$ 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 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.095.815 I srv llama_server: initializing ... 0.00.095.823 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.095.932 I srv init_listene: The UI is disabled 0.00.095.934 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.096.026 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) 0.00.104.048 I srv load_model: loading model 'C:\quantdiff\dl\campaign\22086870b009\Ornith-1.5-9B-Q8_0.gguf' 0.01.004.522 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.01.004.538 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.01.004.563 W model has unused tensor blk.32.attn_q.weight (size = 35651584 bytes) -- ignoring 0.01.004.574 W model has unused tensor blk.32.attn_k.weight (size = 4456448 bytes) -- ignoring 0.01.004.582 W model has unused tensor blk.32.attn_v.weight (size = 4456448 bytes) -- ignoring 0.01.004.615 W model has unused tensor blk.32.attn_output.weight (size = 17825792 bytes) -- ignoring 0.01.004.626 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.01.004.635 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.01.004.644 W model has unused tensor blk.32.ffn_gate.weight (size = 53477376 bytes) -- ignoring 0.01.004.653 W model has unused tensor blk.32.ffn_down.weight (size = 53477376 bytes) -- ignoring 0.01.004.661 W model has unused tensor blk.32.ffn_up.weight (size = 53477376 bytes) -- ignoring 0.01.004.671 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring 0.01.004.681 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.01.004.691 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.01.004.719 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.04.028.917 I cmn init: llama threadpool init, n_threads = 8 0.04.115.058 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.04.120.289 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.04.120.308 I srv llama_server: model loaded 0.04.120.311 I srv llama_server: listening on http://127.0.0.1:8089 0.04.644.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.644.796 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.904.523 I slot print_timing: id 0 | task 0 | prompt eval time = 135.60 ms / 368 tokens ( 0.37 ms per token, 2713.88 tokens per second) 0.05.904.528 I slot print_timing: id 0 | task 0 | eval time = 1124.11 ms / 72 tokens ( 15.83 ms per token, 63.16 tokens per second) 0.05.904.529 I slot print_timing: id 0 | task 0 | total time = 1259.71 ms / 440 tokens 0.05.904.535 I slot print_timing: id 0 | task 0 | graphs reused = 71 0.05.904.536 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.904.578 I slot release: id 0 | task 0 | stop processing: n_tokens = 439, truncated = 0 0.05.932.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 5810822 0.05.957.242 I slot launch_slot_: id 0 | task 75 | processing task, is_child = 0 0.07.002.967 I slot print_timing: id 0 | task 75 | prompt eval time = 124.84 ms / 322 tokens ( 0.39 ms per token, 2579.36 tokens per second) 0.07.002.973 I slot print_timing: id 0 | task 75 | eval time = 920.87 ms / 59 tokens ( 15.88 ms per token, 62.98 tokens per second) 0.07.002.974 I slot print_timing: id 0 | task 75 | total time = 1045.71 ms / 381 tokens 0.07.002.975 I slot print_timing: id 0 | task 75 | graphs reused = 128 0.07.002.976 I slot print_timing: id 0 | task 75 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.003.003 I slot release: id 0 | task 75 | stop processing: n_tokens = 380, truncated = 0 0.07.024.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 6909246 0.07.048.445 I slot launch_slot_: id 0 | task 137 | processing task, is_child = 0 0.08.092.541 I slot print_timing: id 0 | task 137 | prompt eval time = 125.77 ms / 365 tokens ( 0.34 ms per token, 2902.05 tokens per second) 0.08.092.547 I slot print_timing: id 0 | task 137 | eval time = 918.30 ms / 60 tokens ( 15.56 ms per token, 64.25 tokens per second) 0.08.092.548 I slot print_timing: id 0 | task 137 | total time = 1044.08 ms / 425 tokens 0.08.092.548 I slot print_timing: id 0 | task 137 | graphs reused = 186 0.08.092.549 I slot print_timing: id 0 | task 137 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.092.577 I slot release: id 0 | task 137 | stop processing: n_tokens = 424, truncated = 0 0.08.108.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 7998820 0.08.133.377 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.09.516.743 I slot print_timing: id 0 | task 200 | prompt eval time = 127.73 ms / 397 tokens ( 0.32 ms per token, 3108.09 tokens per second) 0.09.516.748 I slot print_timing: id 0 | task 200 | eval time = 1255.62 ms / 82 tokens ( 15.50 ms per token, 64.51 tokens per second) 0.09.516.749 I slot print_timing: id 0 | task 200 | total time = 1383.35 ms / 479 tokens 0.09.516.750 I slot print_timing: id 0 | task 200 | graphs reused = 266 0.09.516.751 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.516.784 I slot release: id 0 | task 200 | stop processing: n_tokens = 478, truncated = 0 0.09.556.009 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.094 0.09.580.803 I slot launch_slot_: id 0 | task 285 | processing task, is_child = 0 0.10.573.392 I slot print_timing: id 0 | task 285 | prompt eval time = 132.30 ms / 383 tokens ( 0.35 ms per token, 2894.94 tokens per second) 0.10.573.398 I slot print_timing: id 0 | task 285 | eval time = 860.27 ms / 55 tokens ( 15.93 ms per token, 62.77 tokens per second) 0.10.573.399 I slot print_timing: id 0 | task 285 | total time = 992.57 ms / 438 tokens 0.10.573.399 I slot print_timing: id 0 | task 285 | graphs reused = 319 0.10.573.400 I slot print_timing: id 0 | task 285 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.573.431 I slot release: id 0 | task 285 | stop processing: n_tokens = 437, truncated = 0 0.10.600.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 10479674 0.10.625.443 I slot launch_slot_: id 0 | task 343 | processing task, is_child = 0 0.11.842.838 I slot print_timing: id 0 | task 343 | prompt eval time = 130.59 ms / 372 tokens ( 0.35 ms per token, 2848.65 tokens per second) 0.11.842.844 I slot print_timing: id 0 | task 343 | eval time = 1086.79 ms / 70 tokens ( 15.75 ms per token, 63.49 tokens per second) 0.11.842.845 I slot print_timing: id 0 | task 343 | total time = 1217.38 ms / 442 tokens 0.11.842.846 I slot print_timing: id 0 | task 343 | graphs reused = 387 0.11.842.847 I slot print_timing: id 0 | task 343 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.842.876 I slot release: id 0 | task 343 | stop processing: n_tokens = 441, truncated = 0 0.11.863.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 11749119 0.11.890.583 I slot launch_slot_: id 0 | task 416 | processing task, is_child = 0 0.13.078.000 I slot print_timing: id 0 | task 416 | prompt eval time = 144.28 ms / 422 tokens ( 0.34 ms per token, 2924.81 tokens per second) 0.13.078.006 I slot print_timing: id 0 | task 416 | eval time = 1043.11 ms / 69 tokens ( 15.34 ms per token, 65.19 tokens per second) 0.13.078.007 I slot print_timing: id 0 | task 416 | total time = 1187.39 ms / 491 tokens 0.13.078.009 I slot print_timing: id 0 | task 416 | graphs reused = 454 0.13.078.009 I slot print_timing: id 0 | task 416 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.078.042 I slot release: id 0 | task 416 | stop processing: n_tokens = 490, truncated = 0 0.13.105.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 12984285 0.13.130.021 I slot launch_slot_: id 0 | task 488 | processing task, is_child = 0 0.14.684.575 I slot print_timing: id 0 | task 488 | prompt eval time = 151.05 ms / 470 tokens ( 0.32 ms per token, 3111.49 tokens per second) 0.14.684.581 I slot print_timing: id 0 | task 488 | eval time = 1403.48 ms / 89 tokens ( 15.95 ms per token, 62.70 tokens per second) 0.14.684.582 I slot print_timing: id 0 | task 488 | total time = 1554.53 ms / 559 tokens 0.14.684.582 I slot print_timing: id 0 | task 488 | graphs reused = 540 0.14.684.583 I slot print_timing: id 0 | task 488 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.684.617 I slot release: id 0 | task 488 | stop processing: n_tokens = 558, truncated = 0 0.14.689.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 14590860 0.14.715.288 I slot launch_slot_: id 0 | task 580 | processing task, is_child = 0 0.15.580.050 I slot print_timing: id 0 | task 580 | prompt eval time = 126.77 ms / 345 tokens ( 0.37 ms per token, 2721.40 tokens per second) 0.15.580.056 I slot print_timing: id 0 | task 580 | eval time = 737.97 ms / 47 tokens ( 16.04 ms per token, 62.33 tokens per second) 0.15.580.058 I slot print_timing: id 0 | task 580 | total time = 864.74 ms / 392 tokens 0.15.580.058 I slot print_timing: id 0 | task 580 | graphs reused = 585 0.15.580.059 I slot print_timing: id 0 | task 580 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.580.088 I slot release: id 0 | task 580 | stop processing: n_tokens = 391, truncated = 0 0.15.596.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 15486332 0.15.620.997 I slot launch_slot_: id 0 | task 630 | processing task, is_child = 0 0.16.541.788 I slot print_timing: id 0 | task 630 | prompt eval time = 124.69 ms / 364 tokens ( 0.34 ms per token, 2919.31 tokens per second) 0.16.541.793 I slot print_timing: id 0 | task 630 | eval time = 796.08 ms / 53 tokens ( 15.31 ms per token, 65.32 tokens per second) 0.16.541.794 I slot print_timing: id 0 | task 630 | total time = 920.77 ms / 417 tokens 0.16.541.795 I slot print_timing: id 0 | task 630 | graphs reused = 636 0.16.541.796 I slot print_timing: id 0 | task 630 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.541.824 I slot release: id 0 | task 630 | stop processing: n_tokens = 416, truncated = 0 0.16.560.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 16448067 0.16.584.545 I slot launch_slot_: id 0 | task 686 | processing task, is_child = 0 0.17.948.196 I slot print_timing: id 0 | task 686 | prompt eval time = 126.54 ms / 376 tokens ( 0.34 ms per token, 2971.35 tokens per second) 0.17.948.202 I slot print_timing: id 0 | task 686 | eval time = 1237.09 ms / 80 tokens ( 15.66 ms per token, 63.86 tokens per second) 0.17.948.203 I slot print_timing: id 0 | task 686 | total time = 1363.63 ms / 456 tokens 0.17.948.204 I slot print_timing: id 0 | task 686 | graphs reused = 714 0.17.948.204 I slot print_timing: id 0 | task 686 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.948.235 I slot release: id 0 | task 686 | stop processing: n_tokens = 455, truncated = 0 0.17.976.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 17854478 0.18.001.643 I slot launch_slot_: id 0 | task 769 | processing task, is_child = 0 0.19.230.974 I slot print_timing: id 0 | task 769 | prompt eval time = 132.15 ms / 412 tokens ( 0.32 ms per token, 3117.74 tokens per second) 0.19.230.981 I slot print_timing: id 0 | task 769 | eval time = 1097.16 ms / 70 tokens ( 15.90 ms per token, 62.89 tokens per second) 0.19.230.983 I slot print_timing: id 0 | task 769 | total time = 1229.31 ms / 482 tokens 0.19.230.985 I slot print_timing: id 0 | task 769 | graphs reused = 782 0.19.230.986 I slot print_timing: id 0 | task 769 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.231.019 I slot release: id 0 | task 769 | stop processing: n_tokens = 481, truncated = 0 0.19.265.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 19137262 0.19.290.165 I slot launch_slot_: id 0 | task 842 | processing task, is_child = 0 0.20.366.338 I slot print_timing: id 0 | task 842 | prompt eval time = 127.61 ms / 376 tokens ( 0.34 ms per token, 2946.43 tokens per second) 0.20.366.344 I slot print_timing: id 0 | task 842 | eval time = 948.54 ms / 62 tokens ( 15.55 ms per token, 64.31 tokens per second) 0.20.366.345 I slot print_timing: id 0 | task 842 | total time = 1076.15 ms / 438 tokens 0.20.366.345 I slot print_timing: id 0 | task 842 | graphs reused = 842 0.20.366.346 I slot print_timing: id 0 | task 842 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.366.374 I slot release: id 0 | task 842 | stop processing: n_tokens = 437, truncated = 0 0.20.371.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 20272617 0.20.395.942 I slot launch_slot_: id 0 | task 907 | processing task, is_child = 0 0.21.593.085 I slot print_timing: id 0 | task 907 | prompt eval time = 127.16 ms / 378 tokens ( 0.34 ms per token, 2972.56 tokens per second) 0.21.593.090 I slot print_timing: id 0 | task 907 | eval time = 1069.96 ms / 70 tokens ( 15.51 ms per token, 64.49 tokens per second) 0.21.593.091 I slot print_timing: id 0 | task 907 | total time = 1197.12 ms / 448 tokens 0.21.593.092 I slot print_timing: id 0 | task 907 | graphs reused = 910 0.21.593.093 I slot print_timing: id 0 | task 907 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.593.123 I slot release: id 0 | task 907 | stop processing: n_tokens = 447, truncated = 0 0.21.616.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 21499366 0.21.641.252 I slot launch_slot_: id 0 | task 980 | processing task, is_child = 0 0.22.745.099 I slot print_timing: id 0 | task 980 | prompt eval time = 130.68 ms / 367 tokens ( 0.36 ms per token, 2808.32 tokens per second) 0.22.745.105 I slot print_timing: id 0 | task 980 | eval time = 973.14 ms / 62 tokens ( 15.95 ms per token, 62.68 tokens per second) 0.22.745.106 I slot print_timing: id 0 | task 980 | total time = 1103.83 ms / 429 tokens 0.22.745.107 I slot print_timing: id 0 | task 980 | graphs reused = 970 0.22.745.107 I slot print_timing: id 0 | task 980 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.745.136 I slot release: id 0 | task 980 | stop processing: n_tokens = 428, truncated = 0 0.22.767.