C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\22086870b009\Ornith-1.5-9B-Q8_0.gguf --host 127.0.0.1 --port 8091 -c 16384 -np 4 -ngl 29 -fa on --jinja --seed 1234 --chat-template-kwargs "{\"enable_thinking\": false}" --no-webui -a quant 0.00.094.247 W Setting 'enable_thinking' via --chat-template-kwargs is deprecated. Use --reasoning on / --reasoning off instead. 0.00.094.430 I srv llama_server: initializing ... 0.00.094.434 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.094.547 I srv init_listene: The UI is disabled 0.00.094.549 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.094.633 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) 0.00.109.445 I srv load_model: loading model 'C:\quantdiff\dl\campaign\22086870b009\Ornith-1.5-9B-Q8_0.gguf' 0.00.981.485 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.00.981.499 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.00.981.524 W model has unused tensor blk.32.attn_q.weight (size = 35651584 bytes) -- ignoring 0.00.981.533 W model has unused tensor blk.32.attn_k.weight (size = 4456448 bytes) -- ignoring 0.00.981.542 W model has unused tensor blk.32.attn_v.weight (size = 4456448 bytes) -- ignoring 0.00.981.575 W model has unused tensor blk.32.attn_output.weight (size = 17825792 bytes) -- ignoring 0.00.981.586 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.981.595 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.981.604 W model has unused tensor blk.32.ffn_gate.weight (size = 53477376 bytes) -- ignoring 0.00.981.612 W model has unused tensor blk.32.ffn_down.weight (size = 53477376 bytes) -- ignoring 0.00.981.621 W model has unused tensor blk.32.ffn_up.weight (size = 53477376 bytes) -- ignoring 0.00.981.631 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring 0.00.981.641 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.00.981.650 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.00.981.679 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.03.656.132 I cmn init: llama threadpool init, n_threads = 8 0.03.869.017 I srv load_model: initializing, n_slots = 4, n_ctx_slot = 4096, kv_unified = 'false' 0.03.876.307 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.03.876.330 I srv llama_server: model loaded 0.03.876.334 I srv llama_server: listening on http://127.0.0.1:8091 0.43.806.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.43.806.365 I slot launch_slot_: id 0 | task 1 | processing task, is_child = 0 0.43.806.370 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.43.806.393 I slot launch_slot_: id 1 | task 2 | processing task, is_child = 0 0.43.806.396 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.43.806.418 I slot launch_slot_: id 2 | task 0 | processing task, is_child = 0 0.44.211.164 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.44.211.378 I slot launch_slot_: id 3 | task 4 | processing task, is_child = 0 0.44.667.609 I slot print_timing: id 0 | task 1 | prompt eval time = 712.17 ms / 115 tokens ( 6.19 ms per token, 161.48 tokens per second) 0.44.667.615 I slot print_timing: id 0 | task 1 | eval time = 149.00 ms / 2 tokens ( 149.00 ms per token, 6.71 tokens per second) 0.44.667.616 I slot print_timing: id 0 | task 1 | total time = 861.17 ms / 117 tokens 0.44.667.623 I slot print_timing: id 0 | task 1 | graphs reused = 1 0.44.667.625 I slot print_timing: id 0 | task 1 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.667.658 I slot release: id 0 | task 1 | stop processing: n_tokens = 116, truncated = 0 0.44.667.959 I slot print_timing: id 1 | task 2 | prompt eval time = 712.71 ms / 122 tokens ( 5.84 ms per token, 171.18 tokens per second) 0.44.667.962 I slot print_timing: id 1 | task 2 | eval time = 148.80 ms / 2 tokens ( 148.80 ms per token, 6.72 tokens per second) 0.44.667.963 I slot print_timing: id 1 | task 2 | total time = 861.51 ms / 124 tokens 0.44.667.963 I slot print_timing: id 1 | task 2 | graphs reused = 1 0.44.667.964 I slot print_timing: id 1 | task 2 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.667.982 I slot release: id 1 | task 2 | stop processing: n_tokens = 123, truncated = 0 0.44.668.319 I slot print_timing: id 2 | task 0 | prompt eval time = 713.26 ms / 115 tokens ( 6.20 ms per token, 161.23 tokens per second) 0.44.668.325 I slot print_timing: id 2 | task 0 | eval time = 148.60 ms / 2 tokens ( 148.60 ms per token, 6.73 tokens per second) 0.44.668.326 I slot print_timing: id 2 | task 0 | total time = 861.86 ms / 117 tokens 0.44.668.326 I slot print_timing: id 2 | task 0 | graphs reused = 1 0.44.668.327 I slot print_timing: id 2 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.668.344 I slot release: id 2 | task 0 | stop processing: n_tokens = 116, truncated = 0 0.44.722.337 I slot print_timing: id 3 | task 4 | prompt eval time = 421.82 ms / 130 tokens ( 3.24 ms per token, 308.19 tokens per second) 0.44.722.342 I slot print_timing: id 3 | task 4 | eval time = 53.32 ms / 2 tokens ( 53.32 ms per token, 18.76 tokens per second) 0.44.722.343 I slot print_timing: id 3 | task 4 | total time = 475.14 ms / 132 tokens 0.44.722.344 I slot print_timing: id 3 | task 4 | graphs reused = 1 0.44.722.344 I slot print_timing: id 3 | task 4 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.722.370 I slot release: id 3 | task 4 | stop processing: n_tokens = 131, truncated = 0 0.44.722.382 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.191 (> 0.100 thold), f_keep = 0.236 0.44.739.316 I slot launch_slot_: id 1 | task 8 | processing task, is_child = 0 0.44.793.319 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.241 0.44.793.575 I slot launch_slot_: id 0 | task 9 | processing task, is_child = 0 0.44.793.651 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 0.44.793.854 I slot launch_slot_: id 2 | task 10 | processing task, is_child = 0 0.44.793.896 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.221 0.44.794.086 I slot launch_slot_: id 3 | task 11 | processing task, is_child = 0 0.45.618.432 I slot print_timing: id 0 | task 9 | prompt eval time = 757.42 ms / 160 tokens ( 4.73 ms per token, 211.24 tokens per second) 0.45.618.438 I slot print_timing: id 0 | task 9 | eval time = 66.91 ms / 2 tokens ( 66.91 ms per token, 14.95 tokens per second) 0.45.618.439 I slot print_timing: id 0 | task 9 | total time = 824.32 ms / 162 tokens 0.45.618.440 I slot print_timing: id 0 | task 9 | graphs reused = 1 0.45.618.440 I slot print_timing: id 0 | task 9 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.618.474 I slot release: id 0 | task 9 | stop processing: n_tokens = 161, truncated = 0 0.45.618.764 I slot print_timing: id 1 | task 8 | prompt eval time = 756.25 ms / 152 tokens ( 4.98 ms per token, 200.99 tokens per second) 0.45.618.767 I slot print_timing: id 1 | task 8 | eval time = 66.68 ms / 2 tokens ( 66.68 ms per token, 15.00 tokens per second) 0.45.618.768 I slot print_timing: id 1 | task 8 | total time = 822.93 ms / 154 tokens 0.45.618.768 I slot print_timing: id 1 | task 8 | graphs reused = 1 0.45.618.769 I slot print_timing: id 1 | task 8 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.618.786 I slot release: id 1 | task 8 | stop processing: n_tokens = 153, truncated = 0 0.45.619.094 I slot print_timing: id 2 | task 10 | prompt eval time = 755.08 ms / 200 tokens ( 3.78 ms per token, 264.87 tokens per second) 0.45.619.097 I slot print_timing: id 2 | task 10 | eval time = 66.42 ms / 2 tokens ( 66.42 ms per token, 15.06 tokens per second) 0.45.619.098 I slot print_timing: id 2 | task 10 | total time = 821.50 ms / 202 tokens 0.45.619.099 I slot print_timing: id 2 | task 10 | graphs reused = 1 0.45.619.099 I slot print_timing: id 2 | task 10 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.619.118 I slot release: id 2 | task 10 | stop processing: n_tokens = 201, truncated = 0 0.45.619.428 I slot print_timing: id 3 | task 11 | prompt eval time = 753.96 ms / 108 tokens ( 6.98 ms per token, 143.24 tokens per second) 0.45.619.432 I slot print_timing: id 3 | task 11 | eval time = 66.10 ms / 2 tokens ( 66.10 ms per token, 15.13 tokens per second) 0.45.619.433 I slot print_timing: id 3 | task 11 | total time = 820.06 ms / 110 tokens 0.45.619.433 I slot print_timing: id 3 | task 11 | graphs reused = 1 0.45.619.434 I slot print_timing: id 3 | task 11 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.619.447 I slot release: id 3 | task 11 | stop processing: n_tokens = 109, truncated = 0 0.45.628.420 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 0.45.648.036 I slot launch_slot_: id 1 | task 15 | processing task, is_child = 0 0.45.701.105 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 0.45.701.300 I slot launch_slot_: id 0 | task 16 | processing task, is_child = 0 0.45.701.346 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 0.45.701.507 I slot launch_slot_: id 2 | task 17 | processing task, is_child = 0 0.45.701.529 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 0.45.701.664 I slot launch_slot_: id 3 | task 18 | processing task, is_child = 0 0.46.433.866 I slot print_timing: id 0 | task 16 | prompt eval time = 667.98 ms / 150 tokens ( 4.45 ms per token, 224.56 tokens per second) 0.46.433.872 I slot print_timing: id 0 | task 16 | eval time = 64.20 ms / 2 tokens ( 64.20 ms per token, 15.58 tokens per second) 0.46.433.874 I slot print_timing: id 0 | task 16 | total time = 732.18 ms / 152 tokens 0.46.433.874 I slot print_timing: id 0 | task 16 | graphs reused = 1 0.46.433.875 I slot print_timing: id 0 | task 16 | graph reallocs = 1 / 0 (same size) / (changed size) 0.46.433.910 I slot release: id 0 | task 16 | stop processing: n_tokens = 151, truncated = 0 0.46.434.248 I slot print_timing: id 1 | task 15 | prompt eval time = 667.28 ms / 118 tokens ( 5.65 ms per token, 176.84 tokens per second) 0.46.434.253 I slot print_timing: id 1 | task 15 | eval time = 64.02 ms / 2 tokens ( 64.02 ms per token, 15.62 tokens per second) 0.46.434.254 I slot print_timing: id 1 | task 15 | total time = 731.30 ms / 120 tokens 0.46.434.255 I slot print_timing: id 1 | task 15 | graphs reused = 1 0.46.434.256 I slot print_timing: id 1 | task 15 | graph reallocs = 1 / 0 (same size) / (changed size) 0.46.434.276 I slot release: id 1 | task 15 | stop processing: n_tokens = 119, truncated = 0 0.46.434.617 I slot print_timing: id 2 | task 17 | prompt eval time = 666.58 ms / 117 tokens ( 5.70 ms per token, 175.52 tokens per second) 0.46.434.621 I slot print_timing: id 2 | task 17 | eval time = 63.83 ms / 2 tokens ( 63.83 ms per token, 15.67 tokens per second) 0.46.434.622 I slot print_timing: id 2 | task 17 | total time = 730.41 ms / 119 tokens 0.46.434.623 I slot print_timing: id 2 | task 17 | graphs reused = 1 0.46.434.624 I slot print_timing: id 2 | task 17 | graph reallocs = 1 / 0 (same size) / (changed size) 0.46.434.639 I slot release: id 2 | task 17 | stop processing: n_tokens = 118, truncated = 0 0.46.434.989 I slot print_timing: id 3 | task 18 | prompt eval time = 665.85 ms / 125 tokens ( 5.33 ms per token, 187.73 tokens per second) 0.46.434.993 I slot print_timing: id 3 | task 18 | eval time = 63.65 ms / 2 tokens ( 63.65 ms per token, 15.71 tokens per second) 0.46.434.994 I slot print_timing: id 3 | task 18 | total time = 729.49 ms / 127 tokens 0.46.434.995 I slot print_timing: id 3 | task 18 | graphs reused = 1 0.46.434.995 I slot print_timing: id 3 | task 18 | graph reallocs = 1 / 0 (same size) / (changed size) 0.46.435.010 I slot release: id 3 | task 18 | stop processing: n_tokens = 126, truncated = 0 0.46.444.209 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.185 0.46.461.568 I slot launch_slot_: id 0 | task 22 | processing task, is_child = 0 0.46.512.951 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.155 (> 0.100 thold), f_keep = 0.235 0.46.513.210 I slot launch_slot_: id 1 | task 23 | processing task, is_child = 0 0.46.513.284 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.235 (> 0.100 thold), f_keep = 0.237 0.46.513.493 I slot launch_slot_: id 2 | task 24 | processing task, is_child = 0 0.46.513.533 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 0.46.513.720 I slot launch_slot_: id 3 | task 25 | processing task, is_child = 0 0.47.403.601 I slot print_timing: id 0 | task 22 | prompt eval time = 825.16 ms / 143 tokens ( 5.77 ms per token, 173.30 tokens per second) 0.47.403.607 I slot print_timing: id 0 | task 22 | eval time = 64.70 ms / 2 tokens ( 64.70 ms per token, 15.46 tokens per second) 0.47.403.609 I slot print_timing: id 0 | task 22 | total time = 889.86 ms / 145 tokens 0.47.403.610 I slot print_timing: id 0 | task 22 | graphs reused = 1 0.47.403.611 I slot print_timing: id 0 | task 22 | graph reallocs = 2 / 0 (same size) / (changed size) 0.47.403.642 I slot release: id 0 | task 22 | stop processing: n_tokens = 144, truncated = 0 0.47.403.973 I slot print_timing: id 1 | task 23 | prompt eval time = 824.40 ms / 181 tokens ( 4.55 ms per token, 219.55 tokens per second) 0.47.403.978 I slot print_timing: id 1 | task 23 | eval time = 64.41 ms / 2 tokens ( 64.41 ms per token, 15.53 tokens per second) 0.47.403.979 I slot print_timing: id 1 | task 23 | total time = 888.81 ms / 183 tokens 0.47.403.980 I slot print_timing: id 1 | task 23 | graphs reused = 1 0.47.403.982 I slot print_timing: id 1 | task 23 | graph reallocs = 2 / 0 (same size) / (changed size) 0.47.404.006 I slot release: id 1 | task 23 | stop processing: n_tokens = 182, truncated = 0 0.47.404.341 I slot print_timing: id 2 | task 24 | prompt eval time = 823.81 ms / 119 tokens ( 6.92 ms per token, 144.45 tokens per second) 0.47.404.345 I slot print_timing: id 2 | task 24 | eval time = 64.12 ms / 2 tokens ( 64.12 ms per token, 15.60 tokens per second) 0.47.404.346 I slot print_timing: id 2 | task 24 | total time = 887.93 ms / 121 tokens 0.47.404.347 I slot print_timing: id 2 | task 24 | graphs reused = 1 0.47.404.348 I slot print_timing: id 2 | task 24 | graph reallocs = 2 / 0 (same size) / (changed size) 0.47.404.364 I slot release: id 2 | task 24 | stop processing: n_tokens = 120, truncated = 0 0.47.404.718 I slot print_timing: id 3 | task 25 | prompt eval time = 823.12 ms / 136 tokens ( 6.05 ms per token, 165.22 tokens per second) 0.47.404.722 I slot print_timing: id 3 | task 25 | eval time = 63.93 ms / 2 tokens ( 63.93 ms per token, 15.64 tokens per second) 0.47.404.724 I slot print_timing: id 3 | task 25 | total time = 887.06 ms / 138 tokens 0.47.404.724 I slot print_timing: id 3 | task 25 | graphs reused = 1 0.47.404.725 I slot print_timing: id 3 | task 25 | graph reallocs = 2 / 0 (same size) / (changed size) 0.47.404.741 I slot release: id 3 | task 25 | stop processing: n_tokens = 137, truncated = 0 0.47.412.852 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.194 0.47.439.404 I slot launch_slot_: id 0 | task 29 | processing task, is_child = 0 0.47.490.326 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.154 0.47.499.273 I slot launch_slot_: id 1 | task 30 | processing task, is_child = 0 0.47.499.342 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.233 0.47.499.499 I slot launch_slot_: id 2 | task 31 | processing task, is_child = 0 0.47.499.523 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.157 (> 0.100 thold), f_keep = 0.204 0.47.499.660 I slot launch_slot_: id 3 | task 32 | processing task, is_child = 0 0.48.332.891 I slot print_timing: id 0 | task 29 | prompt eval time = 769.30 ms / 131 tokens ( 5.87 ms per token, 170.29 tokens per second) 0.48.332.897 I slot print_timing: id 0 | task 29 | eval time = 63.91 ms / 2 tokens ( 63.91 ms per token, 15.65 tokens per second) 0.48.332.898 I slot print_timing: id 0 | task 29 | total time = 833.21 ms / 133 tokens 0.48.332.899 I slot print_timing: id 0 | task 29 | graphs reused = 1 0.48.332.900 I slot print_timing: id 0 | task 29 | graph reallocs = 2 / 0 (same size) / (changed size) 0.48.332.926 I slot release: id 0 | task 29 | stop processing: n_tokens = 132, truncated = 0 0.48.333.206 I slot print_timing: id 1 | task 30 | prompt eval time = 768.64 ms / 122 tokens ( 6.30 ms per token, 158.72 tokens per second) 0.48.333.209 I slot print_timing: id 1 | task 30 | eval time = 63.67 ms / 2 tokens ( 63.67 ms per token, 15.71 tokens per second) 0.48.333.210 I slot print_timing: id 1 | task 30 | total time = 832.30 ms / 124 tokens 0.48.333.210 I slot print_timing: id 1 | task 30 | graphs reused = 1 0.48.333.211 I slot print_timing: id 1 | task 30 | graph reallocs = 2 / 0 (same size) / (changed size) 0.48.333.226 I slot release: id 1 | task 30 | stop processing: n_tokens = 123, truncated = 0 0.48.333.564 I slot print_timing: id 2 | task 31 | prompt eval time = 768.03 ms / 144 tokens ( 5.33 ms per token, 187.49 tokens per second) 0.48.333.569 I slot print_timing: id 2 | task 31 | eval time = 63.42 ms / 2 tokens ( 63.42 ms per token, 15.77 tokens per second) 0.48.333.570 I slot print_timing: id 2 | task 31 | total time = 831.45 ms / 146 tokens 0.48.333.571 I slot print_timing: id 2 | task 31 | graphs reused = 1 0.48.333.572 I slot print_timing: id 2 | task 31 | graph reallocs = 2 / 0 (same size) / (changed size) 0.48.333.591 I slot release: id 2 | task 31 | stop processing: n_tokens = 145, truncated = 0 0.48.333.927 I slot print_timing: id 3 | task 32 | prompt eval time = 767.39 ms / 178 tokens ( 4.31 ms per token, 231.96 tokens per second) 0.48.333.931 I slot print_timing: id 3 | task 32 | eval time = 63.23 ms / 2 tokens ( 63.23 ms per token, 15.82 tokens per second) 0.48.333.932 I slot print_timing: id 3 | task 32 | total time = 830.61 ms / 180 tokens 0.48.333.933 I slot print_timing: id 3 | task 32 | graphs reused = 1 0.48.333.934 I slot print_timing: id 3 | task 32 | graph reallocs = 2 / 0 (same size) / (changed size) 0.48.333.951 I slot release: id 3 | task 32 | stop processing: n_tokens = 179, truncated = 0 0.48.342.752 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.197 (> 0.100 thold), f_keep = 0.212 0.48.359.963 I slot launch_slot_: id 0 | task 36 | processing task, is_child = 0 0.48.410.881 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 0.48.411.141 I slot launch_slot_: id 1 | task 38 | processing task, is_child = 0 0.48.411.221 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.162 0.48.411.415 I slot launch_slot_: id 3 | task 37 | processing task, is_child = 0 0.48.411.457 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.193 0.48.411.637 I slot launch_slot_: id 2 | task 39 | processing task, is_child = 0 0.49.353.034 I slot print_timing: id 0 | task 36 | prompt eval time = 876.38 ms / 142 tokens ( 6.17 ms per token, 162.03 tokens per second) 0.49.353.041 I slot print_timing: id 0 | task 36 | eval time = 64.99 ms / 2 tokens ( 64.99 ms per token, 15.39 tokens per second) 0.49.353.042 I slot print_timing: id 0 | task 36 | total time = 941.37 ms / 144 tokens 0.49.353.043 I slot print_timing: id 0 | task 36 | graphs reused = 1 0.49.353.044 I slot print_timing: id 0 | task 36 | graph reallocs = 5 / 0 (same size) / (changed size) 0.49.353.076 I slot release: id 0 | task 36 | stop processing: n_tokens = 143, truncated = 0 0.49.353.405 I slot print_timing: id 1 | task 38 | prompt eval time = 875.67 ms / 120 tokens ( 7.30 ms per token, 137.04 tokens per second) 0.49.353.408 I slot print_timing: id 1 | task 38 | eval time = 64.80 ms / 2 tokens ( 64.80 ms per token, 15.43 tokens per second) 0.49.353.409 I slot print_timing: id 1 | task 38 | total time = 940.47 ms / 122 tokens 0.49.353.409 I slot print_timing: id 1 | task 38 | graphs reused = 1 0.49.353.410 I slot print_timing: id 1 | task 38 | graph reallocs = 5 / 0 (same size) / (changed size) 0.49.353.423 I slot release: id 1 | task 38 | stop processing: n_tokens = 121, truncated = 0 0.49.353.738 I slot print_timing: id 2 | task 39 | prompt eval time = 875.01 ms / 113 tokens ( 7.74 ms per token, 129.14 tokens per second) 0.49.353.743 I slot print_timing: id 2 | task 39 | eval time = 64.54 ms / 2 tokens ( 64.54 ms per token, 15.49 tokens per second) 0.49.353.744 I slot print_timing: id 2 | task 39 | total time = 939.55 ms / 115 tokens 0.49.353.744 I slot print_timing: id 2 | task 39 | graphs reused = 1 0.49.353.745 I slot print_timing: id 2 | task 39 | graph reallocs = 5 / 0 (same size) / (changed size) 0.49.353.759 I slot release: id 2 | task 39 | stop processing: n_tokens = 114, truncated = 0 0.49.354.083 I slot print_timing: id 3 | task 37 | prompt eval time = 874.33 ms / 144 tokens ( 6.07 ms per token, 164.70 tokens per second) 0.49.354.086 I slot print_timing: id 3 | task 37 | eval time = 64.32 ms / 2 tokens ( 64.32 ms per token, 15.55 tokens per second) 0.49.354.087 I slot print_timing: id 3 | task 37 | total time = 938.64 ms / 146 tokens 0.49.354.088 I slot print_timing: id 3 | task 37 | graphs reused = 1 0.49.354.088 I slot print_timing: id 3 | task 37 | graph reallocs = 5 / 0 (same size) / (changed size) 0.49.354.101 I slot release: id 3 | task 37 | stop processing: n_tokens = 145, truncated = 0 0.49.362.652 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.240 0.49.380.150 I slot launch_slot_: id 1 | task 43 | processing task, is_child = 0 0.49.433.608 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.196 0.49.433.826 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.49.433.871 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.246 0.49.434.026 I slot launch_slot_: id 2 | task 45 | processing task, is_child = 0 0.49.434.051 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.196 (> 0.100 thold), f_keep = 0.193 0.49.434.185 I slot launch_slot_: id 3 | task 46 | processing task, is_child = 0 0.50.294.072 I slot print_timing: id 0 | task 44 | prompt eval time = 794.74 ms / 109 tokens ( 7.29 ms per token, 137.15 tokens per second) 0.50.294.078 I slot print_timing: id 0 | task 44 | eval time = 65.12 ms / 2 tokens ( 65.12 ms per token, 15.36 tokens per second) 0.50.294.080 I slot print_timing: id 0 | task 44 | total time = 859.86 ms / 111 tokens 0.50.294.081 I slot print_timing: id 0 | task 44 | graphs reused = 1 0.50.294.082 I slot print_timing: id 0 | task 44 | graph reallocs = 7 / 0 (same size) / (changed size) 0.50.294.112 I slot release: id 0 | task 44 | stop processing: n_tokens = 110, truncated = 0 0.50.294.435 I slot print_timing: id 1 | task 43 | prompt eval time = 794.14 ms / 112 tokens ( 7.09 ms per token, 141.03 tokens per second) 0.50.294.438 I slot print_timing: id 1 | task 43 | eval time = 64.83 ms / 2 tokens ( 64.83 ms per token, 15.42 tokens per second) 0.50.294.438 I slot print_timing: id 1 | task 43 | total time = 858.97 ms / 114 tokens 0.50.294.439 I slot print_timing: id 1 | task 43 | graphs reused = 1 0.50.294.440 I slot print_timing: id 1 | task 43 | graph reallocs = 7 / 0 (same size) / (changed size) 0.50.294.456 I slot release: id 1 | task 43 | stop processing: n_tokens = 113, truncated = 0 0.50.294.834 I slot print_timing: id 2 | task 45 | prompt eval time = 793.39 ms / 123 tokens ( 6.45 ms per token, 155.03 tokens per second) 0.50.294.839 I slot print_timing: id 2 | task 45 | eval time = 64.65 ms / 2 tokens ( 64.65 ms per token, 15.47 tokens per second) 0.50.294.840 I slot print_timing: id 2 | task 45 | total time = 858.03 ms / 125 tokens 0.50.294.841 I slot print_timing: id 2 | task 45 | graphs reused = 1 0.50.294.842 I slot print_timing: id 2 | task 45 | graph reallocs = 7 / 0 (same size) / (changed size) 0.50.294.864 I slot release: id 2 | task 45 | stop processing: n_tokens = 124, truncated = 0 0.50.295.217 I slot print_timing: id 3 | task 46 | prompt eval time = 792.20 ms / 143 tokens ( 5.54 ms per token, 180.51 tokens per second) 0.50.295.224 I slot print_timing: id 3 | task 46 | eval time = 64.45 ms / 2 tokens ( 64.45 ms per token, 15.52 tokens per second) 0.50.295.225 I slot print_timing: id 3 | task 46 | total time = 856.65 ms / 145 tokens 0.50.295.226 I slot print_timing: id 3 | task 46 | graphs reused = 1 0.50.295.227 I slot print_timing: id 3 | task 46 | graph reallocs = 7 / 0 (same size) / (changed size) 0.50.295.243 I slot release: id 3 | task 46 | stop processing: n_tokens = 144, truncated = 0 0.50.304.328 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.283 0.50.323.419 I slot launch_slot_: id 1 | task 51 | processing task, is_child = 0 0.50.374.274 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.206 (> 0.100 thold), f_keep = 0.255 0.50.374.533 I slot launch_slot_: id 0 | task 50 | processing task, is_child = 0 0.50.374.611 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.226 0.50.374.814 I slot launch_slot_: id 2 | task 52 | processing task, is_child = 0 0.50.374.856 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.194 0.50.384.429 I slot launch_slot_: id 3 | task 53 | processing task, is_child = 0 0.51.166.018 I slot print_timing: id 0 | task 50 | prompt eval time = 716.33 ms / 136 tokens ( 5.27 ms per token, 189.86 tokens per second) 0.51.166.023 I slot print_timing: id 0 | task 50 | eval time = 65.23 ms / 2 tokens ( 65.23 ms per token, 15.33 tokens per second) 0.51.166.024 I slot print_timing: id 0 | task 50 | total time = 781.56 ms / 138 tokens 0.51.166.025 I slot print_timing: id 0 | task 50 | graphs reused = 1 0.51.166.026 I slot print_timing: id 0 | task 50 | graph reallocs = 8 / 0 (same size) / (changed size) 0.51.166.053 I slot release: id 0 | task 50 | stop processing: n_tokens = 137, truncated = 0 0.51.166.349 I slot print_timing: id 1 | task 51 | prompt eval time = 715.63 ms / 129 tokens ( 5.55 ms per token, 180.26 tokens per second) 0.51.166.352 I slot print_timing: id 1 | task 51 | eval time = 64.94 ms / 2 tokens ( 64.94 ms per token, 15.40 tokens per second) 0.51.166.353 I slot print_timing: id 1 | task 51 | total time = 780.57 ms / 131 tokens 0.51.166.354 I slot print_timing: id 1 | task 51 | graphs reused = 1 0.51.166.354 I slot print_timing: id 1 | task 51 | graph reallocs = 8 / 0 (same size) / (changed size) 0.51.166.367 I slot release: id 1 | task 51 | stop processing: n_tokens = 130, truncated = 0 0.51.166.667 I slot print_timing: id 2 | task 52 | prompt eval time = 714.97 ms / 102 tokens ( 7.01 ms per token, 142.66 tokens per second) 0.51.166.670 I slot print_timing: id 2 | task 52 | eval time = 64.68 ms / 2 tokens ( 64.68 ms per token, 15.46 tokens per second) 0.51.166.671 I slot print_timing: id 2 | task 52 | total time = 779.65 ms / 104 tokens 0.51.166.671 I slot print_timing: id 2 | task 52 | graphs reused = 1 0.51.166.672 I slot print_timing: id 2 | task 52 | graph reallocs = 8 / 0 (same size) / (changed size) 0.51.166.684 I slot release: id 2 | task 52 | stop processing: n_tokens = 103, truncated = 0 0.51.167.006 I slot print_timing: id 3 | task 53 | prompt eval time = 714.31 ms / 112 tokens ( 6.38 ms per token, 156.79 tokens per second) 0.51.167.011 I slot print_timing: id 3 | task 53 | eval time = 64.45 ms / 2 tokens ( 64.45 ms per token, 15.52 tokens per second) 0.51.167.012 I slot print_timing: id 3 | task 53 | total time = 778.76 ms / 114 tokens 0.51.167.012 I slot print_timing: id 3 | task 53 | graphs reused = 1 0.51.167.013 I slot print_timing: id 3 | task 53 | graph reallocs = 8 / 0 (same size) / (changed size) 0.51.167.027 I slot release: id 3 | task 53 | stop processing: n_tokens = 113, truncated = 0 0.51.175.736 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 0.51.193.907 I slot launch_slot_: id 0 | task 57 | processing task, is_child = 0 0.51.247.480 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.215 0.51.247.743 I slot launch_slot_: id 1 | task 58 | processing task, is_child = 0 0.51.247.817 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.158 (> 0.100 thold), f_keep = 0.272 0.51.248.027 I slot launch_slot_: id 2 | task 59 | processing task, is_child = 0 0.51.248.068 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.248 0.51.248.265 I slot launch_slot_: id 3 | task 60 | processing task, is_child = 0 0.52.080.025 I slot print_timing: id 0 | task 57 | prompt eval time = 768.97 ms / 182 tokens ( 4.23 ms per token, 236.68 tokens per second) 0.52.080.031 I slot print_timing: id 0 | task 57 | eval time = 62.77 ms / 2 tokens ( 62.77 ms per token, 15.93 tokens per second) 0.52.080.032 I slot print_timing: id 0 | task 57 | total time = 831.74 ms / 184 tokens 0.52.080.033 I slot print_timing: id 0 | task 57 | graphs reused = 1 0.52.080.034 I slot print_timing: id 0 | task 57 | graph reallocs = 9 / 0 (same size) / (changed size) 0.52.080.065 I slot release: id 0 | task 57 | stop processing: n_tokens = 183, truncated = 0 0.52.080.345 I slot print_timing: id 1 | task 58 | prompt eval time = 767.92 ms / 166 tokens ( 4.63 ms per token, 216.17 tokens per second) 0.52.080.350 I slot print_timing: id 1 | task 58 | eval time = 62.40 ms / 2 tokens ( 62.40 ms per token, 16.03 tokens per second) 0.52.080.351 I slot print_timing: id 1 | task 58 | total time = 830.32 ms / 168 tokens 0.52.080.351 I slot print_timing: id 1 | task 58 | graphs reused = 1 0.52.080.352 I slot print_timing: id 1 | task 58 | graph reallocs = 9 / 0 (same size) / (changed size) 0.52.080.371 I slot release: id 1 | task 58 | stop processing: n_tokens = 167, truncated = 0 0.52.080.660 I slot print_timing: id 2 | task 59 | prompt eval time = 766.74 ms / 177 tokens ( 4.33 ms per token, 230.85 tokens per second) 0.52.080.665 I slot print_timing: id 2 | task 59 | eval time = 62.13 ms / 2 tokens ( 62.13 ms per token, 16.10 tokens per second) 0.52.080.666 I slot print_timing: id 2 | task 59 | total time = 828.87 ms / 179 tokens 0.52.080.666 I slot print_timing: id 2 | task 59 | graphs reused = 1 0.52.080.667 I slot print_timing: id 2 | task 59 | graph reallocs = 9 / 0 (same size) / (changed size) 0.52.080.687 I slot release: id 2 | task 59 | stop processing: n_tokens = 178, truncated = 0 0.52.081.014 I slot print_timing: id 3 | task 60 | prompt eval time = 765.63 ms / 132 tokens ( 5.80 ms per token, 172.41 tokens per second) 0.52.081.019 I slot print_timing: id 3 | task 60 | eval time = 61.91 ms / 2 tokens ( 61.91 ms per token, 16.15 tokens per second) 0.52.081.020 I slot print_timing: id 3 | task 60 | total time = 827.55 ms / 134 tokens 0.52.081.020 I slot print_timing: id 3 | task 60 | graphs reused = 1 0.52.081.021 I slot print_timing: id 3 | task 60 | graph reallocs = 9 / 0 (same size) / (changed size) 0.52.081.036 I slot release: id 3 | task 60 | stop processing: n_tokens = 133, truncated = 0 0.52.089.337 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 0.52.106.886 I slot launch_slot_: id 0 | task 64 | processing task, is_child = 0 0.52.158.077 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.168 0.52.158.342 I slot launch_slot_: id 1 | task 65 | processing task, is_child = 0 0.52.158.426 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.157 0.52.158.647 I slot launch_slot_: id 2 | task 66 | processing task, is_child = 0 0.52.158.689 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.211 0.52.169.051 I slot launch_slot_: id 3 | task 67 | processing task, is_child = 0 0.53.056.642 I slot print_timing: id 0 | task 64 | prompt eval time = 822.62 ms / 169 tokens ( 4.87 ms per token, 205.44 tokens per second) 0.53.056.647 I slot print_timing: id 0 | task 64 | eval time = 64.95 ms / 2 tokens ( 64.95 ms per token, 15.40 tokens per second) 0.53.056.649 I slot print_timing: id 0 | task 64 | total time = 887.56 ms / 171 tokens 0.53.056.650 I slot print_timing: id 0 | task 64 | graphs reused = 1 0.53.056.650 I slot print_timing: id 0 | task 64 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.056.680 I slot release: id 0 | task 64 | stop processing: n_tokens = 170, truncated = 0 0.53.056.990 I slot print_timing: id 1 | task 65 | prompt eval time = 821.44 ms / 149 tokens ( 5.51 ms per token, 181.39 tokens per second) 0.53.056.995 I slot print_timing: id 1 | task 65 | eval time = 64.73 ms / 2 tokens ( 64.73 ms per token, 15.45 tokens per second) 0.53.056.996 I slot print_timing: id 1 | task 65 | total time = 886.16 ms / 151 tokens 0.53.056.997 I slot print_timing: id 1 | task 65 | graphs reused = 1 0.53.056.997 I slot print_timing: id 1 | task 65 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.057.014 I slot release: id 1 | task 65 | stop processing: n_tokens = 150, truncated = 0 0.53.057.350 I slot print_timing: id 2 | task 66 | prompt eval time = 820.28 ms / 123 tokens ( 6.67 ms per token, 149.95 tokens per second) 0.53.057.355 I slot print_timing: id 2 | task 66 | eval time = 64.51 ms / 2 tokens ( 64.51 ms per token, 15.50 tokens per second) 0.53.057.356 I slot print_timing: id 2 | task 66 | total time = 884.78 ms / 125 tokens 0.53.057.356 I slot print_timing: id 2 | task 66 | graphs reused = 1 0.53.057.357 I slot print_timing: id 2 | task 66 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.057.371 I slot release: id 2 | task 66 | stop processing: n_tokens = 124, truncated = 0 0.53.057.725 I slot print_timing: id 3 | task 67 | prompt eval time = 819.11 ms / 140 tokens ( 5.85 ms per token, 170.92 tokens per second) 0.53.057.729 I slot print_timing: id 3 | task 67 | eval time = 64.32 ms / 2 tokens ( 64.32 ms per token, 15.55 tokens per second) 0.53.057.730 I slot print_timing: id 3 | task 67 | total time = 883.43 ms / 142 tokens 0.53.057.731 I slot print_timing: id 3 | task 67 | graphs reused = 1 0.53.057.732 I slot print_timing: id 3 | task 67 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.057.749 I slot release: id 3 | task 67 | stop processing: n_tokens = 141, truncated = 0 0.53.065.614 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 0.53.082.836 I slot launch_slot_: id 0 | task 71 | processing task, is_child = 0 0.53.133.529 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.261 (> 0.100 thold), f_keep = 0.206 0.53.133.730 I slot launch_slot_: id 3 | task 72 | processing task, is_child = 0 0.53.133.776 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.234 0.53.133.927 I slot launch_slot_: id 2 | task 73 | processing task, is_child = 0 0.53.133.952 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.187 0.53.134.082 I slot launch_slot_: id 1 | task 74 | processing task, is_child = 0 0.53.946.201 I slot print_timing: id 0 | task 71 | prompt eval time = 745.78 ms / 128 tokens ( 5.83 ms per token, 171.63 tokens per second) 0.53.946.207 I slot print_timing: id 0 | task 71 | eval time = 66.31 ms / 2 tokens ( 66.31 ms per token, 15.08 tokens per second) 0.53.946.208 I slot print_timing: id 0 | task 71 | total time = 812.10 ms / 130 tokens 0.53.946.209 I slot print_timing: id 0 | task 71 | graphs reused = 1 0.53.946.210 I slot print_timing: id 0 | task 71 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.946.236 I slot release: id 0 | task 71 | stop processing: n_tokens = 129, truncated = 0 0.53.946.528 I slot print_timing: id 1 | task 74 | prompt eval time = 745.27 ms / 161 tokens ( 4.63 ms per token, 216.03 tokens per second) 0.53.946.532 I slot print_timing: id 1 | task 74 | eval time = 65.98 ms / 2 tokens ( 65.98 ms per token, 15.15 tokens per second) 0.53.946.533 I slot print_timing: id 1 | task 74 | total time = 811.26 ms / 163 tokens 0.53.946.533 I slot print_timing: id 1 | task 74 | graphs reused = 1 0.53.946.534 I slot print_timing: id 1 | task 74 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.946.553 I slot release: id 1 | task 74 | stop processing: n_tokens = 162, truncated = 0 0.53.946.865 I slot print_timing: id 2 | task 73 | prompt eval time = 744.76 ms / 163 tokens ( 4.57 ms per token, 218.86 tokens per second) 0.53.946.870 I slot print_timing: id 2 | task 73 | eval time = 65.65 ms / 2 tokens ( 65.65 ms per token, 15.23 tokens per second) 0.53.946.872 I slot print_timing: id 2 | task 73 | total time = 810.41 ms / 165 tokens 0.53.946.873 I slot print_timing: id 2 | task 73 | graphs reused = 1 0.53.946.874 I slot print_timing: id 2 | task 73 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.946.891 I slot release: id 2 | task 73 | stop processing: n_tokens = 164, truncated = 0 0.53.947.197 I slot print_timing: id 3 | task 72 | prompt eval time = 744.25 ms / 111 tokens ( 6.70 ms per token, 149.14 tokens per second) 0.53.947.200 I slot print_timing: id 3 | task 72 | eval time = 65.32 ms / 2 tokens ( 65.32 ms per token, 15.31 tokens per second) 0.53.947.201 I slot print_timing: id 3 | task 72 | total time = 809.57 ms / 113 tokens 0.53.947.202 I slot print_timing: id 3 | task 72 | graphs reused = 1 0.53.947.202 I slot print_timing: id 3 | task 72 | graph reallocs = 10 / 0 (same size) / (changed size) 0.53.947.213 I slot release: id 3 | task 72 | stop processing: n_tokens = 112, truncated = 0 0.53.955.574 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 0.53.972.880 I slot launch_slot_: id 0 | task 78 | processing task, is_child = 0 0.54.024.372 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.173 0.54.024.577 I slot launch_slot_: id 1 | task 79 | processing task, is_child = 0 0.54.024.624 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.177 0.54.024.788 I slot launch_slot_: id 2 | task 80 | processing task, is_child = 0 0.54.024.812 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.257 (> 0.100 thold), f_keep = 0.250 0.54.024.948 I slot launch_slot_: id 3 | task 81 | processing task, is_child = 0 0.54.851.733 I slot print_timing: id 0 | task 78 | prompt eval time = 757.67 ms / 167 tokens ( 4.54 ms per token, 220.41 tokens per second) 0.54.851.738 I slot print_timing: id 0 | task 78 | eval time = 69.10 ms / 2 tokens ( 69.10 ms per token, 14.47 tokens per second) 0.54.851.740 I slot print_timing: id 0 | task 78 | total time = 826.76 ms / 169 tokens 0.54.851.740 I slot print_timing: id 0 | task 78 | graphs reused = 1 0.54.851.741 I slot print_timing: id 0 | task 78 | graph reallocs = 10 / 0 (same size) / (changed size) 0.54.851.771 I slot release: id 0 | task 78 | stop processing: n_tokens = 168, truncated = 0 0.54.852.114 I slot print_timing: id 1 | task 79 | prompt eval time = 757.88 ms / 112 tokens ( 6.77 ms per token, 147.78 tokens per second) 0.54.852.120 I slot print_timing: id 1 | task 79 | eval time = 68.02 ms / 2 tokens ( 68.02 ms per token, 14.70 tokens per second) 0.54.852.121 I slot print_timing: id 1 | task 79 | total time = 825.90 ms / 114 tokens 0.54.852.122 I slot print_timing: id 1 | task 79 | graphs reused = 1 0.54.852.122 I slot print_timing: id 1 | task 79 | graph reallocs = 10 / 0 (same size) / (changed size) 0.54.852.138 I slot release: id 1 | task 79 | stop processing: n_tokens = 113, truncated = 0 0.54.852.448 I slot print_timing: id 2 | task 80 | prompt eval time = 757.88 ms / 164 tokens ( 4.62 ms per token, 216.39 tokens per second) 0.54.852.454 I slot print_timing: id 2 | task 80 | eval time = 67.13 ms / 2 tokens ( 67.13 ms per token, 14.90 tokens per second) 0.54.852.454 I slot print_timing: id 2 | task 80 | total time = 825.00 ms / 166 tokens 0.54.852.455 I slot print_timing: id 2 | task 80 | graphs reused = 1 0.54.852.455 I slot print_timing: id 2 | task 80 | graph reallocs = 10 / 0 (same size) / (changed size) 0.54.852.470 I slot release: id 2 | task 80 | stop processing: n_tokens = 165, truncated = 0 0.54.852.795 I slot print_timing: id 3 | task 81 | prompt eval time = 757.91 ms / 109 tokens ( 6.95 ms per token, 143.82 tokens per second) 0.54.852.800 I slot print_timing: id 3 | task 81 | eval time = 66.22 ms / 2 tokens ( 66.22 ms per token, 15.10 tokens per second) 0.54.852.801 I slot print_timing: id 3 | task 81 | total time = 824.12 ms / 111 tokens 0.54.852.801 I slot print_timing: id 3 | task 81 | graphs reused = 1 0.54.852.802 I slot print_timing: id 3 | task 81 | graph reallocs = 10 / 0 (same size) / (changed size) 0.54.852.815 I slot release: id 3 | task 81 | stop processing: n_tokens = 110, truncated = 0 0.54.861.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.167 0.54.879.100 I slot launch_slot_: id 0 | task 85 | processing task, is_child = 0 0.54.929.606 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.248 0.54.939.327 I slot launch_slot_: id 1 | task 86 | processing task, is_child = 0 0.54.939.423 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.170 0.54.939.630 I slot launch_slot_: id 2 | task 87 | processing task, is_child = 0 0.54.939.671 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.190 (> 0.100 thold), f_keep = 0.255 0.54.939.865 I slot launch_slot_: id 3 | task 88 | processing task, is_child = 0 0.55.746.176 I slot print_timing: id 0 | task 85 | prompt eval time = 741.66 ms / 131 tokens ( 5.66 ms per token, 176.63 tokens per second) 0.55.746.183 I slot print_timing: id 0 | task 85 | eval time = 64.63 ms / 2 tokens ( 64.63 ms per token, 15.47 tokens per second) 0.55.746.184 I slot print_timing: id 0 | task 85 | total time = 806.29 ms / 133 tokens 0.55.746.185 I slot print_timing: id 0 | task 85 | graphs reused = 1 0.55.746.185 I slot print_timing: id 0 | task 85 | graph reallocs = 12 / 0 (same size) / (changed size) 0.55.746.212 I slot release: id 0 | task 85 | stop processing: n_tokens = 132, truncated = 0 0.55.746.495 I slot print_timing: id 1 | task 86 | prompt eval time = 740.48 ms / 122 tokens ( 6.07 ms per token, 164.76 tokens per second) 0.55.746.500 I slot print_timing: id 1 | task 86 | eval time = 64.39 ms / 2 tokens ( 64.39 ms per token, 15.53 tokens per second) 0.55.746.501 I slot print_timing: id 1 | task 86 | total time = 804.86 ms / 124 tokens 0.55.746.501 I slot print_timing: id 1 | task 86 | graphs reused = 1 0.55.746.502 I slot print_timing: id 1 | task 86 | graph reallocs = 12 / 0 (same size) / (changed size) 0.55.746.518 I slot release: id 1 | task 86 | stop processing: n_tokens = 123, truncated = 0 0.55.746.873 I slot print_timing: id 2 | task 87 | prompt eval time = 739.39 ms / 120 tokens ( 6.16 ms per token, 162.30 tokens per second) 0.55.746.879 I slot print_timing: id 2 | task 87 | eval time = 64.17 ms / 2 tokens ( 64.17 ms per token, 15.58 tokens per second) 0.55.746.880 I slot print_timing: id 2 | task 87 | total time = 803.56 ms / 122 tokens 0.55.746.881 I slot print_timing: id 2 | task 87 | graphs reused = 1 0.55.746.882 I slot print_timing: id 2 | task 87 | graph reallocs = 12 / 0 (same size) / (changed size) 0.55.746.900 I slot release: id 2 | task 87 | stop processing: n_tokens = 121, truncated = 0 0.55.747.214 I slot print_timing: id 3 | task 88 | prompt eval time = 738.24 ms / 147 tokens ( 5.02 ms per token, 199.12 tokens per second) 0.55.747.219 I slot print_timing: id 3 | task 88 | eval time = 63.93 ms / 2 tokens ( 63.93 ms per token, 15.64 tokens per second) 0.55.747.220 I slot print_timing: id 3 | task 88 | total time = 802.17 ms / 149 tokens 0.55.747.220 I slot print_timing: id 3 | task 88 | graphs reused = 1 0.55.747.221 I slot print_timing: id 3 | task 88 | graph reallocs = 12 / 0 (same size) / (changed size) 0.55.747.234 I slot release: id 3 | task 88 | stop processing: n_tokens = 148, truncated = 0 0.55.755.891 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.201 (> 0.100 thold), f_keep = 0.236 0.55.773.104 I slot launch_slot_: id 1 | task 92 | processing task, is_child = 0 0.55.833.410 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.212 0.55.833.659 I slot launch_slot_: id 0 | task 93 | processing task, is_child = 0 0.55.833.737 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.214 (> 0.100 thold), f_keep = 0.231 0.55.833.940 I slot launch_slot_: id 2 | task 94 | processing task, is_child = 0 0.55.833.982 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.189 0.55.843.974 I slot launch_slot_: id 3 | task 95 | processing task, is_child = 0 0.56.652.191 I slot print_timing: id 0 | task 93 | prompt eval time = 744.97 ms / 124 tokens ( 6.01 ms per token, 166.45 tokens per second) 0.56.652.198 I slot print_timing: id 0 | task 93 | eval time = 63.22 ms / 2 tokens ( 63.22 ms per token, 15.82 tokens per second) 0.56.652.200 I slot print_timing: id 0 | task 93 | total time = 808.19 ms / 126 tokens 0.56.652.201 I slot print_timing: id 0 | task 93 | graphs reused = 1 0.56.652.202 I slot print_timing: id 0 | task 93 | graph reallocs = 13 / 0 (same size) / (changed size) 0.56.652.233 I slot release: id 0 | task 93 | stop processing: n_tokens = 125, truncated = 0 0.56.652.538 I slot print_timing: id 1 | task 92 | prompt eval time = 743.74 ms / 144 tokens ( 5.16 ms per token, 193.62 tokens per second) 0.56.652.543 I slot print_timing: id 1 | task 92 | eval time = 63.02 ms / 2 tokens ( 63.02 ms per token, 15.87 tokens per second) 0.56.652.544 I slot print_timing: id 1 | task 92 | total time = 806.77 ms / 146 tokens 0.56.652.545 I slot print_timing: id 1 | task 92 | graphs reused = 1 0.56.652.545 I slot print_timing: id 1 | task 92 | graph reallocs = 13 / 0 (same size) / (changed size) 0.56.652.562 I slot release: id 1 | task 92 | stop processing: n_tokens = 145, truncated = 0 0.56.652.920 I slot print_timing: id 2 | task 94 | prompt eval time = 742.59 ms / 131 tokens ( 5.67 ms per token, 176.41 tokens per second) 0.56.652.927 I slot print_timing: id 2 | task 94 | eval time = 62.84 ms / 2 tokens ( 62.84 ms per token, 15.91 tokens per second) 0.56.652.928 I slot print_timing: id 2 | task 94 | total time = 805.43 ms / 133 tokens 0.56.652.929 I slot print_timing: id 2 | task 94 | graphs reused = 1 0.56.652.929 I slot print_timing: id 2 | task 94 | graph reallocs = 13 / 0 (same size) / (changed size) 0.56.652.947 I slot release: id 2 | task 94 | stop processing: n_tokens = 132, truncated = 0 0.56.653.304 I slot print_timing: id 3 | task 95 | prompt eval time = 741.43 ms / 141 tokens ( 5.26 ms per token, 190.17 tokens per second) 0.56.653.311 I slot print_timing: id 3 | task 95 | eval time = 62.67 ms / 2 tokens ( 62.67 ms per token, 15.96 tokens per second) 0.56.653.312 I slot print_timing: id 3 | task 95 | total time = 804.10 ms / 143 tokens 0.56.653.313 I slot print_timing: id 3 | task 95 | graphs reused = 1 0.56.653.314 I slot print_timing: id 3 | task 95 | graph reallocs = 13 / 0 (same size) / (changed size) 0.56.653.339 I slot release: id 3 | task 95 | stop processing: n_tokens = 142, truncated = 0 0.56.660.932 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 0.56.677.982 I slot launch_slot_: id 1 | task 99 | processing task, is_child = 0 0.56.727.618 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.271 (> 0.100 thold), f_keep = 0.220 0.56.727.835 I slot launch_slot_: id 2 | task 100 | processing task, is_child = 0 0.56.727.882 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 0.56.728.031 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.56.728.056 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.169 (> 0.100 thold), f_keep = 0.204 0.56.728.194 I slot launch_slot_: id 3 | task 102 | processing task, is_child = 0 0.57.563.012 I slot print_timing: id 0 | task 101 | prompt eval time = 769.63 ms / 121 tokens ( 6.36 ms per token, 157.22 tokens per second) 0.57.563.019 I slot print_timing: id 0 | task 101 | eval time = 65.17 ms / 2 tokens ( 65.17 ms per token, 15.35 tokens per second) 0.57.563.020 I slot print_timing: id 0 | task 101 | total time = 834.80 ms / 123 tokens 0.57.563.021 I slot print_timing: id 0 | task 101 | graphs reused = 1 0.57.563.022 I slot print_timing: id 0 | task 101 | graph reallocs = 13 / 0 (same size) / (changed size) 0.57.563.050 I slot release: id 0 | task 101 | stop processing: n_tokens = 122, truncated = 0 0.57.563.379 I slot print_timing: id 1 | task 99 | prompt eval time = 769.06 ms / 118 tokens ( 6.52 ms per token, 153.43 tokens per second) 0.57.563.383 I slot print_timing: id 1 | task 99 | eval time = 64.87 ms / 2 tokens ( 64.87 ms per token, 15.42 tokens per second) 0.57.563.384 I slot print_timing: id 1 | task 99 | total time = 833.93 ms / 120 tokens 0.57.563.385 I slot print_timing: id 1 | task 99 | graphs reused = 1 0.57.563.386 I slot print_timing: id 1 | task 99 | graph reallocs = 13 / 0 (same size) / (changed size) 0.57.563.401 I slot release: id 1 | task 99 | stop processing: n_tokens = 119, truncated = 0 0.57.563.735 I slot print_timing: id 2 | task 100 | prompt eval time = 768.50 ms / 107 tokens ( 7.18 ms per token, 139.23 tokens per second) 0.57.563.740 I slot print_timing: id 2 | task 100 | eval time = 64.53 ms / 2 tokens ( 64.53 ms per token, 15.50 tokens per second) 0.57.563.741 I slot print_timing: id 2 | task 100 | total time = 833.03 ms / 109 tokens 0.57.563.741 I slot print_timing: id 2 | task 100 | graphs reused = 1 0.57.563.742 I slot print_timing: id 2 | task 100 | graph reallocs = 13 / 0 (same size) / (changed size) 0.57.563.755 I slot release: id 2 | task 100 | stop processing: n_tokens = 108, truncated = 0 0.57.564.084 I slot print_timing: id 3 | task 102 | prompt eval time = 767.84 ms / 172 tokens ( 4.46 ms per token, 224.01 tokens per second) 0.57.564.088 I slot print_timing: id 3 | task 102 | eval time = 64.29 ms / 2 tokens ( 64.29 ms per token, 15.55 tokens per second) 0.57.564.089 I slot print_timing: id 3 | task 102 | total time = 832.13 ms / 174 tokens 0.57.564.090 I slot print_timing: id 3 | task 102 | graphs reused = 1 0.57.564.091 I slot print_timing: id 3 | task 102 | graph reallocs = 13 / 0 (same size) / (changed size) 0.57.564.105 I slot release: id 3 | task 102 | stop processing: n_tokens = 173, truncated = 0 0.57.572.889 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.244 0.57.600.200 I slot launch_slot_: id 1 | task 106 | processing task, is_child = 0 0.57.654.428 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.250 (> 0.100 thold), f_keep = 0.269 0.57.654.718 I slot launch_slot_: id 2 | task 107 | processing task, is_child = 0 0.57.654.800 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 0.57.654.999 I slot launch_slot_: id 0 | task 108 | processing task, is_child = 0 0.57.655.044 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.162 0.57.655.241 I slot launch_slot_: id 3 | task 109 | processing task, is_child = 0 0.58.549.907 I slot print_timing: id 0 | task 108 | prompt eval time = 829.19 ms / 177 tokens ( 4.68 ms per token, 213.46 tokens per second) 0.58.549.915 I slot print_timing: id 0 | task 108 | eval time = 65.45 ms / 2 tokens ( 65.45 ms per token, 15.28 tokens per second) 0.58.549.916 I slot print_timing: id 0 | task 108 | total time = 894.64 ms / 179 tokens 0.58.549.917 I slot print_timing: id 0 | task 108 | graphs reused = 1 0.58.549.918 I slot print_timing: id 0 | task 108 | graph reallocs = 14 / 0 (same size) / (changed size) 0.58.549.949 I slot release: id 0 | task 108 | stop processing: n_tokens = 178, truncated = 0 0.58.550.280 I slot print_timing: id 1 | task 106 | prompt eval time = 828.04 ms / 136 tokens ( 6.09 ms per token, 164.24 tokens per second) 0.58.550.284 I slot print_timing: id 1 | task 106 | eval time = 65.25 ms / 2 tokens ( 65.25 ms per token, 15.33 tokens per second) 0.58.550.285 I slot print_timing: id 1 | task 106 | total time = 893.29 ms / 138 tokens 0.58.550.285 I slot print_timing: id 1 | task 106 | graphs reused = 1 0.58.550.286 I slot print_timing: id 1 | task 106 | graph reallocs = 14 / 0 (same size) / (changed size) 0.58.550.303 I slot release: id 1 | task 106 | stop processing: n_tokens = 137, truncated = 0 0.58.550.639 I slot print_timing: id 2 | task 107 | prompt eval time = 826.88 ms / 116 tokens ( 7.13 ms per token, 140.29 tokens per second) 0.58.550.651 I slot print_timing: id 2 | task 107 | eval time = 65.03 ms / 2 tokens ( 65.03 ms per token, 15.38 tokens per second) 0.58.550.656 I slot print_timing: id 2 | task 107 | total time = 891.91 ms / 118 tokens 0.58.550.657 I slot print_timing: id 2 | task 107 | graphs reused = 1 0.58.550.658 I slot print_timing: id 2 | task 107 | graph reallocs = 14 / 0 (same size) / (changed size) 0.58.550.676 I slot release: id 2 | task 107 | stop processing: n_tokens = 117, truncated = 0 0.58.551.008 I slot print_timing: id 3 | task 109 | prompt eval time = 825.73 ms / 240 tokens ( 3.44 ms per token, 290.65 tokens per second) 0.58.551.013 I slot print_timing: id 3 | task 109 | eval time = 64.83 ms / 2 tokens ( 64.83 ms per token, 15.42 tokens per second) 0.58.551.014 I slot print_timing: id 3 | task 109 | total time = 890.56 ms / 242 tokens 0.58.551.015 I slot print_timing: id 3 | task 109 | graphs reused = 1 0.58.551.016 I slot print_timing: id 3 | task 109 | graph reallocs = 14 / 0 (same size) / (changed size) 0.58.551.041 I slot release: id 3 | task 109 | stop processing: n_tokens = 241, truncated = 0 0.58.559.