C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\e4d9634a3b65\Ornith-1.5-9B-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 0.00.099.264 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.099.406 I srv llama_server: initializing ... 0.00.099.410 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.099.516 I srv init_listene: The UI is disabled 0.00.099.518 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.099.594 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) 0.00.107.080 I srv load_model: loading model 'C:\quantdiff\dl\campaign\e4d9634a3b65\Ornith-1.5-9B-Q5_K_M.gguf' 0.00.944.425 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.00.944.440 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.00.944.466 W model has unused tensor blk.32.attn_q.weight (size = 23068672 bytes) -- ignoring 0.00.944.475 W model has unused tensor blk.32.attn_k.weight (size = 2883584 bytes) -- ignoring 0.00.944.484 W model has unused tensor blk.32.attn_v.weight (size = 3440640 bytes) -- ignoring 0.00.944.517 W model has unused tensor blk.32.attn_output.weight (size = 11534336 bytes) -- ignoring 0.00.944.527 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.944.536 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.944.545 W model has unused tensor blk.32.ffn_gate.weight (size = 34603008 bytes) -- ignoring 0.00.944.554 W model has unused tensor blk.32.ffn_down.weight (size = 41287680 bytes) -- ignoring 0.00.944.564 W model has unused tensor blk.32.ffn_up.weight (size = 34603008 bytes) -- ignoring 0.00.944.573 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 23068672 bytes) -- ignoring 0.00.944.585 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.00.944.595 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.00.944.623 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.02.963.413 I cmn init: llama threadpool init, n_threads = 8 0.03.045.918 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.03.050.925 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.03.050.943 I srv llama_server: model loaded 0.03.050.945 I srv llama_server: listening on http://127.0.0.1:8091 0.43.856.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.43.856.146 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.43.856.151 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.43.856.177 I slot launch_slot_: id 1 | task 0 | processing task, is_child = 0 0.44.046.871 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.046.947 I slot launch_slot_: id 2 | task 3 | processing task, is_child = 0 0.44.046.951 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.046.982 I slot launch_slot_: id 3 | task 4 | processing task, is_child = 0 0.44.220.600 I slot print_timing: id 0 | task 1 | prompt eval time = 310.82 ms / 130 tokens ( 2.39 ms per token, 418.25 tokens per second) 0.44.220.605 I slot print_timing: id 0 | task 1 | eval time = 53.59 ms / 2 tokens ( 53.59 ms per token, 18.66 tokens per second) 0.44.220.606 I slot print_timing: id 0 | task 1 | total time = 364.41 ms / 132 tokens 0.44.220.610 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.44.220.611 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.220.643 I slot release: id 0 | task 1 | stop processing: n_tokens = 131, truncated = 0 0.44.220.940 I slot print_timing: id 1 | task 0 | prompt eval time = 311.49 ms / 115 tokens ( 2.71 ms per token, 369.19 tokens per second) 0.44.220.944 I slot print_timing: id 1 | task 0 | eval time = 53.25 ms / 2 tokens ( 53.25 ms per token, 18.78 tokens per second) 0.44.220.944 I slot print_timing: id 1 | task 0 | total time = 364.74 ms / 117 tokens 0.44.220.945 I slot print_timing: id 1 | task 0 | graphs reused = 1 0.44.220.946 I slot print_timing: id 1 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.220.959 I slot release: id 1 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.44.237.708 I slot print_timing: id 2 | task 3 | prompt eval time = 147.35 ms / 115 tokens ( 1.28 ms per token, 780.45 tokens per second) 0.44.237.714 I slot print_timing: id 2 | task 3 | eval time = 16.12 ms / 2 tokens ( 16.12 ms per token, 62.05 tokens per second) 0.44.237.715 I slot print_timing: id 2 | task 3 | total time = 163.47 ms / 117 tokens 0.44.237.716 I slot print_timing: id 2 | task 3 | graphs reused = 1 0.44.237.717 I slot print_timing: id 2 | task 3 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.237.734 I slot release: id 2 | task 3 | stop processing: n_tokens = 116, truncated = 0 0.44.238.012 I slot print_timing: id 3 | task 4 | prompt eval time = 147.94 ms / 122 tokens ( 1.21 ms per token, 824.65 tokens per second) 0.44.238.015 I slot print_timing: id 3 | task 4 | eval time = 15.82 ms / 2 tokens ( 15.82 ms per token, 63.20 tokens per second) 0.44.238.016 I slot print_timing: id 3 | task 4 | total time = 163.77 ms / 124 tokens 0.44.238.016 I slot print_timing: id 3 | task 4 | graphs reused = 1 0.44.238.017 I slot print_timing: id 3 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.238.029 I slot release: id 3 | task 4 | stop processing: n_tokens = 123, truncated = 0 0.44.238.040 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.214 0.44.255.863 I slot launch_slot_: id 0 | task 8 | processing task, is_child = 0 0.44.305.124 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.250 0.44.305.289 I slot launch_slot_: id 1 | task 9 | processing task, is_child = 0 0.44.305.329 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.140 (> 0.100 thold), f_keep = 0.241 0.44.305.432 I slot launch_slot_: id 2 | task 10 | processing task, is_child = 0 0.44.305.455 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.236 0.44.305.566 I slot launch_slot_: id 3 | task 11 | processing task, is_child = 0 0.44.561.751 I slot print_timing: id 0 | task 8 | prompt eval time = 237.66 ms / 160 tokens ( 1.49 ms per token, 673.23 tokens per second) 0.44.561.756 I slot print_timing: id 0 | task 8 | eval time = 18.50 ms / 2 tokens ( 18.50 ms per token, 54.04 tokens per second) 0.44.561.757 I slot print_timing: id 0 | task 8 | total time = 256.17 ms / 162 tokens 0.44.561.758 I slot print_timing: id 0 | task 8 | graphs reused = 1 0.44.561.759 I slot print_timing: id 0 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.561.790 I slot release: id 0 | task 8 | stop processing: n_tokens = 161, truncated = 0 0.44.562.064 I slot print_timing: id 1 | task 9 | prompt eval time = 237.36 ms / 152 tokens ( 1.56 ms per token, 640.37 tokens per second) 0.44.562.066 I slot print_timing: id 1 | task 9 | eval time = 18.24 ms / 2 tokens ( 18.24 ms per token, 54.82 tokens per second) 0.44.562.067 I slot print_timing: id 1 | task 9 | total time = 255.60 ms / 154 tokens 0.44.562.067 I slot print_timing: id 1 | task 9 | graphs reused = 1 0.44.562.068 I slot print_timing: id 1 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.562.084 I slot release: id 1 | task 9 | stop processing: n_tokens = 153, truncated = 0 0.44.562.357 I slot print_timing: id 2 | task 10 | prompt eval time = 237.06 ms / 200 tokens ( 1.19 ms per token, 843.66 tokens per second) 0.44.562.360 I slot print_timing: id 2 | task 10 | eval time = 17.96 ms / 2 tokens ( 17.96 ms per token, 55.66 tokens per second) 0.44.562.361 I slot print_timing: id 2 | task 10 | total time = 255.03 ms / 202 tokens 0.44.562.361 I slot print_timing: id 2 | task 10 | graphs reused = 1 0.44.562.362 I slot print_timing: id 2 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.562.379 I slot release: id 2 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.44.562.648 I slot print_timing: id 3 | task 11 | prompt eval time = 236.76 ms / 108 tokens ( 2.19 ms per token, 456.17 tokens per second) 0.44.562.651 I slot print_timing: id 3 | task 11 | eval time = 17.69 ms / 2 tokens ( 17.69 ms per token, 56.54 tokens per second) 0.44.562.651 I slot print_timing: id 3 | task 11 | total time = 254.44 ms / 110 tokens 0.44.562.652 I slot print_timing: id 3 | task 11 | graphs reused = 1 0.44.562.652 I slot print_timing: id 3 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.562.663 I slot release: id 3 | task 11 | stop processing: n_tokens = 109, truncated = 0 0.44.571.021 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.190 0.44.588.059 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.44.637.817 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.187 (> 0.100 thold), f_keep = 0.174 0.44.637.942 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.44.637.985 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.139 0.44.638.092 I slot launch_slot_: id 2 | task 17 | processing task, is_child = 0 0.44.638.114 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.257 0.44.638.215 I slot launch_slot_: id 3 | task 18 | processing task, is_child = 0 0.44.870.425 I slot print_timing: id 0 | task 16 | prompt eval time = 213.58 ms / 150 tokens ( 1.42 ms per token, 702.33 tokens per second) 0.44.870.430 I slot print_timing: id 0 | task 16 | eval time = 18.62 ms / 2 tokens ( 18.62 ms per token, 53.71 tokens per second) 0.44.870.431 I slot print_timing: id 0 | task 16 | total time = 232.19 ms / 152 tokens 0.44.870.432 I slot print_timing: id 0 | task 16 | graphs reused = 1 0.44.870.433 I slot print_timing: id 0 | task 16 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.870.463 I slot release: id 0 | task 16 | stop processing: n_tokens = 151, truncated = 0 0.44.870.754 I slot print_timing: id 1 | task 15 | prompt eval time = 213.36 ms / 118 tokens ( 1.81 ms per token, 553.05 tokens per second) 0.44.870.757 I slot print_timing: id 1 | task 15 | eval time = 18.31 ms / 2 tokens ( 18.31 ms per token, 54.63 tokens per second) 0.44.870.758 I slot print_timing: id 1 | task 15 | total time = 231.67 ms / 120 tokens 0.44.870.759 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.44.870.759 I slot print_timing: id 1 | task 15 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.870.773 I slot release: id 1 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.44.871.018 I slot print_timing: id 2 | task 17 | prompt eval time = 213.05 ms / 117 tokens ( 1.82 ms per token, 549.17 tokens per second) 0.44.871.021 I slot print_timing: id 2 | task 17 | eval time = 18.01 ms / 2 tokens ( 18.01 ms per token, 55.53 tokens per second) 0.44.871.022 I slot print_timing: id 2 | task 17 | total time = 231.06 ms / 119 tokens 0.44.871.022 I slot print_timing: id 2 | task 17 | graphs reused = 1 0.44.871.023 I slot print_timing: id 2 | task 17 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.871.035 I slot release: id 2 | task 17 | stop processing: n_tokens = 118, truncated = 0 0.44.871.281 I slot print_timing: id 3 | task 18 | prompt eval time = 212.76 ms / 125 tokens ( 1.70 ms per token, 587.52 tokens per second) 0.44.871.283 I slot print_timing: id 3 | task 18 | eval time = 17.70 ms / 2 tokens ( 17.70 ms per token, 56.50 tokens per second) 0.44.871.284 I slot print_timing: id 3 | task 18 | total time = 230.46 ms / 127 tokens 0.44.871.284 I slot print_timing: id 3 | task 18 | graphs reused = 1 0.44.871.285 I slot print_timing: id 3 | task 18 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.871.297 I slot release: id 3 | task 18 | stop processing: n_tokens = 126, truncated = 0 0.44.879.920 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.185 0.44.896.995 I slot launch_slot_: id 0 | task 22 | processing task, is_child = 0 0.44.945.803 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.235 0.44.945.971 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.44.946.012 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.237 0.44.946.121 I slot launch_slot_: id 2 | task 24 | processing task, is_child = 0 0.44.946.144 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.222 0.44.946.246 I slot launch_slot_: id 3 | task 25 | processing task, is_child = 0 0.45.192.275 I slot print_timing: id 0 | task 22 | prompt eval time = 226.96 ms / 119 tokens ( 1.91 ms per token, 524.32 tokens per second) 0.45.192.281 I slot print_timing: id 0 | task 22 | eval time = 19.05 ms / 2 tokens ( 19.05 ms per token, 52.50 tokens per second) 0.45.192.282 I slot print_timing: id 0 | task 22 | total time = 246.01 ms / 121 tokens 0.45.192.283 I slot print_timing: id 0 | task 22 | graphs reused = 1 0.45.192.284 I slot print_timing: id 0 | task 22 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.192.310 I slot release: id 0 | task 22 | stop processing: n_tokens = 120, truncated = 0 0.45.192.632 I slot print_timing: id 1 | task 23 | prompt eval time = 226.68 ms / 143 tokens ( 1.59 ms per token, 630.86 tokens per second) 0.45.192.635 I slot print_timing: id 1 | task 23 | eval time = 18.83 ms / 2 tokens ( 18.83 ms per token, 53.10 tokens per second) 0.45.192.636 I slot print_timing: id 1 | task 23 | total time = 245.51 ms / 145 tokens 0.45.192.636 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.45.192.637 I slot print_timing: id 1 | task 23 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.192.652 I slot release: id 1 | task 23 | stop processing: n_tokens = 144, truncated = 0 0.45.192.951 I slot print_timing: id 2 | task 24 | prompt eval time = 226.40 ms / 181 tokens ( 1.25 ms per token, 799.48 tokens per second) 0.45.192.954 I slot print_timing: id 2 | task 24 | eval time = 18.60 ms / 2 tokens ( 18.60 ms per token, 53.77 tokens per second) 0.45.192.955 I slot print_timing: id 2 | task 24 | total time = 245.00 ms / 183 tokens 0.45.192.955 I slot print_timing: id 2 | task 24 | graphs reused = 1 0.45.192.956 I slot print_timing: id 2 | task 24 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.192.971 I slot release: id 2 | task 24 | stop processing: n_tokens = 182, truncated = 0 0.45.193.269 I slot print_timing: id 3 | task 25 | prompt eval time = 226.16 ms / 136 tokens ( 1.66 ms per token, 601.34 tokens per second) 0.45.193.272 I slot print_timing: id 3 | task 25 | eval time = 18.34 ms / 2 tokens ( 18.34 ms per token, 54.53 tokens per second) 0.45.193.273 I slot print_timing: id 3 | task 25 | total time = 244.50 ms / 138 tokens 0.45.193.274 I slot print_timing: id 3 | task 25 | graphs reused = 1 0.45.193.274 I slot print_timing: id 3 | task 25 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.193.285 I slot release: id 3 | task 25 | stop processing: n_tokens = 137, truncated = 0 0.45.200.498 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 0.45.226.044 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.45.277.001 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.194 0.45.285.206 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.45.285.257 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.154 0.45.285.370 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 0.45.285.396 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.204 0.45.285.501 I slot launch_slot_: id 3 | task 32 | processing task, is_child = 0 0.45.533.136 I slot print_timing: id 0 | task 29 | prompt eval time = 228.70 ms / 131 tokens ( 1.75 ms per token, 572.81 tokens per second) 0.45.533.141 I slot print_timing: id 0 | task 29 | eval time = 18.92 ms / 2 tokens ( 18.92 ms per token, 52.85 tokens per second) 0.45.533.142 I slot print_timing: id 0 | task 29 | total time = 247.62 ms / 133 tokens 0.45.533.143 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.45.533.144 I slot print_timing: id 0 | task 29 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.533.170 I slot release: id 0 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.45.533.495 I slot print_timing: id 1 | task 30 | prompt eval time = 228.49 ms / 122 tokens ( 1.87 ms per token, 533.95 tokens per second) 0.45.533.498 I slot print_timing: id 1 | task 30 | eval time = 18.63 ms / 2 tokens ( 18.63 ms per token, 53.68 tokens per second) 0.45.533.499 I slot print_timing: id 1 | task 30 | total time = 247.11 ms / 124 tokens 0.45.533.500 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.45.533.501 I slot print_timing: id 1 | task 30 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.533.514 I slot release: id 1 | task 30 | stop processing: n_tokens = 123, truncated = 0 0.45.533.792 I slot print_timing: id 2 | task 31 | prompt eval time = 228.27 ms / 178 tokens ( 1.28 ms per token, 779.79 tokens per second) 0.45.533.795 I slot print_timing: id 2 | task 31 | eval time = 18.35 ms / 2 tokens ( 18.35 ms per token, 54.51 tokens per second) 0.45.533.796 I slot print_timing: id 2 | task 31 | total time = 246.61 ms / 180 tokens 0.45.533.796 I slot print_timing: id 2 | task 31 | graphs reused = 1 0.45.533.797 I slot print_timing: id 2 | task 31 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.533.812 I slot release: id 2 | task 31 | stop processing: n_tokens = 179, truncated = 0 0.45.534.101 I slot print_timing: id 3 | task 32 | prompt eval time = 227.94 ms / 144 tokens ( 1.58 ms per token, 631.74 tokens per second) 0.45.534.103 I slot print_timing: id 3 | task 32 | eval time = 18.09 ms / 2 tokens ( 18.09 ms per token, 55.27 tokens per second) 0.45.534.104 I slot print_timing: id 3 | task 32 | total time = 246.04 ms / 146 tokens 0.45.534.104 I slot print_timing: id 3 | task 32 | graphs reused = 1 0.45.534.105 I slot print_timing: id 3 | task 32 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.534.116 I slot release: id 3 | task 32 | stop processing: n_tokens = 145, truncated = 0 0.45.542.583 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 0.45.559.727 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.45.609.160 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.228 0.45.609.339 I slot launch_slot_: id 1 | task 37 | processing task, is_child = 0 0.45.609.387 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.156 0.45.609.499 I slot launch_slot_: id 2 | task 38 | processing task, is_child = 0 0.45.609.522 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.193 0.45.609.628 I slot launch_slot_: id 3 | task 39 | processing task, is_child = 0 0.45.846.012 I slot print_timing: id 0 | task 36 | prompt eval time = 217.21 ms / 113 tokens ( 1.92 ms per token, 520.24 tokens per second) 0.45.846.018 I slot print_timing: id 0 | task 36 | eval time = 19.16 ms / 2 tokens ( 19.16 ms per token, 52.20 tokens per second) 0.45.846.019 I slot print_timing: id 0 | task 36 | total time = 236.37 ms / 115 tokens 0.45.846.020 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.45.846.020 I slot print_timing: id 0 | task 36 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.846.047 I slot release: id 0 | task 36 | stop processing: n_tokens = 114, truncated = 0 0.45.846.349 I slot print_timing: id 1 | task 37 | prompt eval time = 216.89 ms / 142 tokens ( 1.53 ms per token, 654.70 tokens per second) 0.45.846.352 I slot print_timing: id 1 | task 37 | eval time = 18.93 ms / 2 tokens ( 18.93 ms per token, 52.82 tokens per second) 0.45.846.352 I slot print_timing: id 1 | task 37 | total time = 235.83 ms / 144 tokens 0.45.846.353 I slot print_timing: id 1 | task 37 | graphs reused = 1 0.45.846.353 I slot print_timing: id 1 | task 37 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.846.369 I slot release: id 1 | task 37 | stop processing: n_tokens = 143, truncated = 0 0.45.846.665 I slot print_timing: id 2 | task 38 | prompt eval time = 216.60 ms / 120 tokens ( 1.81 ms per token, 554.01 tokens per second) 0.45.846.668 I slot print_timing: id 2 | task 38 | eval time = 18.69 ms / 2 tokens ( 18.69 ms per token, 53.50 tokens per second) 0.45.846.669 I slot print_timing: id 2 | task 38 | total time = 235.29 ms / 122 tokens 0.45.846.670 I slot print_timing: id 2 | task 38 | graphs reused = 1 0.45.846.670 I slot print_timing: id 2 | task 38 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.846.680 I slot release: id 2 | task 38 | stop processing: n_tokens = 121, truncated = 0 0.45.846.970 I slot print_timing: id 3 | task 39 | prompt eval time = 216.33 ms / 144 tokens ( 1.50 ms per token, 665.65 tokens per second) 0.45.846.973 I slot print_timing: id 3 | task 39 | eval time = 18.44 ms / 2 tokens ( 18.44 ms per token, 54.24 tokens per second) 0.45.846.974 I slot print_timing: id 3 | task 39 | total time = 234.77 ms / 146 tokens 0.45.846.974 I slot print_timing: id 3 | task 39 | graphs reused = 1 0.45.846.975 I slot print_timing: id 3 | task 39 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.846.987 I slot release: id 3 | task 39 | stop processing: n_tokens = 145, truncated = 0 0.45.855.192 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 0.45.872.148 I slot launch_slot_: id 0 | task 43 | processing task, is_child = 0 0.45.921.599 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.45.921.761 I slot launch_slot_: id 2 | task 44 | processing task, is_child = 0 0.45.921.805 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 0.45.921.921 I slot launch_slot_: id 1 | task 45 | processing task, is_child = 0 0.45.921.945 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.193 0.45.922.047 I slot launch_slot_: id 3 | task 46 | processing task, is_child = 0 0.46.156.635 I slot print_timing: id 0 | task 43 | prompt eval time = 215.62 ms / 123 tokens ( 1.75 ms per token, 570.44 tokens per second) 0.46.156.640 I slot print_timing: id 0 | task 43 | eval time = 18.95 ms / 2 tokens ( 18.95 ms per token, 52.78 tokens per second) 0.46.156.641 I slot print_timing: id 0 | task 43 | total time = 234.57 ms / 125 tokens 0.46.156.643 I slot print_timing: id 0 | task 43 | graphs reused = 1 0.46.156.643 I slot print_timing: id 0 | task 43 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.156.667 I slot release: id 0 | task 43 | stop processing: n_tokens = 124, truncated = 0 0.46.157.004 I slot print_timing: id 1 | task 45 | prompt eval time = 215.44 ms / 143 tokens ( 1.51 ms per token, 663.76 tokens per second) 0.46.157.007 I slot print_timing: id 1 | task 45 | eval time = 18.66 ms / 2 tokens ( 18.66 ms per token, 53.60 tokens per second) 0.46.157.007 I slot print_timing: id 1 | task 45 | total time = 234.09 ms / 145 tokens 0.46.157.008 I slot print_timing: id 1 | task 45 | graphs reused = 1 0.46.157.009 I slot print_timing: id 1 | task 45 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.157.023 I slot release: id 1 | task 45 | stop processing: n_tokens = 144, truncated = 0 0.46.157.323 I slot print_timing: id 2 | task 44 | prompt eval time = 215.16 ms / 112 tokens ( 1.92 ms per token, 520.53 tokens per second) 0.46.157.326 I slot print_timing: id 2 | task 44 | eval time = 18.41 ms / 2 tokens ( 18.41 ms per token, 54.32 tokens per second) 0.46.157.327 I slot print_timing: id 2 | task 44 | total time = 233.57 ms / 114 tokens 0.46.157.327 I slot print_timing: id 2 | task 44 | graphs reused = 1 0.46.157.328 I slot print_timing: id 2 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.157.342 I slot release: id 2 | task 44 | stop processing: n_tokens = 113, truncated = 0 0.46.157.631 I slot print_timing: id 3 | task 46 | prompt eval time = 214.92 ms / 109 tokens ( 1.97 ms per token, 507.16 tokens per second) 0.46.157.634 I slot print_timing: id 3 | task 46 | eval time = 18.15 ms / 2 tokens ( 18.15 ms per token, 55.09 tokens per second) 0.46.157.635 I slot print_timing: id 3 | task 46 | total time = 233.07 ms / 111 tokens 0.46.157.635 I slot print_timing: id 3 | task 46 | graphs reused = 1 0.46.157.636 I slot print_timing: id 3 | task 46 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.157.645 I slot release: id 3 | task 46 | stop processing: n_tokens = 110, truncated = 0 0.46.165.559 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.283 0.46.182.592 I slot launch_slot_: id 2 | task 50 | processing task, is_child = 0 0.46.232.197 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.226 0.46.232.371 I slot launch_slot_: id 0 | task 51 | processing task, is_child = 0 0.46.232.418 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.194 0.46.240.753 I slot launch_slot_: id 1 | task 52 | processing task, is_child = 0 0.46.240.780 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.255 0.46.240.885 I slot launch_slot_: id 3 | task 53 | processing task, is_child = 0 0.46.475.530 I slot print_timing: id 0 | task 51 | prompt eval time = 215.37 ms / 136 tokens ( 1.58 ms per token, 631.48 tokens per second) 0.46.475.535 I slot print_timing: id 0 | task 51 | eval time = 19.26 ms / 2 tokens ( 19.26 ms per token, 51.93 tokens per second) 0.46.475.536 I slot print_timing: id 0 | task 51 | total time = 234.63 ms / 138 tokens 0.46.475.537 I slot print_timing: id 0 | task 51 | graphs reused = 1 0.46.475.538 I slot print_timing: id 0 | task 51 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.475.565 I slot release: id 0 | task 51 | stop processing: n_tokens = 137, truncated = 0 0.46.475.881 I slot print_timing: id 1 | task 52 | prompt eval time = 215.10 ms / 112 tokens ( 1.92 ms per token, 520.68 tokens per second) 0.46.475.884 I slot print_timing: id 1 | task 52 | eval time = 18.96 ms / 2 tokens ( 18.96 ms per token, 52.73 tokens per second) 0.46.475.885 I slot print_timing: id 1 | task 52 | total time = 234.07 ms / 114 tokens 0.46.475.886 I slot print_timing: id 1 | task 52 | graphs reused = 1 0.46.475.886 I slot print_timing: id 1 | task 52 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.475.899 I slot release: id 1 | task 52 | stop processing: n_tokens = 113, truncated = 0 0.46.476.215 I slot print_timing: id 2 | task 50 | prompt eval time = 214.74 ms / 129 tokens ( 1.66 ms per token, 600.72 tokens per second) 0.46.476.218 I slot print_timing: id 2 | task 50 | eval time = 18.66 ms / 2 tokens ( 18.66 ms per token, 53.58 tokens per second) 0.46.476.219 I slot print_timing: id 2 | task 50 | total time = 233.41 ms / 131 tokens 0.46.476.219 I slot print_timing: id 2 | task 50 | graphs reused = 1 0.46.476.220 I slot print_timing: id 2 | task 50 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.476.231 I slot release: id 2 | task 50 | stop processing: n_tokens = 130, truncated = 0 0.46.476.519 I slot print_timing: id 3 | task 53 | prompt eval time = 214.39 ms / 102 tokens ( 2.10 ms per token, 475.78 tokens per second) 0.46.476.522 I slot print_timing: id 3 | task 53 | eval time = 18.41 ms / 2 tokens ( 18.41 ms per token, 54.31 tokens per second) 0.46.476.523 I slot print_timing: id 3 | task 53 | total time = 232.80 ms / 104 tokens 0.46.476.523 I slot print_timing: id 3 | task 53 | graphs reused = 1 0.46.476.524 I slot print_timing: id 3 | task 53 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.476.534 I slot release: id 3 | task 53 | stop processing: n_tokens = 103, truncated = 0 0.46.484.364 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.204 0.46.501.609 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 0.46.558.167 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.248 0.46.558.339 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 0.46.558.379 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.215 0.46.558.483 I slot launch_slot_: id 2 | task 59 | processing task, is_child = 0 0.46.558.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.272 0.46.558.601 I slot launch_slot_: id 3 | task 60 | processing task, is_child = 0 0.46.825.346 I slot print_timing: id 0 | task 57 | prompt eval time = 247.38 ms / 182 tokens ( 1.36 ms per token, 735.71 tokens per second) 0.46.825.351 I slot print_timing: id 0 | task 57 | eval time = 19.35 ms / 2 tokens ( 19.35 ms per token, 51.68 tokens per second) 0.46.825.352 I slot print_timing: id 0 | task 57 | total time = 266.73 ms / 184 tokens 0.46.825.353 I slot print_timing: id 0 | task 57 | graphs reused = 1 0.46.825.354 I slot print_timing: id 0 | task 57 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.825.383 I slot release: id 0 | task 57 | stop processing: n_tokens = 183, truncated = 0 0.46.825.692 I slot print_timing: id 1 | task 58 | prompt eval time = 247.21 ms / 132 tokens ( 1.87 ms per token, 533.96 tokens per second) 0.46.825.696 I slot print_timing: id 1 | task 58 | eval time = 19.01 ms / 2 tokens ( 19.01 ms per token, 52.60 tokens per second) 0.46.825.697 I slot print_timing: id 1 | task 58 | total time = 266.22 ms / 134 tokens 0.46.825.697 I slot print_timing: id 1 | task 58 | graphs reused = 1 0.46.825.698 I slot print_timing: id 1 | task 58 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.825.712 I slot release: id 1 | task 58 | stop processing: n_tokens = 133, truncated = 0 0.46.825.995 I slot print_timing: id 2 | task 59 | prompt eval time = 247.07 ms / 166 tokens ( 1.49 ms per token, 671.89 tokens per second) 0.46.825.998 I slot print_timing: id 2 | task 59 | eval time = 18.63 ms / 2 tokens ( 18.63 ms per token, 53.68 tokens per second) 0.46.825.999 I slot print_timing: id 2 | task 59 | total time = 265.69 ms / 168 tokens 0.46.825.999 I slot print_timing: id 2 | task 59 | graphs reused = 1 0.46.826.000 I slot print_timing: id 2 | task 59 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.826.013 I slot release: id 2 | task 59 | stop processing: n_tokens = 167, truncated = 0 0.46.826.297 I slot print_timing: id 3 | task 60 | prompt eval time = 246.95 ms / 177 tokens ( 1.40 ms per token, 716.76 tokens per second) 0.46.826.300 I slot print_timing: id 3 | task 60 | eval time = 18.25 ms / 2 tokens ( 18.25 ms per token, 54.81 tokens per second) 0.46.826.301 I slot print_timing: id 3 | task 60 | total time = 265.19 ms / 179 tokens 0.46.826.301 I slot print_timing: id 3 | task 60 | graphs reused = 1 0.46.826.302 I slot print_timing: id 3 | task 60 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.826.316 I slot release: id 3 | task 60 | stop processing: n_tokens = 178, truncated = 0 0.46.834.087 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.166 (> 0.100 thold), f_keep = 0.153 0.46.857.323 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 0.46.909.782 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.211 0.46.909.927 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 0.46.909.975 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.168 0.46.918.285 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 0.46.918.316 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.157 0.46.918.427 I slot launch_slot_: id 3 | task 67 | processing task, is_child = 0 0.47.167.827 I slot print_timing: id 0 | task 64 | prompt eval time = 230.05 ms / 169 tokens ( 1.36 ms per token, 734.61 tokens per second) 0.47.167.833 I slot print_timing: id 0 | task 64 | eval time = 19.33 ms / 2 tokens ( 19.33 ms per token, 51.73 tokens per second) 0.47.167.835 I slot print_timing: id 0 | task 64 | total time = 249.38 ms / 171 tokens 0.47.167.836 I slot print_timing: id 0 | task 64 | graphs reused = 1 0.47.167.837 I slot print_timing: id 0 | task 64 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.167.865 I slot release: id 0 | task 64 | stop processing: n_tokens = 170, truncated = 0 0.47.168.275 I slot print_timing: id 1 | task 65 | prompt eval time = 229.78 ms / 123 tokens ( 1.87 ms per token, 535.30 tokens per second) 0.47.168.278 I slot print_timing: id 1 | task 65 | eval time = 19.13 ms / 2 tokens ( 19.13 ms per token, 52.27 tokens per second) 0.47.168.279 I slot print_timing: id 1 | task 65 | total time = 248.91 ms / 125 tokens 0.47.168.280 I slot print_timing: id 1 | task 65 | graphs reused = 1 0.47.168.282 I slot print_timing: id 1 | task 65 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.168.298 I slot release: id 1 | task 65 | stop processing: n_tokens = 124, truncated = 0 0.47.168.735 I slot print_timing: id 2 | task 66 | prompt eval time = 229.52 ms / 140 tokens ( 1.64 ms per token, 609.97 tokens per second) 0.47.168.741 I slot print_timing: id 2 | task 66 | eval time = 18.94 ms / 2 tokens ( 18.94 ms per token, 52.80 tokens per second) 0.47.168.742 I slot print_timing: id 2 | task 66 | total time = 248.46 ms / 142 tokens 0.47.168.743 I slot print_timing: id 2 | task 66 | graphs reused = 1 0.47.168.745 I slot print_timing: id 2 | task 66 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.168.765 I slot release: id 2 | task 66 | stop processing: n_tokens = 141, truncated = 0 0.47.169.146 I slot print_timing: id 3 | task 67 | prompt eval time = 229.23 ms / 149 tokens ( 1.54 ms per token, 650.01 tokens per second) 0.47.169.151 I slot print_timing: id 3 | task 67 | eval time = 18.77 ms / 2 tokens ( 18.77 ms per token, 53.27 tokens per second) 0.47.169.152 I slot print_timing: id 3 | task 67 | total time = 248.00 ms / 151 tokens 0.47.169.152 I slot print_timing: id 3 | task 67 | graphs reused = 1 0.47.169.153 I slot print_timing: id 3 | task 67 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.169.167 I slot release: id 3 | task 67 | stop processing: n_tokens = 150, truncated = 0 0.47.176.478 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.165 0.47.193.971 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.47.243.510 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 0.47.243.674 I slot launch_slot_: id 2 | task 72 | processing task, is_child = 0 0.47.243.718 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.234 0.47.243.830 I slot launch_slot_: id 1 | task 73 | processing task, is_child = 0 0.47.243.854 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.187 0.47.243.958 I slot launch_slot_: id 3 | task 74 | processing task, is_child = 0 0.47.497.098 I slot print_timing: id 0 | task 71 | prompt eval time = 233.80 ms / 128 tokens ( 1.83 ms per token, 547.47 tokens per second) 0.47.497.104 I slot print_timing: id 0 | task 71 | eval time = 19.32 ms / 2 tokens ( 19.32 ms per token, 51.75 tokens per second) 0.47.497.105 I slot print_timing: id 0 | task 71 | total time = 253.12 ms / 130 tokens 0.47.497.106 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.47.497.107 I slot print_timing: id 0 | task 71 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.497.130 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 0.47.497.468 I slot print_timing: id 1 | task 73 | prompt eval time = 233.72 ms / 163 tokens ( 1.43 ms per token, 697.42 tokens per second) 0.47.497.472 I slot print_timing: id 1 | task 73 | eval time = 18.89 ms / 2 tokens ( 18.89 ms per token, 52.94 tokens per second) 0.47.497.472 I slot print_timing: id 1 | task 73 | total time = 252.61 ms / 165 tokens 0.47.497.473 I slot print_timing: id 1 | task 73 | graphs reused = 1 0.47.497.473 I slot print_timing: id 1 | task 73 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.497.489 I slot release: id 1 | task 73 | stop processing: n_tokens = 164, truncated = 0 0.47.497.840 I slot print_timing: id 2 | task 72 | prompt eval time = 233.70 ms / 111 tokens ( 2.11 ms per token, 474.96 tokens per second) 0.47.497.844 I slot print_timing: id 2 | task 72 | eval time = 18.41 ms / 2 tokens ( 18.41 ms per token, 54.30 tokens per second) 0.47.497.844 I slot print_timing: id 2 | task 72 | total time = 252.12 ms / 113 tokens 0.47.497.845 I slot print_timing: id 2 | task 72 | graphs reused = 1 0.47.497.846 I slot print_timing: id 2 | task 72 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.497.857 I slot release: id 2 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.47.498.231 I slot print_timing: id 3 | task 74 | prompt eval time = 233.59 ms / 161 tokens ( 1.45 ms per token, 689.24 tokens per second) 0.47.498.235 I slot print_timing: id 3 | task 74 | eval time = 18.07 ms / 2 tokens ( 18.07 ms per token, 55.34 tokens per second) 0.47.498.235 I slot print_timing: id 3 | task 74 | total time = 251.66 ms / 163 tokens 0.47.498.236 I slot print_timing: id 3 | task 74 | graphs reused = 1 0.47.498.236 I slot print_timing: id 3 | task 74 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.498.249 I slot release: id 3 | task 74 | stop processing: n_tokens = 162, truncated = 0 0.47.505.960 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.217 0.47.523.143 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.47.572.482 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.177 0.47.572.650 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.47.572.694 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.250 0.47.572.810 I slot launch_slot_: id 2 | task 81 | processing task, is_child = 0 0.47.572.835 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.179 0.47.572.943 I slot launch_slot_: id 3 | task 80 | processing task, is_child = 0 0.47.825.009 I slot print_timing: id 0 | task 78 | prompt eval time = 232.96 ms / 167 tokens ( 1.39 ms per token, 716.86 tokens per second) 0.47.825.015 I slot print_timing: id 0 | task 78 | eval time = 19.09 ms / 2 tokens ( 19.09 ms per token, 52.39 tokens per second) 0.47.825.016 I slot print_timing: id 0 | task 78 | total time = 252.05 ms / 169 tokens 0.47.825.017 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.47.825.019 I slot print_timing: id 0 | task 78 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.825.044 I slot release: id 0 | task 78 | stop processing: n_tokens = 168, truncated = 0 0.47.825.422 I slot print_timing: id 1 | task 79 | prompt eval time = 232.94 ms / 164 tokens ( 1.42 ms per token, 704.05 tokens per second) 0.47.825.426 I slot print_timing: id 1 | task 79 | eval time = 18.70 ms / 2 tokens ( 18.70 ms per token, 53.48 tokens per second) 0.47.825.427 I slot print_timing: id 1 | task 79 | total time = 251.64 ms / 166 tokens 0.47.825.427 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.47.825.428 I slot print_timing: id 1 | task 79 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.825.444 I slot release: id 1 | task 79 | stop processing: n_tokens = 165, truncated = 0 0.47.825.829 I slot print_timing: id 2 | task 81 | prompt eval time = 232.85 ms / 112 tokens ( 2.08 ms per token, 481.00 tokens per second) 0.47.825.832 I slot print_timing: id 2 | task 81 | eval time = 18.36 ms / 2 tokens ( 18.36 ms per token, 54.47 tokens per second) 0.47.825.833 I slot print_timing: id 2 | task 81 | total time = 251.21 ms / 114 tokens 0.47.825.833 I slot print_timing: id 2 | task 81 | graphs reused = 1 0.47.825.834 I slot print_timing: id 2 | task 81 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.825.845 I slot release: id 2 | task 81 | stop processing: n_tokens = 113, truncated = 0 0.47.826.164 I slot print_timing: id 3 | task 80 | prompt eval time = 232.56 ms / 109 tokens ( 2.13 ms per token, 468.70 tokens per second) 0.47.826.167 I slot print_timing: id 3 | task 80 | eval time = 18.14 ms / 2 tokens ( 18.14 ms per token, 55.11 tokens per second) 0.47.826.167 I slot print_timing: id 3 | task 80 | total time = 250.70 ms / 111 tokens 0.47.826.168 I slot print_timing: id 3 | task 80 | graphs reused = 1 0.47.826.169 I slot print_timing: id 3 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.826.179 I slot release: id 3 | task 80 | stop processing: n_tokens = 110, truncated = 0 0.47.834.983 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.167 0.47.860.234 I slot launch_slot_: id 0 | task 86 | processing task, is_child = 0 0.47.912.444 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.170 0.47.912.579 I slot launch_slot_: id 1 | task 85 | processing task, is_child = 0 0.47.912.621 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.248 0.47.912.725 I slot launch_slot_: id 2 | task 87 | processing task, is_child = 0 0.47.912.750 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.255 0.47.912.841 I slot launch_slot_: id 3 | task 88 | processing task, is_child = 0 0.48.145.797 I slot print_timing: id 0 | task 86 | prompt eval time = 214.56 ms / 122 tokens ( 1.76 ms per token, 568.62 tokens per second) 0.48.145.802 I slot print_timing: id 0 | task 86 | eval time = 18.38 ms / 2 tokens ( 18.38 ms per token, 54.40 tokens per second) 0.48.145.803 I slot print_timing: id 0 | task 86 | total time = 232.94 ms / 124 tokens 0.48.145.804 I slot print_timing: id 0 | task 86 | graphs reused = 1 0.48.145.805 I slot print_timing: id 0 | task 86 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.145.828 I slot release: id 0 | task 86 | stop processing: n_tokens = 123, truncated = 0 0.48.146.078 I slot print_timing: id 1 | task 85 | prompt eval time = 214.33 ms / 147 tokens ( 1.46 ms per token, 685.87 tokens per second) 0.48.146.080 I slot print_timing: id 1 | task 85 | eval time = 18.10 ms / 2 tokens ( 18.10 ms per token, 55.24 tokens per second) 0.48.146.081 I slot print_timing: id 1 | task 85 | total time = 232.43 ms / 149 tokens 0.48.146.082 I slot print_timing: id 1 | task 85 | graphs reused = 1 0.48.146.083 I slot print_timing: id 1 | task 85 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.146.098 I slot release: id 1 | task 85 | stop processing: n_tokens = 148, truncated = 0 0.48.146.348 I slot print_timing: id 2 | task 87 | prompt eval time = 213.98 ms / 120 tokens ( 1.78 ms per token, 560.79 tokens per second) 0.48.146.351 I slot print_timing: id 2 | task 87 | eval time = 17.82 ms / 2 tokens ( 17.82 ms per token, 56.13 tokens per second) 0.48.146.352 I slot print_timing: id 2 | task 87 | total time = 231.80 ms / 122 tokens 0.48.146.352 I slot print_timing: id 2 | task 87 | graphs reused = 1 0.48.146.353 I slot print_timing: id 2 | task 87 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.146.365 I slot release: id 2 | task 87 | stop processing: n_tokens = 121, truncated = 0 0.48.146.631 I slot print_timing: id 3 | task 88 | prompt eval time = 213.64 ms / 131 tokens ( 1.63 ms per token, 613.18 tokens per second) 0.48.146.634 I slot print_timing: id 3 | task 88 | eval time = 17.55 ms / 2 tokens ( 17.55 ms per token, 56.97 tokens per second) 0.48.146.634 I slot print_timing: id 3 | task 88 | total time = 231.19 ms / 133 tokens 0.48.146.635 I slot print_timing: id 3 | task 88 | graphs reused = 1 0.48.146.635 I slot print_timing: id 3 | task 88 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.146.646 I slot release: id 3 | task 88 | stop processing: n_tokens = 132, truncated = 0 0.48.154.971 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.228 0.48.171.795 I slot launch_slot_: id 0 | task 92 | processing task, is_child = 0 0.48.220.764 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.189 0.48.220.917 I slot launch_slot_: id 1 | task 93 | processing task, is_child = 0 0.48.220.960 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.231 0.48.229.255 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.48.229.283 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.212 0.48.229.389 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 0.48.470.779 I slot print_timing: id 0 | task 92 | prompt eval time = 222.37 ms / 124 tokens ( 1.79 ms per token, 557.63 tokens per second) 0.48.470.784 I slot print_timing: id 0 | task 92 | eval time = 19.00 ms / 2 tokens ( 19.00 ms per token, 52.62 tokens per second) 0.48.470.786 I slot print_timing: id 0 | task 92 | total time = 241.37 ms / 126 tokens 0.48.470.786 I slot print_timing: id 0 | task 92 | graphs reused = 1 0.48.470.787 I slot print_timing: id 0 | task 92 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.470.813 I slot release: id 0 | task 92 | stop processing: n_tokens = 125, truncated = 0 0.48.471.108 I slot print_timing: id 1 | task 93 | prompt eval time = 222.31 ms / 144 tokens ( 1.54 ms per token, 647.74 tokens per second) 0.48.471.111 I slot print_timing: id 1 | task 93 | eval time = 18.55 ms / 2 tokens ( 18.55 ms per token, 53.89 tokens per second) 0.48.471.112 I slot print_timing: id 1 | task 93 | total time = 240.87 ms / 146 tokens 0.48.471.112 I slot print_timing: id 1 | task 93 | graphs reused = 1 0.48.471.113 I slot print_timing: id 1 | task 93 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.471.127 I slot release: id 1 | task 93 | stop processing: n_tokens = 145, truncated = 0 0.48.471.427 I slot print_timing: id 2 | task 94 | prompt eval time = 222.24 ms / 141 tokens ( 1.58 ms per token, 634.46 tokens per second) 0.48.471.430 I slot print_timing: id 2 | task 94 | eval time = 18.09 ms / 2 tokens ( 18.09 ms per token, 55.28 tokens per second) 0.48.471.431 I slot print_timing: id 2 | task 94 | total time = 240.32 ms / 143 tokens 0.48.471.431 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.48.471.432 I slot print_timing: id 2 | task 94 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.471.443 I slot release: id 2 | task 94 | stop processing: n_tokens = 142, truncated = 0 0.48.471.693 I slot print_timing: id 3 | task 95 | prompt eval time = 222.20 ms / 131 tokens ( 1.70 ms per token, 589.57 tokens per second) 0.48.471.696 I slot print_timing: id 3 | task 95 | eval time = 17.64 ms / 2 tokens ( 17.64 ms per token, 56.70 tokens per second) 0.48.471.697 I slot print_timing: id 3 | task 95 | total time = 239.83 ms / 133 tokens 0.48.471.697 I slot print_timing: id 3 | task 95 | graphs reused = 1 0.48.471.698 I slot print_timing: id 3 | task 95 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.471.707 I slot release: id 3 | task 95 | stop processing: n_tokens = 132, truncated = 0 0.48.479.729 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.200 0.48.497.264 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.48.546.275 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.48.546.406 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.48.546.449 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.231 (> 0.100 thold), f_keep = 0.224 0.48.546.560 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.48.546.585 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 0.48.546.690 I slot launch_slot_: id 3 | task 102 | processing task, is_child = 0 0.48.787.060 I slot print_timing: id 0 | task 101 | prompt eval time = 221.63 ms / 121 tokens ( 1.83 ms per token, 545.95 tokens per second) 0.48.787.066 I slot print_timing: id 0 | task 101 | eval time = 18.73 ms / 2 tokens ( 18.73 ms per token, 53.40 tokens per second) 0.48.787.068 I slot print_timing: id 0 | task 101 | total time = 240.36 ms / 123 tokens 0.48.787.069 I slot print_timing: id 0 | task 101 | graphs reused = 1 0.48.787.070 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.787.092 I slot release: id 0 | task 101 | stop processing: n_tokens = 122, truncated = 0 0.48.787.402 I slot print_timing: id 1 | task 99 | prompt eval time = 221.45 ms / 118 tokens ( 1.88 ms per token, 532.85 tokens per second) 0.48.787.405 I slot print_timing: id 1 | task 99 | eval time = 18.34 ms / 2 tokens ( 18.34 ms per token, 54.51 tokens per second) 0.48.787.406 I slot print_timing: id 1 | task 99 | total time = 239.79 ms / 120 tokens 0.48.787.406 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.48.787.407 I slot print_timing: id 1 | task 99 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.787.420 I slot release: id 1 | task 99 | stop processing: n_tokens = 119, truncated = 0 0.48.787.692 I slot print_timing: id 2 | task 100 | prompt eval time = 221.16 ms / 172 tokens ( 1.29 ms per token, 777.72 tokens per second) 0.48.787.695 I slot print_timing: id 2 | task 100 | eval time = 18.02 ms / 2 tokens ( 18.02 ms per token, 55.48 tokens per second) 0.48.787.696 I slot print_timing: id 2 | task 100 | total time = 239.18 ms / 174 tokens 0.48.787.696 I slot print_timing: id 2 | task 100 | graphs reused = 1 0.48.787.697 I slot print_timing: id 2 | task 100 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.787.709 I slot release: id 2 | task 100 | stop processing: n_tokens = 173, truncated = 0 0.48.787.948 I slot print_timing: id 3 | task 102 | prompt eval time = 220.87 ms / 107 tokens ( 2.06 ms per token, 484.45 tokens per second) 0.48.787.951 I slot print_timing: id 3 | task 102 | eval time = 17.70 ms / 2 tokens ( 17.70 ms per token, 56.51 tokens per second) 0.48.787.952 I slot print_timing: id 3 | task 102 | total time = 238.57 ms / 109 tokens 0.48.787.952 I slot print_timing: id 3 | task 102 | graphs reused = 1 0.48.787.953 I slot print_timing: id 3 | task 102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.787.962 I slot release: id 3 | task 102 | stop processing: n_tokens = 108, truncated = 0 0.48.795.833 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.244 0.48.812.891 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 0.48.862.077 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 0.48.862.233 I slot launch_slot_: id 3 | task 107 | processing task, is_child = 0 0.48.862.278 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.230 0.48.862.397 I slot launch_slot_: id 0 | task 108 | processing task, is_child = 0 0.48.862.423 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 0.48.862.524 I slot launch_slot_: id 2 | task 109 | processing task, is_child = 0 0.49.116.474 I slot print_timing: id 0 | task 108 | prompt eval time = 235.10 ms / 177 tokens ( 1.33 ms per token, 752.86 tokens per second) 0.49.116.479 I slot print_timing: id 0 | task 108 | eval time = 18.82 ms / 2 tokens ( 18.82 ms per token, 53.12 tokens per second) 0.49.116.480 I slot print_timing: id 0 | task 108 | total time = 253.93 ms / 179 tokens 0.49.116.481 I slot print_timing: id 0 | task 108 | graphs reused = 1 0.49.116.482 I slot print_timing: id 0 | task 108 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.116.509 I slot release: id 0 | task 108 | stop processing: n_tokens = 178, truncated = 0 0.49.116.835 I slot print_timing: id 1 | task 106 | prompt eval time = 234.86 ms / 116 tokens ( 2.02 ms per token, 493.90 tokens per second) 0.49.116.839 I slot print_timing: id 1 | task 106 | eval time = 18.60 ms / 2 tokens ( 18.60 ms per token, 53.76 tokens per second) 0.49.116.840 I slot print_timing: id 1 | task 106 | total time = 253.47 ms / 118 tokens 0.49.116.840 I slot print_timing: id 1 | task 106 | graphs reused = 1 0.49.116.841 I slot print_timing: id 1 | task 106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.116.854 I slot release: id 1 | task 106 | stop processing: n_tokens = 117, truncated = 0 0.49.117.194 I slot print_timing: id 2 | task 109 | prompt eval time = 234.63 ms / 240 tokens ( 0.98 ms per token, 1022.89 tokens per second) 0.49.117.197 I slot print_timing: id 2 | task 109 | eval time = 18.38 ms / 2 tokens ( 18.38 ms per token, 54.41 tokens per second) 0.49.117.198 I slot print_timing: id 2 | task 109 | total time = 253.01 ms / 242 tokens 0.49.117.198 I slot print_timing: id 2 | task 109 | graphs reused = 1 0.49.117.199 I slot print_timing: id 2 | task 109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.117.214 I slot release: id 2 | task 109 | stop processing: n_tokens = 241, truncated = 0 0.49.117.556 I slot print_timing: id 3 | task 107 | prompt eval time = 234.36 ms / 136 tokens ( 1.72 ms per token, 580.29 tokens per second) 0.49.117.559 I slot print_timing: id 3 | task 107 | eval time = 18.17 ms / 2 tokens ( 18.17 ms per token, 55.05 tokens per second) 0.49.117.560 I slot print_timing: id 3 | task 107 | total time = 252.53 ms / 138 tokens 0.49.117.560 I slot print_timing: id 3 | task 107 | graphs reused = 1 0.49.117.561 I slot print_timing: id 3 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.117.572 I slot release: id 3 | task 107 | stop processing: n_tokens = 137, truncated = 0 0.49.124.777 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.256 0.49.141.699 I slot launch_slot_: id 1 | task 113 | processing task, is_child = 0 0.49.191.518 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.157 0.49.191.689 I slot launch_slot_: id 0 | task 114 | processing task, is_child = 0 0.49.191.739 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 0.49.191.848 I slot launch_slot_: id 2 | task 115 | processing task, is_child = 0 0.49.191.873 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.212 0.49.200.068 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 0.49.481.866 I slot print_timing: id 0 | task 114 | prompt eval time = 262.33 ms / 160 tokens ( 1.64 ms per token, 609.91 tokens per second) 0.49.481.872 I slot print_timing: id 0 | task 114 | eval time = 19.45 ms / 2 tokens ( 19.45 ms per token, 51.42 tokens per second) 0.49.481.873 I slot print_timing: id 0 | task 114 | total time = 281.78 ms / 