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 22651379 0.22.792.937 I slot launch_slot_: id 0 | task 1045 | processing task, is_child = 0 0.24.133.489 I slot print_timing: id 0 | task 1045 | prompt eval time = 128.70 ms / 347 tokens ( 0.37 ms per token, 2696.28 tokens per second) 0.24.133.494 I slot print_timing: id 0 | task 1045 | eval time = 1211.83 ms / 78 tokens ( 15.74 ms per token, 63.54 tokens per second) 0.24.133.495 I slot print_timing: id 0 | task 1045 | total time = 1340.53 ms / 425 tokens 0.24.133.496 I slot print_timing: id 0 | task 1045 | graphs reused = 1046 0.24.133.497 I slot print_timing: id 0 | task 1045 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.133.529 I slot release: id 0 | task 1045 | stop processing: n_tokens = 424, truncated = 0 0.24.150.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 24039772 0.24.175.293 I slot launch_slot_: id 0 | task 1126 | processing task, is_child = 0 0.25.215.173 I slot print_timing: id 0 | task 1126 | prompt eval time = 122.36 ms / 369 tokens ( 0.33 ms per token, 3015.74 tokens per second) 0.25.215.179 I slot print_timing: id 0 | task 1126 | eval time = 917.50 ms / 61 tokens ( 15.29 ms per token, 65.39 tokens per second) 0.25.215.180 I slot print_timing: id 0 | task 1126 | total time = 1039.86 ms / 430 tokens 0.25.215.181 I slot print_timing: id 0 | task 1126 | graphs reused = 1105 0.25.215.182 I slot print_timing: id 0 | task 1126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.215.210 I slot release: id 0 | task 1126 | stop processing: n_tokens = 429, truncated = 0 0.25.219.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 25121453 0.25.244.716 I slot launch_slot_: id 0 | task 1190 | processing task, is_child = 0 0.26.003.687 I slot print_timing: id 0 | task 1190 | prompt eval time = 123.21 ms / 352 tokens ( 0.35 ms per token, 2857.00 tokens per second) 0.26.003.692 I slot print_timing: id 0 | task 1190 | eval time = 635.74 ms / 41 tokens ( 15.89 ms per token, 62.92 tokens per second) 0.26.003.693 I slot print_timing: id 0 | task 1190 | total time = 758.95 ms / 393 tokens 0.26.003.694 I slot print_timing: id 0 | task 1190 | graphs reused = 1144 0.26.003.695 I slot print_timing: id 0 | task 1190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.003.721 I slot release: id 0 | task 1190 | stop processing: n_tokens = 392, truncated = 0 0.26.023.921 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 25909965 0.26.048.095 I slot launch_slot_: id 0 | task 1234 | processing task, is_child = 0 0.27.020.643 I slot print_timing: id 0 | task 1234 | prompt eval time = 127.27 ms / 349 tokens ( 0.36 ms per token, 2742.12 tokens per second) 0.27.020.649 I slot print_timing: id 0 | task 1234 | eval time = 845.25 ms / 54 tokens ( 15.95 ms per token, 62.70 tokens per second) 0.27.020.650 I slot print_timing: id 0 | task 1234 | total time = 972.52 ms / 403 tokens 0.27.020.651 I slot print_timing: id 0 | task 1234 | graphs reused = 1196 0.27.020.652 I slot print_timing: id 0 | task 1234 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.020.682 I slot release: id 0 | task 1234 | stop processing: n_tokens = 402, truncated = 0 0.27.048.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 26926925 0.27.073.297 I slot launch_slot_: id 0 | task 1291 | processing task, is_child = 0 0.28.514.296 I slot print_timing: id 0 | task 1291 | prompt eval time = 134.22 ms / 384 tokens ( 0.35 ms per token, 2860.87 tokens per second) 0.28.514.301 I slot print_timing: id 0 | task 1291 | eval time = 1306.75 ms / 84 tokens ( 15.74 ms per token, 63.52 tokens per second) 0.28.514.302 I slot print_timing: id 0 | task 1291 | total time = 1440.98 ms / 468 tokens 0.28.514.303 I slot print_timing: id 0 | task 1291 | graphs reused = 1278 0.28.514.304 I slot print_timing: id 0 | task 1291 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.514.337 I slot release: id 0 | task 1291 | stop processing: n_tokens = 467, truncated = 0 0.28.535.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 28420580 0.28.561.184 I slot launch_slot_: id 0 | task 1378 | processing task, is_child = 0 0.29.892.499 I slot print_timing: id 0 | task 1378 | prompt eval time = 121.15 ms / 356 tokens ( 0.34 ms per token, 2938.58 tokens per second) 0.29.892.505 I slot print_timing: id 0 | task 1378 | eval time = 1210.15 ms / 79 tokens ( 15.51 ms per token, 64.46 tokens per second) 0.29.892.506 I slot print_timing: id 0 | task 1378 | total time = 1331.29 ms / 435 tokens 0.29.892.507 I slot print_timing: id 0 | task 1378 | graphs reused = 1355 0.29.892.508 I slot print_timing: id 0 | task 1378 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.892.538 I slot release: id 0 | task 1378 | stop processing: n_tokens = 434, truncated = 0 0.29.920.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 29798782 0.29.945.242 I slot launch_slot_: id 0 | task 1460 | processing task, is_child = 0 0.31.455.785 I slot print_timing: id 0 | task 1460 | prompt eval time = 132.61 ms / 410 tokens ( 0.32 ms per token, 3091.70 tokens per second) 0.31.455.791 I slot print_timing: id 0 | task 1460 | eval time = 1377.91 ms / 88 tokens ( 15.84 ms per token, 63.14 tokens per second) 0.31.455.792 I slot print_timing: id 0 | task 1460 | total time = 1510.52 ms / 498 tokens 0.31.455.793 I slot print_timing: id 0 | task 1460 | graphs reused = 1441 0.31.455.794 I slot print_timing: id 0 | task 1460 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.455.823 I slot release: id 0 | task 1460 | stop processing: n_tokens = 497, truncated = 0 0.31.492.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 497, t_last = 31362066 0.31.517.915 I slot launch_slot_: id 0 | task 1551 | processing task, is_child = 0 0.32.532.860 I slot print_timing: id 0 | task 1551 | prompt eval time = 130.75 ms / 385 tokens ( 0.34 ms per token, 2944.62 tokens per second) 0.32.532.866 I slot print_timing: id 0 | task 1551 | eval time = 884.18 ms / 58 tokens ( 15.51 ms per token, 64.47 tokens per second) 0.32.532.867 I slot print_timing: id 0 | task 1551 | total time = 1014.92 ms / 443 tokens 0.32.532.868 I slot print_timing: id 0 | task 1551 | graphs reused = 1497 0.32.532.869 I slot print_timing: id 0 | task 1551 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.532.898 I slot release: id 0 | task 1551 | stop processing: n_tokens = 442, truncated = 0 0.32.571.603 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 32439141 0.32.596.474 I slot launch_slot_: id 0 | task 1612 | processing task, is_child = 0 0.34.141.638 I slot print_timing: id 0 | task 1612 | prompt eval time = 129.20 ms / 395 tokens ( 0.33 ms per token, 3057.35 tokens per second) 0.34.141.643 I slot print_timing: id 0 | task 1612 | eval time = 1415.95 ms / 92 tokens ( 15.56 ms per token, 64.27 tokens per second) 0.34.141.645 I slot print_timing: id 0 | task 1612 | total time = 1545.15 ms / 487 tokens 0.34.141.645 I slot print_timing: id 0 | task 1612 | graphs reused = 1587 0.34.141.646 I slot print_timing: id 0 | task 1612 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.141.676 I slot release: id 0 | task 1612 | stop processing: n_tokens = 486, truncated = 0 0.34.168.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 34047920 0.34.193.537 I slot launch_slot_: id 0 | task 1707 | processing task, is_child = 0 0.35.649.350 I slot print_timing: id 0 | task 1707 | prompt eval time = 134.86 ms / 430 tokens ( 0.31 ms per token, 3188.52 tokens per second) 0.35.649.356 I slot print_timing: id 0 | task 1707 | eval time = 1320.93 ms / 84 tokens ( 15.91 ms per token, 62.83 tokens per second) 0.35.649.358 I slot print_timing: id 0 | task 1707 | total time = 1455.79 ms / 514 tokens 0.35.649.358 I slot print_timing: id 0 | task 1707 | graphs reused = 1668 0.35.649.359 I slot print_timing: id 0 | task 1707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.649.390 I slot release: id 0 | task 1707 | stop processing: n_tokens = 513, truncated = 0 0.35.677.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 35555633 0.35.702.047 I slot launch_slot_: id 0 | task 1794 | processing task, is_child = 0 0.36.773.662 I slot print_timing: id 0 | task 1794 | prompt eval time = 132.41 ms / 392 tokens ( 0.34 ms per token, 2960.52 tokens per second) 0.36.773.668 I slot print_timing: id 0 | task 1794 | eval time = 939.19 ms / 62 tokens ( 15.40 ms per token, 64.95 tokens per second) 0.36.773.669 I slot print_timing: id 0 | task 1794 | total time = 1071.60 ms / 454 tokens 0.36.773.669 I slot print_timing: id 0 | task 1794 | graphs reused = 1728 0.36.773.670 I slot print_timing: id 0 | task 1794 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.773.698 I slot release: id 0 | task 1794 | stop processing: n_tokens = 453, truncated = 0 0.36.816.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 36679941 0.36.841.266 I slot launch_slot_: id 0 | task 1859 | processing task, is_child = 0 0.38.034.091 I slot print_timing: id 0 | task 1859 | prompt eval time = 121.05 ms / 350 tokens ( 0.35 ms per token, 2891.32 tokens per second) 0.38.034.097 I slot print_timing: id 0 | task 1859 | eval time = 1071.75 ms / 70 tokens ( 15.53 ms per token, 64.38 tokens per second) 0.38.034.098 I slot print_timing: id 0 | task 1859 | total time = 1192.80 ms / 420 tokens 0.38.034.099 I slot print_timing: id 0 | task 1859 | graphs reused = 1796 0.38.034.099 I slot print_timing: id 0 | task 1859 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.034.131 I slot release: id 0 | task 1859 | stop processing: n_tokens = 419, truncated = 0 0.38.039.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 37940374 0.38.064.827 I slot launch_slot_: id 0 | task 1932 | processing task, is_child = 0 0.39.470.932 I slot print_timing: id 0 | task 1932 | prompt eval time = 133.16 ms / 380 tokens ( 0.35 ms per token, 2853.69 tokens per second) 0.39.470.938 I slot print_timing: id 0 | task 1932 | eval time = 1272.92 ms / 80 tokens ( 16.11 ms per token, 62.06 tokens per second) 0.39.470.939 I slot print_timing: id 0 | task 1932 | total time = 1406.09 ms / 460 tokens 0.39.470.940 I slot print_timing: id 0 | task 1932 | graphs reused = 1874 0.39.470.940 I slot print_timing: id 0 | task 1932 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.470.971 I slot release: id 0 | task 1932 | stop processing: n_tokens = 459, truncated = 0 0.39.496.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 39377215 0.39.524.522 I slot launch_slot_: id 0 | task 2015 | processing task, is_child = 0 0.41.135.520 I slot print_timing: id 0 | task 2015 | prompt eval time = 135.84 ms / 410 tokens ( 0.33 ms per token, 3018.28 tokens per second) 0.41.135.527 I slot print_timing: id 0 | task 2015 | eval time = 1475.13 ms / 95 tokens ( 15.69 ms per token, 63.72 tokens per second) 0.41.135.528 I slot print_timing: id 0 | task 2015 | total time = 1610.97 ms / 505 tokens 0.41.135.529 I slot print_timing: id 0 | task 2015 | graphs reused = 1967 0.41.135.530 I slot print_timing: id 0 | task 2015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.135.560 I slot release: id 0 | task 2015 | stop processing: n_tokens = 504, truncated = 0 0.41.162.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 41041803 0.41.186.939 I slot launch_slot_: id 0 | task 2113 | processing task, is_child = 0 0.42.363.814 I slot print_timing: id 0 | task 2113 | prompt eval time = 126.55 ms / 387 tokens ( 0.33 ms per token, 3058.20 tokens per second) 0.42.363.821 I slot print_timing: id 0 | task 2113 | eval time = 1050.31 ms / 68 tokens ( 15.68 ms per token, 63.79 tokens per second) 0.42.363.822 I slot print_timing: id 0 | task 2113 | total time = 1176.86 ms / 455 tokens 0.42.363.823 I slot print_timing: id 0 | task 2113 | graphs reused = 2033 0.42.363.824 I slot print_timing: id 0 | task 2113 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.363.858 I slot release: id 0 | task 2113 | stop processing: n_tokens = 454, truncated = 0 0.42.383.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 42270101 0.42.408.179 I slot launch_slot_: id 0 | task 2184 | processing task, is_child = 0 0.43.734.646 I slot print_timing: id 0 | task 2184 | prompt eval time = 124.55 ms / 358 tokens ( 0.35 ms per token, 2874.28 tokens per second) 0.43.734.651 I slot print_timing: id 0 | task 2184 | eval time = 1201.89 ms / 77 tokens ( 15.81 ms per token, 63.23 tokens per second) 0.43.734.652 I slot print_timing: id 0 | task 2184 | total time = 1326.45 ms / 435 tokens 0.43.734.653 I slot print_timing: id 0 | task 2184 | graphs reused = 2108 0.43.734.654 I slot print_timing: id 0 | task 2184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.734.683 I slot release: id 0 | task 2184 | stop processing: n_tokens = 434, truncated = 0 0.43.756.