timing: id 0 | task 9208 | prompt eval time = 57119.33 ms / 825 tokens ( 69.24 ms per token, 14.44 tokens per second) 80.24.922.109 I slot print_timing: id 0 | task 9208 | eval time = 11111.70 ms / 2 tokens (11111.70 ms per token, 0.09 tokens per second) 80.24.922.110 I slot print_timing: id 0 | task 9208 | total time = 68231.03 ms / 827 tokens 80.24.922.110 I slot print_timing: id 0 | task 9208 | graphs reused = 7735 80.24.922.111 I slot print_timing: id 0 | task 9208 | graph reallocs = 0 / 0 (same size) / (changed size) 80.24.923.369 I slot release: id 0 | task 9208 | stop processing: n_tokens = 826, truncated = 0 80.24.923.408 I slot print_timing: id 1 | task 9211 | prompt processing, n_tokens = 1374, progress = 0.87, t = 58.51 s / 23.48 tokens per second 80.24.940.899 I slot print_timing: id 2 | task 9212 | prompt processing, n_tokens = 1374, progress = 0.84, t = 58.51 s / 23.48 tokens per second 80.24.955.879 I slot print_timing: id 3 | task 9213 | prompt processing, n_tokens = 1374, progress = 0.85, t = 58.51 s / 23.48 tokens per second 80.33.610.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 107899860994 80.33.610.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 872.677 MiB) 80.35.890.225 I slot launch_slot_: id 0 | task 9219 | processing task, is_child = 0 80.35.890.347 I slot print_timing: id 1 | task 9211 | prompt processing, n_tokens = 1583, progress = 1.00, t = 67.20 s / 23.56 tokens per second 80.35.902.199 I slot print_timing: id 2 | task 9212 | prompt processing, n_tokens = 1625, progress = 1.00, t = 67.20 s / 24.18 tokens per second 80.35.906.851 I slot print_timing: id 3 | task 9213 | prompt processing, n_tokens = 1611, progress = 1.00, t = 67.20 s / 23.97 tokens per second 80.40.680.811 I slot print_timing: id 0 | task 9219 | prompt processing, n_tokens = 352, progress = 0.22, t = 4.79 s / 73.51 tokens per second 80.43.212.748 I slot print_timing: id 1 | task 9211 | prompt eval time = 74269.10 ms / 1587 tokens ( 46.80 ms per token, 21.37 tokens per second) 80.43.212.751 I slot print_timing: id 1 | task 9211 | eval time = 2533.18 ms / 2 tokens ( 2533.18 ms per token, 0.39 tokens per second) 80.43.212.751 I slot print_timing: id 1 | task 9211 | total time = 76802.28 ms / 1589 tokens 80.43.212.752 I slot print_timing: id 1 | task 9211 | graphs reused = 7735 80.43.212.752 I slot print_timing: id 1 | task 9211 | graph reallocs = 0 / 0 (same size) / (changed size) 80.43.218.169 I slot release: id 1 | task 9211 | stop processing: n_tokens = 1588, truncated = 0 80.43.218.703 I slot print_timing: id 2 | task 9212 | prompt eval time = 74269.41 ms / 1629 tokens ( 45.59 ms per token, 21.93 tokens per second) 80.43.218.709 I slot print_timing: id 2 | task 9212 | eval time = 2538.70 ms / 2 tokens ( 2538.70 ms per token, 0.39 tokens per second) 80.43.218.710 I slot print_timing: id 2 | task 9212 | total time = 76808.11 ms / 1631 tokens 80.43.218.710 I slot print_timing: id 2 | task 9212 | graphs reused = 7735 80.43.218.711 I slot print_timing: id 2 | task 9212 | graph reallocs = 0 / 0 (same size) / (changed size) 80.43.219.350 I slot release: id 2 | task 9212 | stop processing: n_tokens = 1630, truncated = 0 80.43.219.933 I slot print_timing: id 3 | task 9213 | prompt eval time = 74270.11 ms / 1615 tokens ( 45.99 ms per token, 21.74 tokens per second) 80.43.219.938 I slot print_timing: id 3 | task 9213 | eval time = 2539.15 ms / 2 tokens ( 2539.15 ms per token, 0.39 tokens per second) 80.43.219.938 I slot print_timing: id 3 | task 9213 | total time = 76809.26 ms / 1617 tokens 80.43.219.939 I slot print_timing: id 3 | task 9213 | graphs reused = 7735 80.43.219.939 I slot print_timing: id 3 | task 9213 | graph reallocs = 0 / 0 (same size) / (changed size) 80.43.221.032 I slot release: id 3 | task 9213 | stop processing: n_tokens = 1616, truncated = 0 80.43.221.061 I slot print_timing: id 0 | task 9219 | prompt processing, n_tokens = 533, progress = 0.33, t = 7.32 s / 72.79 tokens per second 80.49.273.776 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1588, t_last = 107918155794 80.49.273.