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.256 0.58.576.833 I slot launch_slot_: id 2 | task 113 | processing task, is_child = 0 0.58.629.749 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.212 0.58.639.534 I slot launch_slot_: id 1 | task 114 | processing task, is_child = 0 0.58.639.639 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 0.58.639.834 I slot launch_slot_: id 0 | task 115 | processing task, is_child = 0 0.58.639.885 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.124 (> 0.100 thold), f_keep = 0.116 0.58.640.084 I slot launch_slot_: id 3 | task 116 | processing task, is_child = 0 0.59.734.364 I slot print_timing: id 0 | task 115 | prompt eval time = 1029.35 ms / 160 tokens ( 6.43 ms per token, 155.44 tokens per second) 0.59.734.369 I slot print_timing: id 0 | task 115 | eval time = 64.90 ms / 2 tokens ( 64.90 ms per token, 15.41 tokens per second) 0.59.734.370 I slot print_timing: id 0 | task 115 | total time = 1094.26 ms / 162 tokens 0.59.734.371 I slot print_timing: id 0 | task 115 | graphs reused = 1 0.59.734.372 I slot print_timing: id 0 | task 115 | graph reallocs = 15 / 0 (same size) / (changed size) 0.59.734.403 I slot release: id 0 | task 115 | stop processing: n_tokens = 161, truncated = 0 0.59.734.677 I slot print_timing: id 1 | task 114 | prompt eval time = 1028.18 ms / 142 tokens ( 7.24 ms per token, 138.11 tokens per second) 0.59.734.680 I slot print_timing: id 1 | task 114 | eval time = 64.66 ms / 2 tokens ( 64.66 ms per token, 15.47 tokens per second) 0.59.734.681 I slot print_timing: id 1 | task 114 | total time = 1092.84 ms / 144 tokens 0.59.734.682 I slot print_timing: id 1 | task 114 | graphs reused = 1 0.59.734.682 I slot print_timing: id 1 | task 114 | graph reallocs = 15 / 0 (same size) / (changed size) 0.59.734.696 I slot release: id 1 | task 114 | stop processing: n_tokens = 143, truncated = 0 0.59.734.992 I slot print_timing: id 2 | task 113 | prompt eval time = 1026.99 ms / 155 tokens ( 6.63 ms per token, 150.93 tokens per second) 0.59.734.998 I slot print_timing: id 2 | task 113 | eval time = 64.39 ms / 2 tokens ( 64.39 ms per token, 15.53 tokens per second) 0.59.734.999 I slot print_timing: id 2 | task 113 | total time = 1091.38 ms / 157 tokens 0.59.734.999 I slot print_timing: id 2 | task 113 | graphs reused = 1 0.59.735.000 I slot print_timing: id 2 | task 113 | graph reallocs = 15 / 0 (same size) / (changed size) 0.59.735.016 I slot release: id 2 | task 113 | stop processing: n_tokens = 156, truncated = 0 0.59.735.339 I slot print_timing: id 3 | task 116 | prompt eval time = 1025.83 ms / 226 tokens ( 4.54 ms per token, 220.31 tokens per second) 0.59.735.344 I slot print_timing: id 3 | task 116 | eval time = 64.17 ms / 2 tokens ( 64.17 ms per token, 15.58 tokens per second) 0.59.735.345 I slot print_timing: id 3 | task 116 | total time = 1090.00 ms / 228 tokens 0.59.735.345 I slot print_timing: id 3 | task 116 | graphs reused = 1 0.59.735.346 I slot print_timing: id 3 | task 116 | graph reallocs = 15 / 0 (same size) / (changed size) 0.59.735.363 I slot release: id 3 | task 116 | stop processing: n_tokens = 227, truncated = 0 0.59.744.207 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.295 (> 0.100 thold), f_keep = 0.217 0.59.762.636 I slot launch_slot_: id 1 | task 120 | processing task, is_child = 0 0.59.817.544 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.146 (> 0.100 thold), f_keep = 0.174 0.59.826.434 I slot launch_slot_: id 0 | task 121 | processing task, is_child = 0 0.59.826.501 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.179 0.59.826.650 I slot launch_slot_: id 2 | task 122 | processing task, is_child = 0 0.59.826.678 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.123 0.59.835.170 I slot launch_slot_: id 3 | task 123 | processing task, is_child = 0 1.00.751.679 I slot print_timing: id 0 | task 121 | prompt eval time = 853.14 ms / 192 tokens ( 4.44 ms per token, 225.05 tokens per second) 1.00.751.685 I slot print_timing: id 0 | task 121 | eval time = 63.35 ms / 2 tokens ( 63.35 ms per token, 15.79 tokens per second) 1.00.751.687 I slot print_timing: id 0 | task 121 | total time = 916.49 ms / 194 tokens 1.00.751.687 I slot print_timing: id 0 | task 121 | graphs reused = 1 1.00.751.688 I slot print_timing: id 0 | task 121 | graph reallocs = 17 / 0 (same size) / (changed size) 1.00.751.720 I slot release: id 0 | task 121 | stop processing: n_tokens = 193, truncated = 0 1.00.751.997 I slot print_timing: id 1 | task 120 | prompt eval time = 852.54 ms / 105 tokens ( 8.12 ms per token, 123.16 tokens per second) 1.00.752.001 I slot print_timing: id 1 | task 120 | eval time = 63.10 ms / 2 tokens ( 63.10 ms per token, 15.85 tokens per second) 1.00.752.002 I slot print_timing: id 1 | task 120 | total time = 915.64 ms / 107 tokens 1.00.752.002 I slot print_timing: id 1 | task 120 | graphs reused = 1 1.00.752.004 I slot print_timing: id 1 | task 120 | graph reallocs = 17 / 0 (same size) / (changed size) 1.00.752.019 I slot release: id 1 | task 120 | stop processing: n_tokens = 106, truncated = 0 1.00.752.313 I slot print_timing: id 2 | task 122 | prompt eval time = 851.92 ms / 141 tokens ( 6.04 ms per token, 165.51 tokens per second) 1.00.752.317 I slot print_timing: id 2 | task 122 | eval time = 62.84 ms / 2 tokens ( 62.84 ms per token, 15.91 tokens per second) 1.00.752.318 I slot print_timing: id 2 | task 122 | total time = 914.76 ms / 143 tokens 1.00.752.319 I slot print_timing: id 2 | task 122 | graphs reused = 1 1.00.752.320 I slot print_timing: id 2 | task 122 | graph reallocs = 17 / 0 (same size) / (changed size) 1.00.752.334 I slot release: id 2 | task 122 | stop processing: n_tokens = 142, truncated = 0 1.00.752.644 I slot print_timing: id 3 | task 123 | prompt eval time = 851.31 ms / 114 tokens ( 7.47 ms per token, 133.91 tokens per second) 1.00.752.649 I slot print_timing: id 3 | task 123 | eval time = 62.60 ms / 2 tokens ( 62.60 ms per token, 15.97 tokens per second) 1.00.752.650 I slot print_timing: id 3 | task 123 | total time = 913.90 ms / 116 tokens 1.00.752.651 I slot print_timing: id 3 | task 123 | graphs reused = 1 1.00.752.651 I slot print_timing: id 3 | task 123 | graph reallocs = 17 / 0 (same size) / (changed size) 1.00.752.663 I slot release: id 3 | task 123 | stop processing: n_tokens = 115, truncated = 0 1.00.761.762 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.145 1.00.779.716 I slot launch_slot_: id 0 | task 127 | processing task, is_child = 0 1.00.844.257 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.269 (> 0.100 thold), f_keep = 0.274 1.00.844.449 I slot launch_slot_: id 1 | task 128 | processing task, is_child = 0 1.00.844.493 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.252 1.00.844.638 I slot launch_slot_: id 3 | task 129 | processing task, is_child = 0 1.00.844.664 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.197 1.00.844.815 I slot launch_slot_: id 2 | task 130 | processing task, is_child = 0 1.01.841.813 I slot print_timing: id 0 | task 127 | prompt eval time = 922.51 ms / 135 tokens ( 6.83 ms per token, 146.34 tokens per second) 1.01.841.819 I slot print_timing: id 0 | task 127 | eval time = 74.47 ms / 2 tokens ( 74.47 ms per token, 13.43 tokens per second) 1.01.841.820 I slot print_timing: id 0 | task 127 | total time = 996.98 ms / 137 tokens 1.01.841.821 I slot print_timing: id 0 | task 127 | graphs reused = 1 1.01.841.822 I slot print_timing: id 0 | task 127 | graph reallocs = 18 / 0 (same size) / (changed size) 1.01.841.849 I slot release: id 0 | task 127 | stop processing: n_tokens = 136, truncated = 0 1.01.842.141 I slot print_timing: id 1 | task 128 | prompt eval time = 921.96 ms / 108 tokens ( 8.54 ms per token, 117.14 tokens per second) 1.01.842.146 I slot print_timing: id 1 | task 128 | eval time = 74.15 ms / 2 tokens ( 74.15 ms per token, 13.49 tokens per second) 1.01.842.147 I slot print_timing: id 1 | task 128 | total time = 996.12 ms / 110 tokens 1.01.842.147 I slot print_timing: id 1 | task 128 | graphs reused = 1 1.01.842.148 I slot print_timing: id 1 | task 128 | graph reallocs = 18 / 0 (same size) / (changed size) 1.01.842.165 I slot release: id 1 | task 128 | stop processing: n_tokens = 109, truncated = 0 1.01.842.469 I slot print_timing: id 2 | task 130 | prompt eval time = 921.44 ms / 172 tokens ( 5.36 ms per token, 186.66 tokens per second) 1.01.842.474 I slot print_timing: id 2 | task 130 | eval time = 73.82 ms / 2 tokens ( 73.82 ms per token, 13.55 tokens per second) 1.01.842.475 I slot print_timing: id 2 | task 130 | total time = 995.26 ms / 174 tokens 1.01.842.476 I slot print_timing: id 2 | task 130 | graphs reused = 1 1.01.842.476 I slot print_timing: id 2 | task 130 | graph reallocs = 18 / 0 (same size) / (changed size) 1.01.842.495 I slot release: id 2 | task 130 | stop processing: n_tokens = 173, truncated = 0 1.01.842.845 I slot print_timing: id 3 | task 129 | prompt eval time = 920.86 ms / 122 tokens ( 7.55 ms per token, 132.48 tokens per second) 1.01.842.848 I slot print_timing: id 3 | task 129 | eval time = 73.55 ms / 2 tokens ( 73.55 ms per token, 13.60 tokens per second) 1.01.842.849 I slot print_timing: id 3 | task 129 | total time = 994.42 ms / 124 tokens 1.01.842.851 I slot print_timing: id 3 | task 129 | graphs reused = 1 1.01.842.852 I slot print_timing: id 3 | task 129 | graph reallocs = 18 / 0 (same size) / (changed size) 1.01.842.864 I slot release: id 3 | task 129 | stop processing: n_tokens = 123, truncated = 0 1.01.851.455 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.206 1.01.868.847 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 1.01.920.283 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.176 (> 0.100 thold), f_keep = 0.257 1.01.920.552 I slot launch_slot_: id 1 | task 135 | processing task, is_child = 0 1.01.920.635 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.242 (> 0.100 thold), f_keep = 0.236 1.01.930.624 I slot launch_slot_: id 3 | task 136 | processing task, is_child = 0 1.01.930.689 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.162 1.01.930.901 I slot launch_slot_: id 2 | task 137 | processing task, is_child = 0 1.02.770.762 I slot print_timing: id 0 | task 134 | prompt eval time = 774.90 ms / 134 tokens ( 5.78 ms per token, 172.93 tokens per second) 1.02.770.768 I slot print_timing: id 0 | task 134 | eval time = 64.94 ms / 2 tokens ( 64.94 ms per token, 15.40 tokens per second) 1.02.770.769 I slot print_timing: id 0 | task 134 | total time = 839.84 ms / 136 tokens 1.02.770.770 I slot print_timing: id 0 | task 134 | graphs reused = 1 1.02.770.770 I slot print_timing: id 0 | task 134 | graph reallocs = 19 / 0 (same size) / (changed size) 1.02.770.797 I slot release: id 0 | task 134 | stop processing: n_tokens = 135, truncated = 0 1.02.771.093 I slot print_timing: id 1 | task 135 | prompt eval time = 773.77 ms / 159 tokens ( 4.87 ms per token, 205.49 tokens per second) 1.02.771.097 I slot print_timing: id 1 | task 135 | eval time = 64.68 ms / 2 tokens ( 64.68 ms per token, 15.46 tokens per second) 1.02.771.097 I slot print_timing: id 1 | task 135 | total time = 838.45 ms / 161 tokens 1.02.771.098 I slot print_timing: id 1 | task 135 | graphs reused = 1 1.02.771.099 I slot print_timing: id 1 | task 135 | graph reallocs = 19 / 0 (same size) / (changed size) 1.02.771.118 I slot release: id 1 | task 135 | stop processing: n_tokens = 160, truncated = 0 1.02.771.452 I slot print_timing: id 2 | task 137 | prompt eval time = 772.63 ms / 135 tokens ( 5.72 ms per token, 174.73 tokens per second) 1.02.771.458 I slot print_timing: id 2 | task 137 | eval time = 64.45 ms / 2 tokens ( 64.45 ms per token, 15.51 tokens per second) 1.02.771.458 I slot print_timing: id 2 | task 137 | total time = 837.09 ms / 137 tokens 1.02.771.459 I slot print_timing: id 2 | task 137 | graphs reused = 1 1.02.771.460 I slot print_timing: id 2 | task 137 | graph reallocs = 19 / 0 (same size) / (changed size) 1.02.771.476 I slot release: id 2 | task 137 | stop processing: n_tokens = 136, truncated = 0 1.02.771.813 I slot print_timing: id 3 | task 136 | prompt eval time = 771.66 ms / 120 tokens ( 6.43 ms per token, 155.51 tokens per second) 1.02.771.818 I slot print_timing: id 3 | task 136 | eval time = 64.23 ms / 2 tokens ( 64.23 ms per token, 15.57 tokens per second) 1.02.771.819 I slot print_timing: id 3 | task 136 | total time = 835.89 ms / 122 tokens 1.02.771.819 I slot print_timing: id 3 | task 136 | graphs reused = 1 1.02.771.820 I slot print_timing: id 3 | task 136 | graph reallocs = 19 / 0 (same size) / (changed size) 1.02.771.832 I slot release: id 3 | task 136 | stop processing: n_tokens = 121, truncated = 0 1.02.781.891 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.163 (> 0.100 thold), f_keep = 0.207 1.02.808.578 I slot launch_slot_: id 0 | task 141 | processing task, is_child = 0 1.02.861.249 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.175 1.02.861.466 I slot launch_slot_: id 1 | task 142 | processing task, is_child = 0 1.02.861.514 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.160 (> 0.100 thold), f_keep = 0.206 1.02.861.673 I slot launch_slot_: id 2 | task 143 | processing task, is_child = 0 1.02.861.698 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.231 1.02.861.836 I slot launch_slot_: id 3 | task 144 | processing task, is_child = 0 1.03.686.755 I slot print_timing: id 0 | task 141 | prompt eval time = 759.21 ms / 172 tokens ( 4.41 ms per token, 226.55 tokens per second) 1.03.686.762 I slot print_timing: id 0 | task 141 | eval time = 65.69 ms / 2 tokens ( 65.69 ms per token, 15.22 tokens per second) 1.03.686.764 I slot print_timing: id 0 | task 141 | total time = 824.89 ms / 174 tokens 1.03.686.765 I slot print_timing: id 0 | task 141 | graphs reused = 1 1.03.686.766 I slot print_timing: id 0 | task 141 | graph reallocs = 19 / 0 (same size) / (changed size) 1.03.686.804 I slot release: id 0 | task 141 | stop processing: n_tokens = 173, truncated = 0 1.03.687.140 I slot print_timing: id 1 | task 142 | prompt eval time = 758.66 ms / 130 tokens ( 5.84 ms per token, 171.36 tokens per second) 1.03.687.144 I slot print_timing: id 1 | task 142 | eval time = 65.38 ms / 2 tokens ( 65.38 ms per token, 15.29 tokens per second) 1.03.687.145 I slot print_timing: id 1 | task 142 | total time = 824.04 ms / 132 tokens 1.03.687.145 I slot print_timing: id 1 | task 142 | graphs reused = 1 1.03.687.147 I slot print_timing: id 1 | task 142 | graph reallocs = 19 / 0 (same size) / (changed size) 1.03.687.167 I slot release: id 1 | task 142 | stop processing: n_tokens = 131, truncated = 0 1.03.687.502 I slot print_timing: id 2 | task 143 | prompt eval time = 758.11 ms / 175 tokens ( 4.33 ms per token, 230.84 tokens per second) 1.03.687.506 I slot print_timing: id 2 | task 143 | eval time = 65.03 ms / 2 tokens ( 65.03 ms per token, 15.38 tokens per second) 1.03.687.507 I slot print_timing: id 2 | task 143 | total time = 823.14 ms / 177 tokens 1.03.687.508 I slot print_timing: id 2 | task 143 | graphs reused = 1 1.03.687.509 I slot print_timing: id 2 | task 143 | graph reallocs = 19 / 0 (same size) / (changed size) 1.03.687.526 I slot release: id 2 | task 143 | stop processing: n_tokens = 176, truncated = 0 1.03.687.862 I slot print_timing: id 3 | task 144 | prompt eval time = 757.43 ms / 180 tokens ( 4.21 ms per token, 237.65 tokens per second) 1.03.687.866 I slot print_timing: id 3 | task 144 | eval time = 64.69 ms / 2 tokens ( 64.69 ms per token, 15.46 tokens per second) 1.03.687.867 I slot print_timing: id 3 | task 144 | total time = 822.12 ms / 182 tokens 1.03.687.868 I slot print_timing: id 3 | task 144 | graphs reused = 1 1.03.687.869 I slot print_timing: id 3 | task 144 | graph reallocs = 19 / 0 (same size) / (changed size) 1.03.687.886 I slot release: id 3 | task 144 | stop processing: n_tokens = 181, truncated = 0 1.03.697.282 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.162 1.03.728.606 I slot launch_slot_: id 0 | task 148 | processing task, is_child = 0 1.03.785.287 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.214 1.03.785.492 I slot launch_slot_: id 1 | task 149 | processing task, is_child = 0 1.03.785.545 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.243 (> 0.100 thold), f_keep = 0.159 1.03.785.707 I slot launch_slot_: id 2 | task 150 | processing task, is_child = 0 1.03.785.734 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 1.03.795.071 I slot launch_slot_: id 3 | task 151 | processing task, is_child = 0 1.04.378.308 I slot print_timing: id 0 | task 148 | prompt eval time = 519.11 ms / 123 tokens ( 4.22 ms per token, 236.94 tokens per second) 1.04.378.315 I slot print_timing: id 0 | task 148 | eval time = 64.11 ms / 2 tokens ( 64.11 ms per token, 15.60 tokens per second) 1.04.378.318 I slot print_timing: id 0 | task 148 | total time = 583.21 ms / 125 tokens 1.04.378.319 I slot print_timing: id 0 | task 148 | graphs reused = 1 1.04.378.320 I slot print_timing: id 0 | task 148 | graph reallocs = 20 / 0 (same size) / (changed size) 1.04.378.349 I slot release: id 0 | task 148 | stop processing: n_tokens = 124, truncated = 0 1.04.378.628 I slot print_timing: id 1 | task 149 | prompt eval time = 518.37 ms / 123 tokens ( 4.21 ms per token, 237.28 tokens per second) 1.04.378.632 I slot print_timing: id 1 | task 149 | eval time = 63.70 ms / 2 tokens ( 63.70 ms per token, 15.70 tokens per second) 1.04.378.633 I slot print_timing: id 1 | task 149 | total time = 582.07 ms / 125 tokens 1.04.378.633 I slot print_timing: id 1 | task 149 | graphs reused = 1 1.04.378.634 I slot print_timing: id 1 | task 149 | graph reallocs = 20 / 0 (same size) / (changed size) 1.04.378.646 I slot release: id 1 | task 149 | stop processing: n_tokens = 124, truncated = 0 1.04.378.930 I slot print_timing: id 2 | task 150 | prompt eval time = 517.85 ms / 115 tokens ( 4.50 ms per token, 222.07 tokens per second) 1.04.378.933 I slot print_timing: id 2 | task 150 | eval time = 63.27 ms / 2 tokens ( 63.27 ms per token, 15.80 tokens per second) 1.04.378.934 I slot print_timing: id 2 | task 150 | total time = 581.13 ms / 117 tokens 1.04.378.935 I slot print_timing: id 2 | task 150 | graphs reused = 1 1.04.378.935 I slot print_timing: id 2 | task 150 | graph reallocs = 20 / 0 (same size) / (changed size) 1.04.378.947 I slot release: id 2 | task 150 | stop processing: n_tokens = 116, truncated = 0 1.04.379.261 I slot print_timing: id 3 | task 151 | prompt eval time = 517.33 ms / 115 tokens ( 4.50 ms per token, 222.29 tokens per second) 1.04.379.266 I slot print_timing: id 3 | task 151 | eval time = 62.89 ms / 2 tokens ( 62.89 ms per token, 15.90 tokens per second) 1.04.379.267 I slot print_timing: id 3 | task 151 | total time = 580.23 ms / 117 tokens 1.04.379.267 I slot print_timing: id 3 | task 151 | graphs reused = 1 1.04.379.268 I slot print_timing: id 3 | task 151 | graph reallocs = 20 / 0 (same size) / (changed size) 1.04.379.279 I slot release: id 3 | task 151 | stop processing: n_tokens = 116, truncated = 0 1.04.388.083 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.219 (> 0.100 thold), f_keep = 0.226 1.04.418.418 I slot launch_slot_: id 0 | task 155 | processing task, is_child = 0 1.04.475.472 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.252 (> 0.100 thold), f_keep = 0.276 1.04.475.684 I slot launch_slot_: id 3 | task 156 | processing task, is_child = 0 1.04.475.731 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.226 1.04.475.869 I slot launch_slot_: id 1 | task 157 | processing task, is_child = 0 1.04.475.894 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.241 1.04.476.050 I slot launch_slot_: id 2 | task 158 | processing task, is_child = 0 1.05.171.155 I slot print_timing: id 0 | task 155 | prompt eval time = 630.02 ms / 128 tokens ( 4.92 ms per token, 203.17 tokens per second) 1.05.171.161 I slot print_timing: id 0 | task 155 | eval time = 65.06 ms / 2 tokens ( 65.06 ms per token, 15.37 tokens per second) 1.05.171.162 I slot print_timing: id 0 | task 155 | total time = 695.09 ms / 130 tokens 1.05.171.163 I slot print_timing: id 0 | task 155 | graphs reused = 1 1.05.171.164 I slot print_timing: id 0 | task 155 | graph reallocs = 22 / 0 (same size) / (changed size) 1.05.171.191 I slot release: id 0 | task 155 | stop processing: n_tokens = 129, truncated = 0 1.05.171.600 I slot print_timing: id 1 | task 157 | prompt eval time = 629.46 ms / 130 tokens ( 4.84 ms per token, 206.53 tokens per second) 1.05.171.606 I slot print_timing: id 1 | task 157 | eval time = 64.88 ms / 2 tokens ( 64.88 ms per token, 15.41 tokens per second) 1.05.171.606 I slot print_timing: id 1 | task 157 | total time = 694.35 ms / 132 tokens 1.05.171.607 I slot print_timing: id 1 | task 157 | graphs reused = 1 1.05.171.608 I slot print_timing: id 1 | task 157 | graph reallocs = 22 / 0 (same size) / (changed size) 1.05.171.625 I slot release: id 1 | task 157 | stop processing: n_tokens = 131, truncated = 0 1.05.172.043 I slot print_timing: id 2 | task 158 | prompt eval time = 628.84 ms / 141 tokens ( 4.46 ms per token, 224.22 tokens per second) 1.05.172.046 I slot print_timing: id 2 | task 158 | eval time = 64.67 ms / 2 tokens ( 64.67 ms per token, 15.46 tokens per second) 1.05.172.047 I slot print_timing: id 2 | task 158 | total time = 693.52 ms / 143 tokens 1.05.172.047 I slot print_timing: id 2 | task 158 | graphs reused = 1 1.05.172.048 I slot print_timing: id 2 | task 158 | graph reallocs = 22 / 0 (same size) / (changed size) 1.05.172.062 I slot release: id 2 | task 158 | stop processing: n_tokens = 142, truncated = 0 1.05.172.412 I slot print_timing: id 3 | task 156 | prompt eval time = 628.20 ms / 127 tokens ( 4.95 ms per token, 202.17 tokens per second) 1.05.172.418 I slot print_timing: id 3 | task 156 | eval time = 64.45 ms / 2 tokens ( 64.45 ms per token, 15.52 tokens per second) 1.05.172.419 I slot print_timing: id 3 | task 156 | total time = 692.64 ms / 129 tokens 1.05.172.420 I slot print_timing: id 3 | task 156 | graphs reused = 1 1.05.172.421 I slot print_timing: id 3 | task 156 | graph reallocs = 22 / 0 (same size) / (changed size) 1.05.172.437 I slot release: id 3 | task 156 | stop processing: n_tokens = 128, truncated = 0 1.05.180.266 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.217 1.05.197.422 I slot launch_slot_: id 0 | task 162 | processing task, is_child = 0 1.05.230.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 1.05.256.115 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.217 (> 0.100 thold), f_keep = 0.214 1.05.256.350 I slot launch_slot_: id 1 | task 163 | processing task, is_child = 0 1.05.256.435 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.276 (> 0.100 thold), f_keep = 0.227 1.05.256.635 I slot launch_slot_: id 3 | task 164 | processing task, is_child = 0 1.05.256.679 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.174 (> 0.100 thold), f_keep = 0.197 1.05.256.889 I slot launch_slot_: id 2 | task 165 | processing task, is_child = 0 1.06.113.719 I slot print_timing: id 0 | task 162 | prompt eval time = 790.96 ms / 123 tokens ( 6.43 ms per token, 155.51 tokens per second) 1.06.113.726 I slot print_timing: id 0 | task 162 | eval time = 65.85 ms / 2 tokens ( 65.85 ms per token, 15.19 tokens per second) 1.06.113.727 I slot print_timing: id 0 | task 162 | total time = 856.81 ms / 125 tokens 1.06.113.728 I slot print_timing: id 0 | task 162 | graphs reused = 1 1.06.113.729 I slot print_timing: id 0 | task 162 | graph reallocs = 22 / 0 (same size) / (changed size) 1.06.113.763 I slot release: id 0 | task 162 | stop processing: n_tokens = 124, truncated = 0 1.06.114.135 I slot print_timing: id 1 | task 163 | prompt eval time = 789.80 ms / 129 tokens ( 6.12 ms per token, 163.33 tokens per second) 1.06.114.139 I slot print_timing: id 1 | task 163 | eval time = 65.64 ms / 2 tokens ( 65.64 ms per token, 15.24 tokens per second) 1.06.114.140 I slot print_timing: id 1 | task 163 | total time = 855.44 ms / 131 tokens 1.06.114.141 I slot print_timing: id 1 | task 163 | graphs reused = 1 1.06.114.141 I slot print_timing: id 1 | task 163 | graph reallocs = 22 / 0 (same size) / (changed size) 1.06.114.160 I slot release: id 1 | task 163 | stop processing: n_tokens = 130, truncated = 0 1.06.114.582 I slot print_timing: id 2 | task 165 | prompt eval time = 788.70 ms / 161 tokens ( 4.90 ms per token, 204.13 tokens per second) 1.06.114.587 I slot print_timing: id 2 | task 165 | eval time = 65.45 ms / 2 tokens ( 65.45 ms per token, 15.28 tokens per second) 1.06.114.588 I slot print_timing: id 2 | task 165 | total time = 854.15 ms / 163 tokens 1.06.114.589 I slot print_timing: id 2 | task 165 | graphs reused = 1 1.06.114.590 I slot print_timing: id 2 | task 165 | graph reallocs = 22 / 0 (same size) / (changed size) 1.06.114.610 I slot release: id 2 | task 165 | stop processing: n_tokens = 162, truncated = 0 1.06.114.970 I slot print_timing: id 3 | task 164 | prompt eval time = 787.52 ms / 105 tokens ( 7.50 ms per token, 133.33 tokens per second) 1.06.114.974 I slot print_timing: id 3 | task 164 | eval time = 65.28 ms / 2 tokens ( 65.28 ms per token, 15.32 tokens per second) 1.06.114.975 I slot print_timing: id 3 | task 164 | total time = 852.81 ms / 107 tokens 1.06.114.976 I slot print_timing: id 3 | task 164 | graphs reused = 1 1.06.114.977 I slot print_timing: id 3 | task 164 | graph reallocs = 22 / 0 (same size) / (changed size) 1.06.114.990 I slot release: id 3 | task 164 | stop processing: n_tokens = 106, truncated = 0 1.06.124.415 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.226 1.06.124.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.129 MiB) 1.06.149.560 I slot launch_slot_: id 0 | task 169 | processing task, is_child = 0 1.06.149.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 1.06.173.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 1.06.199.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 1.06.225.759 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.274 1.06.225.957 I slot launch_slot_: id 3 | task 170 | processing task, is_child = 0 1.06.226.004 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.215 1.06.226.139 I slot launch_slot_: id 1 | task 171 | processing task, is_child = 0 1.06.226.166 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.173 1.06.226.323 I slot launch_slot_: id 2 | task 172 | processing task, is_child = 0 1.07.146.643 I slot print_timing: id 0 | task 169 | prompt eval time = 854.62 ms / 164 tokens ( 5.21 ms per token, 191.90 tokens per second) 1.07.146.649 I slot print_timing: id 0 | task 169 | eval time = 65.68 ms / 2 tokens ( 65.68 ms per token, 15.23 tokens per second) 1.07.146.650 I slot print_timing: id 0 | task 169 | total time = 920.30 ms / 166 tokens 1.07.146.651 I slot print_timing: id 0 | task 169 | graphs reused = 1 1.07.146.652 I slot print_timing: id 0 | task 169 | graph reallocs = 23 / 0 (same size) / (changed size) 1.07.146.678 I slot release: id 0 | task 169 | stop processing: n_tokens = 165, truncated = 0 1.07.146.985 I slot print_timing: id 1 | task 171 | prompt eval time = 853.85 ms / 141 tokens ( 6.06 ms per token, 165.13 tokens per second) 1.07.146.988 I slot print_timing: id 1 | task 171 | eval time = 65.44 ms / 2 tokens ( 65.44 ms per token, 15.28 tokens per second) 1.07.146.989 I slot print_timing: id 1 | task 171 | total time = 919.29 ms / 143 tokens 1.07.146.989 I slot print_timing: id 1 | task 171 | graphs reused = 1 1.07.146.990 I slot print_timing: id 1 | task 171 | graph reallocs = 23 / 0 (same size) / (changed size) 1.07.147.005 I slot release: id 1 | task 171 | stop processing: n_tokens = 142, truncated = 0 1.07.147.334 I slot print_timing: id 2 | task 172 | prompt eval time = 852.73 ms / 154 tokens ( 5.54 ms per token, 180.60 tokens per second) 1.07.147.337 I slot print_timing: id 2 | task 172 | eval time = 65.17 ms / 2 tokens ( 65.17 ms per token, 15.34 tokens per second) 1.07.147.338 I slot print_timing: id 2 | task 172 | total time = 917.90 ms / 156 tokens 1.07.147.338 I slot print_timing: id 2 | task 172 | graphs reused = 1 1.07.147.339 I slot print_timing: id 2 | task 172 | graph reallocs = 23 / 0 (same size) / (changed size) 1.07.147.351 I slot release: id 2 | task 172 | stop processing: n_tokens = 155, truncated = 0 1.07.147.729 I slot print_timing: id 3 | task 170 | prompt eval time = 851.59 ms / 110 tokens ( 7.74 ms per token, 129.17 tokens per second) 1.07.147.735 I slot print_timing: id 3 | task 170 | eval time = 64.97 ms / 2 tokens ( 64.97 ms per token, 15.39 tokens per second) 1.07.147.736 I slot print_timing: id 3 | task 170 | total time = 916.56 ms / 112 tokens 1.07.147.737 I slot print_timing: id 3 | task 170 | graphs reused = 1 1.07.147.738 I slot print_timing: id 3 | task 170 | graph reallocs = 23 / 0 (same size) / (changed size) 1.07.147.756 I slot release: id 3 | task 170 | stop processing: n_tokens = 111, truncated = 0 1.07.156.674 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.170 1.07.156.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.787 MiB) 1.07.182.425 I slot launch_slot_: id 0 | task 176 | processing task, is_child = 0 1.07.182.476 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.224 MiB) 1.07.207.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 1.07.233.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 1.07.260.431 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.197 1.07.260.631 I slot launch_slot_: id 1 | task 177 | processing task, is_child = 0 1.07.260.680 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.181 1.07.260.841 I slot launch_slot_: id 2 | task 178 | processing task, is_child = 0 1.07.260.866 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.264 (> 0.100 thold), f_keep = 0.261 1.07.261.003 I slot launch_slot_: id 3 | task 179 | processing task, is_child = 0 1.07.978.363 I slot print_timing: id 0 | task 176 | prompt eval time = 653.29 ms / 110 tokens ( 5.94 ms per token, 168.38 tokens per second) 1.07.978.369 I slot print_timing: id 0 | task 176 | eval time = 64.04 ms / 2 tokens ( 64.04 ms per token, 15.61 tokens per second) 1.07.978.371 I slot print_timing: id 0 | task 176 | total time = 717.34 ms / 112 tokens 1.07.978.372 I slot print_timing: id 0 | task 176 | graphs reused = 1 1.07.978.373 I slot print_timing: id 0 | task 176 | graph reallocs = 24 / 0 (same size) / (changed size) 1.07.978.407 I slot release: id 0 | task 176 | stop processing: n_tokens = 111, truncated = 0 1.07.978.719 I slot print_timing: id 1 | task 177 | prompt eval time = 652.76 ms / 148 tokens ( 4.41 ms per token, 226.73 tokens per second) 1.07.978.723 I slot print_timing: id 1 | task 177 | eval time = 63.67 ms / 2 tokens ( 63.67 ms per token, 15.70 tokens per second) 1.07.978.724 I slot print_timing: id 1 | task 177 | total time = 716.43 ms / 150 tokens 1.07.978.724 I slot print_timing: id 1 | task 177 | graphs reused = 1 1.07.978.725 I slot print_timing: id 1 | task 177 | graph reallocs = 24 / 0 (same size) / (changed size) 1.07.978.744 I slot release: id 1 | task 177 | stop processing: n_tokens = 149, truncated = 0 1.07.979.104 I slot print_timing: id 2 | task 178 | prompt eval time = 652.12 ms / 137 tokens ( 4.76 ms per token, 210.09 tokens per second) 1.07.979.108 I slot print_timing: id 2 | task 178 | eval time = 63.45 ms / 2 tokens ( 63.45 ms per token, 15.76 tokens per second) 1.07.979.109 I slot print_timing: id 2 | task 178 | total time = 715.56 ms / 139 tokens 1.07.979.110 I slot print_timing: id 2 | task 178 | graphs reused = 1 1.07.979.111 I slot print_timing: id 2 | task 178 | graph reallocs = 24 / 0 (same size) / (changed size) 1.07.979.125 I slot release: id 2 | task 178 | stop processing: n_tokens = 138, truncated = 0 1.07.979.483 I slot print_timing: id 3 | task 179 | prompt eval time = 651.34 ms / 110 tokens ( 5.92 ms per token, 168.88 tokens per second) 1.07.979.487 I slot print_timing: id 3 | task 179 | eval time = 63.22 ms / 2 tokens ( 63.22 ms per token, 15.82 tokens per second) 1.07.979.488 I slot print_timing: id 3 | task 179 | total time = 714.56 ms / 112 tokens 1.07.979.489 I slot print_timing: id 3 | task 179 | graphs reused = 1 1.07.979.490 I slot print_timing: id 3 | task 179 | graph reallocs = 24 / 0 (same size) / (changed size) 1.07.979.502 I slot release: id 3 | task 179 | stop processing: n_tokens = 111, truncated = 0 1.07.988.148 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.261 1.08.004.952 I slot launch_slot_: id 3 | task 183 | processing task, is_child = 0 1.08.005.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 1.08.030.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.193 MiB) 1.08.056.982 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.254 MiB) 1.08.082.135 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.215 (> 0.100 thold), f_keep = 0.252 1.08.082.336 I slot launch_slot_: id 0 | task 184 | processing task, is_child = 0 1.08.082.382 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.228 (> 0.100 thold), f_keep = 0.188 1.08.082.514 I slot launch_slot_: id 1 | task 185 | processing task, is_child = 0 1.08.082.541 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.184 (> 0.100 thold), f_keep = 0.203 1.08.082.694 I slot launch_slot_: id 2 | task 186 | processing task, is_child = 0 1.08.978.641 I slot print_timing: id 0 | task 184 | prompt eval time = 831.37 ms / 130 tokens ( 6.40 ms per token, 156.37 tokens per second) 1.08.978.648 I slot print_timing: id 0 | task 184 | eval time = 64.55 ms / 2 tokens ( 64.55 ms per token, 15.49 tokens per second) 1.08.978.649 I slot print_timing: id 0 | task 184 | total time = 895.92 ms / 132 tokens 1.08.978.653 I slot print_timing: id 0 | task 184 | graphs reused = 1 1.08.978.654 I slot print_timing: id 0 | task 184 | graph reallocs = 25 / 0 (same size) / (changed size) 1.08.978.683 I slot release: id 0 | task 184 | stop processing: n_tokens = 131, truncated = 0 1.08.979.092 I slot print_timing: id 1 | task 185 | prompt eval time = 830.68 ms / 123 tokens ( 6.75 ms per token, 148.07 tokens per second) 1.08.979.096 I slot print_timing: id 1 | task 185 | eval time = 64.45 ms / 2 tokens ( 64.45 ms per token, 15.52 tokens per second) 1.08.979.098 I slot print_timing: id 1 | task 185 | total time = 895.13 ms / 125 tokens 1.08.979.098 I slot print_timing: id 1 | task 185 | graphs reused = 1 1.08.979.099 I slot print_timing: id 1 | task 185 | graph reallocs = 25 / 0 (same size) / (changed size) 1.08.979.117 I slot release: id 1 | task 185 | stop processing: n_tokens = 124, truncated = 0 1.08.979.535 I slot print_timing: id 2 | task 186 | prompt eval time = 830.14 ms / 152 tokens ( 5.46 ms per token, 183.10 tokens per second) 1.08.979.539 I slot print_timing: id 2 | task 186 | eval time = 64.19 ms / 2 tokens ( 64.19 ms per token, 15.58 tokens per second) 1.08.979.540 I slot print_timing: id 2 | task 186 | total time = 894.33 ms / 154 tokens 1.08.979.541 I slot print_timing: id 2 | task 186 | graphs reused = 1 1.08.979.542 I slot print_timing: id 2 | task 186 | graph reallocs = 25 / 0 (same size) / (changed size) 1.08.979.556 I slot release: id 2 | task 186 | stop processing: n_tokens = 153, truncated = 0 1.08.979.932 I slot print_timing: id 3 | task 183 | prompt eval time = 829.75 ms / 112 tokens ( 7.41 ms per token, 134.98 tokens per second) 1.08.979.937 I slot print_timing: id 3 | task 183 | eval time = 63.74 ms / 2 tokens ( 63.74 ms per token, 15.69 tokens per second) 1.08.979.938 I slot print_timing: id 3 | task 183 | total time = 893.48 ms / 114 tokens 1.08.979.939 I slot print_timing: id 3 | task 183 | graphs reused = 1 1.08.979.940 I slot print_timing: id 3 | task 183 | graph reallocs = 25 / 0 (same size) / (changed size) 1.08.979.956 I slot release: id 3 | task 183 | stop processing: n_tokens = 113, truncated = 0 1.08.988.180 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.257 1.08.988.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 1.09.013.648 I slot launch_slot_: id 3 | task 190 | processing task, is_child = 0 1.09.013.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 1.09.039.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 1.09.064.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 1.09.090.556 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.227 (> 0.100 thold), f_keep = 0.221 1.09.090.780 I slot launch_slot_: id 0 | task 191 | processing task, is_child = 0 1.09.090.830 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 1.09.090.965 I slot launch_slot_: id 1 | task 192 | processing task, is_child = 0 1.09.090.992 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.183 1.09.091.147 I slot launch_slot_: id 2 | task 193 | processing task, is_child = 0 1.09.962.578 I slot print_timing: id 0 | task 191 | prompt eval time = 805.47 ms / 128 tokens ( 6.29 ms per token, 158.91 tokens per second) 1.09.962.586 I slot print_timing: id 0 | task 191 | eval time = 65.94 ms / 2 tokens ( 65.94 ms per token, 15.17 tokens per second) 1.09.962.587 I slot print_timing: id 0 | task 191 | total time = 871.41 ms / 130 tokens 1.09.962.588 I slot print_timing: id 0 | task 191 | graphs reused = 1 1.09.962.589 I slot print_timing: id 0 | task 191 | graph reallocs = 27 / 0 (same size) / (changed size) 1.09.962.622 I slot release: id 0 | task 191 | stop processing: n_tokens = 129, truncated = 0 1.09.962.970 I slot print_timing: id 1 | task 192 | prompt eval time = 804.85 ms / 166 tokens ( 4.85 ms per token, 206.25 tokens per second) 1.09.962.974 I slot print_timing: id 1 | task 192 | eval time = 65.75 ms / 2 tokens ( 65.75 ms per token, 15.21 tokens per second) 1.09.962.975 I slot print_timing: id 1 | task 192 | total time = 870.60 ms / 168 tokens 1.09.962.976 I slot print_timing: id 1 | task 192 | graphs reused = 1 1.09.962.977 I slot print_timing: id 1 | task 192 | graph reallocs = 27 / 0 (same size) / (changed size) 1.09.962.998 I slot release: id 1 | task 192 | stop processing: n_tokens = 167, truncated = 0 1.09.963.353 I slot print_timing: id 2 | task 193 | prompt eval time = 804.25 ms / 157 tokens ( 5.12 ms per token, 195.21 tokens per second) 1.09.963.358 I slot print_timing: id 2 | task 193 | eval time = 65.51 ms / 2 tokens ( 65.51 ms per token, 15.26 tokens per second) 1.09.963.359 I slot print_timing: id 2 | task 193 | total time = 869.76 ms / 159 tokens 1.09.963.359 I slot print_timing: id 2 | task 193 | graphs reused = 1 1.09.963.360 I slot print_timing: id 2 | task 193 | graph reallocs = 27 / 0 (same size) / (changed size) 1.09.963.376 I slot release: id 2 | task 193 | stop processing: n_tokens = 158, truncated = 0 1.09.963.747 I slot print_timing: id 3 | task 190 | prompt eval time = 803.73 ms / 114 tokens ( 7.05 ms per token, 141.84 tokens per second) 1.09.963.751 I slot print_timing: id 3 | task 190 | eval time = 65.21 ms / 2 tokens ( 65.21 ms per token, 15.34 tokens per second) 1.09.963.752 I slot print_timing: id 3 | task 190 | total time = 868.93 ms / 116 tokens 1.09.963.752 I slot print_timing: id 3 | task 190 | graphs reused = 1 1.09.963.753 I slot print_timing: id 3 | task 190 | graph reallocs = 27 / 0 (same size) / (changed size) 1.09.963.766 I slot release: id 3 | task 190 | stop processing: n_tokens = 115, truncated = 0 1.09.972.188 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.217 1.09.972.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.099 MiB) 1.09.996.536 I slot launch_slot_: id 0 | task 197 | processing task, is_child = 0 1.09.996.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 1.10.022.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 1.10.047.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.066 MiB) 1.10.073.080 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.199 (> 0.100 thold), f_keep = 0.168 1.10.082.051 I slot launch_slot_: id 1 | task 198 | processing task, is_child = 0 1.10.082.110 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.156 (> 0.100 thold), f_keep = 0.177 1.10.082.272 I slot launch_slot_: id 2 | task 199 | processing task, is_child = 0 1.10.082.299 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.183 (> 0.100 thold), f_keep = 0.243 1.10.082.440 I slot launch_slot_: id 3 | task 200 | processing task, is_child = 0 1.11.044.646 I slot print_timing: id 0 | task 197 | prompt eval time = 896.19 ms / 108 tokens ( 8.30 ms per token, 120.51 tokens per second) 1.11.044.653 I slot print_timing: id 0 | task 197 | eval time = 65.99 ms / 2 tokens ( 65.99 ms per token, 15.15 tokens per second) 1.11.044.654 I slot print_timing: id 0 | task 197 | total time = 962.18 ms / 110 tokens 1.11.044.656 I slot print_timing: id 0 | task 197 | graphs reused = 1 1.11.044.657 I slot print_timing: id 0 | task 197 | graph reallocs = 29 / 0 (same size) / (changed size) 1.11.044.690 I slot release: id 0 | task 197 | stop processing: n_tokens = 109, truncated = 0 1.11.045.017 I slot print_timing: id 1 | task 198 | prompt eval time = 895.49 ms / 141 tokens ( 6.35 ms per token, 157.46 tokens per second) 1.11.045.022 I slot print_timing: id 1 | task 198 | eval time = 65.81 ms / 2 tokens ( 65.81 ms per token, 15.20 tokens per second) 1.11.045.023 I slot print_timing: id 1 | task 198 | total time = 961.30 ms / 143 tokens 1.11.045.023 I slot print_timing: id 1 | task 198 | graphs reused = 1 1.11.045.024 I slot print_timing: id 1 | task 198 | graph reallocs = 29 / 0 (same size) / (changed size) 1.11.045.041 I slot release: id 1 | task 198 | stop processing: n_tokens = 142, truncated = 0 1.11.045.377 I slot print_timing: id 2 | task 199 | prompt eval time = 894.95 ms / 179 tokens ( 5.00 ms per token, 200.01 tokens per second) 1.11.045.381 I slot print_timing: id 2 | task 199 | eval time = 65.58 ms / 2 tokens ( 65.58 ms per token, 15.25 tokens per second) 1.11.045.382 I slot print_timing: id 2 | task 199 | total time = 960.54 ms / 181 tokens 1.11.045.382 I slot print_timing: id 2 | task 199 | graphs reused = 1 1.11.045.383 I slot print_timing: id 2 | task 199 | graph reallocs = 29 / 0 (same size) / (changed size) 1.11.045.403 I slot release: id 2 | task 199 | stop processing: n_tokens = 180, truncated = 0 1.11.045.761 I slot print_timing: id 3 | task 200 | prompt eval time = 894.25 ms / 153 tokens ( 5.84 ms per token, 171.09 tokens per second) 1.11.045.765 I slot print_timing: id 3 | task 200 | eval time = 65.41 ms / 2 tokens ( 65.41 ms per token, 15.29 tokens per second) 1.11.045.766 I slot print_timing: id 3 | task 200 | total time = 959.66 ms / 155 tokens 1.11.045.766 I slot print_timing: id 3 | task 200 | graphs reused = 1 1.11.045.767 I slot print_timing: id 3 | task 200 | graph reallocs = 29 / 0 (same size) / (changed size) 1.11.045.782 I slot release: id 3 | task 200 | stop processing: n_tokens = 154, truncated = 0 1.11.054.852 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.207 (> 0.100 thold), f_keep = 0.257 1.11.071.600 I slot launch_slot_: id 0 | task 204 | processing task, is_child = 0 1.11.071.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 1.11.097.248 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 1.11.122.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.005 MiB) 1.11.147.492 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.241 (> 0.100 thold), f_keep = 0.197 1.11.156.827 I slot launch_slot_: id 1 | task 205 | processing task, is_child = 0 1.11.156.884 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.209 (> 0.100 thold), f_keep = 0.156 1.11.157.036 I slot launch_slot_: id 2 | task 206 | processing task, is_child = 0 1.11.157.063 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.177 (> 0.100 thold), f_keep = 0.182 1.11.157.198 I slot launch_slot_: id 3 | task 207 | processing task, is_child = 0 1.12.069.929 I slot print_timing: id 0 | task 204 | prompt eval time = 849.25 ms / 135 tokens ( 6.29 ms per token, 158.96 tokens per second) 1.12.069.935 I slot print_timing: id 0 | task 204 | eval time = 63.47 ms / 2 tokens ( 63.47 ms per token, 15.76 tokens per second) 1.12.069.937 I slot print_timing: id 0 | task 204 | total time = 912.71 ms / 137 tokens 1.12.069.937 I slot print_timing: id 0 | task 204 | graphs reused = 1 1.12.069.938 I slot print_timing: id 0 | task 204 | graph reallocs = 30 / 0 (same size) / (changed size) 1.12.069.962 I slot release: id 0 | task 204 | stop processing: n_tokens = 136, truncated = 0 1.12.070.279 I slot print_timing: id 1 | task 205 | prompt eval time = 848.59 ms / 116 tokens ( 7.32 ms per token, 136.70 tokens per second) 1.12.070.285 I slot print_timing: id 1 | task 205 | eval time = 63.26 ms / 2 tokens ( 63.26 ms per token, 15.81 tokens per second) 1.12.070.286 I slot print_timing: id 1 | task 205 | total time = 911.85 ms / 118 tokens 1.12.070.287 I slot print_timing: id 1 | task 205 | graphs reused = 1 1.12.070.287 I slot print_timing: id 1 | task 205 | graph reallocs = 30 / 0 (same size) / (changed size) 1.12.070.306 I slot release: id 1 | task 205 | stop processing: n_tokens = 117, truncated = 0 1.12.070.596 I slot print_timing: id 2 | task 206 | prompt eval time = 848.10 ms / 134 tokens ( 6.33 ms per token, 158.00 tokens per second) 1.12.070.599 I slot print_timing: id 2 | task 206 | eval time = 62.98 ms / 2 tokens ( 62.98 ms per token, 15.88 tokens per second) 1.12.070.600 I slot print_timing: id 2 | task 206 | total time = 911.08 ms / 136 tokens 1.12.070.600 I slot print_timing: id 2 | task 206 | graphs reused = 1 1.12.070.601 I slot print_timing: id 2 | task 206 | graph reallocs = 30 / 0 (same size) / (changed size) 1.12.070.612 I slot release: id 2 | task 206 | stop processing: n_tokens = 135, truncated = 0 1.12.070.979 I slot print_timing: id 3 | task 207 | prompt eval time = 847.48 ms / 158 tokens ( 5.36 ms per token, 186.44 tokens per second) 1.12.070.985 I slot print_timing: id 3 | task 207 | eval time = 62.77 ms / 2 tokens ( 62.77 ms per token, 15.93 tokens per second) 1.12.070.986 I slot print_timing: id 3 | task 207 | total time = 910.25 ms / 160 tokens 1.12.070.987 I slot print_timing: id 3 | task 207 | graphs reused = 1 1.12.070.988 I slot print_timing: id 3 | task 207 | graph reallocs = 30 / 0 (same size) / (changed size) 1.12.071.007 I slot release: id 3 | task 207 | stop processing: n_tokens = 159, truncated = 0 1.12.079.621 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.206 1.12.079.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 1.12.100.830 I slot launch_slot_: id 0 | task 211 | processing task, is_child = 0 1.12.123.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 1.12.125.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 1.12.149.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 1.12.173.693 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.248 1.12.173.956 I slot launch_slot_: id 1 | task 212 | processing task, is_child = 0 1.12.174.043 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.207 1.12.184.192 I slot launch_slot_: id 2 | task 213 | processing task, is_child = 0 1.12.184.245 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.178 (> 0.100 thold), f_keep = 0.176 1.12.184.440 I slot launch_slot_: id 3 | task 214 | processing task, is_child = 0 1.13.001.853 I slot print_timing: id 0 | task 211 | prompt eval time = 753.48 ms / 149 tokens ( 5.06 ms per token, 197.75 tokens per second) 1.13.001.860 I slot print_timing: id 0 | task 211 | eval time = 63.91 ms / 2 tokens ( 63.91 ms per token, 15.65 tokens per second) 1.13.001.861 I slot print_timing: id 0 | task 211 | total time = 817.39 ms / 151 tokens 1.13.001.861 I slot print_timing: id 0 | task 211 | graphs reused = 1 1.13.001.862 I slot print_timing: id 0 | task 211 | graph reallocs = 30 / 0 (same size) / (changed size) 1.13.001.891 I slot release: id 0 | task 211 | stop processing: n_tokens = 150, truncated = 0 1.13.002.188 I slot print_timing: id 1 | task 212 | prompt eval time = 752.40 ms / 117 tokens ( 6.43 ms per token, 155.50 tokens per second) 1.13.002.193 I slot print_timing: id 1 | task 212 | eval time = 63.68 ms / 2 tokens ( 63.68 ms per token, 15.70 tokens per second) 1.13.002.193 I slot print_timing: id 1 | task 212 | total time = 816.09 ms / 119 tokens 1.13.002.194 I slot print_timing: id 1 | task 212 | graphs reused = 1 1.13.002.194 I slot print_timing: id 1 | task 212 | graph reallocs = 30 / 0 (same size) / (changed size) 1.13.002.209 I slot release: id 1 | task 212 | stop processing: n_tokens = 118, truncated = 0 1.13.002.505 I slot print_timing: id 2 | task 213 | prompt eval time = 751.25 ms / 122 tokens ( 6.16 ms per token, 162.40 tokens per second) 1.13.002.510 I slot print_timing: id 2 | task 213 | eval time = 63.43 ms / 2 tokens ( 63.43 ms per token, 15.76 tokens per second) 1.13.002.511 I slot print_timing: id 2 | task 213 | total time = 814.68 ms / 124 tokens 1.13.002.512 I slot print_timing: id 2 | task 213 | graphs reused = 1 1.13.002.513 I slot print_timing: id 2 | task 213 | graph reallocs = 30 / 0 (same size) / (changed size) 1.13.002.531 I slot release: id 2 | task 213 | stop processing: n_tokens = 123, truncated = 0 1.13.002.842 I slot print_timing: id 3 | task 214 | prompt eval time = 750.11 ms / 157 tokens ( 4.78 ms per token, 209.30 tokens per second) 1.13.002.845 I slot print_timing: id 3 | task 214 | eval time = 63.20 ms / 2 tokens ( 63.20 ms per token, 15.82 tokens per second) 1.13.002.846 I slot print_timing: id 3 | task 214 | total time = 813.32 ms / 159 tokens 1.13.002.847 I slot print_timing: id 3 | task 214 | graphs reused = 1 1.13.002.848 I slot print_timing: id 3 | task 214 | graph reallocs = 30 / 0 (same size) / (changed size) 1.13.002.863 I slot release: id 3 | task 214 | stop processing: n_tokens = 158, truncated = 0 1.13.011.689 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.188 (> 0.100 thold), f_keep = 0.187 1.13.029.705 I slot launch_slot_: id 0 | task 218 | processing task, is_child = 0 1.13.029.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 1.13.072.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 1.13.097.611 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.182 (> 0.100 thold), f_keep = 0.237 1.13.097.883 I slot launch_slot_: id 1 | task 219 | processing task, is_child = 0 1.13.097.963 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.228 1.13.098.174 I slot launch_slot_: id 2 | task 220 | processing task, is_child = 0 1.13.098.220 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.175 (> 0.100 thold), f_keep = 0.177 1.13.098.416 I slot launch_slot_: id 3 | task 221 | processing task, is_child = 0 1.14.000.703 I slot print_timing: id 0 | task 218 | prompt eval time = 836.26 ms / 149 tokens ( 5.61 ms per token, 178.17 tokens per second) 1.14.000.709 I slot print_timing: id 0 | task 218 | eval time = 66.00 ms / 2 tokens ( 66.00 ms per token, 15.15 tokens per second) 1.14.000.711 I slot print_timing: id 0 | task 218 | total time = 902.26 ms / 151 tokens 1.14.000.711 I slot print_timing: id 0 | task 218 | graphs reused = 1 1.14.000.712 I slot print_timing: id 0 | task 218 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.000.739 I slot release: id 0 | task 218 | stop processing: n_tokens = 150, truncated = 0 1.14.001.049 I slot print_timing: id 1 | task 219 | prompt eval time = 835.16 ms / 154 tokens ( 5.42 ms per token, 184.40 tokens per second) 1.14.001.053 I slot print_timing: id 1 | task 219 | eval time = 65.74 ms / 2 tokens ( 65.74 ms per token, 15.21 tokens per second) 1.14.001.054 I slot print_timing: id 1 | task 219 | total time = 900.90 ms / 156 tokens 1.14.001.054 I slot print_timing: id 1 | task 219 | graphs reused = 1 1.14.001.055 I slot print_timing: id 1 | task 219 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.001.071 I slot release: id 1 | task 219 | stop processing: n_tokens = 155, truncated = 0 1.14.001.391 I slot print_timing: id 2 | task 220 | prompt eval time = 834.07 ms / 155 tokens ( 5.38 ms per token, 185.84 tokens per second) 1.14.001.394 I slot print_timing: id 2 | task 220 | eval time = 65.45 ms / 2 tokens ( 65.45 ms per token, 15.28 tokens per second) 1.14.001.395 I slot print_timing: id 2 | task 220 | total time = 899.52 ms / 157 tokens 1.14.001.395 I slot print_timing: id 2 | task 220 | graphs reused = 1 1.14.001.396 I slot print_timing: id 2 | task 220 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.001.408 I slot release: id 2 | task 220 | stop processing: n_tokens = 156, truncated = 0 1.14.001.757 I slot print_timing: id 3 | task 221 | prompt eval time = 833.44 ms / 160 tokens ( 5.21 ms per token, 191.98 tokens per second) 1.14.001.763 I slot print_timing: id 3 | task 221 | eval time = 65.15 ms / 2 tokens ( 65.15 ms per token, 15.35 tokens per second) 1.14.001.764 I slot print_timing: id 3 | task 221 | total time = 898.59 ms / 162 tokens 1.14.001.765 I slot print_timing: id 3 | task 221 | graphs reused = 1 1.14.001.765 I slot print_timing: id 3 | task 221 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.001.780 I slot release: id 3 | task 221 | stop processing: n_tokens = 161, truncated = 0 1.14.011.255 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.151 (> 0.100 thold), f_keep = 0.187 1.14.011.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.661 MiB) 1.14.036.594 I slot launch_slot_: id 0 | task 225 | processing task, is_child = 0 1.14.036.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.818 MiB) 1.14.060.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 1.14.085.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 1.14.087.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 1.14.111.262 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.181 1.14.111.474 I slot launch_slot_: id 1 | task 226 | processing task, is_child = 0 1.14.111.521 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.275 (> 0.100 thold), f_keep = 0.179 1.14.120.336 I slot launch_slot_: id 2 | task 227 | processing task, is_child = 0 1.14.120.367 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.262 (> 0.100 thold), f_keep = 0.174 1.14.120.505 I slot launch_slot_: id 3 | task 228 | processing task, is_child = 0 1.14.969.041 I slot print_timing: id 0 | task 225 | prompt eval time = 783.07 ms / 185 tokens ( 4.23 ms per token, 236.25 tokens per second) 1.14.969.047 I slot print_timing: id 0 | task 225 | eval time = 65.45 ms / 2 tokens ( 65.45 ms per token, 15.28 tokens per second) 1.14.969.048 I slot print_timing: id 0 | task 225 | total time = 848.51 ms / 187 tokens 1.14.969.049 I slot print_timing: id 0 | task 225 | graphs reused = 1 1.14.969.050 I slot print_timing: id 0 | task 225 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.969.078 I slot release: id 0 | task 225 | stop processing: n_tokens = 186, truncated = 0 1.14.969.393 I slot print_timing: id 1 | task 226 | prompt eval time = 782.50 ms / 114 tokens ( 6.86 ms per token, 145.69 tokens per second) 1.14.969.396 I slot print_timing: id 1 | task 226 | eval time = 65.17 ms / 2 tokens ( 65.17 ms per token, 15.34 tokens per second) 1.14.969.397 I slot print_timing: id 1 | task 226 | total time = 847.67 ms / 116 tokens 1.14.969.397 I slot print_timing: id 1 | task 226 | graphs reused = 1 1.14.969.398 I slot print_timing: id 1 | task 226 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.969.412 I slot release: id 1 | task 226 | stop processing: n_tokens = 115, truncated = 0 1.14.969.774 I slot print_timing: id 2 | task 227 | prompt eval time = 781.97 ms / 102 tokens ( 7.67 ms per token, 130.44 tokens per second) 1.14.969.779 I slot print_timing: id 2 | task 227 | eval time = 64.87 ms / 2 tokens ( 64.87 ms per token, 15.42 tokens per second) 1.14.969.781 I slot print_timing: id 2 | task 227 | total time = 846.84 ms / 104 tokens 1.14.969.782 I slot print_timing: id 2 | task 227 | graphs reused = 1 1.14.969.783 I slot print_timing: id 2 | task 227 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.969.797 I slot release: id 2 | task 227 | stop processing: n_tokens = 103, truncated = 0 1.14.970.135 I slot print_timing: id 3 | task 228 | prompt eval time = 781.37 ms / 107 tokens ( 7.30 ms per token, 136.94 tokens per second) 1.14.970.139 I slot print_timing: id 3 | task 228 | eval time = 64.63 ms / 2 tokens ( 64.63 ms per token, 15.47 tokens per second) 1.14.970.140 I slot print_timing: id 3 | task 228 | total time = 846.00 ms / 109 tokens 1.14.970.141 I slot print_timing: id 3 | task 228 | graphs reused = 1 1.14.970.142 I slot print_timing: id 3 | task 228 | graph reallocs = 31 / 0 (same size) / (changed size) 1.14.970.154 I slot release: id 3 | task 228 | stop processing: n_tokens = 108, truncated = 0 1.14.978.395 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.151 1.14.995.883 I slot launch_slot_: id 0 | task 232 | processing task, is_child = 0 1.14.995.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 1.15.015.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 1.15.061.835 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.171 (> 0.100 thold), f_keep = 0.243 1.15.062.043 I slot launch_slot_: id 1 | task 233 | processing task, is_child = 0 1.15.062.092 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.222 (> 0.100 thold), f_keep = 0.272 1.15.062.256 I slot launch_slot_: id 2 | task 234 | processing task, is_child = 0 1.15.062.282 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.259 1.15.071.114 I slot launch_slot_: id 3 | task 235 | processing task, is_child = 0 1.15.886.494 I slot print_timing: id 0 | task 232 | prompt eval time = 752.02 ms / 122 tokens ( 6.16 ms per token, 162.23 tokens per second) 1.15.886.500 I slot print_timing: id 0 | task 232 | eval time = 63.34 ms / 2 tokens ( 63.34 ms per token, 15.79 tokens per second) 1.15.886.501 I slot print_timing: id 0 | task 232 | total time = 815.36 ms / 124 tokens 1.15.886.502 I slot print_timing: id 0 | task 232 | graphs reused = 1 1.15.886.503 I slot print_timing: id 0 | task 232 | graph reallocs = 31 / 0 (same size) / (changed size) 1.15.886.528 I slot release: id 0 | task 232 | stop processing: n_tokens = 123, truncated = 0 1.15.886.797 I slot print_timing: id 1 | task 233 | prompt eval time = 751.34 ms / 164 tokens ( 4.58 ms per token, 218.28 tokens per second) 1.15.886.800 I slot print_timing: id 1 | task 233 | eval time = 63.06 ms / 2 tokens ( 63.06 ms per token, 15.86 tokens per second) 1.15.886.801 I slot print_timing: id 1 | task 233 | total time = 814.41 ms / 166 tokens 1.15.886.801 I slot print_timing: id 1 | task 233 | graphs reused = 1 1.15.886.802 I slot print_timing: id 1 | task 233 | graph reallocs = 31 / 0 (same size) / (changed size) 1.15.886.817 I slot release: id 1 | task 233 | stop processing: n_tokens = 165, truncated = 0 1.15.887.113 I slot print_timing: id 2 | task 234 | prompt eval time = 750.68 ms / 126 tokens ( 5.96 ms per token, 167.85 tokens per second) 1.15.887.118 I slot print_timing: id 2 | task 234 | eval time = 62.79 ms / 2 tokens ( 62.79 ms per token, 15.93 tokens per second) 1.15.887.119 I slot print_timing: id 2 | task 234 | total time = 813.47 ms / 128 tokens 1.15.887.119 I slot print_timing: id 2 | task 234 | graphs reused = 1 1.15.887.120 I slot print_timing: id 2 | task 234 | graph reallocs = 31 / 0 (same size) / (changed size) 1.15.887.137 I slot release: id 2 | task 234 | stop processing: n_tokens = 127, truncated = 0 1.15.887.438 I slot print_timing: id 3 | task 235 | prompt eval time = 749.92 ms / 110 tokens ( 6.82 ms per token, 146.68 tokens per second) 1.15.887.442 I slot print_timing: id 3 | task 235 | eval time = 62.56 ms / 2 tokens ( 62.56 ms per token, 15.99 tokens per second) 1.15.887.443 I slot print_timing: id 3 | task 235 | total time = 812.47 ms / 112 tokens 1.15.887.443 I slot print_timing: id 3 | task 235 | graphs reused = 1 1.15.887.444 I slot print_timing: id 3 | task 235 | graph reallocs = 31 / 0 (same size) / (changed size) 1.15.887.456 I slot release: id 3 | task 235 | stop processing: n_tokens = 111, truncated = 0 1.15.896.293 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.210 (> 0.100 thold), f_keep = 0.261 1.15.914.159 I slot launch_slot_: id 3 | task 239 | processing task, is_child = 0 1.15.914.