162 tokens 0.49.481.874 I slot print_timing: id 0 | task 114 | graphs reused = 1 0.49.481.874 I slot print_timing: id 0 | task 114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.481.901 I slot release: id 0 | task 114 | stop processing: n_tokens = 161, truncated = 0 0.49.482.203 I slot print_timing: id 1 | task 113 | prompt eval time = 262.22 ms / 155 tokens ( 1.69 ms per token, 591.10 tokens per second) 0.49.482.206 I slot print_timing: id 1 | task 113 | eval time = 19.06 ms / 2 tokens ( 19.06 ms per token, 52.46 tokens per second) 0.49.482.207 I slot print_timing: id 1 | task 113 | total time = 281.28 ms / 157 tokens 0.49.482.208 I slot print_timing: id 1 | task 113 | graphs reused = 1 0.49.482.208 I slot print_timing: id 1 | task 113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.482.222 I slot release: id 1 | task 113 | stop processing: n_tokens = 156, truncated = 0 0.49.482.522 I slot print_timing: id 2 | task 115 | prompt eval time = 262.10 ms / 226 tokens ( 1.16 ms per token, 862.28 tokens per second) 0.49.482.525 I slot print_timing: id 2 | task 115 | eval time = 18.69 ms / 2 tokens ( 18.69 ms per token, 53.51 tokens per second) 0.49.482.526 I slot print_timing: id 2 | task 115 | total time = 280.79 ms / 228 tokens 0.49.482.526 I slot print_timing: id 2 | task 115 | graphs reused = 1 0.49.482.527 I slot print_timing: id 2 | task 115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.482.544 I slot release: id 2 | task 115 | stop processing: n_tokens = 227, truncated = 0 0.49.482.833 I slot print_timing: id 3 | task 116 | prompt eval time = 261.94 ms / 142 tokens ( 1.84 ms per token, 542.10 tokens per second) 0.49.482.836 I slot print_timing: id 3 | task 116 | eval time = 18.30 ms / 2 tokens ( 18.30 ms per token, 54.63 tokens per second) 0.49.482.837 I slot print_timing: id 3 | task 116 | total time = 280.25 ms / 144 tokens 0.49.482.837 I slot print_timing: id 3 | task 116 | graphs reused = 1 0.49.482.838 I slot print_timing: id 3 | task 116 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.482.848 I slot release: id 3 | task 116 | stop processing: n_tokens = 143, truncated = 0 0.49.492.095 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.186 0.49.510.502 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 0.49.560.175 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 0.49.560.325 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.49.560.374 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.123 0.49.568.498 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.49.568.527 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 0.49.568.635 I slot launch_slot_: id 3 | task 123 | processing task, is_child = 0 0.49.821.837 I slot print_timing: id 0 | task 121 | prompt eval time = 233.26 ms / 141 tokens ( 1.65 ms per token, 604.48 tokens per second) 0.49.821.843 I slot print_timing: id 0 | task 121 | eval time = 19.92 ms / 2 tokens ( 19.92 ms per token, 50.19 tokens per second) 0.49.821.844 I slot print_timing: id 0 | task 121 | total time = 253.18 ms / 143 tokens 0.49.821.845 I slot print_timing: id 0 | task 121 | graphs reused = 1 0.49.821.846 I slot print_timing: id 0 | task 121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.821.872 I slot release: id 0 | task 121 | stop processing: n_tokens = 142, truncated = 0 0.49.822.192 I slot print_timing: id 1 | task 120 | prompt eval time = 233.25 ms / 114 tokens ( 2.05 ms per token, 488.76 tokens per second) 0.49.822.195 I slot print_timing: id 1 | task 120 | eval time = 19.47 ms / 2 tokens ( 19.47 ms per token, 51.36 tokens per second) 0.49.822.196 I slot print_timing: id 1 | task 120 | total time = 252.72 ms / 116 tokens 0.49.822.197 I slot print_timing: id 1 | task 120 | graphs reused = 1 0.49.822.198 I slot print_timing: id 1 | task 120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.822.210 I slot release: id 1 | task 120 | stop processing: n_tokens = 115, truncated = 0 0.49.822.533 I slot print_timing: id 2 | task 122 | prompt eval time = 233.23 ms / 192 tokens ( 1.21 ms per token, 823.23 tokens per second) 0.49.822.535 I slot print_timing: id 2 | task 122 | eval time = 19.01 ms / 2 tokens ( 19.01 ms per token, 52.60 tokens per second) 0.49.822.536 I slot print_timing: id 2 | task 122 | total time = 252.24 ms / 194 tokens 0.49.822.537 I slot print_timing: id 2 | task 122 | graphs reused = 1 0.49.822.538 I slot print_timing: id 2 | task 122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.822.553 I slot release: id 2 | task 122 | stop processing: n_tokens = 193, truncated = 0 0.49.822.857 I slot print_timing: id 3 | task 123 | prompt eval time = 233.18 ms / 105 tokens ( 2.22 ms per token, 450.29 tokens per second) 0.49.822.860 I slot print_timing: id 3 | task 123 | eval time = 18.63 ms / 2 tokens ( 18.63 ms per token, 53.68 tokens per second) 0.49.822.860 I slot print_timing: id 3 | task 123 | total time = 251.81 ms / 107 tokens 0.49.822.861 I slot print_timing: id 3 | task 123 | graphs reused = 1 0.49.822.861 I slot print_timing: id 3 | task 123 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.822.870 I slot release: id 3 | task 123 | stop processing: n_tokens = 106, truncated = 0 0.49.831.549 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.252 0.49.851.334 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 0.49.901.850 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.274 0.49.902.019 I slot launch_slot_: id 3 | task 127 | processing task, is_child = 0 0.49.902.067 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.197 0.49.902.185 I slot launch_slot_: id 0 | task 129 | processing task, is_child = 0 0.49.902.212 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.145 0.49.902.316 I slot launch_slot_: id 2 | task 130 | processing task, is_child = 0 0.50.145.349 I slot print_timing: id 0 | task 129 | prompt eval time = 223.46 ms / 172 tokens ( 1.30 ms per token, 769.70 tokens per second) 0.50.145.354 I slot print_timing: id 0 | task 129 | eval time = 19.55 ms / 2 tokens ( 19.55 ms per token, 51.15 tokens per second) 0.50.145.356 I slot print_timing: id 0 | task 129 | total time = 243.01 ms / 174 tokens 0.50.145.356 I slot print_timing: id 0 | task 129 | graphs reused = 1 0.50.145.357 I slot print_timing: id 0 | task 129 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.145.385 I slot release: id 0 | task 129 | stop processing: n_tokens = 173, truncated = 0 0.50.145.720 I slot print_timing: id 1 | task 128 | prompt eval time = 223.33 ms / 122 tokens ( 1.83 ms per token, 546.27 tokens per second) 0.50.145.724 I slot print_timing: id 1 | task 128 | eval time = 19.21 ms / 2 tokens ( 19.21 ms per token, 52.06 tokens per second) 0.50.145.724 I slot print_timing: id 1 | task 128 | total time = 242.54 ms / 124 tokens 0.50.145.725 I slot print_timing: id 1 | task 128 | graphs reused = 1 0.50.145.726 I slot print_timing: id 1 | task 128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.145.740 I slot release: id 1 | task 128 | stop processing: n_tokens = 123, truncated = 0 0.50.146.163 I slot print_timing: id 2 | task 130 | prompt eval time = 223.25 ms / 135 tokens ( 1.65 ms per token, 604.70 tokens per second) 0.50.146.166 I slot print_timing: id 2 | task 130 | eval time = 18.93 ms / 2 tokens ( 18.93 ms per token, 52.82 tokens per second) 0.50.146.167 I slot print_timing: id 2 | task 130 | total time = 242.18 ms / 137 tokens 0.50.146.168 I slot print_timing: id 2 | task 130 | graphs reused = 1 0.50.146.168 I slot print_timing: id 2 | task 130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.146.181 I slot release: id 2 | task 130 | stop processing: n_tokens = 136, truncated = 0 0.50.146.509 I slot print_timing: id 3 | task 127 | prompt eval time = 222.96 ms / 108 tokens ( 2.06 ms per token, 484.40 tokens per second) 0.50.146.513 I slot print_timing: id 3 | task 127 | eval time = 18.71 ms / 2 tokens ( 18.71 ms per token, 53.44 tokens per second) 0.50.146.514 I slot print_timing: id 3 | task 127 | total time = 241.67 ms / 110 tokens 0.50.146.514 I slot print_timing: id 3 | task 127 | graphs reused = 1 0.50.146.514 I slot print_timing: id 3 | task 127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.146.525 I slot release: id 3 | task 127 | stop processing: n_tokens = 109, truncated = 0 0.50.154.940 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.162 0.50.172.085 I slot launch_slot_: id 0 | task 135 | processing task, is_child = 0 0.50.221.161 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 0.50.229.213 I slot launch_slot_: id 1 | task 134 | processing task, is_child = 0 0.50.229.264 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.206 0.50.229.379 I slot launch_slot_: id 2 | task 136 | processing task, is_child = 0 0.50.229.403 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.257 0.50.229.504 I slot launch_slot_: id 3 | task 137 | processing task, is_child = 0 0.50.480.853 I slot print_timing: id 0 | task 135 | prompt eval time = 231.76 ms / 134 tokens ( 1.73 ms per token, 578.18 tokens per second) 0.50.480.858 I slot print_timing: id 0 | task 135 | eval time = 19.57 ms / 2 tokens ( 19.57 ms per token, 51.10 tokens per second) 0.50.480.859 I slot print_timing: id 0 | task 135 | total time = 251.33 ms / 136 tokens 0.50.480.860 I slot print_timing: id 0 | task 135 | graphs reused = 1 0.50.480.861 I slot print_timing: id 0 | task 135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.480.885 I slot release: id 0 | task 135 | stop processing: n_tokens = 135, truncated = 0 0.50.481.203 I slot print_timing: id 1 | task 134 | prompt eval time = 231.66 ms / 120 tokens ( 1.93 ms per token, 518.00 tokens per second) 0.50.481.206 I slot print_timing: id 1 | task 134 | eval time = 19.16 ms / 2 tokens ( 19.16 ms per token, 52.20 tokens per second) 0.50.481.206 I slot print_timing: id 1 | task 134 | total time = 250.82 ms / 122 tokens 0.50.481.207 I slot print_timing: id 1 | task 134 | graphs reused = 1 0.50.481.208 I slot print_timing: id 1 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.481.221 I slot release: id 1 | task 134 | stop processing: n_tokens = 121, truncated = 0 0.50.481.547 I slot print_timing: id 2 | task 136 | prompt eval time = 231.69 ms / 135 tokens ( 1.72 ms per token, 582.69 tokens per second) 0.50.481.550 I slot print_timing: id 2 | task 136 | eval time = 18.73 ms / 2 tokens ( 18.73 ms per token, 53.38 tokens per second) 0.50.481.551 I slot print_timing: id 2 | task 136 | total time = 250.42 ms / 137 tokens 0.50.481.551 I slot print_timing: id 2 | task 136 | graphs reused = 1 0.50.481.552 I slot print_timing: id 2 | task 136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.481.563 I slot release: id 2 | task 136 | stop processing: n_tokens = 136, truncated = 0 0.50.481.846 I slot print_timing: id 3 | task 137 | prompt eval time = 231.54 ms / 159 tokens ( 1.46 ms per token, 686.72 tokens per second) 0.50.481.849 I slot print_timing: id 3 | task 137 | eval time = 18.34 ms / 2 tokens ( 18.34 ms per token, 54.52 tokens per second) 0.50.481.849 I slot print_timing: id 3 | task 137 | total time = 249.88 ms / 161 tokens 0.50.481.850 I slot print_timing: id 3 | task 137 | graphs reused = 1 0.50.481.850 I slot print_timing: id 3 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.481.864 I slot release: id 3 | task 137 | stop processing: n_tokens = 160, truncated = 0 0.50.489.263 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.207 0.50.508.787 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 0.50.557.936 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.231 0.50.558.081 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 0.50.558.128 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.206 0.50.558.240 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 0.50.558.267 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.175 0.50.558.376 I slot launch_slot_: id 3 | task 144 | processing task, is_child = 0 0.50.822.978 I slot print_timing: id 0 | task 141 | prompt eval time = 245.10 ms / 130 tokens ( 1.89 ms per token, 530.40 tokens per second) 0.50.822.984 I slot print_timing: id 0 | task 141 | eval time = 19.48 ms / 2 tokens ( 19.48 ms per token, 51.32 tokens per second) 0.50.822.985 I slot print_timing: id 0 | task 141 | total time = 264.58 ms / 132 tokens 0.50.822.985 I slot print_timing: id 0 | task 141 | graphs reused = 1 0.50.822.986 I slot print_timing: id 0 | task 141 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.823.013 I slot release: id 0 | task 141 | stop processing: n_tokens = 131, truncated = 0 0.50.823.400 I slot print_timing: id 1 | task 142 | prompt eval time = 245.09 ms / 175 tokens ( 1.40 ms per token, 714.03 tokens per second) 0.50.823.403 I slot print_timing: id 1 | task 142 | eval time = 19.09 ms / 2 tokens ( 19.09 ms per token, 52.39 tokens per second) 0.50.823.404 I slot print_timing: id 1 | task 142 | total time = 264.18 ms / 177 tokens 0.50.823.405 I slot print_timing: id 1 | task 142 | graphs reused = 1 0.50.823.405 I slot print_timing: id 1 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.823.423 I slot release: id 1 | task 142 | stop processing: n_tokens = 176, truncated = 0 0.50.823.777 I slot print_timing: id 2 | task 143 | prompt eval time = 244.96 ms / 172 tokens ( 1.42 ms per token, 702.14 tokens per second) 0.50.823.780 I slot print_timing: id 2 | task 143 | eval time = 18.76 ms / 2 tokens ( 18.76 ms per token, 53.31 tokens per second) 0.50.823.781 I slot print_timing: id 2 | task 143 | total time = 263.72 ms / 174 tokens 0.50.823.781 I slot print_timing: id 2 | task 143 | graphs reused = 1 0.50.823.782 I slot print_timing: id 2 | task 143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.823.797 I slot release: id 2 | task 143 | stop processing: n_tokens = 173, truncated = 0 0.50.824.161 I slot print_timing: id 3 | task 144 | prompt eval time = 244.73 ms / 180 tokens ( 1.36 ms per token, 735.49 tokens per second) 0.50.824.167 I slot print_timing: id 3 | task 144 | eval time = 18.56 ms / 2 tokens ( 18.56 ms per token, 53.88 tokens per second) 0.50.824.168 I slot print_timing: id 3 | task 144 | total time = 263.29 ms / 182 tokens 0.50.824.170 I slot print_timing: id 3 | task 144 | graphs reused = 1 0.50.824.171 I slot print_timing: id 3 | task 144 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.824.193 I slot release: id 3 | task 144 | stop processing: n_tokens = 181, truncated = 0 0.50.832.665 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 0.50.849.712 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 0.50.899.894 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.159 0.50.908.074 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 0.50.908.126 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.162 0.50.916.549 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 0.50.916.582 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.155 0.50.916.688 I slot launch_slot_: id 3 | task 151 | processing task, is_child = 0 0.51.115.987 I slot print_timing: id 0 | task 148 | prompt eval time = 180.60 ms / 123 tokens ( 1.47 ms per token, 681.06 tokens per second) 0.51.115.992 I slot print_timing: id 0 | task 148 | eval time = 18.68 ms / 2 tokens ( 18.68 ms per token, 53.53 tokens per second) 0.51.115.993 I slot print_timing: id 0 | task 148 | total time = 199.28 ms / 125 tokens 0.51.115.994 I slot print_timing: id 0 | task 148 | graphs reused = 1 0.51.115.995 I slot print_timing: id 0 | task 148 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.116.020 I slot release: id 0 | task 148 | stop processing: n_tokens = 124, truncated = 0 0.51.116.321 I slot print_timing: id 1 | task 149 | prompt eval time = 180.33 ms / 123 tokens ( 1.47 ms per token, 682.09 tokens per second) 0.51.116.324 I slot print_timing: id 1 | task 149 | eval time = 18.46 ms / 2 tokens ( 18.46 ms per token, 54.17 tokens per second) 0.51.116.325 I slot print_timing: id 1 | task 149 | total time = 198.79 ms / 125 tokens 0.51.116.326 I slot print_timing: id 1 | task 149 | graphs reused = 1 0.51.116.327 I slot print_timing: id 1 | task 149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.116.341 I slot release: id 1 | task 149 | stop processing: n_tokens = 124, truncated = 0 0.51.116.641 I slot print_timing: id 2 | task 150 | prompt eval time = 180.16 ms / 115 tokens ( 1.57 ms per token, 638.31 tokens per second) 0.51.116.645 I slot print_timing: id 2 | task 150 | eval time = 18.20 ms / 2 tokens ( 18.20 ms per token, 54.95 tokens per second) 0.51.116.645 I slot print_timing: id 2 | task 150 | total time = 198.36 ms / 117 tokens 0.51.116.646 I slot print_timing: id 2 | task 150 | graphs reused = 1 0.51.116.647 I slot print_timing: id 2 | task 150 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.116.659 I slot release: id 2 | task 150 | stop processing: n_tokens = 116, truncated = 0 0.51.116.961 I slot print_timing: id 3 | task 151 | prompt eval time = 179.98 ms / 115 tokens ( 1.57 ms per token, 638.95 tokens per second) 0.51.116.965 I slot print_timing: id 3 | task 151 | eval time = 17.93 ms / 2 tokens ( 17.93 ms per token, 55.76 tokens per second) 0.51.116.966 I slot print_timing: id 3 | task 151 | total time = 197.91 ms / 117 tokens 0.51.116.966 I slot print_timing: id 3 | task 151 | graphs reused = 1 0.51.116.967 I slot print_timing: id 3 | task 151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.116.977 I slot release: id 3 | task 151 | stop processing: n_tokens = 116, truncated = 0 0.51.125.001 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 0.51.141.981 I slot launch_slot_: id 2 | task 155 | processing task, is_child = 0 0.51.192.558 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 0.51.192.735 I slot launch_slot_: id 0 | task 156 | processing task, is_child = 0 0.51.192.782 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 0.51.200.994 I slot launch_slot_: id 1 | task 157 | processing task, is_child = 0 0.51.201.024 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.241 0.51.201.135 I slot launch_slot_: id 3 | task 158 | processing task, is_child = 0 0.51.442.529 I slot print_timing: id 0 | task 156 | prompt eval time = 221.85 ms / 141 tokens ( 1.57 ms per token, 635.56 tokens per second) 0.51.442.535 I slot print_timing: id 0 | task 156 | eval time = 19.52 ms / 2 tokens ( 19.52 ms per token, 51.22 tokens per second) 0.51.442.536 I slot print_timing: id 0 | task 156 | total time = 241.38 ms / 143 tokens 0.51.442.537 I slot print_timing: id 0 | task 156 | graphs reused = 1 0.51.442.538 I slot print_timing: id 0 | task 156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.442.563 I slot release: id 0 | task 156 | stop processing: n_tokens = 142, truncated = 0 0.51.442.887 I slot print_timing: id 1 | task 157 | prompt eval time = 221.81 ms / 128 tokens ( 1.73 ms per token, 577.08 tokens per second) 0.51.442.890 I slot print_timing: id 1 | task 157 | eval time = 19.12 ms / 2 tokens ( 19.12 ms per token, 52.29 tokens per second) 0.51.442.891 I slot print_timing: id 1 | task 157 | total time = 240.93 ms / 130 tokens 0.51.442.892 I slot print_timing: id 1 | task 157 | graphs reused = 1 0.51.442.892 I slot print_timing: id 1 | task 157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.442.905 I slot release: id 1 | task 157 | stop processing: n_tokens = 129, truncated = 0 0.51.443.228 I slot print_timing: id 2 | task 155 | prompt eval time = 221.76 ms / 127 tokens ( 1.75 ms per token, 572.69 tokens per second) 0.51.443.231 I slot print_timing: id 2 | task 155 | eval time = 18.70 ms / 2 tokens ( 18.70 ms per token, 53.46 tokens per second) 0.51.443.231 I slot print_timing: id 2 | task 155 | total time = 240.47 ms / 129 tokens 0.51.443.232 I slot print_timing: id 2 | task 155 | graphs reused = 1 0.51.443.232 I slot print_timing: id 2 | task 155 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.443.243 I slot release: id 2 | task 155 | stop processing: n_tokens = 128, truncated = 0 0.51.443.528 I slot print_timing: id 3 | task 158 | prompt eval time = 221.62 ms / 130 tokens ( 1.70 ms per token, 586.59 tokens per second) 0.51.443.532 I slot print_timing: id 3 | task 158 | eval time = 18.32 ms / 2 tokens ( 18.32 ms per token, 54.59 tokens per second) 0.51.443.532 I slot print_timing: id 3 | task 158 | total time = 239.94 ms / 132 tokens 0.51.443.533 I slot print_timing: id 3 | task 158 | graphs reused = 1 0.51.443.533 I slot print_timing: id 3 | task 158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.443.542 I slot release: id 3 | task 158 | stop processing: n_tokens = 131, truncated = 0 0.51.452.031 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.197 0.51.474.125 I slot launch_slot_: id 0 | task 163 | processing task, is_child = 0 0.51.474.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 0.51.498.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.129 MiB) 0.51.521.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.51.544.532 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.217 0.51.544.708 I slot launch_slot_: id 1 | task 162 | processing task, is_child = 0 0.51.544.754 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 0.51.544.876 I slot launch_slot_: id 2 | task 164 | processing task, is_child = 0 0.51.544.902 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 0.51.545.010 I slot launch_slot_: id 3 | task 165 | processing task, is_child = 0 0.51.791.840 I slot print_timing: id 0 | task 163 | prompt eval time = 227.39 ms / 123 tokens ( 1.85 ms per token, 540.92 tokens per second) 0.51.791.845 I slot print_timing: id 0 | task 163 | eval time = 19.42 ms / 2 tokens ( 19.42 ms per token, 51.48 tokens per second) 0.51.791.847 I slot print_timing: id 0 | task 163 | total time = 246.81 ms / 125 tokens 0.51.791.847 I slot print_timing: id 0 | task 163 | graphs reused = 1 0.51.791.848 I slot print_timing: id 0 | task 163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.791.872 I slot release: id 0 | task 163 | stop processing: n_tokens = 124, truncated = 0 0.51.792.168 I slot print_timing: id 1 | task 162 | prompt eval time = 227.28 ms / 129 tokens ( 1.76 ms per token, 567.58 tokens per second) 0.51.792.172 I slot print_timing: id 1 | task 162 | eval time = 19.03 ms / 2 tokens ( 19.03 ms per token, 52.55 tokens per second) 0.51.792.173 I slot print_timing: id 1 | task 162 | total time = 246.31 ms / 131 tokens 0.51.792.173 I slot print_timing: id 1 | task 162 | graphs reused = 1 0.51.792.174 I slot print_timing: id 1 | task 162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.792.188 I slot release: id 1 | task 162 | stop processing: n_tokens = 130, truncated = 0 0.51.792.541 I slot print_timing: id 2 | task 164 | prompt eval time = 227.19 ms / 105 tokens ( 2.16 ms per token, 462.17 tokens per second) 0.51.792.544 I slot print_timing: id 2 | task 164 | eval time = 18.65 ms / 2 tokens ( 18.65 ms per token, 53.62 tokens per second) 0.51.792.545 I slot print_timing: id 2 | task 164 | total time = 245.84 ms / 107 tokens 0.51.792.546 I slot print_timing: id 2 | task 164 | graphs reused = 1 0.51.792.546 I slot print_timing: id 2 | task 164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.792.557 I slot release: id 2 | task 164 | stop processing: n_tokens = 106, truncated = 0 0.51.792.935 I slot print_timing: id 3 | task 165 | prompt eval time = 227.08 ms / 161 tokens ( 1.41 ms per token, 709.00 tokens per second) 0.51.792.939 I slot print_timing: id 3 | task 165 | eval time = 18.30 ms / 2 tokens ( 18.30 ms per token, 54.65 tokens per second) 0.51.792.939 I slot print_timing: id 3 | task 165 | total time = 245.38 ms / 163 tokens 0.51.792.940 I slot print_timing: id 3 | task 165 | graphs reused = 1 0.51.792.940 I slot print_timing: id 3 | task 165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.792.956 I slot release: id 3 | task 165 | stop processing: n_tokens = 162, truncated = 0 0.51.800.660 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.226 0.51.800.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 0.51.824.143 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 0.51.824.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 0.51.864.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.787 MiB) 0.51.887.980 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 0.51.888.154 I slot launch_slot_: id 2 | task 170 | processing task, is_child = 0 0.51.888.202 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.215 0.51.888.317 I slot launch_slot_: id 1 | task 171 | processing task, is_child = 0 0.51.888.343 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.173 0.51.888.449 I slot launch_slot_: id 3 | task 172 | processing task, is_child = 0 0.52.126.122 I slot print_timing: id 0 | task 169 | prompt eval time = 219.13 ms / 141 tokens ( 1.55 ms per token, 643.45 tokens per second) 0.52.126.128 I slot print_timing: id 0 | task 169 | eval time = 18.53 ms / 2 tokens ( 18.53 ms per token, 53.98 tokens per second) 0.52.126.129 I slot print_timing: id 0 | task 169 | total time = 237.66 ms / 143 tokens 0.52.126.130 I slot print_timing: id 0 | task 169 | graphs reused = 1 0.52.126.131 I slot print_timing: id 0 | task 169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.126.157 I slot release: id 0 | task 169 | stop processing: n_tokens = 142, truncated = 0 0.52.126.489 I slot print_timing: id 1 | task 171 | prompt eval time = 218.88 ms / 164 tokens ( 1.33 ms per token, 749.25 tokens per second) 0.52.126.492 I slot print_timing: id 1 | task 171 | eval time = 18.32 ms / 2 tokens ( 18.32 ms per token, 54.57 tokens per second) 0.52.126.493 I slot print_timing: id 1 | task 171 | total time = 237.21 ms / 166 tokens 0.52.126.494 I slot print_timing: id 1 | task 171 | graphs reused = 1 0.52.126.495 I slot print_timing: id 1 | task 171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.126.517 I slot release: id 1 | task 171 | stop processing: n_tokens = 165, truncated = 0 0.52.126.811 I slot print_timing: id 2 | task 170 | prompt eval time = 218.60 ms / 110 tokens ( 1.99 ms per token, 503.20 tokens per second) 0.52.126.814 I slot print_timing: id 2 | task 170 | eval time = 18.08 ms / 2 tokens ( 18.08 ms per token, 55.31 tokens per second) 0.52.126.815 I slot print_timing: id 2 | task 170 | total time = 236.68 ms / 112 tokens 0.52.126.815 I slot print_timing: id 2 | task 170 | graphs reused = 1 0.52.126.816 I slot print_timing: id 2 | task 170 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.126.828 I slot release: id 2 | task 170 | stop processing: n_tokens = 111, truncated = 0 0.52.127.126 I slot print_timing: id 3 | task 172 | prompt eval time = 218.32 ms / 154 tokens ( 1.42 ms per token, 705.39 tokens per second) 0.52.127.129 I slot print_timing: id 3 | task 172 | eval time = 17.84 ms / 2 tokens ( 17.84 ms per token, 56.07 tokens per second) 0.52.127.130 I slot print_timing: id 3 | task 172 | total time = 236.15 ms / 156 tokens 0.52.127.130 I slot print_timing: id 3 | task 172 | graphs reused = 1 0.52.127.131 I slot print_timing: id 3 | task 172 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.127.142 I slot release: id 3 | task 172 | stop processing: n_tokens = 155, truncated = 0 0.52.134.541 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.197 0.52.134.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.224 MiB) 0.52.158.244 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 0.52.158.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.223 MiB) 0.52.181.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 0.52.204.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 0.52.227.575 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.170 0.52.227.747 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 0.52.227.791 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 0.52.227.902 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 0.52.227.928 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.181 0.52.228.030 I slot launch_slot_: id 3 | task 179 | processing task, is_child = 0 0.52.450.137 I slot print_timing: id 0 | task 176 | prompt eval time = 203.03 ms / 110 tokens ( 1.85 ms per token, 541.78 tokens per second) 0.52.450.142 I slot print_timing: id 0 | task 176 | eval time = 19.06 ms / 2 tokens ( 19.06 ms per token, 52.47 tokens per second) 0.52.450.144 I slot print_timing: id 0 | task 176 | total time = 222.09 ms / 112 tokens 0.52.450.144 I slot print_timing: id 0 | task 176 | graphs reused = 1 0.52.450.145 I slot print_timing: id 0 | task 176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.450.168 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 0.52.450.493 I slot print_timing: id 1 | task 177 | prompt eval time = 202.96 ms / 137 tokens ( 1.48 ms per token, 675.02 tokens per second) 0.52.450.496 I slot print_timing: id 1 | task 177 | eval time = 18.66 ms / 2 tokens ( 18.66 ms per token, 53.60 tokens per second) 0.52.450.497 I slot print_timing: id 1 | task 177 | total time = 221.62 ms / 139 tokens 0.52.450.497 I slot print_timing: id 1 | task 177 | graphs reused = 1 0.52.450.498 I slot print_timing: id 1 | task 177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.450.513 I slot release: id 1 | task 177 | stop processing: n_tokens = 138, truncated = 0 0.52.450.807 I slot print_timing: id 2 | task 178 | prompt eval time = 202.88 ms / 110 tokens ( 1.84 ms per token, 542.19 tokens per second) 0.52.450.810 I slot print_timing: id 2 | task 178 | eval time = 18.20 ms / 2 tokens ( 18.20 ms per token, 54.95 tokens per second) 0.52.450.811 I slot print_timing: id 2 | task 178 | total time = 221.08 ms / 112 tokens 0.52.450.812 I slot print_timing: id 2 | task 178 | graphs reused = 1 0.52.450.812 I slot print_timing: id 2 | task 178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.450.822 I slot release: id 2 | task 178 | stop processing: n_tokens = 111, truncated = 0 0.52.451.173 I slot print_timing: id 3 | task 179 | prompt eval time = 202.79 ms / 148 tokens ( 1.37 ms per token, 729.83 tokens per second) 0.52.451.176 I slot print_timing: id 3 | task 179 | eval time = 17.83 ms / 2 tokens ( 17.83 ms per token, 56.09 tokens per second) 0.52.451.176 I slot print_timing: id 3 | task 179 | total time = 220.62 ms / 150 tokens 0.52.451.177 I slot print_timing: id 3 | task 179 | graphs reused = 1 0.52.451.177 I slot print_timing: id 3 | task 179 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.451.190 I slot release: id 3 | task 179 | stop processing: n_tokens = 149, truncated = 0 0.52.459.707 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 0.52.459.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.254 MiB) 0.52.483.140 I slot launch_slot_: id 2 | task 183 | processing task, is_child = 0 0.52.483.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 0.52.505.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.193 MiB) 0.52.529.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 0.52.552.452 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 0.52.552.629 I slot launch_slot_: id 0 | task 184 | processing task, is_child = 0 0.52.552.679 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.203 0.52.552.801 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 0.52.552.828 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.188 0.52.552.932 I slot launch_slot_: id 3 | task 186 | processing task, is_child = 0 0.52.789.553 I slot print_timing: id 0 | task 184 | prompt eval time = 217.73 ms / 152 tokens ( 1.43 ms per token, 698.11 tokens per second) 0.52.789.558 I slot print_timing: id 0 | task 184 | eval time = 18.87 ms / 2 tokens ( 18.87 ms per token, 52.98 tokens per second) 0.52.789.559 I slot print_timing: id 0 | task 184 | total time = 236.60 ms / 154 tokens 0.52.789.560 I slot print_timing: id 0 | task 184 | graphs reused = 1 0.52.789.561 I slot print_timing: id 0 | task 184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.789.586 I slot release: id 0 | task 184 | stop processing: n_tokens = 153, truncated = 0 0.52.789.861 I slot print_timing: id 1 | task 185 | prompt eval time = 217.56 ms / 123 tokens ( 1.77 ms per token, 565.36 tokens per second) 0.52.789.864 I slot print_timing: id 1 | task 185 | eval time = 18.48 ms / 2 tokens ( 18.48 ms per token, 54.12 tokens per second) 0.52.789.865 I slot print_timing: id 1 | task 185 | total time = 236.04 ms / 125 tokens 0.52.789.866 I slot print_timing: id 1 | task 185 | graphs reused = 1 0.52.789.867 I slot print_timing: id 1 | task 185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.789.879 I slot release: id 1 | task 185 | stop processing: n_tokens = 124, truncated = 0 0.52.790.166 I slot print_timing: id 2 | task 183 | prompt eval time = 217.41 ms / 112 tokens ( 1.94 ms per token, 515.16 tokens per second) 0.52.790.169 I slot print_timing: id 2 | task 183 | eval time = 18.07 ms / 2 tokens ( 18.07 ms per token, 55.35 tokens per second) 0.52.790.170 I slot print_timing: id 2 | task 183 | total time = 235.48 ms / 114 tokens 0.52.790.170 I slot print_timing: id 2 | task 183 | graphs reused = 1 0.52.790.171 I slot print_timing: id 2 | task 183 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.790.183 I slot release: id 2 | task 183 | stop processing: n_tokens = 113, truncated = 0 0.52.790.525 I slot print_timing: id 3 | task 186 | prompt eval time = 217.30 ms / 130 tokens ( 1.67 ms per token, 598.25 tokens per second) 0.52.790.527 I slot print_timing: id 3 | task 186 | eval time = 17.68 ms / 2 tokens ( 17.68 ms per token, 56.55 tokens per second) 0.52.790.528 I slot print_timing: id 3 | task 186 | total time = 234.98 ms / 132 tokens 0.52.790.528 I slot print_timing: id 3 | task 186 | graphs reused = 1 0.52.790.529 I slot print_timing: id 3 | task 186 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.790.540 I slot release: id 3 | task 186 | stop processing: n_tokens = 131, truncated = 0 0.52.797.978 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 0.52.798.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.52.821.529 I slot launch_slot_: id 2 | task 190 | processing task, is_child = 0 0.52.821.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.52.845.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.099 MiB) 0.52.868.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.52.892.222 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 0.52.892.413 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 0.52.892.464 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 0.52.892.583 I slot launch_slot_: id 3 | task 192 | processing task, is_child = 0 0.52.892.623 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 0.52.892.740 I slot launch_slot_: id 1 | task 193 | processing task, is_child = 0 0.53.137.083 I slot print_timing: id 0 | task 191 | prompt eval time = 225.76 ms / 157 tokens ( 1.44 ms per token, 695.41 tokens per second) 0.53.137.089 I slot print_timing: id 0 | task 191 | eval time = 18.56 ms / 2 tokens ( 18.56 ms per token, 53.87 tokens per second) 0.53.137.090 I slot print_timing: id 0 | task 191 | total time = 244.33 ms / 159 tokens 0.53.137.091 I slot print_timing: id 0 | task 191 | graphs reused = 1 0.53.137.091 I slot print_timing: id 0 | task 191 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.137.117 I slot release: id 0 | task 191 | stop processing: n_tokens = 158, truncated = 0 0.53.137.412 I slot print_timing: id 1 | task 193 | prompt eval time = 225.56 ms / 166 tokens ( 1.36 ms per token, 735.94 tokens per second) 0.53.137.415 I slot print_timing: id 1 | task 193 | eval time = 18.22 ms / 2 tokens ( 18.22 ms per token, 54.87 tokens per second) 0.53.137.416 I slot print_timing: id 1 | task 193 | total time = 243.78 ms / 168 tokens 0.53.137.416 I slot print_timing: id 1 | task 193 | graphs reused = 1 0.53.137.417 I slot print_timing: id 1 | task 193 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.137.433 I slot release: id 1 | task 193 | stop processing: n_tokens = 167, truncated = 0 0.53.137.659 I slot print_timing: id 2 | task 190 | prompt eval time = 225.20 ms / 114 tokens ( 1.98 ms per token, 506.22 tokens per second) 0.53.137.662 I slot print_timing: id 2 | task 190 | eval time = 17.91 ms / 2 tokens ( 17.91 ms per token, 55.83 tokens per second) 0.53.137.663 I slot print_timing: id 2 | task 190 | total time = 243.11 ms / 116 tokens 0.53.137.663 I slot print_timing: id 2 | task 190 | graphs reused = 1 0.53.137.664 I slot print_timing: id 2 | task 190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.137.673 I slot release: id 2 | task 190 | stop processing: n_tokens = 115, truncated = 0 0.53.137.908 I slot print_timing: id 3 | task 192 | prompt eval time = 224.77 ms / 128 tokens ( 1.76 ms per token, 569.46 tokens per second) 0.53.137.911 I slot print_timing: id 3 | task 192 | eval time = 17.61 ms / 2 tokens ( 17.61 ms per token, 56.77 tokens per second) 0.53.137.911 I slot print_timing: id 3 | task 192 | total time = 242.39 ms / 130 tokens 0.53.137.912 I slot print_timing: id 3 | task 192 | graphs reused = 1 0.53.137.912 I slot print_timing: id 3 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.137.921 I slot release: id 3 | task 192 | stop processing: n_tokens = 129, truncated = 0 0.53.146.943 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.177 0.53.146.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.066 MiB) 0.53.170.622 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 0.53.170.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 0.53.193.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 0.53.216.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.53.239.948 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 0.53.240.113 I slot launch_slot_: id 1 | task 198 | processing task, is_child = 0 0.53.240.157 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.243 0.53.240.255 I slot launch_slot_: id 2 | task 200 | processing task, is_child = 0 0.53.240.279 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.217 0.53.248.461 I slot launch_slot_: id 3 | task 199 | processing task, is_child = 0 0.53.499.690 I slot print_timing: id 0 | task 197 | prompt eval time = 232.24 ms / 179 tokens ( 1.30 ms per token, 770.77 tokens per second) 0.53.499.696 I slot print_timing: id 0 | task 197 | eval time = 18.98 ms / 2 tokens ( 18.98 ms per token, 52.70 tokens per second) 0.53.499.698 I slot print_timing: id 0 | task 197 | total time = 251.21 ms / 181 tokens 0.53.499.698 I slot print_timing: id 0 | task 197 | graphs reused = 1 0.53.499.699 I slot print_timing: id 0 | task 197 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.499.725 I slot release: id 0 | task 197 | stop processing: n_tokens = 180, truncated = 0 0.53.500.004 I slot print_timing: id 1 | task 198 | prompt eval time = 232.10 ms / 153 tokens ( 1.52 ms per token, 659.19 tokens per second) 0.53.500.007 I slot print_timing: id 1 | task 198 | eval time = 18.55 ms / 2 tokens ( 18.55 ms per token, 53.91 tokens per second) 0.53.500.008 I slot print_timing: id 1 | task 198 | total time = 250.65 ms / 155 tokens 0.53.500.008 I slot print_timing: id 1 | task 198 | graphs reused = 1 0.53.500.009 I slot print_timing: id 1 | task 198 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.500.021 I slot release: id 1 | task 198 | stop processing: n_tokens = 154, truncated = 0 0.53.500.316 I slot print_timing: id 2 | task 200 | prompt eval time = 232.00 ms / 108 tokens ( 2.15 ms per token, 465.52 tokens per second) 0.53.500.319 I slot print_timing: id 2 | task 200 | eval time = 18.14 ms / 2 tokens ( 18.14 ms per token, 55.12 tokens per second) 0.53.500.319 I slot print_timing: id 2 | task 200 | total time = 250.14 ms / 110 tokens 0.53.500.320 I slot print_timing: id 2 | task 200 | graphs reused = 1 0.53.500.320 I slot print_timing: id 2 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.500.330 I slot release: id 2 | task 200 | stop processing: n_tokens = 109, truncated = 0 0.53.500.614 I slot print_timing: id 3 | task 199 | prompt eval time = 231.91 ms / 141 tokens ( 1.64 ms per token, 607.98 tokens per second) 0.53.500.618 I slot print_timing: id 3 | task 199 | eval time = 17.73 ms / 2 tokens ( 17.73 ms per token, 56.40 tokens per second) 0.53.500.618 I slot print_timing: id 3 | task 199 | total time = 249.65 ms / 143 tokens 0.53.500.619 I slot print_timing: id 3 | task 199 | graphs reused = 1 0.53.500.620 I slot print_timing: id 3 | task 199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.500.630 I slot release: id 3 | task 199 | stop processing: n_tokens = 142, truncated = 0 0.53.509.550 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.156 0.53.535.530 I slot launch_slot_: id 0 | task 205 | processing task, is_child = 0 0.53.535.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 0.53.579.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 0.53.601.950 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.182 0.53.602.091 I slot launch_slot_: id 1 | task 204 | processing task, is_child = 0 0.53.602.135 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.257 0.53.602.241 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 0.53.602.266 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.197 0.53.602.367 I slot launch_slot_: id 3 | task 207 | processing task, is_child = 0 0.53.842.641 I slot print_timing: id 0 | task 205 | prompt eval time = 220.83 ms / 116 tokens ( 1.90 ms per token, 525.30 tokens per second) 0.53.842.646 I slot print_timing: id 0 | task 205 | eval time = 19.43 ms / 2 tokens ( 19.43 ms per token, 51.47 tokens per second) 0.53.842.647 I slot print_timing: id 0 | task 205 | total time = 240.25 ms / 118 tokens 0.53.842.648 I slot print_timing: id 0 | task 205 | graphs reused = 1 0.53.842.649 I slot print_timing: id 0 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.842.673 I slot release: id 0 | task 205 | stop processing: n_tokens = 117, truncated = 0 0.53.843.003 I slot print_timing: id 1 | task 204 | prompt eval time = 220.91 ms / 135 tokens ( 1.64 ms per token, 611.12 tokens per second) 0.53.843.006 I slot print_timing: id 1 | task 204 | eval time = 18.93 ms / 2 tokens ( 18.93 ms per token, 52.82 tokens per second) 0.53.843.007 I slot print_timing: id 1 | task 204 | total time = 239.84 ms / 137 tokens 0.53.843.007 I slot print_timing: id 1 | task 204 | graphs reused = 1 0.53.843.008 I slot print_timing: id 1 | task 204 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.843.022 I slot release: id 1 | task 204 | stop processing: n_tokens = 136, truncated = 0 0.53.843.358 I slot print_timing: id 2 | task 206 | prompt eval time = 220.90 ms / 134 tokens ( 1.65 ms per token, 606.61 tokens per second) 0.53.843.362 I slot print_timing: id 2 | task 206 | eval time = 18.46 ms / 2 tokens ( 18.46 ms per token, 54.18 tokens per second) 0.53.843.362 I slot print_timing: id 2 | task 206 | total time = 239.36 ms / 136 tokens 0.53.843.363 I slot print_timing: id 2 | task 206 | graphs reused = 1 0.53.843.364 I slot print_timing: id 2 | task 206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.843.375 I slot release: id 2 | task 206 | stop processing: n_tokens = 135, truncated = 0 0.53.843.700 I slot print_timing: id 3 | task 207 | prompt eval time = 220.87 ms / 158 tokens ( 1.40 ms per token, 715.35 tokens per second) 0.53.843.703 I slot print_timing: id 3 | task 207 | eval time = 18.01 ms / 2 tokens ( 18.01 ms per token, 55.53 tokens per second) 0.53.843.704 I slot print_timing: id 3 | task 207 | total time = 238.88 ms / 160 tokens 0.53.843.705 I slot print_timing: id 3 | task 207 | graphs reused = 1 0.53.843.705 I slot print_timing: id 3 | task 207 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.843.717 I slot release: id 3 | task 207 | stop processing: n_tokens = 159, truncated = 0 0.53.851.293 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.239 0.53.851.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 0.53.874.953 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 0.53.874.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 0.53.897.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 0.53.899.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 0.53.945.172 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.206 0.53.953.453 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 0.53.953.515 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.207 0.53.953.637 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 0.53.953.667 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.176 0.53.961.685 I slot launch_slot_: id 3 | task 214 | processing task, is_child = 0 0.54.200.154 I slot print_timing: id 0 | task 211 | prompt eval time = 220.09 ms / 149 tokens ( 1.48 ms per token, 676.99 tokens per second) 0.54.200.160 I slot print_timing: id 0 | task 211 | eval time = 18.36 ms / 2 tokens ( 18.36 ms per token, 54.47 tokens per second) 0.54.200.161 I slot print_timing: id 0 | task 211 | total time = 238.45 ms / 151 tokens 0.54.200.161 I slot print_timing: id 0 | task 211 | graphs reused = 1 0.54.200.162 I slot print_timing: id 0 | task 211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.200.188 I slot release: id 0 | task 211 | stop processing: n_tokens = 150, truncated = 0 0.54.200.431 I slot print_timing: id 1 | task 212 | prompt eval time = 219.79 ms / 122 tokens ( 1.80 ms per token, 555.07 tokens per second) 0.54.200.434 I slot print_timing: id 1 | task 212 | eval time = 18.07 ms / 2 tokens ( 18.07 ms per token, 55.34 tokens per second) 0.54.200.434 I slot print_timing: id 1 | task 212 | total time = 237.86 ms / 124 tokens 0.54.200.435 I slot print_timing: id 1 | task 212 | graphs reused = 1 0.54.200.435 I slot print_timing: id 1 | task 212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.200.448 I slot release: id 1 | task 212 | stop processing: n_tokens = 123, truncated = 0 0.54.200.687 I slot print_timing: id 2 | task 213 | prompt eval time = 219.52 ms / 157 tokens ( 1.40 ms per token, 715.19 tokens per second) 0.54.200.690 I slot print_timing: id 2 | task 213 | eval time = 17.75 ms / 2 tokens ( 17.75 ms per token, 56.35 tokens per second) 0.54.200.691 I slot print_timing: id 2 | task 213 | total time = 237.27 ms / 159 tokens 0.54.200.691 I slot print_timing: id 2 | task 213 | graphs reused = 1 0.54.200.692 I slot print_timing: id 2 | task 213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.200.705 I slot release: id 2 | task 213 | stop processing: n_tokens = 158, truncated = 0 0.54.200.952 I slot print_timing: id 3 | task 214 | prompt eval time = 219.24 ms / 117 tokens ( 1.87 ms per token, 533.67 tokens per second) 0.54.200.955 I slot print_timing: id 3 | task 214 | eval time = 17.44 ms / 2 tokens ( 17.44 ms per token, 57.34 tokens per second) 0.54.200.956 I slot print_timing: id 3 | task 214 | total time = 236.68 ms / 119 tokens 0.54.200.956 I slot print_timing: id 3 | task 214 | graphs reused = 1 0.54.200.956 I slot print_timing: id 3 | task 214 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.200.965 I slot release: id 3 | task 214 | stop processing: n_tokens = 118, truncated = 0 0.54.209.536 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.187 0.54.226.837 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 0.54.226.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.661 MiB) 0.54.249.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 0.54.268.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 0.54.287.411 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.228 0.54.287.575 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 0.54.287.623 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.177 0.54.287.737 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 0.54.287.762 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.237 0.54.287.870 I slot launch_slot_: id 3 | task 221 | processing task, is_child = 0 0.54.558.252 I slot print_timing: id 0 | task 218 | prompt eval time = 250.87 ms / 160 tokens ( 1.57 ms per token, 637.79 tokens per second) 0.54.558.258 I slot print_timing: id 0 | task 218 | eval time = 19.50 ms / 2 tokens ( 19.50 ms per token, 51.30 tokens per second) 0.54.558.259 I slot print_timing: id 0 | task 218 | total time = 270.36 ms / 162 tokens 0.54.558.260 I slot print_timing: id 0 | task 218 | graphs reused = 1 0.54.558.261 I slot print_timing: id 0 | task 218 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.558.289 I slot release: id 0 | task 218 | stop processing: n_tokens = 161, truncated = 0 0.54.558.637 I slot print_timing: id 1 | task 219 | prompt eval time = 250.81 ms / 149 tokens ( 1.68 ms per token, 594.08 tokens per second) 0.54.558.640 I slot print_timing: id 1 | task 219 | eval time = 19.10 ms / 2 tokens ( 19.10 ms per token, 52.35 tokens per second) 0.54.558.640 I slot print_timing: id 1 | task 219 | total time = 269.91 ms / 151 tokens 0.54.558.641 I slot print_timing: id 1 | task 219 | graphs reused = 1 0.54.558.641 I slot print_timing: id 1 | task 219 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.558.655 I slot release: id 1 | task 219 | stop processing: n_tokens = 150, truncated = 0 0.54.559.021 I slot print_timing: id 2 | task 220 | prompt eval time = 250.80 ms / 154 tokens ( 1.63 ms per token, 614.04 tokens per second) 0.54.559.025 I slot print_timing: id 2 | task 220 | eval time = 18.66 ms / 2 tokens ( 18.66 ms per token, 53.60 tokens per second) 0.54.559.025 I slot print_timing: id 2 | task 220 | total time = 269.45 ms / 156 tokens 0.54.559.026 I slot print_timing: id 2 | task 220 | graphs reused = 1 0.54.559.026 I slot print_timing: id 2 | task 220 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.559.039 I slot release: id 2 | task 220 | stop processing: n_tokens = 155, truncated = 0 0.54.559.375 I slot print_timing: id 3 | task 221 | prompt eval time = 250.74 ms / 155 tokens ( 1.62 ms per token, 618.18 tokens per second) 0.54.559.378 I slot print_timing: id 3 | task 221 | eval time = 18.24 ms / 2 tokens ( 18.24 ms per token, 54.82 tokens per second) 0.54.559.379 I slot print_timing: id 3 | task 221 | total time = 268.98 ms / 157 tokens 0.54.559.379 I slot print_timing: id 3 | task 221 | graphs reused = 1 0.54.559.380 I slot print_timing: id 3 | task 221 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.559.391 I slot release: id 3 | task 221 | stop processing: n_tokens = 156, truncated = 0 0.54.567.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.174 0.54.589.972 I slot launch_slot_: id 0 | task 225 | processing task, is_child = 0 0.54.590.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.818 MiB) 0.54.613.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 0.54.636.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 0.54.638.