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 840.415 MiB) 80.51.435.268 I slot launch_slot_: id 1 | task 9223 | processing task, is_child = 0 80.51.435.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 853.044 MiB) 80.53.706.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 845.417 MiB) 80.56.211.753 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.860 80.56.211.841 I slot launch_slot_: id 2 | task 9224 | processing task, is_child = 0 80.56.211.928 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 107918158657 80.56.212.019 I slot launch_slot_: id 3 | task 9225 | processing task, is_child = 0 80.56.212.026 I slot print_timing: id 0 | task 9219 | prompt processing, n_tokens = 1113, progress = 0.68, t = 13.38 s / 83.16 tokens per second 81.04.464.512 I slot print_timing: id 0 | task 9219 | prompt processing, n_tokens = 1374, progress = 0.84, t = 28.57 s / 48.09 tokens per second 81.07.183.642 I slot print_timing: id 1 | task 9223 | prompt processing, n_tokens = 126, progress = 0.15, t = 8.17 s / 15.42 tokens per second 81.07.294.462 I slot print_timing: id 2 | task 9224 | prompt processing, n_tokens = 340, progress = 1.00, t = 8.17 s / 41.61 tokens per second 81.07.343.568 I slot print_timing: id 3 | task 9225 | prompt processing, n_tokens = 126, progress = 0.15, t = 8.09 s / 15.57 tokens per second 81.14.378.428 I slot print_timing: id 0 | task 9219 | prompt processing, n_tokens = 1625, progress = 1.00, t = 38.49 s / 42.22 tokens per second 81.14.395.608 I slot print_timing: id 1 | task 9223 | prompt processing, n_tokens = 245, progress = 0.29, t = 18.08 s / 13.55 tokens per second 81.14.395.618 I slot print_timing: id 3 | task 9225 | prompt processing, n_tokens = 245, progress = 0.28, t = 18.01 s / 13.60 tokens per second 81.17.529.268 I slot print_timing: id 2 | task 9224 | prompt eval time = 18084.08 ms / 344 tokens ( 52.57 ms per token, 19.02 tokens per second) 81.17.529.271 I slot print_timing: id 2 | task 9224 | eval time = 3150.85 ms / 2 tokens ( 3150.85 ms per token, 0.32 tokens per second) 81.17.529.272 I slot print_timing: id 2 | task 9224 | total time = 21234.93 ms / 346 tokens 81.17.529.272 I slot print_timing: id 2 | task 9224 | graphs reused = 7735 81.17.529.273 I slot print_timing: id 2 | task 9224 | graph reallocs = 0 / 0 (same size) / (changed size) 81.17.534.441 I slot release: id 2 | task 9224 | stop processing: n_tokens = 1719, truncated = 0 81.17.534.469 I slot print_timing: id 1 | task 9223 | prompt processing, n_tokens = 322, progress = 0.38, t = 21.23 s / 15.16 tokens per second 81.17.552.278 I slot print_timing: id 3 | task 9225 | prompt processing, n_tokens = 349, progress = 0.40, t = 21.16 s / 16.49 tokens per second 81.27.211.275 I slot print_timing: id 0 | task 9219 | prompt eval time = 41638.77 ms / 1629 tokens ( 25.56 ms per token, 39.12 tokens per second) 81.27.211.277 I slot print_timing: id 0 | task 9219 | eval time = 9682.25 ms / 2 tokens ( 9682.25 ms per token, 0.10 tokens per second) 81.27.211.282 I slot print_timing: id 0 | task 9219 | total time = 51321.02 ms / 1631 tokens 81.27.211.283 I slot print_timing: id 0 | task 9219 | graphs reused = 7735 81.27.211.283 I slot print_timing: id 0 | task 9219 | graph reallocs = 0 / 0 (same size) / (changed size) 81.27.211.373 I slot release: id 0 | task 9219 | stop processing: n_tokens = 1630, truncated = 0 81.27.211.382 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 107952472065 81.27.211.