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.630 MiB) 1.15.937.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.755 MiB) 1.15.961.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 1.15.985.609 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.224 (> 0.100 thold), f_keep = 0.228 1.15.985.820 I slot launch_slot_: id 0 | task 240 | processing task, is_child = 0 1.15.985.868 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.230 (> 0.100 thold), f_keep = 0.170 1.15.986.006 I slot launch_slot_: id 1 | task 241 | processing task, is_child = 0 1.15.986.032 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.204 (> 0.100 thold), f_keep = 0.220 1.15.994.936 I slot launch_slot_: id 2 | task 242 | processing task, is_child = 0 1.16.788.512 I slot print_timing: id 0 | task 240 | prompt eval time = 729.44 ms / 125 tokens ( 5.84 ms per token, 171.37 tokens per second) 1.16.788.518 I slot print_timing: id 0 | task 240 | eval time = 64.12 ms / 2 tokens ( 64.12 ms per token, 15.60 tokens per second) 1.16.788.519 I slot print_timing: id 0 | task 240 | total time = 793.55 ms / 127 tokens 1.16.788.520 I slot print_timing: id 0 | task 240 | graphs reused = 1 1.16.788.521 I slot print_timing: id 0 | task 240 | graph reallocs = 31 / 0 (same size) / (changed size) 1.16.788.547 I slot release: id 0 | task 240 | stop processing: n_tokens = 126, truncated = 0 1.16.788.828 I slot print_timing: id 1 | task 241 | prompt eval time = 728.86 ms / 122 tokens ( 5.97 ms per token, 167.38 tokens per second) 1.16.788.831 I slot print_timing: id 1 | task 241 | eval time = 63.74 ms / 2 tokens ( 63.74 ms per token, 15.69 tokens per second) 1.16.788.832 I slot print_timing: id 1 | task 241 | total time = 792.60 ms / 124 tokens 1.16.788.832 I slot print_timing: id 1 | task 241 | graphs reused = 1 1.16.788.833 I slot print_timing: id 1 | task 241 | graph reallocs = 31 / 0 (same size) / (changed size) 1.16.788.846 I slot release: id 1 | task 241 | stop processing: n_tokens = 123, truncated = 0 1.16.789.192 I slot print_timing: id 2 | task 242 | prompt eval time = 728.36 ms / 137 tokens ( 5.32 ms per token, 188.10 tokens per second) 1.16.789.198 I slot print_timing: id 2 | task 242 | eval time = 63.34 ms / 2 tokens ( 63.34 ms per token, 15.79 tokens per second) 1.16.789.199 I slot print_timing: id 2 | task 242 | total time = 791.69 ms / 139 tokens 1.16.789.200 I slot print_timing: id 2 | task 242 | graphs reused = 1 1.16.789.201 I slot print_timing: id 2 | task 242 | graph reallocs = 31 / 0 (same size) / (changed size) 1.16.789.220 I slot release: id 2 | task 242 | stop processing: n_tokens = 138, truncated = 0 1.16.789.584 I slot print_timing: id 3 | task 239 | prompt eval time = 727.86 ms / 138 tokens ( 5.27 ms per token, 189.60 tokens per second) 1.16.789.591 I slot print_timing: id 3 | task 239 | eval time = 63.03 ms / 2 tokens ( 63.03 ms per token, 15.86 tokens per second) 1.16.789.592 I slot print_timing: id 3 | task 239 | total time = 790.90 ms / 140 tokens 1.16.789.593 I slot print_timing: id 3 | task 239 | graphs reused = 1 1.16.789.594 I slot print_timing: id 3 | task 239 | graph reallocs = 31 / 0 (same size) / (changed size) 1.16.789.610 I slot release: id 3 | task 239 | stop processing: n_tokens = 139, truncated = 0 1.16.798.391 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 1.16.826.481 I slot launch_slot_: id 0 | task 246 | processing task, is_child = 0 1.16.847.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 1.16.871.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 1.16.896.811 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.200 (> 0.100 thold), f_keep = 0.228 1.16.897.086 I slot launch_slot_: id 1 | task 247 | processing task, is_child = 0 1.16.897.168 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.167 (> 0.100 thold), f_keep = 0.203 1.16.897.378 I slot launch_slot_: id 2 | task 248 | processing task, is_child = 0 1.16.897.422 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.233 (> 0.100 thold), f_keep = 0.201 1.16.897.616 I slot launch_slot_: id 3 | task 249 | processing task, is_child = 0 1.17.852.943 I slot print_timing: id 0 | task 246 | prompt eval time = 888.70 ms / 158 tokens ( 5.62 ms per token, 177.79 tokens per second) 1.17.852.949 I slot print_timing: id 0 | task 246 | eval time = 66.61 ms / 2 tokens ( 66.61 ms per token, 15.01 tokens per second) 1.17.852.950 I slot print_timing: id 0 | task 246 | total time = 955.31 ms / 160 tokens 1.17.852.951 I slot print_timing: id 0 | task 246 | graphs reused = 1 1.17.852.953 I slot print_timing: id 0 | task 246 | graph reallocs = 33 / 0 (same size) / (changed size) 1.17.852.980 I slot release: id 0 | task 246 | stop processing: n_tokens = 159, truncated = 0 1.17.853.315 I slot print_timing: id 1 | task 247 | prompt eval time = 887.64 ms / 140 tokens ( 6.34 ms per token, 157.72 tokens per second) 1.17.853.318 I slot print_timing: id 1 | task 247 | eval time = 66.26 ms / 2 tokens ( 66.26 ms per token, 15.09 tokens per second) 1.17.853.318 I slot print_timing: id 1 | task 247 | total time = 953.91 ms / 142 tokens 1.17.853.319 I slot print_timing: id 1 | task 247 | graphs reused = 1 1.17.853.320 I slot print_timing: id 1 | task 247 | graph reallocs = 33 / 0 (same size) / (changed size) 1.17.853.333 I slot release: id 1 | task 247 | stop processing: n_tokens = 141, truncated = 0 1.17.853.709 I slot print_timing: id 2 | task 248 | prompt eval time = 886.72 ms / 168 tokens ( 5.28 ms per token, 189.46 tokens per second) 1.17.853.714 I slot print_timing: id 2 | task 248 | eval time = 65.87 ms / 2 tokens ( 65.87 ms per token, 15.18 tokens per second) 1.17.853.715 I slot print_timing: id 2 | task 248 | total time = 952.59 ms / 170 tokens 1.17.853.716 I slot print_timing: id 2 | task 248 | graphs reused = 1 1.17.853.717 I slot print_timing: id 2 | task 248 | graph reallocs = 33 / 0 (same size) / (changed size) 1.17.853.736 I slot release: id 2 | task 248 | stop processing: n_tokens = 169, truncated = 0 1.17.854.147 I slot print_timing: id 3 | task 249 | prompt eval time = 885.99 ms / 120 tokens ( 7.38 ms per token, 135.44 tokens per second) 1.17.854.152 I slot print_timing: id 3 | task 249 | eval time = 65.65 ms / 2 tokens ( 65.65 ms per token, 15.23 tokens per second) 1.17.854.154 I slot print_timing: id 3 | task 249 | total time = 951.64 ms / 122 tokens 1.17.854.155 I slot print_timing: id 3 | task 249 | graphs reused = 1 1.17.854.156 I slot print_timing: id 3 | task 249 | graph reallocs = 33 / 0 (same size) / (changed size) 1.17.854.175 I slot release: id 3 | task 249 | stop processing: n_tokens = 121, truncated = 0 1.17.863.192 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.272 (> 0.100 thold), f_keep = 0.176 1.17.863.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 1.17.888.724 I slot launch_slot_: id 0 | task 253 | processing task, is_child = 0 1.17.888.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.130 MiB) 1.17.912.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 1.17.915.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 1.17.961.597 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.165 (> 0.100 thold), f_keep = 0.248 1.17.961.833 I slot launch_slot_: id 3 | task 254 | processing task, is_child = 0 1.17.961.896 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.199 1.17.971.973 I slot launch_slot_: id 1 | task 255 | processing task, is_child = 0 1.17.972.030 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.181 (> 0.100 thold), f_keep = 0.166 1.17.972.253 I slot launch_slot_: id 2 | task 256 | processing task, is_child = 0 1.18.958.738 I slot print_timing: id 0 | task 253 | prompt eval time = 920.72 ms / 103 tokens ( 8.94 ms per token, 111.87 tokens per second) 1.18.958.743 I slot print_timing: id 0 | task 253 | eval time = 65.74 ms / 2 tokens ( 65.74 ms per token, 15.21 tokens per second) 1.18.958.744 I slot print_timing: id 0 | task 253 | total time = 986.46 ms / 105 tokens 1.18.958.745 I slot print_timing: id 0 | task 253 | graphs reused = 1 1.18.958.746 I slot print_timing: id 0 | task 253 | graph reallocs = 34 / 0 (same size) / (changed size) 1.18.958.772 I slot release: id 0 | task 253 | stop processing: n_tokens = 104, truncated = 0 1.18.959.073 I slot print_timing: id 1 | task 255 | prompt eval time = 919.54 ms / 133 tokens ( 6.91 ms per token, 144.64 tokens per second) 1.18.959.077 I slot print_timing: id 1 | task 255 | eval time = 65.51 ms / 2 tokens ( 65.51 ms per token, 15.27 tokens per second) 1.18.959.078 I slot print_timing: id 1 | task 255 | total time = 985.05 ms / 135 tokens 1.18.959.078 I slot print_timing: id 1 | task 255 | graphs reused = 1 1.18.959.079 I slot print_timing: id 1 | task 255 | graph reallocs = 34 / 0 (same size) / (changed size) 1.18.959.095 I slot release: id 1 | task 255 | stop processing: n_tokens = 134, truncated = 0 1.18.959.415 I slot print_timing: id 2 | task 256 | prompt eval time = 918.38 ms / 155 tokens ( 5.93 ms per token, 168.77 tokens per second) 1.18.959.420 I slot print_timing: id 2 | task 256 | eval time = 65.26 ms / 2 tokens ( 65.26 ms per token, 15.32 tokens per second) 1.18.959.420 I slot print_timing: id 2 | task 256 | total time = 983.65 ms / 157 tokens 1.18.959.421 I slot print_timing: id 2 | task 256 | graphs reused = 1 1.18.959.422 I slot print_timing: id 2 | task 256 | graph reallocs = 34 / 0 (same size) / (changed size) 1.18.959.438 I slot release: id 2 | task 256 | stop processing: n_tokens = 156, truncated = 0 1.18.959.757 I slot print_timing: id 3 | task 254 | prompt eval time = 917.22 ms / 182 tokens ( 5.04 ms per token, 198.43 tokens per second) 1.18.959.763 I slot print_timing: id 3 | task 254 | eval time = 65.04 ms / 2 tokens ( 65.04 ms per token, 15.37 tokens per second) 1.18.959.763 I slot print_timing: id 3 | task 254 | total time = 982.26 ms / 184 tokens 1.18.959.764 I slot print_timing: id 3 | task 254 | graphs reused = 1 1.18.959.765 I slot print_timing: id 3 | task 254 | graph reallocs = 34 / 0 (same size) / (changed size) 1.18.959.780 I slot release: id 3 | task 254 | stop processing: n_tokens = 183, truncated = 0 1.18.967.993 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.269 1.18.985.135 I slot launch_slot_: id 0 | task 260 | processing task, is_child = 0 1.18.985.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.629 MiB) 1.19.008.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 1.19.011.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.223 MiB) 1.19.035.307 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.317 MiB) 1.19.060.384 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.194 (> 0.100 thold), f_keep = 0.209 1.19.060.655 I slot launch_slot_: id 1 | task 261 | processing task, is_child = 0 1.19.534.530 I slot print_timing: id 0 | task 260 | prompt eval time = 416.78 ms / 124 tokens ( 3.36 ms per token, 297.52 tokens per second) 1.19.534.536 I slot print_timing: id 0 | task 260 | eval time = 56.99 ms / 2 tokens ( 56.99 ms per token, 17.55 tokens per second) 1.19.534.537 I slot print_timing: id 0 | task 260 | total time = 473.77 ms / 126 tokens 1.19.534.538 I slot print_timing: id 0 | task 260 | graphs reused = 1 1.19.534.538 I slot print_timing: id 0 | task 260 | graph reallocs = 35 / 0 (same size) / (changed size) 1.19.534.561 I slot release: id 0 | task 260 | stop processing: n_tokens = 125, truncated = 0 1.19.534.906 I slot print_timing: id 1 | task 261 | prompt eval time = 415.71 ms / 144 tokens ( 2.89 ms per token, 346.39 tokens per second) 1.19.534.911 I slot print_timing: id 1 | task 261 | eval time = 56.67 ms / 2 tokens ( 56.67 ms per token, 17.65 tokens per second) 1.19.534.912 I slot print_timing: id 1 | task 261 | total time = 472.38 ms / 146 tokens 1.19.534.912 I slot print_timing: id 1 | task 261 | graphs reused = 1 1.19.534.913 I slot print_timing: id 1 | task 261 | graph reallocs = 35 / 0 (same size) / (changed size) 1.19.534.926 I slot release: id 1 | task 261 | stop processing: n_tokens = 145, truncated = 0 1.19.559.780 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 156, t_last = 78867060 1.19.560.064 I slot launch_slot_: id 2 | task 265 | processing task, is_child = 0 1.19.560.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 1.19.585.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.068 MiB) 1.19.611.188 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 183, t_last = 78867401 1.19.611.442 I slot launch_slot_: id 3 | task 266 | processing task, is_child = 0 1.19.611.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 125, t_last = 79442182 1.19.611.712 I slot launch_slot_: id 0 | task 267 | processing task, is_child = 0 1.19.611.756 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 145, t_last = 79442548 1.19.611.944 I slot launch_slot_: id 1 | task 268 | processing task, is_child = 0 1.22.874.128 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1125, progress = 0.91, t = 3.26 s / 344.87 tokens per second 1.22.892.155 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1125, progress = 0.91, t = 3.26 s / 345.05 tokens per second 1.22.901.919 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1125, progress = 0.93, t = 3.26 s / 345.24 tokens per second 1.22.912.641 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 1125, progress = 0.91, t = 3.26 s / 345.38 tokens per second 1.23.578.704 I slot print_timing: id 0 | task 267 | prompt processing, n_tokens = 1226, progress = 1.00, t = 3.97 s / 309.07 tokens per second 1.23.597.402 I slot print_timing: id 1 | task 268 | prompt processing, n_tokens = 1239, progress = 1.00, t = 3.96 s / 312.49 tokens per second 1.23.607.699 I slot print_timing: id 2 | task 265 | prompt processing, n_tokens = 1211, progress = 1.00, t = 3.96 s / 305.56 tokens per second 1.23.617.566 I slot print_timing: id 3 | task 266 | prompt processing, n_tokens = 1230, progress = 1.00, t = 3.96 s / 310.46 tokens per second 1.25.649.009 I slot print_timing: id 1 | task 268 | prompt eval time = 4149.77 ms / 1243 tokens ( 3.34 ms per token, 299.54 tokens per second) 1.25.649.015 I slot print_timing: id 1 | task 268 | eval time = 1885.51 ms / 31 tokens ( 62.85 ms per token, 15.91 tokens per second) 1.25.649.016 I slot print_timing: id 1 | task 268 | total time = 6035.27 ms / 1274 tokens 1.25.649.017 I slot print_timing: id 1 | task 268 | graphs reused = 32 1.25.649.018 I slot print_timing: id 1 | task 268 | graph reallocs = 41 / 0 (same size) / (changed size) 1.25.649.074 I slot release: id 1 | task 268 | stop processing: n_tokens = 1273, truncated = 0 1.25.759.685 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 1.25.759.890 I slot launch_slot_: id 1 | task 306 | processing task, is_child = 0 1.28.096.577 I slot print_timing: id 2 | task 265 | prompt eval time = 4148.69 ms / 1215 tokens ( 3.41 ms per token, 292.86 tokens per second) 1.28.096.583 I slot print_timing: id 2 | task 265 | eval time = 4332.40 ms / 63 tokens ( 69.88 ms per token, 14.31 tokens per second) 1.28.096.584 I slot print_timing: id 2 | task 265 | total time = 8481.09 ms / 1278 tokens 1.28.096.585 I slot print_timing: id 2 | task 265 | graphs reused = 59 1.28.096.586 I slot print_timing: id 2 | task 265 | graph reallocs = 45 / 0 (same size) / (changed size) 1.28.096.642 I slot release: id 2 | task 265 | stop processing: n_tokens = 1277, truncated = 0 1.28.203.017 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.897 1.28.203.174 I slot launch_slot_: id 2 | task 339 | processing task, is_child = 0 1.28.912.802 I slot print_timing: id 0 | task 267 | prompt eval time = 4150.89 ms / 1230 tokens ( 3.37 ms per token, 296.32 tokens per second) 1.28.912.809 I slot print_timing: id 0 | task 267 | eval time = 5149.94 ms / 69 tokens ( 75.73 ms per token, 13.20 tokens per second) 1.28.912.810 I slot print_timing: id 0 | task 267 | total time = 9300.83 ms / 1299 tokens 1.28.912.811 I slot print_timing: id 0 | task 267 | graphs reused = 61 1.28.912.812 I slot print_timing: id 0 | task 267 | graph reallocs = 46 / 0 (same size) / (changed size) 1.28.912.876 I slot release: id 0 | task 267 | stop processing: n_tokens = 1298, truncated = 0 1.28.995.783 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.883 1.28.995.936 I slot launch_slot_: id 0 | task 346 | processing task, is_child = 0 1.31.184.462 I slot print_timing: id 3 | task 266 | n_gen = 100, tg = 13.34 t/s, tg_3s = 13.48 t/s 1.31.942.848 I slot print_timing: id 1 | task 306 | prompt eval time = 484.22 ms / 132 tokens ( 3.67 ms per token, 272.60 tokens per second) 1.31.942.854 I slot print_timing: id 1 | task 306 | eval time = 5698.72 ms / 79 tokens ( 73.06 ms per token, 13.69 tokens per second) 1.31.942.855 I slot print_timing: id 1 | task 306 | total time = 6182.93 ms / 211 tokens 1.31.942.856 I slot print_timing: id 1 | task 306 | graphs reused = 101 1.31.942.856 I slot print_timing: id 1 | task 306 | graph reallocs = 48 / 0 (same size) / (changed size) 1.31.942.914 I slot release: id 1 | task 306 | stop processing: n_tokens = 1335, truncated = 0 1.32.053.188 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 1.32.053.341 I slot launch_slot_: id 1 | task 390 | processing task, is_child = 0 1.34.218.416 I slot print_timing: id 3 | task 266 | n_gen = 142, tg = 13.49 t/s, tg_3s = 13.84 t/s 1.35.112.878 I slot print_timing: id 2 | task 339 | prompt eval time = 519.28 ms / 139 tokens ( 3.74 ms per token, 267.68 tokens per second) 1.35.112.884 I slot print_timing: id 2 | task 339 | eval time = 6390.41 ms / 91 tokens ( 71.00 ms per token, 14.08 tokens per second) 1.35.112.886 I slot print_timing: id 2 | task 339 | total time = 6909.68 ms / 230 tokens 1.35.112.888 I slot print_timing: id 2 | task 339 | graphs reused = 141 1.35.112.889 I slot print_timing: id 2 | task 339 | graph reallocs = 51 / 0 (same size) / (changed size) 1.35.112.947 I slot release: id 2 | task 339 | stop processing: n_tokens = 1354, truncated = 0 1.35.223.222 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.846 1.35.223.384 I slot launch_slot_: id 2 | task 435 | processing task, is_child = 0 1.36.142.287 I slot print_timing: id 0 | task 346 | prompt eval time = 397.98 ms / 139 tokens ( 2.86 ms per token, 349.26 tokens per second) 1.36.142.293 I slot print_timing: id 0 | task 346 | eval time = 6748.34 ms / 94 tokens ( 72.56 ms per token, 13.78 tokens per second) 1.36.142.295 I slot print_timing: id 0 | task 346 | total time = 7146.33 ms / 233 tokens 1.36.142.296 I slot print_timing: id 0 | task 346 | graphs reused = 146 1.36.142.297 I slot print_timing: id 0 | task 346 | graph reallocs = 52 / 0 (same size) / (changed size) 1.36.142.371 I slot release: id 0 | task 346 | stop processing: n_tokens = 1357, truncated = 0 1.36.228.499 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.886 (> 0.100 thold), f_keep = 0.845 1.36.228.664 I slot launch_slot_: id 0 | task 445 | processing task, is_child = 0 1.37.267.826 I slot print_timing: id 3 | task 266 | n_gen = 178, tg = 13.11 t/s, tg_3s = 11.81 t/s 1.39.526.334 I slot print_timing: id 1 | task 390 | n_gen = 100, tg = 14.13 t/s, tg_3s = 14.27 t/s 1.40.083.968 I slot print_timing: id 1 | task 390 | prompt eval time = 465.28 ms / 114 tokens ( 4.08 ms per token, 245.01 tokens per second) 1.40.083.975 I slot print_timing: id 1 | task 390 | eval time = 7565.33 ms / 109 tokens ( 70.05 ms per token, 14.28 tokens per second) 1.40.083.976 I slot print_timing: id 1 | task 390 | total time = 8030.61 ms / 223 tokens 1.40.083.977 I slot print_timing: id 1 | task 390 | graphs reused = 201 1.40.083.978 I slot print_timing: id 1 | task 390 | graph reallocs = 54 / 0 (same size) / (changed size) 1.40.084.039 I slot release: id 1 | task 390 | stop processing: n_tokens = 1347, truncated = 0 1.40.190.957 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.851 1.40.191.117 I slot launch_slot_: id 1 | task 504 | processing task, is_child = 0 1.40.465.607 I slot print_timing: id 3 | task 266 | n_gen = 225, tg = 13.41 t/s, tg_3s = 14.70 t/s 1.42.652.091 I slot print_timing: id 2 | task 435 | n_gen = 100, tg = 14.35 t/s, tg_3s = 14.50 t/s 1.43.088.310 I slot print_timing: id 2 | task 435 | prompt eval time = 531.58 ms / 141 tokens ( 3.77 ms per token, 265.25 tokens per second) 1.43.088.317 I slot print_timing: id 2 | task 435 | eval time = 7333.33 ms / 107 tokens ( 69.18 ms per token, 14.45 tokens per second) 1.43.088.318 I slot print_timing: id 2 | task 435 | total time = 7864.91 ms / 248 tokens 1.43.088.319 I slot print_timing: id 2 | task 435 | graphs reused = 239 1.43.088.320 I slot print_timing: id 2 | task 435 | graph reallocs = 57 / 0 (same size) / (changed size) 1.43.088.378 I slot release: id 2 | task 435 | stop processing: n_tokens = 1372, truncated = 0 1.43.194.507 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.835 1.43.194.698 I slot launch_slot_: id 2 | task 547 | processing task, is_child = 0 1.43.481.999 I slot print_timing: id 0 | task 445 | n_gen = 100, tg = 14.46 t/s, tg_3s = 14.61 t/s 1.43.482.543 I slot print_timing: id 3 | task 266 | n_gen = 267, tg = 13.49 t/s, tg_3s = 13.92 t/s 1.45.502.063 I slot print_timing: id 0 | task 445 | prompt eval time = 406.87 ms / 169 tokens ( 2.41 ms per token, 415.37 tokens per second) 1.45.502.070 I slot print_timing: id 0 | task 445 | eval time = 8866.51 ms / 130 tokens ( 68.73 ms per token, 14.55 tokens per second) 1.45.502.071 I slot print_timing: id 0 | task 445 | total time = 9273.38 ms / 299 tokens 1.45.502.072 I slot print_timing: id 0 | task 445 | graphs reused = 267 1.45.502.073 I slot print_timing: id 0 | task 445 | graph reallocs = 58 / 0 (same size) / (changed size) 1.45.502.147 I slot release: id 0 | task 445 | stop processing: n_tokens = 1423, truncated = 0 1.45.584.796 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.805 1.45.584.977 I slot launch_slot_: id 0 | task 580 | processing task, is_child = 0 1.46.305.719 I slot print_timing: id 3 | task 266 | prompt eval time = 4148.00 ms / 1234 tokens ( 3.36 ms per token, 297.49 tokens per second) 1.46.305.725 I slot print_timing: id 3 | task 266 | eval time = 22540.88 ms / 305 tokens ( 74.15 ms per token, 13.49 tokens per second) 1.46.305.727 I slot print_timing: id 3 | task 266 | total time = 26688.88 ms / 1539 tokens 1.46.305.727 I slot print_timing: id 3 | task 266 | graphs reused = 271 1.46.305.728 I slot print_timing: id 3 | task 266 | graph reallocs = 61 / 0 (same size) / (changed size) 1.46.305.782 I slot release: id 3 | task 266 | stop processing: n_tokens = 1538, truncated = 0 1.46.386.025 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.745 1.46.386.184 I slot launch_slot_: id 3 | task 589 | processing task, is_child = 0 1.47.820.775 I slot print_timing: id 1 | task 504 | n_gen = 100, tg = 13.83 t/s, tg_3s = 13.97 t/s 1.47.945.457 I slot print_timing: id 1 | task 504 | prompt eval time = 470.18 ms / 125 tokens ( 3.76 ms per token, 265.86 tokens per second) 1.47.945.463 I slot print_timing: id 1 | task 504 | eval time = 7284.14 ms / 102 tokens ( 72.12 ms per token, 13.87 tokens per second) 1.47.945.464 I slot print_timing: id 1 | task 504 | total time = 7754.32 ms / 227 tokens 1.47.945.466 I slot print_timing: id 1 | task 504 | graphs reused = 289 1.47.945.467 I slot print_timing: id 1 | task 504 | graph reallocs = 62 / 0 (same size) / (changed size) 1.47.945.520 I slot release: id 1 | task 504 | stop processing: n_tokens = 1351, truncated = 0 1.48.054.459 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.848 1.48.054.608 I slot launch_slot_: id 1 | task 612 | processing task, is_child = 0 1.49.645.032 I slot print_timing: id 2 | task 547 | prompt eval time = 501.48 ms / 101 tokens ( 4.97 ms per token, 201.40 tokens per second) 1.49.645.038 I slot print_timing: id 2 | task 547 | eval time = 5948.84 ms / 81 tokens ( 74.36 ms per token, 13.45 tokens per second) 1.49.645.039 I slot print_timing: id 2 | task 547 | total time = 6450.31 ms / 182 tokens 1.49.645.040 I slot print_timing: id 2 | task 547 | graphs reused = 306 1.49.645.041 I slot print_timing: id 2 | task 547 | graph reallocs = 65 / 0 (same size) / (changed size) 1.49.645.097 I slot release: id 2 | task 547 | stop processing: n_tokens = 1306, truncated = 0 1.49.754.215 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.877 1.49.754.412 I slot launch_slot_: id 2 | task 634 | processing task, is_child = 0 1.50.535.123 I slot print_timing: id 0 | task 580 | prompt eval time = 397.36 ms / 101 tokens ( 3.93 ms per token, 254.18 tokens per second) 1.50.535.129 I slot print_timing: id 0 | task 580 | eval time = 4552.77 ms / 56 tokens ( 82.78 ms per token, 12.08 tokens per second) 1.50.535.130 I slot print_timing: id 0 | task 580 | total time = 4950.12 ms / 157 tokens 1.50.535.132 I slot print_timing: id 0 | task 580 | graphs reused = 308 1.50.535.133 I slot print_timing: id 0 | task 580 | graph reallocs = 67 / 0 (same size) / (changed size) 1.50.535.208 I slot release: id 0 | task 580 | stop processing: n_tokens = 1281, truncated = 0 1.50.615.965 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.895 1.50.616.135 I slot launch_slot_: id 0 | task 642 | processing task, is_child = 0 1.53.998.416 I slot print_timing: id 3 | task 589 | prompt eval time = 376.45 ms / 95 tokens ( 3.96 ms per token, 252.36 tokens per second) 1.53.998.422 I slot print_timing: id 3 | task 589 | eval time = 7235.76 ms / 99 tokens ( 73.83 ms per token, 13.54 tokens per second) 1.53.998.424 I slot print_timing: id 3 | task 589 | total time = 7612.21 ms / 194 tokens 1.53.998.424 I slot print_timing: id 3 | task 589 | graphs reused = 356 1.53.998.425 I slot print_timing: id 3 | task 589 | graph reallocs = 69 / 0 (same size) / (changed size) 1.53.998.481 I slot release: id 3 | task 589 | stop processing: n_tokens = 1318, truncated = 0 1.54.082.934 I slot print_timing: id 1 | task 612 | prompt eval time = 469.88 ms / 120 tokens ( 3.92 ms per token, 255.38 tokens per second) 1.54.082.940 I slot print_timing: id 1 | task 612 | eval time = 5558.42 ms / 78 tokens ( 72.19 ms per token, 13.85 tokens per second) 1.54.082.942 I slot print_timing: id 1 | task 612 | total time = 6028.30 ms / 198 tokens 1.54.082.943 I slot print_timing: id 1 | task 612 | graphs reused = 356 1.54.082.943 I slot print_timing: id 1 | task 612 | graph reallocs = 69 / 0 (same size) / (changed size) 1.54.083.004 I slot release: id 1 | task 612 | stop processing: n_tokens = 1322, truncated = 0 1.54.083.319 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.867 1.54.083.467 I slot launch_slot_: id 1 | task 694 | processing task, is_child = 0 1.54.083.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.786 MiB) 1.54.086.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.038 MiB) 1.54.142.526 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.869 1.54.142.738 I slot launch_slot_: id 3 | task 695 | processing task, is_child = 0 1.57.113.889 I slot print_timing: id 0 | task 642 | prompt eval time = 394.48 ms / 86 tokens ( 4.59 ms per token, 218.01 tokens per second) 1.57.113.895 I slot print_timing: id 0 | task 642 | eval time = 6103.25 ms / 88 tokens ( 70.15 ms per token, 14.25 tokens per second) 1.57.113.897 I slot print_timing: id 0 | task 642 | total time = 6497.73 ms / 174 tokens 1.57.113.897 I slot print_timing: id 0 | task 642 | graphs reused = 391 1.57.113.898 I slot print_timing: id 0 | task 642 | graph reallocs = 72 / 0 (same size) / (changed size) 1.57.113.951 I slot release: id 0 | task 642 | stop processing: n_tokens = 1298, truncated = 0 1.57.195.688 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.948 (> 0.100 thold), f_keep = 0.883 1.57.195.859 I slot launch_slot_: id 0 | task 735 | processing task, is_child = 0 1.57.711.070 I slot print_timing: id 2 | task 634 | n_gen = 100, tg = 13.32 t/s, tg_3s = 13.45 t/s 1.59.021.527 I slot print_timing: id 3 | task 695 | prompt eval time = 693.50 ms / 97 tokens ( 7.15 ms per token, 139.87 tokens per second) 1.59.021.532 I slot print_timing: id 3 | task 695 | eval time = 4165.35 ms / 63 tokens ( 67.18 ms per token, 14.88 tokens per second) 1.59.021.534 I slot print_timing: id 3 | task 695 | total time = 4858.86 ms / 160 tokens 1.59.021.535 I slot print_timing: id 3 | task 695 | graphs reused = 414 1.59.021.535 I slot print_timing: id 3 | task 695 | graph reallocs = 74 / 0 (same size) / (changed size) 1.59.021.589 I slot release: id 3 | task 695 | stop processing: n_tokens = 1284, truncated = 0 1.59.102.446 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.893 1.59.102.619 I slot launch_slot_: id 3 | task 762 | processing task, is_child = 0 2.00.717.811 I slot print_timing: id 2 | task 634 | n_gen = 144, tg = 13.70 t/s, tg_3s = 14.63 t/s 2.01.212.814 I slot print_timing: id 2 | task 634 | prompt eval time = 523.08 ms / 148 tokens ( 3.53 ms per token, 282.94 tokens per second) 2.01.212.820 I slot print_timing: id 2 | task 634 | eval time = 10935.30 ms / 152 tokens ( 72.42 ms per token, 13.81 tokens per second) 2.01.212.821 I slot print_timing: id 2 | task 634 | total time = 11458.38 ms / 300 tokens 2.01.212.822 I slot print_timing: id 2 | task 634 | graphs reused = 441 2.01.212.823 I slot print_timing: id 2 | task 634 | graph reallocs = 75 / 0 (same size) / (changed size) 2.01.212.879 I slot release: id 2 | task 634 | stop processing: n_tokens = 1424, truncated = 0 2.01.318.959 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.805 2.01.319.109 I slot launch_slot_: id 2 | task 794 | processing task, is_child = 0 2.02.011.430 I slot print_timing: id 1 | task 694 | n_gen = 100, tg = 13.83 t/s, tg_3s = 13.97 t/s 2.02.137.039 I slot print_timing: id 1 | task 694 | prompt eval time = 712.57 ms / 133 tokens ( 5.36 ms per token, 186.65 tokens per second) 2.02.137.046 I slot print_timing: id 1 | task 694 | eval time = 7281.71 ms / 102 tokens ( 72.10 ms per token, 13.87 tokens per second) 2.02.137.047 I slot print_timing: id 1 | task 694 | total time = 7994.28 ms / 235 tokens 2.02.137.049 I slot print_timing: id 1 | task 694 | graphs reused = 445 2.02.137.049 I slot print_timing: id 1 | task 694 | graph reallocs = 76 / 0 (same size) / (changed size) 2.02.137.119 I slot release: id 1 | task 694 | stop processing: n_tokens = 1359, truncated = 0 2.02.244.365 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.843 2.02.244.525 I slot launch_slot_: id 1 | task 803 | processing task, is_child = 0 2.03.027.733 I slot print_timing: id 0 | task 735 | prompt eval time = 383.31 ms / 84 tokens ( 4.56 ms per token, 219.14 tokens per second) 2.03.027.739 I slot print_timing: id 0 | task 735 | eval time = 5448.54 ms / 71 tokens ( 77.84 ms per token, 12.85 tokens per second) 2.03.027.740 I slot print_timing: id 0 | task 735 | total time = 5831.85 ms / 155 tokens 2.03.027.741 I slot print_timing: id 0 | task 735 | graphs reused = 449 2.03.027.742 I slot print_timing: id 0 | task 735 | graph reallocs = 79 / 0 (same size) / (changed size) 2.03.027.798 I slot release: id 0 | task 735 | stop processing: n_tokens = 1279, truncated = 0 2.03.110.180 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.943 (> 0.100 thold), f_keep = 0.896 2.03.110.401 I slot launch_slot_: id 0 | task 812 | processing task, is_child = 0 2.04.933.563 I slot print_timing: id 3 | task 762 | prompt eval time = 371.48 ms / 101 tokens ( 3.68 ms per token, 271.88 tokens per second) 2.04.933.569 I slot print_timing: id 3 | task 762 | eval time = 5459.44 ms / 71 tokens ( 77.99 ms per token, 12.82 tokens per second) 2.04.933.570 I slot print_timing: id 3 | task 762 | total time = 5830.93 ms / 172 tokens 2.04.933.571 I slot print_timing: id 3 | task 762 | graphs reused = 471 2.04.933.572 I slot print_timing: id 3 | task 762 | graph reallocs = 82 / 0 (same size) / (changed size) 2.04.933.629 I slot release: id 3 | task 762 | stop processing: n_tokens = 1296, truncated = 0 2.05.016.210 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.884 2.05.016.376 I slot launch_slot_: id 3 | task 839 | processing task, is_child = 0 2.06.267.469 I slot print_timing: id 2 | task 794 | prompt eval time = 500.75 ms / 95 tokens ( 5.27 ms per token, 189.72 tokens per second) 2.06.267.476 I slot print_timing: id 2 | task 794 | eval time = 4447.59 ms / 57 tokens ( 79.42 ms per token, 12.59 tokens per second) 2.06.267.477 I slot print_timing: id 2 | task 794 | total time = 4948.34 ms / 152 tokens 2.06.267.477 I slot print_timing: id 2 | task 794 | graphs reused = 484 2.06.267.478 I slot print_timing: id 2 | task 794 | graph reallocs = 83 / 0 (same size) / (changed size) 2.06.267.534 I slot release: id 2 | task 794 | stop processing: n_tokens = 1276, truncated = 0 2.06.374.098 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.898 2.06.374.253 I slot launch_slot_: id 2 | task 857 | processing task, is_child = 0 2.09.856.406 I slot print_timing: id 1 | task 803 | n_gen = 100, tg = 13.85 t/s, tg_3s = 13.99 t/s 2.10.291.892 I slot print_timing: id 0 | task 812 | prompt eval time = 385.38 ms / 90 tokens ( 4.28 ms per token, 233.54 tokens per second) 2.10.291.898 I slot print_timing: id 0 | task 812 | eval time = 6796.09 ms / 99 tokens ( 69.35 ms per token, 14.42 tokens per second) 2.10.291.899 I slot print_timing: id 0 | task 812 | total time = 7181.47 ms / 189 tokens 2.10.291.901 I slot print_timing: id 0 | task 812 | graphs reused = 538 2.10.291.902 I slot print_timing: id 0 | task 812 | graph reallocs = 84 / 0 (same size) / (changed size) 2.10.291.975 I slot release: id 0 | task 812 | stop processing: n_tokens = 1313, truncated = 0 2.10.375.376 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.874 2.10.375.545 I slot launch_slot_: id 0 | task 916 | processing task, is_child = 0 2.11.207.528 I slot print_timing: id 3 | task 839 | prompt eval time = 374.60 ms / 96 tokens ( 3.90 ms per token, 256.27 tokens per second) 2.11.207.535 I slot print_timing: id 3 | task 839 | eval time = 5816.53 ms / 83 tokens ( 70.93 ms per token, 14.10 tokens per second) 2.11.207.536 I slot print_timing: id 3 | task 839 | total time = 6191.13 ms / 179 tokens 2.11.207.537 I slot print_timing: id 3 | task 839 | graphs reused = 545 2.11.207.538 I slot print_timing: id 3 | task 839 | graph reallocs = 86 / 0 (same size) / (changed size) 2.11.207.596 I slot release: id 3 | task 839 | stop processing: n_tokens = 1303, truncated = 0 2.11.287.695 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.880 2.11.287.872 I slot launch_slot_: id 3 | task 927 | processing task, is_child = 0 2.12.610.093 I slot print_timing: id 1 | task 803 | prompt eval time = 464.49 ms / 130 tokens ( 3.57 ms per token, 279.88 tokens per second) 2.12.610.100 I slot print_timing: id 1 | task 803 | eval time = 9901.06 ms / 135 tokens ( 73.89 ms per token, 13.53 tokens per second) 2.12.610.101 I slot print_timing: id 1 | task 803 | total time = 10365.55 ms / 265 tokens 2.12.610.102 I slot print_timing: id 1 | task 803 | graphs reused = 559 2.12.610.102 I slot print_timing: id 1 | task 803 | graph reallocs = 87 / 0 (same size) / (changed size) 2.12.610.157 I slot release: id 1 | task 803 | stop processing: n_tokens = 1389, truncated = 0 2.12.717.070 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.825 2.12.717.228 I slot launch_slot_: id 1 | task 946 | processing task, is_child = 0 2.13.520.056 I slot print_timing: id 2 | task 857 | prompt eval time = 501.47 ms / 87 tokens ( 5.76 ms per token, 173.49 tokens per second) 2.13.520.062 I slot print_timing: id 2 | task 857 | eval time = 6644.31 ms / 92 tokens ( 73.01 ms per token, 13.70 tokens per second) 2.13.520.063 I slot print_timing: id 2 | task 857 | total time = 7145.78 ms / 179 tokens 2.13.520.064 I slot print_timing: id 2 | task 857 | graphs reused = 563 2.13.520.064 I slot print_timing: id 2 | task 857 | graph reallocs = 90 / 0 (same size) / (changed size) 2.13.520.123 I slot release: id 2 | task 857 | stop processing: n_tokens = 1303, truncated = 0 2.13.632.049 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.941 (> 0.100 thold), f_keep = 0.880 2.13.632.228 I slot launch_slot_: id 2 | task 955 | processing task, is_child = 0 2.18.136.294 I slot print_timing: id 0 | task 916 | n_gen = 100, tg = 13.43 t/s, tg_3s = 13.57 t/s 2.18.328.958 I slot print_timing: id 2 | task 955 | prompt eval time = 523.24 ms / 93 tokens ( 5.63 ms per token, 177.74 tokens per second) 2.18.328.964 I slot print_timing: id 2 | task 955 | eval time = 4173.47 ms / 67 tokens ( 63.23 ms per token, 15.81 tokens per second) 2.18.328.965 I slot print_timing: id 2 | task 955 | total time = 4696.71 ms / 160 tokens 2.18.328.966 I slot print_timing: id 2 | task 955 | graphs reused = 628 2.18.328.967 I slot print_timing: id 2 | task 955 | graph reallocs = 91 / 0 (same size) / (changed size) 2.18.329.025 I slot release: id 2 | task 955 | stop processing: n_tokens = 1284, truncated = 0 2.18.438.809 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.893 2.18.438.980 I slot launch_slot_: id 2 | task 1025 | processing task, is_child = 0 2.19.231.873 I slot print_timing: id 3 | task 927 | n_gen = 100, tg = 13.10 t/s, tg_3s = 13.23 t/s 2.20.360.247 I slot print_timing: id 1 | task 946 | n_gen = 100, tg = 13.81 t/s, tg_3s = 13.95 t/s 2.21.173.540 I slot print_timing: id 0 | task 916 | n_gen = 141, tg = 13.45 t/s, tg_3s = 13.50 t/s 2.22.256.298 I slot print_timing: id 3 | task 927 | n_gen = 148, tg = 13.89 t/s, tg_3s = 15.87 t/s 2.22.637.124 I slot print_timing: id 2 | task 1025 | prompt eval time = 531.07 ms / 87 tokens ( 6.10 ms per token, 163.82 tokens per second) 2.22.637.130 I slot print_timing: id 2 | task 1025 | eval time = 3667.05 ms / 59 tokens ( 63.23 ms per token, 15.82 tokens per second) 2.22.637.132 I slot print_timing: id 2 | task 1025 | total time = 4198.12 ms / 146 tokens 2.22.637.132 I slot print_timing: id 2 | task 1025 | graphs reused = 685 2.22.637.133 I slot print_timing: id 2 | task 1025 | graph reallocs = 92 / 0 (same size) / (changed size) 2.22.637.187 I slot release: id 2 | task 1025 | stop processing: n_tokens = 1270, truncated = 0 2.22.748.469 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.902 2.22.748.621 I slot launch_slot_: id 2 | task 1087 | processing task, is_child = 0 2.23.399.331 I slot print_timing: id 1 | task 946 | n_gen = 141, tg = 13.72 t/s, tg_3s = 13.49 t/s 2.23.716.271 I slot print_timing: id 0 | task 916 | prompt eval time = 390.38 ms / 131 tokens ( 2.98 ms per token, 335.57 tokens per second) 2.23.716.278 I slot print_timing: id 0 | task 916 | eval time = 12950.33 ms / 174 tokens ( 74.86 ms per token, 13.36 tokens per second) 2.23.716.279 I slot print_timing: id 0 | task 916 | total time = 13340.70 ms / 305 tokens 2.23.716.279 I slot print_timing: id 0 | task 916 | graphs reused = 691 2.23.716.280 I slot print_timing: id 0 | task 916 | graph reallocs = 93 / 0 (same size) / (changed size) 2.23.716.334 I slot release: id 0 | task 916 | stop processing: n_tokens = 1429, truncated = 0 2.23.804.569 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.802 2.23.804.736 I slot launch_slot_: id 0 | task 1098 | processing task, is_child = 0 2.25.263.622 I slot print_timing: id 3 | task 927 | n_gen = 184, tg = 13.47 t/s, tg_3s = 11.97 t/s 2.26.408.143 I slot print_timing: id 1 | task 946 | n_gen = 184, tg = 13.85 t/s, tg_3s = 14.29 t/s 2.26.597.897 I slot print_timing: id 2 | task 1087 | prompt eval time = 519.83 ms / 98 tokens ( 5.30 ms per token, 188.52 tokens per second) 2.26.597.903 I slot print_timing: id 2 | task 1087 | eval time = 3329.43 ms / 49 tokens ( 69.36 ms per token, 14.42 tokens per second) 2.26.597.904 I slot print_timing: id 2 | task 1087 | total time = 3849.26 ms / 147 tokens 2.26.597.904 I slot print_timing: id 2 | task 1087 | graphs reused = 729 2.26.597.905 I slot print_timing: id 2 | task 1087 | graph reallocs = 95 / 0 (same size) / (changed size) 2.26.597.963 I slot release: id 2 | task 1087 | stop processing: n_tokens = 1271, truncated = 0 2.26.707.638 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 2.26.707.801 I slot launch_slot_: id 2 | task 1140 | processing task, is_child = 0 2.27.230.935 I slot print_timing: id 1 | task 946 | prompt eval time = 474.50 ms / 153 tokens ( 3.10 ms per token, 322.45 tokens per second) 2.27.230.942 I slot print_timing: id 1 | task 946 | eval time = 14039.19 ms / 190 tokens ( 74.28 ms per token, 13.46 tokens per second) 2.27.230.943 I slot print_timing: id 1 | task 946 | total time = 14513.68 ms / 343 tokens 2.27.230.944 I slot print_timing: id 1 | task 946 | graphs reused = 729 2.27.230.945 I slot print_timing: id 1 | task 946 | graph reallocs = 95 / 0 (same size) / (changed size) 2.27.231.011 I slot release: id 1 | task 946 | stop processing: n_tokens = 1467, truncated = 0 2.27.341.066 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.781 2.27.341.219 I slot launch_slot_: id 1 | task 1144 | processing task, is_child = 0 2.28.269.558 I slot print_timing: id 3 | task 927 | n_gen = 218, tg = 13.08 t/s, tg_3s = 11.31 t/s 2.31.298.350 I slot print_timing: id 0 | task 1098 | n_gen = 100, tg = 13.94 t/s, tg_3s = 14.08 t/s 2.31.299.254 I slot print_timing: id 3 | task 927 | n_gen = 266, tg = 13.50 t/s, tg_3s = 15.84 t/s 2.32.372.693 I slot print_timing: id 0 | task 1098 | prompt eval time = 390.65 ms / 105 tokens ( 3.72 ms per token, 268.78 tokens per second) 2.32.372.698 I slot print_timing: id 0 | task 1098 | eval time = 8177.28 ms / 117 tokens ( 70.49 ms per token, 14.19 tokens per second) 2.32.372.699 I slot print_timing: id 0 | task 1098 | total time = 8567.93 ms / 222 tokens 2.32.372.701 I slot print_timing: id 0 | task 1098 | graphs reused = 799 2.32.372.702 I slot print_timing: id 0 | task 1098 | graph reallocs = 99 / 0 (same size) / (changed size) 2.32.372.758 I slot release: id 0 | task 1098 | stop processing: n_tokens = 1346, truncated = 0 2.32.455.133 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.851 2.32.455.329 I slot launch_slot_: id 0 | task 1220 | processing task, is_child = 0 2.32.973.379 I slot print_timing: id 1 | task 1144 | prompt eval time = 486.03 ms / 122 tokens ( 3.98 ms per token, 251.01 tokens per second) 2.32.973.385 I slot print_timing: id 1 | task 1144 | eval time = 5146.11 ms / 78 tokens ( 66.83 ms per token, 14.96 tokens per second) 2.32.973.386 I slot print_timing: id 1 | task 1144 | total time = 5632.14 ms / 200 tokens 2.32.973.388 I slot print_timing: id 1 | task 1144 | graphs reused = 801 2.32.973.388 I slot print_timing: id 1 | task 1144 | graph reallocs = 101 / 0 (same size) / (changed size) 2.32.973.442 I slot release: id 1 | task 1144 | stop processing: n_tokens = 1324, truncated = 0 2.33.081.632 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.866 2.33.081.795 I slot launch_slot_: id 1 | task 1226 | processing task, is_child = 0 2.34.323.541 I slot print_timing: id 3 | task 927 | n_gen = 303, tg = 13.33 t/s, tg_3s = 12.23 t/s 2.34.579.627 I slot print_timing: id 2 | task 1140 | n_gen = 100, tg = 13.47 t/s, tg_3s = 13.61 t/s 2.36.876.882 I slot print_timing: id 2 | task 1140 | prompt eval time = 523.84 ms / 113 tokens ( 4.64 ms per token, 215.72 tokens per second) 2.36.876.889 I slot print_timing: id 2 | task 1140 | eval time = 9645.22 ms / 136 tokens ( 71.45 ms per token, 14.00 tokens per second) 2.36.876.890 I slot print_timing: id 2 | task 1140 | total time = 10169.06 ms / 249 tokens 2.36.876.891 I slot print_timing: id 2 | task 1140 | graphs reused = 852 2.36.876.892 I slot print_timing: id 2 | task 1140 | graph reallocs = 104 / 0 (same size) / (changed size) 2.36.876.961 I slot release: id 2 | task 1140 | stop processing: n_tokens = 1373, truncated = 0 2.36.987.560 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.835 2.36.987.713 I slot launch_slot_: id 2 | task 1282 | processing task, is_child = 0 2.37.532.334 I slot print_timing: id 3 | task 927 | n_gen = 346, tg = 13.34 t/s, tg_3s = 13.40 t/s 2.37.799.568 I slot print_timing: id 3 | task 927 | prompt eval time = 386.64 ms / 137 tokens ( 2.82 ms per token, 354.33 tokens per second) 2.37.799.575 I slot print_timing: id 3 | task 927 | eval time = 26125.04 ms / 350 tokens ( 74.86 ms per token, 13.36 tokens per second) 2.37.799.576 I slot print_timing: id 3 | task 927 | total time = 26511.68 ms / 487 tokens 2.37.799.577 I slot print_timing: id 3 | task 927 | graphs reused = 855 2.37.799.577 I slot print_timing: id 3 | task 927 | graph reallocs = 105 / 0 (same size) / (changed size) 2.37.799.635 I slot release: id 3 | task 927 | stop processing: n_tokens = 1611, truncated = 0 2.37.886.624 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.711 2.37.886.854 I slot launch_slot_: id 3 | task 1290 | processing task, is_child = 0 2.39.202.832 I slot print_timing: id 0 | task 1220 | prompt eval time = 387.78 ms / 96 tokens ( 4.04 ms per token, 247.56 tokens per second) 2.39.202.839 I slot print_timing: id 0 | task 1220 | eval time = 6359.70 ms / 82 tokens ( 78.51 ms per token, 12.74 tokens per second) 2.39.202.840 I slot print_timing: id 0 | task 1220 | total time = 6747.48 ms / 178 tokens 2.39.202.841 I slot print_timing: id 0 | task 1220 | graphs reused = 868 2.39.202.842 I slot print_timing: id 0 | task 1220 | graph reallocs = 106 / 0 (same size) / (changed size) 2.39.202.898 I slot release: id 0 | task 1220 | stop processing: n_tokens = 1302, truncated = 0 2.39.296.570 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.880 2.39.296.791 I slot launch_slot_: id 0 | task 1308 | processing task, is_child = 0 2.40.985.730 I slot print_timing: id 1 | task 1226 | n_gen = 100, tg = 13.32 t/s, tg_3s = 13.46 t/s 2.41.360.105 I slot print_timing: id 1 | task 1226 | prompt eval time = 473.87 ms / 113 tokens ( 4.19 ms per token, 238.46 tokens per second) 2.41.360.114 I slot print_timing: id 1 | task 1226 | eval time = 7804.42 ms / 106 tokens ( 74.33 ms per token, 13.45 tokens per second) 2.41.360.115 I slot print_timing: id 1 | task 1226 | total time = 8278.29 ms / 219 tokens 2.41.360.116 I slot print_timing: id 1 | task 1226 | graphs reused = 894 2.41.360.116 I slot print_timing: id 1 | task 1226 | graph reallocs = 108 / 0 (same size) / (changed size) 2.41.360.172 I slot release: id 1 | task 1226 | stop processing: n_tokens = 1343, truncated = 0 2.41.468.607 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.853 2.41.468.763 I slot launch_slot_: id 1 | task 1338 | processing task, is_child = 0 2.44.868.712 I slot print_timing: id 2 | task 1282 | n_gen = 100, tg = 13.49 t/s, tg_3s = 13.63 t/s 2.45.319.079 I slot print_timing: id 3 | task 1290 | n_gen = 100, tg = 14.08 t/s, tg_3s = 14.22 t/s 2.46.416.788 I slot print_timing: id 0 | task 1308 | n_gen = 100, tg = 14.77 t/s, tg_3s = 14.92 t/s 2.46.742.315 I slot print_timing: id 0 | task 1308 | prompt eval time = 415.98 ms / 117 tokens ( 3.56 ms per token, 281.26 tokens per second) 2.46.742.322 I slot print_timing: id 0 | task 1308 | eval time = 7029.52 ms / 105 tokens ( 67.59 ms per token, 14.79 tokens per second) 2.46.742.323 I slot print_timing: id 0 | task 1308 | total time = 7445.50 ms / 222 tokens 2.46.742.324 I slot print_timing: id 0 | task 1308 | graphs reused = 968 2.46.742.325 I slot print_timing: id 0 | task 1308 | graph reallocs = 111 / 0 (same size) / (changed size) 2.46.742.387 I slot release: id 0 | task 1308 | stop processing: n_tokens = 1346, truncated = 0 2.46.828.308 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.851 2.46.828.499 I slot launch_slot_: id 0 | task 1417 | processing task, is_child = 0 2.47.880.506 I slot print_timing: id 2 | task 1282 | n_gen = 142, tg = 13.63 t/s, tg_3s = 13.95 t/s 2.48.134.107 I slot print_timing: id 3 | task 1290 | prompt eval time = 400.77 ms / 131 tokens ( 3.06 ms per token, 326.87 tokens per second) 2.48.134.113 I slot print_timing: id 3 | task 1290 | eval time = 9846.46 ms / 139 tokens ( 71.35 ms per token, 14.02 tokens per second) 2.48.134.114 I slot print_timing: id 3 | task 1290 | total time = 10247.23 ms / 270 tokens 2.48.134.115 I slot print_timing: id 3 | task 1290 | graphs reused = 982 2.48.134.116 I slot print_timing: id 3 | task 1290 | graph reallocs = 113 / 0 (same size) / (changed size) 2.48.134.173 I slot release: id 3 | task 1290 | stop processing: n_tokens = 1394, truncated = 0 2.48.217.905 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.822 2.48.218.129 I slot launch_slot_: id 3 | task 1435 | processing task, is_child = 0 2.48.850.796 I slot print_timing: id 1 | task 1338 | n_gen = 100, tg = 14.34 t/s, tg_3s = 14.49 t/s 2.49.469.543 I slot print_timing: id 1 | task 1338 | prompt eval time = 478.74 ms / 127 tokens ( 3.77 ms per token, 265.28 tokens per second) 2.49.469.549 I slot print_timing: id 1 | task 1338 | eval time = 7522.02 ms / 110 tokens ( 69.01 ms per token, 14.49 tokens per second) 2.49.469.550 I slot print_timing: id 1 | task 1338 | total time = 8000.76 ms / 237 tokens 2.49.469.551 I slot print_timing: id 1 | task 1338 | graphs reused = 995 2.49.469.551 I slot print_timing: id 1 | task 1338 | graph reallocs = 114 / 0 (same size) / (changed size) 2.49.469.607 I slot release: id 1 | task 1338 | stop processing: n_tokens = 1361, truncated = 0 2.49.579.451 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.842 2.49.579.611 I slot launch_slot_: id 1 | task 1453 | processing task, is_child = 0 2.50.898.393 I slot print_timing: id 2 | task 1282 | n_gen = 179, tg = 13.32 t/s, tg_3s = 12.26 t/s 2.53.920.960 I slot print_timing: id 2 | task 1282 | n_gen = 227, tg = 13.79 t/s, tg_3s = 15.88 t/s 2.54.173.491 I slot print_timing: id 0 | task 1417 | n_gen = 100, tg = 14.27 t/s, tg_3s = 14.42 t/s 2.54.173.804 I slot print_timing: id 1 | task 1453 | prompt eval time = 486.82 ms / 104 tokens ( 4.68 ms per token, 213.63 tokens per second) 2.54.173.809 I slot print_timing: id 1 | task 1453 | eval time = 4107.36 ms / 66 tokens ( 63.19 ms per token, 15.83 tokens per second) 2.54.173.810 I slot print_timing: id 1 | task 1453 | total time = 4594.18 ms / 170 tokens 2.54.173.812 I slot print_timing: id 1 | task 1453 | graphs reused = 1059 2.54.173.814 I slot print_timing: id 1 | task 1453 | graph reallocs = 117 / 0 (same size) / (changed size) 2.54.173.884 I slot release: id 1 | task 1453 | stop processing: n_tokens = 1294, truncated = 0 2.54.284.943 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.886 2.54.285.103 I slot launch_slot_: id 1 | task 1522 | processing task, is_child = 0 2.55.026.536 I slot print_timing: id 3 | task 1435 | prompt eval time = 378.21 ms / 96 tokens ( 3.94 ms per token, 253.83 tokens per second) 2.55.026.543 I slot print_timing: id 3 | task 1435 | eval time = 6430.18 ms / 90 tokens ( 72.25 ms per token, 13.84 tokens per second) 2.55.026.544 I slot print_timing: id 3 | task 1435 | total time = 6808.38 ms / 186 tokens 2.55.026.544 I slot print_timing: id 3 | task 1435 | graphs reused = 1062 2.55.026.545 I slot print_timing: id 3 | task 1435 | graph reallocs = 120 / 0 (same size) / (changed size) 2.55.026.603 I slot release: id 3 | task 1435 | stop processing: n_tokens = 1310, truncated = 0 2.55.111.248 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.934 (> 0.100 thold), f_keep = 0.875 2.55.111.433 I slot launch_slot_: id 3 | task 1530 | processing task, is_child = 0 2.56.958.547 I slot print_timing: id 2 | task 1282 | n_gen = 264, tg = 13.54 t/s, tg_3s = 12.18 t/s 2.57.209.818 I slot print_timing: id 0 | task 1417 | n_gen = 137, tg = 13.64 t/s, tg_3s = 12.19 t/s 2.58.277.518 I slot print_timing: id 0 | task 1417 | prompt eval time = 409.71 ms / 137 tokens ( 2.99 ms per token, 334.38 tokens per second) 2.58.277.524 I slot print_timing: id 0 | task 1417 | eval time = 11039.28 ms / 154 tokens ( 72.15 ms per token, 13.86 tokens per second) 2.58.277.525 I slot print_timing: id 0 | task 1417 | total time = 11449.00 ms / 291 tokens 2.58.277.525 I slot print_timing: id 0 | task 1417 | graphs reused = 1104 2.58.277.527 I slot print_timing: id 0 | task 1417 | graph reallocs = 122 / 0 (same size) / (changed size) 2.58.277.583 I slot release: id 0 | task 1417 | stop processing: n_tokens = 1415, truncated = 0 2.58.362.399 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.810 2.58.362.567 I slot launch_slot_: id 0 | task 1578 | processing task, is_child = 0 2.59.283.459 I slot print_timing: id 1 | task 1522 | prompt eval time = 481.37 ms / 98 tokens ( 4.91 ms per token, 203.58 tokens per second) 2.59.283.464 I slot print_timing: id 1 | task 1522 | eval time = 4516.96 ms / 63 tokens ( 72.85 ms per token, 13.73 tokens per second) 2.59.283.466 I slot print_timing: id 1 | task 1522 | total time = 4998.34 ms / 161 tokens 2.59.283.466 I slot print_timing: id 1 | task 1522 | graphs reused = 1112 2.59.283.467 I slot print_timing: id 1 | task 1522 | graph reallocs = 124 / 0 (same size) / (changed size) 2.59.283.525 I slot release: id 1 | task 1522 | stop processing: n_tokens = 1285, truncated = 0 2.59.393.000 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.892 2.59.393.203 I slot launch_slot_: id 1 | task 1590 | processing task, is_child = 0 3.00.009.816 I slot print_timing: id 2 | task 1282 | n_gen = 301, tg = 13.35 t/s, tg_3s = 12.13 t/s 3.00.265.193 I slot print_timing: id 3 | task 1530 | prompt eval time = 380.93 ms / 102 tokens ( 3.73 ms per token, 267.76 tokens per second) 3.00.265.200 I slot print_timing: id 3 | task 1530 | eval time = 4772.81 ms / 65 tokens ( 74.58 ms per token, 13.41 tokens per second) 3.00.265.201 I slot print_timing: id 3 | task 1530 | total time = 5153.74 ms / 167 tokens 3.00.265.202 I slot print_timing: id 3 | task 1530 | graphs reused = 1117 3.00.265.203 I slot print_timing: id 3 | task 1530 | graph reallocs = 127 / 0 (same size) / (changed size) 3.00.265.269 I slot release: id 3 | task 1530 | stop processing: n_tokens = 1291, truncated = 0 3.00.347.575 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.888 3.00.347.738 I slot launch_slot_: id 3 | task 1600 | processing task, is_child = 0 3.03.065.464 I slot print_timing: id 2 | task 1282 | n_gen = 345, tg = 13.47 t/s, tg_3s = 14.40 t/s 3.05.712.912 I slot print_timing: id 0 | task 1578 | n_gen = 100, tg = 14.25 t/s, tg_3s = 14.39 t/s 3.06.025.067 I slot print_timing: id 0 | task 1578 | prompt eval time = 402.83 ms / 108 tokens ( 3.73 ms per token, 268.10 tokens per second) 3.06.025.073 I slot print_timing: id 0 | task 1578 | eval time = 7259.65 ms / 105 tokens ( 69.80 ms per token, 14.33 tokens per second) 3.06.025.074 I slot print_timing: id 0 | task 1578 | total time = 7662.48 ms / 213 tokens 3.06.025.075 I slot print_timing: id 0 | task 1578 | graphs reused = 1200 3.06.025.076 I slot print_timing: id 0 | task 1578 | graph reallocs = 128 / 0 (same size) / (changed size) 3.06.025.133 I slot release: id 0 | task 1578 | stop processing: n_tokens = 1337, truncated = 0 3.06.108.275 I slot print_timing: id 2 | task 1282 | n_gen = 393, tg = 13.72 t/s, tg_3s = 15.77 t/s 3.06.108.612 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.857 3.06.108.822 I slot launch_slot_: id 0 | task 1688 | processing task, is_child = 0 3.06.360.242 I slot print_timing: id 1 | task 1590 | prompt eval time = 483.34 ms / 122 tokens ( 3.96 ms per token, 252.41 tokens per second) 3.06.360.249 I slot print_timing: id 1 | task 1590 | eval time = 6483.67 ms / 96 tokens ( 68.25 ms per token, 14.65 tokens per second) 3.06.360.250 I slot print_timing: id 1 | task 1590 | total time = 6967.02 ms / 218 tokens 3.06.360.251 I slot print_timing: id 1 | task 1590 | graphs reused = 1201 3.06.360.253 I slot print_timing: id 1 | task 1590 | graph reallocs = 128 / 0 (same size) / (changed size) 3.06.360.323 I slot release: id 1 | task 1590 | stop processing: n_tokens = 1342, truncated = 0 3.06.490.982 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.854 3.06.491.189 I slot launch_slot_: id 1 | task 1691 | processing task, is_child = 0 3.07.623.156 I slot print_timing: id 3 | task 1600 | n_gen = 100, tg = 14.37 t/s, tg_3s = 14.52 t/s 3.08.573.084 I slot print_timing: id 3 | task 1600 | prompt eval time = 386.19 ms / 124 tokens ( 3.11 ms per token, 321.08 tokens per second) 3.08.573.091 I slot print_timing: id 3 | task 1600 | eval time = 7839.13 ms / 115 tokens ( 68.76 ms per token, 14.54 tokens per second) 3.08.573.092 I slot print_timing: id 3 | task 1600 | total time = 8225.33 ms / 239 tokens 3.08.573.093 I slot print_timing: id 3 | task 1600 | graphs reused = 1225 3.08.573.094 I slot print_timing: id 3 | task 1600 | graph reallocs = 134 / 0 (same size) / (changed size) 3.08.573.163 I slot release: id 3 | task 1600 | stop processing: n_tokens = 1363, truncated = 0 3.08.658.365 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.931 (> 0.100 thold), f_keep = 0.841 3.08.658.540 I slot launch_slot_: id 3 | task 1720 | processing task, is_child = 0 3.09.164.180 I slot print_timing: id 2 | task 1282 | n_gen = 427, tg = 13.47 t/s, tg_3s = 11.13 t/s 3.10.657.582 I slot print_timing: id 1 | task 1691 | prompt eval time = 487.90 ms / 86 tokens ( 5.67 ms per token, 176.26 tokens per second) 3.10.657.588 I slot print_timing: id 1 | task 1691 | eval time = 3678.47 ms / 55 tokens ( 68.12 ms per token, 14.68 tokens per second) 3.10.657.589 I slot print_timing: id 1 | task 1691 | total time = 4166.37 ms / 141 tokens 3.10.657.590 I slot print_timing: id 1 | task 1691 | graphs reused = 1250 3.10.657.590 I slot print_timing: id 1 | task 1691 | graph reallocs = 135 / 0 (same size) / (changed size) 3.10.657.645 I slot release: id 1 | task 1691 | stop processing: n_tokens = 1265, truncated = 0 3.10.764.457 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.906 3.10.764.613 I slot launch_slot_: id 1 | task 1750 | processing task, is_child = 0 3.11.420.217 I slot print_timing: id 2 | task 1282 | prompt eval time = 544.33 ms / 149 tokens ( 3.65 ms per token, 273.73 tokens per second) 3.11.420.223 I slot print_timing: id 2 | task 1282 | eval time = 33888.15 ms / 457 tokens ( 74.32 ms per token, 13.46 tokens per second) 3.11.420.224 I slot print_timing: id 2 | task 1282 | total time = 34432.48 ms / 606 tokens 3.11.420.225 I slot print_timing: id 2 | task 1282 | graphs reused = 1252 3.11.420.226 I slot print_timing: id 2 | task 1282 | graph reallocs = 138 / 0 (same size) / (changed size) 3.11.420.283 I slot release: id 2 | task 1282 | stop processing: n_tokens = 1730, truncated = 0 3.11.526.828 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.662 3.11.526.994 I slot launch_slot_: id 2 | task 1757 | processing task, is_child = 0 3.14.142.049 I slot print_timing: id 0 | task 1688 | n_gen = 100, tg = 12.94 t/s, tg_3s = 13.07 t/s 3.15.692.132 I slot print_timing: id 0 | task 1688 | prompt eval time = 381.36 ms / 111 tokens ( 3.44 ms per token, 291.06 tokens per second) 3.15.692.138 I slot print_timing: id 0 | task 1688 | eval time = 9201.93 ms / 125 tokens ( 74.21 ms per token, 13.48 tokens per second) 3.15.692.139 I slot print_timing: id 0 | task 1688 | total time = 9583.29 ms / 236 tokens 3.15.692.140 I slot print_timing: id 0 | task 1688 | graphs reused = 1310 3.15.692.141 I slot print_timing: id 0 | task 1688 | graph reallocs = 139 / 0 (same size) / (changed size) 3.15.692.197 I slot release: id 0 | task 1688 | stop processing: n_tokens = 1360, truncated = 0 3.15.773.