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 0.54.662.243 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.187 0.54.662.413 I slot launch_slot_: id 1 | task 226 | processing task, is_child = 0 0.54.662.465 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.181 0.54.662.590 I slot launch_slot_: id 2 | task 227 | processing task, is_child = 0 0.54.662.618 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.179 0.54.671.049 I slot launch_slot_: id 3 | task 228 | processing task, is_child = 0 0.54.917.161 I slot print_timing: id 0 | task 225 | prompt eval time = 226.07 ms / 107 tokens ( 2.11 ms per token, 473.30 tokens per second) 0.54.917.166 I slot print_timing: id 0 | task 225 | eval time = 20.02 ms / 2 tokens ( 20.02 ms per token, 49.95 tokens per second) 0.54.917.167 I slot print_timing: id 0 | task 225 | total time = 246.09 ms / 109 tokens 0.54.917.168 I slot print_timing: id 0 | task 225 | graphs reused = 1 0.54.917.169 I slot print_timing: id 0 | task 225 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.917.197 I slot release: id 0 | task 225 | stop processing: n_tokens = 108, truncated = 0 0.54.917.578 I slot print_timing: id 1 | task 226 | prompt eval time = 226.01 ms / 114 tokens ( 1.98 ms per token, 504.41 tokens per second) 0.54.917.581 I slot print_timing: id 1 | task 226 | eval time = 19.63 ms / 2 tokens ( 19.63 ms per token, 50.93 tokens per second) 0.54.917.582 I slot print_timing: id 1 | task 226 | total time = 245.64 ms / 116 tokens 0.54.917.582 I slot print_timing: id 1 | task 226 | graphs reused = 1 0.54.917.583 I slot print_timing: id 1 | task 226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.917.597 I slot release: id 1 | task 226 | stop processing: n_tokens = 115, truncated = 0 0.54.917.959 I slot print_timing: id 2 | task 227 | prompt eval time = 225.89 ms / 185 tokens ( 1.22 ms per token, 818.97 tokens per second) 0.54.917.962 I slot print_timing: id 2 | task 227 | eval time = 19.28 ms / 2 tokens ( 19.28 ms per token, 51.86 tokens per second) 0.54.917.963 I slot print_timing: id 2 | task 227 | total time = 245.18 ms / 187 tokens 0.54.917.963 I slot print_timing: id 2 | task 227 | graphs reused = 1 0.54.917.964 I slot print_timing: id 2 | task 227 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.917.977 I slot release: id 2 | task 227 | stop processing: n_tokens = 186, truncated = 0 0.54.918.389 I slot print_timing: id 3 | task 228 | prompt eval time = 225.84 ms / 102 tokens ( 2.21 ms per token, 451.65 tokens per second) 0.54.918.393 I slot print_timing: id 3 | task 228 | eval time = 18.93 ms / 2 tokens ( 18.93 ms per token, 52.83 tokens per second) 0.54.918.393 I slot print_timing: id 3 | task 228 | total time = 244.76 ms / 104 tokens 0.54.918.394 I slot print_timing: id 3 | task 228 | graphs reused = 1 0.54.918.394 I slot print_timing: id 3 | task 228 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.918.404 I slot release: id 3 | task 228 | stop processing: n_tokens = 103, truncated = 0 0.54.927.048 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.282 0.54.948.772 I slot launch_slot_: id 3 | task 232 | processing task, is_child = 0 0.54.970.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 0.54.993.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.630 MiB) 0.55.017.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.259 0.55.017.547 I slot launch_slot_: id 0 | task 233 | processing task, is_child = 0 0.55.017.598 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.243 0.55.017.711 I slot launch_slot_: id 1 | task 234 | processing task, is_child = 0 0.55.017.740 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.151 0.55.017.853 I slot launch_slot_: id 2 | task 235 | processing task, is_child = 0 0.55.263.368 I slot print_timing: id 0 | task 233 | prompt eval time = 226.32 ms / 164 tokens ( 1.38 ms per token, 724.65 tokens per second) 0.55.263.374 I slot print_timing: id 0 | task 233 | eval time = 19.18 ms / 2 tokens ( 19.18 ms per token, 52.15 tokens per second) 0.55.263.376 I slot print_timing: id 0 | task 233 | total time = 245.49 ms / 166 tokens 0.55.263.377 I slot print_timing: id 0 | task 233 | graphs reused = 1 0.55.263.378 I slot print_timing: id 0 | task 233 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.263.410 I slot release: id 0 | task 233 | stop processing: n_tokens = 165, truncated = 0 0.55.263.825 I slot print_timing: id 1 | task 234 | prompt eval time = 226.27 ms / 126 tokens ( 1.80 ms per token, 556.85 tokens per second) 0.55.263.830 I slot print_timing: id 1 | task 234 | eval time = 18.83 ms / 2 tokens ( 18.83 ms per token, 53.10 tokens per second) 0.55.263.831 I slot print_timing: id 1 | task 234 | total time = 245.10 ms / 128 tokens 0.55.263.833 I slot print_timing: id 1 | task 234 | graphs reused = 1 0.55.263.833 I slot print_timing: id 1 | task 234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.263.852 I slot release: id 1 | task 234 | stop processing: n_tokens = 127, truncated = 0 0.55.264.361 I slot print_timing: id 2 | task 235 | prompt eval time = 226.15 ms / 122 tokens ( 1.85 ms per token, 539.47 tokens per second) 0.55.264.366 I slot print_timing: id 2 | task 235 | eval time = 18.64 ms / 2 tokens ( 18.64 ms per token, 53.65 tokens per second) 0.55.264.367 I slot print_timing: id 2 | task 235 | total time = 244.79 ms / 124 tokens 0.55.264.367 I slot print_timing: id 2 | task 235 | graphs reused = 1 0.55.264.368 I slot print_timing: id 2 | task 235 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.264.384 I slot release: id 2 | task 235 | stop processing: n_tokens = 123, truncated = 0 0.55.264.752 I slot print_timing: id 3 | task 232 | prompt eval time = 225.85 ms / 110 tokens ( 2.05 ms per token, 487.05 tokens per second) 0.55.264.758 I slot print_timing: id 3 | task 232 | eval time = 18.46 ms / 2 tokens ( 18.46 ms per token, 54.16 tokens per second) 0.55.264.759 I slot print_timing: id 3 | task 232 | total time = 244.31 ms / 112 tokens 0.55.264.761 I slot print_timing: id 3 | task 232 | graphs reused = 1 0.55.264.762 I slot print_timing: id 3 | task 232 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.264.780 I slot release: id 3 | task 232 | stop processing: n_tokens = 111, truncated = 0 0.55.294.299 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.261 0.55.294.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 0.55.314.855 I slot launch_slot_: id 3 | task 240 | processing task, is_child = 0 0.55.314.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.755 MiB) 0.55.337.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 0.55.360.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 0.55.383.469 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.170 0.55.383.632 I slot launch_slot_: id 0 | task 239 | processing task, is_child = 0 0.55.383.678 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.203 (> 0.100 thold), f_keep = 0.220 0.55.392.121 I slot launch_slot_: id 1 | task 241 | processing task, is_child = 0 0.55.392.151 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.228 0.55.392.266 I slot launch_slot_: id 2 | task 242 | processing task, is_child = 0 0.55.640.054 I slot print_timing: id 0 | task 239 | prompt eval time = 228.00 ms / 125 tokens ( 1.82 ms per token, 548.24 tokens per second) 0.55.640.061 I slot print_timing: id 0 | task 239 | eval time = 19.77 ms / 2 tokens ( 19.77 ms per token, 50.58 tokens per second) 0.55.640.062 I slot print_timing: id 0 | task 239 | total time = 247.77 ms / 127 tokens 0.55.640.063 I slot print_timing: id 0 | task 239 | graphs reused = 1 0.55.640.064 I slot print_timing: id 0 | task 239 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.640.090 I slot release: id 0 | task 239 | stop processing: n_tokens = 126, truncated = 0 0.55.640.475 I slot print_timing: id 1 | task 241 | prompt eval time = 227.94 ms / 138 tokens ( 1.65 ms per token, 605.41 tokens per second) 0.55.640.479 I slot print_timing: id 1 | task 241 | eval time = 19.38 ms / 2 tokens ( 19.38 ms per token, 51.61 tokens per second) 0.55.640.480 I slot print_timing: id 1 | task 241 | total time = 247.32 ms / 140 tokens 0.55.640.480 I slot print_timing: id 1 | task 241 | graphs reused = 1 0.55.640.481 I slot print_timing: id 1 | task 241 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.640.499 I slot release: id 1 | task 241 | stop processing: n_tokens = 139, truncated = 0 0.55.640.885 I slot print_timing: id 2 | task 242 | prompt eval time = 227.82 ms / 122 tokens ( 1.87 ms per token, 535.51 tokens per second) 0.55.640.888 I slot print_timing: id 2 | task 242 | eval time = 19.00 ms / 2 tokens ( 19.00 ms per token, 52.63 tokens per second) 0.55.640.889 I slot print_timing: id 2 | task 242 | total time = 246.82 ms / 124 tokens 0.55.640.889 I slot print_timing: id 2 | task 242 | graphs reused = 1 0.55.640.890 I slot print_timing: id 2 | task 242 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.640.903 I slot release: id 2 | task 242 | stop processing: n_tokens = 123, truncated = 0 0.55.641.268 I slot print_timing: id 3 | task 240 | prompt eval time = 227.68 ms / 137 tokens ( 1.66 ms per token, 601.73 tokens per second) 0.55.641.271 I slot print_timing: id 3 | task 240 | eval time = 18.63 ms / 2 tokens ( 18.63 ms per token, 53.68 tokens per second) 0.55.641.272 I slot print_timing: id 3 | task 240 | total time = 246.30 ms / 139 tokens 0.55.641.272 I slot print_timing: id 3 | task 240 | graphs reused = 1 0.55.641.273 I slot print_timing: id 3 | task 240 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.641.284 I slot release: id 3 | task 240 | stop processing: n_tokens = 138, truncated = 0 0.55.648.569 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.222 0.55.679.004 I slot launch_slot_: id 0 | task 246 | processing task, is_child = 0 0.55.700.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.130 MiB) 0.55.723.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 0.55.746.982 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.201 0.55.747.170 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 0.55.747.220 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.228 0.55.747.371 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 0.55.747.398 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.203 0.55.747.515 I slot launch_slot_: id 3 | task 249 | processing task, is_child = 0 0.56.005.253 I slot print_timing: id 0 | task 246 | prompt eval time = 237.90 ms / 158 tokens ( 1.51 ms per token, 664.13 tokens per second) 0.56.005.259 I slot print_timing: id 0 | task 246 | eval time = 19.82 ms / 2 tokens ( 19.82 ms per token, 50.46 tokens per second) 0.56.005.260 I slot print_timing: id 0 | task 246 | total time = 257.72 ms / 160 tokens 0.56.005.261 I slot print_timing: id 0 | task 246 | graphs reused = 1 0.56.005.262 I slot print_timing: id 0 | task 246 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.005.287 I slot release: id 0 | task 246 | stop processing: n_tokens = 159, truncated = 0 0.56.005.598 I slot print_timing: id 1 | task 247 | prompt eval time = 237.84 ms / 120 tokens ( 1.98 ms per token, 504.53 tokens per second) 0.56.005.601 I slot print_timing: id 1 | task 247 | eval time = 19.39 ms / 2 tokens ( 19.39 ms per token, 51.57 tokens per second) 0.56.005.601 I slot print_timing: id 1 | task 247 | total time = 257.23 ms / 122 tokens 0.56.005.602 I slot print_timing: id 1 | task 247 | graphs reused = 1 0.56.005.603 I slot print_timing: id 1 | task 247 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.005.616 I slot release: id 1 | task 247 | stop processing: n_tokens = 121, truncated = 0 0.56.005.934 I slot print_timing: id 2 | task 248 | prompt eval time = 237.74 ms / 140 tokens ( 1.70 ms per token, 588.88 tokens per second) 0.56.005.937 I slot print_timing: id 2 | task 248 | eval time = 18.94 ms / 2 tokens ( 18.94 ms per token, 52.80 tokens per second) 0.56.005.938 I slot print_timing: id 2 | task 248 | total time = 256.68 ms / 142 tokens 0.56.005.938 I slot print_timing: id 2 | task 248 | graphs reused = 1 0.56.005.939 I slot print_timing: id 2 | task 248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.005.950 I slot release: id 2 | task 248 | stop processing: n_tokens = 141, truncated = 0 0.56.006.237 I slot print_timing: id 3 | task 249 | prompt eval time = 237.56 ms / 168 tokens ( 1.41 ms per token, 707.20 tokens per second) 0.56.006.240 I slot print_timing: id 3 | task 249 | eval time = 18.55 ms / 2 tokens ( 18.55 ms per token, 53.90 tokens per second) 0.56.006.241 I slot print_timing: id 3 | task 249 | total time = 256.11 ms / 170 tokens 0.56.006.241 I slot print_timing: id 3 | task 249 | graphs reused = 1 0.56.006.242 I slot print_timing: id 3 | task 249 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.006.256 I slot release: id 3 | task 249 | stop processing: n_tokens = 169, truncated = 0 0.56.015.160 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.176 0.56.015.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.56.037.691 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 0.56.037.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 0.56.058.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 0.56.081.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 0.56.103.941 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.231 0.56.104.120 I slot launch_slot_: id 1 | task 254 | processing task, is_child = 0 0.56.104.170 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.199 0.56.112.577 I slot launch_slot_: id 2 | task 255 | processing task, is_child = 0 0.56.112.609 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.154 (> 0.100 thold), f_keep = 0.166 0.56.112.718 I slot launch_slot_: id 3 | task 256 | processing task, is_child = 0 0.56.373.004 I slot print_timing: id 0 | task 253 | prompt eval time = 241.04 ms / 155 tokens ( 1.56 ms per token, 643.05 tokens per second) 0.56.373.010 I slot print_timing: id 0 | task 253 | eval time = 19.23 ms / 2 tokens ( 19.23 ms per token, 52.00 tokens per second) 0.56.373.011 I slot print_timing: id 0 | task 253 | total time = 260.27 ms / 157 tokens 0.56.373.011 I slot print_timing: id 0 | task 253 | graphs reused = 1 0.56.373.013 I slot print_timing: id 0 | task 253 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.373.040 I slot release: id 0 | task 253 | stop processing: n_tokens = 156, truncated = 0 0.56.373.390 I slot print_timing: id 1 | task 254 | prompt eval time = 240.96 ms / 103 tokens ( 2.34 ms per token, 427.46 tokens per second) 0.56.373.393 I slot print_timing: id 1 | task 254 | eval time = 18.82 ms / 2 tokens ( 18.82 ms per token, 53.15 tokens per second) 0.56.373.394 I slot print_timing: id 1 | task 254 | total time = 259.77 ms / 105 tokens 0.56.373.395 I slot print_timing: id 1 | task 254 | graphs reused = 1 0.56.373.396 I slot print_timing: id 1 | task 254 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.373.411 I slot release: id 1 | task 254 | stop processing: n_tokens = 104, truncated = 0 0.56.373.709 I slot print_timing: id 2 | task 255 | prompt eval time = 240.80 ms / 133 tokens ( 1.81 ms per token, 552.32 tokens per second) 0.56.373.712 I slot print_timing: id 2 | task 255 | eval time = 18.40 ms / 2 tokens ( 18.40 ms per token, 54.35 tokens per second) 0.56.373.713 I slot print_timing: id 2 | task 255 | total time = 259.20 ms / 135 tokens 0.56.373.714 I slot print_timing: id 2 | task 255 | graphs reused = 1 0.56.373.714 I slot print_timing: id 2 | task 255 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.373.726 I slot release: id 2 | task 255 | stop processing: n_tokens = 134, truncated = 0 0.56.374.018 I slot print_timing: id 3 | task 256 | prompt eval time = 240.61 ms / 182 tokens ( 1.32 ms per token, 756.41 tokens per second) 0.56.374.021 I slot print_timing: id 3 | task 256 | eval time = 18.01 ms / 2 tokens ( 18.01 ms per token, 55.53 tokens per second) 0.56.374.022 I slot print_timing: id 3 | task 256 | total time = 258.62 ms / 184 tokens 0.56.374.022 I slot print_timing: id 3 | task 256 | graphs reused = 1 0.56.374.023 I slot print_timing: id 3 | task 256 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.374.036 I slot release: id 3 | task 256 | stop processing: n_tokens = 183, truncated = 0 0.56.382.100 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.179 0.56.382.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 0.56.405.377 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 0.56.426.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.223 MiB) 0.56.449.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.317 MiB) 0.56.451.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 0.56.474.368 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.269 0.56.474.548 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 0.56.607.899 I slot print_timing: id 0 | task 260 | prompt eval time = 116.72 ms / 124 tokens ( 0.94 ms per token, 1062.34 tokens per second) 0.56.607.904 I slot print_timing: id 0 | task 260 | eval time = 16.57 ms / 2 tokens ( 16.57 ms per token, 60.35 tokens per second) 0.56.607.905 I slot print_timing: id 0 | task 260 | total time = 133.29 ms / 126 tokens 0.56.607.906 I slot print_timing: id 0 | task 260 | graphs reused = 1 0.56.607.907 I slot print_timing: id 0 | task 260 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.607.926 I slot release: id 0 | task 260 | stop processing: n_tokens = 125, truncated = 0 0.56.608.172 I slot print_timing: id 1 | task 261 | prompt eval time = 116.53 ms / 144 tokens ( 0.81 ms per token, 1235.78 tokens per second) 0.56.608.175 I slot print_timing: id 1 | task 261 | eval time = 16.15 ms / 2 tokens ( 16.15 ms per token, 61.92 tokens per second) 0.56.608.176 I slot print_timing: id 1 | task 261 | total time = 132.68 ms / 146 tokens 0.56.608.176 I slot print_timing: id 1 | task 261 | graphs reused = 1 0.56.608.178 I slot print_timing: id 1 | task 261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.608.187 I slot release: id 1 | task 261 | stop processing: n_tokens = 145, truncated = 0 0.56.630.926 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 134, t_last = 56276322 0.56.631.196 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 0.56.631.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 0.56.677.629 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 56276632 0.56.677.759 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 0.56.677.806 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 56510522 0.56.677.918 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 0.56.677.943 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 56510783 0.56.678.042 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 0.58.535.780 I slot print_timing: id 1 | task 268 | prompt eval time = 1418.66 ms / 1243 tokens ( 1.14 ms per token, 876.18 tokens per second) 0.58.535.786 I slot print_timing: id 1 | task 268 | eval time = 438.12 ms / 31 tokens ( 14.60 ms per token, 68.47 tokens per second) 0.58.535.787 I slot print_timing: id 1 | task 268 | total time = 1856.78 ms / 1274 tokens 0.58.535.788 I slot print_timing: id 1 | task 268 | graphs reused = 32 0.58.535.789 I slot print_timing: id 1 | task 268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.535.840 I slot release: id 1 | task 268 | stop processing: n_tokens = 1273, truncated = 0 0.58.565.364 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.900 0.58.565.464 I slot launch_slot_: id 1 | task 306 | processing task, is_child = 0 0.59.020.038 I slot print_timing: id 3 | task 266 | prompt eval time = 1417.96 ms / 1215 tokens ( 1.17 ms per token, 856.86 tokens per second) 0.59.020.044 I slot print_timing: id 3 | task 266 | eval time = 921.24 ms / 55 tokens ( 17.06 ms per token, 58.62 tokens per second) 0.59.020.045 I slot print_timing: id 3 | task 266 | total time = 2339.20 ms / 1270 tokens 0.59.020.046 I slot print_timing: id 3 | task 266 | graphs reused = 51 0.59.020.046 I slot print_timing: id 3 | task 266 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.020.098 I slot release: id 3 | task 266 | stop processing: n_tokens = 1269, truncated = 0 0.59.054.492 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.903 0.59.054.596 I slot launch_slot_: id 3 | task 332 | processing task, is_child = 0 0.59.347.533 I slot print_timing: id 0 | task 267 | prompt eval time = 1419.02 ms / 1230 tokens ( 1.15 ms per token, 866.79 tokens per second) 0.59.347.539 I slot print_timing: id 0 | task 267 | eval time = 1250.45 ms / 70 tokens ( 18.12 ms per token, 55.18 tokens per second) 0.59.347.540 I slot print_timing: id 0 | task 267 | total time = 2669.47 ms / 1300 tokens 0.59.347.540 I slot print_timing: id 0 | task 267 | graphs reused = 62 0.59.347.541 I slot print_timing: id 0 | task 267 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.347.595 I slot release: id 0 | task 267 | stop processing: n_tokens = 1299, truncated = 0 0.59.365.802 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.882 0.59.365.912 I slot launch_slot_: id 0 | task 347 | processing task, is_child = 0 1.00.086.141 I slot print_timing: id 1 | task 306 | prompt eval time = 137.38 ms / 132 tokens ( 1.04 ms per token, 960.83 tokens per second) 1.00.086.146 I slot print_timing: id 1 | task 306 | eval time = 1383.28 ms / 79 tokens ( 17.73 ms per token, 56.39 tokens per second) 1.00.086.147 I slot print_timing: id 1 | task 306 | total time = 1520.66 ms / 211 tokens 1.00.086.148 I slot print_timing: id 1 | task 306 | graphs reused = 101 1.00.086.149 I slot print_timing: id 1 | task 306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.086.201 I slot release: id 1 | task 306 | stop processing: n_tokens = 1335, truncated = 0 1.00.117.029 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.858 1.00.117.127 I slot launch_slot_: id 1 | task 390 | processing task, is_child = 0 1.00.653.452 I slot print_timing: id 2 | task 265 | prompt eval time = 1418.32 ms / 1234 tokens ( 1.15 ms per token, 870.04 tokens per second) 1.00.653.457 I slot print_timing: id 2 | task 265 | eval time = 2555.21 ms / 141 tokens ( 18.25 ms per token, 54.79 tokens per second) 1.00.653.458 I slot print_timing: id 2 | task 265 | total time = 3973.53 ms / 1375 tokens 1.00.653.460 I slot print_timing: id 2 | task 265 | graphs reused = 126 1.00.653.460 I slot print_timing: id 2 | task 265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.653.513 I slot release: id 2 | task 265 | stop processing: n_tokens = 1374, truncated = 0 1.00.683.626 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.834 1.00.683.749 I slot launch_slot_: id 2 | task 420 | processing task, is_child = 0 1.00.897.782 I slot print_timing: id 3 | task 332 | prompt eval time = 123.31 ms / 139 tokens ( 0.89 ms per token, 1127.25 tokens per second) 1.00.897.788 I slot print_timing: id 3 | task 332 | eval time = 1719.86 ms / 90 tokens ( 19.32 ms per token, 51.75 tokens per second) 1.00.897.789 I slot print_timing: id 3 | task 332 | total time = 1843.17 ms / 229 tokens 1.00.897.791 I slot print_timing: id 3 | task 332 | graphs reused = 129 1.00.897.791 I slot print_timing: id 3 | task 332 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.897.844 I slot release: id 3 | task 332 | stop processing: n_tokens = 1353, truncated = 0 1.00.932.107 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.847 1.00.932.215 I slot launch_slot_: id 3 | task 429 | processing task, is_child = 0 1.02.115.512 I slot print_timing: id 0 | task 347 | prompt eval time = 120.58 ms / 139 tokens ( 0.87 ms per token, 1152.80 tokens per second) 1.02.115.517 I slot print_timing: id 0 | task 347 | eval time = 2629.01 ms / 151 tokens ( 17.53 ms per token, 57.06 tokens per second) 1.02.115.518 I slot print_timing: id 0 | task 347 | total time = 2749.58 ms / 290 tokens 1.02.115.519 I slot print_timing: id 0 | task 347 | graphs reused = 200 1.02.115.520 I slot print_timing: id 0 | task 347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.115.571 I slot release: id 0 | task 347 | stop processing: n_tokens = 1414, truncated = 0 1.02.148.826 I slot print_timing: id 1 | task 390 | prompt eval time = 137.77 ms / 114 tokens ( 1.21 ms per token, 827.45 tokens per second) 1.02.148.831 I slot print_timing: id 1 | task 390 | eval time = 1893.91 ms / 111 tokens ( 17.22 ms per token, 58.08 tokens per second) 1.02.148.832 I slot print_timing: id 1 | task 390 | total time = 2031.68 ms / 225 tokens 1.02.148.833 I slot print_timing: id 1 | task 390 | graphs reused = 201 1.02.148.834 I slot print_timing: id 1 | task 390 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.148.881 I slot release: id 1 | task 390 | stop processing: n_tokens = 1349, truncated = 0 1.02.165.109 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.810 1.02.165.210 I slot launch_slot_: id 0 | task 506 | processing task, is_child = 0 1.02.165.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.038 MiB) 1.02.166.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 1.02.168.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 1.02.220.113 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.850 1.02.220.237 I slot launch_slot_: id 1 | task 507 | processing task, is_child = 0 1.02.865.525 I slot print_timing: id 2 | task 420 | prompt eval time = 148.03 ms / 141 tokens ( 1.05 ms per token, 952.52 tokens per second) 1.02.865.531 I slot print_timing: id 2 | task 420 | eval time = 2033.73 ms / 117 tokens ( 17.53 ms per token, 57.04 tokens per second) 1.02.865.532 I slot print_timing: id 2 | task 420 | total time = 2181.76 ms / 258 tokens 1.02.865.533 I slot print_timing: id 2 | task 420 | graphs reused = 233 1.02.865.534 I slot print_timing: id 2 | task 420 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.865.584 I slot release: id 2 | task 420 | stop processing: n_tokens = 1382, truncated = 0 1.02.924.071 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.829 1.02.924.199 I slot launch_slot_: id 2 | task 544 | processing task, is_child = 0 1.03.339.873 I slot print_timing: id 3 | task 429 | prompt eval time = 130.43 ms / 169 tokens ( 0.77 ms per token, 1295.69 tokens per second) 1.03.339.879 I slot print_timing: id 3 | task 429 | eval time = 2277.21 ms / 131 tokens ( 17.52 ms per token, 57.09 tokens per second) 1.03.339.880 I slot print_timing: id 3 | task 429 | total time = 2407.64 ms / 300 tokens 1.03.339.881 I slot print_timing: id 3 | task 429 | graphs reused = 250 1.03.339.882 I slot print_timing: id 3 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.339.936 I slot release: id 3 | task 429 | stop processing: n_tokens = 1424, truncated = 0 1.03.374.283 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.805 1.03.374.391 I slot launch_slot_: id 3 | task 567 | processing task, is_child = 0 1.03.928.616 I slot print_timing: id 1 | task 507 | prompt eval time = 155.92 ms / 101 tokens ( 1.54 ms per token, 647.77 tokens per second) 1.03.928.623 I slot print_timing: id 1 | task 507 | eval time = 1533.01 ms / 88 tokens ( 17.62 ms per token, 56.75 tokens per second) 1.03.928.624 I slot print_timing: id 1 | task 507 | total time = 1688.93 ms / 189 tokens 1.03.928.624 I slot print_timing: id 1 | task 507 | graphs reused = 279 1.03.928.625 I slot print_timing: id 1 | task 507 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.928.677 I slot release: id 1 | task 507 | stop processing: n_tokens = 1313, truncated = 0 1.03.959.310 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.873 1.03.959.426 I slot launch_slot_: id 1 | task 600 | processing task, is_child = 0 1.04.196.432 I slot print_timing: id 0 | task 506 | prompt eval time = 174.76 ms / 125 tokens ( 1.40 ms per token, 715.28 tokens per second) 1.04.196.438 I slot print_timing: id 0 | task 506 | eval time = 1801.42 ms / 97 tokens ( 18.76 ms per token, 53.29 tokens per second) 1.04.196.439 I slot print_timing: id 0 | task 506 | total time = 1976.18 ms / 222 tokens 1.04.196.441 I slot print_timing: id 0 | task 506 | graphs reused = 284 1.04.196.441 I slot print_timing: id 0 | task 506 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.196.492 I slot release: id 0 | task 506 | stop processing: n_tokens = 1346, truncated = 0 1.04.231.700 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.851 1.04.231.803 I slot launch_slot_: id 0 | task 611 | processing task, is_child = 0 1.04.400.616 I slot print_timing: id 2 | task 544 | prompt eval time = 139.32 ms / 101 tokens ( 1.38 ms per token, 724.96 tokens per second) 1.04.400.622 I slot print_timing: id 2 | task 544 | eval time = 1337.08 ms / 68 tokens ( 19.96 ms per token, 50.11 tokens per second) 1.04.400.623 I slot print_timing: id 2 | task 544 | total time = 1476.40 ms / 169 tokens 1.04.400.624 I slot print_timing: id 2 | task 544 | graphs reused = 288 1.04.400.625 I slot print_timing: id 2 | task 544 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.400.677 I slot release: id 2 | task 544 | stop processing: n_tokens = 1293, truncated = 0 1.04.461.298 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.886 1.04.461.443 I slot launch_slot_: id 2 | task 619 | processing task, is_child = 0 1.05.087.305 I slot print_timing: id 1 | task 600 | prompt eval time = 141.36 ms / 120 tokens ( 1.18 ms per token, 848.89 tokens per second) 1.05.087.311 I slot print_timing: id 1 | task 600 | eval time = 986.50 ms / 50 tokens ( 20.13 ms per token, 49.67 tokens per second) 1.05.087.312 I slot print_timing: id 1 | task 600 | total time = 1127.86 ms / 170 tokens 1.05.087.313 I slot print_timing: id 1 | task 600 | graphs reused = 319 1.05.087.314 I slot print_timing: id 1 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.087.366 I slot release: id 1 | task 600 | stop processing: n_tokens = 1294, truncated = 0 1.05.147.529 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.886 1.05.147.649 I slot launch_slot_: id 1 | task 656 | processing task, is_child = 0 1.05.756.282 I slot print_timing: id 3 | task 567 | prompt eval time = 109.76 ms / 95 tokens ( 1.16 ms per token, 865.55 tokens per second) 1.05.756.287 I slot print_timing: id 3 | task 567 | eval time = 2272.12 ms / 117 tokens ( 19.59 ms per token, 51.05 tokens per second) 1.05.756.288 I slot print_timing: id 3 | task 567 | total time = 2381.88 ms / 212 tokens 1.05.756.289 I slot print_timing: id 3 | task 567 | graphs reused = 349 1.05.756.290 I slot print_timing: id 3 | task 567 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.756.340 I slot release: id 3 | task 567 | stop processing: n_tokens = 1336, truncated = 0 1.05.790.151 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.858 1.05.790.265 I slot launch_slot_: id 3 | task 692 | processing task, is_child = 0 1.06.034.312 I slot print_timing: id 2 | task 619 | prompt eval time = 132.99 ms / 86 tokens ( 1.55 ms per token, 646.67 tokens per second) 1.06.034.317 I slot print_timing: id 2 | task 619 | eval time = 1439.87 ms / 81 tokens ( 18.00 ms per token, 55.56 tokens per second) 1.06.034.319 I slot print_timing: id 2 | task 619 | total time = 1572.85 ms / 167 tokens 1.06.034.320 I slot print_timing: id 2 | task 619 | graphs reused = 358 1.06.034.321 I slot print_timing: id 2 | task 619 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.034.370 I slot release: id 2 | task 619 | stop processing: n_tokens = 1291, truncated = 0 1.06.063.773 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.888 1.06.063.878 I slot launch_slot_: id 2 | task 705 | processing task, is_child = 0 1.06.949.849 I slot print_timing: id 1 | task 656 | prompt eval time = 140.79 ms / 133 tokens ( 1.06 ms per token, 944.66 tokens per second) 1.06.949.855 I slot print_timing: id 1 | task 656 | eval time = 1661.39 ms / 100 tokens ( 16.78 ms per token, 59.59 tokens per second) 1.06.949.856 I slot print_timing: id 1 | task 656 | total time = 1802.18 ms / 233 tokens 1.06.949.856 I slot print_timing: id 1 | task 656 | graphs reused = 409 1.06.949.857 I slot print_timing: id 1 | task 656 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.949.911 I slot release: id 1 | task 656 | stop processing: n_tokens = 1357, truncated = 0 1.06.979.888 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.845 1.06.979.993 I slot launch_slot_: id 1 | task 761 | processing task, is_child = 0 1.07.168.632 I slot print_timing: id 0 | task 611 | prompt eval time = 117.39 ms / 148 tokens ( 0.79 ms per token, 1260.74 tokens per second) 1.07.168.637 I slot print_timing: id 0 | task 611 | eval time = 2819.42 ms / 149 tokens ( 19.05 ms per token, 52.49 tokens per second) 1.07.168.638 I slot print_timing: id 0 | task 611 | total time = 2936.81 ms / 297 tokens 1.07.168.639 I slot print_timing: id 0 | task 611 | graphs reused = 411 1.07.168.640 I slot print_timing: id 0 | task 611 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.168.692 I slot release: id 0 | task 611 | stop processing: n_tokens = 1421, truncated = 0 1.07.203.060 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.806 1.07.203.169 I slot launch_slot_: id 0 | task 769 | processing task, is_child = 0 1.07.306.965 I slot print_timing: id 3 | task 692 | prompt eval time = 108.29 ms / 97 tokens ( 1.12 ms per token, 895.76 tokens per second) 1.07.306.971 I slot print_timing: id 3 | task 692 | eval time = 1408.39 ms / 75 tokens ( 19.03 ms per token, 52.54 tokens per second) 1.07.306.972 I slot print_timing: id 3 | task 692 | total time = 1516.68 ms / 172 tokens 1.07.306.973 I slot print_timing: id 3 | task 692 | graphs reused = 413 1.07.306.974 I slot print_timing: id 3 | task 692 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.307.028 I slot release: id 3 | task 692 | stop processing: n_tokens = 1296, truncated = 0 1.07.354.662 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.884 1.07.354.786 I slot launch_slot_: id 3 | task 775 | processing task, is_child = 0 1.07.586.497 I slot print_timing: id 2 | task 705 | prompt eval time = 128.38 ms / 84 tokens ( 1.53 ms per token, 654.30 tokens per second) 1.07.586.503 I slot print_timing: id 2 | task 705 | eval time = 1394.22 ms / 75 tokens ( 18.84 ms per token, 53.08 tokens per second) 1.07.586.504 I slot print_timing: id 2 | task 705 | total time = 1522.60 ms / 159 tokens 1.07.586.505 I slot print_timing: id 2 | task 705 | graphs reused = 420 1.07.586.506 I slot print_timing: id 2 | task 705 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.586.560 I slot release: id 2 | task 705 | stop processing: n_tokens = 1283, truncated = 0 1.07.616.963 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.893 1.07.617.080 I slot launch_slot_: id 2 | task 786 | processing task, is_child = 0 1.08.383.384 I slot print_timing: id 0 | task 769 | prompt eval time = 102.93 ms / 95 tokens ( 1.08 ms per token, 922.96 tokens per second) 1.08.383.390 I slot print_timing: id 0 | task 769 | eval time = 1077.27 ms / 57 tokens ( 19.24 ms per token, 51.98 tokens per second) 1.08.383.391 I slot print_timing: id 0 | task 769 | total time = 1180.20 ms / 152 tokens 1.08.383.392 I slot print_timing: id 0 | task 769 | graphs reused = 459 1.08.383.393 I slot print_timing: id 0 | task 769 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.383.446 I slot release: id 0 | task 769 | stop processing: n_tokens = 1276, truncated = 0 1.08.418.531 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.898 1.08.418.646 I slot launch_slot_: id 0 | task 832 | processing task, is_child = 0 1.08.576.964 I slot print_timing: id 1 | task 761 | prompt eval time = 138.60 ms / 101 tokens ( 1.37 ms per token, 728.72 tokens per second) 1.08.576.970 I slot print_timing: id 1 | task 761 | eval time = 1458.35 ms / 71 tokens ( 20.83 ms per token, 48.00 tokens per second) 1.08.576.971 I slot print_timing: id 1 | task 761 | total time = 1596.95 ms / 172 tokens 1.08.576.972 I slot print_timing: id 1 | task 761 | graphs reused = 463 1.08.576.972 I slot print_timing: id 1 | task 761 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.577.024 I slot release: id 1 | task 761 | stop processing: n_tokens = 1296, truncated = 0 1.08.607.859 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.884 1.08.607.968 I slot launch_slot_: id 1 | task 839 | processing task, is_child = 0 1.09.456.807 I slot print_timing: id 2 | task 786 | prompt eval time = 133.91 ms / 90 tokens ( 1.49 ms per token, 672.09 tokens per second) 1.09.456.813 I slot print_timing: id 2 | task 786 | eval time = 1705.80 ms / 99 tokens ( 17.41 ms per token, 57.45 tokens per second) 1.09.456.813 I slot print_timing: id 2 | task 786 | total time = 1839.71 ms / 189 tokens 1.09.456.814 I slot print_timing: id 2 | task 786 | graphs reused = 509 1.09.456.815 I slot print_timing: id 2 | task 786 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.456.866 I slot release: id 2 | task 786 | stop processing: n_tokens = 1313, truncated = 0 1.09.516.697 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.874 1.09.516.810 I slot launch_slot_: id 2 | task 891 | processing task, is_child = 0 1.09.985.887 I slot print_timing: id 3 | task 775 | prompt eval time = 114.60 ms / 130 tokens ( 0.88 ms per token, 1134.34 tokens per second) 1.09.985.893 I slot print_timing: id 3 | task 775 | eval time = 2516.48 ms / 135 tokens ( 18.78 ms per token, 53.25 tokens per second) 1.09.985.895 I slot print_timing: id 3 | task 775 | total time = 2631.09 ms / 265 tokens 1.09.985.896 I slot print_timing: id 3 | task 775 | graphs reused = 530 1.09.985.896 I slot print_timing: id 3 | task 775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.985.947 I slot release: id 3 | task 775 | stop processing: n_tokens = 1389, truncated = 0 1.10.033.005 I slot print_timing: id 0 | task 832 | prompt eval time = 105.70 ms / 96 tokens ( 1.10 ms per token, 908.21 tokens per second) 1.10.033.011 I slot print_timing: id 0 | task 832 | eval time = 1508.64 ms / 83 tokens ( 18.40 ms per token, 54.35 tokens per second) 1.10.033.012 I slot print_timing: id 0 | task 832 | total time = 1614.34 ms / 179 tokens 1.10.033.013 I slot print_timing: id 0 | task 832 | graphs reused = 532 1.10.033.014 I slot print_timing: id 0 | task 832 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.033.062 I slot release: id 0 | task 832 | stop processing: n_tokens = 1303, truncated = 0 1.10.033.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.880 1.10.033.808 I slot launch_slot_: id 0 | task 919 | processing task, is_child = 0 1.10.033.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 1.10.035.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.600 MiB) 1.10.037.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 1.10.086.385 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.825 1.10.086.515 I slot launch_slot_: id 3 | task 920 | processing task, is_child = 0 1.10.489.313 I slot print_timing: id 1 | task 839 | prompt eval time = 135.54 ms / 87 tokens ( 1.56 ms per token, 641.89 tokens per second) 1.10.489.318 I slot print_timing: id 1 | task 839 | eval time = 1745.79 ms / 92 tokens ( 19.18 ms per token, 52.13 tokens per second) 1.10.489.319 I slot print_timing: id 1 | task 839 | total time = 1881.33 ms / 179 tokens 1.10.489.320 I slot print_timing: id 1 | task 839 | graphs reused = 544 1.10.489.321 I slot print_timing: id 1 | task 839 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.489.370 I slot release: id 1 | task 839 | stop processing: n_tokens = 1303, truncated = 0 1.10.518.999 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.880 1.10.519.104 I slot launch_slot_: id 1 | task 937 | processing task, is_child = 0 1.11.607.558 I slot print_timing: id 1 | task 937 | prompt eval time = 131.78 ms / 93 tokens ( 1.42 ms per token, 705.69 tokens per second) 1.11.607.562 I slot print_timing: id 1 | task 937 | eval time = 956.65 ms / 65 tokens ( 14.95 ms per token, 66.90 tokens per second) 1.11.607.563 I slot print_timing: id 1 | task 937 | total time = 1088.43 ms / 158 tokens 1.11.607.565 I slot print_timing: id 1 | task 937 | graphs reused = 607 1.11.607.566 I slot print_timing: id 1 | task 937 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.607.620 I slot release: id 1 | task 937 | stop processing: n_tokens = 1282, truncated = 0 1.11.638.585 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.894 1.11.638.695 I slot launch_slot_: id 1 | task 1005 | processing task, is_child = 0 1.11.914.979 I slot print_timing: id 2 | task 891 | prompt eval time = 139.22 ms / 131 tokens ( 1.06 ms per token, 940.93 tokens per second) 1.11.914.984 I slot print_timing: id 2 | task 891 | eval time = 2258.93 ms / 120 tokens ( 18.98 ms per token, 52.68 tokens per second) 1.11.914.986 I slot print_timing: id 2 | task 891 | total time = 2398.15 ms / 251 tokens 1.11.914.987 I slot print_timing: id 2 | task 891 | graphs reused = 615 1.11.914.988 I slot print_timing: id 2 | task 891 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.915.041 I slot release: id 2 | task 891 | stop processing: n_tokens = 1375, truncated = 0 1.11.945.368 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.833 1.11.945.484 I slot launch_slot_: id 2 | task 1018 | processing task, is_child = 0 1.12.781.755 I slot print_timing: id 1 | task 1005 | prompt eval time = 135.10 ms / 87 tokens ( 1.55 ms per token, 643.98 tokens per second) 1.12.781.760 I slot print_timing: id 1 | task 1005 | eval time = 1007.95 ms / 59 tokens ( 17.38 ms per token, 57.54 tokens per second) 1.12.781.761 I slot print_timing: id 1 | task 1005 | total time = 1143.04 ms / 146 tokens 1.12.781.763 I slot print_timing: id 1 | task 1005 | graphs reused = 660 1.12.781.763 I slot print_timing: id 1 | task 1005 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.781.815 I slot release: id 1 | task 1005 | stop processing: n_tokens = 1270, truncated = 0 1.12.841.168 I slot print_timing: id 2 | task 1018 | prompt eval time = 136.67 ms / 98 tokens ( 1.39 ms per token, 717.08 tokens per second) 1.12.841.173 I slot print_timing: id 2 | task 1018 | eval time = 759.00 ms / 49 tokens ( 15.81 ms per token, 63.24 tokens per second) 1.12.841.174 I slot print_timing: id 2 | task 1018 | total time = 895.67 ms / 147 tokens 1.12.841.175 I slot print_timing: id 2 | task 1018 | graphs reused = 660 1.12.841.176 I slot print_timing: id 2 | task 1018 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.841.226 I slot release: id 2 | task 1018 | stop processing: n_tokens = 1271, truncated = 0 1.12.841.524 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.902 1.12.841.630 I slot launch_slot_: id 1 | task 1069 | processing task, is_child = 0 1.12.841.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 1.12.843.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.537 MiB) 1.12.844.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 1.12.888.296 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.902 1.12.888.426 I slot launch_slot_: id 2 | task 1070 | processing task, is_child = 0 1.13.175.746 I slot print_timing: id 0 | task 919 | prompt eval time = 206.23 ms / 137 tokens ( 1.51 ms per token, 664.32 tokens per second) 1.13.175.752 I slot print_timing: id 0 | task 919 | eval time = 2882.99 ms / 151 tokens ( 19.22 ms per token, 52.03 tokens per second) 1.13.175.753 I slot print_timing: id 0 | task 919 | total time = 3089.21 ms / 288 tokens 1.13.175.754 I slot print_timing: id 0 | task 919 | graphs reused = 664 1.13.175.754 I slot print_timing: id 0 | task 919 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.175.807 I slot release: id 0 | task 919 | stop processing: n_tokens = 1412, truncated = 0 1.13.210.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.812 1.13.210.590 I slot launch_slot_: id 0 | task 1080 | processing task, is_child = 0 1.13.320.762 I slot print_timing: id 3 | task 920 | n_gen = 155, tg = 50.88 t/s, tg_3s = 51.21 t/s 1.13.582.408 I slot print_timing: id 3 | task 920 | prompt eval time = 188.04 ms / 153 tokens ( 1.23 ms per token, 813.64 tokens per second) 1.13.582.413 I slot print_timing: id 3 | task 920 | eval time = 3288.51 ms / 172 tokens ( 19.23 ms per token, 52.00 tokens per second) 1.13.582.414 I slot print_timing: id 3 | task 920 | total time = 3476.56 ms / 325 tokens 1.13.582.415 I slot print_timing: id 3 | task 920 | graphs reused = 682 1.13.582.416 I slot print_timing: id 3 | task 920 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.582.468 I slot release: id 3 | task 920 | stop processing: n_tokens = 1449, truncated = 0 1.13.616.906 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.791 1.13.617.011 I slot launch_slot_: id 3 | task 1102 | processing task, is_child = 0 1.14.549.864 I slot print_timing: id 0 | task 1080 | prompt eval time = 109.32 ms / 122 tokens ( 0.90 ms per token, 1115.97 tokens per second) 1.14.549.870 I slot print_timing: id 0 | task 1080 | eval time = 1229.94 ms / 78 tokens ( 15.97 ms per token, 62.60 tokens per second) 1.14.549.871 I slot print_timing: id 0 | task 1080 | total time = 1339.26 ms / 200 tokens 1.14.549.872 I slot print_timing: id 0 | task 1080 | graphs reused = 737 1.14.549.873 I slot print_timing: id 0 | task 1080 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.549.926 I slot release: id 0 | task 1080 | stop processing: n_tokens = 1324, truncated = 0 1.14.583.980 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.866 1.14.584.095 I slot launch_slot_: id 0 | task 1163 | processing task, is_child = 0 1.14.798.195 I slot print_timing: id 2 | task 1070 | prompt eval time = 187.14 ms / 113 tokens ( 1.66 ms per token, 603.82 tokens per second) 1.14.798.200 I slot print_timing: id 2 | task 1070 | eval time = 1703.42 ms / 98 tokens ( 17.56 ms per token, 56.94 tokens per second) 1.14.798.201 I slot print_timing: id 2 | task 1070 | total time = 1890.56 ms / 211 tokens 1.14.798.202 I slot print_timing: id 2 | task 1070 | graphs reused = 745 1.14.798.203 I slot print_timing: id 2 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.798.253 I slot release: id 2 | task 1070 | stop processing: n_tokens = 1335, truncated = 0 1.14.827.533 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.858 1.14.827.643 I slot launch_slot_: id 2 | task 1174 | processing task, is_child = 0 1.15.211.986 I slot print_timing: id 1 | task 1069 | prompt eval time = 205.75 ms / 105 tokens ( 1.96 ms per token, 510.33 tokens per second) 1.15.211.992 I slot print_timing: id 1 | task 1069 | eval time = 2117.79 ms / 117 tokens ( 18.26 ms per token, 54.77 tokens per second) 1.15.211.993 I slot print_timing: id 1 | task 1069 | total time = 2323.54 ms / 222 tokens 1.15.211.994 I slot print_timing: id 1 | task 1069 | graphs reused = 760 1.15.211.994 I slot print_timing: id 1 | task 1069 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.212.047 I slot release: id 1 | task 1069 | stop processing: n_tokens = 1346, truncated = 0 1.15.272.122 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.851 1.15.272.243 I slot launch_slot_: id 1 | task 1195 | processing task, is_child = 0 1.15.569.137 I slot print_timing: id 3 | task 1102 | prompt eval time = 109.96 ms / 96 tokens ( 1.15 ms per token, 873.07 tokens per second) 1.15.569.142 I slot print_timing: id 3 | task 1102 | eval time = 1842.15 ms / 101 tokens ( 18.42 ms per token, 54.28 tokens per second) 1.15.569.144 I slot print_timing: id 3 | task 1102 | total time = 1952.11 ms / 197 tokens 1.15.569.146 I slot print_timing: id 3 | task 1102 | graphs reused = 769 1.15.569.146 I slot print_timing: id 3 | task 1102 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.569.199 I slot release: id 3 | task 1102 | stop processing: n_tokens = 1321, truncated = 0 1.15.602.852 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.868 1.15.602.961 I slot launch_slot_: id 3 | task 1210 | processing task, is_child = 0 1.16.766.311 I slot print_timing: id 0 | task 1163 | prompt eval time = 105.03 ms / 113 tokens ( 0.93 ms per token, 1075.83 tokens per second) 1.16.766.316 I slot print_timing: id 0 | task 1163 | eval time = 2077.16 ms / 114 tokens ( 18.38 ms per token, 54.40 tokens per second) 1.16.766.317 I slot print_timing: id 0 | task 1163 | total time = 2182.20 ms / 227 tokens 1.16.766.318 I slot print_timing: id 0 | task 1163 | graphs reused = 838 1.16.766.319 I slot print_timing: id 0 | task 1163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.766.376 I slot release: id 0 | task 1163 | stop processing: n_tokens = 1351, truncated = 0 1.16.815.274 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.848 1.16.815.389 I slot launch_slot_: id 0 | task 1285 | processing task, is_child = 0 1.17.443.553 I slot print_timing: id 3 | task 1210 | prompt eval time = 113.86 ms / 117 tokens ( 0.97 ms per token, 1027.61 tokens per second) 1.17.443.559 I slot print_timing: id 3 | task 1210 | eval time = 1726.72 ms / 109 tokens ( 15.99 ms per token, 62.55 tokens per second) 1.17.443.560 I slot print_timing: id 3 | task 1210 | total time = 1840.58 ms / 226 tokens 1.17.443.561 I slot print_timing: id 3 | task 1210 | graphs reused = 874 1.17.443.562 I slot print_timing: id 3 | task 1210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.443.616 I slot release: id 3 | task 1210 | stop processing: n_tokens = 1350, truncated = 0 1.17.477.718 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.849 1.17.477.829 I slot launch_slot_: id 3 | task 1324 | processing task, is_child = 0 1.17.713.161 I slot print_timing: id 2 | task 1174 | prompt eval time = 145.72 ms / 149 tokens ( 0.98 ms per token, 1022.48 tokens per second) 1.17.713.167 I slot print_timing: id 2 | task 1174 | eval time = 2739.78 ms / 154 tokens ( 17.91 ms per token, 55.84 tokens per second) 1.17.713.168 I slot print_timing: id 2 | task 1174 | total time = 2885.50 ms / 303 tokens 1.17.713.169 I slot print_timing: id 2 | task 1174 | graphs reused = 881 1.17.713.170 I slot print_timing: id 2 | task 1174 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.713.222 I slot release: id 2 | task 1174 | stop processing: n_tokens = 1427, truncated = 0 1.17.772.848 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.803 1.17.772.972 I slot launch_slot_: id 2 | task 1336 | processing task, is_child = 0 1.17.851.747 I slot print_timing: id 1 | task 1195 | prompt eval time = 140.65 ms / 131 tokens ( 1.07 ms per token, 931.42 tokens per second) 1.17.851.753 I slot print_timing: id 1 | task 1195 | eval time = 2438.84 ms / 137 tokens ( 17.93 ms per token, 55.76 tokens per second) 1.17.851.754 I slot print_timing: id 1 | task 1195 | total time = 2579.49 ms / 268 tokens 1.17.851.755 I slot print_timing: id 1 | task 1195 | graphs reused = 881 1.17.851.755 I slot print_timing: id 1 | task 1195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.851.811 I slot release: id 1 | task 1195 | stop processing: n_tokens = 1392, truncated = 0 1.17.905.395 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.823 1.17.905.510 I slot launch_slot_: id 1 | task 1339 | processing task, is_child = 0 1.19.021.242 I slot print_timing: id 1 | task 1339 | prompt eval time = 141.85 ms / 104 tokens ( 1.36 ms per token, 733.17 tokens per second) 1.19.021.250 I slot print_timing: id 1 | task 1339 | eval time = 973.86 ms / 68 tokens ( 14.54 ms per token, 68.80 tokens per second) 1.19.021.251 I slot print_timing: id 1 | task 1339 | total time = 1115.71 ms / 172 tokens 1.19.021.252 I slot print_timing: id 1 | task 1339 | graphs reused = 947 1.19.021.254 I slot print_timing: id 1 | task 1339 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.021.315 I slot release: id 1 | task 1339 | stop processing: n_tokens = 1296, truncated = 0 1.19.051.536 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.884 1.19.051.672 I slot launch_slot_: id 1 | task 1410 | processing task, is_child = 0 1.19.277.284 I slot print_timing: id 0 | task 1285 | prompt eval time = 109.40 ms / 127 tokens ( 0.86 ms per token, 1160.85 tokens per second) 1.19.277.289 I slot print_timing: id 0 | task 1285 | eval time = 2352.48 ms / 128 tokens ( 18.52 ms per token, 53.99 tokens per second) 1.19.277.290 I slot print_timing: id 0 | task 1285 | total time = 2461.88 ms / 255 tokens 1.19.277.291 I slot print_timing: id 0 | task 1285 | graphs reused = 952 1.19.277.292 I slot print_timing: id 0 | task 1285 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.277.345 I slot release: id 0 | task 1285 | stop processing: n_tokens = 1379, truncated = 0 1.19.325.221 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.831 1.19.325.337 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 1.19.530.175 I slot print_timing: id 2 | task 1336 | prompt eval time = 132.12 ms / 96 tokens ( 1.38 ms per token, 726.62 tokens per second) 1.19.530.182 I slot print_timing: id 2 | task 1336 | eval time = 1625.07 ms / 90 tokens ( 18.26 ms per token, 54.77 tokens per second) 1.19.530.183 I slot print_timing: id 2 | task 1336 | total time = 1757.19 ms / 186 tokens 1.19.530.184 I slot print_timing: id 2 | task 1336 | graphs reused = 960 1.19.530.184 I slot print_timing: id 2 | task 1336 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.530.239 I slot release: id 2 | task 1336 | stop processing: n_tokens = 1310, truncated = 0 1.19.590.412 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.875 