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 43640926 0.43.780.829 I slot launch_slot_: id 0 | task 2264 | processing task, is_child = 0 0.44.993.644 I slot print_timing: id 0 | task 2264 | prompt eval time = 123.57 ms / 359 tokens ( 0.34 ms per token, 2905.33 tokens per second) 0.44.993.650 I slot print_timing: id 0 | task 2264 | eval time = 1089.23 ms / 72 tokens ( 15.34 ms per token, 65.18 tokens per second) 0.44.993.651 I slot print_timing: id 0 | task 2264 | total time = 1212.79 ms / 431 tokens 0.44.993.652 I slot print_timing: id 0 | task 2264 | graphs reused = 2178 0.44.993.652 I slot print_timing: id 0 | task 2264 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.993.680 I slot release: id 0 | task 2264 | stop processing: n_tokens = 430, truncated = 0 0.45.008.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 44899923 0.45.032.580 I slot launch_slot_: id 0 | task 2339 | processing task, is_child = 0 0.46.419.620 I slot print_timing: id 0 | task 2339 | prompt eval time = 126.01 ms / 387 tokens ( 0.33 ms per token, 3071.26 tokens per second) 0.46.419.626 I slot print_timing: id 0 | task 2339 | eval time = 1261.01 ms / 82 tokens ( 15.57 ms per token, 64.23 tokens per second) 0.46.419.627 I slot print_timing: id 0 | task 2339 | total time = 1387.02 ms / 469 tokens 0.46.419.628 I slot print_timing: id 0 | task 2339 | graphs reused = 2258 0.46.419.629 I slot print_timing: id 0 | task 2339 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.419.659 I slot release: id 0 | task 2339 | stop processing: n_tokens = 468, truncated = 0 0.46.447.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 46325902 0.46.471.443 I slot launch_slot_: id 0 | task 2424 | processing task, is_child = 0 0.47.929.859 I slot print_timing: id 0 | task 2424 | prompt eval time = 131.10 ms / 410 tokens ( 0.32 ms per token, 3127.26 tokens per second) 0.47.929.864 I slot print_timing: id 0 | task 2424 | eval time = 1327.29 ms / 85 tokens ( 15.80 ms per token, 63.29 tokens per second) 0.47.929.866 I slot print_timing: id 0 | task 2424 | total time = 1458.39 ms / 495 tokens 0.47.929.866 I slot print_timing: id 0 | task 2424 | graphs reused = 2341 0.47.929.867 I slot print_timing: id 0 | task 2424 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.929.896 I slot release: id 0 | task 2424 | stop processing: n_tokens = 494, truncated = 0 0.47.956.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 47836140 0.47.980.446 I slot launch_slot_: id 0 | task 2512 | processing task, is_child = 0 0.48.856.861 I slot print_timing: id 0 | task 2512 | prompt eval time = 123.76 ms / 351 tokens ( 0.35 ms per token, 2836.13 tokens per second) 0.48.856.866 I slot print_timing: id 0 | task 2512 | eval time = 752.63 ms / 50 tokens ( 15.36 ms per token, 65.10 tokens per second) 0.48.856.867 I slot print_timing: id 0 | task 2512 | total time = 876.39 ms / 401 tokens 0.48.856.868 I slot print_timing: id 0 | task 2512 | graphs reused = 2389 0.48.856.869 I slot print_timing: id 0 | task 2512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.856.897 I slot release: id 0 | task 2512 | stop processing: n_tokens = 400, truncated = 0 0.48.896.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 48763140 0.48.921.074 I slot launch_slot_: id 0 | task 2565 | processing task, is_child = 0 0.52.062.093 I slot print_timing: id 0 | task 2565 | n_gen = 192, tg = 63.35 t/s, tg_3s = 63.68 t/s 0.52.845.130 I slot print_timing: id 0 | task 2565 | prompt eval time = 125.95 ms / 393 tokens ( 0.32 ms per token, 3120.24 tokens per second) 0.52.845.136 I slot print_timing: id 0 | task 2565 | eval time = 3798.08 ms / 243 tokens ( 15.69 ms per token, 63.72 tokens per second) 0.52.845.137 I slot print_timing: id 0 | task 2565 | total time = 3924.03 ms / 636 tokens 0.52.845.138 I slot print_timing: id 0 | task 2565 | graphs reused = 2629 0.52.845.140 I slot print_timing: id 0 | task 2565 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.845.170 I slot release: id 0 | task 2565 | stop processing: n_tokens = 635, truncated = 0 0.52.869.603 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 52751413 0.52.896.225 I slot launch_slot_: id 0 | task 2811 | processing task, is_child = 0 0.53.732.457 I slot print_timing: id 0 | task 2811 | prompt eval time = 119.33 ms / 321 tokens ( 0.37 ms per token, 2689.93 tokens per second) 0.53.732.463 I slot print_timing: id 0 | task 2811 | eval time = 716.88 ms / 48 tokens ( 15.25 ms per token, 65.56 tokens per second) 0.53.732.464 I slot print_timing: id 0 | task 2811 | total time = 836.21 ms / 369 tokens 0.53.732.465 I slot print_timing: id 0 | task 2811 | graphs reused = 2675 0.53.732.466 I slot print_timing: id 0 | task 2811 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.732.491 I slot release: id 0 | task 2811 | stop processing: n_tokens = 368, truncated = 0 0.53.759.877 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 53638734 0.53.783.909 I slot launch_slot_: id 0 | task 2862 | processing task, is_child = 0 0.55.956.191 I slot print_timing: id 0 | task 2862 | prompt eval time = 123.70 ms / 330 tokens ( 0.37 ms per token, 2667.70 tokens per second) 0.55.956.196 I slot print_timing: id 0 | task 2862 | eval time = 2048.56 ms / 131 tokens ( 15.76 ms per token, 63.46 tokens per second) 0.55.956.198 I slot print_timing: id 0 | task 2862 | total time = 2172.26 ms / 461 tokens 0.55.956.199 I slot print_timing: id 0 | task 2862 | graphs reused = 2804 0.55.956.199 I slot print_timing: id 0 | task 2862 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.956.228 I slot release: id 0 | task 2862 | stop processing: n_tokens = 460, truncated = 0 0.55.979.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 55862471 0.56.003.755 I slot launch_slot_: id 0 | task 2996 | processing task, is_child = 0 0.57.037.013 I slot print_timing: id 0 | task 2996 | prompt eval time = 123.58 ms / 341 tokens ( 0.36 ms per token, 2759.35 tokens per second) 0.57.037.019 I slot print_timing: id 0 | task 2996 | eval time = 909.66 ms / 60 tokens ( 15.42 ms per token, 64.86 tokens per second) 0.57.037.020 I slot print_timing: id 0 | task 2996 | total time = 1033.24 ms / 401 tokens 0.57.037.021 I slot print_timing: id 0 | task 2996 | graphs reused = 2862 0.57.037.022 I slot print_timing: id 0 | task 2996 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.037.050 I slot release: id 0 | task 2996 | stop processing: n_tokens = 400, truncated = 0 0.57.076.224 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 56943293 0.57.099.831 I slot launch_slot_: id 0 | task 3059 | processing task, is_child = 0 0.58.129.126 I slot print_timing: id 0 | task 3059 | prompt eval time = 119.58 ms / 338 tokens ( 0.35 ms per token, 2826.44 tokens per second) 0.58.129.131 I slot print_timing: id 0 | task 3059 | eval time = 909.69 ms / 60 tokens ( 15.42 ms per token, 64.86 tokens per second) 0.58.129.133 I slot print_timing: id 0 | task 3059 | total time = 1029.27 ms / 398 tokens 0.58.129.134 I slot print_timing: id 0 | task 3059 | graphs reused = 2920 0.58.129.134 I slot print_timing: id 0 | task 3059 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.129.160 I slot release: id 0 | task 3059 | stop processing: n_tokens = 397, truncated = 0 0.58.152.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 58035403 0.58.176.199 I slot launch_slot_: id 0 | task 3122 | processing task, is_child = 0 0.59.177.114 I slot print_timing: id 0 | task 3122 | prompt eval time = 130.86 ms / 395 tokens ( 0.33 ms per token, 3018.47 tokens per second) 0.59.177.119 I slot print_timing: id 0 | task 3122 | eval time = 870.03 ms / 56 tokens ( 15.82 ms per token, 63.22 tokens per second) 0.59.177.120 I slot print_timing: id 0 | task 3122 | total time = 1000.89 ms / 451 tokens 0.59.177.121 I slot print_timing: id 0 | task 3122 | graphs reused = 2974 0.59.177.122 I slot print_timing: id 0 | task 3122 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.177.151 I slot release: id 0 | task 3122 | stop processing: n_tokens = 450, truncated = 0 0.59.207.868 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 59083394 0.59.232.049 I slot launch_slot_: id 0 | task 3181 | processing task, is_child = 0 1.00.704.099 I slot print_timing: id 0 | task 3181 | prompt eval time = 184.81 ms / 528 tokens ( 0.35 ms per token, 2856.94 tokens per second) 1.00.704.105 I slot print_timing: id 0 | task 3181 | eval time = 1287.22 ms / 83 tokens ( 15.70 ms per token, 63.70 tokens per second) 1.00.704.106 I slot print_timing: id 0 | task 3181 | total time = 1472.03 ms / 611 tokens 1.00.704.107 I slot print_timing: id 0 | task 3181 | graphs reused = 3055 1.00.704.107 I slot print_timing: id 0 | task 3181 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.704.142 I slot release: id 0 | task 3181 | stop processing: n_tokens = 610, truncated = 0 1.00.726.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 60610385 1.00.756.765 I slot launch_slot_: id 0 | task 3268 | processing task, is_child = 0 1.01.826.390 I slot print_timing: id 0 | task 3268 | prompt eval time = 139.36 ms / 331 tokens ( 0.42 ms per token, 2375.11 tokens per second) 1.01.826.396 I slot print_timing: id 0 | task 3268 | eval time = 930.24 ms / 62 tokens ( 15.25 ms per token, 65.57 tokens per second) 1.01.826.397 I slot print_timing: id 0 | task 3268 | total time = 1069.61 ms / 393 tokens 1.01.826.398 I slot print_timing: id 0 | task 3268 | graphs reused = 3115 1.01.826.399 I slot print_timing: id 0 | task 3268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.826.425 I slot release: id 0 | task 3268 | stop processing: n_tokens = 404, truncated = 0 1.01.850.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 61732668 1.01.880.973 I slot launch_slot_: id 0 | task 3333 | processing task, is_child = 0 1.03.211.212 I slot print_timing: id 0 | task 3333 | prompt eval time = 146.94 ms / 362 tokens ( 0.41 ms per token, 2463.56 tokens per second) 1.03.211.218 I slot print_timing: id 0 | task 3333 | eval time = 1183.28 ms / 76 tokens ( 15.78 ms per token, 63.38 tokens per second) 1.03.211.219 I slot print_timing: id 0 | task 3333 | total time = 1330.22 ms / 438 tokens 1.03.211.220 I slot print_timing: id 0 | task 3333 | graphs reused = 3189 1.03.211.220 I slot print_timing: id 0 | task 3333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.211.251 I slot release: id 0 | task 3333 | stop processing: n_tokens = 449, truncated = 0 1.03.240.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 63117494 1.03.269.579 I slot launch_slot_: id 0 | task 3412 | processing task, is_child = 0 1.04.660.548 I slot print_timing: id 0 | task 3412 | prompt eval time = 149.10 ms / 419 tokens ( 0.36 ms per token, 2810.12 tokens per second) 1.04.660.553 I slot print_timing: id 0 | task 3412 | eval time = 1241.84 ms / 80 tokens ( 15.72 ms per token, 63.62 tokens per second) 1.04.660.554 I slot print_timing: id 0 | task 3412 | total time = 1390.95 ms / 499 tokens 1.04.660.555 I slot print_timing: id 0 | task 3412 | graphs reused = 3267 1.04.660.556 I slot print_timing: id 0 | task 3412 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.660.587 I slot release: id 0 | task 3412 | stop processing: n_tokens = 510, truncated = 0 1.04.692.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 64566830 1.04.722.655 I slot launch_slot_: id 0 | task 3495 | processing task, is_child = 0 1.05.538.994 I slot print_timing: id 0 | task 3495 | prompt eval time = 159.47 ms / 423 tokens ( 0.38 ms per token, 2652.49 tokens per second) 1.05.539.000 I slot print_timing: id 0 | task 3495 | eval time = 656.84 ms / 44 tokens ( 15.28 ms per token, 65.46 tokens per second) 1.05.539.001 I slot print_timing: id 0 | task 3495 | total time = 816.32 ms / 467 tokens 1.05.539.002 I slot print_timing: id 0 | task 3495 | graphs reused = 3309 1.05.539.003 I slot print_timing: id 0 | task 3495 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.539.035 I slot release: id 0 | task 3495 | stop processing: n_tokens = 478, truncated = 0 1.05.554.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 65445278 1.05.584.108 I slot launch_slot_: id 0 | task 3542 | processing task, is_child = 0 1.06.383.595 I slot print_timing: id 0 | task 3542 | prompt eval time = 138.35 ms / 341 tokens ( 0.41 ms per token, 2464.69 tokens per second) 1.06.383.601 I slot print_timing: id 0 | task 3542 | eval time = 661.11 ms / 43 tokens ( 15.74 ms per token, 63.53 tokens per second) 1.06.383.602 I slot print_timing: id 0 | task 3542 | total time = 799.47 ms / 384 tokens 1.06.383.602 I slot print_timing: id 0 | task 3542 | graphs reused = 3350 1.06.383.603 I slot print_timing: id 0 | task 3542 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.383.632 I slot release: id 0 | task 3542 | stop processing: n_tokens = 395, truncated = 0 1.06.408.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 66289875 1.06.436.727 I slot launch_slot_: id 0 | task 3588 | processing task, is_child = 0 1.07.614.819 I slot print_timing: id 0 | task 3588 | prompt eval time = 143.44 ms / 356 tokens ( 0.40 ms per token, 2481.91 tokens per second) 1.07.614.824 I slot print_timing: id 0 | task 3588 | eval time = 1034.63 ms / 66 tokens ( 15.92 ms per token, 62.82 tokens per second) 1.07.614.826 I slot print_timing: id 0 | task 3588 | total time = 1178.07 ms / 422 tokens 1.07.614.826 I slot print_timing: id 0 | task 3588 | graphs reused = 3414 1.07.614.827 I slot print_timing: id 0 | task 3588 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.614.854 I slot release: id 0 | task 3588 | stop processing: n_tokens = 433, truncated = 0 1.07.655.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 67521097 1.07.655.