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 810.029 MiB) 81.29.536.528 I slot launch_slot_: id 2 | task 9230 | processing task, is_child = 0 81.29.536.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.278 MiB) 81.31.635.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 107962148996 81.31.636.287 I slot launch_slot_: id 0 | task 9231 | processing task, is_child = 0 81.31.636.447 I slot print_timing: id 1 | task 9223 | prompt processing, n_tokens = 725, progress = 0.87, t = 30.92 s / 23.45 tokens per second 81.31.643.703 I slot print_timing: id 3 | task 9225 | prompt processing, n_tokens = 725, progress = 0.84, t = 30.84 s / 23.51 tokens per second 81.38.827.710 I slot print_timing: id 0 | task 9231 | prompt processing, n_tokens = 149, progress = 0.17, t = 7.19 s / 20.72 tokens per second 81.39.231.380 I slot print_timing: id 1 | task 9223 | prompt processing, n_tokens = 834, progress = 1.00, t = 42.53 s / 19.61 tokens per second 81.39.281.760 I slot print_timing: id 2 | task 9230 | prompt processing, n_tokens = 149, progress = 0.18, t = 7.18 s / 20.74 tokens per second 81.39.346.773 I slot print_timing: id 3 | task 9225 | prompt processing, n_tokens = 861, progress = 1.00, t = 42.46 s / 20.28 tokens per second 81.42.937.388 I slot print_timing: id 0 | task 9231 | prompt processing, n_tokens = 277, progress = 0.32, t = 11.30 s / 24.52 tokens per second 81.42.937.413 I slot print_timing: id 2 | task 9230 | prompt processing, n_tokens = 277, progress = 0.33, t = 11.29 s / 24.53 tokens per second 81.45.241.333 I slot print_timing: id 1 | task 9223 | prompt eval time = 46640.85 ms / 838 tokens ( 55.66 ms per token, 17.97 tokens per second) 81.45.241.338 I slot print_timing: id 1 | task 9223 | eval time = 2306.29 ms / 2 tokens ( 2306.29 ms per token, 0.43 tokens per second) 81.45.241.339 I slot print_timing: id 1 | task 9223 | total time = 48947.14 ms / 840 tokens 81.45.241.339 I slot print_timing: id 1 | task 9223 | graphs reused = 7735 81.45.241.340 I slot print_timing: id 1 | task 9223 | graph reallocs = 0 / 0 (same size) / (changed size) 81.45.244.492 I slot release: id 1 | task 9223 | stop processing: n_tokens = 839, truncated = 0 81.45.244.972 I slot print_timing: id 3 | task 9225 | prompt eval time = 46566.31 ms / 865 tokens ( 53.83 ms per token, 18.58 tokens per second) 81.45.244.978 I slot print_timing: id 3 | task 9225 | eval time = 2309.09 ms / 2 tokens ( 2309.09 ms per token, 0.43 tokens per second) 81.45.244.978 I slot print_timing: id 3 | task 9225 | total time = 48875.40 ms / 867 tokens 81.45.244.979 I slot print_timing: id 3 | task 9225 | graphs reused = 7735 81.45.244.979 I slot print_timing: id 3 | task 9225 | graph reallocs = 0 / 0 (same size) / (changed size) 81.45.245.376 I slot release: id 3 | task 9225 | stop processing: n_tokens = 866, truncated = 0 81.45.245.396 I slot print_timing: id 0 | task 9231 | prompt processing, n_tokens = 343, progress = 0.40, t = 13.60 s / 25.21 tokens per second 81.45.258.488 I slot print_timing: id 2 | task 9230 | prompt processing, n_tokens = 326, progress = 0.39, t = 13.60 s / 23.98 tokens per second 81.49.804.481 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 107980182116 81.49.804.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.216 MiB) 81.54.719.895 I slot launch_slot_: id 1 | task 9236 | processing task, is_child = 0 81.54.719.