1.19.590.536 I slot launch_slot_: id 2 | task 1433 | processing task, is_child = 0 1.20.322.205 I slot print_timing: id 1 | task 1410 | prompt eval time = 133.31 ms / 98 tokens ( 1.36 ms per token, 735.13 tokens per second) 1.20.322.211 I slot print_timing: id 1 | task 1410 | eval time = 1137.21 ms / 61 tokens ( 18.95 ms per token, 52.76 tokens per second) 1.20.322.213 I slot print_timing: id 1 | task 1410 | total time = 1270.52 ms / 159 tokens 1.20.322.213 I slot print_timing: id 1 | task 1410 | graphs reused = 998 1.20.322.214 I slot print_timing: id 1 | task 1410 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.322.264 I slot release: id 1 | task 1410 | stop processing: n_tokens = 1283, truncated = 0 1.20.382.612 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.893 1.20.382.725 I slot launch_slot_: id 1 | task 1477 | processing task, is_child = 0 1.20.574.439 I slot print_timing: id 3 | task 1324 | prompt eval time = 124.79 ms / 137 tokens ( 0.91 ms per token, 1097.81 tokens per second) 1.20.574.445 I slot print_timing: id 3 | task 1324 | eval time = 2971.80 ms / 151 tokens ( 19.81 ms per token, 50.47 tokens per second) 1.20.574.446 I slot print_timing: id 3 | task 1324 | total time = 3096.59 ms / 288 tokens 1.20.574.447 I slot print_timing: id 3 | task 1324 | graphs reused = 1000 1.20.574.447 I slot print_timing: id 3 | task 1324 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.574.498 I slot release: id 3 | task 1324 | stop processing: n_tokens = 1412, truncated = 0 1.20.608.938 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.812 1.20.609.051 I slot launch_slot_: id 3 | task 1485 | processing task, is_child = 0 1.20.896.283 I slot print_timing: id 0 | task 1422 | prompt eval time = 106.87 ms / 102 tokens ( 1.05 ms per token, 954.43 tokens per second) 1.20.896.289 I slot print_timing: id 0 | task 1422 | eval time = 1464.06 ms / 72 tokens ( 20.62 ms per token, 48.50 tokens per second) 1.20.896.290 I slot print_timing: id 0 | task 1422 | total time = 1570.93 ms / 174 tokens 1.20.896.292 I slot print_timing: id 0 | task 1422 | graphs reused = 1011 1.20.896.293 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.896.349 I slot release: id 0 | task 1422 | stop processing: n_tokens = 1298, truncated = 0 1.20.932.118 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.883 1.20.932.237 I slot launch_slot_: id 0 | task 1501 | processing task, is_child = 0 1.21.622.531 I slot print_timing: id 2 | task 1433 | prompt eval time = 137.46 ms / 108 tokens ( 1.27 ms per token, 785.67 tokens per second) 1.21.622.536 I slot print_timing: id 2 | task 1433 | eval time = 1894.52 ms / 104 tokens ( 18.39 ms per token, 54.37 tokens per second) 1.21.622.537 I slot print_timing: id 2 | task 1433 | total time = 2031.98 ms / 212 tokens 1.21.622.538 I slot print_timing: id 2 | task 1433 | graphs reused = 1050 1.21.622.539 I slot print_timing: id 2 | task 1433 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.622.589 I slot release: id 2 | task 1433 | stop processing: n_tokens = 1336, truncated = 0 1.21.652.745 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.858 1.21.652.869 I slot launch_slot_: id 2 | task 1543 | processing task, is_child = 0 1.22.204.267 I slot print_timing: id 1 | task 1477 | prompt eval time = 140.55 ms / 122 tokens ( 1.15 ms per token, 868.01 tokens per second) 1.22.204.272 I slot print_timing: id 1 | task 1477 | eval time = 1680.97 ms / 92 tokens ( 18.47 ms per token, 54.14 tokens per second) 1.22.204.273 I slot print_timing: id 1 | task 1477 | total time = 1821.53 ms / 214 tokens 1.22.204.274 I slot print_timing: id 1 | task 1477 | graphs reused = 1077 1.22.204.275 I slot print_timing: id 1 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.204.327 I slot release: id 1 | task 1477 | stop processing: n_tokens = 1338, truncated = 0 1.22.233.932 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.857 1.22.234.035 I slot launch_slot_: id 1 | task 1575 | processing task, is_child = 0 1.22.680.934 I slot print_timing: id 2 | task 1543 | prompt eval time = 134.27 ms / 86 tokens ( 1.56 ms per token, 640.50 tokens per second) 1.22.680.939 I slot print_timing: id 2 | task 1543 | eval time = 893.78 ms / 53 tokens ( 17.19 ms per token, 58.18 tokens per second) 1.22.680.940 I slot print_timing: id 2 | task 1543 | total time = 1028.05 ms / 139 tokens 1.22.680.941 I slot print_timing: id 2 | task 1543 | graphs reused = 1097 1.22.680.942 I slot print_timing: id 2 | task 1543 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.680.992 I slot release: id 2 | task 1543 | stop processing: n_tokens = 1263, truncated = 0 1.22.710.231 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.907 1.22.710.341 I slot launch_slot_: id 2 | task 1600 | processing task, is_child = 0 1.23.197.304 I slot print_timing: id 0 | task 1501 | prompt eval time = 110.86 ms / 111 tokens ( 1.00 ms per token, 1001.24 tokens per second) 1.23.197.309 I slot print_timing: id 0 | task 1501 | eval time = 2154.19 ms / 121 tokens ( 17.95 ms per token, 55.71 tokens per second) 1.23.197.310 I slot print_timing: id 0 | task 1501 | total time = 2265.05 ms / 232 tokens 1.23.197.313 I slot print_timing: id 0 | task 1501 | graphs reused = 1120 1.23.197.314 I slot print_timing: id 0 | task 1501 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.197.364 I slot release: id 0 | task 1501 | stop processing: n_tokens = 1356, truncated = 0 1.23.231.226 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.845 1.23.231.336 I slot launch_slot_: id 0 | task 1629 | processing task, is_child = 0 1.23.334.156 I slot print_timing: id 3 | task 1485 | prompt eval time = 116.91 ms / 124 tokens ( 0.94 ms per token, 1060.65 tokens per second) 1.23.334.162 I slot print_timing: id 3 | task 1485 | eval time = 2608.18 ms / 140 tokens ( 18.76 ms per token, 53.29 tokens per second) 1.23.334.163 I slot print_timing: id 3 | task 1485 | total time = 2725.09 ms / 264 tokens 1.23.334.163 I slot print_timing: id 3 | task 1485 | graphs reused = 1122 1.23.334.164 I slot print_timing: id 3 | task 1485 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.334.219 I slot release: id 3 | task 1485 | stop processing: n_tokens = 1388, truncated = 0 1.23.366.754 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.826 1.23.366.869 I slot launch_slot_: id 3 | task 1634 | processing task, is_child = 0 1.24.213.266 I slot print_timing: id 1 | task 1575 | prompt eval time = 137.64 ms / 106 tokens ( 1.30 ms per token, 770.12 tokens per second) 1.24.213.272 I slot print_timing: id 1 | task 1575 | eval time = 1841.57 ms / 105 tokens ( 17.71 ms per token, 56.47 tokens per second) 1.24.213.273 I slot print_timing: id 1 | task 1575 | total time = 1979.22 ms / 211 tokens 1.24.213.274 I slot print_timing: id 1 | task 1575 | graphs reused = 1170 1.24.213.274 I slot print_timing: id 1 | task 1575 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.213.325 I slot release: id 1 | task 1575 | stop processing: n_tokens = 1335, truncated = 0 1.24.244.073 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.858 1.24.244.185 I slot launch_slot_: id 1 | task 1686 | processing task, is_child = 0 1.24.464.619 I slot print_timing: id 3 | task 1634 | prompt eval time = 116.18 ms / 121 tokens ( 0.96 ms per token, 1041.48 tokens per second) 1.24.464.624 I slot print_timing: id 3 | task 1634 | eval time = 981.55 ms / 57 tokens ( 17.53 ms per token, 57.05 tokens per second) 1.24.464.626 I slot print_timing: id 3 | task 1634 | total time = 1097.73 ms / 178 tokens 1.24.464.627 I slot print_timing: id 3 | task 1634 | graphs reused = 1174 1.24.464.627 I slot print_timing: id 3 | task 1634 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.464.679 I slot release: id 3 | task 1634 | stop processing: n_tokens = 1302, truncated = 0 1.24.499.639 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.880 1.24.499.774 I slot launch_slot_: id 3 | task 1696 | processing task, is_child = 0 1.24.977.683 I slot print_timing: id 2 | task 1600 | prompt eval time = 132.23 ms / 98 tokens ( 1.35 ms per token, 741.14 tokens per second) 1.24.977.689 I slot print_timing: id 2 | task 1600 | eval time = 2135.10 ms / 117 tokens ( 18.41 ms per token, 54.33 tokens per second) 1.24.977.690 I slot print_timing: id 2 | task 1600 | total time = 2267.32 ms / 215 tokens 1.24.977.692 I slot print_timing: id 2 | task 1600 | graphs reused = 1198 1.24.977.692 I slot print_timing: id 2 | task 1600 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.977.749 I slot release: id 2 | task 1600 | stop processing: n_tokens = 1339, truncated = 0 1.25.010.097 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.856 1.25.010.198 I slot launch_slot_: id 2 | task 1724 | processing task, is_child = 0 1.25.226.737 I slot print_timing: id 0 | task 1629 | prompt eval time = 102.02 ms / 91 tokens ( 1.12 ms per token, 892.00 tokens per second) 1.25.226.743 I slot print_timing: id 0 | task 1629 | eval time = 1893.37 ms / 96 tokens ( 19.93 ms per token, 50.18 tokens per second) 1.25.226.744 I slot print_timing: id 0 | task 1629 | total time = 1995.38 ms / 187 tokens 1.25.226.745 I slot print_timing: id 0 | task 1629 | graphs reused = 1201 1.25.226.746 I slot print_timing: id 0 | task 1629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.226.804 I slot release: id 0 | task 1629 | stop processing: n_tokens = 1311, truncated = 0 1.25.262.195 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.874 1.25.262.306 I slot launch_slot_: id 0 | task 1733 | processing task, is_child = 0 1.25.984.733 I slot print_timing: id 1 | task 1686 | prompt eval time = 139.38 ms / 105 tokens ( 1.33 ms per token, 753.31 tokens per second) 1.25.984.738 I slot print_timing: id 1 | task 1686 | eval time = 1601.15 ms / 85 tokens ( 19.06 ms per token, 52.46 tokens per second) 1.25.984.740 I slot print_timing: id 1 | task 1686 | total time = 1740.53 ms / 190 tokens 1.25.984.741 I slot print_timing: id 1 | task 1686 | graphs reused = 1241 1.25.984.741 I slot print_timing: id 1 | task 1686 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.984.793 I slot release: id 1 | task 1686 | stop processing: n_tokens = 1314, truncated = 0 1.26.044.794 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.872 1.26.044.899 I slot launch_slot_: id 1 | task 1778 | processing task, is_child = 0 1.26.228.194 I slot print_timing: id 3 | task 1696 | prompt eval time = 111.40 ms / 95 tokens ( 1.17 ms per token, 852.81 tokens per second) 1.26.228.200 I slot print_timing: id 3 | task 1696 | eval time = 1617.01 ms / 82 tokens ( 19.96 ms per token, 50.09 tokens per second) 1.26.228.201 I slot print_timing: id 3 | task 1696 | total time = 1728.40 ms / 177 tokens 1.26.228.202 I slot print_timing: id 3 | task 1696 | graphs reused = 1242 1.26.228.203 I slot print_timing: id 3 | task 1696 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.228.256 I slot release: id 3 | task 1696 | stop processing: n_tokens = 1301, truncated = 0 1.26.261.586 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.881 1.26.261.701 I slot launch_slot_: id 3 | task 1785 | processing task, is_child = 0 1.26.682.566 I slot print_timing: id 0 | task 1733 | prompt eval time = 107.21 ms / 110 tokens ( 0.97 ms per token, 1026.01 tokens per second) 1.26.682.571 I slot print_timing: id 0 | task 1733 | eval time = 1313.03 ms / 72 tokens ( 18.49 ms per token, 54.07 tokens per second) 1.26.682.572 I slot print_timing: id 0 | task 1733 | total time = 1420.24 ms / 182 tokens 1.26.682.573 I slot print_timing: id 0 | task 1733 | graphs reused = 1263 1.26.682.574 I slot print_timing: id 0 | task 1733 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.682.625 I slot release: id 0 | task 1733 | stop processing: n_tokens = 1306, truncated = 0 1.26.716.438 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.877 1.26.716.550 I slot launch_slot_: id 0 | task 1811 | processing task, is_child = 0 1.27.682.218 I slot print_timing: id 3 | task 1785 | prompt eval time = 111.97 ms / 115 tokens ( 0.97 ms per token, 1027.11 tokens per second) 1.27.682.224 I slot print_timing: id 3 | task 1785 | eval time = 1308.53 ms / 84 tokens ( 15.77 ms per token, 63.43 tokens per second) 1.27.682.225 I slot print_timing: id 3 | task 1785 | total time = 1420.50 ms / 199 tokens 1.27.682.226 I slot print_timing: id 3 | task 1785 | graphs reused = 1322 1.27.682.227 I slot print_timing: id 3 | task 1785 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.682.280 I slot release: id 3 | task 1785 | stop processing: n_tokens = 1323, truncated = 0 1.27.716.303 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.866 1.27.716.413 I slot launch_slot_: id 3 | task 1874 | processing task, is_child = 0 1.28.043.671 I slot print_timing: id 2 | task 1724 | prompt eval time = 150.49 ms / 144 tokens ( 1.05 ms per token, 956.89 tokens per second) 1.28.043.678 I slot print_timing: id 2 | task 1724 | eval time = 2882.97 ms / 160 tokens ( 18.13 ms per token, 55.15 tokens per second) 1.28.043.679 I slot print_timing: id 2 | task 1724 | total time = 3033.45 ms / 304 tokens 1.28.043.680 I slot print_timing: id 2 | task 1724 | graphs reused = 1336 1.28.043.681 I slot print_timing: id 2 | task 1724 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.043.742 I slot release: id 2 | task 1724 | stop processing: n_tokens = 1428, truncated = 0 1.28.074.523 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.803 1.28.074.641 I slot launch_slot_: id 2 | task 1892 | processing task, is_child = 0 1.28.729.798 I slot print_timing: id 1 | task 1778 | prompt eval time = 148.54 ms / 158 tokens ( 0.94 ms per token, 1063.72 tokens per second) 1.28.729.804 I slot print_timing: id 1 | task 1778 | eval time = 2536.35 ms / 145 tokens ( 17.61 ms per token, 56.77 tokens per second) 1.28.729.805 I slot print_timing: id 1 | task 1778 | total time = 2684.88 ms / 303 tokens 1.28.729.806 I slot print_timing: id 1 | task 1778 | graphs reused = 1369 1.28.729.806 I slot print_timing: id 1 | task 1778 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.729.859 I slot release: id 1 | task 1778 | stop processing: n_tokens = 1427, truncated = 0 1.28.760.294 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.803 1.28.760.409 I slot launch_slot_: id 1 | task 1930 | processing task, is_child = 0 1.28.953.952 I slot print_timing: id 3 | task 1874 | prompt eval time = 108.48 ms / 81 tokens ( 1.34 ms per token, 746.70 tokens per second) 1.28.953.958 I slot print_timing: id 3 | task 1874 | eval time = 1129.05 ms / 58 tokens ( 19.81 ms per token, 50.49 tokens per second) 1.28.953.959 I slot print_timing: id 3 | task 1874 | total time = 1237.52 ms / 139 tokens 1.28.953.960 I slot print_timing: id 3 | task 1874 | graphs reused = 1371 1.28.953.960 I slot print_timing: id 3 | task 1874 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.954.014 I slot release: id 3 | task 1874 | stop processing: n_tokens = 1263, truncated = 0 1.28.971.285 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.907 1.28.971.391 I slot launch_slot_: id 3 | task 1937 | processing task, is_child = 0 1.29.634.326 I slot print_timing: id 2 | task 1892 | prompt eval time = 137.28 ms / 104 tokens ( 1.32 ms per token, 757.55 tokens per second) 1.29.634.331 I slot print_timing: id 2 | task 1892 | eval time = 1422.38 ms / 80 tokens ( 18.00 ms per token, 55.54 tokens per second) 1.29.634.333 I slot print_timing: id 2 | task 1892 | total time = 1559.67 ms / 184 tokens 1.29.634.333 I slot print_timing: id 2 | task 1892 | graphs reused = 1406 1.29.634.334 I slot print_timing: id 2 | task 1892 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.634.385 I slot release: id 2 | task 1892 | stop processing: n_tokens = 1308, truncated = 0 1.29.664.399 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.876 1.29.664.514 I slot launch_slot_: id 2 | task 1977 | processing task, is_child = 0 1.29.840.050 I slot print_timing: id 0 | task 1811 | n_gen = 164, tg = 54.05 t/s, tg_3s = 54.38 t/s 1.29.960.486 I slot print_timing: id 1 | task 1930 | prompt eval time = 141.89 ms / 125 tokens ( 1.14 ms per token, 880.95 tokens per second) 1.29.960.493 I slot print_timing: id 1 | task 1930 | eval time = 1058.17 ms / 56 tokens ( 19.24 ms per token, 51.98 tokens per second) 1.29.960.494 I slot print_timing: id 1 | task 1930 | total time = 1200.06 ms / 181 tokens 1.29.960.495 I slot print_timing: id 1 | task 1930 | graphs reused = 1415 1.29.960.496 I slot print_timing: id 1 | task 1930 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.960.558 I slot release: id 1 | task 1930 | stop processing: n_tokens = 1305, truncated = 0 1.29.991.296 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.878 1.29.991.411 I slot launch_slot_: id 1 | task 1991 | processing task, is_child = 0 1.30.980.213 I slot print_timing: id 2 | task 1977 | prompt eval time = 141.12 ms / 126 tokens ( 1.12 ms per token, 892.86 tokens per second) 1.30.980.219 I slot print_timing: id 2 | task 1977 | eval time = 1174.57 ms / 72 tokens ( 16.54 ms per token, 60.45 tokens per second) 1.30.980.220 I slot print_timing: id 2 | task 1977 | total time = 1315.68 ms / 198 tokens 1.30.980.221 I slot print_timing: id 2 | task 1977 | graphs reused = 1472 1.30.980.222 I slot print_timing: id 2 | task 1977 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.980.272 I slot release: id 2 | task 1977 | stop processing: n_tokens = 1322, truncated = 0 1.31.038.770 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.867 1.31.038.878 I slot launch_slot_: id 2 | task 2054 | processing task, is_child = 0 1.31.939.572 I slot print_timing: id 3 | task 1937 | prompt eval time = 114.52 ms / 103 tokens ( 1.11 ms per token, 899.44 tokens per second) 1.31.939.578 I slot print_timing: id 3 | task 1937 | eval time = 2853.65 ms / 166 tokens ( 17.29 ms per token, 57.82 tokens per second) 1.31.939.579 I slot print_timing: id 3 | task 1937 | total time = 2968.17 ms / 269 tokens 1.31.939.580 I slot print_timing: id 3 | task 1937 | graphs reused = 1521 1.31.939.581 I slot print_timing: id 3 | task 1937 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.939.632 I slot release: id 3 | task 1937 | stop processing: n_tokens = 1393, truncated = 0 1.31.974.712 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.823 1.31.974.824 I slot launch_slot_: id 3 | task 2110 | processing task, is_child = 0 1.32.505.156 I slot print_timing: id 2 | task 2054 | prompt eval time = 135.83 ms / 108 tokens ( 1.26 ms per token, 795.13 tokens per second) 1.32.505.162 I slot print_timing: id 2 | task 2054 | eval time = 1330.44 ms / 83 tokens ( 16.22 ms per token, 61.63 tokens per second) 1.32.505.163 I slot print_timing: id 2 | task 2054 | total time = 1466.26 ms / 191 tokens 1.32.505.165 I slot print_timing: id 2 | task 2054 | graphs reused = 1548 1.32.505.166 I slot print_timing: id 2 | task 2054 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.505.218 I slot release: id 2 | task 2054 | stop processing: n_tokens = 1315, truncated = 0 1.32.535.645 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.871 1.32.535.761 I slot launch_slot_: id 2 | task 2141 | processing task, is_child = 0 1.32.772.248 I slot print_timing: id 1 | task 1991 | prompt eval time = 141.78 ms / 125 tokens ( 1.13 ms per token, 881.63 tokens per second) 1.32.772.253 I slot print_timing: id 1 | task 1991 | eval time = 2639.04 ms / 153 tokens ( 17.36 ms per token, 57.60 tokens per second) 1.32.772.254 I slot print_timing: id 1 | task 1991 | total time = 2780.82 ms / 278 tokens 1.32.772.255 I slot print_timing: id 1 | task 1991 | graphs reused = 1552 1.32.772.256 I slot print_timing: id 1 | task 1991 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.772.310 I slot release: id 1 | task 1991 | stop processing: n_tokens = 1402, truncated = 0 1.32.803.018 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.817 1.32.803.130 I slot launch_slot_: id 1 | task 2150 | processing task, is_child = 0 1.32.882.267 I slot print_timing: id 0 | task 1811 | n_gen = 329, tg = 54.14 t/s, tg_3s = 54.24 t/s 1.33.399.581 I slot print_timing: id 3 | task 2110 | prompt eval time = 115.75 ms / 100 tokens ( 1.16 ms per token, 863.92 tokens per second) 1.33.399.587 I slot print_timing: id 3 | task 2110 | eval time = 1308.99 ms / 69 tokens ( 19.25 ms per token, 51.95 tokens per second) 1.33.399.588 I slot print_timing: id 3 | task 2110 | total time = 1424.74 ms / 169 tokens 1.33.399.589 I slot print_timing: id 3 | task 2110 | graphs reused = 1581 1.33.399.590 I slot print_timing: id 3 | task 2110 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.399.644 I slot release: id 3 | task 2110 | stop processing: n_tokens = 1293, truncated = 0 1.33.434.175 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.886 1.33.434.289 I slot launch_slot_: id 3 | task 2185 | processing task, is_child = 0 1.33.804.833 I slot print_timing: id 2 | task 2141 | prompt eval time = 155.90 ms / 171 tokens ( 0.91 ms per token, 1096.85 tokens per second) 1.33.804.839 I slot print_timing: id 2 | task 2141 | eval time = 1113.15 ms / 60 tokens ( 18.87 ms per token, 53.00 tokens per second) 1.33.804.840 I slot print_timing: id 2 | task 2141 | total time = 1269.06 ms / 231 tokens 1.33.804.841 I slot print_timing: id 2 | task 2141 | graphs reused = 1598 1.33.804.842 I slot print_timing: id 2 | task 2141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.804.895 I slot release: id 2 | task 2141 | stop processing: n_tokens = 1355, truncated = 0 1.33.865.376 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.846 1.33.865.504 I slot launch_slot_: id 2 | task 2207 | processing task, is_child = 0 1.34.420.206 I slot print_timing: id 1 | task 2150 | prompt eval time = 135.80 ms / 89 tokens ( 1.53 ms per token, 655.39 tokens per second) 1.34.420.212 I slot print_timing: id 1 | task 2150 | eval time = 1481.26 ms / 84 tokens ( 17.85 ms per token, 56.03 tokens per second) 1.34.420.213 I slot print_timing: id 1 | task 2150 | total time = 1617.06 ms / 173 tokens 1.34.420.214 I slot print_timing: id 1 | task 2150 | graphs reused = 1625 1.34.420.215 I slot print_timing: id 1 | task 2150 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.420.264 I slot release: id 1 | task 2150 | stop processing: n_tokens = 1297, truncated = 0 1.34.478.668 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.884 1.34.478.775 I slot launch_slot_: id 1 | task 2240 | processing task, is_child = 0 1.34.677.323 I slot print_timing: id 3 | task 2185 | prompt eval time = 109.03 ms / 82 tokens ( 1.33 ms per token, 752.12 tokens per second) 1.34.677.329 I slot print_timing: id 3 | task 2185 | eval time = 1133.99 ms / 58 tokens ( 19.89 ms per token, 50.26 tokens per second) 1.34.677.330 I slot print_timing: id 3 | task 2185 | total time = 1243.02 ms / 140 tokens 1.34.677.331 I slot print_timing: id 3 | task 2185 | graphs reused = 1628 1.34.677.331 I slot print_timing: id 3 | task 2185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.677.383 I slot release: id 3 | task 2185 | stop processing: n_tokens = 1264, truncated = 0 1.34.693.992 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.907 1.34.694.100 I slot launch_slot_: id 3 | task 2248 | processing task, is_child = 0 1.35.360.709 I slot print_timing: id 2 | task 2207 | prompt eval time = 140.14 ms / 114 tokens ( 1.23 ms per token, 813.47 tokens per second) 1.35.360.714 I slot print_timing: id 2 | task 2207 | eval time = 1355.05 ms / 78 tokens ( 17.60 ms per token, 56.82 tokens per second) 1.35.360.715 I slot print_timing: id 2 | task 2207 | total time = 1495.19 ms / 192 tokens 1.35.360.716 I slot print_timing: id 2 | task 2207 | graphs reused = 1665 1.35.360.717 I slot print_timing: id 2 | task 2207 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.360.767 I slot release: id 2 | task 2207 | stop processing: n_tokens = 1316, truncated = 0 1.35.419.029 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.871 1.35.419.140 I slot launch_slot_: id 2 | task 2291 | processing task, is_child = 0 1.35.873.502 I slot print_timing: id 1 | task 2240 | prompt eval time = 133.73 ms / 98 tokens ( 1.36 ms per token, 732.84 tokens per second) 1.35.873.508 I slot print_timing: id 1 | task 2240 | eval time = 1260.98 ms / 71 tokens ( 18.01 ms per token, 55.51 tokens per second) 1.35.873.509 I slot print_timing: id 1 | task 2240 | total time = 1394.71 ms / 169 tokens 1.35.873.509 I slot print_timing: id 1 | task 2240 | graphs reused = 1685 1.35.873.510 I slot print_timing: id 1 | task 2240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.873.562 I slot release: id 1 | task 2240 | stop processing: n_tokens = 1293, truncated = 0 1.35.903.306 I slot print_timing: id 0 | task 1811 | n_gen = 488, tg = 53.64 t/s, tg_3s = 52.63 t/s 1.35.903.936 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.886 1.35.904.052 I slot launch_slot_: id 1 | task 2316 | processing task, is_child = 0 1.36.127.835 I slot print_timing: id 0 | task 1811 | prompt eval time = 107.55 ms / 128 tokens ( 0.84 ms per token, 1190.11 tokens per second) 1.36.127.841 I slot print_timing: id 0 | task 1811 | eval time = 9303.71 ms / 495 tokens ( 18.83 ms per token, 53.10 tokens per second) 1.36.127.842 I slot print_timing: id 0 | task 1811 | total time = 9411.27 ms / 623 tokens 1.36.127.842 I slot print_timing: id 0 | task 1811 | graphs reused = 1689 1.36.127.844 I slot print_timing: id 0 | task 1811 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.127.896 I slot release: id 0 | task 1811 | stop processing: n_tokens = 1747, truncated = 0 1.36.163.591 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.656 1.36.163.707 I slot launch_slot_: id 0 | task 2326 | processing task, is_child = 0 1.37.532.373 I slot print_timing: id 0 | task 2326 | prompt eval time = 110.66 ms / 119 tokens ( 0.93 ms per token, 1075.37 tokens per second) 1.37.532.380 I slot print_timing: id 0 | task 2326 | eval time = 1257.99 ms / 84 tokens ( 15.16 ms per token, 65.98 tokens per second) 1.37.532.381 I slot print_timing: id 0 | task 2326 | total time = 1368.65 ms / 203 tokens 1.37.532.382 I slot print_timing: id 0 | task 2326 | graphs reused = 1773 1.37.532.383 I slot print_timing: id 0 | task 2326 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.532.438 I slot release: id 0 | task 2326 | stop processing: n_tokens = 1327, truncated = 0 1.37.567.645 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.864 1.37.567.762 I slot launch_slot_: id 0 | task 2414 | processing task, is_child = 0 1.37.646.591 I slot print_timing: id 3 | task 2248 | prompt eval time = 111.15 ms / 109 tokens ( 1.02 ms per token, 980.68 tokens per second) 1.37.646.597 I slot print_timing: id 3 | task 2248 | eval time = 2841.33 ms / 162 tokens ( 17.65 ms per token, 56.66 tokens per second) 1.37.646.598 I slot print_timing: id 3 | task 2248 | total time = 2952.47 ms / 271 tokens 1.37.646.599 I slot print_timing: id 3 | task 2248 | graphs reused = 1775 1.37.646.600 I slot print_timing: id 3 | task 2248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.646.656 I slot release: id 3 | task 2248 | stop processing: n_tokens = 1395, truncated = 0 1.37.689.090 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.822 1.37.689.207 I slot launch_slot_: id 3 | task 2417 | processing task, is_child = 0 1.37.960.752 I slot print_timing: id 1 | task 2316 | prompt eval time = 142.21 ms / 113 tokens ( 1.26 ms per token, 794.61 tokens per second) 1.37.960.757 I slot print_timing: id 1 | task 2316 | eval time = 1914.47 ms / 109 tokens ( 17.73 ms per token, 56.41 tokens per second) 1.37.960.758 I slot print_timing: id 1 | task 2316 | total time = 2056.68 ms / 222 tokens 1.37.960.759 I slot print_timing: id 1 | task 2316 | graphs reused = 1784 1.37.960.759 I slot print_timing: id 1 | task 2316 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.960.809 I slot release: id 1 | task 2316 | stop processing: n_tokens = 1346, truncated = 0 1.37.991.519 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.851 1.37.991.635 I slot launch_slot_: id 1 | task 2431 | processing task, is_child = 0 1.38.331.140 I slot print_timing: id 2 | task 2291 | prompt eval time = 133.23 ms / 97 tokens ( 1.37 ms per token, 728.05 tokens per second) 1.38.331.146 I slot print_timing: id 2 | task 2291 | eval time = 2778.75 ms / 149 tokens ( 18.78 ms per token, 53.26 tokens per second) 1.38.331.147 I slot print_timing: id 2 | task 2291 | total time = 2911.99 ms / 246 tokens 1.38.331.147 I slot print_timing: id 2 | task 2291 | graphs reused = 1796 1.38.331.148 I slot print_timing: id 2 | task 2291 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.331.198 I slot release: id 2 | task 2291 | stop processing: n_tokens = 1370, truncated = 0 1.38.389.319 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.836 1.38.389.432 I slot launch_slot_: id 2 | task 2449 | processing task, is_child = 0 1.39.019.242 I slot print_timing: id 1 | task 2431 | prompt eval time = 142.70 ms / 109 tokens ( 1.31 ms per token, 763.82 tokens per second) 1.39.019.247 I slot print_timing: id 1 | task 2431 | eval time = 884.89 ms / 52 tokens ( 17.35 ms per token, 57.63 tokens per second) 1.39.019.248 I slot print_timing: id 1 | task 2431 | total time = 1027.59 ms / 161 tokens 1.39.019.249 I slot print_timing: id 1 | task 2431 | graphs reused = 1829 1.39.019.250 I slot print_timing: id 1 | task 2431 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.019.299 I slot release: id 1 | task 2431 | stop processing: n_tokens = 1285, truncated = 0 1.39.077.698 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.892 1.39.077.805 I slot launch_slot_: id 1 | task 2488 | processing task, is_child = 0 1.39.744.063 I slot print_timing: id 2 | task 2449 | prompt eval time = 133.31 ms / 95 tokens ( 1.40 ms per token, 712.62 tokens per second) 1.39.744.069 I slot print_timing: id 2 | task 2449 | eval time = 1221.31 ms / 75 tokens ( 16.50 ms per token, 60.59 tokens per second) 1.39.744.070 I slot print_timing: id 2 | task 2449 | total time = 1354.62 ms / 170 tokens 1.39.744.070 I slot print_timing: id 2 | task 2449 | graphs reused = 1864 1.39.744.071 I slot print_timing: id 2 | task 2449 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.744.125 I slot release: id 2 | task 2449 | stop processing: n_tokens = 1294, truncated = 0 1.39.774.104 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.886 1.39.774.215 I slot launch_slot_: id 2 | task 2528 | processing task, is_child = 0 1.40.479.726 I slot print_timing: id 0 | task 2414 | prompt eval time = 120.75 ms / 134 tokens ( 0.90 ms per token, 1109.74 tokens per second) 1.40.479.732 I slot print_timing: id 0 | task 2414 | eval time = 2791.20 ms / 147 tokens ( 19.12 ms per token, 52.31 tokens per second) 1.40.479.733 I slot print_timing: id 0 | task 2414 | total time = 2911.95 ms / 281 tokens 1.40.479.734 I slot print_timing: id 0 | task 2414 | graphs reused = 1900 1.40.479.735 I slot print_timing: id 0 | task 2414 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.479.788 I slot release: id 0 | task 2414 | stop processing: n_tokens = 1405, truncated = 0 1.40.514.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.816 1.40.514.286 I slot launch_slot_: id 0 | task 2570 | processing task, is_child = 0 1.40.812.579 I slot print_timing: id 3 | task 2417 | n_gen = 160, tg = 52.84 t/s, tg_3s = 53.18 t/s 1.40.842.625 I slot print_timing: id 1 | task 2488 | prompt eval time = 133.88 ms / 96 tokens ( 1.39 ms per token, 717.04 tokens per second) 1.40.842.631 I slot print_timing: id 1 | task 2488 | eval time = 1630.92 ms / 94 tokens ( 17.54 ms per token, 57.02 tokens per second) 1.40.842.632 I slot print_timing: id 1 | task 2488 | total time = 1764.81 ms / 190 tokens 1.40.842.633 I slot print_timing: id 1 | task 2488 | graphs reused = 1914 1.40.842.633 I slot print_timing: id 1 | task 2488 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.842.687 I slot release: id 1 | task 2488 | stop processing: n_tokens = 1314, truncated = 0 1.40.873.221 I slot print_timing: id 3 | task 2417 | prompt eval time = 114.43 ms / 112 tokens ( 1.02 ms per token, 978.77 tokens per second) 1.40.873.226 I slot print_timing: id 3 | task 2417 | eval time = 3069.57 ms / 163 tokens ( 18.95 ms per token, 52.78 tokens per second) 1.40.873.227 I slot print_timing: id 3 | task 2417 | total time = 3184.00 ms / 275 tokens 1.40.873.228 I slot print_timing: id 3 | task 2417 | graphs reused = 1914 1.40.873.229 I slot print_timing: id 3 | task 2417 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.873.278 I slot release: id 3 | task 2417 | stop processing: n_tokens = 1399, truncated = 0 1.40.873.292 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.872 1.40.873.411 I slot launch_slot_: id 1 | task 2587 | processing task, is_child = 0 1.40.873.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 1.40.875.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 1.40.876.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 1.40.926.895 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.819 1.40.927.036 I slot launch_slot_: id 3 | task 2588 | processing task, is_child = 0 1.42.437.032 I slot print_timing: id 0 | task 2570 | prompt eval time = 125.44 ms / 166 tokens ( 0.76 ms per token, 1323.37 tokens per second) 1.42.437.038 I slot print_timing: id 0 | task 2570 | eval time = 1797.29 ms / 103 tokens ( 17.62 ms per token, 56.75 tokens per second) 1.42.437.039 I slot print_timing: id 0 | task 2570 | total time = 1922.73 ms / 269 tokens 1.42.437.039 I slot print_timing: id 0 | task 2570 | graphs reused = 1999 1.42.437.040 I slot print_timing: id 0 | task 2570 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.437.095 I slot release: id 0 | task 2570 | stop processing: n_tokens = 1393, truncated = 0 1.42.471.311 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.823 1.42.471.423 I slot launch_slot_: id 0 | task 2679 | processing task, is_child = 0 1.42.537.258 I slot print_timing: id 3 | task 2588 | prompt eval time = 197.78 ms / 104 tokens ( 1.90 ms per token, 525.83 tokens per second) 1.42.537.263 I slot print_timing: id 3 | task 2588 | eval time = 1392.69 ms / 90 tokens ( 15.65 ms per token, 63.91 tokens per second) 1.42.537.264 I slot print_timing: id 3 | task 2588 | total time = 1590.47 ms / 194 tokens 1.42.537.265 I slot print_timing: id 3 | task 2588 | graphs reused = 2001 1.42.537.266 I slot print_timing: id 3 | task 2588 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.537.318 I slot release: id 3 | task 2588 | stop processing: n_tokens = 1318, truncated = 0 1.42.578.870 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.869 1.42.578.974 I slot launch_slot_: id 3 | task 2682 | processing task, is_child = 0 1.42.843.716 I slot print_timing: id 2 | task 2528 | prompt eval time = 141.20 ms / 122 tokens ( 1.16 ms per token, 864.03 tokens per second) 1.42.843.721 I slot print_timing: id 2 | task 2528 | eval time = 2928.28 ms / 160 tokens ( 18.42 ms per token, 54.30 tokens per second) 1.42.843.722 I slot print_timing: id 2 | task 2528 | total time = 3069.48 ms / 282 tokens 1.42.843.723 I slot print_timing: id 2 | task 2528 | graphs reused = 2010 1.42.843.724 I slot print_timing: id 2 | task 2528 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.843.779 I slot release: id 2 | task 2528 | stop processing: n_tokens = 1406, truncated = 0 1.42.873.635 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.815 1.42.873.745 I slot launch_slot_: id 2 | task 2696 | processing task, is_child = 0 1.43.581.081 I slot print_timing: id 1 | task 2587 | prompt eval time = 216.68 ms / 117 tokens ( 1.85 ms per token, 539.97 tokens per second) 1.43.581.087 I slot print_timing: id 1 | task 2587 | eval time = 2437.35 ms / 145 tokens ( 16.93 ms per token, 59.08 tokens per second) 1.43.581.088 I slot print_timing: id 1 | task 2587 | total time = 2654.03 ms / 262 tokens 1.43.581.089 I slot print_timing: id 1 | task 2587 | graphs reused = 2048 1.43.581.089 I slot print_timing: id 1 | task 2587 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.581.139 I slot release: id 1 | task 2587 | stop processing: n_tokens = 1386, truncated = 0 1.43.610.677 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.827 1.43.610.794 I slot launch_slot_: id 1 | task 2739 | processing task, is_child = 0 1.44.570.096 I slot print_timing: id 2 | task 2696 | prompt eval time = 137.05 ms / 112 tokens ( 1.22 ms per token, 817.24 tokens per second) 1.44.570.102 I slot print_timing: id 2 | task 2696 | eval time = 1559.29 ms / 97 tokens ( 16.24 ms per token, 61.57 tokens per second) 1.44.570.103 I slot print_timing: id 2 | task 2696 | total time = 1696.33 ms / 209 tokens 1.44.570.104 I slot print_timing: id 2 | task 2696 | graphs reused = 2101 1.44.570.104 I slot print_timing: id 2 | task 2696 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.570.161 I slot release: id 2 | task 2696 | stop processing: n_tokens = 1333, truncated = 0 1.44.600.474 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.860 1.44.600.589 I slot launch_slot_: id 2 | task 2797 | processing task, is_child = 0 1.45.183.561 I slot print_timing: id 0 | task 2679 | prompt eval time = 106.89 ms / 108 tokens ( 0.99 ms per token, 1010.41 tokens per second) 1.45.183.567 I slot print_timing: id 0 | task 2679 | eval time = 2605.24 ms / 144 tokens ( 18.22 ms per token, 54.89 tokens per second) 1.45.183.568 I slot print_timing: id 0 | task 2679 | total time = 2712.12 ms / 252 tokens 1.45.183.569 I slot print_timing: id 0 | task 2679 | graphs reused = 2129 1.45.183.570 I slot print_timing: id 0 | task 2679 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.183.621 I slot release: id 0 | task 2679 | stop processing: n_tokens = 1376, truncated = 0 1.45.232.821 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.833 1.45.232.935 I slot launch_slot_: id 0 | task 2832 | processing task, is_child = 0 1.45.411.184 I slot print_timing: id 1 | task 2739 | prompt eval time = 138.62 ms / 116 tokens ( 1.19 ms per token, 836.83 tokens per second) 1.45.411.189 I slot print_timing: id 1 | task 2739 | eval time = 1661.75 ms / 96 tokens ( 17.49 ms per token, 57.17 tokens per second) 1.45.411.190 I slot print_timing: id 1 | task 2739 | total time = 1800.37 ms / 212 tokens 1.45.411.191 I slot print_timing: id 1 | task 2739 | graphs reused = 2135 1.45.411.192 I slot print_timing: id 1 | task 2739 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.411.247 I slot release: id 1 | task 2739 | stop processing: n_tokens = 1336, truncated = 0 1.45.442.097 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.858 1.45.442.212 I slot launch_slot_: id 1 | task 2840 | processing task, is_child = 0 1.45.647.613 I slot print_timing: id 3 | task 2682 | prompt eval time = 115.32 ms / 133 tokens ( 0.87 ms per token, 1153.30 tokens per second) 1.45.647.619 I slot print_timing: id 3 | task 2682 | eval time = 2953.30 ms / 158 tokens ( 18.81 ms per token, 53.16 tokens per second) 1.45.647.620 I slot print_timing: id 3 | task 2682 | total time = 3068.62 ms / 291 tokens 1.45.647.621 I slot print_timing: id 3 | task 2682 | graphs reused = 2138 1.45.647.622 I slot print_timing: id 3 | task 2682 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.647.675 I slot release: id 3 | task 2682 | stop processing: n_tokens = 1415, truncated = 0 1.45.682.504 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.810 1.45.682.623 I slot launch_slot_: id 3 | task 2849 | processing task, is_child = 0 1.46.372.759 I slot print_timing: id 0 | task 2832 | prompt eval time = 110.11 ms / 119 tokens ( 0.93 ms per token, 1080.73 tokens per second) 1.46.372.764 I slot print_timing: id 0 | task 2832 | eval time = 1029.70 ms / 54 tokens ( 19.43 ms per token, 51.47 tokens per second) 1.46.372.765 I slot print_timing: id 0 | task 2832 | total time = 1139.81 ms / 173 tokens 1.46.372.766 I slot print_timing: id 0 | task 2832 | graphs reused = 2176 1.46.372.767 I slot print_timing: id 0 | task 2832 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.372.819 I slot release: id 0 | task 2832 | stop processing: n_tokens = 1297, truncated = 0 1.46.390.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.884 1.46.390.273 I slot launch_slot_: id 0 | task 2891 | processing task, is_child = 0 1.46.722.015 I slot print_timing: id 2 | task 2797 | prompt eval time = 142.30 ms / 119 tokens ( 1.20 ms per token, 836.24 tokens per second) 1.46.722.021 I slot print_timing: id 2 | task 2797 | eval time = 1979.11 ms / 106 tokens ( 18.85 ms per token, 53.05 tokens per second) 1.46.722.022 I slot print_timing: id 2 | task 2797 | total time = 2121.41 ms / 225 tokens 1.46.722.023 I slot print_timing: id 2 | task 2797 | graphs reused = 2191 1.46.722.024 I slot print_timing: id 2 | task 2797 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.722.074 I slot release: id 2 | task 2797 | stop processing: n_tokens = 1349, truncated = 0 1.46.751.534 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.850 1.46.751.649 I slot launch_slot_: id 2 | task 2910 | processing task, is_child = 0 1.46.829.975 I slot print_timing: id 3 | task 2849 | prompt eval time = 117.48 ms / 120 tokens ( 0.98 ms per token, 1021.45 tokens per second) 1.46.829.981 I slot print_timing: id 3 | task 2849 | eval time = 1029.86 ms / 59 tokens ( 17.76 ms per token, 56.32 tokens per second) 1.46.829.982 I slot print_timing: id 3 | task 2849 | total time = 1147.34 ms / 179 tokens 1.46.829.983 I slot print_timing: id 3 | task 2849 | graphs reused = 2191 1.46.829.984 I slot print_timing: id 3 | task 2849 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.830.035 I slot release: id 3 | task 2849 | stop processing: n_tokens = 1303, truncated = 0 1.46.872.505 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.880 1.46.872.613 I slot launch_slot_: id 3 | task 2913 | processing task, is_child = 0 1.47.305.146 I slot print_timing: id 1 | task 2840 | prompt eval time = 139.42 ms / 103 tokens ( 1.35 ms per token, 738.75 tokens per second) 1.47.305.152 I slot print_timing: id 1 | task 2840 | eval time = 1723.49 ms / 92 tokens ( 18.94 ms per token, 52.80 tokens per second) 1.47.305.153 I slot print_timing: id 1 | task 2840 | total time = 1862.91 ms / 195 tokens 1.47.305.154 I slot print_timing: id 1 | task 2840 | graphs reused = 2212 1.47.305.155 I slot print_timing: id 1 | task 2840 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.305.207 I slot release: id 1 | task 2840 | stop processing: n_tokens = 1319, truncated = 0 1.47.335.267 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.869 1.47.335.371 I slot launch_slot_: id 1 | task 2939 | processing task, is_child = 0 1.47.950.715 I slot print_timing: id 2 | task 2910 | prompt eval time = 120.84 ms / 97 tokens ( 1.25 ms per token, 802.73 tokens per second) 1.47.950.721 I slot print_timing: id 2 | task 2910 | eval time = 1078.21 ms / 59 tokens ( 18.59 ms per token, 53.79 tokens per second) 1.47.950.722 I slot print_timing: id 2 | task 2910 | total time = 1199.05 ms / 156 tokens 1.47.950.723 I slot print_timing: id 2 | task 2910 | graphs reused = 2242 1.47.950.723 I slot print_timing: id 2 | task 2910 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.950.777 I slot release: id 2 | task 2910 | stop processing: n_tokens = 1280, truncated = 0 1.47.981.041 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.895 1.47.981.146 I slot launch_slot_: id 2 | task 2974 | processing task, is_child = 0 1.48.249.823 I slot print_timing: id 3 | task 2913 | prompt eval time = 109.48 ms / 100 tokens ( 1.09 ms per token, 913.37 tokens per second) 1.48.249.829 I slot print_timing: id 3 | task 2913 | eval time = 1267.71 ms / 68 tokens ( 18.92 ms per token, 52.85 tokens per second) 1.48.249.830 I slot print_timing: id 3 | task 2913 | total time = 1377.19 ms / 168 tokens 1.48.249.831 I slot print_timing: id 3 | task 2913 | graphs reused = 2249 1.48.249.831 I slot print_timing: id 3 | task 2913 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.249.883 I slot release: id 3 | task 2913 | stop processing: n_tokens = 1292, truncated = 0 1.48.284.493 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.887 1.48.284.602 I slot launch_slot_: id 3 | task 2987 | processing task, is_child = 0 1.48.417.510 I slot print_timing: id 0 | task 2891 | prompt eval time = 107.70 ms / 108 tokens ( 1.00 ms per token, 1002.80 tokens per second) 1.48.417.516 I slot print_timing: id 0 | task 2891 | eval time = 1919.52 ms / 93 tokens ( 20.86 ms per token, 47.93 tokens per second) 1.48.417.517 I slot print_timing: id 0 | task 2891 | total time = 2027.22 ms / 201 tokens 1.48.417.518 I slot print_timing: id 0 | task 2891 | graphs reused = 2250 1.48.417.519 I slot print_timing: id 0 | task 2891 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.417.570 I slot release: id 0 | task 2891 | stop processing: n_tokens = 1325, truncated = 0 1.48.453.110 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.865 1.48.453.214 I slot launch_slot_: id 0 | task 2993 | processing task, is_child = 0 1.49.506.409 I slot print_timing: id 0 | task 2993 | prompt eval time = 108.36 ms / 104 tokens ( 1.04 ms per token, 959.72 tokens per second) 1.49.506.415 I slot print_timing: id 0 | task 2993 | eval time = 944.81 ms / 63 tokens ( 15.24 ms per token, 65.62 tokens per second) 1.49.506.416 I slot print_timing: id 0 | task 2993 | total time = 1053.18 ms / 167 tokens 1.49.506.416 I slot print_timing: id 0 | task 2993 | graphs reused = 2313 1.49.506.417 I slot print_timing: id 0 | task 2993 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.506.472 I slot release: id 0 | task 2993 | stop processing: n_tokens = 1291, truncated = 0 1.49.541.295 I slot print_timing: id 1 | task 2939 | prompt eval time = 154.08 ms / 172 tokens ( 0.90 ms per token, 1116.31 tokens per second) 1.49.541.300 I slot print_timing: id 1 | task 2939 | eval time = 2051.83 ms / 116 tokens ( 17.84 ms per token, 56.05 tokens per second) 1.49.541.301 I slot print_timing: id 1 | task 2939 | total time = 2205.91 ms / 288 tokens 1.49.541.302 I slot print_timing: id 1 | task 2939 | graphs reused = 2314 1.49.541.303 I slot print_timing: id 1 | task 2939 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.541.352 I slot release: id 1 | task 2939 | stop processing: n_tokens = 1412, truncated = 0 1.49.541.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.888 1.49.542.104 I slot launch_slot_: id 0 | task 3060 | processing task, is_child = 0 1.49.542.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 1.49.543.