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 1.07.695.332 I slot launch_slot_: id 0 | task 3657 | processing task, is_child = 0 1.08.530.661 I slot print_timing: id 0 | task 3657 | prompt eval time = 148.00 ms / 362 tokens ( 0.41 ms per token, 2445.95 tokens per second) 1.08.530.667 I slot print_timing: id 0 | task 3657 | eval time = 687.31 ms / 44 tokens ( 15.98 ms per token, 62.56 tokens per second) 1.08.530.668 I slot print_timing: id 0 | task 3657 | total time = 835.31 ms / 406 tokens 1.08.530.669 I slot print_timing: id 0 | task 3657 | graphs reused = 3456 1.08.530.670 I slot print_timing: id 0 | task 3657 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.530.701 I slot release: id 0 | task 3657 | stop processing: n_tokens = 417, truncated = 0 1.08.535.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 68436944 1.08.535.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.636 MiB) 1.08.575.363 I slot launch_slot_: id 0 | task 3704 | processing task, is_child = 0 1.09.751.515 I slot print_timing: id 0 | task 3704 | prompt eval time = 146.53 ms / 391 tokens ( 0.37 ms per token, 2668.49 tokens per second) 1.09.751.521 I slot print_timing: id 0 | task 3704 | eval time = 1029.61 ms / 68 tokens ( 15.37 ms per token, 65.07 tokens per second) 1.09.751.522 I slot print_timing: id 0 | task 3704 | total time = 1176.13 ms / 459 tokens 1.09.751.523 I slot print_timing: id 0 | task 3704 | graphs reused = 3522 1.09.751.524 I slot print_timing: id 0 | task 3704 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.751.556 I slot release: id 0 | task 3704 | stop processing: n_tokens = 470, truncated = 0 1.09.780.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 69657799 1.09.780.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 1.09.783.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.700 MiB) 1.09.825.016 I slot launch_slot_: id 0 | task 3775 | processing task, is_child = 0 1.10.798.684 I slot print_timing: id 0 | task 3775 | prompt eval time = 138.45 ms / 343 tokens ( 0.40 ms per token, 2477.41 tokens per second) 1.10.798.689 I slot print_timing: id 0 | task 3775 | eval time = 835.20 ms / 54 tokens ( 15.76 ms per token, 63.46 tokens per second) 1.10.798.690 I slot print_timing: id 0 | task 3775 | total time = 973.65 ms / 397 tokens 1.10.798.691 I slot print_timing: id 0 | task 3775 | graphs reused = 3574 1.10.798.692 I slot print_timing: id 0 | task 3775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.798.719 I slot release: id 0 | task 3775 | stop processing: n_tokens = 408, truncated = 0 1.10.824.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 70704963 1.10.824.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 1.10.861.924 I slot launch_slot_: id 0 | task 3832 | processing task, is_child = 0 1.12.294.516 I slot print_timing: id 0 | task 3832 | prompt eval time = 152.83 ms / 401 tokens ( 0.38 ms per token, 2623.88 tokens per second) 1.12.294.522 I slot print_timing: id 0 | task 3832 | eval time = 1279.75 ms / 82 tokens ( 15.80 ms per token, 63.29 tokens per second) 1.12.294.523 I slot print_timing: id 0 | task 3832 | total time = 1432.57 ms / 483 tokens 1.12.294.524 I slot print_timing: id 0 | task 3832 | graphs reused = 3654 1.12.294.525 I slot print_timing: id 0 | task 3832 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.294.557 I slot release: id 0 | task 3832 | stop processing: n_tokens = 494, truncated = 0 1.12.330.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 72200800 1.12.330.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.543 MiB) 1.12.370.503 I slot launch_slot_: id 0 | task 3917 | processing task, is_child = 0 1.13.539.267 I slot print_timing: id 0 | task 3917 | prompt eval time = 142.81 ms / 355 tokens ( 0.40 ms per token, 2485.91 tokens per second) 1.13.539.273 I slot print_timing: id 0 | task 3917 | eval time = 1025.94 ms / 68 tokens ( 15.31 ms per token, 65.31 tokens per second) 1.13.539.274 I slot print_timing: id 0 | task 3917 | total time = 1168.74 ms / 423 tokens 1.13.539.274 I slot print_timing: id 0 | task 3917 | graphs reused = 3720 1.13.539.275 I slot print_timing: id 0 | task 3917 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.539.304 I slot release: id 0 | task 3917 | stop processing: n_tokens = 434, truncated = 0 1.13.559.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 73445547 1.13.559.476 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.076 MiB) 1.13.599.218 I slot launch_slot_: id 0 | task 3988 | processing task, is_child = 0 1.14.936.368 I slot print_timing: id 0 | task 3988 | prompt eval time = 139.73 ms / 351 tokens ( 0.40 ms per token, 2511.95 tokens per second) 1.14.936.374 I slot print_timing: id 0 | task 3988 | eval time = 1197.40 ms / 76 tokens ( 15.97 ms per token, 62.64 tokens per second) 1.14.936.375 I slot print_timing: id 0 | task 3988 | total time = 1337.13 ms / 427 tokens 1.14.936.375 I slot print_timing: id 0 | task 3988 | graphs reused = 3794 1.14.936.376 I slot print_timing: id 0 | task 3988 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.936.404 I slot release: id 0 | task 3988 | stop processing: n_tokens = 438, truncated = 0 1.14.975.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 74842648 1.14.975.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.202 MiB) 1.14.978.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 1.15.020.465 I slot launch_slot_: id 0 | task 4067 | processing task, is_child = 0 1.16.952.106 I slot print_timing: id 0 | task 4067 | prompt eval time = 169.25 ms / 475 tokens ( 0.36 ms per token, 2806.42 tokens per second) 1.16.952.112 I slot print_timing: id 0 | task 4067 | eval time = 1762.37 ms / 113 tokens ( 15.74 ms per token, 63.55 tokens per second) 1.16.952.113 I slot print_timing: id 0 | task 4067 | total time = 1931.62 ms / 588 tokens 1.16.952.113 I slot print_timing: id 0 | task 4067 | graphs reused = 3904 1.16.952.114 I slot print_timing: id 0 | task 4067 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.952.147 I slot release: id 0 | task 4067 | stop processing: n_tokens = 599, truncated = 0 1.16.977.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 599, t_last = 76858391 1.16.977.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.17.014.942 I slot launch_slot_: id 0 | task 4183 | processing task, is_child = 0 1.19.256.586 I slot print_timing: id 0 | task 4183 | prompt eval time = 163.08 ms / 440 tokens ( 0.37 ms per token, 2698.06 tokens per second) 1.19.256.591 I slot print_timing: id 0 | task 4183 | eval time = 2078.54 ms / 135 tokens ( 15.51 ms per token, 64.47 tokens per second) 1.19.256.592 I slot print_timing: id 0 | task 4183 | total time = 2241.62 ms / 575 tokens 1.19.256.593 I slot print_timing: id 0 | task 4183 | graphs reused = 4036 1.19.256.594 I slot print_timing: id 0 | task 4183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.256.627 I slot release: id 0 | task 4183 | stop processing: n_tokens = 586, truncated = 0 1.19.261.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 79162870 1.19.261.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.981 MiB) 1.19.302.122 I slot launch_slot_: id 0 | task 4321 | processing task, is_child = 0 1.20.569.062 I slot print_timing: id 0 | task 4321 | prompt eval time = 142.75 ms / 345 tokens ( 0.41 ms per token, 2416.74 tokens per second) 1.20.569.069 I slot print_timing: id 0 | task 4321 | eval time = 1124.17 ms / 72 tokens ( 15.83 ms per token, 63.16 tokens per second) 1.20.569.070 I slot print_timing: id 0 | task 4321 | total time = 1266.92 ms / 417 tokens 1.20.569.071 I slot print_timing: id 0 | task 4321 | graphs reused = 4106 1.20.569.072 I slot print_timing: id 0 | task 4321 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.569.102 I slot release: id 0 | task 4321 | stop processing: n_tokens = 428, truncated = 0 1.20.586.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 80475345 1.20.586.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.794 MiB) 1.20.589.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 1.20.631.330 I slot launch_slot_: id 0 | task 4396 | processing task, is_child = 0 1.21.937.531 I slot print_timing: id 0 | task 4396 | prompt eval time = 148.33 ms / 382 tokens ( 0.39 ms per token, 2575.30 tokens per second) 1.21.937.537 I slot print_timing: id 0 | task 4396 | eval time = 1157.85 ms / 77 tokens ( 15.23 ms per token, 65.64 tokens per second) 1.21.937.538 I slot print_timing: id 0 | task 4396 | total time = 1306.18 ms / 459 tokens 1.21.937.539 I slot print_timing: id 0 | task 4396 | graphs reused = 4181 1.21.937.541 I slot print_timing: id 0 | task 4396 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.937.571 I slot release: id 0 | task 4396 | stop processing: n_tokens = 470, truncated = 0 1.21.941.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 81843815 1.21.942.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.21.979.168 I slot launch_slot_: id 0 | task 4476 | processing task, is_child = 0 1.22.807.809 I slot print_timing: id 0 | task 4476 | prompt eval time = 137.87 ms / 337 tokens ( 0.41 ms per token, 2444.37 tokens per second) 1.22.807.814 I slot print_timing: id 0 | task 4476 | eval time = 690.75 ms / 45 tokens ( 15.70 ms per token, 63.70 tokens per second) 1.22.807.815 I slot print_timing: id 0 | task 4476 | total time = 828.62 ms / 382 tokens 1.22.807.815 I slot print_timing: id 0 | task 4476 | graphs reused = 4224 1.22.807.816 I slot print_timing: id 0 | task 4476 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.807.844 I slot release: id 0 | task 4476 | stop processing: n_tokens = 393, truncated = 0 1.22.840.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 82714087 1.22.840.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.137 MiB) 1.22.881.658 I slot launch_slot_: id 0 | task 4524 | processing task, is_child = 0 1.24.456.273 I slot print_timing: id 0 | task 4524 | prompt eval time = 153.13 ms / 402 tokens ( 0.38 ms per token, 2625.22 tokens per second) 1.24.456.279 I slot print_timing: id 0 | task 4524 | eval time = 1421.46 ms / 89 tokens ( 16.15 ms per token, 61.91 tokens per second) 1.24.456.280 I slot print_timing: id 0 | task 4524 | total time = 1574.59 ms / 491 tokens 1.24.456.281 I slot print_timing: id 0 | task 4524 | graphs reused = 4311 1.24.456.281 I slot print_timing: id 0 | task 4524 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.456.312 I slot release: id 0 | task 4524 | stop processing: n_tokens = 502, truncated = 0 1.24.461.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 502, t_last = 84362555 1.24.461.678 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 1.24.464.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 1.24.506.572 I slot launch_slot_: id 0 | task 4616 | processing task, is_child = 0 1.25.961.063 I slot print_timing: id 0 | task 4616 | prompt eval time = 194.49 ms / 549 tokens ( 0.35 ms per token, 2822.78 tokens per second) 1.25.961.069 I slot print_timing: id 0 | task 4616 | eval time = 1259.98 ms / 83 tokens ( 15.37 ms per token, 65.08 tokens per second) 1.25.961.070 I slot print_timing: id 0 | task 4616 | total time = 1454.47 ms / 632 tokens 1.25.961.072 I slot print_timing: id 0 | task 4616 | graphs reused = 4392 1.25.961.073 I slot print_timing: id 0 | task 4616 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.961.107 I slot release: id 0 | task 4616 | stop processing: n_tokens = 643, truncated = 0 1.25.966.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 85867350 1.25.966.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 1.26.013.464 I slot launch_slot_: id 0 | task 4703 | processing task, is_child = 0 1.27.085.117 I slot print_timing: id 0 | task 4703 | prompt eval time = 200.03 ms / 616 tokens ( 0.32 ms per token, 3079.49 tokens per second) 1.27.085.124 I slot print_timing: id 0 | task 4703 | eval time = 871.60 ms / 58 tokens ( 15.29 ms per token, 65.40 tokens per second) 1.27.085.125 I slot print_timing: id 0 | task 4703 | total time = 1071.63 ms / 674 tokens 1.27.085.126 I slot print_timing: id 0 | task 4703 | graphs reused = 4448 1.27.085.127 I slot print_timing: id 0 | task 4703 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.085.165 I slot release: id 0 | task 4703 | stop processing: n_tokens = 685, truncated = 0 1.27.104.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 86991408 1.27.104.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.324 MiB) 1.27.107.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.356 MiB) 1.27.159.202 I slot launch_slot_: id 0 | task 4765 | processing task, is_child = 0 1.28.616.427 I slot print_timing: id 0 | task 4765 | prompt eval time = 208.54 ms / 665 tokens ( 0.31 ms per token, 3188.78 tokens per second) 1.28.616.433 I slot print_timing: id 0 | task 4765 | eval time = 1248.66 ms / 83 tokens ( 15.23 ms per token, 65.67 tokens per second) 1.28.616.434 I slot print_timing: id 0 | task 4765 | total time = 1457.21 ms / 748 tokens 1.28.616.435 I slot print_timing: id 0 | task 4765 | graphs reused = 4529 1.28.616.436 I slot print_timing: id 0 | task 4765 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.616.476 I slot release: id 0 | task 4765 | stop processing: n_tokens = 759, truncated = 0 1.28.635.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 88522719 1.28.635.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.324 MiB) 1.28.638.