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.843 3.15.773.371 I slot launch_slot_: id 0 | task 1820 | processing task, is_child = 0 3.16.299.313 I slot print_timing: id 3 | task 1720 | n_gen = 100, tg = 13.62 t/s, tg_3s = 13.76 t/s 3.17.109.260 I slot print_timing: id 3 | task 1720 | prompt eval time = 374.19 ms / 106 tokens ( 3.53 ms per token, 283.27 tokens per second) 3.17.109.267 I slot print_timing: id 3 | task 1720 | eval time = 8076.51 ms / 113 tokens ( 72.11 ms per token, 13.87 tokens per second) 3.17.109.268 I slot print_timing: id 3 | task 1720 | total time = 8450.70 ms / 219 tokens 3.17.109.270 I slot print_timing: id 3 | task 1720 | graphs reused = 1325 3.17.109.271 I slot print_timing: id 3 | task 1720 | graph reallocs = 141 / 0 (same size) / (changed size) 3.17.109.324 I slot release: id 3 | task 1720 | stop processing: n_tokens = 1343, truncated = 0 3.17.190.697 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.853 3.17.190.865 I slot launch_slot_: id 3 | task 1839 | processing task, is_child = 0 3.18.374.293 I slot print_timing: id 1 | task 1750 | n_gen = 100, tg = 13.85 t/s, tg_3s = 13.99 t/s 3.18.746.745 I slot print_timing: id 2 | task 1757 | n_gen = 100, tg = 14.74 t/s, tg_3s = 14.89 t/s 3.19.244.129 I slot print_timing: id 2 | task 1757 | prompt eval time = 501.77 ms / 91 tokens ( 5.51 ms per token, 181.36 tokens per second) 3.19.244.136 I slot print_timing: id 2 | task 1757 | eval time = 7215.35 ms / 108 tokens ( 67.43 ms per token, 14.83 tokens per second) 3.19.244.137 I slot print_timing: id 2 | task 1757 | total time = 7717.11 ms / 199 tokens 3.19.244.138 I slot print_timing: id 2 | task 1757 | graphs reused = 1351 3.19.244.138 I slot print_timing: id 2 | task 1757 | graph reallocs = 142 / 0 (same size) / (changed size) 3.19.244.191 I slot release: id 2 | task 1757 | stop processing: n_tokens = 1323, truncated = 0 3.19.349.802 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.866 3.19.349.960 I slot launch_slot_: id 2 | task 1870 | processing task, is_child = 0 3.19.852.428 I slot print_timing: id 1 | task 1750 | prompt eval time = 462.28 ms / 98 tokens ( 4.72 ms per token, 211.99 tokens per second) 3.19.852.433 I slot print_timing: id 1 | task 1750 | eval time = 8625.52 ms / 117 tokens ( 74.36 ms per token, 13.45 tokens per second) 3.19.852.434 I slot print_timing: id 1 | task 1750 | total time = 9087.80 ms / 215 tokens 3.19.852.435 I slot print_timing: id 1 | task 1750 | graphs reused = 1351 3.19.852.436 I slot print_timing: id 1 | task 1750 | graph reallocs = 142 / 0 (same size) / (changed size) 3.19.852.491 I slot release: id 1 | task 1750 | stop processing: n_tokens = 1339, truncated = 0 3.19.960.714 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.856 3.19.960.918 I slot launch_slot_: id 1 | task 1874 | processing task, is_child = 0 3.20.879.360 I slot print_timing: id 0 | task 1820 | prompt eval time = 395.58 ms / 121 tokens ( 3.27 ms per token, 305.88 tokens per second) 3.20.879.367 I slot print_timing: id 0 | task 1820 | eval time = 4710.38 ms / 59 tokens ( 81.21 ms per token, 12.31 tokens per second) 3.20.879.368 I slot print_timing: id 0 | task 1820 | total time = 5105.97 ms / 180 tokens 3.20.879.369 I slot print_timing: id 0 | task 1820 | graphs reused = 1357 3.20.879.370 I slot print_timing: id 0 | task 1820 | graph reallocs = 147 / 0 (same size) / (changed size) 3.20.879.427 I slot release: id 0 | task 1820 | stop processing: n_tokens = 1304, truncated = 0 3.20.959.710 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.879 3.20.959.897 I slot launch_slot_: id 0 | task 1885 | processing task, is_child = 0 3.23.516.473 I slot print_timing: id 3 | task 1839 | prompt eval time = 373.59 ms / 105 tokens ( 3.56 ms per token, 281.06 tokens per second) 3.23.516.480 I slot print_timing: id 3 | task 1839 | eval time = 5952.00 ms / 78 tokens ( 77.30 ms per token, 12.94 tokens per second) 3.23.516.481 I slot print_timing: id 3 | task 1839 | total time = 6325.59 ms / 183 tokens 3.23.516.482 I slot print_timing: id 3 | task 1839 | graphs reused = 1390 3.23.516.483 I slot print_timing: id 3 | task 1839 | graph reallocs = 150 / 0 (same size) / (changed size) 3.23.516.541 I slot release: id 3 | task 1839 | stop processing: n_tokens = 1307, truncated = 0 3.23.599.114 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.877 3.23.599.285 I slot launch_slot_: id 3 | task 1923 | processing task, is_child = 0 3.26.282.668 I slot print_timing: id 0 | task 1885 | prompt eval time = 388.25 ms / 110 tokens ( 3.53 ms per token, 283.32 tokens per second) 3.26.282.674 I slot print_timing: id 0 | task 1885 | eval time = 4934.50 ms / 74 tokens ( 67.60 ms per token, 14.79 tokens per second) 3.26.282.675 I slot print_timing: id 0 | task 1885 | total time = 5322.75 ms / 184 tokens 3.26.282.678 I slot print_timing: id 0 | task 1885 | graphs reused = 1425 3.26.282.679 I slot print_timing: id 0 | task 1885 | graph reallocs = 151 / 0 (same size) / (changed size) 3.26.282.738 I slot release: id 0 | task 1885 | stop processing: n_tokens = 1308, truncated = 0 3.26.367.457 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.924 (> 0.100 thold), f_keep = 0.876 3.26.367.625 I slot launch_slot_: id 0 | task 1963 | processing task, is_child = 0 3.27.362.718 I slot print_timing: id 2 | task 1870 | prompt eval time = 503.17 ms / 95 tokens ( 5.30 ms per token, 188.80 tokens per second) 3.27.362.726 I slot print_timing: id 2 | task 1870 | eval time = 7509.56 ms / 99 tokens ( 76.63 ms per token, 13.05 tokens per second) 3.27.362.727 I slot print_timing: id 2 | task 1870 | total time = 8012.74 ms / 194 tokens 3.27.362.728 I slot print_timing: id 2 | task 1870 | graphs reused = 1434 3.27.362.729 I slot print_timing: id 2 | task 1870 | graph reallocs = 153 / 0 (same size) / (changed size) 3.27.362.791 I slot release: id 2 | task 1870 | stop processing: n_tokens = 1318, truncated = 0 3.27.472.626 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.869 3.27.472.777 I slot launch_slot_: id 2 | task 1976 | processing task, is_child = 0 3.28.057.474 I slot print_timing: id 1 | task 1874 | n_gen = 100, tg = 12.99 t/s, tg_3s = 13.12 t/s 3.30.963.451 I slot print_timing: id 1 | task 1874 | prompt eval time = 476.70 ms / 144 tokens ( 3.31 ms per token, 302.08 tokens per second) 3.30.963.457 I slot print_timing: id 1 | task 1874 | eval time = 10525.81 ms / 146 tokens ( 72.59 ms per token, 13.78 tokens per second) 3.30.963.459 I slot print_timing: id 1 | task 1874 | total time = 11002.51 ms / 290 tokens 3.30.963.459 I slot print_timing: id 1 | task 1874 | graphs reused = 1480 3.30.963.460 I slot print_timing: id 1 | task 1874 | graph reallocs = 154 / 0 (same size) / (changed size) 3.30.963.517 I slot release: id 1 | task 1874 | stop processing: n_tokens = 1414, truncated = 0 3.31.073.714 I slot print_timing: id 3 | task 1923 | n_gen = 100, tg = 13.99 t/s, tg_3s = 14.13 t/s 3.31.073.728 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.950 (> 0.100 thold), f_keep = 0.810 3.31.073.881 I slot launch_slot_: id 1 | task 2027 | processing task, is_child = 0 3.32.366.427 I slot print_timing: id 0 | task 1963 | prompt eval time = 411.49 ms / 115 tokens ( 3.58 ms per token, 279.47 tokens per second) 3.32.366.433 I slot print_timing: id 0 | task 1963 | eval time = 5587.29 ms / 76 tokens ( 74.50 ms per token, 13.42 tokens per second) 3.32.366.435 I slot print_timing: id 0 | task 1963 | total time = 5998.78 ms / 191 tokens 3.32.366.435 I slot print_timing: id 0 | task 1963 | graphs reused = 1492 3.32.366.436 I slot print_timing: id 0 | task 1963 | graph reallocs = 157 / 0 (same size) / (changed size) 3.32.366.502 I slot release: id 0 | task 1963 | stop processing: n_tokens = 1315, truncated = 0 3.32.448.453 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.871 3.32.448.615 I slot launch_slot_: id 0 | task 2044 | processing task, is_child = 0 3.34.121.944 I slot print_timing: id 3 | task 1923 | n_gen = 138, tg = 13.53 t/s, tg_3s = 12.47 t/s 3.34.759.133 I slot print_timing: id 3 | task 1923 | prompt eval time = 398.40 ms / 158 tokens ( 2.52 ms per token, 396.59 tokens per second) 3.34.759.139 I slot print_timing: id 3 | task 1923 | eval time = 10761.43 ms / 148 tokens ( 73.21 ms per token, 13.66 tokens per second) 3.34.759.141 I slot print_timing: id 3 | task 1923 | total time = 11159.83 ms / 306 tokens 3.34.759.142 I slot print_timing: id 3 | task 1923 | graphs reused = 1522 3.34.759.142 I slot print_timing: id 3 | task 1923 | graph reallocs = 159 / 0 (same size) / (changed size) 3.34.759.199 I slot release: id 3 | task 1923 | stop processing: n_tokens = 1430, truncated = 0 3.34.847.774 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.801 3.34.847.941 I slot launch_slot_: id 3 | task 2078 | processing task, is_child = 0 3.35.236.224 I slot print_timing: id 2 | task 1976 | n_gen = 100, tg = 13.66 t/s, tg_3s = 13.80 t/s 3.35.750.348 I slot print_timing: id 1 | task 2027 | prompt eval time = 474.33 ms / 81 tokens ( 5.86 ms per token, 170.77 tokens per second) 3.35.750.354 I slot print_timing: id 1 | task 2027 | eval time = 4202.11 ms / 58 tokens ( 73.72 ms per token, 13.56 tokens per second) 3.35.750.356 I slot print_timing: id 1 | task 2027 | total time = 4676.44 ms / 139 tokens 3.35.750.357 I slot print_timing: id 1 | task 2027 | graphs reused = 1529 3.35.750.358 I slot print_timing: id 1 | task 2027 | graph reallocs = 160 / 0 (same size) / (changed size) 3.35.750.419 I slot release: id 1 | task 2027 | stop processing: n_tokens = 1263, truncated = 0 3.35.859.891 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.907 3.35.860.044 I slot launch_slot_: id 1 | task 2090 | processing task, is_child = 0 3.38.239.765 I slot print_timing: id 2 | task 1976 | n_gen = 141, tg = 13.66 t/s, tg_3s = 13.65 t/s 3.38.733.985 I slot print_timing: id 0 | task 2044 | prompt eval time = 396.94 ms / 104 tokens ( 3.82 ms per token, 262.01 tokens per second) 3.38.733.990 I slot print_timing: id 0 | task 2044 | eval time = 5888.41 ms / 83 tokens ( 71.81 ms per token, 13.93 tokens per second) 3.38.733.991 I slot print_timing: id 0 | task 2044 | total time = 6285.35 ms / 187 tokens 3.38.733.992 I slot print_timing: id 0 | task 2044 | graphs reused = 1566 3.38.733.993 I slot print_timing: id 0 | task 2044 | graph reallocs = 163 / 0 (same size) / (changed size) 3.38.734.049 I slot release: id 0 | task 2044 | stop processing: n_tokens = 1311, truncated = 0 3.38.817.192 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.916 (> 0.100 thold), f_keep = 0.874 3.38.817.400 I slot launch_slot_: id 0 | task 2132 | processing task, is_child = 0 3.40.833.432 I slot print_timing: id 3 | task 2078 | prompt eval time = 388.85 ms / 125 tokens ( 3.11 ms per token, 321.46 tokens per second) 3.40.833.437 I slot print_timing: id 3 | task 2078 | eval time = 5596.62 ms / 78 tokens ( 72.68 ms per token, 13.76 tokens per second) 3.40.833.438 I slot print_timing: id 3 | task 2078 | total time = 5985.47 ms / 203 tokens 3.40.833.439 I slot print_timing: id 3 | task 2078 | graphs reused = 1591 3.40.833.440 I slot print_timing: id 3 | task 2078 | graph reallocs = 165 / 0 (same size) / (changed size) 3.40.833.502 I slot release: id 3 | task 2078 | stop processing: n_tokens = 1327, truncated = 0 3.40.920.010 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.917 (> 0.100 thold), f_keep = 0.864 3.40.920.219 I slot launch_slot_: id 3 | task 2161 | processing task, is_child = 0 3.41.304.148 I slot print_timing: id 2 | task 1976 | n_gen = 180, tg = 13.45 t/s, tg_3s = 12.73 t/s 3.43.203.322 I slot print_timing: id 1 | task 2090 | n_gen = 100, tg = 14.41 t/s, tg_3s = 14.56 t/s 3.44.349.881 I slot print_timing: id 2 | task 1976 | n_gen = 228, tg = 13.88 t/s, tg_3s = 15.76 t/s 3.44.729.894 I slot print_timing: id 0 | task 2132 | prompt eval time = 420.60 ms / 126 tokens ( 3.34 ms per token, 299.57 tokens per second) 3.44.729.902 I slot print_timing: id 0 | task 2132 | eval time = 5491.86 ms / 83 tokens ( 66.97 ms per token, 14.93 tokens per second) 3.44.729.903 I slot print_timing: id 0 | task 2132 | total time = 5912.47 ms / 209 tokens 3.44.729.904 I slot print_timing: id 0 | task 2132 | graphs reused = 1644 3.44.729.905 I slot print_timing: id 0 | task 2132 | graph reallocs = 166 / 0 (same size) / (changed size) 3.44.729.974 I slot release: id 0 | task 2132 | stop processing: n_tokens = 1333, truncated = 0 3.44.816.586 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.860 3.44.816.793 I slot launch_slot_: id 0 | task 2219 | processing task, is_child = 0 3.46.221.350 I slot print_timing: id 1 | task 2090 | n_gen = 143, tg = 14.36 t/s, tg_3s = 14.25 t/s 3.47.356.443 I slot print_timing: id 2 | task 1976 | n_gen = 271, tg = 13.94 t/s, tg_3s = 14.30 t/s 3.47.483.417 I slot print_timing: id 1 | task 2090 | prompt eval time = 474.11 ms / 103 tokens ( 4.60 ms per token, 217.25 tokens per second) 3.47.483.423 I slot print_timing: id 1 | task 2090 | eval time = 11149.25 ms / 163 tokens ( 68.82 ms per token, 14.53 tokens per second) 3.47.483.424 I slot print_timing: id 1 | task 2090 | total time = 11623.35 ms / 266 tokens 3.47.483.425 I slot print_timing: id 1 | task 2090 | graphs reused = 1680 3.47.483.426 I slot print_timing: id 1 | task 2090 | graph reallocs = 168 / 0 (same size) / (changed size) 3.47.483.484 I slot release: id 1 | task 2090 | stop processing: n_tokens = 1390, truncated = 0 3.47.594.250 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.824 3.47.594.414 I slot launch_slot_: id 1 | task 2259 | processing task, is_child = 0 3.48.271.494 I slot print_timing: id 3 | task 2161 | n_gen = 100, tg = 14.21 t/s, tg_3s = 14.35 t/s 3.50.414.091 I slot print_timing: id 2 | task 1976 | prompt eval time = 518.30 ms / 128 tokens ( 4.05 ms per token, 246.96 tokens per second) 3.50.414.097 I slot print_timing: id 2 | task 1976 | eval time = 22422.99 ms / 313 tokens ( 71.87 ms per token, 13.91 tokens per second) 3.50.414.098 I slot print_timing: id 2 | task 1976 | total time = 22941.29 ms / 441 tokens 3.50.414.099 I slot print_timing: id 2 | task 1976 | graphs reused = 1715 3.50.414.100 I slot print_timing: id 2 | task 1976 | graph reallocs = 172 / 0 (same size) / (changed size) 3.50.414.156 I slot release: id 2 | task 1976 | stop processing: n_tokens = 1565, truncated = 0 3.50.523.268 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.732 3.50.523.438 I slot launch_slot_: id 2 | task 2300 | processing task, is_child = 0 3.51.321.546 I slot print_timing: id 3 | task 2161 | n_gen = 141, tg = 13.98 t/s, tg_3s = 13.44 t/s 3.51.512.053 I slot print_timing: id 0 | task 2219 | prompt eval time = 402.98 ms / 108 tokens ( 3.73 ms per token, 268.00 tokens per second) 3.51.512.059 I slot print_timing: id 0 | task 2219 | eval time = 6292.25 ms / 87 tokens ( 73.17 ms per token, 13.67 tokens per second) 3.51.512.060 I slot print_timing: id 0 | task 2219 | total time = 6695.23 ms / 195 tokens 3.51.512.061 I slot print_timing: id 0 | task 2219 | graphs reused = 1721 3.51.512.062 I slot print_timing: id 0 | task 2219 | graph reallocs = 173 / 0 (same size) / (changed size) 3.51.512.119 I slot release: id 0 | task 2219 | stop processing: n_tokens = 1319, truncated = 0 3.51.601.919 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.869 3.51.602.141 I slot launch_slot_: id 0 | task 2311 | processing task, is_child = 0 3.52.003.292 I slot print_timing: id 1 | task 2259 | prompt eval time = 478.83 ms / 100 tokens ( 4.79 ms per token, 208.84 tokens per second) 3.52.003.298 I slot print_timing: id 1 | task 2259 | eval time = 3930.03 ms / 51 tokens ( 78.60 ms per token, 12.72 tokens per second) 3.52.003.299 I slot print_timing: id 1 | task 2259 | total time = 4408.86 ms / 151 tokens 3.52.003.301 I slot print_timing: id 1 | task 2259 | graphs reused = 1722 3.52.003.301 I slot print_timing: id 1 | task 2259 | graph reallocs = 174 / 0 (same size) / (changed size) 3.52.003.354 I slot release: id 1 | task 2259 | stop processing: n_tokens = 1275, truncated = 0 3.52.112.949 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.899 3.52.113.106 I slot launch_slot_: id 1 | task 2315 | processing task, is_child = 0 3.52.785.134 I slot print_timing: id 3 | task 2161 | prompt eval time = 384.67 ms / 125 tokens ( 3.08 ms per token, 324.96 tokens per second) 3.52.785.140 I slot print_timing: id 3 | task 2161 | eval time = 11480.23 ms / 153 tokens ( 75.53 ms per token, 13.24 tokens per second) 3.52.785.142 I slot print_timing: id 3 | task 2161 | total time = 11864.89 ms / 278 tokens 3.52.785.143 I slot print_timing: id 3 | task 2161 | graphs reused = 1724 3.52.785.144 I slot print_timing: id 3 | task 2161 | graph reallocs = 177 / 0 (same size) / (changed size) 3.52.785.203 I slot release: id 3 | task 2161 | stop processing: n_tokens = 1402, truncated = 0 3.52.870.502 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.817 3.52.870.684 I slot launch_slot_: id 3 | task 2322 | processing task, is_child = 0 3.56.217.327 I slot print_timing: id 2 | task 2300 | prompt eval time = 536.87 ms / 171 tokens ( 3.14 ms per token, 318.51 tokens per second) 3.56.217.333 I slot print_timing: id 2 | task 2300 | eval time = 5157.00 ms / 67 tokens ( 78.14 ms per token, 12.80 tokens per second) 3.56.217.335 I slot print_timing: id 2 | task 2300 | total time = 5693.87 ms / 238 tokens 3.56.217.335 I slot print_timing: id 2 | task 2300 | graphs reused = 1770 3.56.217.336 I slot print_timing: id 2 | task 2300 | graph reallocs = 178 / 0 (same size) / (changed size) 3.56.217.395 I slot release: id 2 | task 2300 | stop processing: n_tokens = 1362, truncated = 0 3.56.327.339 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.841 3.56.327.512 I slot launch_slot_: id 2 | task 2373 | processing task, is_child = 0 3.56.916.002 I slot print_timing: id 1 | task 2315 | prompt eval time = 475.61 ms / 82 tokens ( 5.80 ms per token, 172.41 tokens per second) 3.56.916.008 I slot print_timing: id 1 | task 2315 | eval time = 4327.26 ms / 58 tokens ( 75.92 ms per token, 13.17 tokens per second) 3.56.916.009 I slot print_timing: id 1 | task 2315 | total time = 4802.88 ms / 140 tokens 3.56.916.010 I slot print_timing: id 1 | task 2315 | graphs reused = 1770 3.56.916.011 I slot print_timing: id 1 | task 2315 | graph reallocs = 179 / 0 (same size) / (changed size) 3.56.916.065 I slot release: id 1 | task 2315 | stop processing: n_tokens = 1264, truncated = 0 3.57.027.342 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.907 3.57.027.498 I slot launch_slot_: id 1 | task 2378 | processing task, is_child = 0 3.58.319.583 I slot print_timing: id 0 | task 2311 | prompt eval time = 400.84 ms / 89 tokens ( 4.50 ms per token, 222.03 tokens per second) 3.58.319.589 I slot print_timing: id 0 | task 2311 | eval time = 6316.57 ms / 77 tokens ( 83.11 ms per token, 12.03 tokens per second) 3.58.319.590 I slot print_timing: id 0 | task 2311 | total time = 6717.42 ms / 166 tokens 3.58.319.592 I slot print_timing: id 0 | task 2311 | graphs reused = 1782 3.58.319.593 I slot print_timing: id 0 | task 2311 | graph reallocs = 182 / 0 (same size) / (changed size) 3.58.319.655 I slot release: id 0 | task 2311 | stop processing: n_tokens = 1290, truncated = 0 3.58.405.202 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.888 3.58.405.415 I slot launch_slot_: id 0 | task 2395 | processing task, is_child = 0 3.58.866.598 I slot print_timing: id 3 | task 2322 | prompt eval time = 386.22 ms / 114 tokens ( 3.39 ms per token, 295.17 tokens per second) 3.58.866.605 I slot print_timing: id 3 | task 2322 | eval time = 5609.67 ms / 72 tokens ( 79.01 ms per token, 12.66 tokens per second) 3.58.866.606 I slot print_timing: id 3 | task 2322 | total time = 5995.89 ms / 186 tokens 3.58.866.607 I slot print_timing: id 3 | task 2322 | graphs reused = 1783 3.58.866.608 I slot print_timing: id 3 | task 2322 | graph reallocs = 184 / 0 (same size) / (changed size) 3.58.866.667 I slot release: id 3 | task 2322 | stop processing: n_tokens = 1310, truncated = 0 3.58.952.460 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.875 3.58.952.641 I slot launch_slot_: id 3 | task 2400 | processing task, is_child = 0 4.02.006.623 I slot print_timing: id 2 | task 2373 | prompt eval time = 521.84 ms / 98 tokens ( 5.32 ms per token, 187.80 tokens per second) 4.02.006.630 I slot print_timing: id 2 | task 2373 | eval time = 5157.25 ms / 67 tokens ( 78.14 ms per token, 12.80 tokens per second) 4.02.006.631 I slot print_timing: id 2 | task 2373 | total time = 5679.09 ms / 165 tokens 4.02.006.632 I slot print_timing: id 2 | task 2373 | graphs reused = 1823 4.02.006.633 I slot print_timing: id 2 | task 2373 | graph reallocs = 186 / 0 (same size) / (changed size) 4.02.006.687 I slot release: id 2 | task 2373 | stop processing: n_tokens = 1289, truncated = 0 4.02.112.638 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.889 4.02.112.808 I slot launch_slot_: id 2 | task 2446 | processing task, is_child = 0 4.04.791.914 I slot print_timing: id 1 | task 2378 | n_gen = 100, tg = 13.58 t/s, tg_3s = 13.72 t/s 4.05.802.882 I slot print_timing: id 0 | task 2395 | n_gen = 100, tg = 14.14 t/s, tg_3s = 14.28 t/s 4.06.052.481 I slot print_timing: id 0 | task 2395 | prompt eval time = 393.87 ms / 97 tokens ( 4.06 ms per token, 246.27 tokens per second) 4.06.052.487 I slot print_timing: id 0 | task 2395 | eval time = 7253.17 ms / 104 tokens ( 70.42 ms per token, 14.20 tokens per second) 4.06.052.488 I slot print_timing: id 0 | task 2395 | total time = 7647.05 ms / 201 tokens 4.06.052.489 I slot print_timing: id 0 | task 2395 | graphs reused = 1876 4.06.052.490 I slot print_timing: id 0 | task 2395 | graph reallocs = 187 / 0 (same size) / (changed size) 4.06.052.543 I slot release: id 0 | task 2395 | stop processing: n_tokens = 1325, truncated = 0 4.06.053.427 I slot print_timing: id 3 | task 2400 | n_gen = 100, tg = 14.75 t/s, tg_3s = 14.90 t/s 4.06.133.616 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.865 4.06.133.779 I slot launch_slot_: id 0 | task 2504 | processing task, is_child = 0 4.07.816.760 I slot print_timing: id 1 | task 2378 | n_gen = 143, tg = 13.77 t/s, tg_3s = 14.22 t/s 4.08.325.084 I slot print_timing: id 2 | task 2446 | prompt eval time = 513.73 ms / 119 tokens ( 4.32 ms per token, 231.64 tokens per second) 4.08.325.090 I slot print_timing: id 2 | task 2446 | eval time = 5698.52 ms / 86 tokens ( 67.04 ms per token, 14.92 tokens per second) 4.08.325.091 I slot print_timing: id 2 | task 2446 | total time = 6212.26 ms / 205 tokens 4.08.325.092 I slot print_timing: id 2 | task 2446 | graphs reused = 1904 4.08.325.093 I slot print_timing: id 2 | task 2446 | graph reallocs = 189 / 0 (same size) / (changed size) 4.08.325.149 I slot release: id 2 | task 2446 | stop processing: n_tokens = 1329, truncated = 0 4.08.435.521 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.862 4.08.435.745 I slot launch_slot_: id 2 | task 2536 | processing task, is_child = 0 4.08.735.869 I slot print_timing: id 1 | task 2378 | prompt eval time = 474.81 ms / 109 tokens ( 4.36 ms per token, 229.57 tokens per second) 4.08.735.874 I slot print_timing: id 1 | task 2378 | eval time = 11233.54 ms / 153 tokens ( 73.90 ms per token, 13.53 tokens per second) 4.08.735.875 I slot print_timing: id 1 | task 2378 | total time = 11708.35 ms / 262 tokens 4.08.735.876 I slot print_timing: id 1 | task 2378 | graphs reused = 1904 4.08.735.877 I slot print_timing: id 1 | task 2378 | graph reallocs = 189 / 0 (same size) / (changed size) 4.08.735.939 I slot release: id 1 | task 2378 | stop processing: n_tokens = 1386, truncated = 0 4.08.908.765 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.827 4.08.908.914 I slot launch_slot_: id 1 | task 2539 | processing task, is_child = 0 4.09.192.666 I slot print_timing: id 3 | task 2400 | n_gen = 135, tg = 13.60 t/s, tg_3s = 11.15 t/s 4.11.788.171 I slot print_timing: id 3 | task 2400 | prompt eval time = 387.32 ms / 113 tokens ( 3.43 ms per token, 291.75 tokens per second) 4.11.788.177 I slot print_timing: id 3 | task 2400 | eval time = 12448.19 ms / 174 tokens ( 71.95 ms per token, 13.90 tokens per second) 4.11.788.178 I slot print_timing: id 3 | task 2400 | total time = 12835.51 ms / 287 tokens 4.11.788.180 I slot print_timing: id 3 | task 2400 | graphs reused = 1941 4.11.788.180 I slot print_timing: id 3 | task 2400 | graph reallocs = 194 / 0 (same size) / (changed size) 4.11.788.237 I slot release: id 3 | task 2400 | stop processing: n_tokens = 1411, truncated = 0 4.11.872.795 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.812 4.11.872.969 I slot launch_slot_: id 3 | task 2581 | processing task, is_child = 0 4.13.842.319 I slot print_timing: id 0 | task 2504 | n_gen = 100, tg = 13.56 t/s, tg_3s = 13.70 t/s 4.15.470.828 I slot print_timing: id 1 | task 2539 | prompt eval time = 487.48 ms / 109 tokens ( 4.47 ms per token, 223.60 tokens per second) 4.15.470.835 I slot print_timing: id 1 | task 2539 | eval time = 6074.42 ms / 93 tokens ( 66.03 ms per token, 15.15 tokens per second) 4.15.470.836 I slot print_timing: id 1 | task 2539 | total time = 6561.89 ms / 202 tokens 4.15.470.837 I slot print_timing: id 1 | task 2539 | graphs reused = 1991 4.15.470.837 I slot print_timing: id 1 | task 2539 | graph reallocs = 195 / 0 (same size) / (changed size) 4.15.470.892 I slot release: id 1 | task 2539 | stop processing: n_tokens = 1326, truncated = 0 4.15.585.370 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.864 4.15.585.528 I slot launch_slot_: id 1 | task 2636 | processing task, is_child = 0 4.16.194.235 I slot print_timing: id 2 | task 2536 | n_gen = 100, tg = 13.59 t/s, tg_3s = 13.73 t/s 4.16.892.657 I slot print_timing: id 0 | task 2504 | n_gen = 142, tg = 13.62 t/s, tg_3s = 13.77 t/s 4.17.085.009 I slot print_timing: id 2 | task 2536 | prompt eval time = 472.63 ms / 112 tokens ( 4.22 ms per token, 236.97 tokens per second) 4.17.085.016 I slot print_timing: id 2 | task 2536 | eval time = 8176.61 ms / 114 tokens ( 72.36 ms per token, 13.82 tokens per second) 4.17.085.017 I slot print_timing: id 2 | task 2536 | total time = 8649.24 ms / 226 tokens 4.17.085.018 I slot print_timing: id 2 | task 2536 | graphs reused = 2006 4.17.085.018 I slot print_timing: id 2 | task 2536 | graph reallocs = 198 / 0 (same size) / (changed size) 4.17.085.077 I slot release: id 2 | task 2536 | stop processing: n_tokens = 1350, truncated = 0 4.17.195.556 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.849 4.17.195.727 I slot launch_slot_: id 2 | task 2656 | processing task, is_child = 0 4.18.470.185 I slot print_timing: id 0 | task 2504 | prompt eval time = 407.40 ms / 134 tokens ( 3.04 ms per token, 328.92 tokens per second) 4.18.470.191 I slot print_timing: id 0 | task 2504 | eval time = 11928.98 ms / 160 tokens ( 75.03 ms per token, 13.33 tokens per second) 4.18.470.192 I slot print_timing: id 0 | task 2504 | total time = 12336.38 ms / 294 tokens 4.18.470.193 I slot print_timing: id 0 | task 2504 | graphs reused = 2017 4.18.470.194 I slot print_timing: id 0 | task 2504 | graph reallocs = 199 / 0 (same size) / (changed size) 4.18.470.250 I slot release: id 0 | task 2504 | stop processing: n_tokens = 1418, truncated = 0 4.18.552.378 I slot print_timing: id 3 | task 2581 | prompt eval time = 384.06 ms / 95 tokens ( 4.04 ms per token, 247.36 tokens per second) 4.18.552.384 I slot print_timing: id 3 | task 2581 | eval time = 6295.33 ms / 87 tokens ( 73.20 ms per token, 13.66 tokens per second) 4.18.552.385 I slot print_timing: id 3 | task 2581 | total time = 6679.39 ms / 182 tokens 4.18.552.386 I slot print_timing: id 3 | task 2581 | graphs reused = 2017 4.18.552.387 I slot print_timing: id 3 | task 2581 | graph reallocs = 199 / 0 (same size) / (changed size) 4.18.552.441 I slot release: id 3 | task 2581 | stop processing: n_tokens = 1306, truncated = 0 4.18.552.461 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.808 4.18.552.623 I slot launch_slot_: id 0 | task 2672 | processing task, is_child = 0 4.18.552.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.973 MiB) 4.18.555.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 4.18.559.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 4.18.615.632 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.877 4.18.615.851 I slot launch_slot_: id 3 | task 2673 | processing task, is_child = 0 4.23.402.943 I slot print_timing: id 1 | task 2636 | n_gen = 100, tg = 13.48 t/s, tg_3s = 13.62 t/s 4.23.466.412 I slot print_timing: id 1 | task 2636 | prompt eval time = 475.84 ms / 96 tokens ( 4.96 ms per token, 201.75 tokens per second) 4.23.466.418 I slot print_timing: id 1 | task 2636 | eval time = 7405.02 ms / 101 tokens ( 74.05 ms per token, 13.50 tokens per second) 4.23.466.420 I slot print_timing: id 1 | task 2636 | total time = 7880.86 ms / 197 tokens 4.23.466.421 I slot print_timing: id 1 | task 2636 | graphs reused = 2082 4.23.466.422 I slot print_timing: id 1 | task 2636 | graph reallocs = 201 / 0 (same size) / (changed size) 4.23.466.489 I slot release: id 1 | task 2636 | stop processing: n_tokens = 1321, truncated = 0 4.23.580.017 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.868 4.23.580.176 I slot launch_slot_: id 1 | task 2743 | processing task, is_child = 0 4.25.031.477 I slot print_timing: id 2 | task 2656 | n_gen = 100, tg = 13.54 t/s, tg_3s = 13.68 t/s 4.25.923.733 I slot print_timing: id 0 | task 2672 | prompt eval time = 661.50 ms / 166 tokens ( 3.98 ms per token, 250.94 tokens per second) 4.25.923.738 I slot print_timing: id 0 | task 2672 | eval time = 6646.35 ms / 99 tokens ( 67.82 ms per token, 14.74 tokens per second) 4.25.923.740 I slot print_timing: id 0 | task 2672 | total time = 7307.86 ms / 265 tokens 4.25.923.741 I slot print_timing: id 0 | task 2672 | graphs reused = 2110 4.25.923.742 I slot print_timing: id 0 | task 2672 | graph reallocs = 204 / 0 (same size) / (changed size) 4.25.923.808 I slot release: id 0 | task 2672 | stop processing: n_tokens = 1389, truncated = 0 4.26.007.650 I slot print_timing: id 3 | task 2673 | n_gen = 100, tg = 14.71 t/s, tg_3s = 14.86 t/s 4.26.007.662 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.825 4.26.007.822 I slot launch_slot_: id 0 | task 2776 | processing task, is_child = 0 4.28.043.181 I slot print_timing: id 2 | task 2656 | n_gen = 143, tg = 13.76 t/s, tg_3s = 14.28 t/s 4.28.107.310 I slot print_timing: id 3 | task 2673 | prompt eval time = 641.55 ms / 117 tokens ( 5.48 ms per token, 182.37 tokens per second) 4.28.107.317 I slot print_timing: id 3 | task 2673 | eval time = 8828.67 ms / 129 tokens ( 68.97 ms per token, 14.50 tokens per second) 4.28.107.318 I slot print_timing: id 3 | task 2673 | total time = 9470.22 ms / 246 tokens 4.28.107.319 I slot print_timing: id 3 | task 2673 | graphs reused = 2137 4.28.107.320 I slot print_timing: id 3 | task 2673 | graph reallocs = 206 / 0 (same size) / (changed size) 4.28.107.391 I slot release: id 3 | task 2673 | stop processing: n_tokens = 1370, truncated = 0 4.28.191.954 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.836 4.28.192.127 I slot launch_slot_: id 3 | task 2807 | processing task, is_child = 0 4.29.607.655 I slot print_timing: id 2 | task 2656 | prompt eval time = 524.40 ms / 122 tokens ( 4.30 ms per token, 232.65 tokens per second) 4.29.607.662 I slot print_timing: id 2 | task 2656 | eval time = 11887.51 ms / 163 tokens ( 73.38 ms per token, 13.63 tokens per second) 4.29.607.663 I slot print_timing: id 2 | task 2656 | total time = 12411.91 ms / 285 tokens 4.29.607.664 I slot print_timing: id 2 | task 2656 | graphs reused = 2152 4.29.607.665 I slot print_timing: id 2 | task 2656 | graph reallocs = 207 / 0 (same size) / (changed size) 4.29.607.721 I slot release: id 2 | task 2656 | stop processing: n_tokens = 1409, truncated = 0 4.29.716.673 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.813 4.29.716.851 I slot launch_slot_: id 2 | task 2827 | processing task, is_child = 0 4.30.302.983 I slot print_timing: id 1 | task 2743 | prompt eval time = 483.32 ms / 104 tokens ( 4.65 ms per token, 215.18 tokens per second) 4.30.302.989 I slot print_timing: id 1 | task 2743 | eval time = 6239.47 ms / 83 tokens ( 76.09 ms per token, 13.14 tokens per second) 4.30.302.990 I slot print_timing: id 1 | task 2743 | total time = 6722.79 ms / 187 tokens 4.30.302.991 I slot print_timing: id 1 | task 2743 | graphs reused = 2152 4.30.302.992 I slot print_timing: id 1 | task 2743 | graph reallocs = 208 / 0 (same size) / (changed size) 4.30.303.047 I slot release: id 1 | task 2743 | stop processing: n_tokens = 1311, truncated = 0 4.30.410.567 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.874 4.30.410.731 I slot launch_slot_: id 1 | task 2832 | processing task, is_child = 0 4.33.819.383 I slot print_timing: id 0 | task 2776 | n_gen = 100, tg = 13.35 t/s, tg_3s = 13.48 t/s 4.35.701.928 I slot print_timing: id 3 | task 2807 | n_gen = 100, tg = 13.90 t/s, tg_3s = 14.04 t/s 4.36.714.383 I slot print_timing: id 2 | task 2827 | prompt eval time = 520.98 ms / 112 tokens ( 4.65 ms per token, 214.98 tokens per second) 4.36.714.390 I slot print_timing: id 2 | task 2827 | eval time = 6476.53 ms / 97 tokens ( 67.46 ms per token, 14.82 tokens per second) 4.36.714.391 I slot print_timing: id 2 | task 2827 | total time = 6997.51 ms / 209 tokens 4.36.714.392 I slot print_timing: id 2 | task 2827 | graphs reused = 2243 4.36.714.393 I slot print_timing: id 2 | task 2827 | graph reallocs = 213 / 0 (same size) / (changed size) 4.36.714.465 I slot release: id 2 | task 2827 | stop processing: n_tokens = 1333, truncated = 0 4.36.823.802 I slot print_timing: id 0 | task 2776 | prompt eval time = 394.03 ms / 108 tokens ( 3.65 ms per token, 274.09 tokens per second) 4.36.823.809 I slot print_timing: id 0 | task 2776 | eval time = 10421.93 ms / 147 tokens ( 71.38 ms per token, 14.01 tokens per second) 4.36.823.810 I slot print_timing: id 0 | task 2776 | total time = 10815.95 ms / 255 tokens 4.36.823.811 I slot print_timing: id 0 | task 2776 | graphs reused = 2243 4.36.823.812 I slot print_timing: id 0 | task 2776 | graph reallocs = 213 / 0 (same size) / (changed size) 4.36.823.883 I slot release: id 0 | task 2776 | stop processing: n_tokens = 1379, truncated = 0 4.36.824.754 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.831 4.36.824.957 I slot launch_slot_: id 0 | task 2928 | processing task, is_child = 0 4.36.825.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.600 MiB) 4.36.828.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.537 MiB) 4.36.832.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 4.36.890.705 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 4.36.890.880 I slot launch_slot_: id 2 | task 2929 | processing task, is_child = 0 4.37.597.409 I slot print_timing: id 1 | task 2832 | prompt eval time = 481.65 ms / 116 tokens ( 4.15 ms per token, 240.84 tokens per second) 4.37.597.416 I slot print_timing: id 1 | task 2832 | eval time = 6705.01 ms / 96 tokens ( 70.58 ms per token, 14.17 tokens per second) 4.37.597.417 I slot print_timing: id 1 | task 2832 | total time = 7186.66 ms / 212 tokens 4.37.597.418 I slot print_timing: id 1 | task 2832 | graphs reused = 2243 4.37.597.419 I slot print_timing: id 1 | task 2832 | graph reallocs = 213 / 0 (same size) / (changed size) 4.37.597.478 I slot release: id 1 | task 2832 | stop processing: n_tokens = 1336, truncated = 0 4.37.707.899 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 4.37.708.070 I slot launch_slot_: id 1 | task 2933 | processing task, is_child = 0 4.38.761.230 I slot print_timing: id 3 | task 2807 | n_gen = 131, tg = 12.77 t/s, tg_3s = 10.13 t/s 4.38.948.607 I slot print_timing: id 3 | task 2807 | prompt eval time = 387.65 ms / 133 tokens ( 2.91 ms per token, 343.09 tokens per second) 4.38.948.614 I slot print_timing: id 3 | task 2807 | eval time = 10368.81 ms / 134 tokens ( 77.96 ms per token, 12.83 tokens per second) 4.38.948.616 I slot print_timing: id 3 | task 2807 | total time = 10756.46 ms / 267 tokens 4.38.948.617 I slot print_timing: id 3 | task 2807 | graphs reused = 2254 4.38.948.618 I slot print_timing: id 3 | task 2807 | graph reallocs = 216 / 0 (same size) / (changed size) 4.38.948.689 I slot release: id 3 | task 2807 | stop processing: n_tokens = 1391, truncated = 0 4.39.029.830 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.920 (> 0.100 thold), f_keep = 0.824 4.39.030.005 I slot launch_slot_: id 3 | task 2949 | processing task, is_child = 0 4.43.089.768 I slot print_timing: id 3 | task 2949 | prompt eval time = 385.39 ms / 120 tokens ( 3.21 ms per token, 311.37 tokens per second) 4.43.089.775 I slot print_timing: id 3 | task 2949 | eval time = 3674.35 ms / 60 tokens ( 62.28 ms per token, 16.06 tokens per second) 4.43.089.776 I slot print_timing: id 3 | task 2949 | total time = 4059.74 ms / 180 tokens 4.43.089.776 I slot print_timing: id 3 | task 2949 | graphs reused = 2311 4.43.089.777 I slot print_timing: id 3 | task 2949 | graph reallocs = 218 / 0 (same size) / (changed size) 4.43.089.833 I slot release: id 3 | task 2949 | stop processing: n_tokens = 1304, truncated = 0 4.43.170.251 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.879 4.43.170.433 I slot launch_slot_: id 3 | task 3012 | processing task, is_child = 0 4.44.049.270 I slot print_timing: id 1 | task 2933 | prompt eval time = 488.35 ms / 103 tokens ( 4.74 ms per token, 210.92 tokens per second) 4.44.049.277 I slot print_timing: id 1 | task 2933 | eval time = 5852.83 ms / 86 tokens ( 68.86 ms per token, 14.52 tokens per second) 4.44.049.279 I slot print_timing: id 1 | task 2933 | total time = 6341.18 ms / 189 tokens 4.44.049.280 I slot print_timing: id 1 | task 2933 | graphs reused = 2318 4.44.049.281 I slot print_timing: id 1 | task 2933 | graph reallocs = 219 / 0 (same size) / (changed size) 4.44.049.355 I slot release: id 1 | task 2933 | stop processing: n_tokens = 1313, truncated = 0 4.44.156.614 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.938 (> 0.100 thold), f_keep = 0.873 4.44.156.813 I slot launch_slot_: id 1 | task 3024 | processing task, is_child = 0 4.45.060.686 I slot print_timing: id 0 | task 2928 | prompt eval time = 706.15 ms / 119 tokens ( 5.93 ms per token, 168.52 tokens per second) 4.45.060.692 I slot print_timing: id 0 | task 2928 | eval time = 7463.63 ms / 99 tokens ( 76.16 ms per token, 13.13 tokens per second) 4.45.060.693 I slot print_timing: id 0 | task 2928 | total time = 8169.77 ms / 218 tokens 4.45.060.694 I slot print_timing: id 0 | task 2928 | graphs reused = 2324 4.45.060.695 I slot print_timing: id 0 | task 2928 | graph reallocs = 222 / 0 (same size) / (changed size) 4.45.060.749 I slot release: id 0 | task 2928 | stop processing: n_tokens = 1342, truncated = 0 4.45.141.395 I slot print_timing: id 2 | task 2929 | n_gen = 100, tg = 13.12 t/s, tg_3s = 13.26 t/s 4.45.141.708 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.854 4.45.141.870 I slot launch_slot_: id 0 | task 3035 | processing task, is_child = 0 4.45.911.040 I slot print_timing: id 2 | task 2929 | prompt eval time = 686.65 ms / 119 tokens ( 5.77 ms per token, 173.31 tokens per second) 4.45.911.046 I slot print_timing: id 2 | task 2929 | eval time = 8312.69 ms / 108 tokens ( 77.69 ms per token, 12.87 tokens per second) 4.45.911.047 I slot print_timing: id 2 | task 2929 | total time = 8999.34 ms / 227 tokens 4.45.911.048 I slot print_timing: id 2 | task 2929 | graphs reused = 2330 4.45.911.049 I slot print_timing: id 2 | task 2929 | graph reallocs = 224 / 0 (same size) / (changed size) 4.45.911.103 I slot release: id 2 | task 2929 | stop processing: n_tokens = 1351, truncated = 0 4.46.016.805 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.848 4.46.016.975 I slot launch_slot_: id 2 | task 3045 | processing task, is_child = 0 4.50.143.117 I slot print_timing: id 3 | task 3012 | prompt eval time = 378.68 ms / 108 tokens ( 3.51 ms per token, 285.20 tokens per second) 4.50.143.124 I slot print_timing: id 3 | task 3012 | eval time = 6593.98 ms / 88 tokens ( 75.79 ms per token, 13.19 tokens per second) 4.50.143.126 I slot print_timing: id 3 | task 3012 | total time = 6972.66 ms / 196 tokens 4.50.143.127 I slot print_timing: id 3 | task 3012 | graphs reused = 2386 4.50.143.128 I slot print_timing: id 3 | task 3012 | graph reallocs = 225 / 0 (same size) / (changed size) 4.50.143.198 I slot release: id 3 | task 3012 | stop processing: n_tokens = 1320, truncated = 0 4.50.228.415 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.921 (> 0.100 thold), f_keep = 0.868 4.50.228.580 I slot launch_slot_: id 3 | task 3106 | processing task, is_child = 0 4.50.681.429 I slot print_timing: id 1 | task 3024 | prompt eval time = 465.40 ms / 97 tokens ( 4.80 ms per token, 208.42 tokens per second) 4.50.681.436 I slot print_timing: id 1 | task 3024 | eval time = 6059.19 ms / 81 tokens ( 75.74 ms per token, 13.20 tokens per second) 4.50.681.437 I slot print_timing: id 1 | task 3024 | total time = 6524.59 ms / 178 tokens 4.50.681.438 I slot print_timing: id 1 | task 3024 | graphs reused = 2386 4.50.681.439 I slot print_timing: id 1 | task 3024 | graph reallocs = 226 / 0 (same size) / (changed size) 4.50.681.506 I slot release: id 1 | task 3024 | stop processing: n_tokens = 1302, truncated = 0 4.50.792.557 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.925 (> 0.100 thold), f_keep = 0.880 4.50.792.729 I slot launch_slot_: id 1 | task 3111 | processing task, is_child = 0 4.51.273.299 I slot print_timing: id 0 | task 3035 | prompt eval time = 390.72 ms / 100 tokens ( 3.91 ms per token, 255.94 tokens per second) 4.51.273.308 I slot print_timing: id 0 | task 3035 | eval time = 5740.69 ms / 74 tokens ( 78.64 ms per token, 12.72 tokens per second) 4.51.273.309 I slot print_timing: id 0 | task 3035 | total time = 6131.41 ms / 174 tokens 4.51.273.310 I slot print_timing: id 0 | task 3035 | graphs reused = 2386 4.51.273.311 I slot print_timing: id 0 | task 3035 | graph reallocs = 228 / 0 (same size) / (changed size) 4.51.273.375 I slot release: id 0 | task 3035 | stop processing: n_tokens = 1298, truncated = 0 4.51.354.647 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.932 (> 0.100 thold), f_keep = 0.883 4.51.354.814 I slot launch_slot_: id 0 | task 3115 | processing task, is_child = 0 4.53.740.022 I slot print_timing: id 2 | task 3045 | n_gen = 100, tg = 13.76 t/s, tg_3s = 13.90 t/s 4.55.169.148 I slot print_timing: id 0 | task 3115 | prompt eval time = 396.52 ms / 104 tokens ( 3.81 ms per token, 262.28 tokens per second) 4.55.169.155 I slot print_timing: id 0 | task 3115 | eval time = 3417.79 ms / 56 tokens ( 62.14 ms per token, 16.09 tokens per second) 4.55.169.156 I slot print_timing: id 0 | task 3115 | total time = 3814.31 ms / 160 tokens 4.55.169.159 I slot print_timing: id 0 | task 3115 | graphs reused = 2441 4.55.169.162 I slot print_timing: id 0 | task 3115 | graph reallocs = 231 / 0 (same size) / (changed size) 4.55.169.253 I slot release: id 0 | task 3115 | stop processing: n_tokens = 1284, truncated = 0 4.55.254.947 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.893 4.55.255.105 I slot launch_slot_: id 0 | task 3174 | processing task, is_child = 0 4.55.652.865 I slot print_timing: id 2 | task 3045 | prompt eval time = 528.33 ms / 172 tokens ( 3.07 ms per token, 325.56 tokens per second) 4.55.652.872 I slot print_timing: id 2 | task 3045 | eval time = 9107.55 ms / 126 tokens ( 72.86 ms per token, 13.72 tokens per second) 4.55.652.873 I slot print_timing: id 2 | task 3045 | total time = 9635.87 ms / 298 tokens 4.55.652.874 I slot print_timing: id 2 | task 3045 | graphs reused = 2442 4.55.652.875 I slot print_timing: id 2 | task 3045 | graph reallocs = 232 / 0 (same size) / (changed size) 4.55.652.943 I slot release: id 2 | task 3045 | stop processing: n_tokens = 1422, truncated = 0 4.55.761.540 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.945 (> 0.100 thold), f_keep = 0.806 4.55.761.719 I slot launch_slot_: id 2 | task 3178 | processing task, is_child = 0 4.58.087.885 I slot print_timing: id 1 | task 3111 | prompt eval time = 481.42 ms / 114 tokens ( 4.22 ms per token, 236.80 tokens per second) 4.58.087.891 I slot print_timing: id 1 | task 3111 | eval time = 6813.71 ms / 94 tokens ( 73.27 ms per token, 13.65 tokens per second) 4.58.087.893 I slot print_timing: id 1 | task 3111 | total time = 7295.14 ms / 208 tokens 4.58.087.894 I slot print_timing: id 1 | task 3111 | graphs reused = 2470 4.58.087.895 I slot print_timing: id 1 | task 3111 | graph reallocs = 234 / 0 (same size) / (changed size) 4.58.087.971 I slot release: id 1 | task 3111 | stop processing: n_tokens = 1332, truncated = 0 4.58.194.057 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.860 4.58.194.239 I slot launch_slot_: id 1 | task 3211 | processing task, is_child = 0 4.58.467.956 I slot print_timing: id 3 | task 3106 | n_gen = 100, tg = 12.61 t/s, tg_3s = 12.73 t/s 5.01.520.897 I slot print_timing: id 2 | task 3178 | prompt eval time = 511.28 ms / 88 tokens ( 5.81 ms per token, 172.12 tokens per second) 5.01.520.904 I slot print_timing: id 2 | task 3178 | eval time = 5247.88 ms / 79 tokens ( 67.28 ms per token, 14.86 tokens per second) 5.01.520.905 I slot print_timing: id 2 | task 3178 | total time = 5759.16 ms / 167 tokens 5.01.520.906 I slot print_timing: id 2 | task 3178 | graphs reused = 2515 5.01.520.907 I slot print_timing: id 2 | task 3178 | graph reallocs = 237 / 0 (same size) / (changed size) 5.01.520.961 I slot release: id 2 | task 3178 | stop processing: n_tokens = 1291, truncated = 0 5.01.521.234 I slot print_timing: id 3 | task 3106 | n_gen = 147, tg = 13.39 t/s, tg_3s = 15.39 t/s 5.01.628.070 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.946 (> 0.100 thold), f_keep = 0.888 5.01.628.297 I slot launch_slot_: id 2 | task 3261 | processing task, is_child = 0 5.02.574.651 I slot print_timing: id 3 | task 3106 | prompt eval time = 386.94 ms / 119 tokens ( 3.25 ms per token, 307.54 tokens per second) 5.02.574.658 I slot print_timing: id 3 | task 3106 | eval time = 11959.10 ms / 157 tokens ( 76.66 ms per token, 13.04 tokens per second) 5.02.574.659 I slot print_timing: id 3 | task 3106 | total time = 12346.05 ms / 276 tokens 5.02.574.660 I slot print_timing: id 3 | task 3106 | graphs reused = 2521 5.02.574.661 I slot print_timing: id 3 | task 3106 | graph reallocs = 238 / 0 (same size) / (changed size) 5.02.574.731 I slot release: id 3 | task 3106 | stop processing: n_tokens = 1400, truncated = 0 5.02.657.253 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.819 5.02.657.428 I slot launch_slot_: id 3 | task 3272 | processing task, is_child = 0 5.03.297.237 I slot print_timing: id 0 | task 3174 | prompt eval time = 397.18 ms / 117 tokens ( 3.39 ms per token, 294.58 tokens per second) 5.03.297.243 I slot print_timing: id 0 | task 3174 | eval time = 7644.93 ms / 99 tokens ( 78.01 ms per token, 12.82 tokens per second) 5.03.297.244 I slot print_timing: id 0 | task 3174 | total time = 8042.11 ms / 216 tokens 5.03.297.245 I slot print_timing: id 0 | task 3174 | graphs reused = 2524 5.03.297.246 I slot print_timing: id 0 | task 3174 | graph reallocs = 239 / 0 (same size) / (changed size) 5.03.297.306 I slot release: id 0 | task 3174 | stop processing: n_tokens = 1340, truncated = 0 5.03.377.303 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.855 5.03.377.466 I slot launch_slot_: id 0 | task 3280 | processing task, is_child = 0 5.04.530.299 I slot print_timing: id 1 | task 3211 | prompt eval time = 470.00 ms / 129 tokens ( 3.64 ms per token, 274.47 tokens per second) 5.04.530.305 I slot print_timing: id 1 | task 3211 | eval time = 5866.04 ms / 79 tokens ( 75.21 ms per token, 13.30 tokens per second) 5.04.530.307 I slot print_timing: id 1 | task 3211 | total time = 6336.04 ms / 208 tokens 5.04.530.307 I slot print_timing: id 1 | task 3211 | graphs reused = 2536 5.04.530.308 I slot print_timing: id 1 | task 3211 | graph reallocs = 241 / 0 (same size) / (changed size) 5.04.530.365 I slot release: id 1 | task 3211 | stop processing: n_tokens = 1332, truncated = 0 5.04.637.057 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.860 5.04.637.235 I slot launch_slot_: id 1 | task 3296 | processing task, is_child = 0 5.07.654.324 I slot print_timing: id 2 | task 3261 | prompt eval time = 506.65 ms / 87 tokens ( 5.82 ms per token, 171.72 tokens per second) 5.07.654.330 I slot print_timing: id 2 | task 3261 | eval time = 5519.35 ms / 74 tokens ( 75.61 ms per token, 13.23 tokens per second) 5.07.654.331 I slot print_timing: id 2 | task 3261 | total time = 6026.00 ms / 161 tokens 5.07.654.333 I slot print_timing: id 2 | task 3261 | graphs reused = 2576 5.07.654.334 I slot print_timing: id 2 | task 3261 | graph reallocs = 244 / 0 (same size) / (changed size) 5.07.654.387 I slot release: id 2 | task 3261 | stop processing: n_tokens = 1285, truncated = 0 5.07.761.154 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.892 5.07.761.341 I slot launch_slot_: id 2 | task 3341 | processing task, is_child = 0 5.09.779.294 I slot print_timing: id 0 | task 3280 | prompt eval time = 392.71 ms / 118 tokens ( 3.33 ms per token, 300.48 tokens per second) 5.09.779.301 I slot print_timing: id 0 | task 3280 | eval time = 6009.09 ms / 84 tokens ( 72.40 ms per token, 13.81 tokens per second) 5.09.779.302 I slot print_timing: id 0 | task 3280 | total time = 6401.80 ms / 202 tokens 5.09.779.303 I slot print_timing: id 0 | task 3280 | graphs reused = 2599 5.09.779.305 I slot print_timing: id 0 | task 3280 | graph reallocs = 245 / 0 (same size) / (changed size) 5.09.779.377 I slot release: id 0 | task 3280 | stop processing: n_tokens = 1326, truncated = 0 5.09.866.386 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.864 5.09.866.622 I slot launch_slot_: id 0 | task 3369 | processing task, is_child = 0 5.10.650.367 I slot print_timing: id 3 | task 3272 | n_gen = 100, tg = 13.01 t/s, tg_3s = 13.15 t/s 5.11.394.033 I slot print_timing: id 3 | task 3272 | prompt eval time = 386.08 ms / 152 tokens ( 2.54 ms per token, 393.70 tokens per second) 5.11.394.039 I slot print_timing: id 3 | task 3272 | eval time = 8350.51 ms / 112 tokens ( 75.23 ms per token, 13.29 tokens per second) 5.11.394.040 I slot print_timing: id 3 | task 3272 | total time = 8736.58 ms / 264 tokens 5.11.394.041 I slot print_timing: id 3 | task 3272 | graphs reused = 2617 5.11.394.042 I slot print_timing: id 3 | task 3272 | graph reallocs = 247 / 0 (same size) / (changed size) 5.11.394.102 I slot release: id 3 | task 3272 | stop processing: n_tokens = 1388, truncated = 0 5.11.474.522 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 5.11.474.706 I slot launch_slot_: id 3 | task 3391 | processing task, is_child = 0 5.12.294.681 I slot print_timing: id 1 | task 3296 | n_gen = 100, tg = 13.78 t/s, tg_3s = 13.91 t/s 5.13.119.939 I slot print_timing: id 2 | task 3341 | prompt eval time = 514.94 ms / 135 tokens ( 3.81 ms per token, 262.16 tokens per second) 5.13.119.946 I slot print_timing: id 2 | task 3341 | eval time = 4843.63 ms / 69 tokens ( 71.23 ms per token, 14.04 tokens per second) 5.13.119.947 I slot print_timing: id 2 | task 3341 | total time = 5358.58 ms / 204 tokens 5.13.119.948 I slot print_timing: id 2 | task 3341 | graphs reused = 2636 5.13.119.949 I slot print_timing: id 2 | task 3341 | graph reallocs = 248 / 0 (same size) / (changed size) 5.13.120.008 I slot release: id 2 | task 3341 | stop processing: n_tokens = 1328, truncated = 0 5.13.231.582 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.863 5.13.231.818 I slot launch_slot_: id 2 | task 3415 | processing task, is_child = 0 5.15.313.325 I slot print_timing: id 1 | task 3296 | n_gen = 140, tg = 13.62 t/s, tg_3s = 13.25 t/s 5.15.948.595 I slot print_timing: id 0 | task 3369 | prompt eval time = 403.60 ms / 92 tokens ( 4.39 ms per token, 227.95 tokens per second) 5.15.948.602 I slot print_timing: id 0 | task 3369 | eval time = 5678.34 ms / 79 tokens ( 72.80 ms per token, 13.74 tokens per second) 5.15.948.603 I slot print_timing: id 0 | task 3369 | total time = 6081.95 ms / 171 tokens 5.15.948.604 I slot print_timing: id 0 | task 3369 | graphs reused = 2669 5.15.948.605 I slot print_timing: id 0 | task 3369 | graph reallocs = 249 / 0 (same size) / (changed size) 5.15.948.673 I slot release: id 0 | task 3369 | stop processing: n_tokens = 1295, truncated = 0 5.16.033.706 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.885 5.16.033.873 I slot launch_slot_: id 0 | task 3453 | processing task, is_child = 0 5.18.338.868 I slot print_timing: id 1 | task 3296 | n_gen = 183, tg = 13.76 t/s, tg_3s = 14.21 t/s 5.18.713.945 I slot print_timing: id 3 | task 3391 | prompt eval time = 377.86 ms / 120 tokens ( 3.15 ms per token, 317.58 tokens per second) 5.18.713.952 I slot print_timing: id 3 | task 3391 | eval time = 6861.35 ms / 97 tokens ( 71.47 ms per token, 13.99 tokens per second) 5.18.713.953 I slot print_timing: id 3 | task 3391 | total time = 7239.22 ms / 217 tokens 5.18.713.954 I slot print_timing: id 3 | task 3391 | graphs reused = 2705 5.18.713.955 I slot print_timing: id 3 | task 3391 | graph reallocs = 251 / 0 (same size) / (changed size) 5.18.714.027 I slot release: id 3 | task 3391 | stop processing: n_tokens = 1341, truncated = 0 5.18.795.649 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.855 5.18.795.826 I slot launch_slot_: id 3 | task 3493 | processing task, is_child = 0 5.20.635.996 I slot print_timing: id 2 | task 3415 | n_gen = 100, tg = 14.47 t/s, tg_3s = 14.62 t/s 5.21.396.567 I slot print_timing: id 1 | task 3296 | n_gen = 227, tg = 13.87 t/s, tg_3s = 14.39 t/s 5.22.960.586 I slot print_timing: id 0 | task 3453 | n_gen = 100, tg = 15.18 t/s, tg_3s = 15.33 t/s 5.23.653.382 I slot print_timing: id 2 | task 3415 | n_gen = 148, tg = 14.91 t/s, tg_3s = 15.91 t/s 5.24.416.833 I slot print_timing: id 1 | task 3296 | n_gen = 275, tg = 14.19 t/s, tg_3s = 15.89 t/s 5.24.925.295 I slot print_timing: id 2 | task 3415 | prompt eval time = 562.28 ms / 131 tokens ( 4.29 ms per token, 232.98 tokens per second) 5.24.925.302 I slot print_timing: id 2 | task 3415 | eval time = 11131.18 ms / 168 tokens ( 66.65 ms per token, 15.00 tokens per second) 5.24.925.303 I slot print_timing: id 2 | task 3415 | total time = 11693.45 ms / 299 tokens 5.24.925.304 I slot print_timing: id 2 | task 3415 | graphs reused = 2795 5.24.925.305 I slot print_timing: id 2 | task 3415 | graph reallocs = 252 / 0 (same size) / (changed size) 5.24.925.362 I slot release: id 2 | task 3415 | stop processing: n_tokens = 1423, truncated = 0 5.25.035.312 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.923 (> 0.100 thold), f_keep = 0.805 5.25.035.493 I slot launch_slot_: id 2 | task 3588 | processing task, is_child = 0 5.25.886.888 I slot print_timing: id 3 | task 3493 | n_gen = 100, tg = 14.74 t/s, tg_3s = 14.89 t/s 5.26.010.953 I slot print_timing: id 0 | task 3453 | n_gen = 141, tg = 14.62 t/s, tg_3s = 13.44 t/s 5.26.073.458 I slot print_timing: id 0 | task 3453 | prompt eval time = 404.19 ms / 95 tokens ( 4.25 ms per token, 235.04 tokens per second) 5.26.073.464 I slot print_timing: id 0 | task 3453 | eval time = 9635.37 ms / 142 tokens ( 68.34 ms per token, 14.63 tokens per second) 5.26.073.465 I slot print_timing: id 0 | task 3453 | total time = 10039.56 ms / 237 tokens 5.26.073.466 I slot print_timing: id 0 | task 3453 | graphs reused = 2802 5.26.073.467 I slot print_timing: id 0 | task 3453 | graph reallocs = 253 / 0 (same size) / (changed size) 5.26.073.518 I slot release: id 0 | task 3453 | stop processing: n_tokens = 1361, truncated = 0 5.26.156.072 I slot print_timing: id 3 | task 3493 | prompt eval time = 373.04 ms / 98 tokens ( 3.81 ms per token, 262.71 tokens per second) 5.26.156.078 I slot print_timing: id 3 | task 3493 | eval time = 6987.19 ms / 104 tokens ( 67.84 ms per token, 14.74 tokens per second) 5.26.156.079 I slot print_timing: id 3 | task 3493 | total time = 7360.23 ms / 202 tokens 5.26.156.080 I slot print_timing: id 3 | task 3493 | graphs reused = 2802 5.26.156.081 I slot print_timing: id 3 | task 3493 | graph reallocs = 253 / 0 (same size) / (changed size) 5.26.156.135 I slot release: id 3 | task 3493 | stop processing: n_tokens = 1326, truncated = 0 5.26.156.152 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.913 (> 0.100 thold), f_keep = 0.842 5.26.156.312 I slot launch_slot_: id 0 | task 3600 | processing task, is_child = 0 5.26.156.