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.505 MiB) 1.49.589.027 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.812 1.49.589.163 I slot launch_slot_: id 1 | task 3061 | processing task, is_child = 0 1.49.986.463 I slot print_timing: id 3 | task 2987 | prompt eval time = 115.20 ms / 114 tokens ( 1.01 ms per token, 989.55 tokens per second) 1.49.986.469 I slot print_timing: id 3 | task 2987 | eval time = 1586.64 ms / 86 tokens ( 18.67 ms per token, 53.57 tokens per second) 1.49.986.470 I slot print_timing: id 3 | task 2987 | total time = 1701.85 ms / 200 tokens 1.49.986.472 I slot print_timing: id 3 | task 2987 | graphs reused = 2327 1.49.986.472 I slot print_timing: id 3 | task 2987 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.986.525 I slot release: id 3 | task 2987 | stop processing: n_tokens = 1324, truncated = 0 1.50.021.373 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.866 1.50.021.550 I slot launch_slot_: id 3 | task 3080 | processing task, is_child = 0 1.50.950.857 I slot print_timing: id 2 | task 2974 | prompt eval time = 142.81 ms / 119 tokens ( 1.20 ms per token, 833.29 tokens per second) 1.50.950.862 I slot print_timing: id 2 | task 2974 | eval time = 2826.89 ms / 157 tokens ( 18.12 ms per token, 55.18 tokens per second) 1.50.950.864 I slot print_timing: id 2 | task 2974 | total time = 2969.69 ms / 276 tokens 1.50.950.864 I slot print_timing: id 2 | task 2974 | graphs reused = 2382 1.50.950.865 I slot print_timing: id 2 | task 2974 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.950.915 I slot release: id 2 | task 2974 | stop processing: n_tokens = 1400, truncated = 0 1.50.980.382 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.819 1.50.980.493 I slot launch_slot_: id 2 | task 3139 | processing task, is_child = 0 1.51.164.157 I slot print_timing: id 1 | task 3061 | prompt eval time = 160.36 ms / 88 tokens ( 1.82 ms per token, 548.77 tokens per second) 1.51.164.162 I slot print_timing: id 1 | task 3061 | eval time = 1394.33 ms / 80 tokens ( 17.65 ms per token, 56.66 tokens per second) 1.51.164.163 I slot print_timing: id 1 | task 3061 | total time = 1554.69 ms / 168 tokens 1.51.164.164 I slot print_timing: id 1 | task 3061 | graphs reused = 2384 1.51.164.165 I slot print_timing: id 1 | task 3061 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.164.215 I slot release: id 1 | task 3061 | stop processing: n_tokens = 1292, truncated = 0 1.51.222.479 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.887 1.51.222.591 I slot launch_slot_: id 1 | task 3147 | processing task, is_child = 0 1.51.549.676 I slot print_timing: id 0 | task 3060 | prompt eval time = 180.06 ms / 117 tokens ( 1.54 ms per token, 649.78 tokens per second) 1.51.549.682 I slot print_timing: id 0 | task 3060 | eval time = 1780.43 ms / 96 tokens ( 18.74 ms per token, 53.36 tokens per second) 1.51.549.683 I slot print_timing: id 0 | task 3060 | total time = 1960.49 ms / 213 tokens 1.51.549.684 I slot print_timing: id 0 | task 3060 | graphs reused = 2395 1.51.549.685 I slot print_timing: id 0 | task 3060 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.549.739 I slot release: id 0 | task 3060 | stop processing: n_tokens = 1337, truncated = 0 1.51.567.585 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.857 1.51.567.700 I slot launch_slot_: id 0 | task 3163 | processing task, is_child = 0 1.52.177.532 I slot print_timing: id 3 | task 3080 | prompt eval time = 118.26 ms / 129 tokens ( 0.92 ms per token, 1090.83 tokens per second) 1.52.177.537 I slot print_timing: id 3 | task 3080 | eval time = 2037.70 ms / 114 tokens ( 18.03 ms per token, 55.45 tokens per second) 1.52.177.538 I slot print_timing: id 3 | task 3080 | total time = 2155.96 ms / 243 tokens 1.52.177.539 I slot print_timing: id 3 | task 3080 | graphs reused = 2428 1.52.177.540 I slot print_timing: id 3 | task 3080 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.177.594 I slot release: id 3 | task 3080 | stop processing: n_tokens = 1367, truncated = 0 1.52.211.228 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.838 1.52.211.342 I slot launch_slot_: id 3 | task 3201 | processing task, is_child = 0 1.52.437.388 I slot print_timing: id 2 | task 3139 | prompt eval time = 135.22 ms / 87 tokens ( 1.55 ms per token, 643.39 tokens per second) 1.52.437.393 I slot print_timing: id 2 | task 3139 | eval time = 1321.66 ms / 67 tokens ( 20.03 ms per token, 49.94 tokens per second) 1.52.437.394 I slot print_timing: id 2 | task 3139 | total time = 1456.88 ms / 154 tokens 1.52.437.395 I slot print_timing: id 2 | task 3139 | graphs reused = 2435 1.52.437.396 I slot print_timing: id 2 | task 3139 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.437.448 I slot release: id 2 | task 3139 | stop processing: n_tokens = 1278, truncated = 0 1.52.497.204 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.897 1.52.497.321 I slot launch_slot_: id 2 | task 3213 | processing task, is_child = 0 1.53.121.085 I slot print_timing: id 0 | task 3163 | prompt eval time = 110.94 ms / 118 tokens ( 0.94 ms per token, 1063.61 tokens per second) 1.53.121.091 I slot print_timing: id 0 | task 3163 | eval time = 1442.42 ms / 80 tokens ( 18.26 ms per token, 54.77 tokens per second) 1.53.121.092 I slot print_timing: id 0 | task 3163 | total time = 1553.37 ms / 198 tokens 1.53.121.094 I slot print_timing: id 0 | task 3163 | graphs reused = 2465 1.53.121.095 I slot print_timing: id 0 | task 3163 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.121.148 I slot release: id 0 | task 3163 | stop processing: n_tokens = 1322, truncated = 0 1.53.156.657 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.867 1.53.156.768 I slot launch_slot_: id 0 | task 3249 | processing task, is_child = 0 1.53.679.382 I slot print_timing: id 1 | task 3147 | prompt eval time = 147.98 ms / 152 tokens ( 0.97 ms per token, 1027.16 tokens per second) 1.53.679.388 I slot print_timing: id 1 | task 3147 | eval time = 2308.80 ms / 126 tokens ( 18.47 ms per token, 54.14 tokens per second) 1.53.679.390 I slot print_timing: id 1 | task 3147 | total time = 2456.78 ms / 278 tokens 1.53.679.391 I slot print_timing: id 1 | task 3147 | graphs reused = 2493 1.53.679.391 I slot print_timing: id 1 | task 3147 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.679.444 I slot release: id 1 | task 3147 | stop processing: n_tokens = 1402, truncated = 0 1.53.709.618 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.817 1.53.709.730 I slot launch_slot_: id 1 | task 3280 | processing task, is_child = 0 1.54.010.626 I slot print_timing: id 2 | task 3213 | prompt eval time = 151.24 ms / 135 tokens ( 1.12 ms per token, 892.62 tokens per second) 1.54.010.631 I slot print_timing: id 2 | task 3213 | eval time = 1362.05 ms / 76 tokens ( 18.16 ms per token, 55.06 tokens per second) 1.54.010.632 I slot print_timing: id 2 | task 3213 | total time = 1513.29 ms / 211 tokens 1.54.010.633 I slot print_timing: id 2 | task 3213 | graphs reused = 2502 1.54.010.634 I slot print_timing: id 2 | task 3213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.010.687 I slot release: id 2 | task 3213 | stop processing: n_tokens = 1335, truncated = 0 1.54.070.674 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.858 1.54.070.790 I slot launch_slot_: id 2 | task 3295 | processing task, is_child = 0 1.54.690.551 I slot print_timing: id 0 | task 3249 | prompt eval time = 106.12 ms / 92 tokens ( 1.15 ms per token, 866.94 tokens per second) 1.54.690.557 I slot print_timing: id 0 | task 3249 | eval time = 1427.65 ms / 77 tokens ( 18.78 ms per token, 53.23 tokens per second) 1.54.690.558 I slot print_timing: id 0 | task 3249 | total time = 1533.77 ms / 169 tokens 1.54.690.559 I slot print_timing: id 0 | task 3249 | graphs reused = 2533 1.54.690.560 I slot print_timing: id 0 | task 3249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.690.611 I slot release: id 0 | task 3249 | stop processing: n_tokens = 1293, truncated = 0 1.54.707.935 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.886 1.54.708.037 I slot launch_slot_: id 0 | task 3331 | processing task, is_child = 0 1.54.865.033 I slot print_timing: id 3 | task 3201 | prompt eval time = 115.00 ms / 110 tokens ( 1.05 ms per token, 956.55 tokens per second) 1.54.865.038 I slot print_timing: id 3 | task 3201 | eval time = 2538.68 ms / 129 tokens ( 19.83 ms per token, 50.42 tokens per second) 1.54.865.039 I slot print_timing: id 3 | task 3201 | total time = 2653.68 ms / 239 tokens 1.54.865.040 I slot print_timing: id 3 | task 3201 | graphs reused = 2536 1.54.865.041 I slot print_timing: id 3 | task 3201 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.865.095 I slot release: id 3 | task 3201 | stop processing: n_tokens = 1363, truncated = 0 1.54.911.517 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.841 1.54.911.621 I slot launch_slot_: id 3 | task 3340 | processing task, is_child = 0 1.55.534.193 I slot print_timing: id 1 | task 3280 | prompt eval time = 142.23 ms / 120 tokens ( 1.19 ms per token, 843.72 tokens per second) 1.55.534.199 I slot print_timing: id 1 | task 3280 | eval time = 1682.22 ms / 93 tokens ( 18.28 ms per token, 54.69 tokens per second) 1.55.534.200 I slot print_timing: id 1 | task 3280 | total time = 1824.45 ms / 213 tokens 1.55.534.200 I slot print_timing: id 1 | task 3280 | graphs reused = 2572 1.55.534.201 I slot print_timing: id 1 | task 3280 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.534.251 I slot release: id 1 | task 3280 | stop processing: n_tokens = 1337, truncated = 0 1.55.592.836 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.857 1.55.592.953 I slot launch_slot_: id 1 | task 3380 | processing task, is_child = 0 1.55.748.226 I slot print_timing: id 2 | task 3295 | prompt eval time = 142.96 ms / 131 tokens ( 1.09 ms per token, 916.33 tokens per second) 1.55.748.232 I slot print_timing: id 2 | task 3295 | eval time = 1534.46 ms / 84 tokens ( 18.49 ms per token, 54.09 tokens per second) 1.55.748.233 I slot print_timing: id 2 | task 3295 | total time = 1677.42 ms / 215 tokens 1.55.748.234 I slot print_timing: id 2 | task 3295 | graphs reused = 2572 1.55.748.235 I slot print_timing: id 2 | task 3295 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.748.289 I slot release: id 2 | task 3295 | stop processing: n_tokens = 1339, truncated = 0 1.55.777.677 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.856 1.55.777.787 I slot launch_slot_: id 2 | task 3385 | processing task, is_child = 0 1.56.924.585 I slot print_timing: id 3 | task 3340 | prompt eval time = 111.09 ms / 98 tokens ( 1.13 ms per token, 882.16 tokens per second) 1.56.924.592 I slot print_timing: id 3 | task 3340 | eval time = 1901.86 ms / 110 tokens ( 17.45 ms per token, 57.31 tokens per second) 1.56.924.593 I slot print_timing: id 3 | task 3340 | total time = 2012.95 ms / 208 tokens 1.56.924.594 I slot print_timing: id 3 | task 3340 | graphs reused = 2636 1.56.924.595 I slot print_timing: id 3 | task 3340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.924.647 I slot release: id 3 | task 3340 | stop processing: n_tokens = 1332, truncated = 0 1.56.959.043 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.860 1.56.959.150 I slot launch_slot_: id 3 | task 3456 | processing task, is_child = 0 1.57.367.346 I slot print_timing: id 2 | task 3385 | prompt eval time = 139.66 ms / 130 tokens ( 1.07 ms per token, 930.81 tokens per second) 1.57.367.352 I slot print_timing: id 2 | task 3385 | eval time = 1449.88 ms / 90 tokens ( 16.29 ms per token, 61.38 tokens per second) 1.57.367.353 I slot print_timing: id 2 | task 3385 | total time = 1589.54 ms / 220 tokens 1.57.367.354 I slot print_timing: id 2 | task 3385 | graphs reused = 2655 1.57.367.355 I slot print_timing: id 2 | task 3385 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.367.409 I slot release: id 2 | task 3385 | stop processing: n_tokens = 1344, truncated = 0 1.57.397.939 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.853 1.57.398.072 I slot launch_slot_: id 2 | task 3479 | processing task, is_child = 0 1.57.772.876 I slot print_timing: id 0 | task 3331 | prompt eval time = 106.42 ms / 95 tokens ( 1.12 ms per token, 892.73 tokens per second) 1.57.772.881 I slot print_timing: id 0 | task 3331 | eval time = 2958.41 ms / 159 tokens ( 18.72 ms per token, 53.41 tokens per second) 1.57.772.882 I slot print_timing: id 0 | task 3331 | total time = 3064.82 ms / 254 tokens 1.57.772.883 I slot print_timing: id 0 | task 3331 | graphs reused = 2669 1.57.772.884 I slot print_timing: id 0 | task 3331 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.772.934 I slot release: id 0 | task 3331 | stop processing: n_tokens = 1378, truncated = 0 1.57.807.300 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.832 1.57.807.413 I slot launch_slot_: id 0 | task 3499 | processing task, is_child = 0 1.58.101.700 I slot print_timing: id 1 | task 3380 | prompt eval time = 137.08 ms / 116 tokens ( 1.18 ms per token, 846.22 tokens per second) 1.58.101.706 I slot print_timing: id 1 | task 3380 | eval time = 2371.65 ms / 127 tokens ( 18.82 ms per token, 53.13 tokens per second) 1.58.101.707 I slot print_timing: id 1 | task 3380 | total time = 2508.73 ms / 243 tokens 1.58.101.707 I slot print_timing: id 1 | task 3380 | graphs reused = 2681 1.58.101.708 I slot print_timing: id 1 | task 3380 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.101.761 I slot release: id 1 | task 3380 | stop processing: n_tokens = 1367, truncated = 0 1.58.132.354 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.838 1.58.132.464 I slot launch_slot_: id 1 | task 3514 | processing task, is_child = 0 1.58.738.307 I slot print_timing: id 3 | task 3456 | prompt eval time = 114.97 ms / 103 tokens ( 1.12 ms per token, 895.86 tokens per second) 1.58.738.313 I slot print_timing: id 3 | task 3456 | eval time = 1664.17 ms / 87 tokens ( 19.35 ms per token, 51.68 tokens per second) 1.58.738.314 I slot print_timing: id 3 | task 3456 | total time = 1779.14 ms / 190 tokens 1.58.738.315 I slot print_timing: id 3 | task 3456 | graphs reused = 2711 1.58.738.316 I slot print_timing: id 3 | task 3456 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.738.367 I slot release: id 3 | task 3456 | stop processing: n_tokens = 1314, truncated = 0 1.58.771.679 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.872 1.58.771.788 I slot launch_slot_: id 3 | task 3550 | processing task, is_child = 0 1.59.545.256 I slot print_timing: id 1 | task 3514 | prompt eval time = 141.88 ms / 123 tokens ( 1.15 ms per token, 866.95 tokens per second) 1.59.545.261 I slot print_timing: id 1 | task 3514 | eval time = 1270.90 ms / 81 tokens ( 15.89 ms per token, 62.95 tokens per second) 1.59.545.262 I slot print_timing: id 1 | task 3514 | total time = 1412.78 ms / 204 tokens 1.59.545.263 I slot print_timing: id 1 | task 3514 | graphs reused = 2756 1.59.545.263 I slot print_timing: id 1 | task 3514 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.545.314 I slot release: id 1 | task 3514 | stop processing: n_tokens = 1328, truncated = 0 1.59.603.523 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.863 1.59.603.633 I slot launch_slot_: id 1 | task 3600 | processing task, is_child = 0 2.00.546.017 I slot print_timing: id 2 | task 3479 | n_gen = 172, tg = 56.90 t/s, tg_3s = 57.24 t/s 2.00.789.528 I slot print_timing: id 2 | task 3479 | prompt eval time = 142.84 ms / 122 tokens ( 1.17 ms per token, 854.08 tokens per second) 2.00.789.534 I slot print_timing: id 2 | task 3479 | eval time = 3248.59 ms / 188 tokens ( 17.37 ms per token, 57.56 tokens per second) 2.00.789.535 I slot print_timing: id 2 | task 3479 | total time = 3391.44 ms / 310 tokens 2.00.789.536 I slot print_timing: id 2 | task 3479 | graphs reused = 2825 2.00.789.536 I slot print_timing: id 2 | task 3479 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.789.589 I slot release: id 2 | task 3479 | stop processing: n_tokens = 1434, truncated = 0 2.00.820.527 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.799 2.00.820.648 I slot launch_slot_: id 2 | task 3674 | processing task, is_child = 0 2.00.956.983 I slot print_timing: id 0 | task 3499 | n_gen = 172, tg = 56.46 t/s, tg_3s = 56.79 t/s 2.01.234.420 I slot print_timing: id 0 | task 3499 | prompt eval time = 120.93 ms / 133 tokens ( 0.91 ms per token, 1099.79 tokens per second) 2.01.234.426 I slot print_timing: id 0 | task 3499 | eval time = 3306.06 ms / 190 tokens ( 17.49 ms per token, 57.17 tokens per second) 2.01.234.427 I slot print_timing: id 0 | task 3499 | total time = 3426.99 ms / 323 tokens 2.01.234.428 I slot print_timing: id 0 | task 3499 | graphs reused = 2842 2.01.234.429 I slot print_timing: id 0 | task 3499 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.234.480 I slot release: id 0 | task 3499 | stop processing: n_tokens = 1447, truncated = 0 2.01.252.425 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.792 2.01.252.535 I slot launch_slot_: id 0 | task 3696 | processing task, is_child = 0 2.01.685.759 I slot print_timing: id 1 | task 3600 | prompt eval time = 134.07 ms / 101 tokens ( 1.33 ms per token, 753.35 tokens per second) 2.01.685.764 I slot print_timing: id 1 | task 3600 | eval time = 1948.04 ms / 115 tokens ( 17.09 ms per token, 58.52 tokens per second) 2.01.685.765 I slot print_timing: id 1 | task 3600 | total time = 2082.11 ms / 216 tokens 2.01.685.766 I slot print_timing: id 1 | task 3600 | graphs reused = 2862 2.01.685.767 I slot print_timing: id 1 | task 3600 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.685.819 I slot release: id 1 | task 3600 | stop processing: n_tokens = 1340, truncated = 0 2.01.716.497 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.855 2.01.716.610 I slot launch_slot_: id 1 | task 3720 | processing task, is_child = 0 2.01.889.230 I slot print_timing: id 3 | task 3550 | n_gen = 169, tg = 55.96 t/s, tg_3s = 56.29 t/s 2.02.299.159 I slot print_timing: id 3 | task 3550 | prompt eval time = 115.19 ms / 118 tokens ( 0.98 ms per token, 1024.38 tokens per second) 2.02.299.165 I slot print_timing: id 3 | task 3550 | eval time = 3412.16 ms / 196 tokens ( 17.50 ms per token, 57.15 tokens per second) 2.02.299.166 I slot print_timing: id 3 | task 3550 | total time = 3527.36 ms / 314 tokens 2.02.299.167 I slot print_timing: id 3 | task 3550 | graphs reused = 2890 2.02.299.168 I slot print_timing: id 3 | task 3550 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.299.219 I slot release: id 3 | task 3550 | stop processing: n_tokens = 1438, truncated = 0 2.02.316.431 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.797 2.02.316.540 I slot launch_slot_: id 3 | task 3753 | processing task, is_child = 0 2.02.642.437 I slot print_timing: id 2 | task 3674 | prompt eval time = 137.23 ms / 95 tokens ( 1.44 ms per token, 692.27 tokens per second) 2.02.642.443 I slot print_timing: id 2 | task 3674 | eval time = 1684.54 ms / 91 tokens ( 18.72 ms per token, 53.43 tokens per second) 2.02.642.444 I slot print_timing: id 2 | task 3674 | total time = 1821.77 ms / 186 tokens 2.02.642.445 I slot print_timing: id 2 | task 3674 | graphs reused = 2903 2.02.642.446 I slot print_timing: id 2 | task 3674 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.642.497 I slot release: id 2 | task 3674 | stop processing: n_tokens = 1310, truncated = 0 2.02.671.882 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.875 2.02.671.990 I slot launch_slot_: id 2 | task 3771 | processing task, is_child = 0 2.02.985.493 I slot print_timing: id 1 | task 3720 | prompt eval time = 136.22 ms / 89 tokens ( 1.53 ms per token, 653.34 tokens per second) 2.02.985.499 I slot print_timing: id 1 | task 3720 | eval time = 1132.64 ms / 62 tokens ( 18.57 ms per token, 53.86 tokens per second) 2.02.985.500 I slot print_timing: id 1 | task 3720 | total time = 1268.86 ms / 151 tokens 2.02.985.500 I slot print_timing: id 1 | task 3720 | graphs reused = 2914 2.02.985.501 I slot print_timing: id 1 | task 3720 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.985.553 I slot release: id 1 | task 3720 | stop processing: n_tokens = 1275, truncated = 0 2.03.044.369 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.899 2.03.044.485 I slot launch_slot_: id 1 | task 3788 | processing task, is_child = 0 2.03.735.955 I slot print_timing: id 2 | task 3771 | prompt eval time = 134.26 ms / 92 tokens ( 1.46 ms per token, 685.23 tokens per second) 2.03.735.961 I slot print_timing: id 2 | task 3771 | eval time = 929.69 ms / 55 tokens ( 17.22 ms per token, 58.08 tokens per second) 2.03.735.962 I slot print_timing: id 2 | task 3771 | total time = 1063.95 ms / 147 tokens 2.03.735.962 I slot print_timing: id 2 | task 3771 | graphs reused = 2951 2.03.735.963 I slot print_timing: id 2 | task 3771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.736.014 I slot release: id 2 | task 3771 | stop processing: n_tokens = 1271, truncated = 0 2.03.794.380 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.902 2.03.794.510 I slot launch_slot_: id 2 | task 3831 | processing task, is_child = 0 2.04.132.314 I slot print_timing: id 3 | task 3753 | prompt eval time = 112.12 ms / 99 tokens ( 1.13 ms per token, 883.01 tokens per second) 2.04.132.319 I slot print_timing: id 3 | task 3753 | eval time = 1703.64 ms / 89 tokens ( 19.36 ms per token, 51.65 tokens per second) 2.04.132.320 I slot print_timing: id 3 | task 3753 | total time = 1815.76 ms / 188 tokens 2.04.132.321 I slot print_timing: id 3 | task 3753 | graphs reused = 2963 2.04.132.322 I slot print_timing: id 3 | task 3753 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.132.374 I slot release: id 3 | task 3753 | stop processing: n_tokens = 1312, truncated = 0 2.04.166.855 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.873 2.04.166.963 I slot launch_slot_: id 3 | task 3849 | processing task, is_child = 0 2.04.390.329 I slot print_timing: id 0 | task 3696 | n_gen = 155, tg = 51.10 t/s, tg_3s = 51.43 t/s 2.04.674.484 I slot print_timing: id 1 | task 3788 | prompt eval time = 136.45 ms / 113 tokens ( 1.21 ms per token, 828.13 tokens per second) 2.04.674.490 I slot print_timing: id 1 | task 3788 | eval time = 1493.53 ms / 86 tokens ( 17.57 ms per token, 56.91 tokens per second) 2.04.674.492 I slot print_timing: id 1 | task 3788 | total time = 1629.98 ms / 199 tokens 2.04.674.492 I slot print_timing: id 1 | task 3788 | graphs reused = 2989 2.04.674.494 I slot print_timing: id 1 | task 3788 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.674.544 I slot release: id 1 | task 3788 | stop processing: n_tokens = 1323, truncated = 0 2.04.705.012 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.866 2.04.705.120 I slot launch_slot_: id 1 | task 3879 | processing task, is_child = 0 2.05.442.527 I slot print_timing: id 3 | task 3849 | prompt eval time = 112.62 ms / 90 tokens ( 1.25 ms per token, 799.13 tokens per second) 2.05.442.533 I slot print_timing: id 3 | task 3849 | eval time = 1162.92 ms / 68 tokens ( 17.36 ms per token, 57.61 tokens per second) 2.05.442.534 I slot print_timing: id 3 | task 3849 | total time = 1275.55 ms / 158 tokens 2.05.442.535 I slot print_timing: id 3 | task 3849 | graphs reused = 3026 2.05.442.536 I slot print_timing: id 3 | task 3849 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.442.585 I slot release: id 3 | task 3849 | stop processing: n_tokens = 1282, truncated = 0 2.05.477.542 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.894 2.05.477.658 I slot launch_slot_: id 3 | task 3922 | processing task, is_child = 0 2.05.547.588 I slot print_timing: id 0 | task 3696 | prompt eval time = 124.14 ms / 152 tokens ( 0.82 ms per token, 1224.41 tokens per second) 2.05.547.593 I slot print_timing: id 0 | task 3696 | eval time = 4170.89 ms / 218 tokens ( 19.22 ms per token, 52.03 tokens per second) 2.05.547.594 I slot print_timing: id 0 | task 3696 | total time = 4295.03 ms / 370 tokens 2.05.547.595 I slot print_timing: id 0 | task 3696 | graphs reused = 3027 2.05.547.596 I slot print_timing: id 0 | task 3696 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.547.655 I slot release: id 0 | task 3696 | stop processing: n_tokens = 1494, truncated = 0 2.05.596.459 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.767 2.05.596.571 I slot launch_slot_: id 0 | task 3925 | processing task, is_child = 0 2.06.546.359 I slot print_timing: id 2 | task 3831 | prompt eval time = 140.13 ms / 118 tokens ( 1.19 ms per token, 842.09 tokens per second) 2.06.546.365 I slot print_timing: id 2 | task 3831 | eval time = 2611.70 ms / 145 tokens ( 18.14 ms per token, 55.14 tokens per second) 2.06.546.366 I slot print_timing: id 2 | task 3831 | total time = 2751.83 ms / 263 tokens 2.06.546.366 I slot print_timing: id 2 | task 3831 | graphs reused = 3080 2.06.546.367 I slot print_timing: id 2 | task 3831 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.546.421 I slot release: id 2 | task 3831 | stop processing: n_tokens = 1387, truncated = 0 2.06.606.011 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.826 2.06.606.126 I slot launch_slot_: id 2 | task 3984 | processing task, is_child = 0 2.07.098.842 I slot print_timing: id 1 | task 3879 | prompt eval time = 158.00 ms / 170 tokens ( 0.93 ms per token, 1075.93 tokens per second) 2.07.098.848 I slot print_timing: id 1 | task 3879 | eval time = 2235.70 ms / 127 tokens ( 17.74 ms per token, 56.36 tokens per second) 2.07.098.849 I slot print_timing: id 1 | task 3879 | total time = 2393.71 ms / 297 tokens 2.07.098.850 I slot print_timing: id 1 | task 3879 | graphs reused = 3103 2.07.098.850 I slot print_timing: id 1 | task 3879 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.098.902 I slot release: id 1 | task 3879 | stop processing: n_tokens = 1421, truncated = 0 2.07.128.500 I slot print_timing: id 3 | task 3922 | prompt eval time = 118.78 ms / 107 tokens ( 1.11 ms per token, 900.84 tokens per second) 2.07.128.505 I slot print_timing: id 3 | task 3922 | eval time = 1532.05 ms / 86 tokens ( 18.02 ms per token, 55.48 tokens per second) 2.07.128.506 I slot print_timing: id 3 | task 3922 | total time = 1650.83 ms / 193 tokens 2.07.128.507 I slot print_timing: id 3 | task 3922 | graphs reused = 3103 2.07.128.508 I slot print_timing: id 3 | task 3922 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.128.556 I slot release: id 3 | task 3922 | stop processing: n_tokens = 1317, truncated = 0 2.07.156.279 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.806 2.07.156.384 I slot launch_slot_: id 1 | task 4013 | processing task, is_child = 0 2.07.156.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.07.158.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.005 MiB) 2.07.159.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 2.07.204.086 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.870 2.07.204.209 I slot launch_slot_: id 3 | task 4014 | processing task, is_child = 0 2.07.741.085 I slot print_timing: id 2 | task 3984 | prompt eval time = 138.78 ms / 109 tokens ( 1.27 ms per token, 785.43 tokens per second) 2.07.741.090 I slot print_timing: id 2 | task 3984 | eval time = 996.16 ms / 50 tokens ( 20.33 ms per token, 49.19 tokens per second) 2.07.741.091 I slot print_timing: id 2 | task 3984 | total time = 1134.94 ms / 159 tokens 2.07.741.092 I slot print_timing: id 2 | task 3984 | graphs reused = 3123 2.07.741.094 I slot print_timing: id 2 | task 3984 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.741.147 I slot release: id 2 | task 3984 | stop processing: n_tokens = 1283, truncated = 0 2.07.770.569 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.893 2.07.770.684 I slot launch_slot_: id 2 | task 4039 | processing task, is_child = 0 2.08.431.737 I slot print_timing: id 0 | task 3925 | prompt eval time = 125.76 ms / 147 tokens ( 0.86 ms per token, 1168.90 tokens per second) 2.08.431.743 I slot print_timing: id 0 | task 3925 | eval time = 2709.39 ms / 145 tokens ( 18.82 ms per token, 53.15 tokens per second) 2.08.431.744 I slot print_timing: id 0 | task 3925 | total time = 2835.15 ms / 292 tokens 2.08.431.745 I slot print_timing: id 0 | task 3925 | graphs reused = 3156 2.08.431.746 I slot print_timing: id 0 | task 3925 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.431.799 I slot release: id 0 | task 3925 | stop processing: n_tokens = 1416, truncated = 0 2.08.467.072 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.809 2.08.467.187 I slot launch_slot_: id 0 | task 4078 | processing task, is_child = 0 2.09.069.779 I slot print_timing: id 3 | task 4014 | prompt eval time = 204.28 ms / 110 tokens ( 1.86 ms per token, 538.47 tokens per second) 2.09.069.784 I slot print_timing: id 3 | task 4014 | eval time = 1641.49 ms / 95 tokens ( 17.46 ms per token, 57.27 tokens per second) 2.09.069.785 I slot print_timing: id 3 | task 4014 | total time = 1845.77 ms / 205 tokens 2.09.069.786 I slot print_timing: id 3 | task 4014 | graphs reused = 3189 2.09.069.786 I slot print_timing: id 3 | task 4014 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.069.838 I slot release: id 3 | task 4014 | stop processing: n_tokens = 1329, truncated = 0 2.09.103.896 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 2.09.103.999 I slot launch_slot_: id 3 | task 4115 | processing task, is_child = 0 2.10.261.201 I slot print_timing: id 2 | task 4039 | prompt eval time = 149.49 ms / 134 tokens ( 1.12 ms per token, 896.36 tokens per second) 2.10.261.207 I slot print_timing: id 2 | task 4039 | eval time = 2341.01 ms / 144 tokens ( 16.37 ms per token, 61.08 tokens per second) 2.10.261.208 I slot print_timing: id 2 | task 4039 | total time = 2490.50 ms / 278 tokens 2.10.261.209 I slot print_timing: id 2 | task 4039 | graphs reused = 3258 2.10.261.209 I slot print_timing: id 2 | task 4039 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.261.266 I slot release: id 2 | task 4039 | stop processing: n_tokens = 1402, truncated = 0 2.10.291.432 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.817 2.10.291.542 I slot launch_slot_: id 2 | task 4188 | processing task, is_child = 0 2.10.431.375 I slot print_timing: id 1 | task 4013 | n_gen = 171, tg = 56.59 t/s, tg_3s = 56.93 t/s 2.10.602.938 I slot print_timing: id 0 | task 4078 | prompt eval time = 111.28 ms / 122 tokens ( 0.91 ms per token, 1096.29 tokens per second) 2.10.602.944 I slot print_timing: id 0 | task 4078 | eval time = 2024.45 ms / 120 tokens ( 17.01 ms per token, 58.78 tokens per second) 2.10.602.945 I slot print_timing: id 0 | task 4078 | total time = 2135.74 ms / 242 tokens 2.10.602.946 I slot print_timing: id 0 | task 4078 | graphs reused = 3268 2.10.602.947 I slot print_timing: id 0 | task 4078 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.603.003 I slot release: id 0 | task 4078 | stop processing: n_tokens = 1366, truncated = 0 2.10.620.965 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.839 2.10.621.083 I slot launch_slot_: id 0 | task 4203 | processing task, is_child = 0 2.10.769.416 I slot print_timing: id 1 | task 4013 | prompt eval time = 223.25 ms / 139 tokens ( 1.61 ms per token, 622.63 tokens per second) 2.10.769.422 I slot print_timing: id 1 | task 4013 | eval time = 3341.94 ms / 187 tokens ( 17.97 ms per token, 55.66 tokens per second) 2.10.769.423 I slot print_timing: id 1 | task 4013 | total time = 3565.19 ms / 326 tokens 2.10.769.423 I slot print_timing: id 1 | task 4013 | graphs reused = 3270 2.10.769.424 I slot print_timing: id 1 | task 4013 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.769.477 I slot release: id 1 | task 4013 | stop processing: n_tokens = 1450, truncated = 0 2.10.799.133 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.790 2.10.799.240 I slot launch_slot_: id 1 | task 4209 | processing task, is_child = 0 2.10.956.056 I slot print_timing: id 3 | task 4115 | prompt eval time = 112.12 ms / 96 tokens ( 1.17 ms per token, 856.25 tokens per second) 2.10.956.061 I slot print_timing: id 3 | task 4115 | eval time = 1739.92 ms / 93 tokens ( 18.91 ms per token, 52.88 tokens per second) 2.10.956.063 I slot print_timing: id 3 | task 4115 | total time = 1852.04 ms / 189 tokens 2.10.956.064 I slot print_timing: id 3 | task 4115 | graphs reused = 3270 2.10.956.065 I slot print_timing: id 3 | task 4115 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.956.118 I slot release: id 3 | task 4115 | stop processing: n_tokens = 1313, truncated = 0 2.10.989.361 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.873 2.10.989.466 I slot launch_slot_: id 3 | task 4215 | processing task, is_child = 0 2.12.215.741 I slot print_timing: id 2 | task 4188 | prompt eval time = 140.56 ms / 111 tokens ( 1.27 ms per token, 789.73 tokens per second) 2.12.215.747 I slot print_timing: id 2 | task 4188 | eval time = 1783.63 ms / 100 tokens ( 18.02 ms per token, 55.50 tokens per second) 2.12.215.748 I slot print_timing: id 2 | task 4188 | total time = 1924.18 ms / 211 tokens 2.12.215.749 I slot print_timing: id 2 | task 4188 | graphs reused = 3345 2.12.215.749 I slot print_timing: id 2 | task 4188 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.215.803 I slot release: id 2 | task 4188 | stop processing: n_tokens = 1335, truncated = 0 2.12.276.274 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.858 2.12.276.402 I slot launch_slot_: id 2 | task 4295 | processing task, is_child = 0 2.12.692.186 I slot print_timing: id 0 | task 4203 | prompt eval time = 111.24 ms / 101 tokens ( 1.10 ms per token, 907.94 tokens per second) 2.12.692.191 I slot print_timing: id 0 | task 4203 | eval time = 1959.84 ms / 108 tokens ( 18.32 ms per token, 54.60 tokens per second) 2.12.692.193 I slot print_timing: id 0 | task 4203 | total time = 2071.08 ms / 209 tokens 2.12.692.193 I slot print_timing: id 0 | task 4203 | graphs reused = 3362 2.12.692.194 I slot print_timing: id 0 | task 4203 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.692.245 I slot release: id 0 | task 4203 | stop processing: n_tokens = 1333, truncated = 0 2.12.728.214 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.860 2.12.728.351 I slot launch_slot_: id 0 | task 4318 | processing task, is_child = 0 2.13.286.251 I slot print_timing: id 1 | task 4209 | prompt eval time = 138.20 ms / 108 tokens ( 1.28 ms per token, 781.46 tokens per second) 2.13.286.257 I slot print_timing: id 1 | task 4209 | eval time = 2348.79 ms / 136 tokens ( 17.40 ms per token, 57.48 tokens per second) 2.13.286.258 I slot print_timing: id 1 | task 4209 | total time = 2486.99 ms / 244 tokens 2.13.286.259 I slot print_timing: id 1 | task 4209 | graphs reused = 3392 2.13.286.259 I slot print_timing: id 1 | task 4209 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.286.310 I slot release: id 1 | task 4209 | stop processing: n_tokens = 1368, truncated = 0 2.13.317.110 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.838 2.13.317.228 I slot launch_slot_: id 1 | task 4351 | processing task, is_child = 0 2.14.132.283 I slot print_timing: id 3 | task 4215 | n_gen = 178, tg = 58.73 t/s, tg_3s = 59.06 t/s 2.14.237.046 I slot print_timing: id 3 | task 4215 | prompt eval time = 128.88 ms / 166 tokens ( 0.78 ms per token, 1287.98 tokens per second) 2.14.237.052 I slot print_timing: id 3 | task 4215 | eval time = 3118.68 ms / 185 tokens ( 16.95 ms per token, 59.00 tokens per second) 2.14.237.053 I slot print_timing: id 3 | task 4215 | total time = 3247.57 ms / 351 tokens 2.14.237.053 I slot print_timing: id 3 | task 4215 | graphs reused = 3442 2.14.237.054 I slot print_timing: id 3 | task 4215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.237.107 I slot release: id 3 | task 4215 | stop processing: n_tokens = 1475, truncated = 0 2.14.254.499 I slot print_timing: id 2 | task 4295 | prompt eval time = 140.84 ms / 110 tokens ( 1.28 ms per token, 781.06 tokens per second) 2.14.254.504 I slot print_timing: id 2 | task 4295 | eval time = 1837.24 ms / 107 tokens ( 17.33 ms per token, 57.70 tokens per second) 2.14.254.505 I slot print_timing: id 2 | task 4295 | total time = 1978.08 ms / 217 tokens 2.14.254.507 I slot print_timing: id 2 | task 4295 | graphs reused = 3442 2.14.254.508 I slot print_timing: id 2 | task 4295 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.254.559 I slot release: id 2 | task 4295 | stop processing: n_tokens = 1341, truncated = 0 2.14.287.200 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.855 2.14.287.310 I slot launch_slot_: id 2 | task 4408 | processing task, is_child = 0 2.14.287.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.162 MiB) 2.14.288.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.14.290.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.14.337.622 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.777 2.14.337.745 I slot launch_slot_: id 3 | task 4409 | processing task, is_child = 0 2.14.589.695 I slot print_timing: id 0 | task 4318 | prompt eval time = 112.42 ms / 128 tokens ( 0.88 ms per token, 1138.57 tokens per second) 2.14.589.701 I slot print_timing: id 0 | task 4318 | eval time = 1748.90 ms / 93 tokens ( 19.01 ms per token, 52.60 tokens per second) 2.14.589.702 I slot print_timing: id 0 | task 4318 | total time = 1861.33 ms / 221 tokens 2.14.589.703 I slot print_timing: id 0 | task 4318 | graphs reused = 3446 2.14.589.703 I slot print_timing: id 0 | task 4318 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.589.753 I slot release: id 0 | task 4318 | stop processing: n_tokens = 1345, truncated = 0 2.14.761.164 I slot print_timing: id 1 | task 4351 | prompt eval time = 141.45 ms / 95 tokens ( 1.49 ms per token, 671.61 tokens per second) 2.14.761.170 I slot print_timing: id 1 | task 4351 | eval time = 1302.47 ms / 73 tokens ( 18.09 ms per token, 55.28 tokens per second) 2.14.761.171 I slot print_timing: id 1 | task 4351 | total time = 1443.92 ms / 168 tokens 2.14.761.172 I slot print_timing: id 1 | task 4351 | graphs reused = 3457 2.14.761.172 I slot print_timing: id 1 | task 4351 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.761.224 I slot release: id 1 | task 4351 | stop processing: n_tokens = 1292, truncated = 0 2.15.627.414 I slot print_timing: id 3 | task 4409 | prompt eval time = 167.47 ms / 96 tokens ( 1.74 ms per token, 573.22 tokens per second) 2.15.627.420 I slot print_timing: id 3 | task 4409 | eval time = 1102.39 ms / 87 tokens ( 12.82 ms per token, 78.01 tokens per second) 2.15.627.421 I slot print_timing: id 3 | task 4409 | total time = 1269.86 ms / 183 tokens 2.15.627.422 I slot print_timing: id 3 | task 4409 | graphs reused = 3526 2.15.627.422 I slot print_timing: id 3 | task 4409 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.627.468 I slot release: id 3 | task 4409 | stop processing: n_tokens = 1307, truncated = 0 2.16.253.797 I slot print_timing: id 2 | task 4408 | prompt eval time = 186.69 ms / 142 tokens ( 1.31 ms per token, 760.64 tokens per second) 2.16.253.803 I slot print_timing: id 2 | task 4408 | eval time = 1729.35 ms / 143 tokens ( 12.18 ms per token, 82.11 tokens per second) 2.16.253.804 I slot print_timing: id 2 | task 4408 | total time = 1916.03 ms / 285 tokens 2.16.253.804 I slot print_timing: id 2 | task 4408 | graphs reused = 3581 2.16.253.805 I slot print_timing: id 2 | task 4408 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.253.855 I slot release: id 2 | task 4408 | stop processing: n_tokens = 1409, truncated = 0 2.16.275.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1345, t_last = 134492349 2.16.275.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.16.277.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 2.16.279.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.504 MiB) 2.16.334.637 I slot launch_slot_: id 0 | task 4554 | processing task, is_child = 0 2.16.334.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.16.336.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.16.338.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 2.16.392.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 2.16.394.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.16.447.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 2.16.449.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 2.16.451.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 2.16.505.715 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1292, t_last = 134663820 2.16.505.943 I slot launch_slot_: id 1 | task 4555 | processing task, is_child = 0 2.16.506.099 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1307, t_last = 135530064 2.16.506.269 I slot launch_slot_: id 3 | task 4556 | processing task, is_child = 0 2.16.506.347 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1409, t_last = 136156451 2.16.506.504 I slot launch_slot_: id 2 | task 4557 | processing task, is_child = 0 2.17.691.398 I slot print_timing: id 0 | task 4554 | prompt eval time = 1118.22 ms / 779 tokens ( 1.44 ms per token, 696.64 tokens per second) 2.17.691.403 I slot print_timing: id 0 | task 4554 | eval time = 66.65 ms / 2 tokens ( 66.65 ms per token, 15.00 tokens per second) 2.17.691.404 I slot print_timing: id 0 | task 4554 | total time = 1184.88 ms / 781 tokens 2.17.691.405 I slot print_timing: id 0 | task 4554 | graphs reused = 3581 2.17.691.405 I slot print_timing: id 0 | task 4554 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.691.449 I slot release: id 0 | task 4554 | stop processing: n_tokens = 780, truncated = 0 2.17.709.939 I slot print_timing: id 1 | task 4555 | prompt eval time = 1182.23 ms / 952 tokens ( 1.24 ms per token, 805.26 tokens per second) 2.17.709.944 I slot print_timing: id 1 | task 4555 | eval time = 17.72 ms / 2 tokens ( 17.72 ms per token, 56.44 tokens per second) 2.17.709.945 I slot print_timing: id 1 | task 4555 | total time = 1199.95 ms / 954 tokens 2.17.709.945 I slot print_timing: id 1 | task 4555 | graphs reused = 3581 2.17.709.946 I slot print_timing: id 1 | task 4555 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.709.992 I slot release: id 1 | task 4555 | stop processing: n_tokens = 953, truncated = 0 2.17.710.285 I slot print_timing: id 2 | task 4557 | prompt eval time = 1179.35 ms / 806 tokens ( 1.46 ms per token, 683.43 tokens per second) 2.17.710.288 I slot print_timing: id 2 | task 4557 | eval time = 17.50 ms / 2 tokens ( 17.50 ms per token, 57.15 tokens per second) 2.17.710.288 I slot print_timing: id 2 | task 4557 | total time = 1196.84 ms / 808 tokens 2.17.710.289 I slot print_timing: id 2 | task 4557 | graphs reused = 3581 2.17.710.290 I slot print_timing: id 2 | task 4557 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.710.319 I slot release: id 2 | task 4557 | stop processing: n_tokens = 807, truncated = 0 2.17.710.634 I slot print_timing: id 3 | task 4556 | prompt eval time = 1176.43 ms / 987 tokens ( 1.19 ms per token, 838.98 tokens per second) 2.17.710.637 I slot print_timing: id 3 | task 4556 | eval time = 17.28 ms / 2 tokens ( 17.28 ms per token, 57.87 tokens per second) 2.17.710.638 I slot print_timing: id 3 | task 4556 | total time = 1193.71 ms / 989 tokens 2.17.710.638 I slot print_timing: id 3 | task 4556 | graphs reused = 3581 2.17.710.639 I slot print_timing: id 3 | task 4556 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.710.672 I slot release: id 3 | task 4556 | stop processing: n_tokens = 988, truncated = 0 2.17.713.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 137594045 2.17.713.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 2.17.715.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.161 MiB) 2.17.718.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.035 MiB) 2.17.769.210 I slot launch_slot_: id 0 | task 4565 | processing task, is_child = 0 2.17.769.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 2.17.771.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 2.17.772.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 2.17.824.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 2.17.826.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 2.17.877.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 2.17.878.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 2.17.880.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.130 MiB) 2.17.931.229 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 137612587 2.17.931.438 I slot launch_slot_: id 1 | task 4566 | processing task, is_child = 0 2.17.931.548 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 137612915 2.17.931.693 I slot launch_slot_: id 2 | task 4567 | processing task, is_child = 0 2.17.931.752 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 137613268 2.17.931.893 I slot launch_slot_: id 3 | task 4568 | processing task, is_child = 0 2.19.036.414 I slot print_timing: id 0 | task 4565 | prompt eval time = 1085.89 ms / 801 tokens ( 1.36 ms per token, 737.64 tokens per second) 2.19.036.420 I slot print_timing: id 0 | task 4565 | eval time = 18.61 ms / 2 tokens ( 18.61 ms per token, 53.73 tokens per second) 2.19.036.421 I slot print_timing: id 0 | task 4565 | total time = 1104.51 ms / 803 tokens 2.19.036.421 I slot print_timing: id 0 | task 4565 | graphs reused = 3581 2.19.036.423 I slot print_timing: id 0 | task 4565 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.036.467 I slot release: id 0 | task 4565 | stop processing: n_tokens = 802, truncated = 0 2.19.036.726 I slot print_timing: id 1 | task 4566 | prompt eval time = 1082.82 ms / 846 tokens ( 1.28 ms per token, 781.30 tokens per second) 2.19.036.730 I slot print_timing: id 1 | task 4566 | eval time = 18.35 ms / 2 tokens ( 18.35 ms per token, 54.50 tokens per second) 2.19.036.730 I slot print_timing: id 1 | task 4566 | total time = 1101.16 ms / 848 tokens 2.19.036.731 I slot print_timing: id 1 | task 4566 | graphs reused = 3581 2.19.036.731 I slot print_timing: id 1 | task 4566 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.036.757 I slot release: id 1 | task 4566 | stop processing: n_tokens = 847, truncated = 0 2.19.036.988 I slot print_timing: id 2 | task 4567 | prompt eval time = 1079.79 ms / 855 tokens ( 1.26 ms per token, 791.82 tokens per second) 2.19.036.991 I slot print_timing: id 2 | task 4567 | eval time = 18.04 ms / 2 tokens ( 18.04 ms per token, 55.42 tokens per second) 2.19.036.992 I slot print_timing: id 2 | task 4567 | total time = 1097.83 ms / 857 tokens 2.19.036.992 I slot print_timing: id 2 | task 4567 | graphs reused = 3581 2.19.036.993 I slot print_timing: id 2 | task 4567 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.037.019 I slot release: id 2 | task 4567 | stop processing: n_tokens = 856, truncated = 0 2.19.037.253 I slot print_timing: id 3 | task 4568 | prompt eval time = 1076.77 ms / 804 tokens ( 1.34 ms per token, 746.68 tokens per second) 2.19.037.255 I slot print_timing: id 3 | task 4568 | eval time = 17.76 ms / 2 tokens ( 17.76 ms per token, 56.30 tokens per second) 2.19.037.256 I slot print_timing: id 3 | task 4568 | total time = 1094.53 ms / 806 tokens 2.19.037.256 I slot print_timing: id 3 | task 4568 | graphs reused = 3581 2.19.037.257 I slot print_timing: id 3 | task 4568 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.037.277 I slot release: id 3 | task 4568 | stop processing: n_tokens = 805, truncated = 0 2.19.050.114 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.903 2.19.050.266 I slot launch_slot_: id 0 | task 4576 | processing task, is_child = 0 2.19.050.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.317 MiB) 2.19.052.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.910 MiB) 2.19.101.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 2.19.103.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.160 MiB) 2.19.105.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 2.19.156.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 2.19.158.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 2.19.160.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 2.19.211.379 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 138939353 2.19.211.591 I slot launch_slot_: id 1 | task 4577 | processing task, is_child = 0 2.19.211.703 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 138939615 2.19.211.876 I slot launch_slot_: id 2 | task 4578 | processing task, is_child = 0 2.19.211.929 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 138939872 2.19.212.065 I slot launch_slot_: id 3 | task 4579 | processing task, is_child = 0 2.19.676.491 I slot print_timing: id 0 | task 4576 | prompt eval time = 379.76 ms / 129 tokens ( 2.94 ms per token, 339.69 tokens per second) 2.19.676.497 I slot print_timing: id 0 | task 4576 | eval time = 84.65 ms / 2 tokens ( 84.65 ms per token, 11.81 tokens per second) 2.19.676.498 I slot print_timing: id 0 | task 4576 | total time = 464.41 ms / 131 tokens 2.19.676.499 I slot print_timing: id 0 | task 4576 | graphs reused = 3581 2.19.676.499 I slot print_timing: id 0 | task 4576 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.676.544 I slot release: id 0 | task 4576 | stop processing: n_tokens = 826, truncated = 0 2.19.987.096 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 139579140 2.19.987.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.19.988.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 2.20.049.421 I slot launch_slot_: id 0 | task 4584 | processing task, is_child = 0 2.20.410.653 I slot print_timing: id 1 | task 4577 | prompt eval time = 1134.96 ms / 880 tokens ( 1.29 ms per token, 775.36 tokens per second) 2.20.410.658 I slot print_timing: id 1 | task 4577 | eval time = 43.67 ms / 2 tokens ( 43.67 ms per token, 22.90 tokens per second) 2.20.410.659 I slot print_timing: id 1 | task 4577 | total time = 1178.63 ms / 882 tokens 2.20.410.662 I slot print_timing: id 1 | task 4577 | graphs reused = 3581 2.20.410.663 I slot print_timing: id 1 | task 4577 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.410.716 I slot release: id 1 | task 4577 | stop processing: n_tokens = 881, truncated = 0 2.20.411.036 I slot print_timing: id 2 | task 4578 | prompt eval time = 1131.98 ms / 896 tokens ( 1.26 ms per token, 791.53 tokens per second) 2.20.411.039 I slot print_timing: id 2 | task 4578 | eval time = 43.43 ms / 2 tokens ( 43.43 ms per token, 23.03 tokens per second) 2.20.411.039 I slot print_timing: id 2 | task 4578 | total time = 1175.41 ms / 898 tokens 2.20.411.040 I slot print_timing: id 2 | task 4578 | graphs reused = 3581 2.20.411.041 I slot print_timing: id 2 | task 4578 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.411.070 I slot release: id 2 | task 4578 | stop processing: n_tokens = 897, truncated = 0 2.20.411.397 I slot print_timing: id 3 | task 4579 | prompt eval time = 1129.02 ms / 963 tokens ( 1.17 ms per token, 852.95 tokens per second) 2.20.411.401 I slot print_timing: id 3 | task 4579 | eval time = 43.13 ms / 2 tokens ( 43.13 ms per token, 23.19 tokens per second) 2.20.411.402 I slot print_timing: id 3 | task 4579 | total time = 1172.15 ms / 965 tokens 2.20.411.402 I slot print_timing: id 3 | task 4579 | graphs reused = 3581 2.20.411.403 I slot print_timing: id 3 | task 4579 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.411.437 I slot release: id 3 | task 4579 | stop processing: n_tokens = 964, truncated = 0 2.20.428.210 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 140313312 2.20.428.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 2.20.429.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 2.20.431.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 2.20.534.186 I slot launch_slot_: id 1 | task 4589 | processing task, is_child = 0 2.20.534.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 2.20.536.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 2.20.537.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 2.20.579.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 2.20.581.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.318 MiB) 2.20.623.899 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 140313666 2.20.624.095 I slot launch_slot_: id 2 | task 4590 | processing task, is_child = 0 2.20.624.155 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 140314032 2.20.624.308 I slot launch_slot_: id 3 | task 4591 | processing task, is_child = 0 2.21.203.066 I slot print_timing: id 0 | task 4584 | prompt eval time = 948.47 ms / 987 tokens ( 0.96 ms per token, 1040.63 tokens per second) 2.21.203.072 I slot print_timing: id 0 | task 4584 | eval time = 205.15 ms / 2 tokens ( 205.15 ms per token, 4.87 tokens per second) 2.21.203.073 I slot print_timing: id 0 | task 4584 | total time = 1153.62 ms / 989 tokens 2.21.203.075 I slot print_timing: id 0 | task 4584 | graphs reused = 3581 2.21.203.076 I slot print_timing: id 0 | task 4584 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.203.127 I slot release: id 0 | task 4584 | stop processing: n_tokens = 988, truncated = 0 2.21.506.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 141105724 2.21.507.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 2.21.508.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 2.21.510.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.473 MiB) 2.21.557.053 I slot launch_slot_: id 0 | task 4596 | processing task, is_child = 0 2.22.020.008 I slot print_timing: id 1 | task 4589 | prompt eval time = 1323.70 ms / 924 tokens ( 1.43 ms per token, 698.04 tokens per second) 2.22.020.014 I slot print_timing: id 1 | task 4589 | eval time = 61.83 ms / 2 tokens ( 61.83 ms per token, 16.17 tokens per second) 2.22.020.015 I slot print_timing: id 1 | task 4589 | total time = 1385.53 ms / 926 tokens 2.22.020.016 I slot print_timing: id 1 | task 4589 | graphs reused = 3581 2.22.020.017 I slot print_timing: id 1 | task 4589 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.020.070 I slot release: id 1 | task 4589 | stop processing: n_tokens = 925, truncated = 0 2.22.020.414 I slot print_timing: id 2 | task 4590 | prompt eval time = 1320.81 ms / 1780 tokens ( 0.74 ms per token, 1347.66 tokens per second) 2.22.020.418 I slot print_timing: id 2 | task 4590 | eval time = 61.66 ms / 2 tokens ( 61.66 ms per token, 16.22 tokens per second) 2.22.020.418 I slot print_timing: id 2 | task 4590 | total time = 1382.47 ms / 1782 tokens 2.22.020.419 I slot print_timing: id 2 | task 4590 | graphs reused = 3581 2.22.020.419 I slot print_timing: id 2 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.020.484 I slot release: id 2 | task 4590 | stop processing: n_tokens = 1781, truncated = 0 2.22.020.805 I slot print_timing: id 3 | task 4591 | prompt eval time = 1317.92 ms / 1022 tokens ( 1.29 ms per token, 775.46 tokens per second) 2.22.020.808 I slot print_timing: id 3 | task 4591 | eval time = 61.47 ms / 2 tokens ( 61.47 ms per token, 16.27 tokens per second) 2.22.020.809 I slot print_timing: id 3 | task 4591 | total time = 1379.39 ms / 1024 tokens 2.22.020.809 I slot print_timing: id 3 | task 4591 | graphs reused = 3581 2.22.020.810 I slot print_timing: id 3 | task 4591 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.020.842 I slot release: id 3 | task 4591 | stop processing: n_tokens = 1023, truncated = 0 2.22.037.046 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 141922666 2.22.037.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.22.038.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 2.22.040.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.848 MiB) 2.22.120.628 I slot launch_slot_: id 1 | task 4601 | processing task, is_child = 0 2.22.120.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 2.22.122.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 2.22.124.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 2.22.178.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 2.22.179.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 2.22.222.929 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 141923081 2.22.223.166 I slot launch_slot_: id 2 | task 4602 | processing task, is_child = 0 2.22.223.231 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 141923438 2.22.223.388 I slot launch_slot_: id 3 | task 4603 | processing task, is_child = 0 2.22.831.236 I slot print_timing: id 0 | task 4596 | prompt eval time = 1005.77 ms / 937 tokens ( 1.07 ms per token, 931.62 tokens per second) 2.22.831.242 I slot print_timing: id 0 | task 4596 | eval time = 268.38 ms / 2 tokens ( 268.38 ms per token, 3.73 tokens per second) 2.22.831.243 I slot print_timing: id 0 | task 4596 | total time = 1274.15 ms / 939 tokens 2.22.831.244 I slot print_timing: id 0 | task 4596 | graphs reused = 3581 2.22.831.245 I slot print_timing: id 0 | task 4596 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.831.298 I slot release: id 0 | task 4596 | stop processing: n_tokens = 938, truncated = 0 2.23.027.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 142733894 2.23.027.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.786 MiB) 2.23.029.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 2.23.030.