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.295 MiB) 1.28.688.491 I slot launch_slot_: id 0 | task 4852 | processing task, is_child = 0 1.29.918.659 I slot print_timing: id 0 | task 4852 | prompt eval time = 208.86 ms / 645 tokens ( 0.32 ms per token, 3088.19 tokens per second) 1.29.918.665 I slot print_timing: id 0 | task 4852 | eval time = 1021.29 ms / 68 tokens ( 15.24 ms per token, 65.60 tokens per second) 1.29.918.666 I slot print_timing: id 0 | task 4852 | total time = 1230.15 ms / 713 tokens 1.29.918.667 I slot print_timing: id 0 | task 4852 | graphs reused = 4595 1.29.918.668 I slot print_timing: id 0 | task 4852 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.918.703 I slot release: id 0 | task 4852 | stop processing: n_tokens = 724, truncated = 0 1.29.923.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 89824946 1.29.923.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 1.29.971.237 I slot launch_slot_: id 0 | task 4924 | processing task, is_child = 0 1.31.267.168 I slot print_timing: id 0 | task 4924 | prompt eval time = 164.93 ms / 474 tokens ( 0.35 ms per token, 2873.96 tokens per second) 1.31.267.173 I slot print_timing: id 0 | task 4924 | eval time = 1130.98 ms / 75 tokens ( 15.28 ms per token, 65.43 tokens per second) 1.31.267.174 I slot print_timing: id 0 | task 4924 | total time = 1295.91 ms / 549 tokens 1.31.267.175 I slot print_timing: id 0 | task 4924 | graphs reused = 4667 1.31.267.176 I slot print_timing: id 0 | task 4924 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.267.206 I slot release: id 0 | task 4924 | stop processing: n_tokens = 560, truncated = 0 1.31.287.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 91173450 1.31.287.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.951 MiB) 1.31.290.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.795 MiB) 1.31.331.396 I slot launch_slot_: id 0 | task 5002 | processing task, is_child = 0 1.32.152.462 I slot print_timing: id 0 | task 5002 | prompt eval time = 194.99 ms / 617 tokens ( 0.32 ms per token, 3164.20 tokens per second) 1.32.152.468 I slot print_timing: id 0 | task 5002 | eval time = 626.05 ms / 42 tokens ( 15.27 ms per token, 65.49 tokens per second) 1.32.152.469 I slot print_timing: id 0 | task 5002 | total time = 821.05 ms / 659 tokens 1.32.152.469 I slot print_timing: id 0 | task 5002 | graphs reused = 4707 1.32.152.470 I slot print_timing: id 0 | task 5002 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.152.504 I slot release: id 0 | task 5002 | stop processing: n_tokens = 670, truncated = 0 1.32.193.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 92058747 1.32.193.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.32.239.955 I slot launch_slot_: id 0 | task 5048 | processing task, is_child = 0 1.33.532.903 I slot print_timing: id 0 | task 5048 | prompt eval time = 193.55 ms / 601 tokens ( 0.32 ms per token, 3105.09 tokens per second) 1.33.532.909 I slot print_timing: id 0 | task 5048 | eval time = 1099.37 ms / 73 tokens ( 15.27 ms per token, 65.49 tokens per second) 1.33.532.910 I slot print_timing: id 0 | task 5048 | total time = 1292.93 ms / 674 tokens 1.33.532.911 I slot print_timing: id 0 | task 5048 | graphs reused = 4778 1.33.532.912 I slot print_timing: id 0 | task 5048 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.532.947 I slot release: id 0 | task 5048 | stop processing: n_tokens = 685, truncated = 0 1.33.538.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 93439190 1.33.538.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.855 MiB) 1.33.541.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.106 MiB) 1.33.592.466 I slot launch_slot_: id 0 | task 5125 | processing task, is_child = 0 1.34.694.213 I slot print_timing: id 0 | task 5125 | prompt eval time = 186.66 ms / 533 tokens ( 0.35 ms per token, 2855.44 tokens per second) 1.34.694.219 I slot print_timing: id 0 | task 5125 | eval time = 915.06 ms / 61 tokens ( 15.25 ms per token, 65.57 tokens per second) 1.34.694.220 I slot print_timing: id 0 | task 5125 | total time = 1101.72 ms / 594 tokens 1.34.694.221 I slot print_timing: id 0 | task 5125 | graphs reused = 4837 1.34.694.222 I slot print_timing: id 0 | task 5125 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.694.261 I slot release: id 0 | task 5125 | stop processing: n_tokens = 605, truncated = 0 1.34.732.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 94600504 1.34.732.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.513 MiB) 1.34.735.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.34.784.539 I slot launch_slot_: id 0 | task 5190 | processing task, is_child = 0 1.36.025.887 I slot print_timing: id 0 | task 5190 | prompt eval time = 170.48 ms / 480 tokens ( 0.36 ms per token, 2815.65 tokens per second) 1.36.025.893 I slot print_timing: id 0 | task 5190 | eval time = 1070.85 ms / 71 tokens ( 15.30 ms per token, 65.37 tokens per second) 1.36.025.894 I slot print_timing: id 0 | task 5190 | total time = 1241.33 ms / 551 tokens 1.36.025.894 I slot print_timing: id 0 | task 5190 | graphs reused = 4905 1.36.025.895 I slot print_timing: id 0 | task 5190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.025.927 I slot release: id 0 | task 5190 | stop processing: n_tokens = 579, truncated = 0 1.36.057.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 95932170 1.36.057.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.324 MiB) 1.36.103.216 I slot launch_slot_: id 0 | task 5264 | processing task, is_child = 0 1.37.144.664 I slot print_timing: id 0 | task 5264 | prompt eval time = 187.35 ms / 567 tokens ( 0.33 ms per token, 3026.49 tokens per second) 1.37.144.670 I slot print_timing: id 0 | task 5264 | eval time = 854.08 ms / 57 tokens ( 15.25 ms per token, 65.57 tokens per second) 1.37.144.671 I slot print_timing: id 0 | task 5264 | total time = 1041.43 ms / 624 tokens 1.37.144.671 I slot print_timing: id 0 | task 5264 | graphs reused = 4960 1.37.144.672 I slot print_timing: id 0 | task 5264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.144.704 I slot release: id 0 | task 5264 | stop processing: n_tokens = 652, truncated = 0 1.37.165.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 652, t_last = 97050947 1.37.165.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.199 MiB) 1.37.168.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.388 MiB) 1.37.227.122 I slot launch_slot_: id 0 | task 5325 | processing task, is_child = 0 1.39.923.556 I slot print_timing: id 0 | task 5325 | prompt eval time = 173.50 ms / 506 tokens ( 0.34 ms per token, 2916.43 tokens per second) 1.39.923.562 I slot print_timing: id 0 | task 5325 | eval time = 2522.91 ms / 167 tokens ( 15.20 ms per token, 65.80 tokens per second) 1.39.923.563 I slot print_timing: id 0 | task 5325 | total time = 2696.41 ms / 673 tokens 1.39.923.564 I slot print_timing: id 0 | task 5325 | graphs reused = 5125 1.39.923.565 I slot print_timing: id 0 | task 5325 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.923.596 I slot release: id 0 | task 5325 | stop processing: n_tokens = 701, truncated = 0 1.39.956.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 701, t_last = 99829839 1.39.956.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.201 MiB) 1.39.959.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.40.009.605 I slot launch_slot_: id 0 | task 5495 | processing task, is_child = 0 1.41.014.060 I slot print_timing: id 0 | task 5495 | prompt eval time = 161.21 ms / 436 tokens ( 0.37 ms per token, 2704.55 tokens per second) 1.41.014.067 I slot print_timing: id 0 | task 5495 | eval time = 843.22 ms / 55 tokens ( 15.62 ms per token, 64.04 tokens per second) 1.41.014.068 I slot print_timing: id 0 | task 5495 | total time = 1004.43 ms / 491 tokens 1.41.014.068 I slot print_timing: id 0 | task 5495 | graphs reused = 5177 1.41.014.071 I slot print_timing: id 0 | task 5495 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.014.105 I slot release: id 0 | task 5495 | stop processing: n_tokens = 519, truncated = 0 1.41.033.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 100920348 1.41.033.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.610 MiB) 1.41.079.352 I slot launch_slot_: id 0 | task 5553 | processing task, is_child = 0 1.42.234.511 I slot print_timing: id 0 | task 5553 | prompt eval time = 187.22 ms / 519 tokens ( 0.36 ms per token, 2772.12 tokens per second) 1.42.234.516 I slot print_timing: id 0 | task 5553 | eval time = 967.92 ms / 62 tokens ( 15.87 ms per token, 63.02 tokens per second) 1.42.234.518 I slot print_timing: id 0 | task 5553 | total time = 1155.14 ms / 581 tokens 1.42.234.518 I slot print_timing: id 0 | task 5553 | graphs reused = 5237 1.42.234.519 I slot print_timing: id 0 | task 5553 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.234.552 I slot release: id 0 | task 5553 | stop processing: n_tokens = 609, truncated = 0 1.42.239.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 102140796 1.42.239.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.260 MiB) 1.42.242.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.137 MiB) 1.42.301.749 I slot launch_slot_: id 0 | task 5619 | processing task, is_child = 0 1.43.189.452 I slot print_timing: id 0 | task 5619 | prompt eval time = 167.45 ms / 465 tokens ( 0.36 ms per token, 2776.96 tokens per second) 1.43.189.458 I slot print_timing: id 0 | task 5619 | eval time = 720.23 ms / 46 tokens ( 16.01 ms per token, 62.48 tokens per second) 1.43.189.459 I slot print_timing: id 0 | task 5619 | total time = 887.68 ms / 511 tokens 1.43.189.460 I slot print_timing: id 0 | task 5619 | graphs reused = 5280 1.43.189.461 I slot print_timing: id 0 | task 5619 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.189.493 I slot release: id 0 | task 5619 | stop processing: n_tokens = 542, truncated = 0 1.43.219.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 103095736 1.43.219.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.43.222.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 1.43.280.469 I slot launch_slot_: id 0 | task 5668 | processing task, is_child = 0 1.44.360.399 I slot print_timing: id 0 | task 5668 | prompt eval time = 166.33 ms / 431 tokens ( 0.39 ms per token, 2591.28 tokens per second) 1.44.360.405 I slot print_timing: id 0 | task 5668 | eval time = 913.58 ms / 60 tokens ( 15.48 ms per token, 64.58 tokens per second) 1.44.360.406 I slot print_timing: id 0 | task 5668 | total time = 1079.91 ms / 491 tokens 1.44.360.407 I slot print_timing: id 0 | task 5668 | graphs reused = 5337 1.44.360.407 I slot print_timing: id 0 | task 5668 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.360.438 I slot release: id 0 | task 5668 | stop processing: n_tokens = 522, truncated = 0 1.44.365.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 522, t_last = 104266681 1.44.365.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.44.368.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.44.427.747 I slot launch_slot_: id 0 | task 5731 | processing task, is_child = 0 1.45.561.893 I slot print_timing: id 0 | task 5731 | prompt eval time = 164.32 ms / 457 tokens ( 0.36 ms per token, 2781.09 tokens per second) 1.45.561.899 I slot print_timing: id 0 | task 5731 | eval time = 969.80 ms / 63 tokens ( 15.64 ms per token, 63.93 tokens per second) 1.45.561.900 I slot print_timing: id 0 | task 5731 | total time = 1134.12 ms / 520 tokens 1.45.561.903 I slot print_timing: id 0 | task 5731 | graphs reused = 5397 1.45.561.903 I slot print_timing: id 0 | task 5731 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.561.936 I slot release: id 0 | task 5731 | stop processing: n_tokens = 551, truncated = 0 1.45.585.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 105468179 1.45.585.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.637 MiB) 1.45.588.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.044 MiB) 1.45.645.620 I slot launch_slot_: id 0 | task 5797 | processing task, is_child = 0 1.46.463.251 I slot print_timing: id 0 | task 5797 | prompt eval time = 167.73 ms / 439 tokens ( 0.38 ms per token, 2617.24 tokens per second) 1.46.463.256 I slot print_timing: id 0 | task 5797 | eval time = 649.88 ms / 42 tokens ( 15.85 ms per token, 63.09 tokens per second) 1.46.463.258 I slot print_timing: id 0 | task 5797 | total time = 817.61 ms / 481 tokens 1.46.463.259 I slot print_timing: id 0 | task 5797 | graphs reused = 5437 1.46.463.259 I slot print_timing: id 0 | task 5797 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.463.291 I slot release: id 0 | task 5797 | stop processing: n_tokens = 512, truncated = 0 1.46.488.048 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 106369534 1.46.488.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.952 MiB) 1.46.539.303 I slot launch_slot_: id 0 | task 5842 | processing task, is_child = 0 1.47.826.938 I slot print_timing: id 0 | task 5842 | prompt eval time = 199.97 ms / 606 tokens ( 0.33 ms per token, 3030.38 tokens per second) 1.47.826.945 I slot print_timing: id 0 | task 5842 | eval time = 1087.64 ms / 70 tokens ( 15.76 ms per token, 63.44 tokens per second) 1.47.826.946 I slot print_timing: id 0 | task 5842 | total time = 1287.62 ms / 676 tokens 1.47.826.947 I slot print_timing: id 0 | task 5842 | graphs reused = 5505 1.47.826.952 I slot print_timing: id 0 | task 5842 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.826.988 I slot release: id 0 | task 5842 | stop processing: n_tokens = 707, truncated = 0 1.47.856.