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 5.26.159.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 5.26.161.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 5.26.218.175 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.933 (> 0.100 thold), f_keep = 0.864 5.26.218.413 I slot launch_slot_: id 3 | task 3601 | processing task, is_child = 0 5.27.435.324 I slot print_timing: id 1 | task 3296 | n_gen = 306, tg = 13.66 t/s, tg_3s = 10.27 t/s 5.30.479.833 I slot print_timing: id 1 | task 3296 | n_gen = 354, tg = 13.91 t/s, tg_3s = 15.77 t/s 5.30.980.190 I slot print_timing: id 2 | task 3588 | prompt eval time = 527.60 ms / 116 tokens ( 4.55 ms per token, 219.86 tokens per second) 5.30.980.196 I slot print_timing: id 2 | task 3588 | eval time = 5417.08 ms / 77 tokens ( 71.28 ms per token, 14.03 tokens per second) 5.30.980.197 I slot print_timing: id 2 | task 3588 | total time = 5944.68 ms / 193 tokens 5.30.980.198 I slot print_timing: id 2 | task 3588 | graphs reused = 2865 5.30.980.199 I slot print_timing: id 2 | task 3588 | graph reallocs = 256 / 0 (same size) / (changed size) 5.30.980.255 I slot release: id 2 | task 3588 | stop processing: n_tokens = 1317, truncated = 0 5.31.087.378 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.919 (> 0.100 thold), f_keep = 0.870 5.31.087.562 I slot launch_slot_: id 2 | task 3670 | processing task, is_child = 0 5.33.133.170 I slot print_timing: id 0 | task 3600 | prompt eval time = 643.12 ms / 130 tokens ( 4.95 ms per token, 202.14 tokens per second) 5.33.133.177 I slot print_timing: id 0 | task 3600 | eval time = 6271.62 ms / 92 tokens ( 68.92 ms per token, 14.51 tokens per second) 5.33.133.178 I slot print_timing: id 0 | task 3600 | total time = 6914.73 ms / 222 tokens 5.33.133.179 I slot print_timing: id 0 | task 3600 | graphs reused = 2887 5.33.133.181 I slot print_timing: id 0 | task 3600 | graph reallocs = 257 / 0 (same size) / (changed size) 5.33.133.245 I slot release: id 0 | task 3600 | stop processing: n_tokens = 1346, truncated = 0 5.33.222.133 I slot print_timing: id 3 | task 3601 | prompt eval time = 623.84 ms / 103 tokens ( 6.06 ms per token, 165.11 tokens per second) 5.33.222.141 I slot print_timing: id 3 | task 3601 | eval time = 6359.49 ms / 93 tokens ( 69.12 ms per token, 14.47 tokens per second) 5.33.222.142 I slot print_timing: id 3 | task 3601 | total time = 6983.33 ms / 196 tokens 5.33.222.143 I slot print_timing: id 3 | task 3601 | graphs reused = 2887 5.33.222.144 I slot print_timing: id 3 | task 3601 | graph reallocs = 257 / 0 (same size) / (changed size) 5.33.222.200 I slot release: id 3 | task 3601 | stop processing: n_tokens = 1320, truncated = 0 5.33.222.221 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.851 5.33.222.389 I slot launch_slot_: id 0 | task 3697 | processing task, is_child = 0 5.33.222.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 5.33.225.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.505 MiB) 5.33.280.661 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.918 (> 0.100 thold), f_keep = 0.868 5.33.280.876 I slot launch_slot_: id 3 | task 3698 | processing task, is_child = 0 5.33.701.219 I slot print_timing: id 1 | task 3296 | n_gen = 390, tg = 13.60 t/s, tg_3s = 11.18 t/s 5.36.717.783 I slot print_timing: id 1 | task 3296 | n_gen = 435, tg = 13.73 t/s, tg_3s = 14.92 t/s 5.37.350.141 I slot print_timing: id 1 | task 3296 | prompt eval time = 470.61 ms / 110 tokens ( 4.28 ms per token, 233.74 tokens per second) 5.37.350.147 I slot print_timing: id 1 | task 3296 | eval time = 32242.28 ms / 445 tokens ( 72.62 ms per token, 13.77 tokens per second) 5.37.350.148 I slot print_timing: id 1 | task 3296 | total time = 32712.89 ms / 555 tokens 5.37.350.149 I slot print_timing: id 1 | task 3296 | graphs reused = 2940 5.37.350.149 I slot print_timing: id 1 | task 3296 | graph reallocs = 259 / 0 (same size) / (changed size) 5.37.350.204 I slot release: id 1 | task 3296 | stop processing: n_tokens = 1679, truncated = 0 5.37.460.065 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.683 5.37.460.251 I slot launch_slot_: id 1 | task 3756 | processing task, is_child = 0 5.38.949.341 I slot print_timing: id 2 | task 3670 | n_gen = 100, tg = 13.51 t/s, tg_3s = 13.64 t/s 5.40.602.849 I slot print_timing: id 0 | task 3697 | n_gen = 100, tg = 14.88 t/s, tg_3s = 15.03 t/s 5.40.603.697 I slot print_timing: id 3 | task 3698 | n_gen = 100, tg = 14.88 t/s, tg_3s = 15.03 t/s 5.42.004.938 I slot print_timing: id 2 | task 3670 | n_gen = 148, tg = 14.15 t/s, tg_3s = 15.71 t/s 5.42.005.221 I slot print_timing: id 3 | task 3698 | prompt eval time = 647.92 ms / 123 tokens ( 5.27 ms per token, 189.84 tokens per second) 5.42.005.226 I slot print_timing: id 3 | task 3698 | eval time = 8055.06 ms / 122 tokens ( 66.57 ms per token, 15.02 tokens per second) 5.42.005.227 I slot print_timing: id 3 | task 3698 | total time = 8702.98 ms / 245 tokens 5.42.005.228 I slot print_timing: id 3 | task 3698 | graphs reused = 3003 5.42.005.229 I slot print_timing: id 3 | task 3698 | graph reallocs = 262 / 0 (same size) / (changed size) 5.42.005.286 I slot release: id 3 | task 3698 | stop processing: n_tokens = 1369, truncated = 0 5.42.090.369 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.837 5.42.090.524 I slot launch_slot_: id 3 | task 3824 | processing task, is_child = 0 5.43.589.900 I slot print_timing: id 2 | task 3670 | prompt eval time = 531.16 ms / 122 tokens ( 4.35 ms per token, 229.68 tokens per second) 5.43.589.908 I slot print_timing: id 2 | task 3670 | eval time = 11971.15 ms / 169 tokens ( 71.26 ms per token, 14.03 tokens per second) 5.43.589.909 I slot print_timing: id 2 | task 3670 | total time = 12502.32 ms / 291 tokens 5.43.589.910 I slot print_timing: id 2 | task 3670 | graphs reused = 3020 5.43.589.911 I slot print_timing: id 2 | task 3670 | graph reallocs = 263 / 0 (same size) / (changed size) 5.43.589.975 I slot release: id 2 | task 3670 | stop processing: n_tokens = 1415, truncated = 0 5.43.700.734 I slot print_timing: id 0 | task 3697 | n_gen = 144, tg = 14.66 t/s, tg_3s = 14.20 t/s 5.43.701.418 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.810 5.43.701.649 I slot launch_slot_: id 2 | task 3846 | processing task, is_child = 0 5.44.932.186 I slot print_timing: id 1 | task 3756 | n_gen = 100, tg = 14.16 t/s, tg_3s = 14.30 t/s 5.46.077.872 I slot print_timing: id 0 | task 3697 | prompt eval time = 668.15 ms / 133 tokens ( 5.02 ms per token, 199.06 tokens per second) 5.46.077.879 I slot print_timing: id 0 | task 3697 | eval time = 12128.82 ms / 175 tokens ( 69.71 ms per token, 14.35 tokens per second) 5.46.077.880 I slot print_timing: id 0 | task 3697 | total time = 12796.97 ms / 308 tokens 5.46.077.881 I slot print_timing: id 0 | task 3697 | graphs reused = 3048 5.46.077.882 I slot print_timing: id 0 | task 3697 | graph reallocs = 264 / 0 (same size) / (changed size) 5.46.077.946 I slot release: id 0 | task 3697 | stop processing: n_tokens = 1432, truncated = 0 5.46.162.017 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.897 (> 0.100 thold), f_keep = 0.800 5.46.162.263 I slot launch_slot_: id 0 | task 3879 | processing task, is_child = 0 5.47.961.341 I slot print_timing: id 1 | task 3756 | n_gen = 143, tg = 14.17 t/s, tg_3s = 14.20 t/s 5.48.468.267 I slot print_timing: id 1 | task 3756 | prompt eval time = 481.23 ms / 118 tokens ( 4.08 ms per token, 245.21 tokens per second) 5.48.468.274 I slot print_timing: id 1 | task 3756 | eval time = 10526.77 ms / 151 tokens ( 70.18 ms per token, 14.25 tokens per second) 5.48.468.276 I slot print_timing: id 1 | task 3756 | total time = 11007.99 ms / 269 tokens 5.48.468.277 I slot print_timing: id 1 | task 3756 | graphs reused = 3078 5.48.468.278 I slot print_timing: id 1 | task 3756 | graph reallocs = 266 / 0 (same size) / (changed size) 5.48.468.348 I slot release: id 1 | task 3756 | stop processing: n_tokens = 1393, truncated = 0 5.48.578.489 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.944 (> 0.100 thold), f_keep = 0.823 5.48.578.681 I slot launch_slot_: id 1 | task 3913 | processing task, is_child = 0 5.49.122.764 I slot print_timing: id 3 | task 3824 | prompt eval time = 374.72 ms / 101 tokens ( 3.71 ms per token, 269.53 tokens per second) 5.49.122.770 I slot print_timing: id 3 | task 3824 | eval time = 6657.50 ms / 88 tokens ( 76.52 ms per token, 13.07 tokens per second) 5.49.122.772 I slot print_timing: id 3 | task 3824 | total time = 7032.22 ms / 189 tokens 5.49.122.773 I slot print_timing: id 3 | task 3824 | graphs reused = 3078 5.49.122.774 I slot print_timing: id 3 | task 3824 | graph reallocs = 269 / 0 (same size) / (changed size) 5.49.122.841 I slot release: id 3 | task 3824 | stop processing: n_tokens = 1313, truncated = 0 5.49.206.155 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.936 (> 0.100 thold), f_keep = 0.873 5.49.206.326 I slot launch_slot_: id 3 | task 3918 | processing task, is_child = 0 5.51.167.896 I slot print_timing: id 2 | task 3846 | prompt eval time = 528.41 ms / 95 tokens ( 5.56 ms per token, 179.78 tokens per second) 5.51.167.903 I slot print_timing: id 2 | task 3846 | eval time = 6937.81 ms / 95 tokens ( 73.81 ms per token, 13.55 tokens per second) 5.51.167.904 I slot print_timing: id 2 | task 3846 | total time = 7466.22 ms / 190 tokens 5.51.167.905 I slot print_timing: id 2 | task 3846 | graphs reused = 3102 5.51.167.905 I slot print_timing: id 2 | task 3846 | graph reallocs = 270 / 0 (same size) / (changed size) 5.51.167.963 I slot release: id 2 | task 3846 | stop processing: n_tokens = 1314, truncated = 0 5.51.274.741 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.872 5.51.274.971 I slot launch_slot_: id 2 | task 3947 | processing task, is_child = 0 5.53.702.702 I slot print_timing: id 1 | task 3913 | prompt eval time = 477.55 ms / 89 tokens ( 5.37 ms per token, 186.37 tokens per second) 5.53.702.716 I slot print_timing: id 1 | task 3913 | eval time = 4646.45 ms / 63 tokens ( 74.94 ms per token, 13.34 tokens per second) 5.53.702.718 I slot print_timing: id 1 | task 3913 | total time = 5123.99 ms / 152 tokens 5.53.702.720 I slot print_timing: id 1 | task 3913 | graphs reused = 3131 5.53.702.721 I slot print_timing: id 1 | task 3913 | graph reallocs = 271 / 0 (same size) / (changed size) 5.53.702.799 I slot release: id 1 | task 3913 | stop processing: n_tokens = 1276, truncated = 0 5.53.813.373 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.926 (> 0.100 thold), f_keep = 0.898 5.53.813.595 I slot launch_slot_: id 1 | task 3981 | processing task, is_child = 0 5.54.357.248 I slot print_timing: id 0 | task 3879 | n_gen = 100, tg = 12.72 t/s, tg_3s = 12.85 t/s 5.55.981.042 I slot print_timing: id 3 | task 3918 | prompt eval time = 385.18 ms / 99 tokens ( 3.89 ms per token, 257.03 tokens per second) 5.55.981.049 I slot print_timing: id 3 | task 3918 | eval time = 6389.52 ms / 89 tokens ( 72.61 ms per token, 13.77 tokens per second) 5.55.981.050 I slot print_timing: id 3 | task 3918 | total time = 6774.69 ms / 188 tokens 5.55.981.051 I slot print_timing: id 3 | task 3918 | graphs reused = 3157 5.55.981.052 I slot print_timing: id 3 | task 3918 | graph reallocs = 274 / 0 (same size) / (changed size) 5.55.981.127 I slot release: id 3 | task 3918 | stop processing: n_tokens = 1312, truncated = 0 5.56.069.613 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.922 (> 0.100 thold), f_keep = 0.873 5.56.069.776 I slot launch_slot_: id 3 | task 4012 | processing task, is_child = 0 5.56.657.316 I slot print_timing: id 2 | task 3947 | prompt eval time = 514.40 ms / 92 tokens ( 5.59 ms per token, 178.85 tokens per second) 5.56.657.322 I slot print_timing: id 2 | task 3947 | eval time = 4867.93 ms / 67 tokens ( 73.76 ms per token, 13.56 tokens per second) 5.56.657.324 I slot print_timing: id 2 | task 3947 | total time = 5382.32 ms / 159 tokens 5.56.657.325 I slot print_timing: id 2 | task 3947 | graphs reused = 3159 5.56.657.325 I slot print_timing: id 2 | task 3947 | graph reallocs = 275 / 0 (same size) / (changed size) 5.56.657.387 I slot release: id 2 | task 3947 | stop processing: n_tokens = 1283, truncated = 0 5.56.766.127 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 5.56.766.351 I slot launch_slot_: id 2 | task 4019 | processing task, is_child = 0 5.57.415.578 I slot print_timing: id 0 | task 3879 | n_gen = 137, tg = 12.55 t/s, tg_3s = 12.10 t/s 6.00.432.231 I slot print_timing: id 0 | task 3879 | n_gen = 185, tg = 13.28 t/s, tg_3s = 15.91 t/s 6.00.495.775 I slot print_timing: id 1 | task 3981 | prompt eval time = 478.58 ms / 113 tokens ( 4.24 ms per token, 236.12 tokens per second) 6.00.495.782 I slot print_timing: id 1 | task 3981 | eval time = 6203.58 ms / 88 tokens ( 71.31 ms per token, 14.02 tokens per second) 6.00.495.783 I slot print_timing: id 1 | task 3981 | total time = 6682.15 ms / 201 tokens 6.00.495.784 I slot print_timing: id 1 | task 3981 | graphs reused = 3209 6.00.495.785 I slot print_timing: id 1 | task 3981 | graph reallocs = 276 / 0 (same size) / (changed size) 6.00.495.843 I slot release: id 1 | task 3981 | stop processing: n_tokens = 1325, truncated = 0 6.00.605.614 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.885 (> 0.100 thold), f_keep = 0.865 6.00.605.785 I slot launch_slot_: id 1 | task 4074 | processing task, is_child = 0 6.02.066.690 I slot print_timing: id 2 | task 4019 | prompt eval time = 517.93 ms / 90 tokens ( 5.75 ms per token, 173.77 tokens per second) 6.02.066.696 I slot print_timing: id 2 | task 4019 | eval time = 4782.39 ms / 70 tokens ( 69.31 ms per token, 14.43 tokens per second) 6.02.066.697 I slot print_timing: id 2 | task 4019 | total time = 5300.32 ms / 160 tokens 6.02.066.699 I slot print_timing: id 2 | task 4019 | graphs reused = 3223 6.02.066.700 I slot print_timing: id 2 | task 4019 | graph reallocs = 279 / 0 (same size) / (changed size) 6.02.066.757 I slot release: id 2 | task 4019 | stop processing: n_tokens = 1284, truncated = 0 6.02.176.855 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.930 (> 0.100 thold), f_keep = 0.893 6.02.177.076 I slot launch_slot_: id 2 | task 4093 | processing task, is_child = 0 6.03.444.789 I slot print_timing: id 0 | task 3879 | n_gen = 219, tg = 12.92 t/s, tg_3s = 11.29 t/s 6.03.883.482 I slot print_timing: id 0 | task 3879 | prompt eval time = 412.83 ms / 152 tokens ( 2.72 ms per token, 368.19 tokens per second) 6.03.883.488 I slot print_timing: id 0 | task 3879 | eval time = 17308.36 ms / 226 tokens ( 76.93 ms per token, 13.00 tokens per second) 6.03.883.489 I slot print_timing: id 0 | task 3879 | total time = 17721.19 ms / 378 tokens 6.03.883.490 I slot print_timing: id 0 | task 3879 | graphs reused = 3241 6.03.883.491 I slot print_timing: id 0 | task 3879 | graph reallocs = 280 / 0 (same size) / (changed size) 6.03.883.549 I slot release: id 0 | task 3879 | stop processing: n_tokens = 1502, truncated = 0 6.03.968.222 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.901 (> 0.100 thold), f_keep = 0.763 6.03.968.415 I slot launch_slot_: id 0 | task 4116 | processing task, is_child = 0 6.04.228.914 I slot print_timing: id 3 | task 4012 | n_gen = 100, tg = 12.74 t/s, tg_3s = 12.87 t/s 6.07.240.624 I slot print_timing: id 3 | task 4012 | n_gen = 146, tg = 13.45 t/s, tg_3s = 15.27 t/s 6.07.736.081 I slot print_timing: id 3 | task 4012 | prompt eval time = 389.81 ms / 118 tokens ( 3.30 ms per token, 302.71 tokens per second) 6.07.736.088 I slot print_timing: id 3 | task 4012 | eval time = 11276.47 ms / 154 tokens ( 73.70 ms per token, 13.57 tokens per second) 6.07.736.089 I slot print_timing: id 3 | task 4012 | total time = 11666.28 ms / 272 tokens 6.07.736.091 I slot print_timing: id 3 | task 4012 | graphs reused = 3294 6.07.736.092 I slot print_timing: id 3 | task 4012 | graph reallocs = 282 / 0 (same size) / (changed size) 6.07.736.153 I slot release: id 3 | task 4012 | stop processing: n_tokens = 1396, truncated = 0 6.07.820.760 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.821 6.07.820.973 I slot launch_slot_: id 3 | task 4173 | processing task, is_child = 0 6.08.407.064 I slot print_timing: id 1 | task 4074 | n_gen = 100, tg = 13.56 t/s, tg_3s = 13.69 t/s 6.08.407.392 I slot print_timing: id 2 | task 4093 | prompt eval time = 515.63 ms / 107 tokens ( 4.82 ms per token, 207.51 tokens per second) 6.08.407.396 I slot print_timing: id 2 | task 4093 | eval time = 5714.67 ms / 82 tokens ( 70.55 ms per token, 14.17 tokens per second) 6.08.407.397 I slot print_timing: id 2 | task 4093 | total time = 6230.30 ms / 189 tokens 6.08.407.398 I slot print_timing: id 2 | task 4093 | graphs reused = 3296 6.08.407.399 I slot print_timing: id 2 | task 4093 | graph reallocs = 283 / 0 (same size) / (changed size) 6.08.407.454 I slot release: id 2 | task 4093 | stop processing: n_tokens = 1313, truncated = 0 6.08.513.313 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.873 6.08.513.502 I slot launch_slot_: id 2 | task 4180 | processing task, is_child = 0 6.09.910.695 I slot print_timing: id 1 | task 4074 | prompt eval time = 498.81 ms / 170 tokens ( 2.93 ms per token, 340.81 tokens per second) 6.09.910.702 I slot print_timing: id 1 | task 4074 | eval time = 8806.08 ms / 117 tokens ( 75.91 ms per token, 13.17 tokens per second) 6.09.910.703 I slot print_timing: id 1 | task 4074 | total time = 9304.89 ms / 287 tokens 6.09.910.704 I slot print_timing: id 1 | task 4074 | graphs reused = 3309 6.09.910.705 I slot print_timing: id 1 | task 4074 | graph reallocs = 284 / 0 (same size) / (changed size) 6.09.910.778 I slot release: id 1 | task 4074 | stop processing: n_tokens = 1411, truncated = 0 6.10.020.528 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.928 (> 0.100 thold), f_keep = 0.812 6.10.020.691 I slot launch_slot_: id 1 | task 4198 | processing task, is_child = 0 6.11.734.992 I slot print_timing: id 0 | task 4116 | n_gen = 100, tg = 13.47 t/s, tg_3s = 13.61 t/s 6.12.917.339 I slot print_timing: id 3 | task 4173 | prompt eval time = 394.58 ms / 109 tokens ( 3.62 ms per token, 276.24 tokens per second) 6.12.917.346 I slot print_timing: id 3 | task 4173 | eval time = 4701.76 ms / 63 tokens ( 75.83 ms per token, 13.19 tokens per second) 6.12.917.347 I slot print_timing: id 3 | task 4173 | total time = 5096.34 ms / 172 tokens 6.12.917.348 I slot print_timing: id 3 | task 4173 | graphs reused = 3347 6.12.917.349 I slot print_timing: id 3 | task 4173 | graph reallocs = 289 / 0 (same size) / (changed size) 6.12.917.403 I slot release: id 3 | task 4173 | stop processing: n_tokens = 1296, truncated = 0 6.12.999.531 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.910 (> 0.100 thold), f_keep = 0.884 6.12.999.743 I slot launch_slot_: id 3 | task 4241 | processing task, is_child = 0 6.14.764.640 I slot print_timing: id 0 | task 4116 | n_gen = 144, tg = 13.78 t/s, tg_3s = 14.52 t/s 6.14.825.871 I slot print_timing: id 0 | task 4116 | prompt eval time = 416.94 ms / 147 tokens ( 2.84 ms per token, 352.57 tokens per second) 6.14.825.877 I slot print_timing: id 0 | task 4116 | eval time = 10440.49 ms / 145 tokens ( 72.50 ms per token, 13.79 tokens per second) 6.14.825.878 I slot print_timing: id 0 | task 4116 | total time = 10857.43 ms / 292 tokens 6.14.825.879 I slot print_timing: id 0 | task 4116 | graphs reused = 3369 6.14.825.880 I slot print_timing: id 0 | task 4116 | graph reallocs = 290 / 0 (same size) / (changed size) 6.14.825.935 I slot release: id 0 | task 4116 | stop processing: n_tokens = 1416, truncated = 0 6.14.907.569 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 6.14.907.750 I slot launch_slot_: id 0 | task 4268 | processing task, is_child = 0 6.16.182.886 I slot print_timing: id 2 | task 4180 | n_gen = 100, tg = 13.85 t/s, tg_3s = 13.99 t/s 6.16.929.391 I slot print_timing: id 1 | task 4198 | prompt eval time = 470.62 ms / 110 tokens ( 4.28 ms per token, 233.73 tokens per second) 6.16.929.397 I slot print_timing: id 1 | task 4198 | eval time = 6438.06 ms / 95 tokens ( 68.49 ms per token, 14.60 tokens per second) 6.16.929.398 I slot print_timing: id 1 | task 4198 | total time = 6908.68 ms / 205 tokens 6.16.929.399 I slot print_timing: id 1 | task 4198 | graphs reused = 3395 6.16.929.400 I slot print_timing: id 1 | task 4198 | graph reallocs = 292 / 0 (same size) / (changed size) 6.16.929.453 I slot release: id 1 | task 4198 | stop processing: n_tokens = 1329, truncated = 0 6.17.036.891 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.862 6.17.037.053 I slot launch_slot_: id 1 | task 4298 | processing task, is_child = 0 6.19.243.456 I slot print_timing: id 2 | task 4180 | n_gen = 143, tg = 13.91 t/s, tg_3s = 14.05 t/s 6.20.240.784 I slot print_timing: id 3 | task 4241 | n_gen = 100, tg = 14.45 t/s, tg_3s = 14.60 t/s 6.21.851.726 I slot print_timing: id 0 | task 4268 | n_gen = 100, tg = 15.12 t/s, tg_3s = 15.27 t/s 6.21.852.253 I slot print_timing: id 2 | task 4180 | prompt eval time = 522.74 ms / 139 tokens ( 3.76 ms per token, 265.91 tokens per second) 6.21.852.257 I slot print_timing: id 2 | task 4180 | eval time = 12816.00 ms / 185 tokens ( 69.65 ms per token, 14.36 tokens per second) 6.21.852.258 I slot print_timing: id 2 | task 4180 | total time = 13338.74 ms / 324 tokens 6.21.852.259 I slot print_timing: id 2 | task 4180 | graphs reused = 3464 6.21.852.260 I slot print_timing: id 2 | task 4180 | graph reallocs = 295 / 0 (same size) / (changed size) 6.21.852.315 I slot release: id 2 | task 4180 | stop processing: n_tokens = 1448, truncated = 0 6.21.958.473 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.927 (> 0.100 thold), f_keep = 0.791 6.21.958.658 I slot launch_slot_: id 2 | task 4372 | processing task, is_child = 0 6.23.243.945 I slot print_timing: id 3 | task 4241 | n_gen = 141, tg = 14.21 t/s, tg_3s = 13.65 t/s 6.23.616.989 I slot print_timing: id 1 | task 4298 | prompt eval time = 464.91 ms / 96 tokens ( 4.84 ms per token, 206.49 tokens per second) 6.23.616.995 I slot print_timing: id 1 | task 4298 | eval time = 6115.00 ms / 92 tokens ( 67.20 ms per token, 14.88 tokens per second) 6.23.616.996 I slot print_timing: id 1 | task 4298 | total time = 6579.91 ms / 188 tokens 6.23.616.997 I slot print_timing: id 1 | task 4298 | graphs reused = 3481 6.23.616.997 I slot print_timing: id 1 | task 4298 | graph reallocs = 296 / 0 (same size) / (changed size) 6.23.617.056 I slot release: id 1 | task 4298 | stop processing: n_tokens = 1312, truncated = 0 6.23.728.929 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.935 (> 0.100 thold), f_keep = 0.873 6.23.729.095 I slot launch_slot_: id 1 | task 4394 | processing task, is_child = 0 6.24.606.259 I slot print_timing: id 0 | task 4268 | prompt eval time = 395.52 ms / 122 tokens ( 3.24 ms per token, 308.46 tokens per second) 6.24.606.265 I slot print_timing: id 0 | task 4268 | eval time = 9302.97 ms / 130 tokens ( 72.12 ms per token, 13.87 tokens per second) 6.24.606.266 I slot print_timing: id 0 | task 4268 | total time = 9698.49 ms / 252 tokens 6.24.606.268 I slot print_timing: id 0 | task 4268 | graphs reused = 3486 6.24.606.269 I slot print_timing: id 0 | task 4268 | graph reallocs = 299 / 0 (same size) / (changed size) 6.24.606.325 I slot release: id 0 | task 4268 | stop processing: n_tokens = 1376, truncated = 0 6.24.690.634 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.929 (> 0.100 thold), f_keep = 0.833 6.24.690.813 I slot launch_slot_: id 0 | task 4404 | processing task, is_child = 0 6.25.949.869 I slot print_timing: id 3 | task 4241 | prompt eval time = 390.76 ms / 134 tokens ( 2.92 ms per token, 342.92 tokens per second) 6.25.949.875 I slot print_timing: id 3 | task 4241 | eval time = 12559.34 ms / 172 tokens ( 73.45 ms per token, 13.62 tokens per second) 6.25.949.876 I slot print_timing: id 3 | task 4241 | total time = 12950.10 ms / 306 tokens 6.25.949.877 I slot print_timing: id 3 | task 4241 | graphs reused = 3499 6.25.949.878 I slot print_timing: id 3 | task 4241 | graph reallocs = 301 / 0 (same size) / (changed size) 6.25.949.934 I slot release: id 3 | task 4241 | stop processing: n_tokens = 1430, truncated = 0 6.26.033.127 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.801 6.26.033.293 I slot launch_slot_: id 3 | task 4421 | processing task, is_child = 0 6.29.794.166 I slot print_timing: id 2 | task 4372 | n_gen = 100, tg = 13.55 t/s, tg_3s = 13.69 t/s 6.29.858.381 I slot print_timing: id 2 | task 4372 | prompt eval time = 528.56 ms / 111 tokens ( 4.76 ms per token, 210.01 tokens per second) 6.29.858.387 I slot print_timing: id 2 | task 4372 | eval time = 7371.14 ms / 101 tokens ( 73.71 ms per token, 13.57 tokens per second) 6.29.858.389 I slot print_timing: id 2 | task 4372 | total time = 7899.70 ms / 212 tokens 6.29.858.389 I slot print_timing: id 2 | task 4372 | graphs reused = 3552 6.29.858.390 I slot print_timing: id 2 | task 4372 | graph reallocs = 302 / 0 (same size) / (changed size) 6.29.858.444 I slot release: id 2 | task 4372 | stop processing: n_tokens = 1336, truncated = 0 6.29.967.986 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 6.29.968.168 I slot launch_slot_: id 2 | task 4479 | processing task, is_child = 0 6.31.429.872 I slot print_timing: id 1 | task 4394 | prompt eval time = 488.43 ms / 101 tokens ( 4.84 ms per token, 206.79 tokens per second) 6.31.429.879 I slot print_timing: id 1 | task 4394 | eval time = 7212.33 ms / 98 tokens ( 74.35 ms per token, 13.45 tokens per second) 6.31.429.880 I slot print_timing: id 1 | task 4394 | total time = 7700.75 ms / 199 tokens 6.31.429.882 I slot print_timing: id 1 | task 4394 | graphs reused = 3566 6.31.429.883 I slot print_timing: id 1 | task 4394 | graph reallocs = 303 / 0 (same size) / (changed size) 6.31.429.951 I slot release: id 1 | task 4394 | stop processing: n_tokens = 1323, truncated = 0 6.31.537.658 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.915 (> 0.100 thold), f_keep = 0.866 6.31.537.828 I slot launch_slot_: id 1 | task 4498 | processing task, is_child = 0 6.32.527.102 I slot print_timing: id 0 | task 4404 | n_gen = 100, tg = 13.34 t/s, tg_3s = 13.47 t/s 6.33.548.367 I slot print_timing: id 3 | task 4421 | n_gen = 100, tg = 13.93 t/s, tg_3s = 14.07 t/s 6.34.117.794 I slot print_timing: id 0 | task 4404 | prompt eval time = 413.86 ms / 108 tokens ( 3.83 ms per token, 260.96 tokens per second) 6.34.117.801 I slot print_timing: id 0 | task 4404 | eval time = 9013.10 ms / 125 tokens ( 72.69 ms per token, 13.76 tokens per second) 6.34.117.802 I slot print_timing: id 0 | task 4404 | total time = 9426.96 ms / 233 tokens 6.34.117.803 I slot print_timing: id 0 | task 4404 | graphs reused = 3598 6.34.117.805 I slot print_timing: id 0 | task 4404 | graph reallocs = 306 / 0 (same size) / (changed size) 6.34.117.870 I slot release: id 0 | task 4404 | stop processing: n_tokens = 1357, truncated = 0 6.34.202.095 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.845 6.34.202.282 I slot launch_slot_: id 0 | task 4535 | processing task, is_child = 0 6.35.545.037 I slot print_timing: id 1 | task 4498 | prompt eval time = 473.99 ms / 128 tokens ( 3.70 ms per token, 270.05 tokens per second) 6.35.545.044 I slot print_timing: id 1 | task 4498 | eval time = 3533.20 ms / 52 tokens ( 69.28 ms per token, 14.43 tokens per second) 6.35.545.045 I slot print_timing: id 1 | task 4498 | total time = 4007.19 ms / 180 tokens 6.35.545.046 I slot print_timing: id 1 | task 4498 | graphs reused = 3613 6.35.545.047 I slot print_timing: id 1 | task 4498 | graph reallocs = 308 / 0 (same size) / (changed size) 6.35.545.103 I slot release: id 1 | task 4498 | stop processing: n_tokens = 1304, truncated = 0 6.35.652.402 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.904 (> 0.100 thold), f_keep = 0.879 6.35.652.616 I slot launch_slot_: id 1 | task 4554 | processing task, is_child = 0 6.36.584.294 I slot print_timing: id 3 | task 4421 | n_gen = 137, tg = 13.41 t/s, tg_3s = 12.19 t/s 6.37.466.588 I slot print_timing: id 3 | task 4421 | prompt eval time = 408.50 ms / 166 tokens ( 2.46 ms per token, 406.36 tokens per second) 6.37.466.595 I slot print_timing: id 3 | task 4421 | eval time = 11024.77 ms / 151 tokens ( 73.50 ms per token, 13.61 tokens per second) 6.37.466.596 I slot print_timing: id 3 | task 4421 | total time = 11433.27 ms / 317 tokens 6.37.466.597 I slot print_timing: id 3 | task 4421 | graphs reused = 3633 6.37.466.598 I slot print_timing: id 3 | task 4421 | graph reallocs = 311 / 0 (same size) / (changed size) 6.37.466.656 I slot release: id 3 | task 4421 | stop processing: n_tokens = 1441, truncated = 0 6.37.550.477 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.939 (> 0.100 thold), f_keep = 0.795 6.37.550.652 I slot launch_slot_: id 3 | task 4579 | processing task, is_child = 0 6.38.075.744 I slot print_timing: id 2 | task 4479 | prompt eval time = 526.79 ms / 110 tokens ( 4.79 ms per token, 208.81 tokens per second) 6.38.075.750 I slot print_timing: id 2 | task 4479 | eval time = 7580.77 ms / 99 tokens ( 77.35 ms per token, 12.93 tokens per second) 6.38.075.751 I slot print_timing: id 2 | task 4479 | total time = 8107.56 ms / 209 tokens 6.38.075.752 I slot print_timing: id 2 | task 4479 | graphs reused = 3634 6.38.075.753 I slot print_timing: id 2 | task 4479 | graph reallocs = 312 / 0 (same size) / (changed size) 6.38.075.808 I slot release: id 2 | task 4479 | stop processing: n_tokens = 1333, truncated = 0 6.41.088.269 I slot print_timing: id 0 | task 4535 | prompt eval time = 401.05 ms / 95 tokens ( 4.22 ms per token, 236.88 tokens per second) 6.41.088.276 I slot print_timing: id 0 | task 4535 | eval time = 6484.91 ms / 73 tokens ( 90.07 ms per token, 11.10 tokens per second) 6.41.088.277 I slot print_timing: id 0 | task 4535 | total time = 6885.96 ms / 168 tokens 6.41.088.280 I slot print_timing: id 0 | task 4535 | graphs reused = 3634 6.41.088.281 I slot print_timing: id 0 | task 4535 | graph reallocs = 312 / 0 (same size) / (changed size) 6.41.088.337 I slot release: id 0 | task 4535 | stop processing: n_tokens = 1292, truncated = 0 6.45.216.125 I slot print_timing: id 1 | task 4554 | prompt eval time = 480.16 ms / 142 tokens ( 3.38 ms per token, 295.74 tokens per second) 6.45.216.131 I slot print_timing: id 1 | task 4554 | eval time = 9083.33 ms / 96 tokens ( 95.61 ms per token, 10.46 tokens per second) 6.45.216.132 I slot print_timing: id 1 | task 4554 | total time = 9563.48 ms / 238 tokens 6.45.216.133 I slot print_timing: id 1 | task 4554 | graphs reused = 3634 6.45.216.133 I slot print_timing: id 1 | task 4554 | graph reallocs = 313 / 0 (same size) / (changed size) 6.45.216.185 I slot release: id 1 | task 4554 | stop processing: n_tokens = 1362, truncated = 0 6.45.797.760 I slot print_timing: id 3 | task 4579 | prompt eval time = 393.55 ms / 96 tokens ( 4.10 ms per token, 243.94 tokens per second) 6.45.797.767 I slot print_timing: id 3 | task 4579 | eval time = 7853.54 ms / 84 tokens ( 94.62 ms per token, 10.57 tokens per second) 6.45.797.768 I slot print_timing: id 3 | task 4579 | total time = 8247.08 ms / 180 tokens 6.45.797.769 I slot print_timing: id 3 | task 4579 | graphs reused = 3646 6.45.797.770 I slot print_timing: id 3 | task 4579 | graph reallocs = 313 / 0 (same size) / (changed size) 6.45.797.827 I slot release: id 3 | task 4579 | stop processing: n_tokens = 1304, truncated = 0 6.45.823.138 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1333, t_last = 397983429 6.45.823.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 6.45.825.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.912 MiB) 6.45.828.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 6.45.888.194 I slot launch_slot_: id 2 | task 4665 | processing task, is_child = 0 6.45.888.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.005 MiB) 6.45.891.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.162 MiB) 6.45.895.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 6.45.950.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 6.45.954.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 6.45.957.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 6.46.008.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 6.46.010.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.504 MiB) 6.46.011.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 6.46.062.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1292, t_last = 400995959 6.46.063.099 I slot launch_slot_: id 0 | task 4666 | processing task, is_child = 0 6.46.063.251 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1362, t_last = 405123807 6.46.063.424 I slot launch_slot_: id 1 | task 4667 | processing task, is_child = 0 6.46.063.499 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1304, t_last = 405705449 6.46.063.664 I slot launch_slot_: id 3 | task 4668 | processing task, is_child = 0 6.49.678.997 I slot print_timing: id 0 | task 4666 | prompt processing, n_tokens = 802, progress = 1.00, t = 3.61 s / 221.88 tokens per second 6.49.689.464 I slot print_timing: id 1 | task 4667 | prompt processing, n_tokens = 983, progress = 1.00, t = 3.61 s / 272.23 tokens per second 6.49.700.612 I slot print_timing: id 3 | task 4668 | prompt processing, n_tokens = 948, progress = 1.00, t = 3.60 s / 263.07 tokens per second 6.49.925.291 I slot print_timing: id 2 | task 4665 | prompt eval time = 3607.96 ms / 779 tokens ( 4.63 ms per token, 215.91 tokens per second) 6.49.925.298 I slot print_timing: id 2 | task 4665 | eval time = 246.31 ms / 2 tokens ( 246.31 ms per token, 4.06 tokens per second) 6.49.925.300 I slot print_timing: id 2 | task 4665 | total time = 3854.27 ms / 781 tokens 6.49.925.302 I slot print_timing: id 2 | task 4665 | graphs reused = 3646 6.49.925.303 I slot print_timing: id 2 | task 4665 | graph reallocs = 316 / 0 (same size) / (changed size) 6.49.925.356 I slot release: id 2 | task 4665 | stop processing: n_tokens = 780, truncated = 0 6.50.039.525 I slot print_timing: id 0 | task 4666 | prompt eval time = 3860.55 ms / 806 tokens ( 4.79 ms per token, 208.78 tokens per second) 6.50.039.531 I slot print_timing: id 0 | task 4666 | eval time = 115.29 ms / 2 tokens ( 115.29 ms per token, 8.67 tokens per second) 6.50.039.532 I slot print_timing: id 0 | task 4666 | total time = 3975.84 ms / 808 tokens 6.50.039.533 I slot print_timing: id 0 | task 4666 | graphs reused = 3646 6.50.039.534 I slot print_timing: id 0 | task 4666 | graph reallocs = 317 / 0 (same size) / (changed size) 6.50.039.578 I slot release: id 0 | task 4666 | stop processing: n_tokens = 807, truncated = 0 6.50.039.891 I slot print_timing: id 1 | task 4667 | prompt eval time = 3857.60 ms / 987 tokens ( 3.91 ms per token, 255.86 tokens per second) 6.50.039.894 I slot print_timing: id 1 | task 4667 | eval time = 114.95 ms / 2 tokens ( 114.95 ms per token, 8.70 tokens per second) 6.50.039.895 I slot print_timing: id 1 | task 4667 | total time = 3972.55 ms / 989 tokens 6.50.039.896 I slot print_timing: id 1 | task 4667 | graphs reused = 3646 6.50.039.896 I slot print_timing: id 1 | task 4667 | graph reallocs = 317 / 0 (same size) / (changed size) 6.50.039.935 I slot release: id 1 | task 4667 | stop processing: n_tokens = 988, truncated = 0 6.50.040.261 I slot print_timing: id 3 | task 4668 | prompt eval time = 3851.52 ms / 952 tokens ( 4.05 ms per token, 247.18 tokens per second) 6.50.040.265 I slot print_timing: id 3 | task 4668 | eval time = 114.14 ms / 2 tokens ( 114.14 ms per token, 8.76 tokens per second) 6.50.040.266 I slot print_timing: id 3 | task 4668 | total time = 3965.66 ms / 954 tokens 6.50.040.266 I slot print_timing: id 3 | task 4668 | graphs reused = 3646 6.50.040.267 I slot print_timing: id 3 | task 4668 | graph reallocs = 317 / 0 (same size) / (changed size) 6.50.040.304 I slot release: id 3 | task 4668 | stop processing: n_tokens = 953, truncated = 0 6.50.040.319 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 409832978 6.50.040.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.567 MiB) 6.50.043.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.568 MiB) 6.50.094.486 I slot launch_slot_: id 2 | task 4676 | processing task, is_child = 0 6.50.094.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 6.50.097.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 6.50.100.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 6.50.155.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 6.50.159.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.161 MiB) 6.50.212.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 6.50.215.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.598 MiB) 6.50.218.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.379 MiB) 6.50.270.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 409947200 6.50.271.021 I slot launch_slot_: id 0 | task 4677 | processing task, is_child = 0 6.50.271.140 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 409947556 6.50.271.298 I slot launch_slot_: id 1 | task 4678 | processing task, is_child = 0 6.50.271.358 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 409947926 6.50.271.501 I slot launch_slot_: id 3 | task 4679 | processing task, is_child = 0 6.53.414.282 I slot print_timing: id 0 | task 4677 | prompt eval time = 3078.19 ms / 804 tokens ( 3.83 ms per token, 261.19 tokens per second) 6.53.414.287 I slot print_timing: id 0 | task 4677 | eval time = 64.57 ms / 2 tokens ( 64.57 ms per token, 15.49 tokens per second) 6.53.414.288 I slot print_timing: id 0 | task 4677 | total time = 3142.76 ms / 806 tokens 6.53.414.289 I slot print_timing: id 0 | task 4677 | graphs reused = 3646 6.53.414.290 I slot print_timing: id 0 | task 4677 | graph reallocs = 322 / 0 (same size) / (changed size) 6.53.414.337 I slot release: id 0 | task 4677 | stop processing: n_tokens = 805, truncated = 0 6.53.414.733 I slot print_timing: id 1 | task 4678 | prompt eval time = 3075.19 ms / 855 tokens ( 3.60 ms per token, 278.03 tokens per second) 6.53.414.738 I slot print_timing: id 1 | task 4678 | eval time = 64.36 ms / 2 tokens ( 64.36 ms per token, 15.54 tokens per second) 6.53.414.739 I slot print_timing: id 1 | task 4678 | total time = 3139.55 ms / 857 tokens 6.53.414.740 I slot print_timing: id 1 | task 4678 | graphs reused = 3646 6.53.414.741 I slot print_timing: id 1 | task 4678 | graph reallocs = 322 / 0 (same size) / (changed size) 6.53.414.783 I slot release: id 1 | task 4678 | stop processing: n_tokens = 856, truncated = 0 6.53.415.171 I slot print_timing: id 2 | task 4676 | prompt eval time = 3072.12 ms / 801 tokens ( 3.84 ms per token, 260.73 tokens per second) 6.53.415.177 I slot print_timing: id 2 | task 4676 | eval time = 64.25 ms / 2 tokens ( 64.25 ms per token, 15.56 tokens per second) 6.53.415.178 I slot print_timing: id 2 | task 4676 | total time = 3136.36 ms / 803 tokens 6.53.415.179 I slot print_timing: id 2 | task 4676 | graphs reused = 3646 6.53.415.180 I slot print_timing: id 2 | task 4676 | graph reallocs = 322 / 0 (same size) / (changed size) 6.53.415.212 I slot release: id 2 | task 4676 | stop processing: n_tokens = 802, truncated = 0 6.53.415.569 I slot print_timing: id 3 | task 4679 | prompt eval time = 3069.15 ms / 846 tokens ( 3.63 ms per token, 275.65 tokens per second) 6.53.415.573 I slot print_timing: id 3 | task 4679 | eval time = 64.10 ms / 2 tokens ( 64.10 ms per token, 15.60 tokens per second) 6.53.415.574 I slot print_timing: id 3 | task 4679 | total time = 3133.25 ms / 848 tokens 6.53.415.575 I slot print_timing: id 3 | task 4679 | graphs reused = 3646 6.53.415.576 I slot print_timing: id 3 | task 4679 | graph reallocs = 322 / 0 (same size) / (changed size) 6.53.415.609 I slot release: id 3 | task 4679 | stop processing: n_tokens = 847, truncated = 0 6.53.429.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 805, t_last = 413321959 6.53.429.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.286 MiB) 6.53.432.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.536 MiB) 6.53.434.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.724 MiB) 6.53.489.708 I slot launch_slot_: id 0 | task 4687 | processing task, is_child = 0 6.53.489.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 6.53.492.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 6.53.547.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.910 MiB) 6.53.550.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.942 MiB) 6.53.553.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.130 MiB) 6.53.606.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.317 MiB) 6.53.608.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.754 MiB) 6.53.610.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.160 MiB) 6.53.660.997 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 413322405 6.53.661.206 I slot launch_slot_: id 1 | task 4688 | processing task, is_child = 0 6.53.661.313 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.903 6.53.661.412 I slot launch_slot_: id 2 | task 4689 | processing task, is_child = 0 6.53.661.471 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 413323230 6.53.661.617 I slot launch_slot_: id 3 | task 4690 | processing task, is_child = 0 6.55.435.314 I slot print_timing: id 2 | task 4689 | prompt eval time = 1271.05 ms / 129 tokens ( 9.85 ms per token, 101.49 tokens per second) 6.55.435.320 I slot print_timing: id 2 | task 4689 | eval time = 495.34 ms / 2 tokens ( 495.34 ms per token, 2.02 tokens per second) 6.55.435.321 I slot print_timing: id 2 | task 4689 | total time = 1766.39 ms / 131 tokens 6.55.435.322 I slot print_timing: id 2 | task 4689 | graphs reused = 3646 6.55.435.323 I slot print_timing: id 2 | task 4689 | graph reallocs = 322 / 0 (same size) / (changed size) 6.55.435.370 I slot release: id 2 | task 4689 | stop processing: n_tokens = 826, truncated = 0 6.56.087.137 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 415342991 6.56.087.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.723 MiB) 6.56.089.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 6.56.168.384 I slot launch_slot_: id 2 | task 4695 | processing task, is_child = 0 6.56.777.441 I slot print_timing: id 0 | task 4687 | prompt processing, n_tokens = 892, progress = 1.00, t = 3.12 s / 286.28 tokens per second 6.56.798.960 I slot print_timing: id 1 | task 4688 | prompt processing, n_tokens = 959, progress = 1.00, t = 3.11 s / 308.15 tokens per second 6.56.820.461 I slot print_timing: id 3 | task 4690 | prompt processing, n_tokens = 876, progress = 1.00, t = 3.09 s / 283.53 tokens per second 6.57.387.461 I slot print_timing: id 0 | task 4687 | prompt eval time = 3462.55 ms / 896 tokens ( 3.86 ms per token, 258.77 tokens per second) 6.57.387.468 I slot print_timing: id 0 | task 4687 | eval time = 263.27 ms / 2 tokens ( 263.27 ms per token, 3.80 tokens per second) 6.57.387.469 I slot print_timing: id 0 | task 4687 | total time = 3725.82 ms / 898 tokens 6.57.387.472 I slot print_timing: id 0 | task 4687 | graphs reused = 3646 6.57.387.473 I slot print_timing: id 0 | task 4687 | graph reallocs = 324 / 0 (same size) / (changed size) 6.57.387.541 I slot release: id 0 | task 4687 | stop processing: n_tokens = 897, truncated = 0 6.57.387.853 I slot print_timing: id 1 | task 4688 | prompt eval time = 3459.56 ms / 963 tokens ( 3.59 ms per token, 278.36 tokens per second) 6.57.387.857 I slot print_timing: id 1 | task 4688 | eval time = 262.99 ms / 2 tokens ( 262.99 ms per token, 3.80 tokens per second) 6.57.387.858 I slot print_timing: id 1 | task 4688 | total time = 3722.55 ms / 965 tokens 6.57.387.859 I slot print_timing: id 1 | task 4688 | graphs reused = 3646 6.57.387.860 I slot print_timing: id 1 | task 4688 | graph reallocs = 324 / 0 (same size) / (changed size) 6.57.387.908 I slot release: id 1 | task 4688 | stop processing: n_tokens = 964, truncated = 0 6.57.388.234 I slot print_timing: id 3 | task 4690 | prompt eval time = 3437.79 ms / 880 tokens ( 3.91 ms per token, 255.98 tokens per second) 6.57.388.238 I slot print_timing: id 3 | task 4690 | eval time = 262.69 ms / 2 tokens ( 262.69 ms per token, 3.81 tokens per second) 6.57.388.239 I slot print_timing: id 3 | task 4690 | total time = 3700.49 ms / 882 tokens 6.57.388.240 I slot print_timing: id 3 | task 4690 | graphs reused = 3646 6.57.388.241 I slot print_timing: id 3 | task 4690 | graph reallocs = 324 / 0 (same size) / (changed size) 6.57.388.276 I slot release: id 3 | task 4690 | stop processing: n_tokens = 881, truncated = 0 6.57.532.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 417295165 6.57.532.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 6.57.535.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.192 MiB) 6.57.537.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 6.57.611.728 I slot launch_slot_: id 0 | task 4700 | processing task, is_child = 0 6.57.611.800 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.442 MiB) 6.57.614.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.192 MiB) 6.57.617.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.349 MiB) 6.57.671.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 6.57.674.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.536 MiB) 6.57.730.163 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 964, t_last = 417295531 6.57.730.385 I slot launch_slot_: id 1 | task 4701 | processing task, is_child = 0 6.57.730.446 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 417295898 6.57.730.603 I slot launch_slot_: id 3 | task 4702 | processing task, is_child = 0 6.59.347.313 I slot print_timing: id 2 | task 4695 | prompt eval time = 2597.52 ms / 987 tokens ( 2.63 ms per token, 379.98 tokens per second) 6.59.347.320 I slot print_timing: id 2 | task 4695 | eval time = 557.38 ms / 2 tokens ( 557.38 ms per token, 1.79 tokens per second) 6.59.347.321 I slot print_timing: id 2 | task 4695 | total time = 3154.90 ms / 989 tokens 6.59.347.322 I slot print_timing: id 2 | task 4695 | graphs reused = 3646 6.59.347.324 I slot print_timing: id 2 | task 4695 | graph reallocs = 327 / 0 (same size) / (changed size) 6.59.347.381 I slot release: id 2 | task 4695 | stop processing: n_tokens = 988, truncated = 0 7.00.050.470 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 988, t_last = 419255002 7.00.050.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.318 MiB) 7.00.054.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.098 MiB) 7.00.057.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.722 MiB) 7.00.117.147 I slot launch_slot_: id 2 | task 4707 | processing task, is_child = 0 7.00.912.288 I slot print_timing: id 0 | task 4700 | prompt processing, n_tokens = 1776, progress = 1.00, t = 3.18 s / 558.20 tokens per second 7.00.933.957 I slot print_timing: id 1 | task 4701 | prompt processing, n_tokens = 920, progress = 1.00, t = 3.18 s / 289.49 tokens per second 7.00.956.358 I slot print_timing: id 3 | task 4702 | prompt processing, n_tokens = 1018, progress = 1.00, t = 3.16 s / 321.91 tokens per second 7.01.531.638 I slot print_timing: id 0 | task 4700 | prompt eval time = 3519.31 ms / 1780 tokens ( 1.98 ms per token, 505.78 tokens per second) 7.01.531.644 I slot print_timing: id 0 | task 4700 | eval time = 281.70 ms / 2 tokens ( 281.70 ms per token, 3.55 tokens per second) 7.01.531.645 I slot print_timing: id 0 | task 4700 | total time = 3801.01 ms / 1782 tokens 7.01.531.647 I slot print_timing: id 0 | task 4700 | graphs reused = 3646 7.01.531.648 I slot print_timing: id 0 | task 4700 | graph reallocs = 333 / 0 (same size) / (changed size) 7.01.531.735 I slot release: id 0 | task 4700 | stop processing: n_tokens = 1781, truncated = 0 7.01.532.203 I slot print_timing: id 1 | task 4701 | prompt eval time = 3516.21 ms / 924 tokens ( 3.81 ms per token, 262.78 tokens per second) 7.01.532.206 I slot print_timing: id 1 | task 4701 | eval time = 281.71 ms / 2 tokens ( 281.71 ms per token, 3.55 tokens per second) 7.01.532.207 I slot print_timing: id 1 | task 4701 | total time = 3797.92 ms / 926 tokens 7.01.532.208 I slot print_timing: id 1 | task 4701 | graphs reused = 3646 7.01.532.208 I slot print_timing: id 1 | task 4701 | graph reallocs = 333 / 0 (same size) / (changed size) 7.01.532.246 I slot release: id 1 | task 4701 | stop processing: n_tokens = 925, truncated = 0 7.01.532.553 I slot print_timing: id 3 | task 4702 | prompt eval time = 3501.13 ms / 1022 tokens ( 3.43 ms per token, 291.91 tokens per second) 7.01.532.558 I slot print_timing: id 3 | task 4702 | eval time = 281.49 ms / 2 tokens ( 281.49 ms per token, 3.55 tokens per second) 7.01.532.559 I slot print_timing: id 3 | task 4702 | total time = 3782.62 ms / 1024 tokens 7.01.532.561 I slot print_timing: id 3 | task 4702 | graphs reused = 3646 7.01.532.562 I slot print_timing: id 3 | task 4702 | graph reallocs = 333 / 0 (same size) / (changed size) 7.01.532.605 I slot release: id 3 | task 4702 | stop processing: n_tokens = 1023, truncated = 0 7.01.675.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1781, t_last = 421439357 7.01.675.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.973 MiB) 7.01.678.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 7.01.681.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.661 MiB) 7.01.738.671 I slot launch_slot_: id 0 | task 4712 | processing task, is_child = 0 7.01.738.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.473 MiB) 7.01.741.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.442 MiB) 7.01.743.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.348 MiB) 7.01.799.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.817 MiB) 7.01.801.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.848 MiB) 7.01.852.415 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 925, t_last = 421439868 7.01.852.651 I slot launch_slot_: id 1 | task 4713 | processing task, is_child = 0 7.01.852.717 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1023, t_last = 421440228 7.01.852.902 I slot launch_slot_: id 3 | task 4714 | processing task, is_child = 0 7.03.667.270 I slot print_timing: id 2 | task 4707 | prompt eval time = 2906.61 ms / 937 tokens ( 3.10 ms per token, 322.37 tokens per second) 7.03.667.275 I slot print_timing: id 2 | task 4707 | eval time = 619.11 ms / 2 tokens ( 619.11 ms per token, 1.62 tokens per second) 7.03.667.277 I slot print_timing: id 2 | task 4707 | total time = 3525.72 ms / 939 tokens 7.03.667.278 I slot print_timing: id 2 | task 4707 | graphs reused = 3646 7.03.667.278 I slot print_timing: id 2 | task 4707 | graph reallocs = 337 / 0 (same size) / (changed size) 7.03.667.333 I slot release: id 2 | task 4707 | stop processing: n_tokens = 938, truncated = 0 7.04.171.919 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 938, t_last = 423574954 7.04.172.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.474 MiB) 7.04.175.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.911 MiB) 7.04.179.