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.754 MiB) 2.23.080.947 I slot launch_slot_: id 0 | task 4608 | processing task, is_child = 0 2.23.288.538 I slot print_timing: id 2 | task 4602 | prompt eval time = 971.09 ms / 713 tokens ( 1.36 ms per token, 734.23 tokens per second) 2.23.288.544 I slot print_timing: id 2 | task 4602 | eval time = 80.34 ms / 2 tokens ( 80.34 ms per token, 12.45 tokens per second) 2.23.288.545 I slot print_timing: id 2 | task 4602 | total time = 1051.43 ms / 715 tokens 2.23.288.546 I slot print_timing: id 2 | task 4602 | graphs reused = 3581 2.23.288.547 I slot print_timing: id 2 | task 4602 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.288.587 I slot release: id 2 | task 4602 | stop processing: n_tokens = 714, truncated = 0 2.23.288.927 I slot print_timing: id 3 | task 4603 | prompt eval time = 968.12 ms / 741 tokens ( 1.31 ms per token, 765.40 tokens per second) 2.23.288.930 I slot print_timing: id 3 | task 4603 | eval time = 80.11 ms / 2 tokens ( 80.11 ms per token, 12.48 tokens per second) 2.23.288.931 I slot print_timing: id 3 | task 4603 | total time = 1048.23 ms / 743 tokens 2.23.288.932 I slot print_timing: id 3 | task 4603 | graphs reused = 3581 2.23.288.932 I slot print_timing: id 3 | task 4603 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.288.956 I slot release: id 3 | task 4603 | stop processing: n_tokens = 742, truncated = 0 2.23.411.905 I slot print_timing: id 1 | task 4601 | prompt eval time = 1054.60 ms / 880 tokens ( 1.20 ms per token, 834.44 tokens per second) 2.23.411.911 I slot print_timing: id 1 | task 4601 | eval time = 123.70 ms / 2 tokens ( 123.70 ms per token, 8.08 tokens per second) 2.23.411.912 I slot print_timing: id 1 | task 4601 | total time = 1178.30 ms / 882 tokens 2.23.411.913 I slot print_timing: id 1 | task 4601 | graphs reused = 3581 2.23.411.914 I slot print_timing: id 1 | task 4601 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.411.960 I slot release: id 1 | task 4601 | stop processing: n_tokens = 881, truncated = 0 2.23.411.975 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.884 2.23.412.122 I slot launch_slot_: id 2 | task 4612 | processing task, is_child = 0 2.23.412.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.692 MiB) 2.23.413.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 2.23.415.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 2.23.461.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 2.23.463.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.440 MiB) 2.23.513.645 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.850 2.23.513.783 I slot launch_slot_: id 3 | task 4613 | processing task, is_child = 0 2.23.513.847 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 143314555 2.23.513.993 I slot launch_slot_: id 1 | task 4614 | processing task, is_child = 0 2.23.878.350 I slot print_timing: id 0 | task 4608 | prompt eval time = 738.25 ms / 716 tokens ( 1.03 ms per token, 969.86 tokens per second) 2.23.878.355 I slot print_timing: id 0 | task 4608 | eval time = 59.12 ms / 2 tokens ( 59.12 ms per token, 16.91 tokens per second) 2.23.878.356 I slot print_timing: id 0 | task 4608 | total time = 797.38 ms / 718 tokens 2.23.878.358 I slot print_timing: id 0 | task 4608 | graphs reused = 3581 2.23.878.358 I slot print_timing: id 0 | task 4608 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.878.397 I slot release: id 0 | task 4608 | stop processing: n_tokens = 717, truncated = 0 2.23.878.725 I slot print_timing: id 2 | task 4612 | prompt eval time = 292.08 ms / 116 tokens ( 2.52 ms per token, 397.15 tokens per second) 2.23.878.728 I slot print_timing: id 2 | task 4612 | eval time = 58.83 ms / 2 tokens ( 58.83 ms per token, 17.00 tokens per second) 2.23.878.729 I slot print_timing: id 2 | task 4612 | total time = 350.92 ms / 118 tokens 2.23.878.729 I slot print_timing: id 2 | task 4612 | graphs reused = 3581 2.23.878.730 I slot print_timing: id 2 | task 4612 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.878.753 I slot release: id 2 | task 4612 | stop processing: n_tokens = 720, truncated = 0 2.23.879.062 I slot print_timing: id 3 | task 4613 | prompt eval time = 272.24 ms / 122 tokens ( 2.23 ms per token, 448.13 tokens per second) 2.23.879.065 I slot print_timing: id 3 | task 4613 | eval time = 58.58 ms / 2 tokens ( 58.58 ms per token, 17.07 tokens per second) 2.23.879.066 I slot print_timing: id 3 | task 4613 | total time = 330.82 ms / 124 tokens 2.23.879.067 I slot print_timing: id 3 | task 4613 | graphs reused = 3581 2.23.879.067 I slot print_timing: id 3 | task 4613 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.879.087 I slot release: id 3 | task 4613 | stop processing: n_tokens = 726, truncated = 0 2.23.895.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 143780993 2.23.895.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 294.691 MiB) 2.24.003.089 I slot launch_slot_: id 0 | task 4619 | processing task, is_child = 0 2.24.003.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.001 MiB) 2.24.072.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.004 MiB) 2.24.120.404 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 143781349 2.24.120.594 I slot launch_slot_: id 2 | task 4620 | processing task, is_child = 0 2.24.120.641 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 143781683 2.24.120.778 I slot launch_slot_: id 3 | task 4621 | processing task, is_child = 0 2.24.650.032 I slot print_timing: id 1 | task 4614 | prompt eval time = 979.85 ms / 876 tokens ( 1.12 ms per token, 894.02 tokens per second) 2.24.650.038 I slot print_timing: id 1 | task 4614 | eval time = 145.85 ms / 2 tokens ( 145.85 ms per token, 6.86 tokens per second) 2.24.650.039 I slot print_timing: id 1 | task 4614 | total time = 1125.70 ms / 878 tokens 2.24.650.040 I slot print_timing: id 1 | task 4614 | graphs reused = 3581 2.24.650.041 I slot print_timing: id 1 | task 4614 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.650.083 I slot release: id 1 | task 4614 | stop processing: n_tokens = 877, truncated = 0 2.24.948.729 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 144552679 2.24.948.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.410 MiB) 2.24.996.692 I slot launch_slot_: id 1 | task 4626 | processing task, is_child = 0 2.25.394.646 I slot print_timing: id 0 | task 4619 | prompt eval time = 1201.07 ms / 992 tokens ( 1.21 ms per token, 825.93 tokens per second) 2.25.394.651 I slot print_timing: id 0 | task 4619 | eval time = 72.78 ms / 2 tokens ( 72.78 ms per token, 13.74 tokens per second) 2.25.394.652 I slot print_timing: id 0 | task 4619 | total time = 1273.85 ms / 994 tokens 2.25.394.653 I slot print_timing: id 0 | task 4619 | graphs reused = 3581 2.25.394.654 I slot print_timing: id 0 | task 4619 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.394.697 I slot release: id 0 | task 4619 | stop processing: n_tokens = 993, truncated = 0 2.25.395.012 I slot print_timing: id 2 | task 4620 | prompt eval time = 1186.06 ms / 1006 tokens ( 1.18 ms per token, 848.19 tokens per second) 2.25.395.016 I slot print_timing: id 2 | task 4620 | eval time = 72.56 ms / 2 tokens ( 72.56 ms per token, 13.78 tokens per second) 2.25.395.017 I slot print_timing: id 2 | task 4620 | total time = 1258.62 ms / 1008 tokens 2.25.395.017 I slot print_timing: id 2 | task 4620 | graphs reused = 3581 2.25.395.018 I slot print_timing: id 2 | task 4620 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.395.044 I slot release: id 2 | task 4620 | stop processing: n_tokens = 1007, truncated = 0 2.25.395.350 I slot print_timing: id 3 | task 4621 | prompt eval time = 1183.25 ms / 1034 tokens ( 1.14 ms per token, 873.87 tokens per second) 2.25.395.353 I slot print_timing: id 3 | task 4621 | eval time = 72.32 ms / 2 tokens ( 72.32 ms per token, 13.83 tokens per second) 2.25.395.353 I slot print_timing: id 3 | task 4621 | total time = 1255.57 ms / 1036 tokens 2.25.395.354 I slot print_timing: id 3 | task 4621 | graphs reused = 3581 2.25.395.355 I slot print_timing: id 3 | task 4621 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.395.380 I slot release: id 3 | task 4621 | stop processing: n_tokens = 1035, truncated = 0 2.25.411.809 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 2.25.411.917 I slot launch_slot_: id 0 | task 4631 | processing task, is_child = 0 2.25.411.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.439 MiB) 2.25.535.654 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1007, t_last = 145297640 2.25.535.934 I slot launch_slot_: id 2 | task 4632 | processing task, is_child = 0 2.25.535.996 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 145297976 2.25.536.205 I slot launch_slot_: id 3 | task 4633 | processing task, is_child = 0 2.25.984.466 I slot print_timing: id 0 | task 4631 | prompt eval time = 356.44 ms / 132 tokens ( 2.70 ms per token, 370.33 tokens per second) 2.25.984.471 I slot print_timing: id 0 | task 4631 | eval time = 91.80 ms / 2 tokens ( 91.80 ms per token, 10.89 tokens per second) 2.25.984.473 I slot print_timing: id 0 | task 4631 | total time = 448.24 ms / 134 tokens 2.25.984.473 I slot print_timing: id 0 | task 4631 | graphs reused = 3581 2.25.984.474 I slot print_timing: id 0 | task 4631 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.984.518 I slot release: id 0 | task 4631 | stop processing: n_tokens = 994, truncated = 0 2.25.984.810 I slot print_timing: id 1 | task 4626 | prompt eval time = 870.67 ms / 999 tokens ( 0.87 ms per token, 1147.39 tokens per second) 2.25.984.813 I slot print_timing: id 1 | task 4626 | eval time = 91.46 ms / 2 tokens ( 91.46 ms per token, 10.93 tokens per second) 2.25.984.814 I slot print_timing: id 1 | task 4626 | total time = 962.13 ms / 1001 tokens 2.25.984.815 I slot print_timing: id 1 | task 4626 | graphs reused = 3581 2.25.984.815 I slot print_timing: id 1 | task 4626 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.984.842 I slot release: id 1 | task 4626 | stop processing: n_tokens = 1000, truncated = 0 2.26.157.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 145887114 2.26.157.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 297.381 MiB) 2.26.204.499 I slot launch_slot_: id 0 | task 4638 | processing task, is_child = 0 2.26.204.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.315 MiB) 2.26.259.929 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 145887438 2.26.260.148 I slot launch_slot_: id 1 | task 4639 | processing task, is_child = 0 2.26.695.103 I slot print_timing: id 2 | task 4632 | prompt eval time = 1032.03 ms / 1018 tokens ( 1.01 ms per token, 986.40 tokens per second) 2.26.695.108 I slot print_timing: id 2 | task 4632 | eval time = 96.84 ms / 2 tokens ( 96.84 ms per token, 10.33 tokens per second) 2.26.695.109 I slot print_timing: id 2 | task 4632 | total time = 1128.87 ms / 1020 tokens 2.26.695.110 I slot print_timing: id 2 | task 4632 | graphs reused = 3581 2.26.695.111 I slot print_timing: id 2 | task 4632 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.695.161 I slot release: id 2 | task 4632 | stop processing: n_tokens = 1019, truncated = 0 2.26.695.451 I slot print_timing: id 3 | task 4633 | prompt eval time = 1029.13 ms / 879 tokens ( 1.17 ms per token, 854.12 tokens per second) 2.26.695.454 I slot print_timing: id 3 | task 4633 | eval time = 96.60 ms / 2 tokens ( 96.60 ms per token, 10.35 tokens per second) 2.26.695.455 I slot print_timing: id 3 | task 4633 | total time = 1125.73 ms / 881 tokens 2.26.695.456 I slot print_timing: id 3 | task 4633 | graphs reused = 3581 2.26.695.456 I slot print_timing: id 3 | task 4633 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.695.484 I slot release: id 3 | task 4633 | stop processing: n_tokens = 880, truncated = 0 2.26.852.661 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.813 (> 0.100 thold), f_keep = 0.786 2.26.852.774 I slot launch_slot_: id 2 | task 4644 | processing task, is_child = 0 2.26.852.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.658 MiB) 2.26.907.744 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 146598079 2.26.907.948 I slot launch_slot_: id 3 | task 4645 | processing task, is_child = 0 2.27.291.117 I slot print_timing: id 0 | task 4638 | prompt eval time = 984.49 ms / 1009 tokens ( 0.98 ms per token, 1024.90 tokens per second) 2.27.291.122 I slot print_timing: id 0 | task 4638 | eval time = 46.46 ms / 2 tokens ( 46.46 ms per token, 21.52 tokens per second) 2.27.291.123 I slot print_timing: id 0 | task 4638 | total time = 1030.95 ms / 1011 tokens 2.27.291.125 I slot print_timing: id 0 | task 4638 | graphs reused = 3581 2.27.291.126 I slot print_timing: id 0 | task 4638 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.291.175 I slot release: id 0 | task 4638 | stop processing: n_tokens = 1010, truncated = 0 2.27.291.451 I slot print_timing: id 1 | task 4639 | prompt eval time = 981.52 ms / 896 tokens ( 1.10 ms per token, 912.87 tokens per second) 2.27.291.454 I slot print_timing: id 1 | task 4639 | eval time = 46.22 ms / 2 tokens ( 46.22 ms per token, 21.63 tokens per second) 2.27.291.455 I slot print_timing: id 1 | task 4639 | total time = 1027.75 ms / 898 tokens 2.27.291.455 I slot print_timing: id 1 | task 4639 | graphs reused = 3581 2.27.291.456 I slot print_timing: id 1 | task 4639 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.291.483 I slot release: id 1 | task 4639 | stop processing: n_tokens = 897, truncated = 0 2.27.291.762 I slot print_timing: id 2 | task 4644 | prompt eval time = 316.81 ms / 212 tokens ( 1.49 ms per token, 669.17 tokens per second) 2.27.291.765 I slot print_timing: id 2 | task 4644 | eval time = 45.97 ms / 2 tokens ( 45.97 ms per token, 21.75 tokens per second) 2.27.291.766 I slot print_timing: id 2 | task 4644 | total time = 362.78 ms / 214 tokens 2.27.291.766 I slot print_timing: id 2 | task 4644 | graphs reused = 3581 2.27.291.767 I slot print_timing: id 2 | task 4644 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.291.795 I slot release: id 2 | task 4644 | stop processing: n_tokens = 986, truncated = 0 2.27.308.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 147193771 2.27.308.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 295.317 MiB) 2.27.410.592 I slot launch_slot_: id 0 | task 4650 | processing task, is_child = 0 2.27.410.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.127 MiB) 2.27.465.437 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.646 MiB) 2.27.520.026 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 2.27.520.162 I slot launch_slot_: id 1 | task 4651 | processing task, is_child = 0 2.27.520.234 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 147194391 2.27.520.387 I slot launch_slot_: id 2 | task 4652 | processing task, is_child = 0 2.27.961.776 I slot print_timing: id 1 | task 4651 | prompt eval time = 312.64 ms / 108 tokens ( 2.89 ms per token, 345.44 tokens per second) 2.27.961.782 I slot print_timing: id 1 | task 4651 | eval time = 125.26 ms / 2 tokens ( 125.26 ms per token, 7.98 tokens per second) 2.27.961.783 I slot print_timing: id 1 | task 4651 | total time = 437.90 ms / 110 tokens 2.27.961.784 I slot print_timing: id 1 | task 4651 | graphs reused = 3581 2.27.961.784 I slot print_timing: id 1 | task 4651 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.961.832 I slot release: id 1 | task 4651 | stop processing: n_tokens = 882, truncated = 0 2.27.962.156 I slot print_timing: id 3 | task 4645 | prompt eval time = 888.27 ms / 902 tokens ( 0.98 ms per token, 1015.46 tokens per second) 2.27.962.159 I slot print_timing: id 3 | task 4645 | eval time = 124.94 ms / 2 tokens ( 124.94 ms per token, 8.00 tokens per second) 2.27.962.160 I slot print_timing: id 3 | task 4645 | total time = 1013.21 ms / 904 tokens 2.27.962.160 I slot print_timing: id 3 | task 4645 | graphs reused = 3581 2.27.962.161 I slot print_timing: id 3 | task 4645 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.962.190 I slot release: id 3 | task 4645 | stop processing: n_tokens = 903, truncated = 0 2.28.073.544 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 147864428 2.28.073.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 2.28.160.563 I slot launch_slot_: id 1 | task 4657 | processing task, is_child = 0 2.28.160.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.490 MiB) 2.28.214.773 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 147864786 2.28.214.978 I slot launch_slot_: id 3 | task 4658 | processing task, is_child = 0 2.28.747.718 I slot print_timing: id 0 | task 4650 | prompt eval time = 1049.64 ms / 952 tokens ( 1.10 ms per token, 906.98 tokens per second) 2.28.747.723 I slot print_timing: id 0 | task 4650 | eval time = 177.67 ms / 2 tokens ( 177.67 ms per token, 5.63 tokens per second) 2.28.747.724 I slot print_timing: id 0 | task 4650 | total time = 1227.31 ms / 954 tokens 2.28.747.725 I slot print_timing: id 0 | task 4650 | graphs reused = 3581 2.28.747.726 I slot print_timing: id 0 | task 4650 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.747.773 I slot release: id 0 | task 4650 | stop processing: n_tokens = 953, truncated = 0 2.28.748.166 I slot print_timing: id 2 | task 4652 | prompt eval time = 1025.17 ms / 906 tokens ( 1.13 ms per token, 883.75 tokens per second) 2.28.748.169 I slot print_timing: id 2 | task 4652 | eval time = 177.34 ms / 2 tokens ( 177.34 ms per token, 5.64 tokens per second) 2.28.748.170 I slot print_timing: id 2 | task 4652 | total time = 1202.52 ms / 908 tokens 2.28.748.170 I slot print_timing: id 2 | task 4652 | graphs reused = 3581 2.28.748.171 I slot print_timing: id 2 | task 4652 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.748.206 I slot release: id 2 | task 4652 | stop processing: n_tokens = 907, truncated = 0 2.28.852.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 148650369 2.28.852.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 2.28.938.935 I slot launch_slot_: id 0 | task 4663 | processing task, is_child = 0 2.28.939.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.741 MiB) 2.28.990.518 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 148650802 2.28.990.717 I slot launch_slot_: id 2 | task 4664 | processing task, is_child = 0 2.29.609.782 I slot print_timing: id 1 | task 4657 | prompt eval time = 1181.03 ms / 1356 tokens ( 0.87 ms per token, 1148.15 tokens per second) 2.29.609.788 I slot print_timing: id 1 | task 4657 | eval time = 203.44 ms / 2 tokens ( 203.44 ms per token, 4.92 tokens per second) 2.29.609.790 I slot print_timing: id 1 | task 4657 | total time = 1384.47 ms / 1358 tokens 2.29.609.790 I slot print_timing: id 1 | task 4657 | graphs reused = 3581 2.29.609.791 I slot print_timing: id 1 | task 4657 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.609.851 I slot release: id 1 | task 4657 | stop processing: n_tokens = 1357, truncated = 0 2.29.610.197 I slot print_timing: id 3 | task 4658 | prompt eval time = 1165.88 ms / 940 tokens ( 1.24 ms per token, 806.26 tokens per second) 2.29.610.200 I slot print_timing: id 3 | task 4658 | eval time = 203.15 ms / 2 tokens ( 203.15 ms per token, 4.92 tokens per second) 2.29.610.201 I slot print_timing: id 3 | task 4658 | total time = 1369.03 ms / 942 tokens 2.29.610.201 I slot print_timing: id 3 | task 4658 | graphs reused = 3581 2.29.610.202 I slot print_timing: id 3 | task 4658 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.610.235 I slot release: id 3 | task 4658 | stop processing: n_tokens = 941, truncated = 0 2.29.714.620 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1357, t_last = 149512447 2.29.714.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 2.29.818.880 I slot launch_slot_: id 1 | task 4670 | processing task, is_child = 0 2.29.818.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.428 MiB) 2.29.874.278 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 149512831 2.29.889.548 I slot launch_slot_: id 3 | task 4669 | processing task, is_child = 0 2.30.343.689 I slot print_timing: id 0 | task 4663 | prompt eval time = 1213.32 ms / 1342 tokens ( 0.90 ms per token, 1106.06 tokens per second) 2.30.343.696 I slot print_timing: id 0 | task 4663 | eval time = 139.63 ms / 2 tokens ( 139.63 ms per token, 7.16 tokens per second) 2.30.343.697 I slot print_timing: id 0 | task 4663 | total time = 1352.95 ms / 1344 tokens 2.30.343.698 I slot print_timing: id 0 | task 4663 | graphs reused = 3581 2.30.343.700 I slot print_timing: id 0 | task 4663 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.343.772 I slot release: id 0 | task 4663 | stop processing: n_tokens = 1343, truncated = 0 2.30.344.200 I slot print_timing: id 2 | task 4664 | prompt eval time = 1186.81 ms / 1259 tokens ( 0.94 ms per token, 1060.83 tokens per second) 2.30.344.206 I slot print_timing: id 2 | task 4664 | eval time = 139.48 ms / 2 tokens ( 139.48 ms per token, 7.17 tokens per second) 2.30.344.208 I slot print_timing: id 2 | task 4664 | total time = 1326.29 ms / 1261 tokens 2.30.344.209 I slot print_timing: id 2 | task 4664 | graphs reused = 3581 2.30.344.210 I slot print_timing: id 2 | task 4664 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.344.259 I slot release: id 2 | task 4664 | stop processing: n_tokens = 1260, truncated = 0 2.30.344.736 I slot print_timing: id 3 | task 4669 | prompt eval time = 287.75 ms / 148 tokens ( 1.94 ms per token, 514.34 tokens per second) 2.30.344.740 I slot print_timing: id 3 | task 4669 | eval time = 139.45 ms / 2 tokens ( 139.45 ms per token, 7.17 tokens per second) 2.30.344.741 I slot print_timing: id 3 | task 4669 | total time = 427.19 ms / 150 tokens 2.30.344.741 I slot print_timing: id 3 | task 4669 | graphs reused = 3581 2.30.344.742 I slot print_timing: id 3 | task 4669 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.344.775 I slot release: id 3 | task 4669 | stop processing: n_tokens = 1301, truncated = 0 2.30.360.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 150246369 2.30.401.190 I slot launch_slot_: id 0 | task 4675 | processing task, is_child = 0 2.30.401.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 2.30.449.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.30.499.698 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 150246855 2.30.499.995 I slot launch_slot_: id 2 | task 4676 | processing task, is_child = 0 2.30.500.070 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 150247371 2.30.500.301 I slot launch_slot_: id 3 | task 4677 | processing task, is_child = 0 2.30.831.956 I slot print_timing: id 1 | task 4670 | prompt eval time = 764.87 ms / 792 tokens ( 0.97 ms per token, 1035.47 tokens per second) 2.30.831.962 I slot print_timing: id 1 | task 4670 | eval time = 165.25 ms / 2 tokens ( 165.25 ms per token, 6.05 tokens per second) 2.30.831.963 I slot print_timing: id 1 | task 4670 | total time = 930.12 ms / 794 tokens 2.30.831.965 I slot print_timing: id 1 | task 4670 | graphs reused = 3581 2.30.831.966 I slot print_timing: id 1 | task 4670 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.832.010 I slot release: id 1 | task 4670 | stop processing: n_tokens = 793, truncated = 0 2.30.883.817 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 150734606 2.30.883.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 2.30.937.891 I slot launch_slot_: id 1 | task 4681 | processing task, is_child = 0 2.31.717.039 I slot print_timing: id 0 | task 4675 | prompt eval time = 1133.33 ms / 808 tokens ( 1.40 ms per token, 712.94 tokens per second) 2.31.717.044 I slot print_timing: id 0 | task 4675 | eval time = 83.39 ms / 2 tokens ( 83.39 ms per token, 11.99 tokens per second) 2.31.717.045 I slot print_timing: id 0 | task 4675 | total time = 1216.71 ms / 810 tokens 2.31.717.046 I slot print_timing: id 0 | task 4675 | graphs reused = 3581 2.31.717.047 I slot print_timing: id 0 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.717.091 I slot release: id 0 | task 4675 | stop processing: n_tokens = 809, truncated = 0 2.31.717.443 I slot print_timing: id 2 | task 4676 | prompt eval time = 1112.82 ms / 859 tokens ( 1.30 ms per token, 771.91 tokens per second) 2.31.717.447 I slot print_timing: id 2 | task 4676 | eval time = 83.15 ms / 2 tokens ( 83.15 ms per token, 12.03 tokens per second) 2.31.717.448 I slot print_timing: id 2 | task 4676 | total time = 1195.97 ms / 861 tokens 2.31.717.448 I slot print_timing: id 2 | task 4676 | graphs reused = 3581 2.31.717.449 I slot print_timing: id 2 | task 4676 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.717.484 I slot release: id 2 | task 4676 | stop processing: n_tokens = 860, truncated = 0 2.31.717.823 I slot print_timing: id 3 | task 4677 | prompt eval time = 1109.88 ms / 891 tokens ( 1.25 ms per token, 802.79 tokens per second) 2.31.717.827 I slot print_timing: id 3 | task 4677 | eval time = 82.95 ms / 2 tokens ( 82.95 ms per token, 12.06 tokens per second) 2.31.717.827 I slot print_timing: id 3 | task 4677 | total time = 1192.83 ms / 893 tokens 2.31.717.828 I slot print_timing: id 3 | task 4677 | graphs reused = 3581 2.31.717.828 I slot print_timing: id 3 | task 4677 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.717.856 I slot release: id 3 | task 4677 | stop processing: n_tokens = 892, truncated = 0 2.31.744.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 151619687 2.31.744.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.400 MiB) 2.31.790.067 I slot launch_slot_: id 0 | task 4687 | processing task, is_child = 0 2.31.790.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 2.31.841.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.181 MiB) 2.31.890.718 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 151620079 2.31.890.912 I slot launch_slot_: id 2 | task 4688 | processing task, is_child = 0 2.31.890.972 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 151620452 2.31.891.119 I slot launch_slot_: id 3 | task 4689 | processing task, is_child = 0 2.32.043.032 I slot print_timing: id 1 | task 4681 | prompt eval time = 794.35 ms / 790 tokens ( 1.01 ms per token, 994.53 tokens per second) 2.32.043.038 I slot print_timing: id 1 | task 4681 | eval time = 298.36 ms / 2 tokens ( 298.36 ms per token, 3.35 tokens per second) 2.32.043.039 I slot print_timing: id 1 | task 4681 | total time = 1092.71 ms / 792 tokens 2.32.043.040 I slot print_timing: id 1 | task 4681 | graphs reused = 3581 2.32.043.041 I slot print_timing: id 1 | task 4681 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.043.088 I slot release: id 1 | task 4681 | stop processing: n_tokens = 791, truncated = 0 2.32.159.853 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 2.32.159.984 I slot launch_slot_: id 1 | task 4692 | processing task, is_child = 0 2.32.769.610 I slot print_timing: id 1 | task 4692 | prompt eval time = 494.97 ms / 147 tokens ( 3.37 ms per token, 296.99 tokens per second) 2.32.769.615 I slot print_timing: id 1 | task 4692 | eval time = 114.63 ms / 2 tokens ( 114.63 ms per token, 8.72 tokens per second) 2.32.769.616 I slot print_timing: id 1 | task 4692 | total time = 609.60 ms / 149 tokens 2.32.769.616 I slot print_timing: id 1 | task 4692 | graphs reused = 3581 2.32.769.617 I slot print_timing: id 1 | task 4692 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.769.658 I slot release: id 1 | task 4692 | stop processing: n_tokens = 803, truncated = 0 2.32.811.584 I slot print_timing: id 2 | task 4688 | prompt eval time = 875.68 ms / 778 tokens ( 1.13 ms per token, 888.45 tokens per second) 2.32.811.589 I slot print_timing: id 2 | task 4688 | eval time = 41.28 ms / 2 tokens ( 41.28 ms per token, 24.23 tokens per second) 2.32.811.590 I slot print_timing: id 2 | task 4688 | total time = 916.96 ms / 780 tokens 2.32.811.591 I slot print_timing: id 2 | task 4688 | graphs reused = 3581 2.32.811.592 I slot print_timing: id 2 | task 4688 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.811.631 I slot release: id 2 | task 4688 | stop processing: n_tokens = 779, truncated = 0 2.32.811.939 I slot print_timing: id 3 | task 4689 | prompt eval time = 872.79 ms / 774 tokens ( 1.13 ms per token, 886.81 tokens per second) 2.32.811.943 I slot print_timing: id 3 | task 4689 | eval time = 41.05 ms / 2 tokens ( 41.05 ms per token, 24.36 tokens per second) 2.32.811.943 I slot print_timing: id 3 | task 4689 | total time = 913.84 ms / 776 tokens 2.32.811.944 I slot print_timing: id 3 | task 4689 | graphs reused = 3581 2.32.811.944 I slot print_timing: id 3 | task 4689 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.811.967 I slot release: id 3 | task 4689 | stop processing: n_tokens = 775, truncated = 0 2.32.811.977 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 152672254 2.32.812.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.950 MiB) 2.32.863.258 I slot launch_slot_: id 1 | task 4697 | processing task, is_child = 0 2.32.863.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.245 MiB) 2.32.907.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.587 MiB) 2.32.958.335 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 152714227 2.32.958.520 I slot launch_slot_: id 2 | task 4698 | processing task, is_child = 0 2.32.958.573 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 152714563 2.32.958.716 I slot launch_slot_: id 3 | task 4699 | processing task, is_child = 0 2.33.115.834 I slot print_timing: id 0 | task 4687 | prompt eval time = 920.16 ms / 855 tokens ( 1.08 ms per token, 929.18 tokens per second) 2.33.115.841 I slot print_timing: id 0 | task 4687 | eval time = 304.53 ms / 2 tokens ( 304.53 ms per token, 3.28 tokens per second) 2.33.115.842 I slot print_timing: id 0 | task 4687 | total time = 1224.69 ms / 857 tokens 2.33.115.843 I slot print_timing: id 0 | task 4687 | graphs reused = 3581 2.33.115.844 I slot print_timing: id 0 | task 4687 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.115.893 I slot release: id 0 | task 4687 | stop processing: n_tokens = 856, truncated = 0 2.33.152.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 153018489 2.33.152.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 2.33.261.893 I slot launch_slot_: id 0 | task 4702 | processing task, is_child = 0 2.34.189.478 I slot print_timing: id 1 | task 4697 | prompt eval time = 1172.18 ms / 971 tokens ( 1.21 ms per token, 828.37 tokens per second) 2.34.189.484 I slot print_timing: id 1 | task 4697 | eval time = 58.56 ms / 2 tokens ( 58.56 ms per token, 17.08 tokens per second) 2.34.189.486 I slot print_timing: id 1 | task 4697 | total time = 1230.74 ms / 973 tokens 2.34.189.486 I slot print_timing: id 1 | task 4697 | graphs reused = 3581 2.34.189.487 I slot print_timing: id 1 | task 4697 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.189.532 I slot release: id 1 | task 4697 | stop processing: n_tokens = 972, truncated = 0 2.34.189.853 I slot print_timing: id 2 | task 4698 | prompt eval time = 1169.34 ms / 964 tokens ( 1.21 ms per token, 824.40 tokens per second) 2.34.189.856 I slot print_timing: id 2 | task 4698 | eval time = 58.26 ms / 2 tokens ( 58.26 ms per token, 17.17 tokens per second) 2.34.189.857 I slot print_timing: id 2 | task 4698 | total time = 1227.60 ms / 966 tokens 2.34.189.858 I slot print_timing: id 2 | task 4698 | graphs reused = 3581 2.34.189.858 I slot print_timing: id 2 | task 4698 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.189.885 I slot release: id 2 | task 4698 | stop processing: n_tokens = 965, truncated = 0 2.34.190.203 I slot print_timing: id 3 | task 4699 | prompt eval time = 1166.51 ms / 944 tokens ( 1.24 ms per token, 809.25 tokens per second) 2.34.190.206 I slot print_timing: id 3 | task 4699 | eval time = 57.96 ms / 2 tokens ( 57.96 ms per token, 17.25 tokens per second) 2.34.190.207 I slot print_timing: id 3 | task 4699 | total time = 1224.47 ms / 946 tokens 2.34.190.208 I slot print_timing: id 3 | task 4699 | graphs reused = 3581 2.34.190.208 I slot print_timing: id 3 | task 4699 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.190.231 I slot release: id 3 | task 4699 | stop processing: n_tokens = 945, truncated = 0 2.34.216.402 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 2.34.216.504 I slot launch_slot_: id 1 | task 4709 | processing task, is_child = 0 2.34.216.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.458 MiB) 2.34.268.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 2.34.315.504 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 154092481 2.34.315.707 I slot launch_slot_: id 2 | task 4710 | processing task, is_child = 0 2.34.315.768 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 154092827 2.34.315.923 I slot launch_slot_: id 3 | task 4711 | processing task, is_child = 0 2.34.466.732 I slot print_timing: id 0 | task 4702 | prompt eval time = 954.49 ms / 947 tokens ( 1.01 ms per token, 992.16 tokens per second) 2.34.466.738 I slot print_timing: id 0 | task 4702 | eval time = 250.33 ms / 2 tokens ( 250.33 ms per token, 3.99 tokens per second) 2.34.466.739 I slot print_timing: id 0 | task 4702 | total time = 1204.81 ms / 949 tokens 2.34.466.740 I slot print_timing: id 0 | task 4702 | graphs reused = 3581 2.34.466.741 I slot print_timing: id 0 | task 4702 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.466.790 I slot release: id 0 | task 4702 | stop processing: n_tokens = 948, truncated = 0 2.34.593.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 154369386 2.34.593.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.770 MiB) 2.34.641.208 I slot launch_slot_: id 0 | task 4714 | processing task, is_child = 0 2.34.916.683 I slot print_timing: id 1 | task 4709 | prompt eval time = 277.86 ms / 133 tokens ( 2.09 ms per token, 478.66 tokens per second) 2.34.916.690 I slot print_timing: id 1 | task 4709 | eval time = 322.88 ms / 2 tokens ( 322.88 ms per token, 3.10 tokens per second) 2.34.916.691 I slot print_timing: id 1 | task 4709 | total time = 600.74 ms / 135 tokens 2.34.916.692 I slot print_timing: id 1 | task 4709 | graphs reused = 3581 2.34.916.693 I slot print_timing: id 1 | task 4709 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.916.742 I slot release: id 1 | task 4709 | stop processing: n_tokens = 970, truncated = 0 2.35.062.974 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 154819338 2.35.063.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 2.35.112.623 I slot launch_slot_: id 1 | task 4717 | processing task, is_child = 0 2.35.422.943 I slot print_timing: id 2 | task 4710 | prompt eval time = 899.96 ms / 799 tokens ( 1.13 ms per token, 887.82 tokens per second) 2.35.422.949 I slot print_timing: id 2 | task 4710 | eval time = 187.71 ms / 2 tokens ( 187.71 ms per token, 5.33 tokens per second) 2.35.422.950 I slot print_timing: id 2 | task 4710 | total time = 1087.67 ms / 801 tokens 2.35.422.951 I slot print_timing: id 2 | task 4710 | graphs reused = 3581 2.35.422.952 I slot print_timing: id 2 | task 4710 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.422.999 I slot release: id 2 | task 4710 | stop processing: n_tokens = 800, truncated = 0 2.35.423.426 I slot print_timing: id 3 | task 4711 | prompt eval time = 897.29 ms / 798 tokens ( 1.12 ms per token, 889.35 tokens per second) 2.35.423.432 I slot print_timing: id 3 | task 4711 | eval time = 187.47 ms / 2 tokens ( 187.47 ms per token, 5.33 tokens per second) 2.35.423.433 I slot print_timing: id 3 | task 4711 | total time = 1084.76 ms / 800 tokens 2.35.423.434 I slot print_timing: id 3 | task 4711 | graphs reused = 3581 2.35.423.436 I slot print_timing: id 3 | task 4711 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.423.482 I slot release: id 3 | task 4711 | stop processing: n_tokens = 799, truncated = 0 2.35.492.524 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 155325594 2.35.492.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.679 MiB) 2.35.537.084 I slot launch_slot_: id 2 | task 4721 | processing task, is_child = 0 2.35.537.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.745 MiB) 2.35.581.507 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 155326078 2.35.581.683 I slot launch_slot_: id 3 | task 4722 | processing task, is_child = 0 2.35.984.101 I slot print_timing: id 0 | task 4714 | prompt eval time = 1158.80 ms / 975 tokens ( 1.19 ms per token, 841.39 tokens per second) 2.35.984.108 I slot print_timing: id 0 | task 4714 | eval time = 184.07 ms / 2 tokens ( 184.07 ms per token, 5.43 tokens per second) 2.35.984.109 I slot print_timing: id 0 | task 4714 | total time = 1342.87 ms / 977 tokens 2.35.984.110 I slot print_timing: id 0 | task 4714 | graphs reused = 3581 2.35.984.111 I slot print_timing: id 0 | task 4714 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.984.163 I slot release: id 0 | task 4714 | stop processing: n_tokens = 976, truncated = 0 2.36.080.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 155886759 2.36.080.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.621 MiB) 2.36.122.815 I slot launch_slot_: id 0 | task 4726 | processing task, is_child = 0 2.36.387.253 I slot print_timing: id 1 | task 4717 | prompt eval time = 967.92 ms / 953 tokens ( 1.02 ms per token, 984.58 tokens per second) 2.36.387.259 I slot print_timing: id 1 | task 4717 | eval time = 306.67 ms / 2 tokens ( 306.67 ms per token, 3.26 tokens per second) 2.36.387.260 I slot print_timing: id 1 | task 4717 | total time = 1274.60 ms / 955 tokens 2.36.387.261 I slot print_timing: id 1 | task 4717 | graphs reused = 3581 2.36.387.261 I slot print_timing: id 1 | task 4717 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.387.307 I slot release: id 1 | task 4717 | stop processing: n_tokens = 954, truncated = 0 2.36.540.043 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 156289903 2.36.540.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.338 MiB) 2.36.586.659 I slot launch_slot_: id 1 | task 4729 | processing task, is_child = 0 2.36.875.869 I slot print_timing: id 2 | task 4721 | prompt eval time = 1100.20 ms / 930 tokens ( 1.18 ms per token, 845.30 tokens per second) 2.36.875.875 I slot print_timing: id 2 | task 4721 | eval time = 173.86 ms / 2 tokens ( 173.86 ms per token, 5.75 tokens per second) 2.36.875.876 I slot print_timing: id 2 | task 4721 | total time = 1274.06 ms / 932 tokens 2.36.875.877 I slot print_timing: id 2 | task 4721 | graphs reused = 3581 2.36.875.878 I slot print_timing: id 2 | task 4721 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.875.931 I slot release: id 2 | task 4721 | stop processing: n_tokens = 931, truncated = 0 2.36.876.263 I slot print_timing: id 3 | task 4722 | prompt eval time = 1097.50 ms / 961 tokens ( 1.14 ms per token, 875.63 tokens per second) 2.36.876.266 I slot print_timing: id 3 | task 4722 | eval time = 173.54 ms / 2 tokens ( 173.54 ms per token, 5.76 tokens per second) 2.36.876.266 I slot print_timing: id 3 | task 4722 | total time = 1271.04 ms / 963 tokens 2.36.876.267 I slot print_timing: id 3 | task 4722 | graphs reused = 3581 2.36.876.268 I slot print_timing: id 3 | task 4722 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.876.301 I slot release: id 3 | task 4722 | stop processing: n_tokens = 962, truncated = 0 2.36.939.505 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 2.36.939.615 I slot launch_slot_: id 2 | task 4733 | processing task, is_child = 0 2.36.939.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.526 MiB) 2.36.997.026 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 156778897 2.36.997.458 I slot launch_slot_: id 3 | task 4734 | processing task, is_child = 0 2.37.392.333 I slot print_timing: id 0 | task 4726 | prompt eval time = 1118.59 ms / 898 tokens ( 1.25 ms per token, 802.80 tokens per second) 2.37.392.339 I slot print_timing: id 0 | task 4726 | eval time = 150.90 ms / 2 tokens ( 150.90 ms per token, 6.63 tokens per second) 2.37.392.340 I slot print_timing: id 0 | task 4726 | total time = 1269.49 ms / 900 tokens 2.37.392.340 I slot print_timing: id 0 | task 4726 | graphs reused = 3581 2.37.392.341 I slot print_timing: id 0 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.392.388 I slot release: id 0 | task 4726 | stop processing: n_tokens = 899, truncated = 0 2.37.458.682 I slot print_timing: id 2 | task 4733 | prompt eval time = 356.62 ms / 120 tokens ( 2.97 ms per token, 336.49 tokens per second) 2.37.458.687 I slot print_timing: id 2 | task 4733 | eval time = 65.67 ms / 2 tokens ( 65.67 ms per token, 15.23 tokens per second) 2.37.458.688 I slot print_timing: id 2 | task 4733 | total time = 422.29 ms / 122 tokens 2.37.458.690 I slot print_timing: id 2 | task 4733 | graphs reused = 3581 2.37.458.690 I slot print_timing: id 2 | task 4733 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.458.735 I slot release: id 2 | task 4733 | stop processing: n_tokens = 900, truncated = 0 2.37.458.746 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 157294984 2.37.458.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.773 MiB) 2.37.514.543 I slot launch_slot_: id 0 | task 4738 | processing task, is_child = 0 2.37.514.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.839 MiB) 2.37.570.137 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 157361331 2.37.570.357 I slot launch_slot_: id 2 | task 4739 | processing task, is_child = 0 2.37.797.692 I slot print_timing: id 1 | task 4729 | prompt eval time = 871.71 ms / 902 tokens ( 0.97 ms per token, 1034.75 tokens per second) 2.37.797.697 I slot print_timing: id 1 | task 4729 | eval time = 339.28 ms / 2 tokens ( 339.28 ms per token, 2.95 tokens per second) 2.37.797.699 I slot print_timing: id 1 | task 4729 | total time = 1210.99 ms / 904 tokens 2.37.797.700 I slot print_timing: id 1 | task 4729 | graphs reused = 3581 2.37.797.701 I slot print_timing: id 1 | task 4729 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.797.755 I slot release: id 1 | task 4729 | stop processing: n_tokens = 903, truncated = 0 2.37.950.497 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 157700351 2.37.950.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 2.38.019.078 I slot launch_slot_: id 1 | task 4742 | processing task, is_child = 0 2.38.538.334 I slot print_timing: id 3 | task 4734 | prompt eval time = 1206.08 ms / 890 tokens ( 1.36 ms per token, 737.93 tokens per second) 2.38.538.339 I slot print_timing: id 3 | task 4734 | eval time = 276.22 ms / 2 tokens ( 276.22 ms per token, 3.62 tokens per second) 2.38.538.340 I slot print_timing: id 3 | task 4734 | total time = 1482.30 ms / 892 tokens 2.38.538.341 I slot print_timing: id 3 | task 4734 | graphs reused = 3581 2.38.538.342 I slot print_timing: id 3 | task 4734 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.538.390 I slot release: id 3 | task 4734 | stop processing: n_tokens = 891, truncated = 0 2.38.689.478 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 158440986 2.38.689.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.088 MiB) 2.38.746.877 I slot launch_slot_: id 3 | task 4746 | processing task, is_child = 0 2.39.215.875 I slot print_timing: id 0 | task 4738 | prompt eval time = 1399.10 ms / 1225 tokens ( 1.14 ms per token, 875.57 tokens per second) 2.39.215.880 I slot print_timing: id 0 | task 4738 | eval time = 246.40 ms / 2 tokens ( 246.40 ms per token, 4.06 tokens per second) 2.39.215.882 I slot print_timing: id 0 | task 4738 | total time = 1645.49 ms / 1227 tokens 2.39.215.883 I slot print_timing: id 0 | task 4738 | graphs reused = 3581 2.39.215.883 I slot print_timing: id 0 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.215.937 I slot release: id 0 | task 4738 | stop processing: n_tokens = 1226, truncated = 0 2.39.216.279 I slot print_timing: id 2 | task 4739 | prompt eval time = 1396.16 ms / 1236 tokens ( 1.13 ms per token, 885.28 tokens per second) 2.39.216.282 I slot print_timing: id 2 | task 4739 | eval time = 246.09 ms / 2 tokens ( 246.09 ms per token, 4.06 tokens per second) 2.39.216.283 I slot print_timing: id 2 | task 4739 | total time = 1642.26 ms / 1238 tokens 2.39.216.283 I slot print_timing: id 2 | task 4739 | graphs reused = 3581 2.39.216.285 I slot print_timing: id 2 | task 4739 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.216.320 I slot release: id 2 | task 4739 | stop processing: n_tokens = 1237, truncated = 0 2.39.501.453 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 159118533 2.39.501.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.836 MiB) 2.39.558.711 I slot launch_slot_: id 0 | task 4750 | processing task, is_child = 0 2.39.558.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 2.39.614.999 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 159118916 2.39.615.216 I slot launch_slot_: id 2 | task 4751 | processing task, is_child = 0 2.39.908.225 I slot print_timing: id 1 | task 4742 | prompt eval time = 1482.33 ms / 1290 tokens ( 1.15 ms per token, 870.25 tokens per second) 2.39.908.230 I slot print_timing: id 1 | task 4742 | eval time = 406.77 ms / 2 tokens ( 406.77 ms per token, 2.46 tokens per second) 2.39.908.232 I slot print_timing: id 1 | task 4742 | total time = 1889.10 ms / 1292 tokens 2.39.908.233 I slot print_timing: id 1 | task 4742 | graphs reused = 3581 2.39.908.234 I slot print_timing: id 1 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.908.292 I slot release: id 1 | task 4742 | stop processing: n_tokens = 1291, truncated = 0 2.40.229.674 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 159810889 2.40.229.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 2.40.306.370 I slot launch_slot_: id 1 | task 4754 | processing task, is_child = 0 2.41.608.066 I slot print_timing: id 3 | task 4746 | prompt eval time = 2436.16 ms / 2587 tokens ( 0.94 ms per token, 1061.92 tokens per second) 2.41.608.071 I slot print_timing: id 3 | task 4746 | eval time = 394.57 ms / 2 tokens ( 394.57 ms per token, 2.53 tokens per second) 2.41.608.072 I slot print_timing: id 3 | task 4746 | total time = 2830.73 ms / 2589 tokens 2.41.608.074 I slot print_timing: id 3 | task 4746 | graphs reused = 3581 2.41.608.075 I slot print_timing: id 3 | task 4746 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.608.191 I slot release: id 3 | task 4746 | stop processing: n_tokens = 2588, truncated = 0 2.41.815.930 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 161510788 2.41.816.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.618 MiB) 2.41.820.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.681 MiB) 2.41.891.990 I slot launch_slot_: id 3 | task 4759 | processing task, is_child = 0 2.42.092.637 I slot print_timing: id 0 | task 4750 | prompt eval time = 2200.68 ms / 2500 tokens ( 0.88 ms per token, 1136.01 tokens per second) 2.42.092.643 I slot print_timing: id 0 | task 4750 | eval time = 276.71 ms / 2 tokens ( 276.71 ms per token, 3.61 tokens per second) 2.42.092.644 I slot print_timing: id 0 | task 4750 | total time = 2477.39 ms / 2502 tokens 2.42.092.646 I slot print_timing: id 0 | task 4750 | graphs reused = 3581 2.42.092.648 I slot print_timing: id 0 | task 4750 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.092.762 I slot release: id 0 | task 4750 | stop processing: n_tokens = 2501, truncated = 0 2.42.220.286 I slot print_timing: id 2 | task 4751 | prompt eval time = 2474.69 ms / 2742 tokens ( 0.90 ms per token, 1108.02 tokens per second) 2.42.220.293 I slot print_timing: id 2 | task 4751 | eval time = 126.88 ms / 2 tokens ( 126.88 ms per token, 7.88 tokens per second) 2.42.220.294 I slot print_timing: id 2 | task 4751 | total time = 2601.57 ms / 2744 tokens 2.42.220.295 I slot print_timing: id 2 | task 4751 | graphs reused = 3581 2.42.220.296 I slot print_timing: id 2 | task 4751 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.220.411 I slot release: id 2 | task 4751 | stop processing: n_tokens = 2743, truncated = 0 2.42.220.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 161995359 2.42.220.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.253 MiB) 2.42.276.739 I slot launch_slot_: id 0 | task 4762 | processing task, is_child = 0 2.42.276.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.657 MiB) 2.42.335.284 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 162123008 2.42.335.571 I slot launch_slot_: id 2 | task 4763 | processing task, is_child = 0 2.42.638.491 I slot print_timing: id 1 | task 4754 | prompt eval time = 1913.58 ms / 2655 tokens ( 0.72 ms per token, 1387.45 tokens per second) 2.42.638.497 I slot print_timing: id 1 | task 4754 | eval time = 418.49 ms / 2 tokens ( 418.49 ms per token, 2.39 tokens per second) 2.42.638.498 I slot print_timing: id 1 | task 4754 | total time = 2332.07 ms / 2657 tokens 2.42.638.499 I slot print_timing: id 1 | task 4754 | graphs reused = 3581 2.42.638.500 I slot print_timing: id 1 | task 4754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.638.614 I slot release: id 1 | task 4754 | stop processing: n_tokens = 2656, truncated = 0 2.42.840.497 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 162541211 2.42.840.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.939 MiB) 2.42.902.121 I slot launch_slot_: id 1 | task 4766 | processing task, is_child = 0 2.44.212.310 I slot print_timing: id 3 | task 4759 | prompt eval time = 2197.21 ms / 1779 tokens ( 1.24 ms per token, 809.66 tokens per second) 2.44.212.318 I slot print_timing: id 3 | task 4759 | eval time = 98.12 ms / 2 tokens ( 98.12 ms per token, 10.19 tokens per second) 2.44.212.319 I slot print_timing: id 3 | task 4759 | total time = 2295.33 ms / 1781 tokens 2.44.212.321 I slot print_timing: id 3 | task 4759 | graphs reused = 3581 2.44.212.322 I slot print_timing: id 3 | task 4759 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.212.409 I slot release: id 3 | task 4759 | stop processing: n_tokens = 1780, truncated = 0 2.44.355.250 I slot print_timing: id 0 | task 4762 | prompt eval time = 1875.88 ms / 1841 tokens ( 1.02 ms per token, 981.41 tokens per second) 2.44.355.256 I slot print_timing: id 0 | task 4762 | eval time = 143.78 ms / 2 tokens ( 143.78 ms per token, 6.96 tokens per second) 2.44.355.257 I slot print_timing: id 0 | task 4762 | total time = 2019.65 ms / 1843 tokens 2.44.355.258 I slot print_timing: id 0 | task 4762 | graphs reused = 3581 2.44.355.259 I slot print_timing: id 0 | task 4762 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.355.346 I slot release: id 0 | task 4762 | stop processing: n_tokens = 1842, truncated = 0 2.44.355.654 I slot print_timing: id 2 | task 4763 | prompt eval time = 1872.77 ms / 2048 tokens ( 0.91 ms per token, 1093.56 tokens per second) 2.44.355.658 I slot print_timing: id 2 | task 4763 | eval time = 143.62 ms / 2 tokens ( 143.62 ms per token, 6.96 tokens per second) 2.44.355.658 I slot print_timing: id 2 | task 4763 | total time = 2016.39 ms / 2050 tokens 2.44.355.659 I slot print_timing: id 2 | task 4763 | graphs reused = 3581 2.44.355.660 I slot print_timing: id 2 | task 4763 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.355.721 I slot release: id 2 | task 4763 | stop processing: n_tokens = 2049, truncated = 0 2.44.355.737 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.806 2.44.355.880 I slot launch_slot_: id 0 | task 4772 | processing task, is_child = 0 2.44.356.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.052 MiB) 2.44.418.