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 809.654 MiB) 81.57.013.600 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 107980182998 81.57.013.746 I slot launch_slot_: id 3 | task 9237 | processing task, is_child = 0 81.57.013.765 I slot print_timing: id 0 | task 9231 | prompt processing, n_tokens = 716, progress = 0.83, t = 18.17 s / 39.41 tokens per second 81.57.081.745 I slot print_timing: id 2 | task 9230 | prompt processing, n_tokens = 716, progress = 0.85, t = 18.16 s / 39.43 tokens per second 82.04.492.418 I slot print_timing: id 0 | task 9231 | prompt processing, n_tokens = 855, progress = 1.00, t = 32.86 s / 26.02 tokens per second 82.04.683.458 I slot print_timing: id 1 | task 9236 | prompt processing, n_tokens = 149, progress = 0.17, t = 7.41 s / 20.11 tokens per second 82.04.711.520 I slot print_timing: id 2 | task 9230 | prompt processing, n_tokens = 838, progress = 1.00, t = 32.85 s / 25.51 tokens per second 82.04.764.246 I slot print_timing: id 3 | task 9237 | prompt processing, n_tokens = 125, progress = 0.16, t = 7.39 s / 16.92 tokens per second 82.08.741.913 I slot print_timing: id 1 | task 9236 | prompt processing, n_tokens = 277, progress = 0.31, t = 11.66 s / 23.76 tokens per second 82.08.741.934 I slot print_timing: id 3 | task 9237 | prompt processing, n_tokens = 260, progress = 0.33, t = 11.63 s / 22.35 tokens per second 82.10.525.263 I slot print_timing: id 0 | task 9231 | prompt eval time = 37105.17 ms / 859 tokens ( 43.20 ms per token, 23.15 tokens per second) 82.10.525.269 I slot print_timing: id 0 | task 9231 | eval time = 1783.79 ms / 2 tokens ( 1783.79 ms per token, 0.56 tokens per second) 82.10.525.269 I slot print_timing: id 0 | task 9231 | total time = 38888.95 ms / 861 tokens 82.10.525.270 I slot print_timing: id 0 | task 9231 | graphs reused = 7735 82.10.525.270 I slot print_timing: id 0 | task 9231 | graph reallocs = 0 / 0 (same size) / (changed size) 82.10.527.672 I slot release: id 0 | task 9231 | stop processing: n_tokens = 860, truncated = 0 82.10.528.065 I slot print_timing: id 2 | task 9230 | prompt eval time = 37098.31 ms / 842 tokens ( 44.06 ms per token, 22.70 tokens per second) 82.10.528.068 I slot print_timing: id 2 | task 9230 | eval time = 1786.18 ms / 2 tokens ( 1786.18 ms per token, 0.56 tokens per second) 82.10.528.069 I slot print_timing: id 2 | task 9230 | total time = 38884.49 ms / 844 tokens 82.10.528.069 I slot print_timing: id 2 | task 9230 | graphs reused = 7735 82.10.528.070 I slot print_timing: id 2 | task 9230 | graph reallocs = 0 / 0 (same size) / (changed size) 82.10.528.643 I slot release: id 2 | task 9230 | stop processing: n_tokens = 843, truncated = 0 82.10.528.663 I slot print_timing: id 1 | task 9236 | prompt processing, n_tokens = 370, progress = 0.42, t = 13.44 s / 27.52 tokens per second 82.10.534.673 I slot print_timing: id 3 | task 9237 | prompt processing, n_tokens = 264, progress = 0.34, t = 13.42 s / 19.67 tokens per second 82.14.780.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 108005465296 82.14.780.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 808.966 MiB) 82.19.390.464 I slot launch_slot_: id 0 | task 9242 | processing task, is_child = 0 82.19.390.