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.786 MiB) 7.04.231.844 I slot launch_slot_: id 2 | task 4719 | processing task, is_child = 0 7.05.023.248 I slot print_timing: id 1 | task 4713 | prompt eval time = 2842.23 ms / 741 tokens ( 3.84 ms per token, 260.71 tokens per second) 7.05.023.254 I slot print_timing: id 1 | task 4713 | eval time = 324.12 ms / 2 tokens ( 324.12 ms per token, 3.09 tokens per second) 7.05.023.255 I slot print_timing: id 1 | task 4713 | total time = 3166.36 ms / 743 tokens 7.05.023.256 I slot print_timing: id 1 | task 4713 | graphs reused = 3646 7.05.023.257 I slot print_timing: id 1 | task 4713 | graph reallocs = 340 / 0 (same size) / (changed size) 7.05.023.304 I slot release: id 1 | task 4713 | stop processing: n_tokens = 742, truncated = 0 7.05.023.699 I slot print_timing: id 3 | task 4714 | prompt eval time = 2827.43 ms / 713 tokens ( 3.97 ms per token, 252.17 tokens per second) 7.05.023.704 I slot print_timing: id 3 | task 4714 | eval time = 323.84 ms / 2 tokens ( 323.84 ms per token, 3.09 tokens per second) 7.05.023.705 I slot print_timing: id 3 | task 4714 | total time = 3151.27 ms / 715 tokens 7.05.023.706 I slot print_timing: id 3 | task 4714 | graphs reused = 3646 7.05.023.706 I slot print_timing: id 3 | task 4714 | graph reallocs = 340 / 0 (same size) / (changed size) 7.05.023.742 I slot release: id 3 | task 4714 | stop processing: n_tokens = 714, truncated = 0 7.05.285.264 I slot print_timing: id 0 | task 4712 | prompt eval time = 3170.00 ms / 880 tokens ( 3.60 ms per token, 277.60 tokens per second) 7.05.285.270 I slot print_timing: id 0 | task 4712 | eval time = 262.34 ms / 2 tokens ( 262.34 ms per token, 3.81 tokens per second) 7.05.285.271 I slot print_timing: id 0 | task 4712 | total time = 3432.34 ms / 882 tokens 7.05.285.271 I slot print_timing: id 0 | task 4712 | graphs reused = 3646 7.05.285.272 I slot print_timing: id 0 | task 4712 | graph reallocs = 340 / 0 (same size) / (changed size) 7.05.285.318 I slot release: id 0 | task 4712 | stop processing: n_tokens = 881, truncated = 0 7.05.285.340 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.878 (> 0.100 thold), f_keep = 0.850 7.05.285.536 I slot launch_slot_: id 1 | task 4723 | processing task, is_child = 0 7.05.285.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.285 MiB) 7.05.288.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.754 MiB) 7.05.291.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.692 MiB) 7.05.343.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.380 MiB) 7.05.346.465 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.224 MiB) 7.05.399.399 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 7.05.399.559 I slot launch_slot_: id 3 | task 4724 | processing task, is_child = 0 7.05.399.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 425192940 7.05.399.789 I slot launch_slot_: id 0 | task 4725 | processing task, is_child = 0 7.06.530.471 I slot print_timing: id 1 | task 4723 | prompt eval time = 901.69 ms / 116 tokens ( 7.77 ms per token, 128.65 tokens per second) 7.06.530.477 I slot print_timing: id 1 | task 4723 | eval time = 224.63 ms / 2 tokens ( 224.63 ms per token, 4.45 tokens per second) 7.06.530.478 I slot print_timing: id 1 | task 4723 | total time = 1126.32 ms / 118 tokens 7.06.530.479 I slot print_timing: id 1 | task 4723 | graphs reused = 3646 7.06.530.481 I slot print_timing: id 1 | task 4723 | graph reallocs = 343 / 0 (same size) / (changed size) 7.06.530.530 I slot release: id 1 | task 4723 | stop processing: n_tokens = 720, truncated = 0 7.06.530.941 I slot print_timing: id 2 | task 4719 | prompt eval time = 2045.48 ms / 716 tokens ( 2.86 ms per token, 350.04 tokens per second) 7.06.530.948 I slot print_timing: id 2 | task 4719 | eval time = 224.49 ms / 2 tokens ( 224.49 ms per token, 4.45 tokens per second) 7.06.530.949 I slot print_timing: id 2 | task 4719 | total time = 2269.97 ms / 718 tokens 7.06.530.951 I slot print_timing: id 2 | task 4719 | graphs reused = 3646 7.06.530.952 I slot print_timing: id 2 | task 4719 | graph reallocs = 343 / 0 (same size) / (changed size) 7.06.530.992 I slot release: id 2 | task 4719 | stop processing: n_tokens = 717, truncated = 0 7.06.531.436 I slot print_timing: id 3 | task 4724 | prompt eval time = 871.96 ms / 122 tokens ( 7.15 ms per token, 139.91 tokens per second) 7.06.531.441 I slot print_timing: id 3 | task 4724 | eval time = 224.36 ms / 2 tokens ( 224.36 ms per token, 4.46 tokens per second) 7.06.531.443 I slot print_timing: id 3 | task 4724 | total time = 1096.32 ms / 124 tokens 7.06.531.443 I slot print_timing: id 3 | task 4724 | graphs reused = 3646 7.06.531.444 I slot print_timing: id 3 | task 4724 | graph reallocs = 343 / 0 (same size) / (changed size) 7.06.531.474 I slot release: id 3 | task 4724 | stop processing: n_tokens = 726, truncated = 0 7.06.679.994 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 426438152 7.06.680.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 104.410 MiB) 7.06.683.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 105.036 MiB) 7.06.687.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.471 MiB) 7.06.760.529 I slot launch_slot_: id 1 | task 4730 | processing task, is_child = 0 7.06.760.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.095 MiB) 7.06.821.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.940 MiB) 7.06.871.808 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 426438614 7.06.872.018 I slot launch_slot_: id 2 | task 4731 | processing task, is_child = 0 7.06.872.070 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 426439096 7.06.872.216 I slot launch_slot_: id 3 | task 4732 | processing task, is_child = 0 7.08.380.804 I slot print_timing: id 0 | task 4725 | prompt eval time = 2462.35 ms / 876 tokens ( 2.81 ms per token, 355.76 tokens per second) 7.08.380.810 I slot print_timing: id 0 | task 4725 | eval time = 518.64 ms / 2 tokens ( 518.64 ms per token, 1.93 tokens per second) 7.08.380.811 I slot print_timing: id 0 | task 4725 | total time = 2980.99 ms / 878 tokens 7.08.380.812 I slot print_timing: id 0 | task 4725 | graphs reused = 3646 7.08.380.813 I slot print_timing: id 0 | task 4725 | graph reallocs = 345 / 0 (same size) / (changed size) 7.08.380.860 I slot release: id 0 | task 4725 | stop processing: n_tokens = 877, truncated = 0 7.09.207.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 877, t_last = 428288481 7.09.247.113 I slot launch_slot_: id 0 | task 4737 | processing task, is_child = 0 7.10.462.135 I slot print_timing: id 1 | task 4730 | prompt eval time = 3341.83 ms / 1006 tokens ( 3.32 ms per token, 301.03 tokens per second) 7.10.462.142 I slot print_timing: id 1 | task 4730 | eval time = 235.88 ms / 2 tokens ( 235.88 ms per token, 4.24 tokens per second) 7.10.462.143 I slot print_timing: id 1 | task 4730 | total time = 3577.71 ms / 1008 tokens 7.10.462.144 I slot print_timing: id 1 | task 4730 | graphs reused = 3646 7.10.462.145 I slot print_timing: id 1 | task 4730 | graph reallocs = 347 / 0 (same size) / (changed size) 7.10.462.195 I slot release: id 1 | task 4730 | stop processing: n_tokens = 1007, truncated = 0 7.10.462.592 I slot print_timing: id 2 | task 4731 | prompt eval time = 3338.79 ms / 992 tokens ( 3.37 ms per token, 297.11 tokens per second) 7.10.462.597 I slot print_timing: id 2 | task 4731 | eval time = 235.73 ms / 2 tokens ( 235.73 ms per token, 4.24 tokens per second) 7.10.462.598 I slot print_timing: id 2 | task 4731 | total time = 3574.52 ms / 994 tokens 7.10.462.598 I slot print_timing: id 2 | task 4731 | graphs reused = 3646 7.10.462.599 I slot print_timing: id 2 | task 4731 | graph reallocs = 347 / 0 (same size) / (changed size) 7.10.462.638 I slot release: id 2 | task 4731 | stop processing: n_tokens = 993, truncated = 0 7.10.463.045 I slot print_timing: id 3 | task 4732 | prompt eval time = 3335.71 ms / 1034 tokens ( 3.23 ms per token, 309.98 tokens per second) 7.10.463.051 I slot print_timing: id 3 | task 4732 | eval time = 235.62 ms / 2 tokens ( 235.62 ms per token, 4.24 tokens per second) 7.10.463.052 I slot print_timing: id 3 | task 4732 | total time = 3571.33 ms / 1036 tokens 7.10.463.053 I slot print_timing: id 3 | task 4732 | graphs reused = 3646 7.10.463.054 I slot print_timing: id 3 | task 4732 | graph reallocs = 347 / 0 (same size) / (changed size) 7.10.463.091 I slot release: id 3 | task 4732 | stop processing: n_tokens = 1035, truncated = 0 7.10.607.045 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.895 (> 0.100 thold), f_keep = 0.883 7.10.607.270 I slot launch_slot_: id 1 | task 4742 | processing task, is_child = 0 7.10.607.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.721 MiB) 7.10.674.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.533 MiB) 7.10.734.385 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 993, t_last = 430370260 7.10.734.711 I slot launch_slot_: id 2 | task 4743 | processing task, is_child = 0 7.10.734.819 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1035, t_last = 430370712 7.10.735.085 I slot launch_slot_: id 3 | task 4744 | processing task, is_child = 0 7.12.216.054 I slot print_timing: id 0 | task 4737 | prompt eval time = 2605.00 ms / 999 tokens ( 2.61 ms per token, 383.49 tokens per second) 7.12.216.061 I slot print_timing: id 0 | task 4737 | eval time = 363.91 ms / 2 tokens ( 363.91 ms per token, 2.75 tokens per second) 7.12.216.062 I slot print_timing: id 0 | task 4737 | total time = 2968.91 ms / 1001 tokens 7.12.216.063 I slot print_timing: id 0 | task 4737 | graphs reused = 3646 7.12.216.064 I slot print_timing: id 0 | task 4737 | graph reallocs = 350 / 0 (same size) / (changed size) 7.12.216.117 I slot release: id 0 | task 4737 | stop processing: n_tokens = 1000, truncated = 0 7.12.216.501 I slot print_timing: id 1 | task 4742 | prompt eval time = 1107.17 ms / 132 tokens ( 8.39 ms per token, 119.22 tokens per second) 7.12.216.504 I slot print_timing: id 1 | task 4742 | eval time = 363.71 ms / 2 tokens ( 363.71 ms per token, 2.75 tokens per second) 7.12.216.505 I slot print_timing: id 1 | task 4742 | total time = 1470.88 ms / 134 tokens 7.12.216.505 I slot print_timing: id 1 | task 4742 | graphs reused = 3646 7.12.216.506 I slot print_timing: id 1 | task 4742 | graph reallocs = 350 / 0 (same size) / (changed size) 7.12.216.542 I slot release: id 1 | task 4742 | stop processing: n_tokens = 994, truncated = 0 7.12.792.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1000, t_last = 432123739 7.12.792.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.940 MiB) 7.12.850.003 I slot launch_slot_: id 0 | task 4749 | processing task, is_child = 0 7.12.850.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.658 MiB) 7.12.909.309 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 432124163 7.12.909.563 I slot launch_slot_: id 1 | task 4750 | processing task, is_child = 0 7.14.187.569 I slot print_timing: id 2 | task 4743 | prompt eval time = 3061.41 ms / 879 tokens ( 3.48 ms per token, 287.12 tokens per second) 7.14.187.576 I slot print_timing: id 2 | task 4743 | eval time = 360.21 ms / 2 tokens ( 360.21 ms per token, 2.78 tokens per second) 7.14.187.577 I slot print_timing: id 2 | task 4743 | total time = 3421.61 ms / 881 tokens 7.14.187.578 I slot print_timing: id 2 | task 4743 | graphs reused = 3646 7.14.187.579 I slot print_timing: id 2 | task 4743 | graph reallocs = 352 / 0 (same size) / (changed size) 7.14.187.630 I slot release: id 2 | task 4743 | stop processing: n_tokens = 880, truncated = 0 7.14.188.049 I slot print_timing: id 3 | task 4744 | prompt eval time = 3056.77 ms / 1018 tokens ( 3.00 ms per token, 333.03 tokens per second) 7.14.188.055 I slot print_timing: id 3 | task 4744 | eval time = 360.06 ms / 2 tokens ( 360.06 ms per token, 2.78 tokens per second) 7.14.188.056 I slot print_timing: id 3 | task 4744 | total time = 3416.84 ms / 1020 tokens 7.14.188.057 I slot print_timing: id 3 | task 4744 | graphs reused = 3646 7.14.188.058 I slot print_timing: id 3 | task 4744 | graph reallocs = 352 / 0 (same size) / (changed size) 7.14.188.108 I slot release: id 3 | task 4744 | stop processing: n_tokens = 1019, truncated = 0 7.14.710.204 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.813 (> 0.100 thold), f_keep = 0.786 7.14.710.397 I slot launch_slot_: id 3 | task 4755 | processing task, is_child = 0 7.14.710.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.847 MiB) 7.14.765.134 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 434095252 7.14.766.078 I slot launch_slot_: id 2 | task 4756 | processing task, is_child = 0 7.16.022.203 I slot print_timing: id 0 | task 4749 | prompt eval time = 2832.57 ms / 896 tokens ( 3.16 ms per token, 316.32 tokens per second) 7.16.022.209 I slot print_timing: id 0 | task 4749 | eval time = 280.04 ms / 2 tokens ( 280.04 ms per token, 3.57 tokens per second) 7.16.022.210 I slot print_timing: id 0 | task 4749 | total time = 3112.61 ms / 898 tokens 7.16.022.211 I slot print_timing: id 0 | task 4749 | graphs reused = 3646 7.16.022.212 I slot print_timing: id 0 | task 4749 | graph reallocs = 354 / 0 (same size) / (changed size) 7.16.022.263 I slot release: id 0 | task 4749 | stop processing: n_tokens = 897, truncated = 0 7.16.022.665 I slot print_timing: id 1 | task 4750 | prompt eval time = 2828.27 ms / 1009 tokens ( 2.80 ms per token, 356.76 tokens per second) 7.16.022.670 I slot print_timing: id 1 | task 4750 | eval time = 279.71 ms / 2 tokens ( 279.71 ms per token, 3.58 tokens per second) 7.16.022.671 I slot print_timing: id 1 | task 4750 | total time = 3107.98 ms / 1011 tokens 7.16.022.672 I slot print_timing: id 1 | task 4750 | graphs reused = 3646 7.16.022.672 I slot print_timing: id 1 | task 4750 | graph reallocs = 354 / 0 (same size) / (changed size) 7.16.022.719 I slot release: id 1 | task 4750 | stop processing: n_tokens = 1010, truncated = 0 7.16.023.052 I slot print_timing: id 3 | task 4755 | prompt eval time = 945.58 ms / 212 tokens ( 4.46 ms per token, 224.20 tokens per second) 7.16.023.055 I slot print_timing: id 3 | task 4755 | eval time = 279.31 ms / 2 tokens ( 279.31 ms per token, 3.58 tokens per second) 7.16.023.056 I slot print_timing: id 3 | task 4755 | total time = 1224.89 ms / 214 tokens 7.16.023.056 I slot print_timing: id 3 | task 4755 | graphs reused = 3646 7.16.023.057 I slot print_timing: id 3 | task 4755 | graph reallocs = 354 / 0 (same size) / (changed size) 7.16.023.088 I slot release: id 3 | task 4755 | stop processing: n_tokens = 986, truncated = 0 7.16.168.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.893 7.16.168.325 I slot launch_slot_: id 0 | task 4761 | processing task, is_child = 0 7.16.168.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 292.033 MiB) 7.16.249.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.646 MiB) 7.16.306.446 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1010, t_last = 435930340 7.16.306.695 I slot launch_slot_: id 1 | task 4762 | processing task, is_child = 0 7.16.306.759 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 986, t_last = 435930709 7.16.306.955 I slot launch_slot_: id 3 | task 4763 | processing task, is_child = 0 7.17.690.036 I slot print_timing: id 0 | task 4761 | prompt eval time = 963.01 ms / 108 tokens ( 8.92 ms per token, 112.15 tokens per second) 7.17.690.043 I slot print_timing: id 0 | task 4761 | eval time = 420.05 ms / 2 tokens ( 420.05 ms per token, 2.38 tokens per second) 7.17.690.044 I slot print_timing: id 0 | task 4761 | total time = 1383.06 ms / 110 tokens 7.17.690.045 I slot print_timing: id 0 | task 4761 | graphs reused = 3646 7.17.690.046 I slot print_timing: id 0 | task 4761 | graph reallocs = 358 / 0 (same size) / (changed size) 7.17.690.102 I slot release: id 0 | task 4761 | stop processing: n_tokens = 882, truncated = 0 7.17.690.494 I slot print_timing: id 2 | task 4756 | prompt eval time = 2479.07 ms / 902 tokens ( 2.75 ms per token, 363.85 tokens per second) 7.17.690.497 I slot print_timing: id 2 | task 4756 | eval time = 419.84 ms / 2 tokens ( 419.84 ms per token, 2.38 tokens per second) 7.17.690.498 I slot print_timing: id 2 | task 4756 | total time = 2898.91 ms / 904 tokens 7.17.690.498 I slot print_timing: id 2 | task 4756 | graphs reused = 3646 7.17.690.500 I slot print_timing: id 2 | task 4756 | graph reallocs = 358 / 0 (same size) / (changed size) 7.17.690.537 I slot release: id 2 | task 4756 | stop processing: n_tokens = 903, truncated = 0 7.18.023.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 882, t_last = 437597723 7.18.023.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.490 MiB) 7.18.086.990 I slot launch_slot_: id 0 | task 4768 | processing task, is_child = 0 7.18.087.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 7.18.144.694 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 437598158 7.18.144.948 I slot launch_slot_: id 2 | task 4769 | processing task, is_child = 0 7.19.723.722 I slot print_timing: id 1 | task 4762 | prompt eval time = 2924.50 ms / 906 tokens ( 3.23 ms per token, 309.80 tokens per second) 7.19.723.729 I slot print_timing: id 1 | task 4762 | eval time = 472.28 ms / 2 tokens ( 472.28 ms per token, 2.12 tokens per second) 7.19.723.731 I slot print_timing: id 1 | task 4762 | total time = 3396.79 ms / 908 tokens 7.19.723.732 I slot print_timing: id 1 | task 4762 | graphs reused = 3646 7.19.723.733 I slot print_timing: id 1 | task 4762 | graph reallocs = 362 / 0 (same size) / (changed size) 7.19.723.796 I slot release: id 1 | task 4762 | stop processing: n_tokens = 907, truncated = 0 7.19.724.140 I slot print_timing: id 3 | task 4763 | prompt eval time = 2905.25 ms / 952 tokens ( 3.05 ms per token, 327.68 tokens per second) 7.19.724.145 I slot print_timing: id 3 | task 4763 | eval time = 472.04 ms / 2 tokens ( 472.04 ms per token, 2.12 tokens per second) 7.19.724.146 I slot print_timing: id 3 | task 4763 | total time = 3377.29 ms / 954 tokens 7.19.724.147 I slot print_timing: id 3 | task 4763 | graphs reused = 3646 7.19.724.147 I slot print_timing: id 3 | task 4763 | graph reallocs = 362 / 0 (same size) / (changed size) 7.19.724.186 I slot release: id 3 | task 4763 | stop processing: n_tokens = 953, truncated = 0 7.20.062.338 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 907, t_last = 439631421 7.20.062.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 7.20.125.995 I slot launch_slot_: id 1 | task 4774 | processing task, is_child = 0 7.20.126.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.428 MiB) 7.20.187.585 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 953, t_last = 439631807 7.20.187.831 I slot launch_slot_: id 3 | task 4775 | processing task, is_child = 0 7.21.943.098 I slot print_timing: id 0 | task 4768 | prompt eval time = 3307.22 ms / 940 tokens ( 3.52 ms per token, 284.23 tokens per second) 7.21.943.104 I slot print_timing: id 0 | task 4768 | eval time = 490.91 ms / 2 tokens ( 490.91 ms per token, 2.04 tokens per second) 7.21.943.105 I slot print_timing: id 0 | task 4768 | total time = 3798.12 ms / 942 tokens 7.21.943.106 I slot print_timing: id 0 | task 4768 | graphs reused = 3646 7.21.943.107 I slot print_timing: id 0 | task 4768 | graph reallocs = 368 / 0 (same size) / (changed size) 7.21.943.158 I slot release: id 0 | task 4768 | stop processing: n_tokens = 941, truncated = 0 7.21.943.538 I slot print_timing: id 2 | task 4769 | prompt eval time = 3288.64 ms / 1356 tokens ( 2.43 ms per token, 412.33 tokens per second) 7.21.943.543 I slot print_timing: id 2 | task 4769 | eval time = 490.70 ms / 2 tokens ( 490.70 ms per token, 2.04 tokens per second) 7.21.943.543 I slot print_timing: id 2 | task 4769 | total time = 3779.33 ms / 1358 tokens 7.21.943.544 I slot print_timing: id 2 | task 4769 | graphs reused = 3646 7.21.943.545 I slot print_timing: id 2 | task 4769 | graph reallocs = 368 / 0 (same size) / (changed size) 7.21.943.607 I slot release: id 2 | task 4769 | stop processing: n_tokens = 1357, truncated = 0 7.22.292.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 941, t_last = 441850779 7.22.292.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 7.22.353.635 I slot launch_slot_: id 0 | task 4780 | processing task, is_child = 0 7.22.353.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.334 MiB) 7.22.417.263 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.870 7.22.417.497 I slot launch_slot_: id 2 | task 4781 | processing task, is_child = 0 7.23.729.241 I slot print_timing: id 1 | task 4774 | prompt eval time = 3229.97 ms / 1259 tokens ( 2.57 ms per token, 389.79 tokens per second) 7.23.729.247 I slot print_timing: id 1 | task 4774 | eval time = 300.17 ms / 2 tokens ( 300.17 ms per token, 3.33 tokens per second) 7.23.729.248 I slot print_timing: id 1 | task 4774 | total time = 3530.14 ms / 1261 tokens 7.23.729.249 I slot print_timing: id 1 | task 4774 | graphs reused = 3646 7.23.729.250 I slot print_timing: id 1 | task 4774 | graph reallocs = 370 / 0 (same size) / (changed size) 7.23.729.308 I slot release: id 1 | task 4774 | stop processing: n_tokens = 1260, truncated = 0 7.23.729.686 I slot print_timing: id 2 | task 4781 | prompt eval time = 994.76 ms / 148 tokens ( 6.72 ms per token, 148.78 tokens per second) 7.23.729.690 I slot print_timing: id 2 | task 4781 | eval time = 300.03 ms / 2 tokens ( 300.03 ms per token, 3.33 tokens per second) 7.23.729.690 I slot print_timing: id 2 | task 4781 | total time = 1294.80 ms / 150 tokens 7.23.729.691 I slot print_timing: id 2 | task 4781 | graphs reused = 3646 7.23.729.692 I slot print_timing: id 2 | task 4781 | graph reallocs = 370 / 0 (same size) / (changed size) 7.23.729.737 I slot release: id 2 | task 4781 | stop processing: n_tokens = 1301, truncated = 0 7.23.730.087 I slot print_timing: id 3 | task 4775 | prompt eval time = 3213.96 ms / 1342 tokens ( 2.39 ms per token, 417.55 tokens per second) 7.23.730.091 I slot print_timing: id 3 | task 4775 | eval time = 299.83 ms / 2 tokens ( 299.83 ms per token, 3.34 tokens per second) 7.23.730.092 I slot print_timing: id 3 | task 4775 | total time = 3513.79 ms / 1344 tokens 7.23.730.093 I slot print_timing: id 3 | task 4775 | graphs reused = 3646 7.23.730.093 I slot print_timing: id 3 | task 4775 | graph reallocs = 370 / 0 (same size) / (changed size) 7.23.730.143 I slot release: id 3 | task 4775 | stop processing: n_tokens = 1343, truncated = 0 7.23.862.224 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1260, t_last = 443636929 7.23.862.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.741 MiB) 7.23.925.785 I slot launch_slot_: id 1 | task 4786 | processing task, is_child = 0 7.23.925.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 7.23.988.365 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 7.24.053.933 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1301, t_last = 443637359 7.24.054.161 I slot launch_slot_: id 2 | task 4787 | processing task, is_child = 0 7.24.054.240 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1343, t_last = 443637764 7.24.054.412 I slot launch_slot_: id 3 | task 4788 | processing task, is_child = 0 7.25.001.460 I slot print_timing: id 0 | task 4780 | prompt eval time = 2152.76 ms / 792 tokens ( 2.72 ms per token, 367.90 tokens per second) 7.25.001.467 I slot print_timing: id 0 | task 4780 | eval time = 431.18 ms / 2 tokens ( 431.18 ms per token, 2.32 tokens per second) 7.25.001.468 I slot print_timing: id 0 | task 4780 | total time = 2583.93 ms / 794 tokens 7.25.001.469 I slot print_timing: id 0 | task 4780 | graphs reused = 3646 7.25.001.470 I slot print_timing: id 0 | task 4780 | graph reallocs = 371 / 0 (same size) / (changed size) 7.25.001.516 I slot release: id 0 | task 4780 | stop processing: n_tokens = 793, truncated = 0 7.25.392.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 793, t_last = 444909137 7.25.392.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.400 MiB) 7.25.436.466 I slot launch_slot_: id 0 | task 4792 | processing task, is_child = 0 7.27.228.672 I slot print_timing: id 1 | task 4786 | prompt processing, n_tokens = 804, progress = 1.00, t = 3.15 s / 255.58 tokens per second 7.27.239.469 I slot print_timing: id 2 | task 4787 | prompt processing, n_tokens = 887, progress = 1.00, t = 3.14 s / 282.30 tokens per second 7.27.250.672 I slot print_timing: id 3 | task 4788 | prompt processing, n_tokens = 855, progress = 1.00, t = 3.14 s / 272.43 tokens per second 7.27.834.466 I slot print_timing: id 1 | task 4786 | prompt eval time = 3518.31 ms / 808 tokens ( 4.35 ms per token, 229.66 tokens per second) 7.27.834.472 I slot print_timing: id 1 | task 4786 | eval time = 251.78 ms / 2 tokens ( 251.78 ms per token, 3.97 tokens per second) 7.27.834.474 I slot print_timing: id 1 | task 4786 | total time = 3770.09 ms / 810 tokens 7.27.834.475 I slot print_timing: id 1 | task 4786 | graphs reused = 3646 7.27.834.476 I slot print_timing: id 1 | task 4786 | graph reallocs = 379 / 0 (same size) / (changed size) 7.27.834.536 I slot release: id 1 | task 4786 | stop processing: n_tokens = 809, truncated = 0 7.27.834.874 I slot print_timing: id 2 | task 4787 | prompt eval time = 3515.28 ms / 891 tokens ( 3.95 ms per token, 253.46 tokens per second) 7.27.834.878 I slot print_timing: id 2 | task 4787 | eval time = 251.50 ms / 2 tokens ( 251.50 ms per token, 3.98 tokens per second) 7.27.834.879 I slot print_timing: id 2 | task 4787 | total time = 3766.79 ms / 893 tokens 7.27.834.880 I slot print_timing: id 2 | task 4787 | graphs reused = 3646 7.27.834.881 I slot print_timing: id 2 | task 4787 | graph reallocs = 379 / 0 (same size) / (changed size) 7.27.834.928 I slot release: id 2 | task 4787 | stop processing: n_tokens = 892, truncated = 0 7.27.835.268 I slot print_timing: id 3 | task 4788 | prompt eval time = 3512.26 ms / 859 tokens ( 4.09 ms per token, 244.57 tokens per second) 7.27.835.271 I slot print_timing: id 3 | task 4788 | eval time = 251.23 ms / 2 tokens ( 251.23 ms per token, 3.98 tokens per second) 7.27.835.272 I slot print_timing: id 3 | task 4788 | total time = 3763.49 ms / 861 tokens 7.27.835.273 I slot print_timing: id 3 | task 4788 | graphs reused = 3646 7.27.835.274 I slot print_timing: id 3 | task 4788 | graph reallocs = 379 / 0 (same size) / (changed size) 7.27.835.307 I slot release: id 3 | task 4788 | stop processing: n_tokens = 860, truncated = 0 7.27.905.129 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 809, t_last = 447742158 7.27.905.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 7.27.964.526 I slot launch_slot_: id 1 | task 4798 | processing task, is_child = 0 7.27.964.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.151 MiB) 7.28.025.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.950 MiB) 7.28.084.359 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 447742550 7.28.084.595 I slot launch_slot_: id 2 | task 4799 | processing task, is_child = 0 7.28.084.654 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 447742928 7.28.084.826 I slot launch_slot_: id 3 | task 4800 | processing task, is_child = 0 7.28.386.910 I slot print_timing: id 0 | task 4792 | prompt eval time = 2468.64 ms / 790 tokens ( 3.12 ms per token, 320.01 tokens per second) 7.28.386.915 I slot print_timing: id 0 | task 4792 | eval time = 481.78 ms / 2 tokens ( 481.78 ms per token, 2.08 tokens per second) 7.28.386.916 I slot print_timing: id 0 | task 4792 | total time = 2950.42 ms / 792 tokens 7.28.386.917 I slot print_timing: id 0 | task 4792 | graphs reused = 3646 7.28.386.918 I slot print_timing: id 0 | task 4792 | graph reallocs = 380 / 0 (same size) / (changed size) 7.28.386.983 I slot release: id 0 | task 4792 | stop processing: n_tokens = 791, truncated = 0 7.28.858.925 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.852 (> 0.100 thold), f_keep = 0.863 7.28.859.128 I slot launch_slot_: id 0 | task 4803 | processing task, is_child = 0 7.30.481.835 I slot print_timing: id 0 | task 4803 | prompt eval time = 1272.61 ms / 147 tokens ( 8.66 ms per token, 115.51 tokens per second) 7.30.481.841 I slot print_timing: id 0 | task 4803 | eval time = 350.07 ms / 2 tokens ( 350.07 ms per token, 2.86 tokens per second) 7.30.481.843 I slot print_timing: id 0 | task 4803 | total time = 1622.68 ms / 149 tokens 7.30.481.843 I slot print_timing: id 0 | task 4803 | graphs reused = 3646 7.30.481.844 I slot print_timing: id 0 | task 4803 | graph reallocs = 384 / 0 (same size) / (changed size) 7.30.481.895 I slot release: id 0 | task 4803 | stop processing: n_tokens = 803, truncated = 0 7.30.651.840 I slot print_timing: id 1 | task 4798 | prompt eval time = 2397.65 ms / 774 tokens ( 3.10 ms per token, 322.82 tokens per second) 7.30.651.847 I slot print_timing: id 1 | task 4798 | eval time = 169.34 ms / 2 tokens ( 169.34 ms per token, 5.91 tokens per second) 7.30.651.849 I slot print_timing: id 1 | task 4798 | total time = 2566.99 ms / 776 tokens 7.30.651.850 I slot print_timing: id 1 | task 4798 | graphs reused = 3646 7.30.651.851 I slot print_timing: id 1 | task 4798 | graph reallocs = 384 / 0 (same size) / (changed size) 7.30.651.904 I slot release: id 1 | task 4798 | stop processing: n_tokens = 775, truncated = 0 7.30.652.229 I slot print_timing: id 2 | task 4799 | prompt eval time = 2393.74 ms / 778 tokens ( 3.08 ms per token, 325.01 tokens per second) 7.30.652.234 I slot print_timing: id 2 | task 4799 | eval time = 169.14 ms / 2 tokens ( 169.14 ms per token, 5.91 tokens per second) 7.30.652.235 I slot print_timing: id 2 | task 4799 | total time = 2562.89 ms / 780 tokens 7.30.652.236 I slot print_timing: id 2 | task 4799 | graphs reused = 3646 7.30.652.237 I slot print_timing: id 2 | task 4799 | graph reallocs = 384 / 0 (same size) / (changed size) 7.30.652.270 I slot release: id 2 | task 4799 | stop processing: n_tokens = 779, truncated = 0 7.30.652.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 803, t_last = 450389517 7.30.653.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.181 MiB) 7.30.713.899 I slot launch_slot_: id 0 | task 4808 | processing task, is_child = 0 7.30.713.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.245 MiB) 7.30.774.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.587 MiB) 7.30.830.834 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 450559526 7.30.831.067 I slot launch_slot_: id 1 | task 4809 | processing task, is_child = 0 7.30.831.124 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 450559891 7.30.831.300 I slot launch_slot_: id 2 | task 4810 | processing task, is_child = 0 7.31.270.140 I slot print_timing: id 3 | task 4800 | prompt eval time = 2559.90 ms / 855 tokens ( 2.99 ms per token, 334.00 tokens per second) 7.31.270.145 I slot print_timing: id 3 | task 4800 | eval time = 617.20 ms / 2 tokens ( 617.20 ms per token, 1.62 tokens per second) 7.31.270.146 I slot print_timing: id 3 | task 4800 | total time = 3177.10 ms / 857 tokens 7.31.270.147 I slot print_timing: id 3 | task 4800 | graphs reused = 3646 7.31.270.148 I slot print_timing: id 3 | task 4800 | graph reallocs = 384 / 0 (same size) / (changed size) 7.31.270.194 I slot release: id 3 | task 4800 | stop processing: n_tokens = 856, truncated = 0 7.31.453.875 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 856, t_last = 451177816 7.31.453.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 7.31.541.441 I slot launch_slot_: id 3 | task 4813 | processing task, is_child = 0 7.34.054.014 I slot print_timing: id 0 | task 4808 | prompt processing, n_tokens = 967, progress = 1.00, t = 3.22 s / 300.06 tokens per second 7.34.071.075 I slot print_timing: id 1 | task 4809 | prompt processing, n_tokens = 940, progress = 1.00, t = 3.22 s / 292.12 tokens per second 7.34.081.744 I slot print_timing: id 2 | task 4810 | prompt processing, n_tokens = 960, progress = 1.00, t = 3.21 s / 298.67 tokens per second 7.34.658.085 I slot print_timing: id 0 | task 4808 | prompt eval time = 3602.54 ms / 971 tokens ( 3.71 ms per token, 269.53 tokens per second) 7.34.658.091 I slot print_timing: id 0 | task 4808 | eval time = 224.22 ms / 2 tokens ( 224.22 ms per token, 4.46 tokens per second) 7.34.658.092 I slot print_timing: id 0 | task 4808 | total time = 3826.76 ms / 973 tokens 7.34.658.093 I slot print_timing: id 0 | task 4808 | graphs reused = 3646 7.34.658.095 I slot print_timing: id 0 | task 4808 | graph reallocs = 389 / 0 (same size) / (changed size) 7.34.658.156 I slot release: id 0 | task 4808 | stop processing: n_tokens = 972, truncated = 0 7.34.658.475 I slot print_timing: id 1 | task 4809 | prompt eval time = 3598.31 ms / 944 tokens ( 3.81 ms per token, 262.35 tokens per second) 7.34.658.479 I slot print_timing: id 1 | task 4809 | eval time = 224.02 ms / 2 tokens ( 224.02 ms per token, 4.46 tokens per second) 7.34.658.480 I slot print_timing: id 1 | task 4809 | total time = 3822.34 ms / 946 tokens 7.34.658.481 I slot print_timing: id 1 | task 4809 | graphs reused = 3646 7.34.658.482 I slot print_timing: id 1 | task 4809 | graph reallocs = 389 / 0 (same size) / (changed size) 7.34.658.516 I slot release: id 1 | task 4809 | stop processing: n_tokens = 945, truncated = 0 7.34.658.857 I slot print_timing: id 2 | task 4810 | prompt eval time = 3595.31 ms / 964 tokens ( 3.73 ms per token, 268.13 tokens per second) 7.34.658.861 I slot print_timing: id 2 | task 4810 | eval time = 223.82 ms / 2 tokens ( 223.82 ms per token, 4.47 tokens per second) 7.34.658.862 I slot print_timing: id 2 | task 4810 | total time = 3819.13 ms / 966 tokens 7.34.658.863 I slot print_timing: id 2 | task 4810 | graphs reused = 3646 7.34.658.864 I slot print_timing: id 2 | task 4810 | graph reallocs = 389 / 0 (same size) / (changed size) 7.34.658.895 I slot release: id 2 | task 4810 | stop processing: n_tokens = 965, truncated = 0 7.34.658.916 I slot print_timing: id 3 | task 4813 | prompt processing, n_tokens = 943, progress = 1.00, t = 3.12 s / 302.60 tokens per second 7.34.728.949 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.892 (> 0.100 thold), f_keep = 0.889 7.34.729.141 I slot launch_slot_: id 0 | task 4820 | processing task, is_child = 0 7.34.729.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.582 MiB) 7.34.787.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.770 MiB) 7.34.845.707 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 945, t_last = 454566138 7.34.846.024 I slot launch_slot_: id 1 | task 4821 | processing task, is_child = 0 7.34.846.126 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 965, t_last = 454566517 7.34.846.397 I slot launch_slot_: id 2 | task 4822 | processing task, is_child = 0 7.35.288.144 I slot print_timing: id 3 | task 4813 | prompt eval time = 3187.45 ms / 947 tokens ( 3.37 ms per token, 297.10 tokens per second) 7.35.288.150 I slot print_timing: id 3 | task 4813 | eval time = 559.20 ms / 2 tokens ( 559.20 ms per token, 1.79 tokens per second) 7.35.288.151 I slot print_timing: id 3 | task 4813 | total time = 3746.65 ms / 949 tokens 7.35.288.152 I slot print_timing: id 3 | task 4813 | graphs reused = 3646 7.35.288.153 I slot print_timing: id 3 | task 4813 | graph reallocs = 389 / 0 (same size) / (changed size) 7.35.288.202 I slot release: id 3 | task 4813 | stop processing: n_tokens = 948, truncated = 0 7.35.655.653 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 455195823 7.35.655.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 7.35.718.842 I slot launch_slot_: id 3 | task 4825 | processing task, is_child = 0 7.36.376.055 I slot print_timing: id 0 | task 4820 | prompt eval time = 809.23 ms / 133 tokens ( 6.08 ms per token, 164.35 tokens per second) 7.36.376.061 I slot print_timing: id 0 | task 4820 | eval time = 720.40 ms / 2 tokens ( 720.40 ms per token, 1.39 tokens per second) 7.36.376.063 I slot print_timing: id 0 | task 4820 | total time = 1529.63 ms / 135 tokens 7.36.376.064 I slot print_timing: id 0 | task 4820 | graphs reused = 3646 7.36.376.065 I slot print_timing: id 0 | task 4820 | graph reallocs = 390 / 0 (same size) / (changed size) 7.36.376.121 I slot release: id 0 | task 4820 | stop processing: n_tokens = 970, truncated = 0 7.36.784.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 456283742 7.36.784.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 7.36.844.278 I slot launch_slot_: id 0 | task 4828 | processing task, is_child = 0 7.37.757.570 I slot print_timing: id 1 | task 4821 | prompt eval time = 2435.77 ms / 798 tokens ( 3.05 ms per token, 327.62 tokens per second) 7.37.757.577 I slot print_timing: id 1 | task 4821 | eval time = 453.67 ms / 2 tokens ( 453.67 ms per token, 2.20 tokens per second) 7.37.757.578 I slot print_timing: id 1 | task 4821 | total time = 2889.44 ms / 800 tokens 7.37.757.579 I slot print_timing: id 1 | task 4821 | graphs reused = 3646 7.37.757.580 I slot print_timing: id 1 | task 4821 | graph reallocs = 392 / 0 (same size) / (changed size) 7.37.757.630 I slot release: id 1 | task 4821 | stop processing: n_tokens = 799, truncated = 0 7.37.758.034 I slot print_timing: id 2 | task 4822 | prompt eval time = 2429.37 ms / 799 tokens ( 3.04 ms per token, 328.89 tokens per second) 7.37.758.038 I slot print_timing: id 2 | task 4822 | eval time = 453.34 ms / 2 tokens ( 453.34 ms per token, 2.21 tokens per second) 7.37.758.039 I slot print_timing: id 2 | task 4822 | total time = 2882.71 ms / 801 tokens 7.37.758.040 I slot print_timing: id 2 | task 4822 | graphs reused = 3646 7.37.758.041 I slot print_timing: id 2 | task 4822 | graph reallocs = 392 / 0 (same size) / (changed size) 7.37.758.079 I slot release: id 2 | task 4822 | stop processing: n_tokens = 800, truncated = 0 7.38.058.788 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 457665251 7.38.058.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.679 MiB) 7.38.115.343 I slot launch_slot_: id 1 | task 4832 | processing task, is_child = 0 7.38.115.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.307 MiB) 7.38.174.416 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 457665700 7.38.174.639 I slot launch_slot_: id 2 | task 4833 | processing task, is_child = 0 7.39.325.094 I slot print_timing: id 3 | task 4825 | prompt eval time = 3018.30 ms / 975 tokens ( 3.10 ms per token, 323.03 tokens per second) 7.39.325.100 I slot print_timing: id 3 | task 4825 | eval time = 563.38 ms / 2 tokens ( 563.38 ms per token, 1.78 tokens per second) 7.39.325.101 I slot print_timing: id 3 | task 4825 | total time = 3581.68 ms / 977 tokens 7.39.325.102 I slot print_timing: id 3 | task 4825 | graphs reused = 3646 7.39.325.103 I slot print_timing: id 3 | task 4825 | graph reallocs = 392 / 0 (same size) / (changed size) 7.39.325.154 I slot release: id 3 | task 4825 | stop processing: n_tokens = 976, truncated = 0 7.39.616.195 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 459232777 7.39.616.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.621 MiB) 7.39.673.162 I slot launch_slot_: id 3 | task 4837 | processing task, is_child = 0 7.40.327.628 I slot print_timing: id 0 | task 4828 | prompt eval time = 2771.88 ms / 953 tokens ( 2.91 ms per token, 343.81 tokens per second) 7.40.327.636 I slot print_timing: id 0 | task 4828 | eval time = 711.43 ms / 2 tokens ( 711.43 ms per token, 1.41 tokens per second) 7.40.327.637 I slot print_timing: id 0 | task 4828 | total time = 3483.32 ms / 955 tokens 7.40.327.640 I slot print_timing: id 0 | task 4828 | graphs reused = 3646 7.40.327.641 I slot print_timing: id 0 | task 4828 | graph reallocs = 393 / 0 (same size) / (changed size) 7.40.327.713 I slot release: id 0 | task 4828 | stop processing: n_tokens = 954, truncated = 0 7.40.848.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 954, t_last = 460235336 7.40.848.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.526 MiB) 7.40.903.586 I slot launch_slot_: id 0 | task 4840 | processing task, is_child = 0 7.41.827.749 I slot print_timing: id 1 | task 4832 | prompt eval time = 3171.03 ms / 961 tokens ( 3.30 ms per token, 303.06 tokens per second) 7.41.827.755 I slot print_timing: id 1 | task 4832 | eval time = 471.03 ms / 2 tokens ( 471.03 ms per token, 2.12 tokens per second) 7.41.827.756 I slot print_timing: id 1 | task 4832 | total time = 3642.06 ms / 963 tokens 7.41.827.758 I slot print_timing: id 1 | task 4832 | graphs reused = 3646 7.41.827.759 I slot print_timing: id 1 | task 4832 | graph reallocs = 396 / 0 (same size) / (changed size) 7.41.827.808 I slot release: id 1 | task 4832 | stop processing: n_tokens = 962, truncated = 0 7.41.828.190 I slot print_timing: id 2 | task 4833 | prompt eval time = 3166.75 ms / 930 tokens ( 3.41 ms per token, 293.68 tokens per second) 7.41.828.194 I slot print_timing: id 2 | task 4833 | eval time = 470.69 ms / 2 tokens ( 470.69 ms per token, 2.12 tokens per second) 7.41.828.195 I slot print_timing: id 2 | task 4833 | total time = 3637.44 ms / 932 tokens 7.41.828.196 I slot print_timing: id 2 | task 4833 | graphs reused = 3646 7.41.828.196 I slot print_timing: id 2 | task 4833 | graph reallocs = 396 / 0 (same size) / (changed size) 7.41.828.239 I slot release: id 2 | task 4833 | stop processing: n_tokens = 931, truncated = 0 7.42.100.770 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 7.42.100.975 I slot launch_slot_: id 2 | task 4844 | processing task, is_child = 0 7.42.101.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.338 MiB) 7.42.159.399 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 962, t_last = 461735429 7.42.159.692 I slot launch_slot_: id 1 | task 4845 | processing task, is_child = 0 7.43.339.946 I slot print_timing: id 3 | task 4837 | prompt eval time = 3157.37 ms / 898 tokens ( 3.52 ms per token, 284.41 tokens per second) 7.43.339.952 I slot print_timing: id 3 | task 4837 | eval time = 483.48 ms / 2 tokens ( 483.48 ms per token, 2.07 tokens per second) 7.43.339.953 I slot print_timing: id 3 | task 4837 | total time = 3640.86 ms / 900 tokens 7.43.339.955 I slot print_timing: id 3 | task 4837 | graphs reused = 3646 7.43.339.955 I slot print_timing: id 3 | task 4837 | graph reallocs = 396 / 0 (same size) / (changed size) 7.43.340.008 I slot release: id 3 | task 4837 | stop processing: n_tokens = 899, truncated = 0 7.43.612.819 I slot print_timing: id 2 | task 4844 | prompt eval time = 1161.10 ms / 120 tokens ( 9.68 ms per token, 103.35 tokens per second) 7.43.612.825 I slot print_timing: id 2 | task 4844 | eval time = 273.21 ms / 2 tokens ( 273.21 ms per token, 3.66 tokens per second) 7.43.612.826 I slot print_timing: id 2 | task 4844 | total time = 1434.30 ms / 122 tokens 7.43.612.827 I slot print_timing: id 2 | task 4844 | graphs reused = 3646 7.43.612.827 I slot print_timing: id 2 | task 4844 | graph reallocs = 396 / 0 (same size) / (changed size) 7.43.612.881 I slot release: id 2 | task 4844 | stop processing: n_tokens = 900, truncated = 0 7.43.612.899 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 463247629 7.43.612.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.773 MiB) 7.43.667.940 I slot launch_slot_: id 3 | task 4849 | processing task, is_child = 0 7.43.668.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.839 MiB) 7.43.728.670 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 900, t_last = 463520503 7.43.729.094 I slot launch_slot_: id 2 | task 4850 | processing task, is_child = 0 7.44.374.724 I slot print_timing: id 0 | task 4840 | prompt eval time = 2708.83 ms / 902 tokens ( 3.00 ms per token, 332.99 tokens per second) 7.44.374.731 I slot print_timing: id 0 | task 4840 | eval time = 762.28 ms / 2 tokens ( 762.28 ms per token, 1.31 tokens per second) 7.44.374.732 I slot print_timing: id 0 | task 4840 | total time = 3471.11 ms / 904 tokens 7.44.374.733 I slot print_timing: id 0 | task 4840 | graphs reused = 3646 7.44.374.734 I slot print_timing: id 0 | task 4840 | graph reallocs = 396 / 0 (same size) / (changed size) 7.44.374.801 I slot release: id 0 | task 4840 | stop processing: n_tokens = 903, truncated = 0 7.44.728.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 903, t_last = 464282424 7.44.728.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.088 MiB) 7.44.783.592 I slot launch_slot_: id 0 | task 4853 | processing task, is_child = 0 7.46.342.083 I slot print_timing: id 1 | task 4845 | prompt eval time = 3395.39 ms / 890 tokens ( 3.82 ms per token, 262.12 tokens per second) 7.46.342.089 I slot print_timing: id 1 | task 4845 | eval time = 774.77 ms / 2 tokens ( 774.77 ms per token, 1.29 tokens per second) 7.46.342.090 I slot print_timing: id 1 | task 4845 | total time = 4170.16 ms / 892 tokens 7.46.342.091 I slot print_timing: id 1 | task 4845 | graphs reused = 3646 7.46.342.092 I slot print_timing: id 1 | task 4845 | graph reallocs = 400 / 0 (same size) / (changed size) 7.46.342.143 I slot release: id 1 | task 4845 | stop processing: n_tokens = 891, truncated = 0 7.46.847.122 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 891, t_last = 466249765 7.46.847.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.836 MiB) 7.46.902.329 I slot launch_slot_: id 1 | task 4857 | processing task, is_child = 0 7.46.919.757 I slot print_timing: id 2 | task 4850 | prompt processing, n_tokens = 1232, progress = 1.00, t = 3.11 s / 396.54 tokens per second 7.46.932.010 I slot print_timing: id 3 | task 4849 | prompt processing, n_tokens = 1221, progress = 1.00, t = 3.10 s / 393.71 tokens per second 7.48.069.019 I slot print_timing: id 2 | task 4850 | prompt eval time = 3853.36 ms / 1236 tokens ( 3.12 ms per token, 320.76 tokens per second) 7.48.069.025 I slot print_timing: id 2 | task 4850 | eval time = 475.41 ms / 2 tokens ( 475.41 ms per token, 2.10 tokens per second) 7.48.069.026 I slot print_timing: id 2 | task 4850 | total time = 4328.77 ms / 1238 tokens 7.48.069.027 I slot print_timing: id 2 | task 4850 | graphs reused = 3646 7.48.069.029 I slot print_timing: id 2 | task 4850 | graph reallocs = 402 / 0 (same size) / (changed size) 7.48.069.099 I slot release: id 2 | task 4850 | stop processing: n_tokens = 1237, truncated = 0 7.48.069.410 I slot print_timing: id 3 | task 4849 | prompt eval time = 3848.57 ms / 1225 tokens ( 3.14 ms per token, 318.30 tokens per second) 7.48.069.414 I slot print_timing: id 3 | task 4849 | eval time = 475.01 ms / 2 tokens ( 475.01 ms per token, 2.11 tokens per second) 7.48.069.415 I slot print_timing: id 3 | task 4849 | total time = 4323.58 ms / 1227 tokens 7.48.069.416 I slot print_timing: id 3 | task 4849 | graphs reused = 3646 7.48.069.417 I slot print_timing: id 3 | task 4849 | graph reallocs = 402 / 0 (same size) / (changed size) 7.48.069.459 I slot release: id 3 | task 4849 | stop processing: n_tokens = 1226, truncated = 0 7.48.069.479 I slot print_timing: id 0 | task 4853 | prompt processing, n_tokens = 1286, progress = 1.00, t = 3.29 s / 391.47 tokens per second 7.48.743.144 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1237, t_last = 467976722 7.48.743.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 7.48.803.187 I slot launch_slot_: id 2 | task 4861 | processing task, is_child = 0 7.48.803.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.618 MiB) 7.48.864.162 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1226, t_last = 467977080 7.48.864.526 I slot launch_slot_: id 3 | task 4862 | processing task, is_child = 0 7.49.534.315 I slot print_timing: id 0 | task 4853 | prompt eval time = 3959.50 ms / 1290 tokens ( 3.07 ms per token, 325.80 tokens per second) 7.49.534.319 I slot print_timing: id 0 | task 4853 | eval time = 791.17 ms / 2 tokens ( 791.17 ms per token, 1.26 tokens per second) 7.49.534.321 I slot print_timing: id 0 | task 4853 | total time = 4750.67 ms / 1292 tokens 7.49.534.322 I slot print_timing: id 0 | task 4853 | graphs reused = 3646 7.49.534.323 I slot print_timing: id 0 | task 4853 | graph reallocs = 404 / 0 (same size) / (changed size) 7.49.534.399 I slot release: id 0 | task 4853 | stop processing: n_tokens = 1291, truncated = 0 7.50.337.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1291, t_last = 469442022 7.50.337.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.056 MiB) 7.50.386.869 I slot launch_slot_: id 0 | task 4865 | processing task, is_child = 0 7.50.392.356 I slot print_timing: id 1 | task 4857 | prompt processing, n_tokens = 2583, progress = 1.00, t = 3.42 s / 754.71 tokens per second 7.52.572.656 I slot print_timing: id 1 | task 4857 | prompt eval time = 4653.56 ms / 2587 tokens ( 1.80 ms per token, 555.92 tokens per second) 7.52.572.662 I slot print_timing: id 1 | task 4857 | eval time = 1004.43 ms / 2 tokens ( 1004.43 ms per token, 1.00 tokens per second) 7.52.572.663 I slot print_timing: id 1 | task 4857 | total time = 5657.99 ms / 2589 tokens 7.52.572.664 I slot print_timing: id 1 | task 4857 | graphs reused = 3646 7.52.572.665 I slot print_timing: id 1 | task 4857 | graph reallocs = 413 / 0 (same size) / (changed size) 7.52.572.786 I slot release: id 1 | task 4857 | stop processing: n_tokens = 2588, truncated = 0 7.52.572.842 I slot print_timing: id 2 | task 4861 | prompt processing, n_tokens = 2288, progress = 0.92, t = 3.70 s / 618.96 tokens per second 7.52.582.749 I slot print_timing: id 3 | task 4862 | prompt processing, n_tokens = 2226, progress = 0.81, t = 3.69 s / 603.38 tokens per second 7.53.463.456 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 2588, t_last = 472480409 7.53.463.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.681 MiB) 7.53.473.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.690 MiB) 7.53.539.063 I slot launch_slot_: id 1 | task 4869 | processing task, is_child = 0 7.53.539.086 I slot print_timing: id 0 | task 4865 | prompt processing, n_tokens = 2139, progress = 0.81, t = 3.08 s / 695.26 tokens per second 7.53.557.927 I slot print_timing: id 2 | task 4861 | prompt processing, n_tokens = 2496, progress = 1.00, t = 4.59 s / 544.07 tokens per second 7.53.570.511 I slot print_timing: id 3 | task 4862 | prompt processing, n_tokens = 2288, progress = 0.83, t = 4.58 s / 499.52 tokens per second 7.54.268.500 I slot print_timing: id 0 | task 4865 | prompt processing, n_tokens = 2288, progress = 0.86, t = 3.88 s / 589.56 tokens per second 7.54.288.373 I slot print_timing: id 3 | task 4862 | prompt processing, n_tokens = 2738, progress = 1.00, t = 5.38 s / 508.48 tokens per second 7.54.944.848 I slot print_timing: id 2 | task 4861 | prompt eval time = 5392.70 ms / 2500 tokens ( 2.16 ms per token, 463.59 tokens per second) 7.54.944.854 I slot print_timing: id 2 | task 4861 | eval time = 676.36 ms / 2 tokens ( 676.36 ms per token, 1.48 tokens per second) 7.54.944.856 I slot print_timing: id 2 | task 4861 | total time = 6069.07 ms / 2502 tokens 7.54.944.858 I slot print_timing: id 2 | task 4861 | graphs reused = 3646 7.54.944.859 I slot print_timing: id 2 | task 4861 | graph reallocs = 417 / 0 (same size) / (changed size) 7.54.945.007 I slot release: id 2 | task 4861 | stop processing: n_tokens = 2501, truncated = 0 7.54.945.749 I slot print_timing: id 0 | task 4865 | prompt processing, n_tokens = 2651, progress = 1.00, t = 4.56 s / 581.66 tokens per second 7.55.479.611 I slot print_timing: id 3 | task 4862 | prompt eval time = 6062.65 ms / 2742 tokens ( 2.21 ms per token, 452.28 tokens per second) 7.55.479.617 I slot print_timing: id 3 | task 4862 | eval time = 533.87 ms / 2 tokens ( 533.87 ms per token, 1.87 tokens per second) 7.55.479.618 I slot print_timing: id 3 | task 4862 | total time = 6596.52 ms / 2744 tokens 7.55.479.620 I slot print_timing: id 3 | task 4862 | graphs reused = 3646 7.55.479.621 I slot print_timing: id 3 | task 4862 | graph reallocs = 417 / 0 (same size) / (changed size) 7.55.479.738 I slot release: id 3 | task 4862 | stop processing: n_tokens = 2743, truncated = 0 7.55.479.755 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 2501, t_last = 474852630 7.55.479.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 290.657 MiB) 7.55.546.569 I slot launch_slot_: id 2 | task 4873 | processing task, is_child = 0 7.55.546.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.939 MiB) 7.55.619.379 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2743, t_last = 475387361 7.55.619.688 I slot launch_slot_: id 3 | task 4874 | processing task, is_child = 0 7.56.246.063 I slot print_timing: id 0 | task 4865 | prompt eval time = 5092.34 ms / 2655 tokens ( 1.92 ms per token, 521.37 tokens per second) 7.56.246.069 I slot print_timing: id 0 | task 4865 | eval time = 766.83 ms / 2 tokens ( 766.83 ms per token, 1.30 tokens per second) 7.56.246.070 I slot print_timing: id 0 | task 4865 | total time = 5859.16 ms / 2657 tokens 7.56.246.071 I slot print_timing: id 0 | task 4865 | graphs reused = 3646 7.56.246.072 I slot print_timing: id 0 | task 4865 | graph reallocs = 418 / 0 (same size) / (changed size) 7.56.246.195 I slot release: id 0 | task 4865 | stop processing: n_tokens = 2656, truncated = 0 7.56.838.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 2656, t_last = 476153818 7.56.838.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 293.253 MiB) 7.56.899.597 I slot launch_slot_: id 0 | task 4877 | processing task, is_child = 0 7.56.904.883 I slot print_timing: id 1 | task 4869 | prompt processing, n_tokens = 1775, progress = 1.00, t = 3.29 s / 539.97 tokens per second 7.58.773.507 I slot print_timing: id 1 | task 4869 | prompt eval time = 4630.35 ms / 1779 tokens ( 2.60 ms per token, 384.20 tokens per second) 7.58.773.513 I slot print_timing: id 1 | task 4869 | eval time = 591.83 ms / 2 tokens ( 591.83 ms per token, 1.69 tokens per second) 7.58.773.514 I slot print_timing: id 1 | task 4869 | total time = 5222.18 ms / 1781 tokens 7.58.773.516 I slot print_timing: id 1 | task 4869 | graphs reused = 3646 7.58.773.517 I slot print_timing: id 1 | task 4869 | graph reallocs = 423 / 0 (same size) / (changed size) 7.58.773.607 I slot release: id 1 | task 4869 | stop processing: n_tokens = 1780, truncated = 0 7.58.773.652 I slot print_timing: id 2 | task 4873 | prompt processing, n_tokens = 1447, progress = 0.79, t = 3.14 s / 460.61 tokens per second 7.58.784.332 I slot print_timing: id 3 | task 4874 | prompt processing, n_tokens = 1532, progress = 0.75, t = 3.14 s / 488.39 tokens per second 7.59.708.019 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.756 (> 0.100 thold), f_keep = 0.834 7.59.708.277 I slot launch_slot_: id 1 | task 4881 | processing task, is_child = 0 7.59.753.166 I slot print_timing: id 2 | task 4873 | prompt processing, n_tokens = 1837, progress = 1.00, t = 4.08 s / 450.65 tokens per second 7.59.765.560 I slot print_timing: id 3 | task 4874 | prompt processing, n_tokens = 2044, progress = 1.00, t = 4.07 s / 502.00 tokens per second 8.00.282.892 I slot print_timing: id 0 | task 4877 | prompt processing, n_tokens = 1447, progress = 0.78, t = 3.38 s / 427.87 tokens per second 8.00.646.000 I slot print_timing: id 2 | task 4873 | prompt eval time = 4650.56 ms / 1841 tokens ( 2.53 ms per token, 395.87 tokens per second) 8.00.646.006 I slot print_timing: id 2 | task 4873 | eval time = 363.78 ms / 2 tokens ( 363.78 ms per token, 2.75 tokens per second) 8.00.646.007 I slot print_timing: id 2 | task 4873 | total time = 5014.34 ms / 1843 tokens 8.00.646.008 I slot print_timing: id 2 | task 4873 | graphs reused = 3646 8.00.646.009 I slot print_timing: id 2 | task 4873 | graph reallocs = 428 / 0 (same size) / (changed size) 8.00.646.095 I slot release: id 2 | task 4873 | stop processing: n_tokens = 1842, truncated = 0 8.00.646.473 I slot print_timing: id 3 | task 4874 | prompt eval time = 4646.55 ms / 2048 tokens ( 2.27 ms per token, 440.76 tokens per second) 8.00.646.476 I slot print_timing: id 3 | task 4874 | eval time = 363.61 ms / 2 tokens ( 363.61 ms per token, 2.75 tokens per second) 8.00.646.477 I slot print_timing: id 3 | task 4874 | total time = 5010.16 ms / 2050 tokens 8.00.646.477 I slot print_timing: id 3 | task 4874 | graphs reused = 3646 8.00.646.478 I slot print_timing: id 3 | task 4874 | graph reallocs = 428 / 0 (same size) / (changed size) 8.00.646.558 I slot release: id 3 | task 4874 | stop processing: n_tokens = 2049, truncated = 0 8.00.646.579 I slot print_timing: id 0 | task 4877 | prompt processing, n_tokens = 1848, progress = 1.00, t = 3.75 s / 493.41 tokens per second 8.00.766.893 I slot print_timing: id 1 | task 4881 | prompt eval time = 910.75 ms / 515 tokens ( 1.77 ms per token, 565.47 tokens per second) 8.00.766.899 I slot print_timing: id 1 | task 4881 | eval time = 121.22 ms / 2 tokens ( 121.22 ms per token, 8.25 tokens per second) 8.00.766.900 I slot print_timing: id 1 | task 4881 | total time = 1031.97 ms / 517 tokens 8.00.766.901 I slot print_timing: id 1 | task 4881 | graphs reused = 3646 8.00.766.902 I slot print_timing: id 1 | task 4881 | graph reallocs = 428 / 0 (same size) / (changed size) 8.00.766.994 I slot release: id 1 | task 4881 | stop processing: n_tokens = 1963, truncated = 0 8.00.767.018 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1842, t_last = 480553718 8.00.767.