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 107733231 1.47.856.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.47.860.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.47.925.003 I slot launch_slot_: id 0 | task 5916 | processing task, is_child = 0 1.48.889.047 I slot print_timing: id 0 | task 5916 | prompt eval time = 165.69 ms / 477 tokens ( 0.35 ms per token, 2878.85 tokens per second) 1.48.889.053 I slot print_timing: id 0 | task 5916 | eval time = 798.33 ms / 53 tokens ( 15.35 ms per token, 65.14 tokens per second) 1.48.889.054 I slot print_timing: id 0 | task 5916 | total time = 964.02 ms / 530 tokens 1.48.889.055 I slot print_timing: id 0 | task 5916 | graphs reused = 5555 1.48.889.056 I slot print_timing: id 0 | task 5916 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.889.089 I slot release: id 0 | task 5916 | stop processing: n_tokens = 561, truncated = 0 1.48.905.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 108795332 1.48.905.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.544 MiB) 1.48.958.106 I slot launch_slot_: id 0 | task 5972 | processing task, is_child = 0 1.50.303.261 I slot print_timing: id 0 | task 5972 | prompt eval time = 237.36 ms / 845 tokens ( 0.28 ms per token, 3559.98 tokens per second) 1.50.303.266 I slot print_timing: id 0 | task 5972 | eval time = 1107.77 ms / 71 tokens ( 15.83 ms per token, 63.19 tokens per second) 1.50.303.267 I slot print_timing: id 0 | task 5972 | total time = 1345.13 ms / 916 tokens 1.50.303.269 I slot print_timing: id 0 | task 5972 | graphs reused = 5624 1.50.303.269 I slot print_timing: id 0 | task 5972 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.303.316 I slot release: id 0 | task 5972 | stop processing: n_tokens = 947, truncated = 0 1.50.308.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 947, t_last = 110209559 1.50.308.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.043 MiB) 1.50.312.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.50.381.144 I slot launch_slot_: id 0 | task 6047 | processing task, is_child = 0 1.51.554.385 I slot print_timing: id 0 | task 6047 | prompt eval time = 172.69 ms / 459 tokens ( 0.38 ms per token, 2657.94 tokens per second) 1.51.554.391 I slot print_timing: id 0 | task 6047 | eval time = 1000.53 ms / 64 tokens ( 15.88 ms per token, 62.97 tokens per second) 1.51.554.392 I slot print_timing: id 0 | task 6047 | total time = 1173.22 ms / 523 tokens 1.51.554.393 I slot print_timing: id 0 | task 6047 | graphs reused = 5685 1.51.554.394 I slot print_timing: id 0 | task 6047 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.554.427 I slot release: id 0 | task 6047 | stop processing: n_tokens = 554, truncated = 0 1.51.560.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 554, t_last = 111460671 1.51.560.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.51.614.476 I slot launch_slot_: id 0 | task 6114 | processing task, is_child = 0 1.52.664.018 I slot print_timing: id 0 | task 6114 | prompt eval time = 210.45 ms / 670 tokens ( 0.31 ms per token, 3183.64 tokens per second) 1.52.664.024 I slot print_timing: id 0 | task 6114 | eval time = 839.07 ms / 56 tokens ( 15.26 ms per token, 65.55 tokens per second) 1.52.664.025 I slot print_timing: id 0 | task 6114 | total time = 1049.52 ms / 726 tokens 1.52.664.026 I slot print_timing: id 0 | task 6114 | graphs reused = 5739 1.52.664.027 I slot print_timing: id 0 | task 6114 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.664.068 I slot release: id 0 | task 6114 | stop processing: n_tokens = 757, truncated = 0 1.52.699.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 112570311 1.52.699.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.451 MiB) 1.52.703.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.52.771.181 I slot launch_slot_: id 0 | task 6174 | processing task, is_child = 0 1.54.287.266 I slot print_timing: id 0 | task 6174 | prompt eval time = 226.80 ms / 775 tokens ( 0.29 ms per token, 3417.11 tokens per second) 1.54.287.272 I slot print_timing: id 0 | task 6174 | eval time = 1289.26 ms / 83 tokens ( 15.72 ms per token, 63.60 tokens per second) 1.54.287.273 I slot print_timing: id 0 | task 6174 | total time = 1516.06 ms / 858 tokens 1.54.287.274 I slot print_timing: id 0 | task 6174 | graphs reused = 5820 1.54.287.274 I slot print_timing: id 0 | task 6174 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.287.319 I slot release: id 0 | task 6174 | stop processing: n_tokens = 889, truncated = 0 1.54.331.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 889, t_last = 114193563 1.54.331.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.700 MiB) 1.54.335.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.735 MiB) 1.54.403.622 I slot launch_slot_: id 0 | task 6261 | processing task, is_child = 0 1.55.883.776 I slot print_timing: id 0 | task 6261 | prompt eval time = 195.67 ms / 573 tokens ( 0.34 ms per token, 2928.38 tokens per second) 1.55.883.783 I slot print_timing: id 0 | task 6261 | eval time = 1284.46 ms / 82 tokens ( 15.86 ms per token, 63.06 tokens per second) 1.55.883.784 I slot print_timing: id 0 | task 6261 | total time = 1480.13 ms / 655 tokens 1.55.883.784 I slot print_timing: id 0 | task 6261 | graphs reused = 5900 1.55.883.785 I slot print_timing: id 0 | task 6261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.883.822 I slot release: id 0 | task 6261 | stop processing: n_tokens = 686, truncated = 0 1.55.888.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 686, t_last = 115790066 1.55.888.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.328 MiB) 1.55.893.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.387 MiB) 1.55.961.583 I slot launch_slot_: id 0 | task 6347 | processing task, is_child = 0 1.57.295.831 I slot print_timing: id 0 | task 6347 | prompt eval time = 167.38 ms / 461 tokens ( 0.36 ms per token, 2754.15 tokens per second) 1.57.295.837 I slot print_timing: id 0 | task 6347 | eval time = 1166.84 ms / 77 tokens ( 15.35 ms per token, 65.13 tokens per second) 1.57.295.839 I slot print_timing: id 0 | task 6347 | total time = 1334.23 ms / 538 tokens 1.57.295.840 I slot print_timing: id 0 | task 6347 | graphs reused = 5974 1.57.295.841 I slot print_timing: id 0 | task 6347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.295.877 I slot release: id 0 | task 6347 | stop processing: n_tokens = 569, truncated = 0 1.57.301.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 117202120 1.57.301.428 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.57.354.567 I slot launch_slot_: id 0 | task 6427 | processing task, is_child = 0 1.58.770.799 I slot print_timing: id 0 | task 6427 | prompt eval time = 198.07 ms / 609 tokens ( 0.33 ms per token, 3074.61 tokens per second) 1.58.770.805 I slot print_timing: id 0 | task 6427 | eval time = 1218.14 ms / 78 tokens ( 15.82 ms per token, 63.21 tokens per second) 1.58.770.806 I slot print_timing: id 0 | task 6427 | total time = 1416.21 ms / 687 tokens 1.58.770.807 I slot print_timing: id 0 | task 6427 | graphs reused = 6050 1.58.770.808 I slot print_timing: id 0 | task 6427 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.770.846 I slot release: id 0 | task 6427 | stop processing: n_tokens = 718, truncated = 0 1.58.791.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 718, t_last = 118677090 1.58.791.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.58.795.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.701 MiB) 1.58.863.429 I slot launch_slot_: id 0 | task 6509 | processing task, is_child = 0 2.00.331.903 I slot print_timing: id 0 | task 6509 | prompt eval time = 236.57 ms / 791 tokens ( 0.30 ms per token, 3343.68 tokens per second) 2.00.331.909 I slot print_timing: id 0 | task 6509 | eval time = 1231.89 ms / 80 tokens ( 15.59 ms per token, 64.13 tokens per second) 2.00.331.910 I slot print_timing: id 0 | task 6509 | total time = 1468.45 ms / 871 tokens 2.00.331.911 I slot print_timing: id 0 | task 6509 | graphs reused = 6128 2.00.331.912 I slot print_timing: id 0 | task 6509 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.331.954 I slot release: id 0 | task 6509 | stop processing: n_tokens = 902, truncated = 0 2.00.360.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 902, t_last = 120238198 2.00.360.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.362 MiB) 2.00.439.249 I slot launch_slot_: id 0 | task 6593 | processing task, is_child = 0 2.01.751.731 I slot print_timing: id 0 | task 6593 | prompt eval time = 184.44 ms / 533 tokens ( 0.35 ms per token, 2889.83 tokens per second) 2.01.751.738 I slot print_timing: id 0 | task 6593 | eval time = 1128.02 ms / 74 tokens ( 15.45 ms per token, 64.72 tokens per second) 2.01.751.740 I slot print_timing: id 0 | task 6593 | total time = 1312.46 ms / 607 tokens 2.01.751.741 I slot print_timing: id 0 | task 6593 | graphs reused = 6200 2.01.751.742 I slot print_timing: id 0 | task 6593 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.751.784 I slot release: id 0 | task 6593 | stop processing: n_tokens = 695, truncated = 0 2.01.770.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 695, t_last = 121658027 2.01.770.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 2.01.832.814 I slot launch_slot_: id 0 | task 6671 | processing task, is_child = 0 2.03.125.553 I slot print_timing: id 0 | task 6671 | prompt eval time = 202.77 ms / 566 tokens ( 0.36 ms per token, 2791.33 tokens per second) 2.03.125.559 I slot print_timing: id 0 | task 6671 | eval time = 1089.95 ms / 68 tokens ( 16.27 ms per token, 61.47 tokens per second) 2.03.125.560 I slot print_timing: id 0 | task 6671 | total time = 1292.72 ms / 634 tokens 2.03.125.560 I slot print_timing: id 0 | task 6671 | graphs reused = 6266 2.03.125.561 I slot print_timing: id 0 | task 6671 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.125.597 I slot release: id 0 | task 6671 | stop processing: n_tokens = 665, truncated = 0 2.03.158.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 123031840 2.03.158.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.989 MiB) 2.03.218.201 I slot launch_slot_: id 0 | task 6743 | processing task, is_child = 0 2.04.187.755 I slot print_timing: id 0 | task 6743 | prompt eval time = 168.53 ms / 443 tokens ( 0.38 ms per token, 2628.63 tokens per second) 2.04.187.760 I slot print_timing: id 0 | task 6743 | eval time = 801.00 ms / 52 tokens ( 15.71 ms per token, 63.67 tokens per second) 2.04.187.761 I slot print_timing: id 0 | task 6743 | total time = 969.53 ms / 495 tokens 2.04.187.762 I slot print_timing: id 0 | task 6743 | graphs reused = 6315 2.04.187.763 I slot print_timing: id 0 | task 6743 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.187.794 I slot release: id 0 | task 6743 | stop processing: n_tokens = 526, truncated = 0 2.04.205.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 526, t_last = 124094037 2.04.205.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.895 MiB) 2.04.257.876 I slot launch_slot_: id 0 | task 6798 | processing task, is_child = 0 2.05.885.789 I slot print_timing: id 0 | task 6798 | prompt eval time = 165.43 ms / 487 tokens ( 0.34 ms per token, 2943.84 tokens per second) 2.05.885.794 I slot print_timing: id 0 | task 6798 | eval time = 1462.46 ms / 96 tokens ( 15.39 ms per token, 64.96 tokens per second) 2.05.885.795 I slot print_timing: id 0 | task 6798 | total time = 1627.89 ms / 583 tokens 2.05.885.797 I slot print_timing: id 0 | task 6798 | graphs reused = 6409 2.05.885.797 I slot print_timing: id 0 | task 6798 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.885.831 I slot release: id 0 | task 6798 | stop processing: n_tokens = 614, truncated = 0 2.05.922.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 614, t_last = 125792074 2.05.922.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.515 MiB) 2.05.926.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 2.05.980.345 I slot launch_slot_: id 0 | task 6897 | processing task, is_child = 0 2.07.218.315 I slot print_timing: id 0 | task 6897 | prompt eval time = 177.59 ms / 507 tokens ( 0.35 ms per token, 2854.92 tokens per second) 2.07.218.321 I slot print_timing: id 0 | task 6897 | eval time = 1060.36 ms / 68 tokens ( 15.83 ms per token, 63.19 tokens per second) 2.07.218.322 I slot print_timing: id 0 | task 6897 | total time = 1237.95 ms / 575 tokens 2.07.218.323 I slot print_timing: id 0 | task 6897 | graphs reused = 6475 2.07.218.324 I slot print_timing: id 0 | task 6897 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.218.360 I slot release: id 0 | task 6897 | stop processing: n_tokens = 606, truncated = 0 2.07.242.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 127124603 2.07.242.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 2.07.288.910 I slot launch_slot_: id 0 | task 6968 | processing task, is_child = 0 2.08.501.274 I slot print_timing: id 0 | task 6968 | prompt eval time = 202.01 ms / 633 tokens ( 0.32 ms per token, 3133.54 tokens per second) 2.08.501.279 I slot print_timing: id 0 | task 6968 | eval time = 1010.33 ms / 66 tokens ( 15.54 ms per token, 64.34 tokens per second) 2.08.501.280 I slot print_timing: id 0 | task 6968 | total time = 1212.34 ms / 699 tokens 2.08.501.281 I slot print_timing: id 0 | task 6968 | graphs reused = 6539 2.08.501.283 I slot print_timing: id 0 | task 6968 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.501.320 I slot release: id 0 | task 6968 | stop processing: n_tokens = 730, truncated = 0 2.08.543.