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 799.775 MiB) 82.21.797.369 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 108005466267 82.21.797.896 I slot launch_slot_: id 2 | task 9243 | processing task, is_child = 0 82.21.798.016 I slot print_timing: id 1 | task 9236 | prompt processing, n_tokens = 716, progress = 0.81, t = 17.70 s / 40.45 tokens per second 82.21.825.319 I slot print_timing: id 3 | task 9237 | prompt processing, n_tokens = 628, progress = 0.81, t = 17.67 s / 35.53 tokens per second 82.28.903.642 I slot print_timing: id 0 | task 9242 | prompt processing, n_tokens = 125, progress = 0.17, t = 7.11 s / 17.59 tokens per second 82.29.701.336 I slot print_timing: id 1 | task 9236 | prompt processing, n_tokens = 882, progress = 1.00, t = 31.82 s / 27.72 tokens per second 82.29.765.040 I slot print_timing: id 2 | task 9243 | prompt processing, n_tokens = 113, progress = 0.16, t = 7.08 s / 15.96 tokens per second 82.29.809.355 I slot print_timing: id 3 | task 9237 | prompt processing, n_tokens = 776, progress = 0.99, t = 31.80 s / 24.40 tokens per second 82.32.628.672 I slot print_timing: id 0 | task 9242 | prompt processing, n_tokens = 233, progress = 0.31, t = 10.83 s / 21.52 tokens per second 82.32.657.131 I slot print_timing: id 2 | task 9243 | prompt processing, n_tokens = 175, progress = 0.25, t = 10.80 s / 16.20 tokens per second 82.42.811.836 I slot print_timing: id 1 | task 9236 | prompt eval time = 35546.18 ms / 886 tokens ( 40.12 ms per token, 24.93 tokens per second) 82.42.811.839 I slot print_timing: id 1 | task 9236 | eval time = 10184.03 ms / 2 tokens (10184.03 ms per token, 0.10 tokens per second) 82.42.811.839 I slot print_timing: id 1 | task 9236 | total time = 45730.21 ms / 888 tokens 82.42.811.840 I slot print_timing: id 1 | task 9236 | graphs reused = 7735 82.42.811.840 I slot print_timing: id 1 | task 9236 | graph reallocs = 0 / 0 (same size) / (changed size) 82.42.812.038 I slot release: id 1 | task 9236 | stop processing: n_tokens = 887, truncated = 0 82.42.813.468 I slot print_timing: id 3 | task 9237 | prompt eval time = 35522.00 ms / 780 tokens ( 45.54 ms per token, 21.96 tokens per second) 82.42.813.473 I slot print_timing: id 3 | task 9237 | eval time = 10183.68 ms / 2 tokens (10183.68 ms per token, 0.10 tokens per second) 82.42.813.474 I slot print_timing: id 3 | task 9237 | total time = 45705.67 ms / 782 tokens 82.42.813.475 I slot print_timing: id 3 | task 9237 | graphs reused = 7735 82.42.813.475 I slot print_timing: id 3 | task 9237 | graph reallocs = 0 / 0 (same size) / (changed size) 82.42.818.281 I slot release: id 3 | task 9237 | stop processing: n_tokens = 781, truncated = 0 82.42.818.297 I slot print_timing: id 0 | task 9242 | prompt processing, n_tokens = 628, progress = 0.84, t = 21.01 s / 29.89 tokens per second 82.42.874.067 I slot print_timing: id 2 | task 9243 | prompt processing, n_tokens = 571, progress = 0.83, t = 20.99 s / 27.21 tokens per second 82.44.443.128 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 108037749662 82.44.443.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 847.417 MiB) 82.46.606.926 I slot launch_slot_: id 1 | task 9248 | processing task, is_child = 0 82.46.606.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 850.043 MiB) 82.48.581.959 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 108037755905 82.48.582.117 I slot launch_slot_: id 3 | task 9249 | processing task, is_child = 0 82.48.582.133 I slot print_timing: id 0 | task 9242 | prompt processing, n_tokens = 745, progress = 0.99, t = 22.65 s / 32.90 tokens per second 82.48.609.865 I slot print_timing: id 2 | task 9243 | prompt processing, n_tokens = 687, progress = 0.99, t = 22.62 s / 30.37 tokens per second 82.52.338.507 I slot print_timing: id 1 | task 9248 | prompt processing, n_tokens = 113, progress = 0.17, t = 3.73 s / 30.31 tokens per second 82.52.353.871 I slot print_timing: id 3 | task 9249 | prompt processing, n_tokens = 113, progress = 0.16, t = 3.69 s / 30.58 tokens per second 82.54.758.440 I slot print_timing: id 0 | task 9242 | prompt eval time = 30540.32 ms / 749 tokens ( 40.77 ms per token, 24.52 tokens per second) 82.54.758.443 I slot print_timing: id 0 | task 9242 | eval time = 2420.21 ms / 2 tokens ( 2420.21 ms per token, 0.41 tokens per second) 82.54.758.443 I slot print_timing: id 0 | task 9242 | total time = 32960.53 ms / 751 tokens 82.54.758.444 I slot print_timing: id 0 | task 9242 | graphs reused = 7735 82.54.758.444 I slot print_timing: id 0 | task 9242 | graph reallocs = 0 / 0 (same size) / (changed size) 82.54.761.162 I slot release: id 0 | task 9242 | stop processing: n_tokens = 750, truncated = 0 82.54.761.520 I slot print_timing: id 2 | task 9243 | prompt eval time = 30513.26 ms / 691 tokens ( 44.16 ms per token, 22.65 tokens per second) 82.54.761.524 I slot print_timing: id 2 | task 9243 | eval time = 2423.02 ms / 2 tokens ( 2423.02 ms per token, 0.41 tokens per second) 82.54.761.524 I slot print_timing: id 2 | task 9243 | total time = 32936.28 ms / 693 tokens 82.54.761.525 I slot print_timing: id 2 | task 9243 | graphs reused = 7735 82.54.761.525 I slot print_timing: id 2 | task 9243 | graph reallocs = 0 / 0 (same size) / (changed size) 82.54.765.359 I slot release: id 2 | task 9243 | stop processing: n_tokens = 692, truncated = 0 82.54.765.382 I slot print_timing: id 1 | task 9248 | prompt processing, n_tokens = 162, progress = 0.24, t = 6.15 s / 26.35 tokens per second 82.54.821.250 I slot print_timing: id 3 | task 9249 | prompt processing, n_tokens = 196, progress = 0.28, t = 6.12 s / 32.05 tokens per second 82.59.787.235 I slot print_timing: id 1 | task 9248 | prompt processing, n_tokens = 571, progress = 0.84, t = 11.18 s / 51.08 tokens per second 83.04.311.533 I slot print_timing: id 3 | task 9249 | prompt processing, n_tokens = 571, progress = 0.80, t = 11.14 s / 51.24 tokens per second 83.05.876.041 I slot print_timing: id 1 | task 9248 | prompt processing, n_tokens = 674, progress = 0.99, t = 17.27 s / 39.04 tokens per second 83.07.797.134 I slot print_timing: id 3 | task 9249 | prompt processing, n_tokens = 708, progress = 0.99, t = 17.23 s / 41.08 tokens per second 83.08.458.519 I slot print_timing: id 1 | task 9248 | prompt eval time = 19597.43 ms / 678 tokens ( 28.90 ms per token, 34.60 tokens per second) 83.08.458.524 I slot print_timing: id 1 | task 9248 | eval time = 251.32 ms / 2 tokens ( 251.32 ms per token, 3.98 tokens per second) 83.08.458.525 I slot print_timing: id 1 | task 9248 | total time = 19848.75 ms / 680 tokens 83.08.458.525 I slot print_timing: id 1 | task 9248 | graphs reused = 7735 83.08.458.526 I slot print_timing: id 1 | task 9248 | graph reallocs = 0 / 0 (same size) / (changed size) 83.08.458.590 I slot release: id 1 | task 9248 | stop processing: n_tokens = 679, truncated = 0 83.08.458.834 I slot print_timing: id 3 | task 9249 | prompt eval time = 19564.65 ms / 712 tokens ( 27.48 ms per token, 36.39 tokens per second) 83.08.458.836 I slot print_timing: id 3 | task 9249 | eval time = 251.30 ms / 2 tokens ( 251.30 ms per token, 3.98 tokens per second) 83.08.458.837 I slot print_timing: id 3 | task 9249 | total time = 19815.95 ms / 714 tokens 83.08.458.837 I slot print_timing: id 3 | task 9249 | graphs reused = 7735 83.08.458.837 I slot print_timing: id 3 | task 9249 | graph reallocs = 0 / 0 (same size) / (changed size) 83.08.459.951 I slot release: id 3 | task 9249 | stop processing: n_tokens = 713, truncated = 0 83.12.430.429 I srv operator(): operator(): cleaning up before exit...