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.553 MiB) 2.44.480.688 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.724 2.44.480.844 I slot launch_slot_: id 2 | task 4773 | processing task, is_child = 0 2.44.480.953 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1780, t_last = 164115006 2.44.481.142 I slot launch_slot_: id 3 | task 4774 | processing task, is_child = 0 2.44.903.364 I slot print_timing: id 1 | task 4766 | prompt eval time = 1887.73 ms / 1852 tokens ( 1.02 ms per token, 981.07 tokens per second) 2.44.903.369 I slot print_timing: id 1 | task 4766 | eval time = 113.47 ms / 2 tokens ( 113.47 ms per token, 8.81 tokens per second) 2.44.903.371 I slot print_timing: id 1 | task 4766 | total time = 2001.20 ms / 1854 tokens 2.44.903.371 I slot print_timing: id 1 | task 4766 | graphs reused = 3581 2.44.903.372 I slot print_timing: id 1 | task 4766 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.903.457 I slot release: id 1 | task 4766 | stop processing: n_tokens = 1853, truncated = 0 2.45.046.386 I slot print_timing: id 0 | task 4772 | prompt eval time = 421.88 ms / 515 tokens ( 0.82 ms per token, 1220.72 tokens per second) 2.45.046.392 I slot print_timing: id 0 | task 4772 | eval time = 143.34 ms / 2 tokens ( 143.34 ms per token, 6.98 tokens per second) 2.45.046.393 I slot print_timing: id 0 | task 4772 | total time = 565.22 ms / 517 tokens 2.45.046.394 I slot print_timing: id 0 | task 4772 | graphs reused = 3581 2.45.046.395 I slot print_timing: id 0 | task 4772 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.046.487 I slot release: id 0 | task 4772 | stop processing: n_tokens = 1963, truncated = 0 2.45.046.834 I slot print_timing: id 2 | task 4773 | prompt eval time = 394.76 ms / 334 tokens ( 1.18 ms per token, 846.08 tokens per second) 2.45.046.837 I slot print_timing: id 2 | task 4773 | eval time = 142.60 ms / 2 tokens ( 142.60 ms per token, 7.01 tokens per second) 2.45.046.838 I slot print_timing: id 2 | task 4773 | total time = 537.37 ms / 336 tokens 2.45.046.838 I slot print_timing: id 2 | task 4773 | graphs reused = 3581 2.45.046.839 I slot print_timing: id 2 | task 4773 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.046.891 I slot release: id 2 | task 4773 | stop processing: n_tokens = 1782, truncated = 0 2.45.046.904 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 164806054 2.45.047.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.148 MiB) 2.45.051.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.149 MiB) 2.45.112.877 I slot launch_slot_: id 1 | task 4778 | processing task, is_child = 0 2.45.112.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.365 MiB) 2.45.174.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.615 MiB) 2.45.220.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1963, t_last = 164949084 2.45.220.279 I slot launch_slot_: id 0 | task 4779 | processing task, is_child = 0 2.45.220.375 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 164949487 2.45.220.567 I slot launch_slot_: id 2 | task 4780 | processing task, is_child = 0 2.45.873.459 I slot print_timing: id 3 | task 4774 | prompt eval time = 1002.30 ms / 726 tokens ( 1.38 ms per token, 724.34 tokens per second) 2.45.873.465 I slot print_timing: id 3 | task 4774 | eval time = 339.43 ms / 2 tokens ( 339.43 ms per token, 2.95 tokens per second) 2.45.873.466 I slot print_timing: id 3 | task 4774 | total time = 1341.73 ms / 728 tokens 2.45.873.467 I slot print_timing: id 3 | task 4774 | graphs reused = 3581 2.45.873.468 I slot print_timing: id 3 | task 4774 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.873.510 I slot release: id 3 | task 4774 | stop processing: n_tokens = 727, truncated = 0 2.46.006.867 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 2.46.007.044 I slot launch_slot_: id 3 | task 4785 | processing task, is_child = 0 2.46.171.973 I slot print_timing: id 0 | task 4779 | prompt eval time = 906.88 ms / 725 tokens ( 1.25 ms per token, 799.44 tokens per second) 2.46.171.978 I slot print_timing: id 0 | task 4779 | eval time = 44.51 ms / 2 tokens ( 44.51 ms per token, 22.47 tokens per second) 2.46.171.979 I slot print_timing: id 0 | task 4779 | total time = 951.39 ms / 727 tokens 2.46.171.980 I slot print_timing: id 0 | task 4779 | graphs reused = 3581 2.46.171.981 I slot print_timing: id 0 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.172.021 I slot release: id 0 | task 4779 | stop processing: n_tokens = 726, truncated = 0 2.46.172.333 I slot print_timing: id 1 | task 4778 | prompt eval time = 903.95 ms / 748 tokens ( 1.21 ms per token, 827.48 tokens per second) 2.46.172.337 I slot print_timing: id 1 | task 4778 | eval time = 44.15 ms / 2 tokens ( 44.15 ms per token, 22.65 tokens per second) 2.46.172.338 I slot print_timing: id 1 | task 4778 | total time = 948.10 ms / 750 tokens 2.46.172.338 I slot print_timing: id 1 | task 4778 | graphs reused = 3581 2.46.172.339 I slot print_timing: id 1 | task 4778 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.172.364 I slot release: id 1 | task 4778 | stop processing: n_tokens = 749, truncated = 0 2.46.172.665 I slot print_timing: id 2 | task 4780 | prompt eval time = 901.12 ms / 761 tokens ( 1.18 ms per token, 844.51 tokens per second) 2.46.172.667 I slot print_timing: id 2 | task 4780 | eval time = 43.77 ms / 2 tokens ( 43.77 ms per token, 22.85 tokens per second) 2.46.172.668 I slot print_timing: id 2 | task 4780 | total time = 944.89 ms / 763 tokens 2.46.172.669 I slot print_timing: id 2 | task 4780 | graphs reused = 3581 2.46.172.669 I slot print_timing: id 2 | task 4780 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.172.691 I slot release: id 2 | task 4780 | stop processing: n_tokens = 762, truncated = 0 2.46.187.442 I slot print_timing: id 3 | task 4785 | prompt eval time = 119.66 ms / 124 tokens ( 0.97 ms per token, 1036.26 tokens per second) 2.46.187.448 I slot print_timing: id 3 | task 4785 | eval time = 14.15 ms / 2 tokens ( 14.15 ms per token, 70.69 tokens per second) 2.46.187.449 I slot print_timing: id 3 | task 4785 | total time = 133.81 ms / 126 tokens 2.46.187.449 I slot print_timing: id 3 | task 4785 | graphs reused = 3581 2.46.187.450 I slot print_timing: id 3 | task 4785 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.187.482 I slot release: id 3 | task 4785 | stop processing: n_tokens = 740, truncated = 0 2.46.197.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 166074617 2.46.197.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.490 MiB) 2.46.248.348 I slot launch_slot_: id 0 | task 4789 | processing task, is_child = 0 2.46.248.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 2.46.301.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.431 MiB) 2.46.352.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.806 MiB) 2.46.398.903 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 166074960 2.46.399.094 I slot launch_slot_: id 1 | task 4790 | processing task, is_child = 0 2.46.399.191 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 166075286 2.46.399.335 I slot launch_slot_: id 2 | task 4791 | processing task, is_child = 0 2.46.399.384 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 166090078 2.46.399.511 I slot launch_slot_: id 3 | task 4792 | processing task, is_child = 0 2.47.557.610 I slot print_timing: id 0 | task 4789 | prompt eval time = 1139.16 ms / 799 tokens ( 1.43 ms per token, 701.39 tokens per second) 2.47.557.616 I slot print_timing: id 0 | task 4789 | eval time = 18.92 ms / 2 tokens ( 18.92 ms per token, 52.85 tokens per second) 2.47.557.618 I slot print_timing: id 0 | task 4789 | total time = 1158.08 ms / 801 tokens 2.47.557.618 I slot print_timing: id 0 | task 4789 | graphs reused = 3581 2.47.557.619 I slot print_timing: id 0 | task 4789 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.557.666 I slot release: id 0 | task 4789 | stop processing: n_tokens = 800, truncated = 0 2.47.557.993 I slot print_timing: id 1 | task 4790 | prompt eval time = 1136.28 ms / 798 tokens ( 1.42 ms per token, 702.29 tokens per second) 2.47.557.996 I slot print_timing: id 1 | task 4790 | eval time = 18.72 ms / 2 tokens ( 18.72 ms per token, 53.41 tokens per second) 2.47.557.997 I slot print_timing: id 1 | task 4790 | total time = 1155.01 ms / 800 tokens 2.47.557.997 I slot print_timing: id 1 | task 4790 | graphs reused = 3581 2.47.557.998 I slot print_timing: id 1 | task 4790 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.558.031 I slot release: id 1 | task 4790 | stop processing: n_tokens = 799, truncated = 0 2.47.558.386 I slot print_timing: id 2 | task 4791 | prompt eval time = 1133.49 ms / 1042 tokens ( 1.09 ms per token, 919.28 tokens per second) 2.47.558.389 I slot print_timing: id 2 | task 4791 | eval time = 18.53 ms / 2 tokens ( 18.53 ms per token, 53.97 tokens per second) 2.47.558.390 I slot print_timing: id 2 | task 4791 | total time = 1152.02 ms / 1044 tokens 2.47.558.390 I slot print_timing: id 2 | task 4791 | graphs reused = 3581 2.47.558.391 I slot print_timing: id 2 | task 4791 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.558.425 I slot release: id 2 | task 4791 | stop processing: n_tokens = 1043, truncated = 0 2.47.558.762 I slot print_timing: id 3 | task 4792 | prompt eval time = 1130.73 ms / 809 tokens ( 1.40 ms per token, 715.47 tokens per second) 2.47.558.765 I slot print_timing: id 3 | task 4792 | eval time = 18.26 ms / 2 tokens ( 18.26 ms per token, 54.77 tokens per second) 2.47.558.766 I slot print_timing: id 3 | task 4792 | total time = 1148.99 ms / 811 tokens 2.47.558.766 I slot print_timing: id 3 | task 4792 | graphs reused = 3581 2.47.558.767 I slot print_timing: id 3 | task 4792 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.558.797 I slot release: id 3 | task 4792 | stop processing: n_tokens = 810, truncated = 0 2.47.572.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 167460262 2.47.572.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.900 MiB) 2.47.619.281 I slot launch_slot_: id 0 | task 4800 | processing task, is_child = 0 2.47.619.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.588 MiB) 2.47.671.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 2.47.717.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 2.47.763.334 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 167460626 2.47.763.538 I slot launch_slot_: id 1 | task 4801 | processing task, is_child = 0 2.47.763.652 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 167461021 2.47.763.811 I slot launch_slot_: id 2 | task 4802 | processing task, is_child = 0 2.47.763.863 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 167461393 2.47.763.996 I slot launch_slot_: id 3 | task 4803 | processing task, is_child = 0 2.48.909.236 I slot print_timing: id 0 | task 4800 | prompt eval time = 1126.17 ms / 901 tokens ( 1.25 ms per token, 800.05 tokens per second) 2.48.909.242 I slot print_timing: id 0 | task 4800 | eval time = 19.05 ms / 2 tokens ( 19.05 ms per token, 52.50 tokens per second) 2.48.909.243 I slot print_timing: id 0 | task 4800 | total time = 1145.22 ms / 903 tokens 2.48.909.244 I slot print_timing: id 0 | task 4800 | graphs reused = 3582 2.48.909.245 I slot print_timing: id 0 | task 4800 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.909.293 I slot release: id 0 | task 4800 | stop processing: n_tokens = 902, truncated = 0 2.48.909.585 I slot print_timing: id 1 | task 4801 | prompt eval time = 1123.10 ms / 839 tokens ( 1.34 ms per token, 747.04 tokens per second) 2.48.909.588 I slot print_timing: id 1 | task 4801 | eval time = 18.84 ms / 2 tokens ( 18.84 ms per token, 53.08 tokens per second) 2.48.909.588 I slot print_timing: id 1 | task 4801 | total time = 1141.94 ms / 841 tokens 2.48.909.589 I slot print_timing: id 1 | task 4801 | graphs reused = 3582 2.48.909.589 I slot print_timing: id 1 | task 4801 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.909.616 I slot release: id 1 | task 4801 | stop processing: n_tokens = 840, truncated = 0 2.48.909.909 I slot print_timing: id 2 | task 4802 | prompt eval time = 1120.04 ms / 910 tokens ( 1.23 ms per token, 812.47 tokens per second) 2.48.909.913 I slot print_timing: id 2 | task 4802 | eval time = 18.60 ms / 2 tokens ( 18.60 ms per token, 53.75 tokens per second) 2.48.909.913 I slot print_timing: id 2 | task 4802 | total time = 1138.64 ms / 912 tokens 2.48.909.914 I slot print_timing: id 2 | task 4802 | graphs reused = 3582 2.48.909.914 I slot print_timing: id 2 | task 4802 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.909.939 I slot release: id 2 | task 4802 | stop processing: n_tokens = 911, truncated = 0 2.48.910.218 I slot print_timing: id 3 | task 4803 | prompt eval time = 1116.94 ms / 845 tokens ( 1.32 ms per token, 756.53 tokens per second) 2.48.910.221 I slot print_timing: id 3 | task 4803 | eval time = 18.36 ms / 2 tokens ( 18.36 ms per token, 54.47 tokens per second) 2.48.910.221 I slot print_timing: id 3 | task 4803 | total time = 1135.30 ms / 847 tokens 2.48.910.222 I slot print_timing: id 3 | task 4803 | graphs reused = 3582 2.48.910.222 I slot print_timing: id 3 | task 4803 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.910.244 I slot release: id 3 | task 4803 | stop processing: n_tokens = 846, truncated = 0 2.48.923.175 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.833 2.48.923.303 I slot launch_slot_: id 0 | task 4811 | processing task, is_child = 0 2.48.923.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.775 MiB) 2.48.967.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.087 MiB) 2.49.026.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.338 MiB) 2.49.085.404 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 168812212 2.49.085.601 I slot launch_slot_: id 1 | task 4812 | processing task, is_child = 0 2.49.085.704 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 168812534 2.49.085.846 I slot launch_slot_: id 2 | task 4813 | processing task, is_child = 0 2.49.085.898 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 846, t_last = 168812840 2.49.086.029 I slot launch_slot_: id 3 | task 4814 | processing task, is_child = 0 2.49.593.271 I slot print_timing: id 0 | task 4811 | prompt eval time = 324.17 ms / 139 tokens ( 2.33 ms per token, 428.79 tokens per second) 2.49.593.276 I slot print_timing: id 0 | task 4811 | eval time = 183.05 ms / 2 tokens ( 183.05 ms per token, 5.46 tokens per second) 2.49.593.277 I slot print_timing: id 0 | task 4811 | total time = 507.22 ms / 141 tokens 2.49.593.278 I slot print_timing: id 0 | task 4811 | graphs reused = 3582 2.49.593.279 I slot print_timing: id 0 | task 4811 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.593.326 I slot release: id 0 | task 4811 | stop processing: n_tokens = 863, truncated = 0 2.49.838.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 169495922 2.49.838.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.367 MiB) 2.49.894.218 I slot launch_slot_: id 0 | task 4819 | processing task, is_child = 0 2.50.161.913 I slot print_timing: id 3 | task 4814 | prompt eval time = 953.53 ms / 688 tokens ( 1.39 ms per token, 721.53 tokens per second) 2.50.161.918 I slot print_timing: id 3 | task 4814 | eval time = 97.35 ms / 2 tokens ( 97.35 ms per token, 10.27 tokens per second) 2.50.161.920 I slot print_timing: id 3 | task 4814 | total time = 1050.88 ms / 690 tokens 2.50.161.922 I slot print_timing: id 3 | task 4814 | graphs reused = 3582 2.50.161.922 I slot print_timing: id 3 | task 4814 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.161.962 I slot release: id 3 | task 4814 | stop processing: n_tokens = 689, truncated = 0 2.50.269.440 I slot print_timing: id 1 | task 4812 | prompt eval time = 1056.89 ms / 825 tokens ( 1.28 ms per token, 780.59 tokens per second) 2.50.269.446 I slot print_timing: id 1 | task 4812 | eval time = 108.41 ms / 2 tokens ( 108.41 ms per token, 9.22 tokens per second) 2.50.269.447 I slot print_timing: id 1 | task 4812 | total time = 1165.30 ms / 827 tokens 2.50.269.448 I slot print_timing: id 1 | task 4812 | graphs reused = 3582 2.50.269.449 I slot print_timing: id 1 | task 4812 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.269.494 I slot release: id 1 | task 4812 | stop processing: n_tokens = 826, truncated = 0 2.50.269.820 I slot print_timing: id 2 | task 4813 | prompt eval time = 1054.03 ms / 851 tokens ( 1.24 ms per token, 807.38 tokens per second) 2.50.269.823 I slot print_timing: id 2 | task 4813 | eval time = 108.21 ms / 2 tokens ( 108.21 ms per token, 9.24 tokens per second) 2.50.269.824 I slot print_timing: id 2 | task 4813 | total time = 1162.24 ms / 853 tokens 2.50.269.824 I slot print_timing: id 2 | task 4813 | graphs reused = 3582 2.50.269.825 I slot print_timing: id 2 | task 4813 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.269.854 I slot release: id 2 | task 4813 | stop processing: n_tokens = 852, truncated = 0 2.50.269.865 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 170064558 2.50.305.611 I slot launch_slot_: id 3 | task 4823 | processing task, is_child = 0 2.50.305.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.399 MiB) 2.50.358.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 2.50.411.981 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 170172090 2.50.412.169 I slot launch_slot_: id 1 | task 4824 | processing task, is_child = 0 2.50.412.226 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 170172450 2.50.412.367 I slot launch_slot_: id 2 | task 4825 | processing task, is_child = 0 2.51.076.768 I slot print_timing: id 0 | task 4819 | prompt eval time = 839.48 ms / 769 tokens ( 1.09 ms per token, 916.05 tokens per second) 2.51.076.774 I slot print_timing: id 0 | task 4819 | eval time = 343.05 ms / 2 tokens ( 343.05 ms per token, 2.92 tokens per second) 2.51.076.775 I slot print_timing: id 0 | task 4819 | total time = 1182.52 ms / 771 tokens 2.51.076.776 I slot print_timing: id 0 | task 4819 | graphs reused = 3582 2.51.076.777 I slot print_timing: id 0 | task 4819 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.076.821 I slot release: id 0 | task 4819 | stop processing: n_tokens = 770, truncated = 0 2.51.203.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 170979417 2.51.203.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.117 MiB) 2.51.257.131 I slot launch_slot_: id 0 | task 4830 | processing task, is_child = 0 2.51.406.107 I slot print_timing: id 1 | task 4824 | prompt eval time = 923.97 ms / 736 tokens ( 1.26 ms per token, 796.57 tokens per second) 2.51.406.113 I slot print_timing: id 1 | task 4824 | eval time = 59.62 ms / 2 tokens ( 59.62 ms per token, 16.77 tokens per second) 2.51.406.114 I slot print_timing: id 1 | task 4824 | total time = 983.58 ms / 738 tokens 2.51.406.115 I slot print_timing: id 1 | task 4824 | graphs reused = 3582 2.51.406.115 I slot print_timing: id 1 | task 4824 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.406.157 I slot release: id 1 | task 4824 | stop processing: n_tokens = 737, truncated = 0 2.51.406.542 I slot print_timing: id 2 | task 4825 | prompt eval time = 921.14 ms / 713 tokens ( 1.29 ms per token, 774.04 tokens per second) 2.51.406.546 I slot print_timing: id 2 | task 4825 | eval time = 59.41 ms / 2 tokens ( 59.41 ms per token, 16.83 tokens per second) 2.51.406.547 I slot print_timing: id 2 | task 4825 | total time = 980.55 ms / 715 tokens 2.51.406.547 I slot print_timing: id 2 | task 4825 | graphs reused = 3582 2.51.406.548 I slot print_timing: id 2 | task 4825 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.406.577 I slot release: id 2 | task 4825 | stop processing: n_tokens = 714, truncated = 0 2.51.406.912 I slot print_timing: id 3 | task 4823 | prompt eval time = 918.34 ms / 752 tokens ( 1.22 ms per token, 818.87 tokens per second) 2.51.406.915 I slot print_timing: id 3 | task 4823 | eval time = 59.14 ms / 2 tokens ( 59.14 ms per token, 16.91 tokens per second) 2.51.406.916 I slot print_timing: id 3 | task 4823 | total time = 977.47 ms / 754 tokens 2.51.406.916 I slot print_timing: id 3 | task 4823 | graphs reused = 3582 2.51.406.917 I slot print_timing: id 3 | task 4823 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.406.945 I slot release: id 3 | task 4823 | stop processing: n_tokens = 753, truncated = 0 2.51.424.152 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.856 2.51.424.279 I slot launch_slot_: id 1 | task 4834 | processing task, is_child = 0 2.51.424.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.594 MiB) 2.51.528.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.938 MiB) 2.51.581.186 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.889 (> 0.100 thold), f_keep = 0.884 2.51.581.331 I slot launch_slot_: id 2 | task 4835 | processing task, is_child = 0 2.51.581.390 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 171309541 2.51.594.427 I slot launch_slot_: id 3 | task 4836 | processing task, is_child = 0 2.51.897.623 I slot print_timing: id 0 | task 4830 | prompt eval time = 621.54 ms / 719 tokens ( 0.86 ms per token, 1156.80 tokens per second) 2.51.897.629 I slot print_timing: id 0 | task 4830 | eval time = 18.93 ms / 2 tokens ( 18.93 ms per token, 52.82 tokens per second) 2.51.897.630 I slot print_timing: id 0 | task 4830 | total time = 640.47 ms / 721 tokens 2.51.897.631 I slot print_timing: id 0 | task 4830 | graphs reused = 3582 2.51.897.632 I slot print_timing: id 0 | task 4830 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.897.672 I slot release: id 0 | task 4830 | stop processing: n_tokens = 720, truncated = 0 2.51.897.966 I slot print_timing: id 1 | task 4834 | prompt eval time = 272.53 ms / 112 tokens ( 2.43 ms per token, 410.97 tokens per second) 2.51.897.969 I slot print_timing: id 1 | task 4834 | eval time = 18.68 ms / 2 tokens ( 18.68 ms per token, 53.53 tokens per second) 2.51.897.970 I slot print_timing: id 1 | task 4834 | total time = 291.21 ms / 114 tokens 2.51.897.970 I slot print_timing: id 1 | task 4834 | graphs reused = 3582 2.51.897.971 I slot print_timing: id 1 | task 4834 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.897.994 I slot release: id 1 | task 4834 | stop processing: n_tokens = 716, truncated = 0 2.51.898.286 I slot print_timing: id 2 | task 4835 | prompt eval time = 253.40 ms / 107 tokens ( 2.37 ms per token, 422.27 tokens per second) 2.51.898.289 I slot print_timing: id 2 | task 4835 | eval time = 18.41 ms / 2 tokens ( 18.41 ms per token, 54.32 tokens per second) 2.51.898.290 I slot print_timing: id 2 | task 4835 | total time = 271.81 ms / 109 tokens 2.51.898.290 I slot print_timing: id 2 | task 4835 | graphs reused = 3582 2.51.898.291 I slot print_timing: id 2 | task 4835 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.898.311 I slot release: id 2 | task 4835 | stop processing: n_tokens = 711, truncated = 0 2.51.898.591 I slot print_timing: id 3 | task 4836 | prompt eval time = 232.79 ms / 106 tokens ( 2.20 ms per token, 455.34 tokens per second) 2.51.898.594 I slot print_timing: id 3 | task 4836 | eval time = 18.17 ms / 2 tokens ( 18.17 ms per token, 55.03 tokens per second) 2.51.898.595 I slot print_timing: id 3 | task 4836 | total time = 250.96 ms / 108 tokens 2.51.898.595 I slot print_timing: id 3 | task 4836 | graphs reused = 3582 2.51.898.596 I slot print_timing: id 3 | task 4836 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.898.614 I slot release: id 3 | task 4836 | stop processing: n_tokens = 710, truncated = 0 2.51.912.548 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.876 2.51.912.688 I slot launch_slot_: id 0 | task 4840 | processing task, is_child = 0 2.51.948.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.626 MiB) 2.52.013.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.187 MiB) 2.52.064.368 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.881 2.52.064.515 I slot launch_slot_: id 1 | task 4841 | processing task, is_child = 0 2.52.064.611 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 2.52.064.701 I slot launch_slot_: id 2 | task 4842 | processing task, is_child = 0 2.52.064.749 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.893 2.52.064.830 I slot launch_slot_: id 3 | task 4843 | processing task, is_child = 0 2.52.381.168 I slot print_timing: id 0 | task 4840 | prompt eval time = 297.09 ms / 113 tokens ( 2.63 ms per token, 380.35 tokens per second) 2.52.381.173 I slot print_timing: id 0 | task 4840 | eval time = 19.23 ms / 2 tokens ( 19.23 ms per token, 52.01 tokens per second) 2.52.381.174 I slot print_timing: id 0 | task 4840 | total time = 316.32 ms / 115 tokens 2.52.381.175 I slot print_timing: id 0 | task 4840 | graphs reused = 3582 2.52.381.176 I slot print_timing: id 0 | task 4840 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.381.219 I slot release: id 0 | task 4840 | stop processing: n_tokens = 717, truncated = 0 2.52.381.574 I slot print_timing: id 1 | task 4841 | prompt eval time = 280.28 ms / 104 tokens ( 2.69 ms per token, 371.06 tokens per second) 2.52.381.577 I slot print_timing: id 1 | task 4841 | eval time = 18.84 ms / 2 tokens ( 18.84 ms per token, 53.06 tokens per second) 2.52.381.578 I slot print_timing: id 1 | task 4841 | total time = 299.12 ms / 106 tokens 2.52.381.578 I slot print_timing: id 1 | task 4841 | graphs reused = 3582 2.52.381.579 I slot print_timing: id 1 | task 4841 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.381.604 I slot release: id 1 | task 4841 | stop processing: n_tokens = 708, truncated = 0 2.52.381.943 I slot print_timing: id 2 | task 4842 | prompt eval time = 261.80 ms / 148 tokens ( 1.77 ms per token, 565.32 tokens per second) 2.52.381.946 I slot print_timing: id 2 | task 4842 | eval time = 18.51 ms / 2 tokens ( 18.51 ms per token, 54.03 tokens per second) 2.52.381.947 I slot print_timing: id 2 | task 4842 | total time = 280.31 ms / 150 tokens 2.52.381.947 I slot print_timing: id 2 | task 4842 | graphs reused = 3582 2.52.381.948 I slot print_timing: id 2 | task 4842 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.381.970 I slot release: id 2 | task 4842 | stop processing: n_tokens = 752, truncated = 0 2.52.382.292 I slot print_timing: id 3 | task 4843 | prompt eval time = 242.87 ms / 114 tokens ( 2.13 ms per token, 469.38 tokens per second) 2.52.382.295 I slot print_timing: id 3 | task 4843 | eval time = 18.15 ms / 2 tokens ( 18.15 ms per token, 55.09 tokens per second) 2.52.382.295 I slot print_timing: id 3 | task 4843 | total time = 261.03 ms / 116 tokens 2.52.382.296 I slot print_timing: id 3 | task 4843 | graphs reused = 3582 2.52.382.297 I slot print_timing: id 3 | task 4843 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.382.317 I slot release: id 3 | task 4843 | stop processing: n_tokens = 718, truncated = 0 2.52.396.322 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 172283815 2.52.396.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.467 MiB) 2.52.447.594 I slot launch_slot_: id 0 | task 4847 | processing task, is_child = 0 2.52.447.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 337.035 MiB) 2.52.493.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.314 MiB) 2.52.584.395 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 172284199 2.52.584.606 I slot launch_slot_: id 1 | task 4848 | processing task, is_child = 0 2.52.584.706 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.839 2.52.584.807 I slot launch_slot_: id 2 | task 4849 | processing task, is_child = 0 2.52.584.856 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 172284913 2.52.584.993 I slot launch_slot_: id 3 | task 4850 | processing task, is_child = 0 2.53.092.198 I slot print_timing: id 2 | task 4849 | prompt eval time = 370.07 ms / 106 tokens ( 3.49 ms per token, 286.43 tokens per second) 2.53.092.204 I slot print_timing: id 2 | task 4849 | eval time = 130.04 ms / 2 tokens ( 130.04 ms per token, 7.69 tokens per second) 2.53.092.205 I slot print_timing: id 2 | task 4849 | total time = 500.11 ms / 108 tokens 2.53.092.208 I slot print_timing: id 2 | task 4849 | graphs reused = 3582 2.53.092.209 I slot print_timing: id 2 | task 4849 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.092.251 I slot release: id 2 | task 4849 | stop processing: n_tokens = 710, truncated = 0 2.53.313.793 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 172994847 2.53.313.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.331 MiB) 2.53.393.905 I slot launch_slot_: id 2 | task 4855 | processing task, is_child = 0 2.53.813.816 I slot print_timing: id 0 | task 4847 | prompt eval time = 1142.27 ms / 880 tokens ( 1.30 ms per token, 770.40 tokens per second) 2.53.813.822 I slot print_timing: id 0 | task 4847 | eval time = 86.53 ms / 2 tokens ( 86.53 ms per token, 11.56 tokens per second) 2.53.813.823 I slot print_timing: id 0 | task 4847 | total time = 1228.80 ms / 882 tokens 2.53.813.823 I slot print_timing: id 0 | task 4847 | graphs reused = 3582 2.53.813.824 I slot print_timing: id 0 | task 4847 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.813.877 I slot release: id 0 | task 4847 | stop processing: n_tokens = 881, truncated = 0 2.53.814.321 I slot print_timing: id 1 | task 4848 | prompt eval time = 1139.67 ms / 896 tokens ( 1.27 ms per token, 786.19 tokens per second) 2.53.814.324 I slot print_timing: id 1 | task 4848 | eval time = 86.20 ms / 2 tokens ( 86.20 ms per token, 11.60 tokens per second) 2.53.814.326 I slot print_timing: id 1 | task 4848 | total time = 1225.87 ms / 898 tokens 2.53.814.326 I slot print_timing: id 1 | task 4848 | graphs reused = 3582 2.53.814.327 I slot print_timing: id 1 | task 4848 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.814.362 I slot release: id 1 | task 4848 | stop processing: n_tokens = 897, truncated = 0 2.53.814.818 I slot print_timing: id 3 | task 4850 | prompt eval time = 1116.92 ms / 1091 tokens ( 1.02 ms per token, 976.79 tokens per second) 2.53.814.820 I slot print_timing: id 3 | task 4850 | eval time = 85.88 ms / 2 tokens ( 85.88 ms per token, 11.64 tokens per second) 2.53.814.821 I slot print_timing: id 3 | task 4850 | total time = 1202.80 ms / 1093 tokens 2.53.814.822 I slot print_timing: id 3 | task 4850 | graphs reused = 3582 2.53.814.822 I slot print_timing: id 3 | task 4850 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.814.857 I slot release: id 3 | task 4850 | stop processing: n_tokens = 1092, truncated = 0 2.53.837.560 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 2.53.837.717 I slot launch_slot_: id 3 | task 4860 | processing task, is_child = 0 2.53.837.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 357.169 MiB) 2.53.923.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.202 MiB) 2.53.979.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 173716472 2.53.979.391 I slot launch_slot_: id 0 | task 4861 | processing task, is_child = 0 2.53.979.452 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 173716958 2.53.979.621 I slot launch_slot_: id 1 | task 4862 | processing task, is_child = 0 2.54.514.413 I slot print_timing: id 2 | task 4855 | prompt eval time = 963.13 ms / 1082 tokens ( 0.89 ms per token, 1123.43 tokens per second) 2.54.514.418 I slot print_timing: id 2 | task 4855 | eval time = 132.79 ms / 2 tokens ( 132.79 ms per token, 7.53 tokens per second) 2.54.514.419 I slot print_timing: id 2 | task 4855 | total time = 1095.91 ms / 1084 tokens 2.54.514.419 I slot print_timing: id 2 | task 4855 | graphs reused = 3582 2.54.514.420 I slot print_timing: id 2 | task 4855 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.514.471 I slot release: id 2 | task 4855 | stop processing: n_tokens = 1083, truncated = 0 2.54.514.781 I slot print_timing: id 3 | task 4860 | prompt eval time = 375.93 ms / 166 tokens ( 2.26 ms per token, 441.57 tokens per second) 2.54.514.785 I slot print_timing: id 3 | task 4860 | eval time = 132.50 ms / 2 tokens ( 132.50 ms per token, 7.55 tokens per second) 2.54.514.786 I slot print_timing: id 3 | task 4860 | total time = 508.43 ms / 168 tokens 2.54.514.786 I slot print_timing: id 3 | task 4860 | graphs reused = 3582 2.54.514.787 I slot print_timing: id 3 | task 4860 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.514.818 I slot release: id 3 | task 4860 | stop processing: n_tokens = 1072, truncated = 0 2.54.698.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.911 2.54.698.374 I slot launch_slot_: id 3 | task 4867 | processing task, is_child = 0 2.54.698.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.642 MiB) 2.54.748.782 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.901 2.54.748.934 I slot launch_slot_: id 2 | task 4868 | processing task, is_child = 0 2.55.087.841 I slot print_timing: id 0 | task 4861 | prompt eval time = 1089.58 ms / 1085 tokens ( 1.00 ms per token, 995.80 tokens per second) 2.55.087.846 I slot print_timing: id 0 | task 4861 | eval time = 18.62 ms / 2 tokens ( 18.62 ms per token, 53.70 tokens per second) 2.55.087.848 I slot print_timing: id 0 | task 4861 | total time = 1108.20 ms / 1087 tokens 2.55.087.848 I slot print_timing: id 0 | task 4861 | graphs reused = 3582 2.55.087.849 I slot print_timing: id 0 | task 4861 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.087.897 I slot release: id 0 | task 4861 | stop processing: n_tokens = 1086, truncated = 0 2.55.088.144 I slot print_timing: id 1 | task 4862 | prompt eval time = 1086.25 ms / 1079 tokens ( 1.01 ms per token, 993.33 tokens per second) 2.55.088.147 I slot print_timing: id 1 | task 4862 | eval time = 18.36 ms / 2 tokens ( 18.36 ms per token, 54.46 tokens per second) 2.55.088.148 I slot print_timing: id 1 | task 4862 | total time = 1104.61 ms / 1081 tokens 2.55.088.149 I slot print_timing: id 1 | task 4862 | graphs reused = 3582 2.55.088.149 I slot print_timing: id 1 | task 4862 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.088.178 I slot release: id 1 | task 4862 | stop processing: n_tokens = 1080, truncated = 0 2.55.088.433 I slot print_timing: id 2 | task 4868 | prompt eval time = 296.93 ms / 175 tokens ( 1.70 ms per token, 589.37 tokens per second) 2.55.088.436 I slot print_timing: id 2 | task 4868 | eval time = 18.07 ms / 2 tokens ( 18.07 ms per token, 55.34 tokens per second) 2.55.088.437 I slot print_timing: id 2 | task 4868 | total time = 315.00 ms / 177 tokens 2.55.088.437 I slot print_timing: id 2 | task 4868 | graphs reused = 3582 2.55.088.438 I slot print_timing: id 2 | task 4868 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.088.463 I slot release: id 2 | task 4868 | stop processing: n_tokens = 1081, truncated = 0 2.55.088.715 I slot print_timing: id 3 | task 4867 | prompt eval time = 277.76 ms / 168 tokens ( 1.65 ms per token, 604.84 tokens per second) 2.55.088.719 I slot print_timing: id 3 | task 4867 | eval time = 17.78 ms / 2 tokens ( 17.78 ms per token, 56.26 tokens per second) 2.55.088.720 I slot print_timing: id 3 | task 4867 | total time = 295.53 ms / 170 tokens 2.55.088.720 I slot print_timing: id 3 | task 4867 | graphs reused = 3582 2.55.088.721 I slot print_timing: id 3 | task 4867 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.088.745 I slot release: id 3 | task 4867 | stop processing: n_tokens = 1074, truncated = 0 2.55.102.448 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.900 2.55.102.579 I slot launch_slot_: id 0 | task 4872 | processing task, is_child = 0 2.55.102.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 256.731 MiB) 2.55.149.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 2.55.201.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.676 MiB) 2.55.257.164 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.905 2.55.257.305 I slot launch_slot_: id 1 | task 4873 | processing task, is_child = 0 2.55.257.437 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.904 2.55.257.545 I slot launch_slot_: id 2 | task 4874 | processing task, is_child = 0 2.55.257.608 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.910 2.55.257.693 I slot launch_slot_: id 3 | task 4875 | processing task, is_child = 0 2.55.618.098 I slot print_timing: id 0 | task 4872 | prompt eval time = 341.41 ms / 177 tokens ( 1.93 ms per token, 518.44 tokens per second) 2.55.618.103 I slot print_timing: id 0 | task 4872 | eval time = 18.97 ms / 2 tokens ( 18.97 ms per token, 52.71 tokens per second) 2.55.618.104 I slot print_timing: id 0 | task 4872 | total time = 360.38 ms / 179 tokens 2.55.618.105 I slot print_timing: id 0 | task 4872 | graphs reused = 3582 2.55.618.106 I slot print_timing: id 0 | task 4872 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.618.152 I slot release: id 0 | task 4872 | stop processing: n_tokens = 1083, truncated = 0 2.55.618.464 I slot print_timing: id 1 | task 4873 | prompt eval time = 322.38 ms / 170 tokens ( 1.90 ms per token, 527.32 tokens per second) 2.55.618.467 I slot print_timing: id 1 | task 4873 | eval time = 18.70 ms / 2 tokens ( 18.70 ms per token, 53.46 tokens per second) 2.55.618.468 I slot print_timing: id 1 | task 4873 | total time = 341.09 ms / 172 tokens 2.55.618.469 I slot print_timing: id 1 | task 4873 | graphs reused = 3582 2.55.618.470 I slot print_timing: id 1 | task 4873 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.618.499 I slot release: id 1 | task 4873 | stop processing: n_tokens = 1076, truncated = 0 2.55.618.811 I slot print_timing: id 2 | task 4874 | prompt eval time = 303.55 ms / 183 tokens ( 1.66 ms per token, 602.86 tokens per second) 2.55.618.815 I slot print_timing: id 2 | task 4874 | eval time = 18.45 ms / 2 tokens ( 18.45 ms per token, 54.19 tokens per second) 2.55.618.816 I slot print_timing: id 2 | task 4874 | total time = 322.01 ms / 185 tokens 2.55.618.816 I slot print_timing: id 2 | task 4874 | graphs reused = 3582 2.55.618.817 I slot print_timing: id 2 | task 4874 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.618.844 I slot release: id 2 | task 4874 | stop processing: n_tokens = 1089, truncated = 0 2.55.619.134 I slot print_timing: id 3 | task 4875 | prompt eval time = 284.52 ms / 178 tokens ( 1.60 ms per token, 625.62 tokens per second) 2.55.619.137 I slot print_timing: id 3 | task 4875 | eval time = 18.22 ms / 2 tokens ( 18.22 ms per token, 54.87 tokens per second) 2.55.619.137 I slot print_timing: id 3 | task 4875 | total time = 302.74 ms / 180 tokens 2.55.619.138 I slot print_timing: id 3 | task 4875 | graphs reused = 3582 2.55.619.139 I slot print_timing: id 3 | task 4875 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.619.168 I slot release: id 3 | task 4875 | stop processing: n_tokens = 1084, truncated = 0 2.55.632.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.902 2.55.632.267 I slot launch_slot_: id 0 | task 4879 | processing task, is_child = 0 2.55.632.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.083 MiB) 2.55.686.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 2.55.734.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 2.55.782.727 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 2.55.782.879 I slot launch_slot_: id 1 | task 4880 | processing task, is_child = 0 2.55.783.019 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.897 2.55.783.126 I slot launch_slot_: id 2 | task 4881 | processing task, is_child = 0 2.55.783.192 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.901 2.55.783.276 I slot launch_slot_: id 3 | task 4882 | processing task, is_child = 0 2.56.136.118 I slot print_timing: id 0 | task 4879 | prompt eval time = 333.61 ms / 171 tokens ( 1.95 ms per token, 512.57 tokens per second) 2.56.136.123 I slot print_timing: id 0 | task 4879 | eval time = 19.21 ms / 2 tokens ( 19.21 ms per token, 52.05 tokens per second) 2.56.136.124 I slot print_timing: id 0 | task 4879 | total time = 352.82 ms / 173 tokens 2.56.136.125 I slot print_timing: id 0 | task 4879 | graphs reused = 3582 2.56.136.125 I slot print_timing: id 0 | task 4879 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.136.173 I slot release: id 0 | task 4879 | stop processing: n_tokens = 1077, truncated = 0 2.56.136.456 I slot print_timing: id 1 | task 4880 | prompt eval time = 314.57 ms / 174 tokens ( 1.81 ms per token, 553.14 tokens per second) 2.56.136.459 I slot print_timing: id 1 | task 4880 | eval time = 18.99 ms / 2 tokens ( 18.99 ms per token, 52.65 tokens per second) 2.56.136.460 I slot print_timing: id 1 | task 4880 | total time = 333.56 ms / 176 tokens 2.56.136.461 I slot print_timing: id 1 | task 4880 | graphs reused = 3582 2.56.136.462 I slot print_timing: id 1 | task 4880 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.136.491 I slot release: id 1 | task 4880 | stop processing: n_tokens = 1080, truncated = 0 2.56.136.769 I slot print_timing: id 2 | task 4881 | prompt eval time = 295.64 ms / 173 tokens ( 1.71 ms per token, 585.17 tokens per second) 2.56.136.772 I slot print_timing: id 2 | task 4881 | eval time = 18.75 ms / 2 tokens ( 18.75 ms per token, 53.33 tokens per second) 2.56.136.772 I slot print_timing: id 2 | task 4881 | total time = 314.39 ms / 175 tokens 2.56.136.773 I slot print_timing: id 2 | task 4881 | graphs reused = 3582 2.56.136.774 I slot print_timing: id 2 | task 4881 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.136.798 I slot release: id 2 | task 4881 | stop processing: n_tokens = 1079, truncated = 0 2.56.137.082 I slot print_timing: id 3 | task 4882 | prompt eval time = 276.60 ms / 175 tokens ( 1.58 ms per token, 632.68 tokens per second) 2.56.137.085 I slot print_timing: id 3 | task 4882 | eval time = 18.53 ms / 2 tokens ( 18.53 ms per token, 53.96 tokens per second) 2.56.137.086 I slot print_timing: id 3 | task 4882 | total time = 295.13 ms / 177 tokens 2.56.137.087 I slot print_timing: id 3 | task 4882 | graphs reused = 3582 2.56.137.087 I slot print_timing: id 3 | task 4882 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.137.111 I slot release: id 3 | task 4882 | stop processing: n_tokens = 1081, truncated = 0 2.56.150.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1077, t_last = 176038768 2.56.150.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 2.56.202.281 I slot launch_slot_: id 0 | task 4886 | processing task, is_child = 0 2.56.202.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.871 MiB) 2.56.249.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.584 MiB) 2.56.296.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.522 MiB) 2.56.348.272 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 176039087 2.56.348.496 I slot launch_slot_: id 1 | task 4887 | processing task, is_child = 0 2.56.348.623 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 176039394 2.56.348.785 I slot launch_slot_: id 2 | task 4888 | processing task, is_child = 0 2.56.348.851 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 176039707 2.56.348.998 I slot launch_slot_: id 3 | task 4889 | processing task, is_child = 0 2.57.650.584 I slot print_timing: id 0 | task 4886 | prompt eval time = 1282.39 ms / 1017 tokens ( 1.26 ms per token, 793.05 tokens per second) 2.57.650.590 I slot print_timing: id 0 | task 4886 | eval time = 19.18 ms / 2 tokens ( 19.18 ms per token, 52.14 tokens per second) 2.57.650.591 I slot print_timing: id 0 | task 4886 | total time = 1301.57 ms / 1019 tokens 2.57.650.592 I slot print_timing: id 0 | task 4886 | graphs reused = 3582 2.57.650.592 I slot print_timing: id 0 | task 4886 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.650.644 I slot release: id 0 | task 4886 | stop processing: n_tokens = 1018, truncated = 0 2.57.650.936 I slot print_timing: id 1 | task 4887 | prompt eval time = 1279.23 ms / 1031 tokens ( 1.24 ms per token, 805.95 tokens per second) 2.57.650.939 I slot print_timing: id 1 | task 4887 | eval time = 18.96 ms / 2 tokens ( 18.96 ms per token, 52.73 tokens per second) 2.57.650.940 I slot print_timing: id 1 | task 4887 | total time = 1298.19 ms / 1033 tokens 2.57.650.940 I slot print_timing: id 1 | task 4887 | graphs reused = 3582 2.57.650.941 I slot print_timing: id 1 | task 4887 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.650.971 I slot release: id 1 | task 4887 | stop processing: n_tokens = 1032, truncated = 0 2.57.651.252 I slot print_timing: id 2 | task 4888 | prompt eval time = 1276.11 ms / 1071 tokens ( 1.19 ms per token, 839.27 tokens per second) 2.57.651.255 I slot print_timing: id 2 | task 4888 | eval time = 18.67 ms / 2 tokens ( 18.67 ms per token, 53.55 tokens per second) 2.57.651.256 I slot print_timing: id 2 | task 4888 | total time = 1294.79 ms / 1073 tokens 2.57.651.256 I slot print_timing: id 2 | task 4888 | graphs reused = 3582 2.57.651.257 I slot print_timing: id 2 | task 4888 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.651.285 I slot release: id 2 | task 4888 | stop processing: n_tokens = 1072, truncated = 0 2.57.651.567 I slot print_timing: id 3 | task 4889 | prompt eval time = 1272.91 ms / 1106 tokens ( 1.15 ms per token, 868.88 tokens per second) 2.57.651.570 I slot print_timing: id 3 | task 4889 | eval time = 18.44 ms / 2 tokens ( 18.44 ms per token, 54.22 tokens per second) 2.57.651.571 I slot print_timing: id 3 | task 4889 | total time = 1291.35 ms / 1108 tokens 2.57.651.571 I slot print_timing: id 3 | task 4889 | graphs reused = 3582 2.57.651.572 I slot print_timing: id 3 | task 4889 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.651.600 I slot release: id 3 | task 4889 | stop processing: n_tokens = 1107, truncated = 0 2.57.664.470 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 2.57.664.614 I slot launch_slot_: id 0 | task 4897 | processing task, is_child = 0 2.57.664.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.743 MiB) 2.57.712.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.710 MiB) 2.57.768.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.242 MiB) 2.57.827.828 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.878 2.57.827.972 I slot launch_slot_: id 1 | task 4898 | processing task, is_child = 0 2.57.828.104 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 177553881 2.57.828.270 I slot launch_slot_: id 2 | task 4899 | processing task, is_child = 0 2.57.828.337 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 177554196 2.57.828.482 I slot launch_slot_: id 3 | task 4900 | processing task, is_child = 0 2.58.313.754 I slot print_timing: id 0 | task 4897 | prompt eval time = 351.48 ms / 167 tokens ( 2.10 ms per token, 475.13 tokens per second) 2.58.313.760 I slot print_timing: id 0 | task 4897 | eval time = 133.77 ms / 2 tokens ( 133.77 ms per token, 7.48 tokens per second) 2.58.313.761 I slot print_timing: id 0 | task 4897 | total time = 485.25 ms / 169 tokens 2.58.313.762 I slot print_timing: id 0 | task 4897 | graphs reused = 3582 2.58.313.763 I slot print_timing: id 0 | task 4897 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.313.819 I slot release: id 0 | task 4897 | stop processing: n_tokens = 1046, truncated = 0 2.58.314.236 I slot print_timing: id 1 | task 4898 | prompt eval time = 332.26 ms / 152 tokens ( 2.19 ms per token, 457.47 tokens per second) 2.58.314.240 I slot print_timing: id 1 | task 4898 | eval time = 133.62 ms / 2 tokens ( 133.62 ms per token, 7.48 tokens per second) 2.58.314.240 I slot print_timing: id 1 | task 4898 | total time = 465.88 ms / 154 tokens 2.58.314.241 I slot print_timing: id 1 | task 4898 | graphs reused = 3582 2.58.314.242 I slot print_timing: id 1 | task 4898 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.314.283 I slot release: id 1 | task 4898 | stop processing: n_tokens = 1031, truncated = 0 2.58.400.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 178216415 2.58.400.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.800 MiB) 2.58.461.527 I slot launch_slot_: id 0 | task 4905 | processing task, is_child = 0 2.58.461.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 2.58.515.869 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 178216879 2.58.516.088 I slot launch_slot_: id 1 | task 4906 | processing task, is_child = 0 2.58.815.802 I slot print_timing: id 2 | task 4899 | prompt eval time = 822.13 ms / 753 tokens ( 1.09 ms per token, 915.92 tokens per second) 2.58.815.809 I slot print_timing: id 2 | task 4899 | eval time = 125.44 ms / 2 tokens ( 125.44 ms per token, 7.97 tokens per second) 2.58.815.810 I slot print_timing: id 2 | task 4899 | total time = 947.57 ms / 755 tokens 2.58.815.811 I slot print_timing: id 2 | task 4899 | graphs reused = 3582 2.58.815.812 I slot print_timing: id 2 | task 4899 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.815.860 I slot release: id 2 | task 4899 | stop processing: n_tokens = 754, truncated = 0 2.59.051.189 I slot print_timing: id 3 | task 4900 | prompt eval time = 944.99 ms / 797 tokens ( 1.19 ms per token, 843.40 tokens per second) 2.59.051.195 I slot print_timing: id 3 | task 4900 | eval time = 234.41 ms / 2 tokens ( 234.41 ms per token, 4.27 tokens per second) 2.59.051.196 I slot print_timing: id 3 | task 4900 | total time = 1179.39 ms / 799 tokens 2.59.051.196 I slot print_timing: id 3 | task 4900 | graphs reused = 3582 2.59.051.197 I slot print_timing: id 3 | task 4900 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.051.241 I slot release: id 3 | task 4900 | stop processing: n_tokens = 798, truncated = 0 2.59.051.257 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.863 2.59.051.399 I slot launch_slot_: id 2 | task 4910 | processing task, is_child = 0 2.59.051.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.898 MiB) 2.59.103.353 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.881 (> 0.100 thold), f_keep = 0.816 2.59.103.498 I slot launch_slot_: id 3 | task 4911 | processing task, is_child = 0 2.59.388.702 I slot print_timing: id 0 | task 4905 | prompt eval time = 853.98 ms / 729 tokens ( 1.17 ms per token, 853.65 tokens per second) 2.59.388.707 I slot print_timing: id 0 | task 4905 | eval time = 18.61 ms / 2 tokens ( 18.61 ms per token, 53.73 tokens per second) 2.59.388.709 I slot print_timing: id 0 | task 4905 | total time = 872.59 ms / 731 tokens 2.59.388.709 I slot print_timing: id 0 | task 4905 | graphs reused = 3582 2.59.388.710 I slot print_timing: id 0 | task 4905 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.388.750 I slot release: id 0 | task 4905 | stop processing: n_tokens = 730, truncated = 0 2.59.389.013 I slot print_timing: id 1 | task 4906 | prompt eval time = 850.93 ms / 740 tokens ( 1.15 ms per token, 869.64 tokens per second) 2.59.389.016 I slot print_timing: id 1 | task 4906 | eval time = 18.36 ms / 2 tokens ( 18.36 ms per token, 54.46 tokens per second) 2.59.389.016 I slot print_timing: id 1 | task 4906 | total time = 869.29 ms / 742 tokens 2.59.389.017 I slot print_timing: id 1 | task 4906 | graphs reused = 3582 2.59.389.018 I slot print_timing: id 1 | task 4906 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.389.041 I slot release: id 1 | task 4906 | stop processing: n_tokens = 741, truncated = 0 2.59.389.295 I slot print_timing: id 2 | task 4910 | prompt eval time = 244.95 ms / 123 tokens ( 1.99 ms per token, 502.14 tokens per second) 2.59.389.298 I slot print_timing: id 2 | task 4910 | eval time = 18.07 ms / 2 tokens ( 18.07 ms per token, 55.33 tokens per second) 2.59.389.299 I slot print_timing: id 2 | task 4910 | total time = 263.02 ms / 125 tokens 2.59.389.299 I slot print_timing: id 2 | task 4910 | graphs reused = 3582 2.59.389.300 I slot print_timing: id 2 | task 4910 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.389.321 I slot release: id 2 | task 4910 | stop processing: n_tokens = 747, truncated = 0 2.59.389.583 I slot print_timing: id 3 | task 4911 | prompt eval time = 225.91 ms / 116 tokens ( 1.95 ms per token, 513.47 tokens per second) 2.59.389.587 I slot print_timing: id 3 | task 4911 | eval time = 17.82 ms / 2 tokens ( 17.82 ms per token, 56.13 tokens per second) 2.59.389.587 I slot print_timing: id 3 | task 4911 | total time = 243.73 ms / 118 tokens 2.59.389.588 I slot print_timing: id 3 | task 4911 | graphs reused = 3582 2.59.389.588 I slot print_timing: id 3 | task 4911 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.389.607 I slot release: id 3 | task 4911 | stop processing: n_tokens = 740, truncated = 0 2.59.402.410 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.892 2.59.402.556 I slot launch_slot_: id 0 | task 4915 | processing task, is_child = 0 2.59.402.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.333 MiB) 2.59.456.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.802 MiB) 2.59.509.