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 128407564 2.08.543.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.173 MiB) 2.08.602.873 I slot launch_slot_: id 0 | task 7038 | processing task, is_child = 0 2.09.812.726 I slot print_timing: id 0 | task 7038 | prompt eval time = 189.75 ms / 571 tokens ( 0.33 ms per token, 3009.29 tokens per second) 2.09.812.732 I slot print_timing: id 0 | task 7038 | eval time = 1020.09 ms / 67 tokens ( 15.46 ms per token, 64.70 tokens per second) 2.09.812.733 I slot print_timing: id 0 | task 7038 | total time = 1209.83 ms / 638 tokens 2.09.812.734 I slot print_timing: id 0 | task 7038 | graphs reused = 6604 2.09.812.734 I slot print_timing: id 0 | task 7038 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.812.770 I slot release: id 0 | task 7038 | stop processing: n_tokens = 669, truncated = 0 2.09.818.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 669, t_last = 129719013 2.09.818.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.360 MiB) 2.09.882.723 I slot launch_slot_: id 0 | task 7109 | processing task, is_child = 0 2.11.151.254 I slot print_timing: id 0 | task 7109 | prompt eval time = 236.86 ms / 798 tokens ( 0.30 ms per token, 3369.05 tokens per second) 2.11.151.260 I slot print_timing: id 0 | task 7109 | eval time = 1031.65 ms / 66 tokens ( 15.87 ms per token, 63.01 tokens per second) 2.11.151.261 I slot print_timing: id 0 | task 7109 | total time = 1268.51 ms / 864 tokens 2.11.151.263 I slot print_timing: id 0 | task 7109 | graphs reused = 6668 2.11.151.263 I slot print_timing: id 0 | task 7109 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.151.308 I slot release: id 0 | task 7109 | stop processing: n_tokens = 895, truncated = 0 2.11.172.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 131057551 2.11.172.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.894 MiB) 2.11.178.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.175 MiB) 2.11.247.949 I slot launch_slot_: id 0 | task 7179 | processing task, is_child = 0 2.12.416.382 I slot print_timing: id 0 | task 7179 | prompt eval time = 197.66 ms / 572 tokens ( 0.35 ms per token, 2893.93 tokens per second) 2.12.416.388 I slot print_timing: id 0 | task 7179 | eval time = 970.76 ms / 63 tokens ( 15.66 ms per token, 63.87 tokens per second) 2.12.416.389 I slot print_timing: id 0 | task 7179 | total time = 1168.41 ms / 635 tokens 2.12.416.390 I slot print_timing: id 0 | task 7179 | graphs reused = 6729 2.12.416.391 I slot print_timing: id 0 | task 7179 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.416.426 I slot release: id 0 | task 7179 | stop processing: n_tokens = 666, truncated = 0 2.12.421.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 666, t_last = 132322669 2.12.421.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.484 MiB) 2.12.480.808 I slot launch_slot_: id 0 | task 7246 | processing task, is_child = 0 2.13.988.028 I slot print_timing: id 0 | task 7246 | prompt eval time = 195.93 ms / 613 tokens ( 0.32 ms per token, 3128.68 tokens per second) 2.13.988.033 I slot print_timing: id 0 | task 7246 | eval time = 1311.27 ms / 86 tokens ( 15.43 ms per token, 64.82 tokens per second) 2.13.988.034 I slot print_timing: id 0 | task 7246 | total time = 1507.20 ms / 699 tokens 2.13.988.035 I slot print_timing: id 0 | task 7246 | graphs reused = 6813 2.13.988.036 I slot print_timing: id 0 | task 7246 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.988.073 I slot release: id 0 | task 7246 | stop processing: n_tokens = 730, truncated = 0 2.14.019.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 133894316 2.14.019.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 2.14.085.843 I slot launch_slot_: id 0 | task 7336 | processing task, is_child = 0 2.15.552.735 I slot print_timing: id 0 | task 7336 | prompt eval time = 200.09 ms / 580 tokens ( 0.34 ms per token, 2898.71 tokens per second) 2.15.552.741 I slot print_timing: id 0 | task 7336 | eval time = 1266.78 ms / 81 tokens ( 15.83 ms per token, 63.15 tokens per second) 2.15.552.742 I slot print_timing: id 0 | task 7336 | total time = 1466.87 ms / 661 tokens 2.15.552.744 I slot print_timing: id 0 | task 7336 | graphs reused = 6892 2.15.552.745 I slot print_timing: id 0 | task 7336 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.552.781 I slot release: id 0 | task 7336 | stop processing: n_tokens = 692, truncated = 0 2.15.558.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 135459024 2.15.558.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 2.15.626.493 I slot launch_slot_: id 0 | task 7421 | processing task, is_child = 0 2.16.915.385 I slot print_timing: id 0 | task 7421 | prompt eval time = 221.33 ms / 716 tokens ( 0.31 ms per token, 3234.93 tokens per second) 2.16.915.391 I slot print_timing: id 0 | task 7421 | eval time = 1067.54 ms / 70 tokens ( 15.47 ms per token, 64.63 tokens per second) 2.16.915.392 I slot print_timing: id 0 | task 7421 | total time = 1288.87 ms / 786 tokens 2.16.915.393 I slot print_timing: id 0 | task 7421 | graphs reused = 6959 2.16.915.394 I slot print_timing: id 0 | task 7421 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.915.433 I slot release: id 0 | task 7421 | stop processing: n_tokens = 817, truncated = 0 2.16.950.900 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 817, t_last = 136821677 2.16.950.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.828 MiB) 2.16.956.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.735 MiB) 2.17.026.331 I slot launch_slot_: id 0 | task 7495 | processing task, is_child = 0 2.19.025.555 I slot print_timing: id 0 | task 7495 | prompt eval time = 228.08 ms / 799 tokens ( 0.29 ms per token, 3503.11 tokens per second) 2.19.025.561 I slot print_timing: id 0 | task 7495 | eval time = 1771.12 ms / 114 tokens ( 15.67 ms per token, 63.80 tokens per second) 2.19.025.562 I slot print_timing: id 0 | task 7495 | total time = 1999.20 ms / 913 tokens 2.19.025.562 I slot print_timing: id 0 | task 7495 | graphs reused = 7071 2.19.025.563 I slot print_timing: id 0 | task 7495 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.025.605 I slot release: id 0 | task 7495 | stop processing: n_tokens = 944, truncated = 0 2.19.030.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 944, t_last = 138931848 2.19.030.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 2.19.090.258 I slot launch_slot_: id 0 | task 7613 | processing task, is_child = 0 2.21.221.692 I slot print_timing: id 0 | task 7613 | prompt eval time = 146.37 ms / 361 tokens ( 0.41 ms per token, 2466.35 tokens per second) 2.21.221.698 I slot print_timing: id 0 | task 7613 | eval time = 1985.05 ms / 129 tokens ( 15.51 ms per token, 64.48 tokens per second) 2.21.221.699 I slot print_timing: id 0 | task 7613 | total time = 2131.41 ms / 490 tokens 2.21.221.700 I slot print_timing: id 0 | task 7613 | graphs reused = 7197 2.21.221.701 I slot print_timing: id 0 | task 7613 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.221.730 I slot release: id 0 | task 7613 | stop processing: n_tokens = 521, truncated = 0 2.21.249.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 141127973 2.21.249.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.864 MiB) 2.21.299.437 I slot launch_slot_: id 0 | task 7745 | processing task, is_child = 0 2.23.330.490 I slot print_timing: id 0 | task 7745 | prompt eval time = 142.55 ms / 381 tokens ( 0.37 ms per token, 2672.71 tokens per second) 2.23.330.496 I slot print_timing: id 0 | task 7745 | eval time = 1888.48 ms / 121 tokens ( 15.74 ms per token, 63.54 tokens per second) 2.23.330.497 I slot print_timing: id 0 | task 7745 | total time = 2031.03 ms / 502 tokens 2.23.330.498 I slot print_timing: id 0 | task 7745 | graphs reused = 7315 2.23.330.498 I slot print_timing: id 0 | task 7745 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.330.527 I slot release: id 0 | task 7745 | stop processing: n_tokens = 533, truncated = 0 2.23.369.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 143236770 2.23.369.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 2.23.426.189 I slot launch_slot_: id 0 | task 7869 | processing task, is_child = 0 2.25.645.974 I slot print_timing: id 0 | task 7869 | prompt eval time = 145.76 ms / 365 tokens ( 0.40 ms per token, 2504.17 tokens per second) 2.25.645.980 I slot print_timing: id 0 | task 7869 | eval time = 2074.01 ms / 135 tokens ( 15.48 ms per token, 64.61 tokens per second) 2.25.645.981 I slot print_timing: id 0 | task 7869 | total time = 2219.76 ms / 500 tokens 2.25.645.982 I slot print_timing: id 0 | task 7869 | graphs reused = 7447 2.25.645.982 I slot print_timing: id 0 | task 7869 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.646.013 I slot release: id 0 | task 7869 | stop processing: n_tokens = 531, truncated = 0 2.25.660.266 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 145552256 2.25.660.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.370 MiB) 2.25.721.985 I slot launch_slot_: id 0 | task 8007 | processing task, is_child = 0 2.27.992.428 I slot print_timing: id 0 | task 8007 | prompt eval time = 143.44 ms / 333 tokens ( 0.43 ms per token, 2321.50 tokens per second) 2.27.992.434 I slot print_timing: id 0 | task 8007 | eval time = 2126.98 ms / 136 tokens ( 15.76 ms per token, 63.47 tokens per second) 2.27.992.435 I slot print_timing: id 0 | task 8007 | total time = 2270.42 ms / 469 tokens 2.27.992.436 I slot print_timing: id 0 | task 8007 | graphs reused = 7581 2.27.992.437 I slot print_timing: id 0 | task 8007 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.992.465 I slot release: id 0 | task 8007 | stop processing: n_tokens = 500, truncated = 0 2.28.033.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 147898708 2.28.073.047 I slot launch_slot_: id 0 | task 8146 | processing task, is_child = 0 2.30.751.128 I slot print_timing: id 0 | task 8146 | prompt eval time = 153.10 ms / 403 tokens ( 0.38 ms per token, 2632.32 tokens per second) 2.30.751.134 I slot print_timing: id 0 | task 8146 | eval time = 2524.96 ms / 164 tokens ( 15.49 ms per token, 64.56 tokens per second) 2.30.751.135 I slot print_timing: id 0 | task 8146 | total time = 2678.06 ms / 567 tokens 2.30.751.136 I slot print_timing: id 0 | task 8146 | graphs reused = 7742 2.30.751.137 I slot print_timing: id 0 | task 8146 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.751.169 I slot release: id 0 | task 8146 | stop processing: n_tokens = 598, truncated = 0 2.30.756.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 150657412 2.30.756.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.829 MiB) 2.30.812.296 I slot launch_slot_: id 0 | task 8313 | processing task, is_child = 0 2.33.975.481 I slot print_timing: id 0 | task 8313 | n_gen = 195, tg = 64.39 t/s, tg_3s = 64.72 t/s 2.33.990.758 I slot print_timing: id 0 | task 8313 | prompt eval time = 150.37 ms / 411 tokens ( 0.37 ms per token, 2733.19 tokens per second) 2.33.990.762 I slot print_timing: id 0 | task 8313 | eval time = 3028.07 ms / 196 tokens ( 15.53 ms per token, 64.40 tokens per second) 2.33.990.763 I slot print_timing: id 0 | task 8313 | total time = 3178.44 ms / 607 tokens 2.33.990.764 I slot print_timing: id 0 | task 8313 | graphs reused = 7935 2.33.990.765 I slot print_timing: id 0 | task 8313 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.990.795 I slot release: id 0 | task 8313 | stop processing: n_tokens = 638, truncated = 0 2.34.011.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 638, t_last = 153897038 2.34.011.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.428 MiB) 2.34.073.878 I slot launch_slot_: id 0 | task 8512 | processing task, is_child = 0 2.37.262.117 I slot print_timing: id 0 | task 8512 | n_gen = 194, tg = 64.04 t/s, tg_3s = 64.37 t/s 2.37.884.497 I slot print_timing: id 0 | task 8512 | prompt eval time = 174.58 ms / 490 tokens ( 0.36 ms per token, 2806.74 tokens per second) 2.37.884.503 I slot print_timing: id 0 | task 8512 | eval time = 3636.02 ms / 235 tokens ( 15.54 ms per token, 64.36 tokens per second) 2.37.884.504 I slot print_timing: id 0 | task 8512 | total time = 3810.60 ms / 725 tokens 2.37.884.505 I slot print_timing: id 0 | task 8512 | graphs reused = 8168 2.37.884.505 I slot print_timing: id 0 | task 8512 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.884.537 I slot release: id 0 | task 8512 | stop processing: n_tokens = 756, truncated = 0 2.37.904.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 157790780 2.37.904.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.556 MiB) 2.37.965.482 I slot launch_slot_: id 0 | task 8750 | processing task, is_child = 0 2.41.005.872 I slot print_timing: id 0 | task 8750 | prompt eval time = 141.23 ms / 344 tokens ( 0.41 ms per token, 2435.69 tokens per second) 2.41.005.877 I slot print_timing: id 0 | task 8750 | eval time = 2899.14 ms / 186 tokens ( 15.67 ms per token, 63.81 tokens per second) 2.41.005.878 I slot print_timing: id 0 | task 8750 | total time = 3040.37 ms / 530 tokens 2.41.005.880 I slot print_timing: id 0 | task 8750 | graphs reused = 8351 2.41.005.881 I slot print_timing: id 0 | task 8750 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.005.909 I slot release: id 0 | task 8750 | stop processing: n_tokens = 561, truncated = 0 2.41.030.096 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 160912153 2.41.030.