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.052 MiB) 8.00.827.805 I slot launch_slot_: id 2 | task 4885 | processing task, is_child = 0 8.00.827.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.553 MiB) 8.00.896.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.149 MiB) 8.00.964.031 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.833 (> 0.100 thold), f_keep = 0.756 8.00.964.187 I slot launch_slot_: id 1 | task 4886 | processing task, is_child = 0 8.00.964.307 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 2049, t_last = 480554181 8.00.964.539 I slot launch_slot_: id 3 | task 4887 | processing task, is_child = 0 8.01.432.875 I slot print_timing: id 0 | task 4877 | prompt eval time = 3866.96 ms / 1852 tokens ( 2.09 ms per token, 478.93 tokens per second) 8.01.432.881 I slot print_timing: id 0 | task 4877 | eval time = 666.29 ms / 2 tokens ( 666.29 ms per token, 1.50 tokens per second) 8.01.432.882 I slot print_timing: id 0 | task 4877 | total time = 4533.25 ms / 1854 tokens 8.01.432.883 I slot print_timing: id 0 | task 4877 | graphs reused = 3646 8.01.432.884 I slot print_timing: id 0 | task 4877 | graph reallocs = 429 / 0 (same size) / (changed size) 8.01.432.973 I slot release: id 0 | task 4877 | stop processing: n_tokens = 1853, truncated = 0 8.01.897.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1853, t_last = 481340596 8.01.897.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.148 MiB) 8.01.913.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.365 MiB) 8.01.969.884 I slot launch_slot_: id 0 | task 4890 | processing task, is_child = 0 8.02.791.552 I slot print_timing: id 1 | task 4886 | prompt eval time = 932.67 ms / 334 tokens ( 2.79 ms per token, 358.11 tokens per second) 8.02.791.567 I slot print_timing: id 1 | task 4886 | eval time = 894.30 ms / 2 tokens ( 894.30 ms per token, 1.12 tokens per second) 8.02.791.569 I slot print_timing: id 1 | task 4886 | total time = 1826.97 ms / 336 tokens 8.02.791.571 I slot print_timing: id 1 | task 4886 | graphs reused = 3646 8.02.791.572 I slot print_timing: id 1 | task 4886 | graph reallocs = 431 / 0 (same size) / (changed size) 8.02.791.740 I slot release: id 1 | task 4886 | stop processing: n_tokens = 1782, truncated = 0 8.03.291.737 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1782, t_last = 482699364 8.03.291.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.490 MiB) 8.03.343.597 I slot launch_slot_: id 1 | task 4893 | processing task, is_child = 0 8.04.224.844 I slot print_timing: id 2 | task 4885 | prompt eval time = 2872.29 ms / 726 tokens ( 3.96 ms per token, 252.76 tokens per second) 8.04.224.849 I slot print_timing: id 2 | task 4885 | eval time = 368.47 ms / 2 tokens ( 368.47 ms per token, 2.71 tokens per second) 8.04.224.850 I slot print_timing: id 2 | task 4885 | total time = 3240.75 ms / 728 tokens 8.04.224.851 I slot print_timing: id 2 | task 4885 | graphs reused = 3646 8.04.224.852 I slot print_timing: id 2 | task 4885 | graph reallocs = 434 / 0 (same size) / (changed size) 8.04.224.901 I slot release: id 2 | task 4885 | stop processing: n_tokens = 727, truncated = 0 8.04.225.172 I slot print_timing: id 3 | task 4887 | prompt eval time = 2869.14 ms / 748 tokens ( 3.84 ms per token, 260.71 tokens per second) 8.04.225.178 I slot print_timing: id 3 | task 4887 | eval time = 368.15 ms / 2 tokens ( 368.15 ms per token, 2.72 tokens per second) 8.04.225.179 I slot print_timing: id 3 | task 4887 | total time = 3237.29 ms / 750 tokens 8.04.225.179 I slot print_timing: id 3 | task 4887 | graphs reused = 3646 8.04.225.180 I slot print_timing: id 3 | task 4887 | graph reallocs = 434 / 0 (same size) / (changed size) 8.04.225.205 I slot release: id 3 | task 4887 | stop processing: n_tokens = 749, truncated = 0 8.04.527.469 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.870 (> 0.100 thold), f_keep = 0.884 8.04.527.708 I slot launch_slot_: id 2 | task 4897 | processing task, is_child = 0 8.04.527.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.615 MiB) 8.04.579.808 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 749, t_last = 484132827 8.04.580.042 I slot launch_slot_: id 3 | task 4898 | processing task, is_child = 0 8.05.123.579 I slot print_timing: id 0 | task 4890 | prompt eval time = 2557.55 ms / 761 tokens ( 3.36 ms per token, 297.55 tokens per second) 8.05.123.584 I slot print_timing: id 0 | task 4890 | eval time = 596.12 ms / 2 tokens ( 596.12 ms per token, 1.68 tokens per second) 8.05.123.585 I slot print_timing: id 0 | task 4890 | total time = 3153.66 ms / 763 tokens 8.05.123.586 I slot print_timing: id 0 | task 4890 | graphs reused = 3646 8.05.123.587 I slot print_timing: id 0 | task 4890 | graph reallocs = 434 / 0 (same size) / (changed size) 8.05.123.633 I slot release: id 0 | task 4890 | stop processing: n_tokens = 762, truncated = 0 8.05.415.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 762, t_last = 485031254 8.05.415.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.023 MiB) 8.05.463.071 I slot launch_slot_: id 0 | task 4901 | processing task, is_child = 0 8.05.879.558 I slot print_timing: id 1 | task 4893 | prompt eval time = 2060.47 ms / 725 tokens ( 2.84 ms per token, 351.86 tokens per second) 8.05.879.564 I slot print_timing: id 1 | task 4893 | eval time = 464.72 ms / 2 tokens ( 464.72 ms per token, 2.15 tokens per second) 8.05.879.565 I slot print_timing: id 1 | task 4893 | total time = 2525.18 ms / 727 tokens 8.05.879.566 I slot print_timing: id 1 | task 4893 | graphs reused = 3646 8.05.879.567 I slot print_timing: id 1 | task 4893 | graph reallocs = 434 / 0 (same size) / (changed size) 8.05.879.612 I slot release: id 1 | task 4893 | stop processing: n_tokens = 726, truncated = 0 8.05.880.019 I slot print_timing: id 2 | task 4897 | prompt eval time = 823.07 ms / 124 tokens ( 6.64 ms per token, 150.66 tokens per second) 8.05.880.024 I slot print_timing: id 2 | task 4897 | eval time = 464.53 ms / 2 tokens ( 464.53 ms per token, 2.15 tokens per second) 8.05.880.025 I slot print_timing: id 2 | task 4897 | total time = 1287.60 ms / 126 tokens 8.05.880.026 I slot print_timing: id 2 | task 4897 | graphs reused = 3646 8.05.880.026 I slot print_timing: id 2 | task 4897 | graph reallocs = 434 / 0 (same size) / (changed size) 8.05.880.062 I slot release: id 2 | task 4897 | stop processing: n_tokens = 740, truncated = 0 8.06.189.748 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 485787234 8.06.189.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.806 MiB) 8.06.255.721 I slot launch_slot_: id 1 | task 4904 | processing task, is_child = 0 8.06.255.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.431 MiB) 8.06.313.826 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 485787684 8.06.314.069 I slot launch_slot_: id 2 | task 4905 | processing task, is_child = 0 8.07.937.662 I slot print_timing: id 3 | task 4898 | prompt eval time = 2893.03 ms / 798 tokens ( 3.63 ms per token, 275.84 tokens per second) 8.07.937.668 I slot print_timing: id 3 | task 4898 | eval time = 431.64 ms / 2 tokens ( 431.64 ms per token, 2.32 tokens per second) 8.07.937.670 I slot print_timing: id 3 | task 4898 | total time = 3324.68 ms / 800 tokens 8.07.937.671 I slot print_timing: id 3 | task 4898 | graphs reused = 3646 8.07.937.672 I slot print_timing: id 3 | task 4898 | graph reallocs = 437 / 0 (same size) / (changed size) 8.07.937.733 I slot release: id 3 | task 4898 | stop processing: n_tokens = 799, truncated = 0 8.08.548.759 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 799, t_last = 487845355 8.08.548.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 280.900 MiB) 8.08.593.918 I slot launch_slot_: id 3 | task 4910 | processing task, is_child = 0 8.09.144.633 I slot print_timing: id 0 | task 4901 | prompt eval time = 3085.66 ms / 1042 tokens ( 2.96 ms per token, 337.69 tokens per second) 8.09.144.639 I slot print_timing: id 0 | task 4901 | eval time = 595.87 ms / 2 tokens ( 595.87 ms per token, 1.68 tokens per second) 8.09.144.641 I slot print_timing: id 0 | task 4901 | total time = 3681.53 ms / 1044 tokens 8.09.144.642 I slot print_timing: id 0 | task 4901 | graphs reused = 3646 8.09.144.643 I slot print_timing: id 0 | task 4901 | graph reallocs = 438 / 0 (same size) / (changed size) 8.09.144.703 I slot release: id 0 | task 4901 | stop processing: n_tokens = 1043, truncated = 0 8.09.445.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 489052325 8.09.445.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.588 MiB) 8.09.494.196 I slot launch_slot_: id 0 | task 4913 | processing task, is_child = 0 8.09.833.762 I slot print_timing: id 1 | task 4904 | prompt eval time = 3130.39 ms / 799 tokens ( 3.92 ms per token, 255.24 tokens per second) 8.09.833.767 I slot print_timing: id 1 | task 4904 | eval time = 389.27 ms / 2 tokens ( 389.27 ms per token, 2.57 tokens per second) 8.09.833.769 I slot print_timing: id 1 | task 4904 | total time = 3519.66 ms / 801 tokens 8.09.833.769 I slot print_timing: id 1 | task 4904 | graphs reused = 3646 8.09.833.770 I slot print_timing: id 1 | task 4904 | graph reallocs = 439 / 0 (same size) / (changed size) 8.09.833.817 I slot release: id 1 | task 4904 | stop processing: n_tokens = 800, truncated = 0 8.09.834.118 I slot print_timing: id 2 | task 4905 | prompt eval time = 3126.00 ms / 809 tokens ( 3.86 ms per token, 258.80 tokens per second) 8.09.834.123 I slot print_timing: id 2 | task 4905 | eval time = 388.95 ms / 2 tokens ( 388.95 ms per token, 2.57 tokens per second) 8.09.834.124 I slot print_timing: id 2 | task 4905 | total time = 3514.96 ms / 811 tokens 8.09.834.125 I slot print_timing: id 2 | task 4905 | graphs reused = 3646 8.09.834.125 I slot print_timing: id 2 | task 4905 | graph reallocs = 439 / 0 (same size) / (changed size) 8.09.834.154 I slot release: id 2 | task 4905 | stop processing: n_tokens = 810, truncated = 0 8.10.145.231 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 800, t_last = 489741438 8.10.145.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 8.10.226.047 I slot launch_slot_: id 1 | task 4916 | processing task, is_child = 0 8.10.226.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 8.10.287.409 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 810, t_last = 489741775 8.10.287.741 I slot launch_slot_: id 2 | task 4917 | processing task, is_child = 0 8.12.010.979 I slot print_timing: id 3 | task 4910 | prompt eval time = 2898.61 ms / 845 tokens ( 3.43 ms per token, 291.52 tokens per second) 8.12.010.985 I slot print_timing: id 3 | task 4910 | eval time = 493.10 ms / 2 tokens ( 493.10 ms per token, 2.03 tokens per second) 8.12.010.986 I slot print_timing: id 3 | task 4910 | total time = 3391.71 ms / 847 tokens 8.12.010.987 I slot print_timing: id 3 | task 4910 | graphs reused = 3646 8.12.010.988 I slot print_timing: id 3 | task 4910 | graph reallocs = 440 / 0 (same size) / (changed size) 8.12.011.038 I slot release: id 3 | task 4910 | stop processing: n_tokens = 846, truncated = 0 8.12.610.576 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.888 8.12.610.798 I slot launch_slot_: id 3 | task 4922 | processing task, is_child = 0 8.13.168.888 I slot print_timing: id 0 | task 4913 | prompt eval time = 3116.34 ms / 839 tokens ( 3.71 ms per token, 269.23 tokens per second) 8.13.168.893 I slot print_timing: id 0 | task 4913 | eval time = 558.32 ms / 2 tokens ( 558.32 ms per token, 1.79 tokens per second) 8.13.168.894 I slot print_timing: id 0 | task 4913 | total time = 3674.66 ms / 841 tokens 8.13.168.895 I slot print_timing: id 0 | task 4913 | graphs reused = 3646 8.13.168.896 I slot print_timing: id 0 | task 4913 | graph reallocs = 440 / 0 (same size) / (changed size) 8.13.168.945 I slot release: id 0 | task 4913 | stop processing: n_tokens = 840, truncated = 0 8.13.309.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 840, t_last = 493076567 8.13.309.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.775 MiB) 8.13.369.246 I slot launch_slot_: id 0 | task 4925 | processing task, is_child = 0 8.13.603.041 I slot print_timing: id 1 | task 4916 | prompt eval time = 3020.43 ms / 910 tokens ( 3.32 ms per token, 301.28 tokens per second) 8.13.603.047 I slot print_timing: id 1 | task 4916 | eval time = 294.83 ms / 2 tokens ( 294.83 ms per token, 3.39 tokens per second) 8.13.603.048 I slot print_timing: id 1 | task 4916 | total time = 3315.27 ms / 912 tokens 8.13.603.049 I slot print_timing: id 1 | task 4916 | graphs reused = 3646 8.13.603.050 I slot print_timing: id 1 | task 4916 | graph reallocs = 441 / 0 (same size) / (changed size) 8.13.603.102 I slot release: id 1 | task 4916 | stop processing: n_tokens = 911, truncated = 0 8.13.603.399 I slot print_timing: id 2 | task 4917 | prompt eval time = 3013.97 ms / 901 tokens ( 3.35 ms per token, 298.94 tokens per second) 8.13.603.403 I slot print_timing: id 2 | task 4917 | eval time = 294.57 ms / 2 tokens ( 294.57 ms per token, 3.39 tokens per second) 8.13.603.403 I slot print_timing: id 2 | task 4917 | total time = 3308.54 ms / 903 tokens 8.13.603.404 I slot print_timing: id 2 | task 4917 | graphs reused = 3646 8.13.603.404 I slot print_timing: id 2 | task 4917 | graph reallocs = 441 / 0 (same size) / (changed size) 8.13.603.433 I slot release: id 2 | task 4917 | stop processing: n_tokens = 902, truncated = 0 8.13.603.750 I slot print_timing: id 3 | task 4922 | prompt eval time = 677.53 ms / 139 tokens ( 4.87 ms per token, 205.16 tokens per second) 8.13.603.753 I slot print_timing: id 3 | task 4922 | eval time = 294.34 ms / 2 tokens ( 294.34 ms per token, 3.40 tokens per second) 8.13.603.754 I slot print_timing: id 3 | task 4922 | total time = 971.87 ms / 141 tokens 8.13.603.754 I slot print_timing: id 3 | task 4922 | graphs reused = 3646 8.13.603.755 I slot print_timing: id 3 | task 4922 | graph reallocs = 441 / 0 (same size) / (changed size) 8.13.603.780 I slot release: id 3 | task 4922 | stop processing: n_tokens = 863, truncated = 0 8.13.741.221 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 911, t_last = 493510724 8.13.741.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.087 MiB) 8.13.808.397 I slot launch_slot_: id 1 | task 4928 | processing task, is_child = 0 8.13.808.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.338 MiB) 8.13.857.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.367 MiB) 8.13.918.790 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 493511055 8.13.919.115 I slot launch_slot_: id 2 | task 4929 | processing task, is_child = 0 8.13.919.207 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 493511401 8.13.919.451 I slot launch_slot_: id 3 | task 4930 | processing task, is_child = 0 8.16.306.744 I slot print_timing: id 0 | task 4925 | prompt eval time = 2231.63 ms / 688 tokens ( 3.24 ms per token, 308.30 tokens per second) 8.16.306.750 I slot print_timing: id 0 | task 4925 | eval time = 705.84 ms / 2 tokens ( 705.84 ms per token, 1.42 tokens per second) 8.16.306.751 I slot print_timing: id 0 | task 4925 | total time = 2937.47 ms / 690 tokens 8.16.306.751 I slot print_timing: id 0 | task 4925 | graphs reused = 3646 8.16.306.752 I slot print_timing: id 0 | task 4925 | graph reallocs = 445 / 0 (same size) / (changed size) 8.16.306.798 I slot release: id 0 | task 4925 | stop processing: n_tokens = 689, truncated = 0 8.16.799.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 689, t_last = 496214419 8.16.799.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.399 MiB) 8.16.853.341 I slot launch_slot_: id 0 | task 4936 | processing task, is_child = 0 8.17.183.933 I slot print_timing: id 1 | task 4928 | prompt eval time = 2867.73 ms / 769 tokens ( 3.73 ms per token, 268.16 tokens per second) 8.17.183.939 I slot print_timing: id 1 | task 4928 | eval time = 384.60 ms / 2 tokens ( 384.60 ms per token, 2.60 tokens per second) 8.17.183.940 I slot print_timing: id 1 | task 4928 | total time = 3252.33 ms / 771 tokens 8.17.183.941 I slot print_timing: id 1 | task 4928 | graphs reused = 3646 8.17.183.942 I slot print_timing: id 1 | task 4928 | graph reallocs = 446 / 0 (same size) / (changed size) 8.17.183.991 I slot release: id 1 | task 4928 | stop processing: n_tokens = 770, truncated = 0 8.17.401.116 I slot print_timing: id 2 | task 4929 | prompt eval time = 3249.49 ms / 825 tokens ( 3.94 ms per token, 253.89 tokens per second) 8.17.401.122 I slot print_timing: id 2 | task 4929 | eval time = 216.31 ms / 2 tokens ( 216.31 ms per token, 4.62 tokens per second) 8.17.401.123 I slot print_timing: id 2 | task 4929 | total time = 3465.80 ms / 827 tokens 8.17.401.124 I slot print_timing: id 2 | task 4929 | graphs reused = 3646 8.17.401.124 I slot print_timing: id 2 | task 4929 | graph reallocs = 446 / 0 (same size) / (changed size) 8.17.401.174 I slot release: id 2 | task 4929 | stop processing: n_tokens = 826, truncated = 0 8.17.401.574 I slot print_timing: id 3 | task 4930 | prompt eval time = 3246.47 ms / 851 tokens ( 3.81 ms per token, 262.13 tokens per second) 8.17.401.579 I slot print_timing: id 3 | task 4930 | eval time = 216.04 ms / 2 tokens ( 216.04 ms per token, 4.63 tokens per second) 8.17.401.580 I slot print_timing: id 3 | task 4930 | total time = 3462.51 ms / 853 tokens 8.17.401.581 I slot print_timing: id 3 | task 4930 | graphs reused = 3646 8.17.401.582 I slot print_timing: id 3 | task 4930 | graph reallocs = 446 / 0 (same size) / (changed size) 8.17.401.622 I slot release: id 3 | task 4930 | stop processing: n_tokens = 852, truncated = 0 8.17.401.638 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 770, t_last = 497091613 8.17.443.820 I slot launch_slot_: id 1 | task 4939 | processing task, is_child = 0 8.17.443.923 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.493 MiB) 8.17.505.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.117 MiB) 8.17.564.813 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 497308796 8.17.565.029 I slot launch_slot_: id 2 | task 4940 | processing task, is_child = 0 8.17.565.086 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 852, t_last = 497309244 8.17.565.245 I slot launch_slot_: id 3 | task 4941 | processing task, is_child = 0 8.20.226.240 I slot print_timing: id 0 | task 4936 | prompt eval time = 2857.47 ms / 752 tokens ( 3.80 ms per token, 263.17 tokens per second) 8.20.226.246 I slot print_timing: id 0 | task 4936 | eval time = 515.39 ms / 2 tokens ( 515.39 ms per token, 1.94 tokens per second) 8.20.226.247 I slot print_timing: id 0 | task 4936 | total time = 3372.87 ms / 754 tokens 8.20.226.248 I slot print_timing: id 0 | task 4936 | graphs reused = 3646 8.20.226.249 I slot print_timing: id 0 | task 4936 | graph reallocs = 454 / 0 (same size) / (changed size) 8.20.226.293 I slot release: id 0 | task 4936 | stop processing: n_tokens = 753, truncated = 0 8.20.364.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 500133915 8.20.364.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.938 MiB) 8.20.426.505 I slot launch_slot_: id 0 | task 4947 | processing task, is_child = 0 8.20.650.117 I slot print_timing: id 1 | task 4939 | prompt eval time = 2787.36 ms / 713 tokens ( 3.91 ms per token, 255.80 tokens per second) 8.20.650.124 I slot print_timing: id 1 | task 4939 | eval time = 287.21 ms / 2 tokens ( 287.21 ms per token, 3.48 tokens per second) 8.20.650.125 I slot print_timing: id 1 | task 4939 | total time = 3074.57 ms / 715 tokens 8.20.650.126 I slot print_timing: id 1 | task 4939 | graphs reused = 3646 8.20.650.128 I slot print_timing: id 1 | task 4939 | graph reallocs = 455 / 0 (same size) / (changed size) 8.20.650.178 I slot release: id 1 | task 4939 | stop processing: n_tokens = 714, truncated = 0 8.20.650.590 I slot print_timing: id 2 | task 4940 | prompt eval time = 2784.29 ms / 736 tokens ( 3.78 ms per token, 264.34 tokens per second) 8.20.650.596 I slot print_timing: id 2 | task 4940 | eval time = 287.07 ms / 2 tokens ( 287.07 ms per token, 3.48 tokens per second) 8.20.650.598 I slot print_timing: id 2 | task 4940 | total time = 3071.35 ms / 738 tokens 8.20.650.599 I slot print_timing: id 2 | task 4940 | graphs reused = 3646 8.20.650.600 I slot print_timing: id 2 | task 4940 | graph reallocs = 455 / 0 (same size) / (changed size) 8.20.650.643 I slot release: id 2 | task 4940 | stop processing: n_tokens = 737, truncated = 0 8.20.651.075 I slot print_timing: id 3 | task 4941 | prompt eval time = 2781.14 ms / 719 tokens ( 3.87 ms per token, 258.53 tokens per second) 8.20.651.081 I slot print_timing: id 3 | task 4941 | eval time = 286.99 ms / 2 tokens ( 286.99 ms per token, 3.48 tokens per second) 8.20.651.081 I slot print_timing: id 3 | task 4941 | total time = 3068.13 ms / 721 tokens 8.20.651.083 I slot print_timing: id 3 | task 4941 | graphs reused = 3646 8.20.651.084 I slot print_timing: id 3 | task 4941 | graph reallocs = 455 / 0 (same size) / (changed size) 8.20.651.117 I slot release: id 3 | task 4941 | stop processing: n_tokens = 720, truncated = 0 8.20.791.556 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.884 8.20.791.739 I slot launch_slot_: id 1 | task 4950 | processing task, is_child = 0 8.20.791.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 289.594 MiB) 8.20.843.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 291.626 MiB) 8.20.905.784 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.893 (> 0.100 thold), f_keep = 0.856 8.20.906.002 I slot launch_slot_: id 2 | task 4951 | processing task, is_child = 0 8.20.906.090 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.876 8.20.906.264 I slot launch_slot_: id 3 | task 4952 | processing task, is_child = 0 8.22.029.664 I slot print_timing: id 1 | task 4950 | prompt eval time = 959.15 ms / 112 tokens ( 8.56 ms per token, 116.77 tokens per second) 8.22.029.670 I slot print_timing: id 1 | task 4950 | eval time = 151.53 ms / 2 tokens ( 151.53 ms per token, 6.60 tokens per second) 8.22.029.672 I slot print_timing: id 1 | task 4950 | total time = 1110.67 ms / 114 tokens 8.22.029.673 I slot print_timing: id 1 | task 4950 | graphs reused = 3646 8.22.029.674 I slot print_timing: id 1 | task 4950 | graph reallocs = 457 / 0 (same size) / (changed size) 8.22.029.730 I slot release: id 1 | task 4950 | stop processing: n_tokens = 716, truncated = 0 8.22.030.048 I slot print_timing: id 2 | task 4951 | prompt eval time = 938.70 ms / 104 tokens ( 9.03 ms per token, 110.79 tokens per second) 8.22.030.052 I slot print_timing: id 2 | task 4951 | eval time = 151.29 ms / 2 tokens ( 151.29 ms per token, 6.61 tokens per second) 8.22.030.053 I slot print_timing: id 2 | task 4951 | total time = 1090.00 ms / 106 tokens 8.22.030.054 I slot print_timing: id 2 | task 4951 | graphs reused = 3646 8.22.030.055 I slot print_timing: id 2 | task 4951 | graph reallocs = 457 / 0 (same size) / (changed size) 8.22.030.087 I slot release: id 2 | task 4951 | stop processing: n_tokens = 708, truncated = 0 8.22.030.413 I slot print_timing: id 3 | task 4952 | prompt eval time = 917.37 ms / 106 tokens ( 8.65 ms per token, 115.55 tokens per second) 8.22.030.418 I slot print_timing: id 3 | task 4952 | eval time = 151.10 ms / 2 tokens ( 151.10 ms per token, 6.62 tokens per second) 8.22.030.420 I slot print_timing: id 3 | task 4952 | total time = 1068.48 ms / 108 tokens 8.22.030.420 I slot print_timing: id 3 | task 4952 | graphs reused = 3646 8.22.030.421 I slot print_timing: id 3 | task 4952 | graph reallocs = 457 / 0 (same size) / (changed size) 8.22.030.448 I slot release: id 3 | task 4952 | stop processing: n_tokens = 710, truncated = 0 8.22.083.302 I slot print_timing: id 0 | task 4947 | prompt eval time = 1602.82 ms / 710 tokens ( 2.26 ms per token, 442.97 tokens per second) 8.22.083.307 I slot print_timing: id 0 | task 4947 | eval time = 53.95 ms / 2 tokens ( 53.95 ms per token, 18.53 tokens per second) 8.22.083.308 I slot print_timing: id 0 | task 4947 | total time = 1656.77 ms / 712 tokens 8.22.083.308 I slot print_timing: id 0 | task 4947 | graphs reused = 3646 8.22.083.309 I slot print_timing: id 0 | task 4947 | graph reallocs = 457 / 0 (same size) / (changed size) 8.22.083.351 I slot release: id 0 | task 4947 | stop processing: n_tokens = 711, truncated = 0 8.22.083.370 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 8.22.083.526 I slot launch_slot_: id 3 | task 4957 | processing task, is_child = 0 8.22.083.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 332.187 MiB) 8.22.144.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 329.467 MiB) 8.22.204.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 337.035 MiB) 8.22.268.128 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.883 (> 0.100 thold), f_keep = 0.893 8.22.268.277 I slot launch_slot_: id 2 | task 4958 | processing task, is_child = 0 8.22.268.385 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.887 8.22.268.488 I slot launch_slot_: id 0 | task 4959 | processing task, is_child = 0 8.22.268.538 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.890 (> 0.100 thold), f_keep = 0.881 8.22.268.630 I slot launch_slot_: id 1 | task 4960 | processing task, is_child = 0 8.23.097.943 I slot print_timing: id 0 | task 4959 | prompt eval time = 763.53 ms / 148 tokens ( 5.16 ms per token, 193.84 tokens per second) 8.23.097.949 I slot print_timing: id 0 | task 4959 | eval time = 65.76 ms / 2 tokens ( 65.76 ms per token, 15.21 tokens per second) 8.23.097.950 I slot print_timing: id 0 | task 4959 | total time = 829.29 ms / 150 tokens 8.23.097.951 I slot print_timing: id 0 | task 4959 | graphs reused = 3646 8.23.097.952 I slot print_timing: id 0 | task 4959 | graph reallocs = 457 / 0 (same size) / (changed size) 8.23.097.997 I slot release: id 0 | task 4959 | stop processing: n_tokens = 752, truncated = 0 8.23.098.360 I slot print_timing: id 1 | task 4960 | prompt eval time = 745.04 ms / 106 tokens ( 7.03 ms per token, 142.27 tokens per second) 8.23.098.364 I slot print_timing: id 1 | task 4960 | eval time = 65.60 ms / 2 tokens ( 65.60 ms per token, 15.24 tokens per second) 8.23.098.365 I slot print_timing: id 1 | task 4960 | total time = 810.64 ms / 108 tokens 8.23.098.366 I slot print_timing: id 1 | task 4960 | graphs reused = 3646 8.23.098.367 I slot print_timing: id 1 | task 4960 | graph reallocs = 457 / 0 (same size) / (changed size) 8.23.098.395 I slot release: id 1 | task 4960 | stop processing: n_tokens = 710, truncated = 0 8.23.098.849 I slot print_timing: id 2 | task 4958 | prompt eval time = 726.13 ms / 113 tokens ( 6.43 ms per token, 155.62 tokens per second) 8.23.098.855 I slot print_timing: id 2 | task 4958 | eval time = 65.45 ms / 2 tokens ( 65.45 ms per token, 15.28 tokens per second) 8.23.098.856 I slot print_timing: id 2 | task 4958 | total time = 791.58 ms / 115 tokens 8.23.098.857 I slot print_timing: id 2 | task 4958 | graphs reused = 3646 8.23.098.858 I slot print_timing: id 2 | task 4958 | graph reallocs = 457 / 0 (same size) / (changed size) 8.23.098.900 I slot release: id 2 | task 4958 | stop processing: n_tokens = 717, truncated = 0 8.23.099.354 I slot print_timing: id 3 | task 4957 | prompt eval time = 707.50 ms / 114 tokens ( 6.21 ms per token, 161.13 tokens per second) 8.23.099.360 I slot print_timing: id 3 | task 4957 | eval time = 65.36 ms / 2 tokens ( 65.36 ms per token, 15.30 tokens per second) 8.23.099.361 I slot print_timing: id 3 | task 4957 | total time = 772.86 ms / 116 tokens 8.23.099.362 I slot print_timing: id 3 | task 4957 | graphs reused = 3646 8.23.099.363 I slot print_timing: id 3 | task 4957 | graph reallocs = 457 / 0 (same size) / (changed size) 8.23.099.394 I slot release: id 3 | task 4957 | stop processing: n_tokens = 718, truncated = 0 8.23.114.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 503005619 8.23.114.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.314 MiB) 8.23.169.788 I slot launch_slot_: id 0 | task 4964 | processing task, is_child = 0 8.23.213.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 308.858 MiB) 8.23.276.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.642 MiB) 8.23.331.872 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 503006017 8.23.332.090 I slot launch_slot_: id 1 | task 4965 | processing task, is_child = 0 8.23.332.188 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 503006522 8.23.332.341 I slot launch_slot_: id 2 | task 4966 | processing task, is_child = 0 8.23.332.390 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 503007015 8.23.332.528 I slot launch_slot_: id 3 | task 4967 | processing task, is_child = 0 8.26.579.269 I slot print_timing: id 0 | task 4964 | prompt processing, n_tokens = 892, progress = 1.00, t = 3.25 s / 274.74 tokens per second 8.26.597.227 I slot print_timing: id 1 | task 4965 | prompt processing, n_tokens = 1078, progress = 1.00, t = 3.24 s / 332.40 tokens per second 8.26.607.273 I slot print_timing: id 2 | task 4966 | prompt processing, n_tokens = 1087, progress = 1.00, t = 3.24 s / 335.56 tokens per second 8.26.617.504 I slot print_timing: id 3 | task 4967 | prompt processing, n_tokens = 876, progress = 1.00, t = 3.24 s / 270.73 tokens per second 8.26.828.998 I slot print_timing: id 0 | task 4964 | prompt eval time = 3429.26 ms / 896 tokens ( 3.83 ms per token, 261.28 tokens per second) 8.26.829.004 I slot print_timing: id 0 | task 4964 | eval time = 67.19 ms / 2 tokens ( 67.19 ms per token, 14.88 tokens per second) 8.26.829.005 I slot print_timing: id 0 | task 4964 | total time = 3496.45 ms / 898 tokens 8.26.829.006 I slot print_timing: id 0 | task 4964 | graphs reused = 3646 8.26.829.007 I slot print_timing: id 0 | task 4964 | graph reallocs = 461 / 0 (same size) / (changed size) 8.26.829.059 I slot release: id 0 | task 4964 | stop processing: n_tokens = 897, truncated = 0 8.26.829.380 I slot print_timing: id 1 | task 4965 | prompt eval time = 3426.38 ms / 1082 tokens ( 3.17 ms per token, 315.79 tokens per second) 8.26.829.384 I slot print_timing: id 1 | task 4965 | eval time = 66.81 ms / 2 tokens ( 66.81 ms per token, 14.97 tokens per second) 8.26.829.385 I slot print_timing: id 1 | task 4965 | total time = 3493.19 ms / 1084 tokens 8.26.829.386 I slot print_timing: id 1 | task 4965 | graphs reused = 3646 8.26.829.386 I slot print_timing: id 1 | task 4965 | graph reallocs = 461 / 0 (same size) / (changed size) 8.26.829.431 I slot release: id 1 | task 4965 | stop processing: n_tokens = 1083, truncated = 0 8.26.829.767 I slot print_timing: id 2 | task 4966 | prompt eval time = 3423.45 ms / 1091 tokens ( 3.14 ms per token, 318.68 tokens per second) 8.26.829.771 I slot print_timing: id 2 | task 4966 | eval time = 66.44 ms / 2 tokens ( 66.44 ms per token, 15.05 tokens per second) 8.26.829.772 I slot print_timing: id 2 | task 4966 | total time = 3489.89 ms / 1093 tokens 8.26.829.773 I slot print_timing: id 2 | task 4966 | graphs reused = 3646 8.26.829.773 I slot print_timing: id 2 | task 4966 | graph reallocs = 461 / 0 (same size) / (changed size) 8.26.829.812 I slot release: id 2 | task 4966 | stop processing: n_tokens = 1092, truncated = 0 8.26.830.157 I slot print_timing: id 3 | task 4967 | prompt eval time = 3420.60 ms / 880 tokens ( 3.89 ms per token, 257.27 tokens per second) 8.26.830.161 I slot print_timing: id 3 | task 4967 | eval time = 66.03 ms / 2 tokens ( 66.03 ms per token, 15.14 tokens per second) 8.26.830.162 I slot print_timing: id 3 | task 4967 | total time = 3486.63 ms / 882 tokens 8.26.830.162 I slot print_timing: id 3 | task 4967 | graphs reused = 3646 8.26.830.163 I slot print_timing: id 3 | task 4967 | graph reallocs = 461 / 0 (same size) / (changed size) 8.26.830.202 I slot release: id 3 | task 4967 | stop processing: n_tokens = 881, truncated = 0 8.26.843.900 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.912 (> 0.100 thold), f_keep = 0.895 8.26.844.049 I slot launch_slot_: id 2 | task 4975 | processing task, is_child = 0 8.26.844.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.331 MiB) 8.26.903.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 309.202 MiB) 8.26.965.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 306.981 MiB) 8.27.030.252 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.900 (> 0.100 thold), f_keep = 0.901 8.27.030.415 I slot launch_slot_: id 1 | task 4976 | processing task, is_child = 0 8.27.030.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 506736680 8.27.044.933 I slot launch_slot_: id 0 | task 4977 | processing task, is_child = 0 8.27.045.015 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 506737823 8.27.045.176 I slot launch_slot_: id 3 | task 4978 | processing task, is_child = 0 8.28.401.054 I slot print_timing: id 0 | task 4977 | prompt eval time = 1133.83 ms / 174 tokens ( 6.52 ms per token, 153.46 tokens per second) 8.28.401.060 I slot print_timing: id 0 | task 4977 | eval time = 222.02 ms / 2 tokens ( 222.02 ms per token, 4.50 tokens per second) 8.28.401.061 I slot print_timing: id 0 | task 4977 | total time = 1355.86 ms / 176 tokens 8.28.401.062 I slot print_timing: id 0 | task 4977 | graphs reused = 3646 8.28.401.063 I slot print_timing: id 0 | task 4977 | graph reallocs = 462 / 0 (same size) / (changed size) 8.28.401.116 I slot release: id 0 | task 4977 | stop processing: n_tokens = 1080, truncated = 0 8.28.401.436 I slot print_timing: id 1 | task 4976 | prompt eval time = 1115.30 ms / 180 tokens ( 6.20 ms per token, 161.39 tokens per second) 8.28.401.439 I slot print_timing: id 1 | task 4976 | eval time = 221.86 ms / 2 tokens ( 221.86 ms per token, 4.51 tokens per second) 8.28.401.440 I slot print_timing: id 1 | task 4976 | total time = 1337.16 ms / 182 tokens 8.28.401.440 I slot print_timing: id 1 | task 4976 | graphs reused = 3646 8.28.401.441 I slot print_timing: id 1 | task 4976 | graph reallocs = 462 / 0 (same size) / (changed size) 8.28.401.472 I slot release: id 1 | task 4976 | stop processing: n_tokens = 1086, truncated = 0 8.28.401.790 I slot print_timing: id 2 | task 4975 | prompt eval time = 1096.87 ms / 166 tokens ( 6.61 ms per token, 151.34 tokens per second) 8.28.401.793 I slot print_timing: id 2 | task 4975 | eval time = 221.67 ms / 2 tokens ( 221.67 ms per token, 4.51 tokens per second) 8.28.401.794 I slot print_timing: id 2 | task 4975 | total time = 1318.54 ms / 168 tokens 8.28.401.795 I slot print_timing: id 2 | task 4975 | graphs reused = 3646 8.28.401.796 I slot print_timing: id 2 | task 4975 | graph reallocs = 462 / 0 (same size) / (changed size) 8.28.401.822 I slot release: id 2 | task 4975 | stop processing: n_tokens = 1072, truncated = 0 8.28.539.032 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.911 (> 0.100 thold), f_keep = 0.905 8.28.539.258 I slot launch_slot_: id 0 | task 4983 | processing task, is_child = 0 8.28.604.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.676 MiB) 8.28.658.229 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.900 8.28.658.397 I slot launch_slot_: id 1 | task 4984 | processing task, is_child = 0 8.28.658.473 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.898 (> 0.100 thold), f_keep = 0.911 8.28.658.595 I slot launch_slot_: id 2 | task 4985 | processing task, is_child = 0 8.29.666.720 I slot print_timing: id 0 | task 4983 | prompt eval time = 939.93 ms / 168 tokens ( 5.59 ms per token, 178.74 tokens per second) 8.29.666.726 I slot print_timing: id 0 | task 4983 | eval time = 68.17 ms / 2 tokens ( 68.17 ms per token, 14.67 tokens per second) 8.29.666.727 I slot print_timing: id 0 | task 4983 | total time = 1008.10 ms / 170 tokens 8.29.666.728 I slot print_timing: id 0 | task 4983 | graphs reused = 3646 8.29.666.729 I slot print_timing: id 0 | task 4983 | graph reallocs = 465 / 0 (same size) / (changed size) 8.29.666.779 I slot release: id 0 | task 4983 | stop processing: n_tokens = 1074, truncated = 0 8.29.667.079 I slot print_timing: id 1 | task 4984 | prompt eval time = 920.44 ms / 177 tokens ( 5.20 ms per token, 192.30 tokens per second) 8.29.667.082 I slot print_timing: id 1 | task 4984 | eval time = 67.95 ms / 2 tokens ( 67.95 ms per token, 14.72 tokens per second) 8.29.667.083 I slot print_timing: id 1 | task 4984 | total time = 988.39 ms / 179 tokens 8.29.667.083 I slot print_timing: id 1 | task 4984 | graphs reused = 3646 8.29.667.084 I slot print_timing: id 1 | task 4984 | graph reallocs = 465 / 0 (same size) / (changed size) 8.29.667.116 I slot release: id 1 | task 4984 | stop processing: n_tokens = 1083, truncated = 0 8.29.667.448 I slot print_timing: id 2 | task 4985 | prompt eval time = 897.46 ms / 183 tokens ( 4.90 ms per token, 203.91 tokens per second) 8.29.667.453 I slot print_timing: id 2 | task 4985 | eval time = 67.75 ms / 2 tokens ( 67.75 ms per token, 14.76 tokens per second) 8.29.667.454 I slot print_timing: id 2 | task 4985 | total time = 965.21 ms / 185 tokens 8.29.667.455 I slot print_timing: id 2 | task 4985 | graphs reused = 3646 8.29.667.456 I slot print_timing: id 2 | task 4985 | graph reallocs = 465 / 0 (same size) / (changed size) 8.29.667.488 I slot release: id 2 | task 4985 | stop processing: n_tokens = 1089, truncated = 0 8.29.667.840 I slot print_timing: id 3 | task 4978 | prompt eval time = 2497.96 ms / 1080 tokens ( 2.31 ms per token, 432.35 tokens per second) 8.29.667.845 I slot print_timing: id 3 | task 4978 | eval time = 67.58 ms / 2 tokens ( 67.58 ms per token, 14.80 tokens per second) 8.29.667.846 I slot print_timing: id 3 | task 4978 | total time = 2565.54 ms / 1082 tokens 8.29.667.847 I slot print_timing: id 3 | task 4978 | graphs reused = 3646 8.29.667.847 I slot print_timing: id 3 | task 4978 | graph reallocs = 465 / 0 (same size) / (changed size) 8.29.667.874 I slot release: id 3 | task 4978 | stop processing: n_tokens = 1081, truncated = 0 8.29.683.062 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.905 (> 0.100 thold), f_keep = 0.910 8.29.683.235 I slot launch_slot_: id 0 | task 4989 | processing task, is_child = 0 8.29.683.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.083 MiB) 8.29.743.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.957 MiB) 8.29.806.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 8.29.865.633 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.909 (> 0.100 thold), f_keep = 0.902 8.29.865.795 I slot launch_slot_: id 1 | task 4990 | processing task, is_child = 0 8.29.865.930 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.897 8.29.866.025 I slot launch_slot_: id 2 | task 4991 | processing task, is_child = 0 8.29.866.090 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.902 (> 0.100 thold), f_keep = 0.904 8.29.866.178 I slot launch_slot_: id 3 | task 4992 | processing task, is_child = 0 8.30.800.053 I slot print_timing: id 0 | task 4989 | prompt eval time = 865.14 ms / 175 tokens ( 4.94 ms per token, 202.28 tokens per second) 8.30.800.061 I slot print_timing: id 0 | task 4989 | eval time = 68.71 ms / 2 tokens ( 68.71 ms per token, 14.55 tokens per second) 8.30.800.062 I slot print_timing: id 0 | task 4989 | total time = 933.85 ms / 177 tokens 8.30.800.063 I slot print_timing: id 0 | task 4989 | graphs reused = 3646 8.30.800.064 I slot print_timing: id 0 | task 4989 | graph reallocs = 467 / 0 (same size) / (changed size) 8.30.800.121 I slot release: id 0 | task 4989 | stop processing: n_tokens = 1081, truncated = 0 8.30.800.472 I slot print_timing: id 1 | task 4990 | prompt eval time = 846.78 ms / 170 tokens ( 4.98 ms per token, 200.76 tokens per second) 8.30.800.479 I slot print_timing: id 1 | task 4990 | eval time = 68.43 ms / 2 tokens ( 68.43 ms per token, 14.61 tokens per second) 8.30.800.480 I slot print_timing: id 1 | task 4990 | total time = 915.22 ms / 172 tokens 8.30.800.480 I slot print_timing: id 1 | task 4990 | graphs reused = 3646 8.30.800.481 I slot print_timing: id 1 | task 4990 | graph reallocs = 467 / 0 (same size) / (changed size) 8.30.800.520 I slot release: id 1 | task 4990 | stop processing: n_tokens = 1076, truncated = 0 8.30.800.920 I slot print_timing: id 2 | task 4991 | prompt eval time = 828.44 ms / 171 tokens ( 4.84 ms per token, 206.41 tokens per second) 8.30.800.927 I slot print_timing: id 2 | task 4991 | eval time = 68.02 ms / 2 tokens ( 68.02 ms per token, 14.70 tokens per second) 8.30.800.928 I slot print_timing: id 2 | task 4991 | total time = 896.46 ms / 173 tokens 8.30.800.929 I slot print_timing: id 2 | task 4991 | graphs reused = 3646 8.30.800.929 I slot print_timing: id 2 | task 4991 | graph reallocs = 467 / 0 (same size) / (changed size) 8.30.800.962 I slot release: id 2 | task 4991 | stop processing: n_tokens = 1077, truncated = 0 8.30.801.312 I slot print_timing: id 3 | task 4992 | prompt eval time = 810.07 ms / 178 tokens ( 4.55 ms per token, 219.74 tokens per second) 8.30.801.316 I slot print_timing: id 3 | task 4992 | eval time = 67.53 ms / 2 tokens ( 67.53 ms per token, 14.81 tokens per second) 8.30.801.317 I slot print_timing: id 3 | task 4992 | total time = 877.60 ms / 180 tokens 8.30.801.317 I slot print_timing: id 3 | task 4992 | graphs reused = 3646 8.30.801.318 I slot print_timing: id 3 | task 4992 | graph reallocs = 467 / 0 (same size) / (changed size) 8.30.801.343 I slot release: id 3 | task 4992 | stop processing: n_tokens = 1084, truncated = 0 8.30.818.494 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.904 8.30.818.681 I slot launch_slot_: id 0 | task 4996 | processing task, is_child = 0 8.30.818.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.240 MiB) 8.30.877.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.871 MiB) 8.30.940.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.271 MiB) 8.31.002.322 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1076, t_last = 510708142 8.31.002.551 I slot launch_slot_: id 1 | task 4997 | processing task, is_child = 0 8.31.002.673 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1077, t_last = 510708583 8.31.002.837 I slot launch_slot_: id 2 | task 4998 | processing task, is_child = 0 8.31.002.905 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 8.31.002.999 I slot launch_slot_: id 3 | task 4999 | processing task, is_child = 0 8.32.447.195 I slot print_timing: id 0 | task 4996 | prompt eval time = 1040.79 ms / 173 tokens ( 6.02 ms per token, 166.22 tokens per second) 8.32.447.202 I slot print_timing: id 0 | task 4996 | eval time = 403.39 ms / 2 tokens ( 403.39 ms per token, 2.48 tokens per second) 8.32.447.203 I slot print_timing: id 0 | task 4996 | total time = 1444.17 ms / 175 tokens 8.32.447.204 I slot print_timing: id 0 | task 4996 | graphs reused = 3646 8.32.447.205 I slot print_timing: id 0 | task 4996 | graph reallocs = 467 / 0 (same size) / (changed size) 8.32.447.271 I slot release: id 0 | task 4996 | stop processing: n_tokens = 1079, truncated = 0 8.32.447.690 I slot print_timing: id 3 | task 4999 | prompt eval time = 1014.21 ms / 174 tokens ( 5.83 ms per token, 171.56 tokens per second) 8.32.447.694 I slot print_timing: id 3 | task 4999 | eval time = 403.31 ms / 2 tokens ( 403.31 ms per token, 2.48 tokens per second) 8.32.447.695 I slot print_timing: id 3 | task 4999 | total time = 1417.53 ms / 176 tokens 8.32.447.696 I slot print_timing: id 3 | task 4999 | graphs reused = 3646 8.32.447.697 I slot print_timing: id 3 | task 4999 | graph reallocs = 467 / 0 (same size) / (changed size) 8.32.447.740 I slot release: id 3 | task 4999 | stop processing: n_tokens = 1080, truncated = 0 8.32.945.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 512354893 8.32.945.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.584 MiB) 8.33.001.272 I slot launch_slot_: id 0 | task 5004 | processing task, is_child = 0 8.33.001.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.522 MiB) 8.33.064.452 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1080, t_last = 512355362 8.33.064.789 I slot launch_slot_: id 3 | task 5005 | processing task, is_child = 0 8.34.910.139 I slot print_timing: id 1 | task 4997 | prompt eval time = 3480.99 ms / 1017 tokens ( 3.42 ms per token, 292.16 tokens per second) 8.34.910.144 I slot print_timing: id 1 | task 4997 | eval time = 406.56 ms / 2 tokens ( 406.56 ms per token, 2.46 tokens per second) 8.34.910.146 I slot print_timing: id 1 | task 4997 | total time = 3887.55 ms / 1019 tokens 8.34.910.147 I slot print_timing: id 1 | task 4997 | graphs reused = 3646 8.34.910.147 I slot print_timing: id 1 | task 4997 | graph reallocs = 468 / 0 (same size) / (changed size) 8.34.910.201 I slot release: id 1 | task 4997 | stop processing: n_tokens = 1018, truncated = 0 8.34.910.584 I slot print_timing: id 2 | task 4998 | prompt eval time = 3477.87 ms / 1031 tokens ( 3.37 ms per token, 296.45 tokens per second) 8.34.910.587 I slot print_timing: id 2 | task 4998 | eval time = 406.37 ms / 2 tokens ( 406.37 ms per token, 2.46 tokens per second) 8.34.910.588 I slot print_timing: id 2 | task 4998 | total time = 3884.24 ms / 1033 tokens 8.34.910.588 I slot print_timing: id 2 | task 4998 | graphs reused = 3646 8.34.910.589 I slot print_timing: id 2 | task 4998 | graph reallocs = 468 / 0 (same size) / (changed size) 8.34.910.629 I slot release: id 2 | task 4998 | stop processing: n_tokens = 1032, truncated = 0 8.35.241.021 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.890 8.35.241.237 I slot launch_slot_: id 1 | task 5010 | processing task, is_child = 0 8.35.241.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.743 MiB) 8.35.298.323 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.878 8.35.298.535 I slot launch_slot_: id 2 | task 5011 | processing task, is_child = 0 8.36.286.677 I slot print_timing: id 0 | task 5004 | prompt processing, n_tokens = 1067, progress = 1.00, t = 3.22 s / 331.18 tokens per second 8.36.331.351 I slot print_timing: id 3 | task 5005 | prompt processing, n_tokens = 1102, progress = 1.00, t = 3.19 s / 345.60 tokens per second 8.36.543.216 I slot print_timing: id 0 | task 5004 | prompt eval time = 3412.77 ms / 1071 tokens ( 3.19 ms per token, 313.82 tokens per second) 8.36.543.222 I slot print_timing: id 0 | task 5004 | eval time = 65.63 ms / 2 tokens ( 65.63 ms per token, 15.24 tokens per second) 8.36.543.223 I slot print_timing: id 0 | task 5004 | total time = 3478.40 ms / 1073 tokens 8.36.543.224 I slot print_timing: id 0 | task 5004 | graphs reused = 3646 8.36.543.225 I slot print_timing: id 0 | task 5004 | graph reallocs = 470 / 0 (same size) / (changed size) 8.36.543.279 I slot release: id 0 | task 5004 | stop processing: n_tokens = 1072, truncated = 0 8.36.543.555 I slot print_timing: id 1 | task 5010 | prompt eval time = 1166.89 ms / 167 tokens ( 6.99 ms per token, 143.12 tokens per second) 8.36.543.558 I slot print_timing: id 1 | task 5010 | eval time = 65.42 ms / 2 tokens ( 65.42 ms per token, 15.29 tokens per second) 8.36.543.559 I slot print_timing: id 1 | task 5010 | total time = 1232.31 ms / 169 tokens 8.36.543.559 I slot print_timing: id 1 | task 5010 | graphs reused = 3646 8.36.543.560 I slot print_timing: id 1 | task 5010 | graph reallocs = 470 / 0 (same size) / (changed size) 8.36.543.590 I slot release: id 1 | task 5010 | stop processing: n_tokens = 1046, truncated = 0 8.36.543.872 I slot print_timing: id 2 | task 5011 | prompt eval time = 1147.50 ms / 152 tokens ( 7.55 ms per token, 132.46 tokens per second) 8.36.543.875 I slot print_timing: id 2 | task 5011 | eval time = 65.17 ms / 2 tokens ( 65.17 ms per token, 15.34 tokens per second) 8.36.543.875 I slot print_timing: id 2 | task 5011 | total time = 1212.67 ms / 154 tokens 8.36.543.876 I slot print_timing: id 2 | task 5011 | graphs reused = 3646 8.36.543.877 I slot print_timing: id 2 | task 5011 | graph reallocs = 470 / 0 (same size) / (changed size) 8.36.543.902 I slot release: id 2 | task 5011 | stop processing: n_tokens = 1031, truncated = 0 8.36.544.266 I slot print_timing: id 3 | task 5005 | prompt eval time = 3381.22 ms / 1106 tokens ( 3.06 ms per token, 327.10 tokens per second) 8.36.544.270 I slot print_timing: id 3 | task 5005 | eval time = 65.02 ms / 2 tokens ( 65.02 ms per token, 15.38 tokens per second) 8.36.544.271 I slot print_timing: id 3 | task 5005 | total time = 3446.24 ms / 1108 tokens 8.36.544.271 I slot print_timing: id 3 | task 5005 | graphs reused = 3646 8.36.544.272 I slot print_timing: id 3 | task 5005 | graph reallocs = 470 / 0 (same size) / (changed size) 8.36.544.312 I slot release: id 3 | task 5005 | stop processing: n_tokens = 1107, truncated = 0 8.36.557.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1072, t_last = 516450900 8.36.557.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.461 MiB) 8.36.619.140 I slot launch_slot_: id 0 | task 5015 | processing task, is_child = 0 8.36.619.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.242 MiB) 8.36.681.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.800 MiB) 8.36.742.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.333 MiB) 8.36.789.482 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1046, t_last = 516451212 8.36.789.687 I slot launch_slot_: id 1 | task 5016 | processing task, is_child = 0 8.36.789.810 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1031, t_last = 516451524 8.36.789.967 I slot launch_slot_: id 2 | task 5017 | processing task, is_child = 0 8.36.790.032 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1107, t_last = 516451934 8.36.790.185 I slot launch_slot_: id 3 | task 5018 | processing task, is_child = 0 8.39.931.942 I slot print_timing: id 0 | task 5015 | prompt eval time = 2945.87 ms / 753 tokens ( 3.91 ms per token, 255.61 tokens per second) 8.39.931.949 I slot print_timing: id 0 | task 5015 | eval time = 195.87 ms / 2 tokens ( 195.87 ms per token, 5.11 tokens per second) 8.39.931.951 I slot print_timing: id 0 | task 5015 | total time = 3141.73 ms / 755 tokens 8.39.931.951 I slot print_timing: id 0 | task 5015 | graphs reused = 3646 8.39.931.952 I slot print_timing: id 0 | task 5015 | graph reallocs = 475 / 0 (same size) / (changed size) 8.39.932.000 I slot release: id 0 | task 5015 | stop processing: n_tokens = 754, truncated = 0 8.39.932.928 I slot print_timing: id 2 | task 5017 | prompt eval time = 2939.06 ms / 729 tokens ( 4.03 ms per token, 248.04 tokens per second) 8.39.932.933 I slot print_timing: id 2 | task 5017 | eval time = 196.29 ms / 2 tokens ( 196.29 ms per token, 5.09 tokens per second) 8.39.932.934 I slot print_timing: id 2 | task 5017 | total time = 3135.35 ms / 731 tokens 8.39.932.935 I slot print_timing: id 2 | task 5017 | graphs reused = 3646 8.39.932.935 I slot print_timing: id 2 | task 5017 | graph reallocs = 475 / 0 (same size) / (changed size) 8.39.932.964 I slot release: id 2 | task 5017 | stop processing: n_tokens = 730, truncated = 0 8.39.933.269 I slot print_timing: id 3 | task 5018 | prompt eval time = 2935.92 ms / 740 tokens ( 3.97 ms per token, 252.05 tokens per second) 8.39.933.274 I slot print_timing: id 3 | task 5018 | eval time = 196.05 ms / 2 tokens ( 196.05 ms per token, 5.10 tokens per second) 8.39.933.275 I slot print_timing: id 3 | task 5018 | total time = 3131.97 ms / 742 tokens 8.39.933.275 I slot print_timing: id 3 | task 5018 | graphs reused = 3646 8.39.933.276 I slot print_timing: id 3 | task 5018 | graph reallocs = 475 / 0 (same size) / (changed size) 8.39.933.300 I slot release: id 3 | task 5018 | stop processing: n_tokens = 741, truncated = 0 8.39.985.029 I slot print_timing: id 1 | task 5016 | prompt eval time = 3138.74 ms / 797 tokens ( 3.94 ms per token, 253.92 tokens per second) 8.39.985.036 I slot print_timing: id 1 | task 5016 | eval time = 52.38 ms / 2 tokens ( 52.38 ms per token, 19.09 tokens per second) 8.39.985.037 I slot print_timing: id 1 | task 5016 | total time = 3191.12 ms / 799 tokens 8.39.985.040 I slot print_timing: id 1 | task 5016 | graphs reused = 3646 8.39.985.041 I slot print_timing: id 1 | task 5016 | graph reallocs = 475 / 0 (same size) / (changed size) 8.39.985.097 I slot release: id 1 | task 5016 | stop processing: n_tokens = 798, truncated = 0 8.39.985.123 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.873 (> 0.100 thold), f_keep = 0.863 8.39.985.361 I slot launch_slot_: id 0 | task 5026 | processing task, is_child = 0 8.39.985.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.085 MiB) 8.40.045.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 277.898 MiB) 8.40.100.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.802 MiB) 8.40.158.487 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.881 8.40.158.695 I slot launch_slot_: id 3 | task 5027 | processing task, is_child = 0 8.40.158.859 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.816 8.40.159.015 I slot launch_slot_: id 1 | task 5028 | processing task, is_child = 0 8.40.159.068 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.862 (> 0.100 thold), f_keep = 0.892 8.40.159.186 I slot launch_slot_: id 2 | task 5029 | processing task, is_child = 0 8.41.028.697 I slot print_timing: id 0 | task 5026 | prompt eval time = 803.54 ms / 123 tokens ( 6.53 ms per token, 153.07 tokens per second) 8.41.028.704 I slot print_timing: id 0 | task 5026 | eval time = 65.95 ms / 2 tokens ( 65.95 ms per token, 15.16 tokens per second) 8.41.028.705 I slot print_timing: id 0 | task 5026 | total time = 869.49 ms / 125 tokens 8.41.028.706 I slot print_timing: id 0 | task 5026 | graphs reused = 3646 8.41.028.707 I slot print_timing: id 0 | task 5026 | graph reallocs = 478 / 0 (same size) / (changed size) 8.41.028.762 I slot release: id 0 | task 5026 | stop processing: n_tokens = 747, truncated = 0 8.41.029.073 I slot print_timing: id 1 | task 5028 | prompt eval time = 784.15 ms / 110 tokens ( 7.13 ms per token, 140.28 tokens per second) 8.41.029.076 I slot print_timing: id 1 | task 5028 | eval time = 65.78 ms / 2 tokens ( 65.78 ms per token, 15.20 tokens per second) 8.41.029.078 I slot print_timing: id 1 | task 5028 | total time = 849.93 ms / 112 tokens 8.41.029.078 I slot print_timing: id 1 | task 5028 | graphs reused = 3646 8.41.029.080 I slot print_timing: id 1 | task 5028 | graph reallocs = 478 / 0 (same size) / (changed size) 8.41.029.109 I slot release: id 1 | task 5028 | stop processing: n_tokens = 734, truncated = 0 8.41.029.433 I slot print_timing: id 2 | task 5029 | prompt eval time = 765.90 ms / 132 tokens ( 5.80 ms per token, 172.35 tokens per second) 8.41.029.436 I slot print_timing: id 2 | task 5029 | eval time = 65.60 ms / 2 tokens ( 65.60 ms per token, 15.24 tokens per second) 8.41.029.437 I slot print_timing: id 2 | task 5029 | total time = 831.51 ms / 134 tokens 8.41.029.438 I slot print_timing: id 2 | task 5029 | graphs reused = 3646 8.41.029.439 I slot print_timing: id 2 | task 5029 | graph reallocs = 478 / 0 (same size) / (changed size) 8.41.029.469 I slot release: id 2 | task 5029 | stop processing: n_tokens = 756, truncated = 0 8.41.029.814 I slot print_timing: id 3 | task 5027 | prompt eval time = 747.63 ms / 116 tokens ( 6.45 ms per token, 155.16 tokens per second) 8.41.029.818 I slot print_timing: id 3 | task 5027 | eval time = 65.43 ms / 2 tokens ( 65.43 ms per token, 15.28 tokens per second) 8.41.029.819 I slot print_timing: id 3 | task 5027 | total time = 813.05 ms / 118 tokens 8.41.029.820 I slot print_timing: id 3 | task 5027 | graphs reused = 3646 8.41.029.821 I slot print_timing: id 3 | task 5027 | graph reallocs = 478 / 0 (same size) / (changed size) 8.41.029.846 I slot release: id 3 | task 5027 | stop processing: n_tokens = 740, truncated = 0 8.41.044.