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.644 MiB) 2.59.549.983 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 179291637 2.59.550.174 I slot launch_slot_: id 1 | task 4916 | processing task, is_child = 0 2.59.550.273 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.871 2.59.550.370 I slot launch_slot_: id 2 | task 4917 | processing task, is_child = 0 2.59.550.421 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.880 2.59.550.507 I slot launch_slot_: id 3 | task 4918 | processing task, is_child = 0 2.59.945.802 I slot print_timing: id 0 | task 4915 | prompt eval time = 330.96 ms / 110 tokens ( 3.01 ms per token, 332.36 tokens per second) 2.59.945.808 I slot print_timing: id 0 | task 4915 | eval time = 64.31 ms / 2 tokens ( 64.31 ms per token, 15.55 tokens per second) 2.59.945.809 I slot print_timing: id 0 | task 4915 | total time = 395.27 ms / 112 tokens 2.59.945.810 I slot print_timing: id 0 | task 4915 | graphs reused = 3582 2.59.945.811 I slot print_timing: id 0 | task 4915 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.945.854 I slot release: id 0 | task 4915 | stop processing: n_tokens = 734, truncated = 0 2.59.946.226 I slot print_timing: id 2 | task 4917 | prompt eval time = 308.52 ms / 132 tokens ( 2.34 ms per token, 427.85 tokens per second) 2.59.946.229 I slot print_timing: id 2 | task 4917 | eval time = 64.02 ms / 2 tokens ( 64.02 ms per token, 15.62 tokens per second) 2.59.946.230 I slot print_timing: id 2 | task 4917 | total time = 372.54 ms / 134 tokens 2.59.946.230 I slot print_timing: id 2 | task 4917 | graphs reused = 3582 2.59.946.231 I slot print_timing: id 2 | task 4917 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.946.258 I slot release: id 2 | task 4917 | stop processing: n_tokens = 756, truncated = 0 2.59.946.618 I slot print_timing: id 3 | task 4918 | prompt eval time = 289.56 ms / 124 tokens ( 2.34 ms per token, 428.24 tokens per second) 2.59.946.621 I slot print_timing: id 3 | task 4918 | eval time = 63.70 ms / 2 tokens ( 63.70 ms per token, 15.70 tokens per second) 2.59.946.622 I slot print_timing: id 3 | task 4918 | total time = 353.25 ms / 126 tokens 2.59.946.622 I slot print_timing: id 3 | task 4918 | graphs reused = 3582 2.59.946.623 I slot print_timing: id 3 | task 4918 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.946.646 I slot release: id 3 | task 4918 | stop processing: n_tokens = 748, truncated = 0 2.59.963.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 179848450 2.59.963.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 3.00.048.324 I slot launch_slot_: id 0 | task 4923 | processing task, is_child = 0 3.00.048.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.457 MiB) 3.00.101.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 3.00.150.930 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 179848854 3.00.151.141 I slot launch_slot_: id 2 | task 4924 | processing task, is_child = 0 3.00.151.199 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 179849241 3.00.151.357 I slot launch_slot_: id 3 | task 4925 | processing task, is_child = 0 3.00.673.638 I slot print_timing: id 1 | task 4916 | prompt eval time = 975.97 ms / 990 tokens ( 0.99 ms per token, 1014.37 tokens per second) 3.00.673.643 I slot print_timing: id 1 | task 4916 | eval time = 127.50 ms / 2 tokens ( 127.50 ms per token, 7.84 tokens per second) 3.00.673.644 I slot print_timing: id 1 | task 4916 | total time = 1103.47 ms / 992 tokens 3.00.673.645 I slot print_timing: id 1 | task 4916 | graphs reused = 3582 3.00.673.646 I slot print_timing: id 1 | task 4916 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.673.700 I slot release: id 1 | task 4916 | stop processing: n_tokens = 991, truncated = 0 3.00.943.672 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 180576297 3.00.943.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.394 MiB) 3.01.007.095 I slot launch_slot_: id 1 | task 4930 | processing task, is_child = 0 3.01.458.483 I slot print_timing: id 0 | task 4923 | prompt eval time = 1205.54 ms / 973 tokens ( 1.24 ms per token, 807.11 tokens per second) 3.01.458.488 I slot print_timing: id 0 | task 4923 | eval time = 101.57 ms / 2 tokens ( 101.57 ms per token, 9.85 tokens per second) 3.01.458.489 I slot print_timing: id 0 | task 4923 | total time = 1307.11 ms / 975 tokens 3.01.458.490 I slot print_timing: id 0 | task 4923 | graphs reused = 3582 3.01.458.491 I slot print_timing: id 0 | task 4923 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.458.543 I slot release: id 0 | task 4923 | stop processing: n_tokens = 974, truncated = 0 3.01.458.916 I slot print_timing: id 2 | task 4924 | prompt eval time = 1190.26 ms / 1044 tokens ( 1.14 ms per token, 877.12 tokens per second) 3.01.458.919 I slot print_timing: id 2 | task 4924 | eval time = 101.38 ms / 2 tokens ( 101.38 ms per token, 9.86 tokens per second) 3.01.458.920 I slot print_timing: id 2 | task 4924 | total time = 1291.65 ms / 1046 tokens 3.01.458.921 I slot print_timing: id 2 | task 4924 | graphs reused = 3582 3.01.458.922 I slot print_timing: id 2 | task 4924 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.458.963 I slot release: id 2 | task 4924 | stop processing: n_tokens = 1045, truncated = 0 3.01.459.298 I slot print_timing: id 3 | task 4925 | prompt eval time = 1187.37 ms / 955 tokens ( 1.24 ms per token, 804.30 tokens per second) 3.01.459.301 I slot print_timing: id 3 | task 4925 | eval time = 101.14 ms / 2 tokens ( 101.14 ms per token, 9.89 tokens per second) 3.01.459.302 I slot print_timing: id 3 | task 4925 | total time = 1288.51 ms / 957 tokens 3.01.459.302 I slot print_timing: id 3 | task 4925 | graphs reused = 3582 3.01.459.303 I slot print_timing: id 3 | task 4925 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.459.333 I slot release: id 3 | task 4925 | stop processing: n_tokens = 956, truncated = 0 3.01.475.657 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 181361139 3.01.475.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.770 MiB) 3.01.564.981 I slot launch_slot_: id 0 | task 4935 | processing task, is_child = 0 3.01.565.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.707 MiB) 3.01.607.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.457 MiB) 3.01.661.563 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 181361559 3.01.661.775 I slot launch_slot_: id 2 | task 4936 | processing task, is_child = 0 3.01.661.836 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 181361929 3.01.661.990 I slot launch_slot_: id 3 | task 4937 | processing task, is_child = 0 3.02.719.673 I slot print_timing: id 1 | task 4930 | prompt eval time = 1199.04 ms / 1124 tokens ( 1.07 ms per token, 937.42 tokens per second) 3.02.719.678 I slot print_timing: id 1 | task 4930 | eval time = 502.20 ms / 2 tokens ( 502.20 ms per token, 1.99 tokens per second) 3.02.719.679 I slot print_timing: id 1 | task 4930 | total time = 1701.23 ms / 1126 tokens 3.02.719.680 I slot print_timing: id 1 | task 4930 | graphs reused = 3582 3.02.719.681 I slot print_timing: id 1 | task 4930 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.719.734 I slot release: id 1 | task 4930 | stop processing: n_tokens = 1125, truncated = 0 3.02.882.504 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 182622330 3.02.882.590 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 3.02.930.542 I slot launch_slot_: id 1 | task 4942 | processing task, is_child = 0 3.03.712.688 I slot print_timing: id 0 | task 4935 | prompt eval time = 1787.59 ms / 1161 tokens ( 1.54 ms per token, 649.48 tokens per second) 3.03.712.697 I slot print_timing: id 0 | task 4935 | eval time = 263.08 ms / 2 tokens ( 263.08 ms per token, 3.80 tokens per second) 3.03.712.698 I slot print_timing: id 0 | task 4935 | total time = 2050.68 ms / 1163 tokens 3.03.712.699 I slot print_timing: id 0 | task 4935 | graphs reused = 3582 3.03.712.701 I slot print_timing: id 0 | task 4935 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.712.759 I slot release: id 0 | task 4935 | stop processing: n_tokens = 1162, truncated = 0 3.03.713.105 I slot print_timing: id 2 | task 4936 | prompt eval time = 1772.42 ms / 2094 tokens ( 0.85 ms per token, 1181.43 tokens per second) 3.03.713.108 I slot print_timing: id 2 | task 4936 | eval time = 262.94 ms / 2 tokens ( 262.94 ms per token, 3.80 tokens per second) 3.03.713.108 I slot print_timing: id 2 | task 4936 | total time = 2035.36 ms / 2096 tokens 3.03.713.109 I slot print_timing: id 2 | task 4936 | graphs reused = 3582 3.03.713.109 I slot print_timing: id 2 | task 4936 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.713.184 I slot release: id 2 | task 4936 | stop processing: n_tokens = 2095, truncated = 0 3.03.792.744 I slot print_timing: id 3 | task 4937 | prompt eval time = 2032.49 ms / 2091 tokens ( 0.97 ms per token, 1028.79 tokens per second) 3.03.792.749 I slot print_timing: id 3 | task 4937 | eval time = 78.91 ms / 2 tokens ( 78.91 ms per token, 12.67 tokens per second) 3.03.792.750 I slot print_timing: id 3 | task 4937 | total time = 2111.40 ms / 2093 tokens 3.03.792.751 I slot print_timing: id 3 | task 4937 | graphs reused = 3582 3.03.792.752 I slot print_timing: id 3 | task 4937 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.792.839 I slot release: id 3 | task 4937 | stop processing: n_tokens = 2092, truncated = 0 3.03.792.854 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.877 (> 0.100 thold), f_keep = 0.854 3.03.792.975 I slot launch_slot_: id 2 | task 4947 | processing task, is_child = 0 3.03.793.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 3.03.850.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.122 MiB) 3.03.855.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.028 MiB) 3.03.918.290 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.856 3.03.918.436 I slot launch_slot_: id 3 | task 4948 | processing task, is_child = 0 3.03.918.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 183615355 3.03.936.741 I slot launch_slot_: id 0 | task 4949 | processing task, is_child = 0 3.04.429.811 I slot print_timing: id 0 | task 4949 | prompt eval time = 473.59 ms / 369 tokens ( 1.28 ms per token, 779.16 tokens per second) 3.04.429.817 I slot print_timing: id 0 | task 4949 | eval time = 19.46 ms / 2 tokens ( 19.46 ms per token, 51.39 tokens per second) 3.04.429.818 I slot print_timing: id 0 | task 4949 | total time = 493.05 ms / 371 tokens 3.04.429.818 I slot print_timing: id 0 | task 4949 | graphs reused = 3583 3.04.429.819 I slot print_timing: id 0 | task 4949 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.429.909 I slot release: id 0 | task 4949 | stop processing: n_tokens = 2131, truncated = 0 3.04.430.244 I slot print_timing: id 1 | task 4942 | prompt eval time = 1470.28 ms / 2057 tokens ( 0.71 ms per token, 1399.05 tokens per second) 3.04.430.247 I slot print_timing: id 1 | task 4942 | eval time = 19.26 ms / 2 tokens ( 19.26 ms per token, 51.92 tokens per second) 3.04.430.248 I slot print_timing: id 1 | task 4942 | total time = 1489.54 ms / 2059 tokens 3.04.430.248 I slot print_timing: id 1 | task 4942 | graphs reused = 3583 3.04.430.249 I slot print_timing: id 1 | task 4942 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.430.304 I slot release: id 1 | task 4942 | stop processing: n_tokens = 2058, truncated = 0 3.04.430.612 I slot print_timing: id 2 | task 4947 | prompt eval time = 442.32 ms / 280 tokens ( 1.58 ms per token, 633.02 tokens per second) 3.04.430.615 I slot print_timing: id 2 | task 4947 | eval time = 19.07 ms / 2 tokens ( 19.07 ms per token, 52.45 tokens per second) 3.04.430.616 I slot print_timing: id 2 | task 4947 | total time = 461.39 ms / 282 tokens 3.04.430.616 I slot print_timing: id 2 | task 4947 | graphs reused = 3583 3.04.430.617 I slot print_timing: id 2 | task 4947 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.430.663 I slot release: id 2 | task 4947 | stop processing: n_tokens = 2042, truncated = 0 3.04.430.963 I slot print_timing: id 3 | task 4948 | prompt eval time = 423.02 ms / 344 tokens ( 1.23 ms per token, 813.21 tokens per second) 3.04.430.966 I slot print_timing: id 3 | task 4948 | eval time = 18.86 ms / 2 tokens ( 18.86 ms per token, 53.01 tokens per second) 3.04.430.967 I slot print_timing: id 3 | task 4948 | total time = 441.88 ms / 346 tokens 3.04.430.967 I slot print_timing: id 3 | task 4948 | graphs reused = 3583 3.04.430.968 I slot print_timing: id 3 | task 4948 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.431.012 I slot release: id 3 | task 4948 | stop processing: n_tokens = 2106, truncated = 0 3.04.445.961 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.840 3.04.446.129 I slot launch_slot_: id 0 | task 4953 | processing task, is_child = 0 3.04.490.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.059 MiB) 3.04.549.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.840 MiB) 3.04.611.533 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.870 3.04.611.683 I slot launch_slot_: id 1 | task 4954 | processing task, is_child = 0 3.04.611.903 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.877 3.04.612.018 I slot launch_slot_: id 2 | task 4955 | processing task, is_child = 0 3.04.612.128 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.850 3.04.612.223 I slot launch_slot_: id 3 | task 4956 | processing task, is_child = 0 3.05.113.301 I slot print_timing: id 0 | task 4953 | prompt eval time = 481.42 ms / 300 tokens ( 1.60 ms per token, 623.16 tokens per second) 3.05.113.306 I slot print_timing: id 0 | task 4953 | eval time = 19.64 ms / 2 tokens ( 19.64 ms per token, 50.93 tokens per second) 3.05.113.307 I slot print_timing: id 0 | task 4953 | total time = 501.06 ms / 302 tokens 3.05.113.308 I slot print_timing: id 0 | task 4953 | graphs reused = 3583 3.05.113.309 I slot print_timing: id 0 | task 4953 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.113.397 I slot release: id 0 | task 4953 | stop processing: n_tokens = 2062, truncated = 0 3.05.113.778 I slot print_timing: id 1 | task 4954 | prompt eval time = 462.00 ms / 380 tokens ( 1.22 ms per token, 822.51 tokens per second) 3.05.113.781 I slot print_timing: id 1 | task 4954 | eval time = 19.39 ms / 2 tokens ( 19.39 ms per token, 51.57 tokens per second) 3.05.113.782 I slot print_timing: id 1 | task 4954 | total time = 481.39 ms / 382 tokens 3.05.113.782 I slot print_timing: id 1 | task 4954 | graphs reused = 3583 3.05.113.783 I slot print_timing: id 1 | task 4954 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.113.844 I slot release: id 1 | task 4954 | stop processing: n_tokens = 2142, truncated = 0 3.05.114.238 I slot print_timing: id 2 | task 4955 | prompt eval time = 442.84 ms / 210 tokens ( 2.11 ms per token, 474.22 tokens per second) 3.05.114.241 I slot print_timing: id 2 | task 4955 | eval time = 19.17 ms / 2 tokens ( 19.17 ms per token, 52.16 tokens per second) 3.05.114.242 I slot print_timing: id 2 | task 4955 | total time = 462.01 ms / 212 tokens 3.05.114.242 I slot print_timing: id 2 | task 4955 | graphs reused = 3583 3.05.114.243 I slot print_timing: id 2 | task 4955 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.114.295 I slot release: id 2 | task 4955 | stop processing: n_tokens = 1972, truncated = 0 3.05.114.709 I slot print_timing: id 3 | task 4956 | prompt eval time = 423.38 ms / 467 tokens ( 0.91 ms per token, 1103.04 tokens per second) 3.05.114.715 I slot print_timing: id 3 | task 4956 | eval time = 19.04 ms / 2 tokens ( 19.04 ms per token, 52.53 tokens per second) 3.05.114.716 I slot print_timing: id 3 | task 4956 | total time = 442.41 ms / 469 tokens 3.05.114.718 I slot print_timing: id 3 | task 4956 | graphs reused = 3583 3.05.114.719 I slot print_timing: id 3 | task 4956 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.114.800 I slot release: id 3 | task 4956 | stop processing: n_tokens = 2229, truncated = 0 3.05.129.103 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.836 3.05.129.247 I slot launch_slot_: id 1 | task 4960 | processing task, is_child = 0 3.05.129.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.903 MiB) 3.05.189.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.309 MiB) 3.05.243.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.153 MiB) 3.05.299.121 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.868 3.05.299.275 I slot launch_slot_: id 0 | task 4961 | processing task, is_child = 0 3.05.299.499 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.908 3.05.299.602 I slot launch_slot_: id 2 | task 4962 | processing task, is_child = 0 3.05.299.715 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.803 3.05.299.800 I slot launch_slot_: id 3 | task 4963 | processing task, is_child = 0 3.05.764.949 I slot print_timing: id 0 | task 4961 | prompt eval time = 445.13 ms / 253 tokens ( 1.76 ms per token, 568.37 tokens per second) 3.05.764.955 I slot print_timing: id 0 | task 4961 | eval time = 20.00 ms / 2 tokens ( 20.00 ms per token, 50.00 tokens per second) 3.05.764.956 I slot print_timing: id 0 | task 4961 | total time = 465.13 ms / 255 tokens 3.05.764.957 I slot print_timing: id 0 | task 4961 | graphs reused = 3583 3.05.764.958 I slot print_timing: id 0 | task 4961 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.765.043 I slot release: id 0 | task 4961 | stop processing: n_tokens = 2015, truncated = 0 3.05.765.407 I slot print_timing: id 1 | task 4960 | prompt eval time = 426.41 ms / 258 tokens ( 1.65 ms per token, 605.05 tokens per second) 3.05.765.410 I slot print_timing: id 1 | task 4960 | eval time = 19.64 ms / 2 tokens ( 19.64 ms per token, 50.91 tokens per second) 3.05.765.410 I slot print_timing: id 1 | task 4960 | total time = 446.05 ms / 260 tokens 3.05.765.411 I slot print_timing: id 1 | task 4960 | graphs reused = 3583 3.05.765.412 I slot print_timing: id 1 | task 4960 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.765.466 I slot release: id 1 | task 4960 | stop processing: n_tokens = 2020, truncated = 0 3.05.765.920 I slot print_timing: id 2 | task 4962 | prompt eval time = 404.93 ms / 345 tokens ( 1.17 ms per token, 852.00 tokens per second) 3.05.765.923 I slot print_timing: id 2 | task 4962 | eval time = 19.36 ms / 2 tokens ( 19.36 ms per token, 51.66 tokens per second) 3.05.765.924 I slot print_timing: id 2 | task 4962 | total time = 424.28 ms / 347 tokens 3.05.765.924 I slot print_timing: id 2 | task 4962 | graphs reused = 3583 3.05.765.925 I slot print_timing: id 2 | task 4962 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.765.975 I slot release: id 2 | task 4962 | stop processing: n_tokens = 2107, truncated = 0 3.05.766.261 I slot print_timing: id 3 | task 4963 | prompt eval time = 385.75 ms / 304 tokens ( 1.27 ms per token, 788.07 tokens per second) 3.05.766.264 I slot print_timing: id 3 | task 4963 | eval time = 19.15 ms / 2 tokens ( 19.15 ms per token, 52.22 tokens per second) 3.05.766.264 I slot print_timing: id 3 | task 4963 | total time = 404.90 ms / 306 tokens 3.05.766.265 I slot print_timing: id 3 | task 4963 | graphs reused = 3583 3.05.766.265 I slot print_timing: id 3 | task 4963 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.766.309 I slot release: id 3 | task 4963 | stop processing: n_tokens = 2066, truncated = 0 3.05.782.341 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 3.05.782.491 I slot launch_slot_: id 0 | task 4967 | processing task, is_child = 0 3.05.782.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.934 MiB) 3.05.839.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.028 MiB) 3.05.898.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.997 MiB) 3.05.962.196 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.886 3.05.962.344 I slot launch_slot_: id 1 | task 4968 | processing task, is_child = 0 3.05.962.573 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.849 3.05.962.682 I slot launch_slot_: id 2 | task 4969 | processing task, is_child = 0 3.05.962.794 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.847 (> 0.100 thold), f_keep = 0.866 3.05.962.882 I slot launch_slot_: id 3 | task 4970 | processing task, is_child = 0 3.06.464.569 I slot print_timing: id 0 | task 4967 | prompt eval time = 482.08 ms / 304 tokens ( 1.59 ms per token, 630.61 tokens per second) 3.06.464.575 I slot print_timing: id 0 | task 4967 | eval time = 19.59 ms / 2 tokens ( 19.59 ms per token, 51.04 tokens per second) 3.06.464.576 I slot print_timing: id 0 | task 4967 | total time = 501.67 ms / 306 tokens 3.06.464.577 I slot print_timing: id 0 | task 4967 | graphs reused = 3583 3.06.464.577 I slot print_timing: id 0 | task 4967 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.464.660 I slot release: id 0 | task 4967 | stop processing: n_tokens = 2066, truncated = 0 3.06.465.053 I slot print_timing: id 1 | task 4968 | prompt eval time = 462.46 ms / 212 tokens ( 2.18 ms per token, 458.42 tokens per second) 3.06.465.057 I slot print_timing: id 1 | task 4968 | eval time = 19.32 ms / 2 tokens ( 19.32 ms per token, 51.75 tokens per second) 3.06.465.058 I slot print_timing: id 1 | task 4968 | total time = 481.78 ms / 214 tokens 3.06.465.058 I slot print_timing: id 1 | task 4968 | graphs reused = 3583 3.06.465.059 I slot print_timing: id 1 | task 4968 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.465.114 I slot release: id 1 | task 4968 | stop processing: n_tokens = 1974, truncated = 0 3.06.465.407 I slot print_timing: id 2 | task 4969 | prompt eval time = 427.59 ms / 405 tokens ( 1.06 ms per token, 947.16 tokens per second) 3.06.465.411 I slot print_timing: id 2 | task 4969 | eval time = 19.11 ms / 2 tokens ( 19.11 ms per token, 52.33 tokens per second) 3.06.465.411 I slot print_timing: id 2 | task 4969 | total time = 446.70 ms / 407 tokens 3.06.465.412 I slot print_timing: id 2 | task 4969 | graphs reused = 3583 3.06.465.413 I slot print_timing: id 2 | task 4969 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.465.463 I slot release: id 2 | task 4969 | stop processing: n_tokens = 2167, truncated = 0 3.06.465.741 I slot print_timing: id 3 | task 4970 | prompt eval time = 407.36 ms / 353 tokens ( 1.15 ms per token, 866.56 tokens per second) 3.06.465.744 I slot print_timing: id 3 | task 4970 | eval time = 18.89 ms / 2 tokens ( 18.89 ms per token, 52.93 tokens per second) 3.06.465.744 I slot print_timing: id 3 | task 4970 | total time = 426.25 ms / 355 tokens 3.06.465.745 I slot print_timing: id 3 | task 4970 | graphs reused = 3583 3.06.465.746 I slot print_timing: id 3 | task 4970 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.465.793 I slot release: id 3 | task 4970 | stop processing: n_tokens = 2115, truncated = 0 3.06.480.591 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.846 3.06.480.768 I slot launch_slot_: id 3 | task 4974 | processing task, is_child = 0 3.06.480.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.059 MiB) 3.06.485.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.527 MiB) 3.06.542.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 3.06.603.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.872 MiB) 3.06.666.294 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.907 3.06.666.440 I slot launch_slot_: id 1 | task 4975 | processing task, is_child = 0 3.06.666.671 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.866 3.06.666.777 I slot launch_slot_: id 0 | task 4976 | processing task, is_child = 0 3.06.666.891 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.826 3.06.666.986 I slot launch_slot_: id 2 | task 4977 | processing task, is_child = 0 3.07.111.669 I slot print_timing: id 0 | task 4976 | prompt eval time = 425.36 ms / 272 tokens ( 1.56 ms per token, 639.46 tokens per second) 3.07.111.674 I slot print_timing: id 0 | task 4976 | eval time = 19.31 ms / 2 tokens ( 19.31 ms per token, 51.79 tokens per second) 3.07.111.675 I slot print_timing: id 0 | task 4976 | total time = 444.67 ms / 274 tokens 3.07.111.676 I slot print_timing: id 0 | task 4976 | graphs reused = 3583 3.07.111.677 I slot print_timing: id 0 | task 4976 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.111.760 I slot release: id 0 | task 4976 | stop processing: n_tokens = 2034, truncated = 0 3.07.112.106 I slot print_timing: id 1 | task 4975 | prompt eval time = 405.96 ms / 236 tokens ( 1.72 ms per token, 581.34 tokens per second) 3.07.112.109 I slot print_timing: id 1 | task 4975 | eval time = 18.96 ms / 2 tokens ( 18.96 ms per token, 52.73 tokens per second) 3.07.112.109 I slot print_timing: id 1 | task 4975 | total time = 424.93 ms / 238 tokens 3.07.112.110 I slot print_timing: id 1 | task 4975 | graphs reused = 3583 3.07.112.110 I slot print_timing: id 1 | task 4975 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.112.168 I slot release: id 1 | task 4975 | stop processing: n_tokens = 1998, truncated = 0 3.07.112.599 I slot print_timing: id 2 | task 4977 | prompt eval time = 386.80 ms / 413 tokens ( 0.94 ms per token, 1067.75 tokens per second) 3.07.112.602 I slot print_timing: id 2 | task 4977 | eval time = 18.71 ms / 2 tokens ( 18.71 ms per token, 53.44 tokens per second) 3.07.112.603 I slot print_timing: id 2 | task 4977 | total time = 405.51 ms / 415 tokens 3.07.112.603 I slot print_timing: id 2 | task 4977 | graphs reused = 3583 3.07.112.604 I slot print_timing: id 2 | task 4977 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.112.664 I slot release: id 2 | task 4977 | stop processing: n_tokens = 2175, truncated = 0 3.07.112.920 I slot print_timing: id 3 | task 4974 | prompt eval time = 367.38 ms / 210 tokens ( 1.75 ms per token, 571.62 tokens per second) 3.07.112.923 I slot print_timing: id 3 | task 4974 | eval time = 18.48 ms / 2 tokens ( 18.48 ms per token, 54.10 tokens per second) 3.07.112.924 I slot print_timing: id 3 | task 4974 | total time = 385.86 ms / 212 tokens 3.07.112.925 I slot print_timing: id 3 | task 4974 | graphs reused = 3583 3.07.112.926 I slot print_timing: id 3 | task 4974 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.112.967 I slot release: id 3 | task 4974 | stop processing: n_tokens = 1972, truncated = 0 3.07.128.245 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.880 3.07.128.366 I slot launch_slot_: id 0 | task 4981 | processing task, is_child = 0 3.07.128.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.965 MiB) 3.07.182.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.495 MiB) 3.07.243.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.209 MiB) 3.07.304.232 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.895 3.07.304.377 I slot launch_slot_: id 1 | task 4982 | processing task, is_child = 0 3.07.304.622 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.823 3.07.304.733 I slot launch_slot_: id 2 | task 4983 | processing task, is_child = 0 3.07.304.843 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.908 3.07.304.931 I slot launch_slot_: id 3 | task 4984 | processing task, is_child = 0 3.07.696.538 I slot print_timing: id 0 | task 4981 | prompt eval time = 372.40 ms / 149 tokens ( 2.50 ms per token, 400.11 tokens per second) 3.07.696.544 I slot print_timing: id 0 | task 4981 | eval time = 19.19 ms / 2 tokens ( 19.19 ms per token, 52.11 tokens per second) 3.07.696.545 I slot print_timing: id 0 | task 4981 | total time = 391.59 ms / 151 tokens 3.07.696.546 I slot print_timing: id 0 | task 4981 | graphs reused = 3583 3.07.696.546 I slot print_timing: id 0 | task 4981 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.696.626 I slot release: id 0 | task 4981 | stop processing: n_tokens = 1911, truncated = 0 3.07.696.960 I slot print_timing: id 1 | task 4982 | prompt eval time = 353.53 ms / 196 tokens ( 1.80 ms per token, 554.40 tokens per second) 3.07.696.964 I slot print_timing: id 1 | task 4982 | eval time = 18.89 ms / 2 tokens ( 18.89 ms per token, 52.94 tokens per second) 3.07.696.965 I slot print_timing: id 1 | task 4982 | total time = 372.42 ms / 198 tokens 3.07.696.966 I slot print_timing: id 1 | task 4982 | graphs reused = 3583 3.07.696.967 I slot print_timing: id 1 | task 4982 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.697.031 I slot release: id 1 | task 4982 | stop processing: n_tokens = 1958, truncated = 0 3.07.697.403 I slot print_timing: id 2 | task 4983 | prompt eval time = 334.56 ms / 264 tokens ( 1.27 ms per token, 789.10 tokens per second) 3.07.697.408 I slot print_timing: id 2 | task 4983 | eval time = 18.65 ms / 2 tokens ( 18.65 ms per token, 53.61 tokens per second) 3.07.697.409 I slot print_timing: id 2 | task 4983 | total time = 353.21 ms / 266 tokens 3.07.697.410 I slot print_timing: id 2 | task 4983 | graphs reused = 3583 3.07.697.411 I slot print_timing: id 2 | task 4983 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.697.463 I slot release: id 2 | task 4983 | stop processing: n_tokens = 2026, truncated = 0 3.07.697.740 I slot print_timing: id 3 | task 4984 | prompt eval time = 315.63 ms / 230 tokens ( 1.37 ms per token, 728.69 tokens per second) 3.07.697.744 I slot print_timing: id 3 | task 4984 | eval time = 18.43 ms / 2 tokens ( 18.43 ms per token, 54.26 tokens per second) 3.07.697.744 I slot print_timing: id 3 | task 4984 | total time = 334.06 ms / 232 tokens 3.07.697.745 I slot print_timing: id 3 | task 4984 | graphs reused = 3583 3.07.697.746 I slot print_timing: id 3 | task 4984 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.697.788 I slot release: id 3 | task 4984 | stop processing: n_tokens = 1992, truncated = 0 3.07.712.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 187599223 3.07.712.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.426 MiB) 3.07.779.820 I slot launch_slot_: id 0 | task 4988 | processing task, is_child = 0 3.07.779.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.614 MiB) 3.07.840.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 3.07.844.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.207 MiB) 3.07.904.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.895 MiB) 3.07.964.122 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 187599627 3.07.964.379 I slot launch_slot_: id 1 | task 4990 | processing task, is_child = 0 3.07.964.594 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2026, t_last = 187600060 3.07.964.796 I slot launch_slot_: id 2 | task 4989 | processing task, is_child = 0 3.07.964.909 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 187600384 3.07.965.097 I slot launch_slot_: id 3 | task 4991 | processing task, is_child = 0 3.09.585.489 I slot print_timing: id 0 | task 4988 | prompt eval time = 1601.09 ms / 1555 tokens ( 1.03 ms per token, 971.22 tokens per second) 3.09.585.494 I slot print_timing: id 0 | task 4988 | eval time = 19.29 ms / 2 tokens ( 19.29 ms per token, 51.85 tokens per second) 3.09.585.495 I slot print_timing: id 0 | task 4988 | total time = 1620.37 ms / 1557 tokens 3.09.585.496 I slot print_timing: id 0 | task 4988 | graphs reused = 3583 3.09.585.497 I slot print_timing: id 0 | task 4988 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.585.573 I slot release: id 0 | task 4988 | stop processing: n_tokens = 1556, truncated = 0 3.09.585.883 I slot print_timing: id 1 | task 4990 | prompt eval time = 1598.02 ms / 1475 tokens ( 1.08 ms per token, 923.02 tokens per second) 3.09.585.887 I slot print_timing: id 1 | task 4990 | eval time = 19.09 ms / 2 tokens ( 19.09 ms per token, 52.37 tokens per second) 3.09.585.888 I slot print_timing: id 1 | task 4990 | total time = 1617.12 ms / 1477 tokens 3.09.585.888 I slot print_timing: id 1 | task 4990 | graphs reused = 3583 3.09.585.889 I slot print_timing: id 1 | task 4990 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.585.932 I slot release: id 1 | task 4990 | stop processing: n_tokens = 1476, truncated = 0 3.09.586.237 I slot print_timing: id 2 | task 4989 | prompt eval time = 1595.00 ms / 1677 tokens ( 0.95 ms per token, 1051.41 tokens per second) 3.09.586.240 I slot print_timing: id 2 | task 4989 | eval time = 18.88 ms / 2 tokens ( 18.88 ms per token, 52.96 tokens per second) 3.09.586.241 I slot print_timing: id 2 | task 4989 | total time = 1613.88 ms / 1679 tokens 3.09.586.241 I slot print_timing: id 2 | task 4989 | graphs reused = 3583 3.09.586.242 I slot print_timing: id 2 | task 4989 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.586.285 I slot release: id 2 | task 4989 | stop processing: n_tokens = 1678, truncated = 0 3.09.586.584 I slot print_timing: id 3 | task 4991 | prompt eval time = 1591.92 ms / 999 tokens ( 1.59 ms per token, 627.54 tokens per second) 3.09.586.586 I slot print_timing: id 3 | task 4991 | eval time = 18.67 ms / 2 tokens ( 18.67 ms per token, 53.55 tokens per second) 3.09.586.587 I slot print_timing: id 3 | task 4991 | total time = 1610.59 ms / 1001 tokens 3.09.586.587 I slot print_timing: id 3 | task 4991 | graphs reused = 3583 3.09.586.588 I slot print_timing: id 3 | task 4991 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.586.620 I slot release: id 3 | task 4991 | stop processing: n_tokens = 1000, truncated = 0 3.09.599.050 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.891 (> 0.100 thold), f_keep = 0.881 3.09.599.183 I slot launch_slot_: id 3 | task 4999 | processing task, is_child = 0 3.09.599.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.645 MiB) 3.09.654.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.245 MiB) 3.09.712.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.713 MiB) 3.09.767.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 189488168 3.09.767.299 I slot launch_slot_: id 0 | task 5000 | processing task, is_child = 0 3.09.767.463 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 189488529 3.09.767.638 I slot launch_slot_: id 1 | task 5001 | processing task, is_child = 0 3.09.767.724 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 189488882 3.09.767.901 I slot launch_slot_: id 2 | task 5002 | processing task, is_child = 0 3.10.283.794 I slot print_timing: id 3 | task 4999 | prompt eval time = 421.46 ms / 136 tokens ( 3.10 ms per token, 322.68 tokens per second) 3.10.283.801 I slot print_timing: id 3 | task 4999 | eval time = 83.50 ms / 2 tokens ( 83.50 ms per token, 11.98 tokens per second) 3.10.283.802 I slot print_timing: id 3 | task 4999 | total time = 504.97 ms / 138 tokens 3.10.283.803 I slot print_timing: id 3 | task 4999 | graphs reused = 3583 3.10.283.804 I slot print_timing: id 3 | task 4999 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.283.861 I slot release: id 3 | task 4999 | stop processing: n_tokens = 990, truncated = 0 3.10.609.584 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 3.10.609.757 I slot launch_slot_: id 3 | task 5007 | processing task, is_child = 0 3.10.899.191 I slot print_timing: id 0 | task 5000 | prompt eval time = 1112.20 ms / 960 tokens ( 1.16 ms per token, 863.15 tokens per second) 3.10.899.197 I slot print_timing: id 0 | task 5000 | eval time = 19.07 ms / 2 tokens ( 19.07 ms per token, 52.45 tokens per second) 3.10.899.199 I slot print_timing: id 0 | task 5000 | total time = 1131.27 ms / 962 tokens 3.10.899.200 I slot print_timing: id 0 | task 5000 | graphs reused = 3583 3.10.899.200 I slot print_timing: id 0 | task 5000 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.899.249 I slot release: id 0 | task 5000 | stop processing: n_tokens = 961, truncated = 0 3.10.899.570 I slot print_timing: id 1 | task 5001 | prompt eval time = 1109.09 ms / 983 tokens ( 1.13 ms per token, 886.31 tokens per second) 3.10.899.573 I slot print_timing: id 1 | task 5001 | eval time = 18.82 ms / 2 tokens ( 18.82 ms per token, 53.13 tokens per second) 3.10.899.574 I slot print_timing: id 1 | task 5001 | total time = 1127.92 ms / 985 tokens 3.10.899.574 I slot print_timing: id 1 | task 5001 | graphs reused = 3583 3.10.899.575 I slot print_timing: id 1 | task 5001 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.899.607 I slot release: id 1 | task 5001 | stop processing: n_tokens = 984, truncated = 0 3.10.899.928 I slot print_timing: id 2 | task 5002 | prompt eval time = 1106.12 ms / 977 tokens ( 1.13 ms per token, 883.27 tokens per second) 3.10.899.931 I slot print_timing: id 2 | task 5002 | eval time = 18.57 ms / 2 tokens ( 18.57 ms per token, 53.85 tokens per second) 3.10.899.932 I slot print_timing: id 2 | task 5002 | total time = 1124.69 ms / 979 tokens 3.10.899.932 I slot print_timing: id 2 | task 5002 | graphs reused = 3583 3.10.899.933 I slot print_timing: id 2 | task 5002 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.899.958 I slot release: id 2 | task 5002 | stop processing: n_tokens = 978, truncated = 0 3.10.900.239 I slot print_timing: id 3 | task 5007 | prompt eval time = 234.75 ms / 119 tokens ( 1.97 ms per token, 506.93 tokens per second) 3.10.900.242 I slot print_timing: id 3 | task 5007 | eval time = 18.32 ms / 2 tokens ( 18.32 ms per token, 54.59 tokens per second) 3.10.900.243 I slot print_timing: id 3 | task 5007 | total time = 253.07 ms / 121 tokens 3.10.900.243 I slot print_timing: id 3 | task 5007 | graphs reused = 3583 3.10.900.244 I slot print_timing: id 3 | task 5007 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.900.268 I slot release: id 3 | task 5007 | stop processing: n_tokens = 973, truncated = 0 3.10.913.406 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.910 3.10.913.566 I slot launch_slot_: id 3 | task 5011 | processing task, is_child = 0 3.10.913.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.933 MiB) 3.10.956.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.150 MiB) 3.11.019.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.435 MiB) 3.11.072.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 190801845 3.11.072.253 I slot launch_slot_: id 0 | task 5012 | processing task, is_child = 0 3.11.072.368 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 190802203 3.11.072.515 I slot launch_slot_: id 1 | task 5013 | processing task, is_child = 0 3.11.072.574 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 978, t_last = 190802554 3.11.072.715 I slot launch_slot_: id 2 | task 5014 | processing task, is_child = 0 3.11.914.164 I slot print_timing: id 3 | task 5011 | prompt eval time = 444.60 ms / 123 tokens ( 3.61 ms per token, 276.65 tokens per second) 3.11.914.170 I slot print_timing: id 3 | task 5011 | eval time = 386.32 ms / 2 tokens ( 386.32 ms per token, 2.59 tokens per second) 3.11.914.171 I slot print_timing: id 3 | task 5011 | total time = 830.92 ms / 125 tokens 3.11.914.172 I slot print_timing: id 3 | task 5011 | graphs reused = 3583 3.11.914.173 I slot print_timing: id 3 | task 5011 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.914.222 I slot release: id 3 | task 5011 | stop processing: n_tokens = 977, truncated = 0 3.12.113.611 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 191816818 3.12.113.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 287.592 MiB) 3.12.162.365 I slot launch_slot_: id 3 | task 5019 | processing task, is_child = 0 3.12.550.352 I slot print_timing: id 2 | task 5014 | prompt eval time = 1348.07 ms / 825 tokens ( 1.63 ms per token, 611.99 tokens per second) 3.12.550.358 I slot print_timing: id 2 | task 5014 | eval time = 122.52 ms / 2 tokens ( 122.52 ms per token, 8.16 tokens per second) 3.12.550.359 I slot print_timing: id 2 | task 5014 | total time = 1470.58 ms / 827 tokens 3.12.550.360 I slot print_timing: id 2 | task 5014 | graphs reused = 3583 3.12.550.361 I slot print_timing: id 2 | task 5014 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.550.408 I slot release: id 2 | task 5014 | stop processing: n_tokens = 826, truncated = 0 3.12.703.853 I slot print_timing: id 0 | task 5012 | prompt eval time = 1476.62 ms / 1587 tokens ( 0.93 ms per token, 1074.75 tokens per second) 3.12.703.859 I slot print_timing: id 0 | task 5012 | eval time = 154.50 ms / 2 tokens ( 154.50 ms per token, 6.47 tokens per second) 3.12.703.860 I slot print_timing: id 0 | task 5012 | total time = 1631.12 ms / 1589 tokens 3.12.703.861 I slot print_timing: id 0 | task 5012 | graphs reused = 3583 3.12.703.862 I slot print_timing: id 0 | task 5012 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.703.942 I slot release: id 0 | task 5012 | stop processing: n_tokens = 1588, truncated = 0 3.12.704.258 I slot print_timing: id 1 | task 5013 | prompt eval time = 1473.77 ms / 1629 tokens ( 0.90 ms per token, 1105.33 tokens per second) 3.12.704.262 I slot print_timing: id 1 | task 5013 | eval time = 154.20 ms / 2 tokens ( 154.20 ms per token, 6.49 tokens per second) 3.12.704.263 I slot print_timing: id 1 | task 5013 | total time = 1627.97 ms / 1631 tokens 3.12.704.263 I slot print_timing: id 1 | task 5013 | graphs reused = 3583 3.12.704.264 I slot print_timing: id 1 | task 5013 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.704.314 I slot release: id 1 | task 5013 | stop processing: n_tokens = 1630, truncated = 0 3.12.704.329 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.861 (> 0.100 thold), f_keep = 0.883 3.12.704.479 I slot launch_slot_: id 0 | task 5023 | processing task, is_child = 0 3.12.704.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.613 MiB) 3.12.757.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.112 MiB) 3.12.808.579 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.860 3.12.808.741 I slot launch_slot_: id 1 | task 5024 | processing task, is_child = 0 3.12.808.809 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 192453004 3.12.808.981 I slot launch_slot_: id 2 | task 5025 | processing task, is_child = 0 3.13.338.382 I slot print_timing: id 0 | task 5023 | prompt eval time = 457.46 ms / 255 tokens ( 1.79 ms per token, 557.42 tokens per second) 3.13.338.388 I slot print_timing: id 0 | task 5023 | eval time = 71.91 ms / 2 tokens ( 71.91 ms per token, 13.91 tokens per second) 3.13.338.389 I slot print_timing: id 0 | task 5023 | total time = 529.38 ms / 257 tokens 3.13.338.390 I slot print_timing: id 0 | task 5023 | graphs reused = 3583 3.13.338.391 I slot print_timing: id 0 | task 5023 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.338.468 I slot release: id 0 | task 5023 | stop processing: n_tokens = 1630, truncated = 0 3.13.338.915 I slot print_timing: id 1 | task 5024 | prompt eval time = 438.35 ms / 344 tokens ( 1.27 ms per token, 784.76 tokens per second) 3.13.338.918 I slot print_timing: id 1 | task 5024 | eval time = 71.83 ms / 2 tokens ( 71.83 ms per token, 13.92 tokens per second) 3.13.338.919 I slot print_timing: id 1 | task 5024 | total time = 510.18 ms / 346 tokens 3.13.338.920 I slot print_timing: id 1 | task 5024 | graphs reused = 3583 3.13.338.920 I slot print_timing: id 1 | task 5024 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.338.988 I slot release: id 1 | task 5024 | stop processing: n_tokens = 1719, truncated = 0 3.13.466.865 I slot print_timing: id 3 | task 5019 | prompt eval time = 1139.92 ms / 1615 tokens ( 0.71 ms per token, 1416.76 tokens per second) 3.13.466.870 I slot print_timing: id 3 | task 5019 | eval time = 127.16 ms / 2 tokens ( 127.16 ms per token, 7.86 tokens per second) 3.13.466.871 I slot print_timing: id 3 | task 5019 | total time = 1267.08 ms / 1617 tokens 3.13.466.872 I slot print_timing: id 3 | task 5019 | graphs reused = 3583 3.13.466.873 I slot print_timing: id 3 | task 5019 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.466.948 I slot release: id 3 | task 5019 | stop processing: n_tokens = 1616, truncated = 0 3.13.466.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 193241065 3.13.467.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.114 MiB) 3.13.527.291 I slot launch_slot_: id 0 | task 5030 | processing task, is_child = 0 3.13.527.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.738 MiB) 3.13.585.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.923 MiB) 3.13.638.354 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 193241585 3.13.638.603 I slot launch_slot_: id 1 | task 5031 | processing task, is_child = 0 3.13.638.691 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1616, t_last = 193369545 3.13.638.866 I slot launch_slot_: id 3 | task 5032 | processing task, is_child = 0 3.14.098.424 I slot print_timing: id 2 | task 5025 | prompt eval time = 1150.62 ms / 838 tokens ( 1.37 ms per token, 728.30 tokens per second) 3.14.098.428 I slot print_timing: id 2 | task 5025 | eval time = 99.26 ms / 2 tokens ( 99.26 ms per token, 10.07 tokens per second) 3.14.098.430 I slot print_timing: id 2 | task 5025 | total time = 1249.88 ms / 840 tokens 3.14.098.431 I slot print_timing: id 2 | task 5025 | graphs reused = 3583 3.14.098.432 I slot print_timing: id 2 | task 5025 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.098.480 I slot release: id 2 | task 5025 | stop processing: n_tokens = 839, truncated = 0 3.14.326.220 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 194001076 3.14.326.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.960 MiB) 3.14.415.285 I slot launch_slot_: id 2 | task 5037 | processing task, is_child = 0 3.14.776.942 I slot print_timing: id 0 | task 5030 | prompt eval time = 1077.56 ms / 865 tokens ( 1.25 ms per token, 802.74 tokens per second) 3.14.776.948 I slot print_timing: id 0 | task 5030 | eval time = 60.50 ms / 2 tokens ( 60.50 ms per token, 16.53 tokens per second) 3.14.776.950 I slot print_timing: id 0 | task 5030 | total time = 1138.06 ms / 867 tokens 3.14.776.951 I slot print_timing: id 0 | task 5030 | graphs reused = 3583 3.14.776.951 I slot print_timing: id 0 | task 5030 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.776.999 I slot release: id 0 | task 5030 | stop processing: n_tokens = 866, truncated = 0 3.14.777.318 I slot print_timing: id 1 | task 5031 | prompt eval time = 1074.48 ms / 842 tokens ( 1.28 ms per token, 783.63 tokens per second) 3.14.777.321 I slot print_timing: id 1 | task 5031 | eval time = 60.26 ms / 2 tokens ( 60.26 ms per token, 16.60 tokens per second) 3.14.777.321 I slot print_timing: id 1 | task 5031 | total time = 1134.74 ms / 844 tokens 3.14.777.322 I slot print_timing: id 1 | task 5031 | graphs reused = 3583 3.14.777.323 I slot print_timing: id 1 | task 5031 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.777.355 I slot release: id 1 | task 5031 | stop processing: n_tokens = 843, truncated = 0 3.14.777.680 I slot print_timing: id 3 | task 5032 | prompt eval time = 1059.25 ms / 859 tokens ( 1.23 ms per token, 810.95 tokens per second) 3.14.777.683 I slot print_timing: id 3 | task 5032 | eval time = 59.90 ms / 2 tokens ( 59.90 ms per token, 16.69 tokens per second) 3.14.777.683 I slot print_timing: id 3 | task 5032 | total time = 1119.15 ms / 861 tokens 3.14.777.684 I slot print_timing: id 3 | task 5032 | graphs reused = 3583 3.14.777.685 I slot print_timing: id 3 | task 5032 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.777.711 I slot release: id 3 | task 5032 | stop processing: n_tokens = 860, truncated = 0 3.14.793.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 194679595 3.14.881.350 I slot launch_slot_: id 0 | task 5042 | processing task, is_child = 0 3.14.881.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.424 MiB) 3.14.931.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.145 MiB) 3.14.977.269 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 194679951 3.14.977.469 I slot launch_slot_: id 1 | task 5043 | processing task, is_child = 0 3.14.977.526 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 194680307 3.14.977.678 I slot launch_slot_: id 3 | task 5044 | processing task, is_child = 0 3.15.557.024 I slot print_timing: id 2 | task 5037 | prompt eval time = 871.03 ms / 886 tokens ( 0.98 ms per token, 1017.18 tokens per second) 3.15.557.029 I slot print_timing: id 2 | task 5037 | eval time = 247.15 ms / 2 tokens ( 247.15 ms per token, 4.05 tokens per second) 3.15.557.030 I slot print_timing: id 2 | task 5037 | total time = 1118.18 ms / 888 tokens 3.15.557.031 I slot print_timing: id 2 | task 5037 | graphs reused = 3583 3.15.557.032 I slot print_timing: id 2 | task 5037 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.557.077 I slot release: id 2 | task 5037 | stop processing: n_tokens = 887, truncated = 0 3.15.709.421 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 195459672 3.15.709.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.863 MiB) 3.15.756.087 I slot launch_slot_: id 2 | task 5049 | processing task, is_child = 0 3.15.981.450 I slot print_timing: id 1 | task 5043 | prompt eval time = 905.29 ms / 749 tokens ( 1.21 ms per token, 827.36 tokens per second) 3.15.981.455 I slot print_timing: id 1 | task 5043 | eval time = 94.79 ms / 2 tokens ( 94.79 ms per token, 10.55 tokens per second) 3.15.981.456 I slot print_timing: id 1 | task 5043 | total time = 1000.08 ms / 751 tokens 3.15.981.457 I slot print_timing: id 1 | task 5043 | graphs reused = 3583 3.15.981.458 I slot print_timing: id 1 | task 5043 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.981.498 I slot release: id 1 | task 5043 | stop processing: n_tokens = 750, truncated = 0 3.15.981.863 I slot print_timing: id 3 | task 5044 | prompt eval time = 885.19 ms / 691 tokens ( 1.28 ms per token, 780.62 tokens per second) 3.15.981.867 I slot print_timing: id 3 | task 5044 | eval time = 94.42 ms / 2 tokens ( 94.42 ms per token, 10.59 tokens per second) 3.15.981.867 I slot print_timing: id 3 | task 5044 | total time = 979.62 ms / 693 tokens 3.15.981.868 I slot print_timing: id 3 | task 5044 | graphs reused = 3583 3.15.981.868 I slot print_timing: id 3 | task 5044 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.981.899 I slot release: id 3 | task 5044 | stop processing: n_tokens = 692, truncated = 0 3.16.088.814 I slot print_timing: id 0 | task 5042 | prompt eval time = 1003.44 ms / 780 tokens ( 1.29 ms per token, 777.33 tokens per second) 3.16.088.820 I slot print_timing: id 0 | task 5042 | eval time = 107.68 ms / 2 tokens ( 107.68 ms per token, 9.29 tokens per second) 3.16.088.822 I slot print_timing: id 0 | task 5042 | total time = 1111.11 ms / 782 tokens 3.16.088.823 I slot print_timing: id 0 | task 5042 | graphs reused = 3583 3.16.088.823 I slot print_timing: id 0 | task 5042 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.088.870 I slot release: id 0 | task 5042 | stop processing: n_tokens = 781, truncated = 0 3.16.088.887 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.866 3.16.089.032 I slot launch_slot_: id 3 | task 5053 | processing task, is_child = 0 3.16.089.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.863 MiB) 3.16.138.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.986 MiB) 3.16.346.136 I slot print_timing: id 2 | task 5049 | prompt eval time = 554.23 ms / 712 tokens ( 0.78 ms per token, 1284.67 tokens per second) 3.16.346.142 I slot print_timing: id 2 | task 5049 | eval time = 15.64 ms / 2 tokens ( 15.64 ms per token, 63.93 tokens per second) 3.16.346.143 I slot print_timing: id 2 | task 5049 | total time = 569.87 ms / 714 tokens 3.16.346.144 I slot print_timing: id 2 | task 5049 | graphs reused = 3583 3.16.346.145 I slot print_timing: id 2 | task 5049 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.346.180 I slot release: id 2 | task 5049 | stop processing: n_tokens = 713, truncated = 0 3.16.346.447 I slot print_timing: id 3 | task 5053 | prompt eval time = 127.49 ms / 107 tokens ( 1.19 ms per token, 839.30 tokens per second) 3.16.346.450 I slot print_timing: id 3 | task 5053 | eval time = 15.39 ms / 2 tokens ( 15.39 ms per token, 64.96 tokens per second) 3.16.346.451 I slot print_timing: id 3 | task 5053 | total time = 142.88 ms / 109 tokens 3.16.346.452 I slot print_timing: id 3 | task 5053 | graphs reused = 3583 3.16.346.452 I slot print_timing: id 3 | task 5053 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.346.472 I slot release: id 3 | task 5053 | stop processing: n_tokens = 679, truncated = 0