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 747, t_last = 520936383 8.41.045.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 8.41.104.081 I slot launch_slot_: id 0 | task 5033 | processing task, is_child = 0 8.41.104.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.770 MiB) 8.41.163.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 8.41.221.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.644 MiB) 8.41.274.797 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 520936730 8.41.274.998 I slot launch_slot_: id 1 | task 5034 | processing task, is_child = 0 8.41.275.103 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.871 (> 0.100 thold), f_keep = 0.861 8.41.275.198 I slot launch_slot_: id 2 | task 5035 | processing task, is_child = 0 8.41.275.247 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 740, t_last = 520937468 8.41.275.381 I slot launch_slot_: id 3 | task 5036 | processing task, is_child = 0 8.42.841.410 I slot print_timing: id 2 | task 5035 | prompt eval time = 1061.68 ms / 124 tokens ( 8.56 ms per token, 116.80 tokens per second) 8.42.841.416 I slot print_timing: id 2 | task 5035 | eval time = 493.18 ms / 2 tokens ( 493.18 ms per token, 2.03 tokens per second) 8.42.841.417 I slot print_timing: id 2 | task 5035 | total time = 1554.85 ms / 126 tokens 8.42.841.418 I slot print_timing: id 2 | task 5035 | graphs reused = 3646 8.42.841.419 I slot print_timing: id 2 | task 5035 | graph reallocs = 478 / 0 (same size) / (changed size) 8.42.841.471 I slot release: id 2 | task 5035 | stop processing: n_tokens = 748, truncated = 0 8.43.521.747 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 522749093 8.43.521.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.394 MiB) 8.43.588.746 I slot launch_slot_: id 2 | task 5041 | processing task, is_child = 0 8.44.345.781 I slot print_timing: id 0 | task 5033 | prompt processing, n_tokens = 986, progress = 1.00, t = 3.07 s / 321.13 tokens per second 8.44.364.402 I slot print_timing: id 1 | task 5034 | prompt processing, n_tokens = 951, progress = 1.00, t = 3.07 s / 310.10 tokens per second 8.44.387.690 I slot print_timing: id 3 | task 5036 | prompt processing, n_tokens = 969, progress = 1.00, t = 3.04 s / 318.82 tokens per second 8.44.970.519 I slot print_timing: id 0 | task 5033 | prompt eval time = 3409.64 ms / 990 tokens ( 3.44 ms per token, 290.35 tokens per second) 8.44.970.527 I slot print_timing: id 0 | task 5033 | eval time = 285.47 ms / 2 tokens ( 285.47 ms per token, 3.50 tokens per second) 8.44.970.528 I slot print_timing: id 0 | task 5033 | total time = 3695.11 ms / 992 tokens 8.44.970.531 I slot print_timing: id 0 | task 5033 | graphs reused = 3646 8.44.970.532 I slot print_timing: id 0 | task 5033 | graph reallocs = 483 / 0 (same size) / (changed size) 8.44.970.610 I slot release: id 0 | task 5033 | stop processing: n_tokens = 991, truncated = 0 8.44.971.009 I slot print_timing: id 1 | task 5034 | prompt eval time = 3406.67 ms / 955 tokens ( 3.57 ms per token, 280.33 tokens per second) 8.44.971.014 I slot print_timing: id 1 | task 5034 | eval time = 285.28 ms / 2 tokens ( 285.28 ms per token, 3.51 tokens per second) 8.44.971.015 I slot print_timing: id 1 | task 5034 | total time = 3691.96 ms / 957 tokens 8.44.971.015 I slot print_timing: id 1 | task 5034 | graphs reused = 3646 8.44.971.016 I slot print_timing: id 1 | task 5034 | graph reallocs = 483 / 0 (same size) / (changed size) 8.44.971.058 I slot release: id 1 | task 5034 | stop processing: n_tokens = 956, truncated = 0 8.44.971.480 I slot print_timing: id 3 | task 5036 | prompt eval time = 3380.00 ms / 973 tokens ( 3.47 ms per token, 287.87 tokens per second) 8.44.971.485 I slot print_timing: id 3 | task 5036 | eval time = 285.07 ms / 2 tokens ( 285.07 ms per token, 3.51 tokens per second) 8.44.971.486 I slot print_timing: id 3 | task 5036 | total time = 3665.07 ms / 975 tokens 8.44.971.487 I slot print_timing: id 3 | task 5036 | graphs reused = 3646 8.44.971.488 I slot print_timing: id 3 | task 5036 | graph reallocs = 483 / 0 (same size) / (changed size) 8.44.971.537 I slot release: id 3 | task 5036 | stop processing: n_tokens = 974, truncated = 0 8.45.107.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 524878233 8.45.107.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.770 MiB) 8.45.167.268 I slot launch_slot_: id 0 | task 5046 | processing task, is_child = 0 8.45.167.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.457 MiB) 8.45.223.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.676 MiB) 8.45.282.474 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 524878680 8.45.282.725 I slot launch_slot_: id 1 | task 5047 | processing task, is_child = 0 8.45.282.788 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 974, t_last = 524879159 8.45.282.971 I slot launch_slot_: id 3 | task 5048 | processing task, is_child = 0 8.47.658.516 I slot print_timing: id 2 | task 5041 | prompt eval time = 3078.90 ms / 1044 tokens ( 2.95 ms per token, 339.08 tokens per second) 8.47.658.521 I slot print_timing: id 2 | task 5041 | eval time = 965.56 ms / 2 tokens ( 965.56 ms per token, 1.04 tokens per second) 8.47.658.522 I slot print_timing: id 2 | task 5041 | total time = 4044.46 ms / 1046 tokens 8.47.658.523 I slot print_timing: id 2 | task 5041 | graphs reused = 3646 8.47.658.523 I slot print_timing: id 2 | task 5041 | graph reallocs = 488 / 0 (same size) / (changed size) 8.47.658.584 I slot release: id 2 | task 5041 | stop processing: n_tokens = 1045, truncated = 0 8.48.174.531 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1045, t_last = 527566205 8.48.174.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.707 MiB) 8.48.239.648 I slot launch_slot_: id 2 | task 5053 | processing task, is_child = 0 8.49.129.724 I slot print_timing: id 0 | task 5046 | prompt processing, n_tokens = 1157, progress = 1.00, t = 3.85 s / 300.78 tokens per second 8.49.148.856 I slot print_timing: id 1 | task 5047 | prompt processing, n_tokens = 2087, progress = 1.00, t = 3.84 s / 543.19 tokens per second 8.49.169.539 I slot print_timing: id 3 | task 5048 | prompt processing, n_tokens = 1120, progress = 1.00, t = 3.83 s / 292.68 tokens per second 8.50.056.239 I slot print_timing: id 0 | task 5046 | prompt eval time = 4204.94 ms / 1161 tokens ( 3.62 ms per token, 276.10 tokens per second) 8.50.056.244 I slot print_timing: id 0 | task 5046 | eval time = 568.30 ms / 2 tokens ( 568.30 ms per token, 1.76 tokens per second) 8.50.056.245 I slot print_timing: id 0 | task 5046 | total time = 4773.24 ms / 1163 tokens 8.50.056.246 I slot print_timing: id 0 | task 5046 | graphs reused = 3646 8.50.056.248 I slot print_timing: id 0 | task 5046 | graph reallocs = 492 / 0 (same size) / (changed size) 8.50.056.302 I slot release: id 0 | task 5046 | stop processing: n_tokens = 1162, truncated = 0 8.50.056.707 I slot print_timing: id 1 | task 5047 | prompt eval time = 4201.14 ms / 2091 tokens ( 2.01 ms per token, 497.72 tokens per second) 8.50.056.712 I slot print_timing: id 1 | task 5047 | eval time = 567.99 ms / 2 tokens ( 567.99 ms per token, 1.76 tokens per second) 8.50.056.713 I slot print_timing: id 1 | task 5047 | total time = 4769.13 ms / 2093 tokens 8.50.056.714 I slot print_timing: id 1 | task 5047 | graphs reused = 3646 8.50.056.714 I slot print_timing: id 1 | task 5047 | graph reallocs = 492 / 0 (same size) / (changed size) 8.50.056.799 I slot release: id 1 | task 5047 | stop processing: n_tokens = 2092, truncated = 0 8.50.057.145 I slot print_timing: id 3 | task 5048 | prompt eval time = 4186.33 ms / 1124 tokens ( 3.72 ms per token, 268.49 tokens per second) 8.50.057.150 I slot print_timing: id 3 | task 5048 | eval time = 567.76 ms / 2 tokens ( 567.76 ms per token, 1.76 tokens per second) 8.50.057.151 I slot print_timing: id 3 | task 5048 | total time = 4754.09 ms / 1126 tokens 8.50.057.151 I slot print_timing: id 3 | task 5048 | graphs reused = 3646 8.50.057.152 I slot print_timing: id 3 | task 5048 | graph reallocs = 492 / 0 (same size) / (changed size) 8.50.057.192 I slot release: id 3 | task 5048 | stop processing: n_tokens = 1125, truncated = 0 8.50.191.656 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.856 8.50.191.860 I slot launch_slot_: id 1 | task 5058 | processing task, is_child = 0 8.50.191.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 279.305 MiB) 8.50.253.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 278.805 MiB) 8.50.316.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1162, t_last = 529963924 8.50.316.476 I slot launch_slot_: id 0 | task 5059 | processing task, is_child = 0 8.50.316.588 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1125, t_last = 529964814 8.50.316.856 I slot launch_slot_: id 3 | task 5060 | processing task, is_child = 0 8.51.467.312 I slot print_timing: id 2 | task 5053 | prompt processing, n_tokens = 2090, progress = 1.00, t = 3.17 s / 659.86 tokens per second 8.52.875.644 I slot print_timing: id 1 | task 5058 | prompt eval time = 1653.49 ms / 344 tokens ( 4.81 ms per token, 208.04 tokens per second) 8.52.875.650 I slot print_timing: id 1 | task 5058 | eval time = 898.08 ms / 2 tokens ( 898.08 ms per token, 1.11 tokens per second) 8.52.875.651 I slot print_timing: id 1 | task 5058 | total time = 2551.57 ms / 346 tokens 8.52.875.652 I slot print_timing: id 1 | task 5058 | graphs reused = 3646 8.52.875.653 I slot print_timing: id 1 | task 5058 | graph reallocs = 498 / 0 (same size) / (changed size) 8.52.875.743 I slot release: id 1 | task 5058 | stop processing: n_tokens = 2106, truncated = 0 8.52.876.143 I slot print_timing: id 2 | task 5053 | prompt eval time = 3712.06 ms / 2094 tokens ( 1.77 ms per token, 564.11 tokens per second) 8.52.876.149 I slot print_timing: id 2 | task 5053 | eval time = 897.90 ms / 2 tokens ( 897.90 ms per token, 1.11 tokens per second) 8.52.876.150 I slot print_timing: id 2 | task 5053 | total time = 4609.96 ms / 2096 tokens 8.52.876.151 I slot print_timing: id 2 | task 5053 | graphs reused = 3646 8.52.876.152 I slot print_timing: id 2 | task 5053 | graph reallocs = 498 / 0 (same size) / (changed size) 8.52.876.261 I slot release: id 2 | task 5053 | stop processing: n_tokens = 2095, truncated = 0 8.53.181.318 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.868 (> 0.100 thold), f_keep = 0.849 8.53.181.525 I slot launch_slot_: id 1 | task 5065 | processing task, is_child = 0 8.53.181.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.215 MiB) 8.53.188.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 8.53.251.066 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.840 (> 0.100 thold), f_keep = 0.854 8.53.251.279 I slot launch_slot_: id 2 | task 5066 | processing task, is_child = 0 8.54.322.385 I slot print_timing: id 0 | task 5059 | prompt processing, n_tokens = 2053, progress = 1.00, t = 4.01 s / 512.55 tokens per second 8.54.367.257 I slot print_timing: id 3 | task 5060 | prompt processing, n_tokens = 2037, progress = 1.00, t = 3.96 s / 513.76 tokens per second 8.54.583.594 I slot print_timing: id 0 | task 5059 | prompt eval time = 4198.56 ms / 2057 tokens ( 2.04 ms per token, 489.93 tokens per second) 8.54.583.600 I slot print_timing: id 0 | task 5059 | eval time = 68.15 ms / 2 tokens ( 68.15 ms per token, 14.67 tokens per second) 8.54.583.601 I slot print_timing: id 0 | task 5059 | total time = 4266.71 ms / 2059 tokens 8.54.583.602 I slot print_timing: id 0 | task 5059 | graphs reused = 3647 8.54.583.603 I slot print_timing: id 0 | task 5059 | graph reallocs = 501 / 0 (same size) / (changed size) 8.54.583.693 I slot release: id 0 | task 5059 | stop processing: n_tokens = 2058, truncated = 0 8.54.584.145 I slot print_timing: id 1 | task 5065 | prompt eval time = 1252.08 ms / 300 tokens ( 4.17 ms per token, 239.60 tokens per second) 8.54.584.151 I slot print_timing: id 1 | task 5065 | eval time = 68.14 ms / 2 tokens ( 68.14 ms per token, 14.68 tokens per second) 8.54.584.153 I slot print_timing: id 1 | task 5065 | total time = 1320.22 ms / 302 tokens 8.54.584.154 I slot print_timing: id 1 | task 5065 | graphs reused = 3647 8.54.584.155 I slot print_timing: id 1 | task 5065 | graph reallocs = 501 / 0 (same size) / (changed size) 8.54.584.265 I slot release: id 1 | task 5065 | stop processing: n_tokens = 2062, truncated = 0 8.54.584.603 I slot print_timing: id 2 | task 5066 | prompt eval time = 1232.57 ms / 369 tokens ( 3.34 ms per token, 299.37 tokens per second) 8.54.584.607 I slot print_timing: id 2 | task 5066 | eval time = 68.02 ms / 2 tokens ( 68.02 ms per token, 14.70 tokens per second) 8.54.584.608 I slot print_timing: id 2 | task 5066 | total time = 1300.59 ms / 371 tokens 8.54.584.609 I slot print_timing: id 2 | task 5066 | graphs reused = 3647 8.54.584.610 I slot print_timing: id 2 | task 5066 | graph reallocs = 501 / 0 (same size) / (changed size) 8.54.584.681 I slot release: id 2 | task 5066 | stop processing: n_tokens = 2131, truncated = 0 8.54.584.986 I slot print_timing: id 3 | task 5060 | prompt eval time = 4159.71 ms / 2041 tokens ( 2.04 ms per token, 490.66 tokens per second) 8.54.584.990 I slot print_timing: id 3 | task 5060 | eval time = 67.82 ms / 2 tokens ( 67.82 ms per token, 14.75 tokens per second) 8.54.584.991 I slot print_timing: id 3 | task 5060 | total time = 4227.53 ms / 2043 tokens 8.54.584.991 I slot print_timing: id 3 | task 5060 | graphs reused = 3647 8.54.584.992 I slot print_timing: id 3 | task 5060 | graph reallocs = 501 / 0 (same size) / (changed size) 8.54.585.041 I slot release: id 3 | task 5060 | stop processing: n_tokens = 2042, truncated = 0 8.54.602.044 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.803 (> 0.100 thold), f_keep = 0.870 8.54.602.229 I slot launch_slot_: id 0 | task 5070 | processing task, is_child = 0 8.54.602.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.122 MiB) 8.54.666.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.309 MiB) 8.54.738.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.059 MiB) 8.54.807.959 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.840 8.54.808.183 I slot launch_slot_: id 2 | task 5071 | processing task, is_child = 0 8.54.808.404 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.887 (> 0.100 thold), f_keep = 0.877 8.54.808.583 I slot launch_slot_: id 3 | task 5072 | processing task, is_child = 0 8.54.808.692 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.868 8.54.808.860 I slot launch_slot_: id 1 | task 5073 | processing task, is_child = 0 8.56.019.993 I slot print_timing: id 0 | task 5070 | prompt eval time = 1143.55 ms / 467 tokens ( 2.45 ms per token, 408.38 tokens per second) 8.56.019.999 I slot print_timing: id 0 | task 5070 | eval time = 67.56 ms / 2 tokens ( 67.56 ms per token, 14.80 tokens per second) 8.56.020.000 I slot print_timing: id 0 | task 5070 | total time = 1211.11 ms / 469 tokens 8.56.020.001 I slot print_timing: id 0 | task 5070 | graphs reused = 3647 8.56.020.001 I slot print_timing: id 0 | task 5070 | graph reallocs = 501 / 0 (same size) / (changed size) 8.56.020.096 I slot release: id 0 | task 5070 | stop processing: n_tokens = 2229, truncated = 0 8.56.020.413 I slot print_timing: id 1 | task 5073 | prompt eval time = 1127.29 ms / 210 tokens ( 5.37 ms per token, 186.29 tokens per second) 8.56.020.417 I slot print_timing: id 1 | task 5073 | eval time = 67.42 ms / 2 tokens ( 67.42 ms per token, 14.83 tokens per second) 8.56.020.417 I slot print_timing: id 1 | task 5073 | total time = 1194.71 ms / 212 tokens 8.56.020.418 I slot print_timing: id 1 | task 5073 | graphs reused = 3647 8.56.020.419 I slot print_timing: id 1 | task 5073 | graph reallocs = 501 / 0 (same size) / (changed size) 8.56.020.471 I slot release: id 1 | task 5073 | stop processing: n_tokens = 1972, truncated = 0 8.56.020.781 I slot print_timing: id 2 | task 5071 | prompt eval time = 1109.25 ms / 380 tokens ( 2.92 ms per token, 342.57 tokens per second) 8.56.020.785 I slot print_timing: id 2 | task 5071 | eval time = 67.23 ms / 2 tokens ( 67.23 ms per token, 14.87 tokens per second) 8.56.020.786 I slot print_timing: id 2 | task 5071 | total time = 1176.48 ms / 382 tokens 8.56.020.786 I slot print_timing: id 2 | task 5071 | graphs reused = 3647 8.56.020.787 I slot print_timing: id 2 | task 5071 | graph reallocs = 501 / 0 (same size) / (changed size) 8.56.020.837 I slot release: id 2 | task 5071 | stop processing: n_tokens = 2142, truncated = 0 8.56.021.160 I slot print_timing: id 3 | task 5072 | prompt eval time = 1090.73 ms / 258 tokens ( 4.23 ms per token, 236.54 tokens per second) 8.56.021.166 I slot print_timing: id 3 | task 5072 | eval time = 67.05 ms / 2 tokens ( 67.05 ms per token, 14.92 tokens per second) 8.56.021.166 I slot print_timing: id 3 | task 5072 | total time = 1157.77 ms / 260 tokens 8.56.021.167 I slot print_timing: id 3 | task 5072 | graphs reused = 3647 8.56.021.167 I slot print_timing: id 3 | task 5072 | graph reallocs = 501 / 0 (same size) / (changed size) 8.56.021.217 I slot release: id 3 | task 5072 | stop processing: n_tokens = 2020, truncated = 0 8.56.037.633 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.850 (> 0.100 thold), f_keep = 0.803 8.56.037.803 I slot launch_slot_: id 0 | task 5077 | processing task, is_child = 0 8.56.037.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.903 MiB) 8.56.102.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.934 MiB) 8.56.169.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.153 MiB) 8.56.232.764 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.867 (> 0.100 thold), f_keep = 0.908 8.56.232.922 I slot launch_slot_: id 1 | task 5078 | processing task, is_child = 0 8.56.233.139 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.888 (> 0.100 thold), f_keep = 0.835 8.56.233.243 I slot launch_slot_: id 2 | task 5079 | processing task, is_child = 0 8.56.233.347 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.907 (> 0.100 thold), f_keep = 0.886 8.56.233.442 I slot launch_slot_: id 3 | task 5080 | processing task, is_child = 0 8.57.399.645 I slot print_timing: id 0 | task 5077 | prompt eval time = 1098.14 ms / 345 tokens ( 3.18 ms per token, 314.17 tokens per second) 8.57.399.651 I slot print_timing: id 0 | task 5077 | eval time = 68.04 ms / 2 tokens ( 68.04 ms per token, 14.70 tokens per second) 8.57.399.653 I slot print_timing: id 0 | task 5077 | total time = 1166.18 ms / 347 tokens 8.57.399.654 I slot print_timing: id 0 | task 5077 | graphs reused = 3647 8.57.399.654 I slot print_timing: id 0 | task 5077 | graph reallocs = 501 / 0 (same size) / (changed size) 8.57.399.746 I slot release: id 0 | task 5077 | stop processing: n_tokens = 2107, truncated = 0 8.57.400.127 I slot print_timing: id 1 | task 5078 | prompt eval time = 1079.79 ms / 304 tokens ( 3.55 ms per token, 281.54 tokens per second) 8.57.400.132 I slot print_timing: id 1 | task 5078 | eval time = 67.85 ms / 2 tokens ( 67.85 ms per token, 14.74 tokens per second) 8.57.400.133 I slot print_timing: id 1 | task 5078 | total time = 1147.64 ms / 306 tokens 8.57.400.133 I slot print_timing: id 1 | task 5078 | graphs reused = 3647 8.57.400.134 I slot print_timing: id 1 | task 5078 | graph reallocs = 501 / 0 (same size) / (changed size) 8.57.400.199 I slot release: id 1 | task 5078 | stop processing: n_tokens = 2066, truncated = 0 8.57.400.603 I slot print_timing: id 2 | task 5079 | prompt eval time = 1061.51 ms / 253 tokens ( 4.20 ms per token, 238.34 tokens per second) 8.57.400.608 I slot print_timing: id 2 | task 5079 | eval time = 67.64 ms / 2 tokens ( 67.64 ms per token, 14.79 tokens per second) 8.57.400.609 I slot print_timing: id 2 | task 5079 | total time = 1129.15 ms / 255 tokens 8.57.400.609 I slot print_timing: id 2 | task 5079 | graphs reused = 3647 8.57.400.610 I slot print_timing: id 2 | task 5079 | graph reallocs = 501 / 0 (same size) / (changed size) 8.57.400.668 I slot release: id 2 | task 5079 | stop processing: n_tokens = 2015, truncated = 0 8.57.401.039 I slot print_timing: id 3 | task 5080 | prompt eval time = 1043.31 ms / 212 tokens ( 4.92 ms per token, 203.20 tokens per second) 8.57.401.044 I slot print_timing: id 3 | task 5080 | eval time = 67.40 ms / 2 tokens ( 67.40 ms per token, 14.84 tokens per second) 8.57.401.044 I slot print_timing: id 3 | task 5080 | total time = 1110.71 ms / 214 tokens 8.57.401.045 I slot print_timing: id 3 | task 5080 | graphs reused = 3647 8.57.401.046 I slot print_timing: id 3 | task 5080 | graph reallocs = 501 / 0 (same size) / (changed size) 8.57.401.095 I slot release: id 3 | task 5080 | stop processing: n_tokens = 1974, truncated = 0 8.57.419.741 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.866 (> 0.100 thold), f_keep = 0.849 8.57.419.938 I slot launch_slot_: id 0 | task 5084 | processing task, is_child = 0 8.57.420.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.997 MiB) 8.57.487.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.028 MiB) 8.57.553.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.527 MiB) 8.57.560.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 284.778 MiB) 8.57.625.399 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.908 (> 0.100 thold), f_keep = 0.866 8.57.625.556 I slot launch_slot_: id 1 | task 5086 | processing task, is_child = 0 8.57.625.777 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.888 8.57.625.889 I slot launch_slot_: id 2 | task 5085 | processing task, is_child = 0 8.57.625.998 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.846 (> 0.100 thold), f_keep = 0.906 8.57.626.096 I slot launch_slot_: id 3 | task 5087 | processing task, is_child = 0 8.58.834.290 I slot print_timing: id 0 | task 5084 | prompt eval time = 1133.07 ms / 304 tokens ( 3.73 ms per token, 268.30 tokens per second) 8.58.834.296 I slot print_timing: id 0 | task 5084 | eval time = 75.10 ms / 2 tokens ( 75.10 ms per token, 13.32 tokens per second) 8.58.834.298 I slot print_timing: id 0 | task 5084 | total time = 1208.17 ms / 306 tokens 8.58.834.299 I slot print_timing: id 0 | task 5084 | graphs reused = 3647 8.58.834.300 I slot print_timing: id 0 | task 5084 | graph reallocs = 501 / 0 (same size) / (changed size) 8.58.834.402 I slot release: id 0 | task 5084 | stop processing: n_tokens = 2066, truncated = 0 8.58.834.760 I slot print_timing: id 1 | task 5086 | prompt eval time = 1114.72 ms / 210 tokens ( 5.31 ms per token, 188.39 tokens per second) 8.58.834.766 I slot print_timing: id 1 | task 5086 | eval time = 74.79 ms / 2 tokens ( 74.79 ms per token, 13.37 tokens per second) 8.58.834.768 I slot print_timing: id 1 | task 5086 | total time = 1189.51 ms / 212 tokens 8.58.834.768 I slot print_timing: id 1 | task 5086 | graphs reused = 3647 8.58.834.769 I slot print_timing: id 1 | task 5086 | graph reallocs = 501 / 0 (same size) / (changed size) 8.58.834.833 I slot release: id 1 | task 5086 | stop processing: n_tokens = 1972, truncated = 0 8.58.835.207 I slot print_timing: id 2 | task 5085 | prompt eval time = 1095.76 ms / 405 tokens ( 2.71 ms per token, 369.61 tokens per second) 8.58.835.212 I slot print_timing: id 2 | task 5085 | eval time = 74.45 ms / 2 tokens ( 74.45 ms per token, 13.43 tokens per second) 8.58.835.213 I slot print_timing: id 2 | task 5085 | total time = 1170.21 ms / 407 tokens 8.58.835.213 I slot print_timing: id 2 | task 5085 | graphs reused = 3647 8.58.835.214 I slot print_timing: id 2 | task 5085 | graph reallocs = 501 / 0 (same size) / (changed size) 8.58.835.268 I slot release: id 2 | task 5085 | stop processing: n_tokens = 2167, truncated = 0 8.58.835.632 I slot print_timing: id 3 | task 5087 | prompt eval time = 1077.06 ms / 353 tokens ( 3.05 ms per token, 327.74 tokens per second) 8.58.835.637 I slot print_timing: id 3 | task 5087 | eval time = 74.10 ms / 2 tokens ( 74.10 ms per token, 13.50 tokens per second) 8.58.835.637 I slot print_timing: id 3 | task 5087 | total time = 1151.15 ms / 355 tokens 8.58.835.638 I slot print_timing: id 3 | task 5087 | graphs reused = 3647 8.58.835.639 I slot print_timing: id 3 | task 5087 | graph reallocs = 501 / 0 (same size) / (changed size) 8.58.835.691 I slot release: id 3 | task 5087 | stop processing: n_tokens = 2115, truncated = 0 8.58.852.012 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.884 (> 0.100 thold), f_keep = 0.908 8.58.852.175 I slot launch_slot_: id 1 | task 5091 | processing task, is_child = 0 8.58.852.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.965 MiB) 8.58.909.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.495 MiB) 8.58.981.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 285.872 MiB) 8.59.045.592 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.896 (> 0.100 thold), f_keep = 0.866 8.59.045.755 I slot launch_slot_: id 0 | task 5092 | processing task, is_child = 0 8.59.045.990 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.880 (> 0.100 thold), f_keep = 0.826 8.59.046.089 I slot launch_slot_: id 2 | task 5093 | processing task, is_child = 0 8.59.046.203 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.846 8.59.046.295 I slot launch_slot_: id 3 | task 5094 | processing task, is_child = 0 9.00.276.392 I slot print_timing: id 0 | task 5092 | prompt eval time = 1164.00 ms / 236 tokens ( 4.93 ms per token, 202.75 tokens per second) 9.00.276.398 I slot print_timing: id 0 | task 5092 | eval time = 66.08 ms / 2 tokens ( 66.08 ms per token, 15.13 tokens per second) 9.00.276.400 I slot print_timing: id 0 | task 5092 | total time = 1230.08 ms / 238 tokens 9.00.276.401 I slot print_timing: id 0 | task 5092 | graphs reused = 3647 9.00.276.402 I slot print_timing: id 0 | task 5092 | graph reallocs = 501 / 0 (same size) / (changed size) 9.00.276.492 I slot release: id 0 | task 5092 | stop processing: n_tokens = 1998, truncated = 0 9.00.276.776 I slot print_timing: id 1 | task 5091 | prompt eval time = 1145.46 ms / 264 tokens ( 4.34 ms per token, 230.48 tokens per second) 9.00.276.779 I slot print_timing: id 1 | task 5091 | eval time = 65.90 ms / 2 tokens ( 65.90 ms per token, 15.17 tokens per second) 9.00.276.780 I slot print_timing: id 1 | task 5091 | total time = 1211.36 ms / 266 tokens 9.00.276.780 I slot print_timing: id 1 | task 5091 | graphs reused = 3647 9.00.276.781 I slot print_timing: id 1 | task 5091 | graph reallocs = 501 / 0 (same size) / (changed size) 9.00.276.830 I slot release: id 1 | task 5091 | stop processing: n_tokens = 2026, truncated = 0 9.00.277.275 I slot print_timing: id 2 | task 5093 | prompt eval time = 1127.06 ms / 272 tokens ( 4.14 ms per token, 241.34 tokens per second) 9.00.277.279 I slot print_timing: id 2 | task 5093 | eval time = 65.71 ms / 2 tokens ( 65.71 ms per token, 15.22 tokens per second) 9.00.277.279 I slot print_timing: id 2 | task 5093 | total time = 1192.77 ms / 274 tokens 9.00.277.280 I slot print_timing: id 2 | task 5093 | graphs reused = 3647 9.00.277.280 I slot print_timing: id 2 | task 5093 | graph reallocs = 501 / 0 (same size) / (changed size) 9.00.277.329 I slot release: id 2 | task 5093 | stop processing: n_tokens = 2034, truncated = 0 9.00.277.650 I slot print_timing: id 3 | task 5094 | prompt eval time = 1108.75 ms / 413 tokens ( 2.68 ms per token, 372.49 tokens per second) 9.00.277.654 I slot print_timing: id 3 | task 5094 | eval time = 65.30 ms / 2 tokens ( 65.30 ms per token, 15.31 tokens per second) 9.00.277.655 I slot print_timing: id 3 | task 5094 | total time = 1174.05 ms / 415 tokens 9.00.277.655 I slot print_timing: id 3 | task 5094 | graphs reused = 3647 9.00.277.656 I slot print_timing: id 3 | task 5094 | graph reallocs = 501 / 0 (same size) / (changed size) 9.00.277.708 I slot release: id 3 | task 5094 | stop processing: n_tokens = 2175, truncated = 0 9.00.293.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1998, t_last = 540184114 9.00.293.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 276.209 MiB) 9.00.361.384 I slot launch_slot_: id 0 | task 5098 | processing task, is_child = 0 9.00.361.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.082 MiB) 9.00.426.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.426 MiB) 9.00.489.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.614 MiB) 9.00.551.288 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.914 (> 0.100 thold), f_keep = 0.883 9.00.551.446 I slot launch_slot_: id 1 | task 5099 | processing task, is_child = 0 9.00.551.683 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.937 (> 0.100 thold), f_keep = 0.880 9.00.551.793 I slot launch_slot_: id 2 | task 5100 | processing task, is_child = 0 9.00.551.909 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.899 (> 0.100 thold), f_keep = 0.823 9.00.552.009 I slot launch_slot_: id 3 | task 5101 | processing task, is_child = 0 9.02.064.349 I slot print_timing: id 1 | task 5099 | prompt eval time = 1223.93 ms / 196 tokens ( 6.24 ms per token, 160.14 tokens per second) 9.02.064.356 I slot print_timing: id 1 | task 5099 | eval time = 284.58 ms / 2 tokens ( 284.58 ms per token, 3.51 tokens per second) 9.02.064.357 I slot print_timing: id 1 | task 5099 | total time = 1508.51 ms / 198 tokens 9.02.064.359 I slot print_timing: id 1 | task 5099 | graphs reused = 3647 9.02.064.360 I slot print_timing: id 1 | task 5099 | graph reallocs = 503 / 0 (same size) / (changed size) 9.02.064.459 I slot release: id 1 | task 5099 | stop processing: n_tokens = 1958, truncated = 0 9.02.064.868 I slot print_timing: id 2 | task 5100 | prompt eval time = 1205.45 ms / 149 tokens ( 8.09 ms per token, 123.61 tokens per second) 9.02.064.873 I slot print_timing: id 2 | task 5100 | eval time = 284.46 ms / 2 tokens ( 284.46 ms per token, 3.52 tokens per second) 9.02.064.874 I slot print_timing: id 2 | task 5100 | total time = 1489.90 ms / 151 tokens 9.02.064.874 I slot print_timing: id 2 | task 5100 | graphs reused = 3647 9.02.064.875 I slot print_timing: id 2 | task 5100 | graph reallocs = 503 / 0 (same size) / (changed size) 9.02.064.952 I slot release: id 2 | task 5100 | stop processing: n_tokens = 1911, truncated = 0 9.02.065.391 I slot print_timing: id 3 | task 5101 | prompt eval time = 1187.17 ms / 230 tokens ( 5.16 ms per token, 193.74 tokens per second) 9.02.065.396 I slot print_timing: id 3 | task 5101 | eval time = 284.41 ms / 2 tokens ( 284.41 ms per token, 3.52 tokens per second) 9.02.065.397 I slot print_timing: id 3 | task 5101 | total time = 1471.58 ms / 232 tokens 9.02.065.398 I slot print_timing: id 3 | task 5101 | graphs reused = 3647 9.02.065.399 I slot print_timing: id 3 | task 5101 | graph reallocs = 503 / 0 (same size) / (changed size) 9.02.065.472 I slot release: id 3 | task 5101 | stop processing: n_tokens = 1992, truncated = 0 9.02.205.988 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1958, t_last = 541972082 9.02.206.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.207 MiB) 9.02.215.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.895 MiB) 9.02.280.958 I slot launch_slot_: id 1 | task 5106 | processing task, is_child = 0 9.02.281.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.395 MiB) 9.02.350.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.645 MiB) 9.02.418.222 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1911, t_last = 541972576 9.02.418.494 I slot launch_slot_: id 2 | task 5107 | processing task, is_child = 0 9.02.418.612 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1992, t_last = 541973095 9.02.418.839 I slot launch_slot_: id 3 | task 5108 | processing task, is_child = 0 9.04.528.383 I slot print_timing: id 0 | task 5098 | prompt eval time = 3196.85 ms / 1475 tokens ( 2.17 ms per token, 461.39 tokens per second) 9.04.528.389 I slot print_timing: id 0 | task 5098 | eval time = 779.50 ms / 2 tokens ( 779.50 ms per token, 1.28 tokens per second) 9.04.528.390 I slot print_timing: id 0 | task 5098 | total time = 3976.35 ms / 1477 tokens 9.04.528.391 I slot print_timing: id 0 | task 5098 | graphs reused = 3647 9.04.528.392 I slot print_timing: id 0 | task 5098 | graph reallocs = 507 / 0 (same size) / (changed size) 9.04.528.467 I slot release: id 0 | task 5098 | stop processing: n_tokens = 1476, truncated = 0 9.05.022.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1476, t_last = 544436089 9.05.022.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 282.245 MiB) 9.05.072.936 I slot launch_slot_: id 0 | task 5113 | processing task, is_child = 0 9.06.064.052 I slot print_timing: id 1 | task 5106 | prompt processing, n_tokens = 1551, progress = 1.00, t = 3.60 s / 430.31 tokens per second 9.06.074.049 I slot print_timing: id 2 | task 5107 | prompt processing, n_tokens = 1673, progress = 1.00, t = 3.60 s / 464.65 tokens per second 9.06.084.229 I slot print_timing: id 3 | task 5108 | prompt processing, n_tokens = 995, progress = 1.00, t = 3.60 s / 276.64 tokens per second 9.06.611.079 I slot print_timing: id 1 | task 5106 | prompt eval time = 3953.88 ms / 1555 tokens ( 2.54 ms per token, 393.28 tokens per second) 9.06.611.086 I slot print_timing: id 1 | task 5106 | eval time = 226.21 ms / 2 tokens ( 226.21 ms per token, 4.42 tokens per second) 9.06.611.087 I slot print_timing: id 1 | task 5106 | total time = 4180.09 ms / 1557 tokens 9.06.611.088 I slot print_timing: id 1 | task 5106 | graphs reused = 3647 9.06.611.089 I slot print_timing: id 1 | task 5106 | graph reallocs = 509 / 0 (same size) / (changed size) 9.06.611.177 I slot release: id 1 | task 5106 | stop processing: n_tokens = 1556, truncated = 0 9.06.611.579 I slot print_timing: id 2 | task 5107 | prompt eval time = 3950.70 ms / 1677 tokens ( 2.36 ms per token, 424.48 tokens per second) 9.06.611.582 I slot print_timing: id 2 | task 5107 | eval time = 226.07 ms / 2 tokens ( 226.07 ms per token, 4.42 tokens per second) 9.06.611.584 I slot print_timing: id 2 | task 5107 | total time = 4176.78 ms / 1679 tokens 9.06.611.584 I slot print_timing: id 2 | task 5107 | graphs reused = 3647 9.06.611.585 I slot print_timing: id 2 | task 5107 | graph reallocs = 509 / 0 (same size) / (changed size) 9.06.611.651 I slot release: id 2 | task 5107 | stop processing: n_tokens = 1678, truncated = 0 9.06.612.062 I slot print_timing: id 3 | task 5108 | prompt eval time = 3947.55 ms / 999 tokens ( 3.95 ms per token, 253.07 tokens per second) 9.06.612.068 I slot print_timing: id 3 | task 5108 | eval time = 225.90 ms / 2 tokens ( 225.90 ms per token, 4.43 tokens per second) 9.06.612.069 I slot print_timing: id 3 | task 5108 | total time = 4173.45 ms / 1001 tokens 9.06.612.071 I slot print_timing: id 3 | task 5108 | graphs reused = 3647 9.06.612.071 I slot print_timing: id 3 | task 5108 | graph reallocs = 509 / 0 (same size) / (changed size) 9.06.612.114 I slot release: id 3 | task 5108 | stop processing: n_tokens = 1000, truncated = 0 9.06.754.347 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.882 9.06.754.553 I slot launch_slot_: id 3 | task 5119 | processing task, is_child = 0 9.06.754.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.150 MiB) 9.06.824.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 281.713 MiB) 9.06.881.397 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1556, t_last = 546518800 9.06.881.787 I slot launch_slot_: id 1 | task 5118 | processing task, is_child = 0 9.06.881.939 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1678, t_last = 546519274 9.06.882.245 I slot launch_slot_: id 2 | task 5120 | processing task, is_child = 0 9.08.314.223 I slot print_timing: id 0 | task 5113 | prompt eval time = 2782.25 ms / 989 tokens ( 2.81 ms per token, 355.47 tokens per second) 9.08.314.229 I slot print_timing: id 0 | task 5113 | eval time = 459.01 ms / 2 tokens ( 459.01 ms per token, 2.18 tokens per second) 9.08.314.230 I slot print_timing: id 0 | task 5113 | total time = 3241.26 ms / 991 tokens 9.08.314.232 I slot print_timing: id 0 | task 5113 | graphs reused = 3647 9.08.314.232 I slot print_timing: id 0 | task 5113 | graph reallocs = 511 / 0 (same size) / (changed size) 9.08.314.302 I slot release: id 0 | task 5113 | stop processing: n_tokens = 990, truncated = 0 9.08.314.683 I slot print_timing: id 3 | task 5119 | prompt eval time = 950.55 ms / 124 tokens ( 7.67 ms per token, 130.45 tokens per second) 9.08.314.687 I slot print_timing: id 3 | task 5119 | eval time = 458.81 ms / 2 tokens ( 458.81 ms per token, 2.18 tokens per second) 9.08.314.687 I slot print_timing: id 3 | task 5119 | total time = 1409.36 ms / 126 tokens 9.08.314.688 I slot print_timing: id 3 | task 5119 | graphs reused = 3647 9.08.314.689 I slot print_timing: id 3 | task 5119 | graph reallocs = 511 / 0 (same size) / (changed size) 9.08.314.725 I slot release: id 3 | task 5119 | stop processing: n_tokens = 978, truncated = 0 9.08.887.845 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.906 (> 0.100 thold), f_keep = 0.890 9.08.888.047 I slot launch_slot_: id 0 | task 5125 | processing task, is_child = 0 9.08.888.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 283.933 MiB) 9.08.941.503 I slot get_availabl: id 3 | task -1 | selected slot by LCP similarity, f_sim_best = 0.903 (> 0.100 thold), f_keep = 0.901 9.08.941.690 I slot launch_slot_: id 3 | task 5126 | processing task, is_child = 0 9.09.784.103 I slot print_timing: id 0 | task 5125 | prompt eval time = 775.15 ms / 119 tokens ( 6.51 ms per token, 153.52 tokens per second) 9.09.784.110 I slot print_timing: id 0 | task 5125 | eval time = 67.23 ms / 2 tokens ( 67.23 ms per token, 14.87 tokens per second) 9.09.784.111 I slot print_timing: id 0 | task 5125 | total time = 842.38 ms / 121 tokens 9.09.784.112 I slot print_timing: id 0 | task 5125 | graphs reused = 3647 9.09.784.113 I slot print_timing: id 0 | task 5125 | graph reallocs = 512 / 0 (same size) / (changed size) 9.09.784.178 I slot release: id 0 | task 5125 | stop processing: n_tokens = 973, truncated = 0 9.09.784.483 I slot print_timing: id 1 | task 5118 | prompt eval time = 2822.26 ms / 960 tokens ( 2.94 ms per token, 340.15 tokens per second) 9.09.784.487 I slot print_timing: id 1 | task 5118 | eval time = 66.85 ms / 2 tokens ( 66.85 ms per token, 14.96 tokens per second) 9.09.784.488 I slot print_timing: id 1 | task 5118 | total time = 2889.11 ms / 962 tokens 9.09.784.489 I slot print_timing: id 1 | task 5118 | graphs reused = 3647 9.09.784.490 I slot print_timing: id 1 | task 5118 | graph reallocs = 512 / 0 (same size) / (changed size) 9.09.784.525 I slot release: id 1 | task 5118 | stop processing: n_tokens = 961, truncated = 0 9.09.784.853 I slot print_timing: id 2 | task 5120 | prompt eval time = 2818.03 ms / 983 tokens ( 2.87 ms per token, 348.83 tokens per second) 9.09.784.857 I slot print_timing: id 2 | task 5120 | eval time = 66.47 ms / 2 tokens ( 66.47 ms per token, 15.04 tokens per second) 9.09.784.858 I slot print_timing: id 2 | task 5120 | total time = 2884.50 ms / 985 tokens 9.09.784.858 I slot print_timing: id 2 | task 5120 | graphs reused = 3647 9.09.784.859 I slot print_timing: id 2 | task 5120 | graph reallocs = 512 / 0 (same size) / (changed size) 9.09.784.894 I slot release: id 2 | task 5120 | stop processing: n_tokens = 984, truncated = 0 9.09.785.244 I slot print_timing: id 3 | task 5126 | prompt eval time = 732.36 ms / 123 tokens ( 5.95 ms per token, 167.95 tokens per second) 9.09.785.248 I slot print_timing: id 3 | task 5126 | eval time = 66.13 ms / 2 tokens ( 66.13 ms per token, 15.12 tokens per second) 9.09.785.249 I slot print_timing: id 3 | task 5126 | total time = 798.49 ms / 125 tokens 9.09.785.250 I slot print_timing: id 3 | task 5126 | graphs reused = 3647 9.09.785.251 I slot print_timing: id 3 | task 5126 | graph reallocs = 512 / 0 (same size) / (changed size) 9.09.785.281 I slot release: id 3 | task 5126 | stop processing: n_tokens = 977, truncated = 0 9.09.801.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 549691799 9.09.801.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 287.592 MiB) 9.09.858.497 I slot launch_slot_: id 0 | task 5130 | processing task, is_child = 0 9.09.858.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 286.435 MiB) 9.09.920.678 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.770 MiB) 9.09.981.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.738 MiB) 9.10.037.411 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 549692146 9.10.037.636 I slot launch_slot_: id 1 | task 5132 | processing task, is_child = 0 9.10.037.756 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 549692516 9.10.037.919 I slot launch_slot_: id 2 | task 5131 | processing task, is_child = 0 9.10.037.981 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 977, t_last = 549692903 9.10.038.136 I slot launch_slot_: id 3 | task 5133 | processing task, is_child = 0 9.13.680.957 I slot print_timing: id 0 | task 5130 | prompt processing, n_tokens = 1374, progress = 0.84, t = 3.64 s / 377.18 tokens per second 9.13.698.398 I slot print_timing: id 1 | task 5132 | prompt processing, n_tokens = 1374, progress = 0.87, t = 3.64 s / 377.57 tokens per second 9.13.709.063 I slot print_timing: id 2 | task 5131 | prompt processing, n_tokens = 1374, progress = 0.85, t = 3.64 s / 377.97 tokens per second 9.13.719.508 I slot print_timing: id 3 | task 5133 | prompt processing, n_tokens = 706, progress = 0.86, t = 3.63 s / 194.41 tokens per second 9.14.456.659 I slot print_timing: id 0 | task 5130 | prompt processing, n_tokens = 1625, progress = 1.00, t = 4.42 s / 367.77 tokens per second 9.14.474.257 I slot print_timing: id 1 | task 5132 | prompt processing, n_tokens = 1583, progress = 1.00, t = 4.41 s / 358.57 tokens per second 9.14.484.975 I slot print_timing: id 2 | task 5131 | prompt processing, n_tokens = 1611, progress = 1.00, t = 4.41 s / 365.23 tokens per second 9.14.495.593 I slot print_timing: id 3 | task 5133 | prompt processing, n_tokens = 821, progress = 1.00, t = 4.41 s / 186.28 tokens per second 9.14.705.938 I slot print_timing: id 0 | task 5130 | prompt eval time = 4601.82 ms / 1629 tokens ( 2.82 ms per token, 353.99 tokens per second) 9.14.705.944 I slot print_timing: id 0 | task 5130 | eval time = 65.96 ms / 2 tokens ( 65.96 ms per token, 15.16 tokens per second) 9.14.705.945 I slot print_timing: id 0 | task 5130 | total time = 4667.78 ms / 1631 tokens 9.14.705.947 I slot print_timing: id 0 | task 5130 | graphs reused = 3647 9.14.705.948 I slot print_timing: id 0 | task 5130 | graph reallocs = 518 / 0 (same size) / (changed size) 9.14.706.030 I slot release: id 0 | task 5130 | stop processing: n_tokens = 1630, truncated = 0 9.14.706.321 I slot print_timing: id 1 | task 5132 | prompt eval time = 4598.64 ms / 1587 tokens ( 2.90 ms per token, 345.10 tokens per second) 9.14.706.324 I slot print_timing: id 1 | task 5132 | eval time = 65.77 ms / 2 tokens ( 65.77 ms per token, 15.20 tokens per second) 9.14.706.325 I slot print_timing: id 1 | task 5132 | total time = 4664.41 ms / 1589 tokens 9.14.706.325 I slot print_timing: id 1 | task 5132 | graphs reused = 3647 9.14.706.326 I slot print_timing: id 1 | task 5132 | graph reallocs = 518 / 0 (same size) / (changed size) 9.14.706.368 I slot release: id 1 | task 5132 | stop processing: n_tokens = 1588, truncated = 0 9.14.706.692 I slot print_timing: id 2 | task 5131 | prompt eval time = 4595.43 ms / 1615 tokens ( 2.85 ms per token, 351.44 tokens per second) 9.14.706.695 I slot print_timing: id 2 | task 5131 | eval time = 65.56 ms / 2 tokens ( 65.56 ms per token, 15.25 tokens per second) 9.14.706.695 I slot print_timing: id 2 | task 5131 | total time = 4660.99 ms / 1617 tokens 9.14.706.696 I slot print_timing: id 2 | task 5131 | graphs reused = 3647 9.14.706.697 I slot print_timing: id 2 | task 5131 | graph reallocs = 518 / 0 (same size) / (changed size) 9.14.706.739 I slot release: id 2 | task 5131 | stop processing: n_tokens = 1616, truncated = 0 9.14.707.112 I slot print_timing: id 3 | task 5133 | prompt eval time = 4592.34 ms / 825 tokens ( 5.57 ms per token, 179.65 tokens per second) 9.14.707.117 I slot print_timing: id 3 | task 5133 | eval time = 65.37 ms / 2 tokens ( 65.37 ms per token, 15.30 tokens per second) 9.14.707.118 I slot print_timing: id 3 | task 5133 | total time = 4657.71 ms / 827 tokens 9.14.707.119 I slot print_timing: id 3 | task 5133 | graphs reused = 3647 9.14.707.120 I slot print_timing: id 3 | task 5133 | graph reallocs = 518 / 0 (same size) / (changed size) 9.14.707.152 I slot release: id 3 | task 5133 | stop processing: n_tokens = 826, truncated = 0 9.14.721.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 554613653 9.14.721.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.896 MiB) 9.14.790.432 I slot launch_slot_: id 0 | task 5141 | processing task, is_child = 0 9.14.790.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.112 MiB) 9.14.860.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.923 MiB) 9.14.923.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.240 MiB) 9.14.986.209 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 1588, t_last = 554613990 9.14.986.453 I slot launch_slot_: id 1 | task 5142 | processing task, is_child = 0 9.14.986.593 I slot get_availabl: id 2 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.868 9.14.986.695 I slot launch_slot_: id 2 | task 5143 | processing task, is_child = 0 9.14.986.749 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 826, t_last = 554614773 9.15.003.504 I slot launch_slot_: id 3 | task 5144 | processing task, is_child = 0 9.16.355.976 I slot print_timing: id 2 | task 5143 | prompt eval time = 935.34 ms / 344 tokens ( 2.72 ms per token, 367.78 tokens per second) 9.16.355.982 I slot print_timing: id 2 | task 5143 | eval time = 409.54 ms / 2 tokens ( 409.54 ms per token, 2.44 tokens per second) 9.16.355.983 I slot print_timing: id 2 | task 5143 | total time = 1344.88 ms / 346 tokens 9.16.355.984 I slot print_timing: id 2 | task 5143 | graphs reused = 3647 9.16.355.985 I slot print_timing: id 2 | task 5143 | graph reallocs = 518 / 0 (same size) / (changed size) 9.16.356.067 I slot release: id 2 | task 5143 | stop processing: n_tokens = 1719, truncated = 0 9.16.356.372 I slot print_timing: id 3 | task 5144 | prompt eval time = 916.88 ms / 255 tokens ( 3.60 ms per token, 278.12 tokens per second) 9.16.356.377 I slot print_timing: id 3 | task 5144 | eval time = 409.31 ms / 2 tokens ( 409.31 ms per token, 2.44 tokens per second) 9.16.356.377 I slot print_timing: id 3 | task 5144 | total time = 1326.19 ms / 257 tokens 9.16.356.378 I slot print_timing: id 3 | task 5144 | graphs reused = 3647 9.16.356.379 I slot print_timing: id 3 | task 5144 | graph reallocs = 518 / 0 (same size) / (changed size) 9.16.356.427 I slot release: id 3 | task 5144 | stop processing: n_tokens = 1630, truncated = 0 9.16.944.083 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 1719, t_last = 556263691 9.16.986.599 I slot launch_slot_: id 2 | task 5149 | processing task, is_child = 0 9.16.986.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.424 MiB) 9.17.036.072 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 1630, t_last = 556264049 9.17.036.332 I slot launch_slot_: id 3 | task 5150 | processing task, is_child = 0 9.18.309.261 I slot print_timing: id 0 | task 5141 | prompt eval time = 2965.76 ms / 865 tokens ( 3.43 ms per token, 291.66 tokens per second) 9.18.309.266 I slot print_timing: id 0 | task 5141 | eval time = 339.98 ms / 2 tokens ( 339.98 ms per token, 2.94 tokens per second) 9.18.309.267 I slot print_timing: id 0 | task 5141 | total time = 3305.73 ms / 867 tokens 9.18.309.268 I slot print_timing: id 0 | task 5141 | graphs reused = 3647 9.18.309.268 I slot print_timing: id 0 | task 5141 | graph reallocs = 518 / 0 (same size) / (changed size) 9.18.309.321 I slot release: id 0 | task 5141 | stop processing: n_tokens = 866, truncated = 0 9.18.309.603 I slot print_timing: id 1 | task 5142 | prompt eval time = 2962.64 ms / 838 tokens ( 3.54 ms per token, 282.86 tokens per second) 9.18.309.606 I slot print_timing: id 1 | task 5142 | eval time = 339.70 ms / 2 tokens ( 339.70 ms per token, 2.94 tokens per second) 9.18.309.608 I slot print_timing: id 1 | task 5142 | total time = 3302.34 ms / 840 tokens 9.18.309.608 I slot print_timing: id 1 | task 5142 | graphs reused = 3647 9.18.309.609 I slot print_timing: id 1 | task 5142 | graph reallocs = 518 / 0 (same size) / (changed size) 9.18.309.635 I slot release: id 1 | task 5142 | stop processing: n_tokens = 839, truncated = 0 9.18.838.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 866, t_last = 558216943 9.18.838.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.863 MiB) 9.18.885.372 I slot launch_slot_: id 0 | task 5155 | processing task, is_child = 0 9.18.933.826 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 839, t_last = 558217257 9.18.934.084 I slot launch_slot_: id 1 | task 5156 | processing task, is_child = 0 9.20.267.221 I slot print_timing: id 2 | task 5149 | prompt eval time = 2939.59 ms / 859 tokens ( 3.42 ms per token, 292.22 tokens per second) 9.20.267.228 I slot print_timing: id 2 | task 5149 | eval time = 268.21 ms / 2 tokens ( 268.21 ms per token, 3.73 tokens per second) 9.20.267.229 I slot print_timing: id 2 | task 5149 | total time = 3207.80 ms / 861 tokens 9.20.267.231 I slot print_timing: id 2 | task 5149 | graphs reused = 3647 9.20.267.233 I slot print_timing: id 2 | task 5149 | graph reallocs = 522 / 0 (same size) / (changed size) 9.20.267.296 I slot release: id 2 | task 5149 | stop processing: n_tokens = 860, truncated = 0 9.20.267.611 I slot print_timing: id 3 | task 5150 | prompt eval time = 2932.87 ms / 842 tokens ( 3.48 ms per token, 287.09 tokens per second) 9.20.267.615 I slot print_timing: id 3 | task 5150 | eval time = 268.03 ms / 2 tokens ( 268.03 ms per token, 3.73 tokens per second) 9.20.267.616 I slot print_timing: id 3 | task 5150 | total time = 3200.90 ms / 844 tokens 9.20.267.616 I slot print_timing: id 3 | task 5150 | graphs reused = 3647 9.20.267.617 I slot print_timing: id 3 | task 5150 | graph reallocs = 522 / 0 (same size) / (changed size) 9.20.267.652 I slot release: id 3 | task 5150 | stop processing: n_tokens = 843, truncated = 0 9.20.788.738 I slot get_availabl: id 2 | task -1 | selected slot by LRU, n_tokens = 860, t_last = 560174917 9.20.788.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.268 MiB) 9.20.846.046 I slot launch_slot_: id 2 | task 5161 | processing task, is_child = 0 9.20.846.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.986 MiB) 9.20.906.110 I slot get_availabl: id 3 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 560175273 9.20.906.339 I slot launch_slot_: id 3 | task 5162 | processing task, is_child = 0 9.22.601.514 I slot print_timing: id 0 | task 5155 | prompt eval time = 3117.95 ms / 886 tokens ( 3.52 ms per token, 284.16 tokens per second) 9.22.601.520 I slot print_timing: id 0 | task 5155 | eval time = 549.45 ms / 2 tokens ( 549.45 ms per token, 1.82 tokens per second) 9.22.601.521 I slot print_timing: id 0 | task 5155 | total time = 3667.40 ms / 888 tokens 9.22.601.523 I slot print_timing: id 0 | task 5155 | graphs reused = 3647 9.22.601.524 I slot print_timing: id 0 | task 5155 | graph reallocs = 526 / 0 (same size) / (changed size) 9.22.601.575 I slot release: id 0 | task 5155 | stop processing: n_tokens = 887, truncated = 0 9.22.601.984 I slot print_timing: id 1 | task 5156 | prompt eval time = 3113.70 ms / 780 tokens ( 3.99 ms per token, 250.51 tokens per second) 9.22.601.988 I slot print_timing: id 1 | task 5156 | eval time = 549.23 ms / 2 tokens ( 549.23 ms per token, 1.82 tokens per second) 9.22.601.989 I slot print_timing: id 1 | task 5156 | total time = 3662.93 ms / 782 tokens 9.22.601.990 I slot print_timing: id 1 | task 5156 | graphs reused = 3647 9.22.601.990 I slot print_timing: id 1 | task 5156 | graph reallocs = 526 / 0 (same size) / (changed size) 9.22.602.032 I slot release: id 1 | task 5156 | stop processing: n_tokens = 781, truncated = 0 9.22.839.368 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 562509198 9.22.839.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.863 MiB) 9.22.901.670 I slot launch_slot_: id 0 | task 5167 | processing task, is_child = 0 9.22.901.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.021 MiB) 9.22.963.301 I slot get_availabl: id 1 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 562509653 9.22.963.621 I slot launch_slot_: id 1 | task 5168 | processing task, is_child = 0 9.23.655.988 I slot print_timing: id 2 | task 5161 | prompt eval time = 2366.84 ms / 749 tokens ( 3.16 ms per token, 316.46 tokens per second) 9.23.655.994 I slot print_timing: id 2 | task 5161 | eval time = 358.17 ms / 2 tokens ( 358.17 ms per token, 2.79 tokens per second) 9.23.655.995 I slot print_timing: id 2 | task 5161 | total time = 2725.01 ms / 751 tokens 9.23.655.996 I slot print_timing: id 2 | task 5161 | graphs reused = 3647 9.23.655.997 I slot print_timing: id 2 | task 5161 | graph reallocs = 526 / 0 (same size) / (changed size) 9.23.656.046 I slot release: id 2 | task 5161 | stop processing: n_tokens = 750, truncated = 0 9.23.656.447 I slot print_timing: id 3 | task 5162 | prompt eval time = 2360.43 ms / 691 tokens ( 3.42 ms per token, 292.74 tokens per second) 9.23.656.450 I slot print_timing: id 3 | task 5162 | eval time = 357.85 ms / 2 tokens ( 357.85 ms per token, 2.79 tokens per second) 9.23.656.451 I slot print_timing: id 3 | task 5162 | total time = 2718.28 ms / 693 tokens 9.23.656.451 I slot print_timing: id 3 | task 5162 | graphs reused = 3647 9.23.656.452 I slot print_timing: id 3 | task 5162 | graph reallocs = 526 / 0 (same size) / (changed size) 9.23.656.485 I slot release: id 3 | task 5162 | stop processing: n_tokens = 692, truncated = 0 9.24.677.885 I slot print_timing: id 0 | task 5167 | prompt eval time = 1657.12 ms / 678 tokens ( 2.44 ms per token, 409.14 tokens per second) 9.24.677.891 I slot print_timing: id 0 | task 5167 | eval time = 57.12 ms / 2 tokens ( 57.12 ms per token, 17.51 tokens per second) 9.24.677.893 I slot print_timing: id 0 | task 5167 | total time = 1714.24 ms / 680 tokens 9.24.677.894 I slot print_timing: id 0 | task 5167 | graphs reused = 3647 9.24.677.895 I slot print_timing: id 0 | task 5167 | graph reallocs = 528 / 0 (same size) / (changed size) 9.24.677.941 I slot release: id 0 | task 5167 | stop processing: n_tokens = 679, truncated = 0 9.24.678.378 I slot print_timing: id 1 | task 5168 | prompt eval time = 1651.54 ms / 712 tokens ( 2.32 ms per token, 431.11 tokens per second) 9.24.678.384 I slot print_timing: id 1 | task 5168 | eval time = 57.06 ms / 2 tokens ( 57.06 ms per token, 17.53 tokens per second) 9.24.678.385 I slot print_timing: id 1 | task 5168 | total time = 1708.60 ms / 714 tokens 9.24.678.386 I slot print_timing: id 1 | task 5168 | graphs reused = 3647 9.24.678.387 I slot print_timing: id 1 | task 5168 | graph reallocs = 528 / 0 (same size) / (changed size) 9.24.678.425 I slot release: id 1 | task 5168 | stop processing: n_tokens = 713, truncated = 0