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.298 MiB) 2.41.085.961 I slot launch_slot_: id 0 | task 8939 | processing task, is_child = 0 2.44.132.187 I slot print_timing: id 0 | task 8939 | prompt eval time = 138.66 ms / 347 tokens ( 0.40 ms per token, 2502.56 tokens per second) 2.44.132.193 I slot print_timing: id 0 | task 8939 | eval time = 2907.55 ms / 187 tokens ( 15.63 ms per token, 63.97 tokens per second) 2.44.132.194 I slot print_timing: id 0 | task 8939 | total time = 3046.21 ms / 534 tokens 2.44.132.195 I slot print_timing: id 0 | task 8939 | graphs reused = 8535 2.44.132.196 I slot print_timing: id 0 | task 8939 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.132.224 I slot release: id 0 | task 8939 | stop processing: n_tokens = 565, truncated = 0 2.44.168.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 565, t_last = 164038468 2.44.168.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.208 MiB) 2.44.225.283 I slot launch_slot_: id 0 | task 9129 | processing task, is_child = 0 2.46.439.532 I slot print_timing: id 0 | task 9129 | prompt eval time = 150.79 ms / 401 tokens ( 0.38 ms per token, 2659.40 tokens per second) 2.46.439.538 I slot print_timing: id 0 | task 9129 | eval time = 2063.44 ms / 135 tokens ( 15.40 ms per token, 64.94 tokens per second) 2.46.439.539 I slot print_timing: id 0 | task 9129 | total time = 2214.23 ms / 536 tokens 2.46.439.540 I slot print_timing: id 0 | task 9129 | graphs reused = 8667 2.46.439.540 I slot print_timing: id 0 | task 9129 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.439.570 I slot release: id 0 | task 9129 | stop processing: n_tokens = 567, truncated = 0 2.46.444.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 166345814 2.46.444.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.962 MiB) 2.46.499.485 I slot launch_slot_: id 0 | task 9267 | processing task, is_child = 0 2.48.705.769 I slot print_timing: id 0 | task 9267 | prompt eval time = 159.17 ms / 456 tokens ( 0.35 ms per token, 2864.86 tokens per second) 2.48.705.774 I slot print_timing: id 0 | task 9267 | eval time = 2047.09 ms / 129 tokens ( 15.99 ms per token, 62.53 tokens per second) 2.48.705.775 I slot print_timing: id 0 | task 9267 | total time = 2206.26 ms / 585 tokens 2.48.705.776 I slot print_timing: id 0 | task 9267 | graphs reused = 8793 2.48.705.777 I slot print_timing: id 0 | task 9267 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.705.809 I slot release: id 0 | task 9267 | stop processing: n_tokens = 616, truncated = 0 2.48.730.040 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.076 2.48.730.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.739 MiB) 2.48.786.850 I slot launch_slot_: id 0 | task 9399 | processing task, is_child = 0 2.50.648.915 I slot print_timing: id 0 | task 9399 | prompt eval time = 152.48 ms / 406 tokens ( 0.38 ms per token, 2662.66 tokens per second) 2.50.648.921 I slot print_timing: id 0 | task 9399 | eval time = 1709.57 ms / 112 tokens ( 15.40 ms per token, 64.93 tokens per second) 2.50.648.922 I slot print_timing: id 0 | task 9399 | total time = 1862.05 ms / 518 tokens 2.50.648.923 I slot print_timing: id 0 | task 9399 | graphs reused = 8902 2.50.648.924 I slot print_timing: id 0 | task 9399 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.648.954 I slot release: id 0 | task 9399 | stop processing: n_tokens = 549, truncated = 0 2.50.654.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 170555197 2.50.694.988 I slot launch_slot_: id 0 | task 9514 | processing task, is_child = 0 2.53.860.216 I slot print_timing: id 0 | task 9514 | n_gen = 193, tg = 63.69 t/s, tg_3s = 64.02 t/s 2.53.967.231 I slot print_timing: id 0 | task 9514 | prompt eval time = 150.68 ms / 406 tokens ( 0.37 ms per token, 2694.45 tokens per second) 2.53.967.236 I slot print_timing: id 0 | task 9514 | eval time = 3121.54 ms / 200 tokens ( 15.69 ms per token, 63.75 tokens per second) 2.53.967.237 I slot print_timing: id 0 | task 9514 | total time = 3272.22 ms / 606 tokens 2.53.967.238 I slot print_timing: id 0 | task 9514 | graphs reused = 9099 2.53.967.238 I slot print_timing: id 0 | task 9514 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.967.271 I slot release: id 0 | task 9514 | stop processing: n_tokens = 637, truncated = 0 2.53.972.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 173873514 2.53.972.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.551 MiB) 2.54.034.022 I slot launch_slot_: id 0 | task 9717 | processing task, is_child = 0 2.56.625.531 I slot print_timing: id 0 | task 9717 | prompt eval time = 150.57 ms / 444 tokens ( 0.34 ms per token, 2948.72 tokens per second) 2.56.625.537 I slot print_timing: id 0 | task 9717 | eval time = 2440.92 ms / 155 tokens ( 15.85 ms per token, 63.09 tokens per second) 2.56.625.538 I slot print_timing: id 0 | task 9717 | total time = 2591.49 ms / 599 tokens 2.56.625.538 I slot print_timing: id 0 | task 9717 | graphs reused = 9251 2.56.625.539 I slot print_timing: id 0 | task 9717 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.625.570 I slot release: id 0 | task 9717 | stop processing: n_tokens = 630, truncated = 0 2.56.630.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 630, t_last = 176531814 2.56.630.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.953 MiB) 2.56.689.826 I slot launch_slot_: id 0 | task 9875 | processing task, is_child = 0 2.58.663.699 I slot print_timing: id 0 | task 9875 | prompt eval time = 146.87 ms / 372 tokens ( 0.39 ms per token, 2532.90 tokens per second) 2.58.663.705 I slot print_timing: id 0 | task 9875 | eval time = 1826.99 ms / 120 tokens ( 15.35 ms per token, 65.13 tokens per second) 2.58.663.706 I slot print_timing: id 0 | task 9875 | total time = 1973.85 ms / 492 tokens 2.58.663.706 I slot print_timing: id 0 | task 9875 | graphs reused = 9368 2.58.663.707 I slot print_timing: id 0 | task 9875 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.663.738 I slot release: id 0 | task 9875 | stop processing: n_tokens = 523, truncated = 0 2.58.699.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 178569981 2.58.699.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.705 MiB) 2.58.758.368 I slot launch_slot_: id 0 | task 9998 | processing task, is_child = 0 3.01.925.211 I slot print_timing: id 0 | task 9998 | n_gen = 194, tg = 64.09 t/s, tg_3s = 64.43 t/s 3.02.885.100 I slot print_timing: id 0 | task 9998 | prompt eval time = 155.63 ms / 454 tokens ( 0.34 ms per token, 2917.19 tokens per second) 3.02.885.105 I slot print_timing: id 0 | task 9998 | eval time = 3971.08 ms / 256 tokens ( 15.57 ms per token, 64.21 tokens per second) 3.02.885.106 I slot print_timing: id 0 | task 9998 | total time = 4126.71 ms / 710 tokens 3.02.885.107 I slot print_timing: id 0 | task 9998 | graphs reused = 9621 3.02.885.108 I slot print_timing: id 0 | task 9998 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.885.140 I slot release: id 0 | task 9998 | stop processing: n_tokens = 741, truncated = 0 3.02.889.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 182791383 3.02.889.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.455 MiB) 3.02.949.902 I slot launch_slot_: id 0 | task 10257 | processing task, is_child = 0 3.05.176.423 I slot print_timing: id 0 | task 10257 | prompt eval time = 145.51 ms / 354 tokens ( 0.41 ms per token, 2432.77 tokens per second) 3.05.176.429 I slot print_timing: id 0 | task 10257 | eval time = 2080.99 ms / 133 tokens ( 15.77 ms per token, 63.43 tokens per second) 3.05.176.430 I slot print_timing: id 0 | task 10257 | total time = 2226.50 ms / 487 tokens 3.05.176.431 I slot print_timing: id 0 | task 10257 | graphs reused = 9751 3.05.176.433 I slot print_timing: id 0 | task 10257 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.176.477 I slot release: id 0 | task 10257 | stop processing: n_tokens = 518, truncated = 0 3.05.181.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 185082720 3.05.181.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 3.05.240.660 I slot launch_slot_: id 0 | task 10393 | processing task, is_child = 0 3.07.822.242 I slot print_timing: id 0 | task 10393 | prompt eval time = 139.12 ms / 334 tokens ( 0.42 ms per token, 2400.79 tokens per second) 3.07.822.248 I slot print_timing: id 0 | task 10393 | eval time = 2442.44 ms / 158 tokens ( 15.56 ms per token, 64.28 tokens per second) 3.07.822.249 I slot print_timing: id 0 | task 10393 | total time = 2581.56 ms / 492 tokens 3.07.822.250 I slot print_timing: id 0 | task 10393 | graphs reused = 9906 3.07.822.251 I slot print_timing: id 0 | task 10393 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.822.281 I slot release: id 0 | task 10393 | stop processing: n_tokens = 523, truncated = 0 3.07.854.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 187728524 3.07.854.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.676 MiB) 3.07.914.576 I slot launch_slot_: id 0 | task 10554 | processing task, is_child = 0 3.11.031.042 I slot print_timing: id 0 | task 10554 | prompt eval time = 153.27 ms / 426 tokens ( 0.36 ms per token, 2779.41 tokens per second) 3.11.031.048 I slot print_timing: id 0 | task 10554 | eval time = 2963.18 ms / 192 tokens ( 15.51 ms per token, 64.46 tokens per second) 3.11.031.048 I slot print_timing: id 0 | task 10554 | total time = 3116.45 ms / 618 tokens 3.11.031.049 I slot print_timing: id 0 | task 10554 | graphs reused = 10095 3.11.031.050 I slot print_timing: id 0 | task 10554 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.031.083 I slot release: id 0 | task 10554 | stop processing: n_tokens = 649, truncated = 0 3.11.058.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 190937326 3.11.058.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.11.113.729 I slot launch_slot_: id 0 | task 10749 | processing task, is_child = 0 3.13.429.836 I slot print_timing: id 0 | task 10749 | prompt eval time = 145.34 ms / 366 tokens ( 0.40 ms per token, 2518.32 tokens per second) 3.13.429.842 I slot print_timing: id 0 | task 10749 | eval time = 2170.75 ms / 139 tokens ( 15.73 ms per token, 63.57 tokens per second) 3.13.429.843 I slot print_timing: id 0 | task 10749 | total time = 2316.09 ms / 505 tokens 3.13.429.844 I slot print_timing: id 0 | task 10749 | graphs reused = 10231 3.13.429.845 I slot print_timing: id 0 | task 10749 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.429.874 I slot release: id 0 | task 10749 | stop processing: n_tokens = 536, truncated = 0 3.13.459.301 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 536, t_last = 193336117 3.13.459.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.582 MiB) 3.13.511.287 I slot launch_slot_: id 0 | task 10891 | processing task, is_child = 0 3.16.676.814 I slot print_timing: id 0 | task 10891 | n_gen = 193, tg = 63.92 t/s, tg_3s = 64.25 t/s 3.18.141.274 I slot print_timing: id 0 | task 10891 | prompt eval time = 161.77 ms / 462 tokens ( 0.35 ms per token, 2855.91 tokens per second) 3.18.141.280 I slot print_timing: id 0 | task 10891 | eval time = 4468.20 ms / 288 tokens ( 15.57 ms per token, 64.23 tokens per second) 3.18.141.281 I slot print_timing: id 0 | task 10891 | total time = 4629.97 ms / 750 tokens 3.18.141.282 I slot print_timing: id 0 | task 10891 | graphs reused = 10515 3.18.141.283 I slot print_timing: id 0 | task 10891 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.141.314 I slot release: id 0 | task 10891 | stop processing: n_tokens = 781, truncated = 0 3.18.168.525 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 781, t_last = 198047557 3.18.168.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 3.18.219.346 I slot launch_slot_: id 0 | task 11182 | processing task, is_child = 0 3.20.784.381 I slot print_timing: id 0 | task 11182 | prompt eval time = 143.60 ms / 396 tokens ( 0.36 ms per token, 2757.74 tokens per second) 3.20.784.386 I slot print_timing: id 0 | task 11182 | eval time = 2421.42 ms / 155 tokens ( 15.72 ms per token, 63.60 tokens per second) 3.20.784.387 I slot print_timing: id 0 | task 11182 | total time = 2565.01 ms / 551 tokens 3.20.784.388 I slot print_timing: id 0 | task 11182 | graphs reused = 10667 3.20.784.389 I slot print_timing: id 0 | task 11182 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.784.419 I slot release: id 0 | task 11182 | stop processing: n_tokens = 582, truncated = 0 3.20.820.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 200690663 3.20.861.027 I slot launch_slot_: id 0 | task 11340 | processing task, is_child = 0 3.23.720.847 I slot print_timing: id 0 | task 11340 | prompt eval time = 160.50 ms / 458 tokens ( 0.35 ms per token, 2853.55 tokens per second) 3.23.720.853 I slot print_timing: id 0 | task 11340 | eval time = 2699.30 ms / 175 tokens ( 15.51 ms per token, 64.46 tokens per second) 3.23.720.854 I slot print_timing: id 0 | task 11340 | total time = 2859.80 ms / 633 tokens 3.23.720.855 I slot print_timing: id 0 | task 11340 | graphs reused = 10839 3.23.720.856 I slot print_timing: id 0 | task 11340 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.720.889 I slot release: id 0 | task 11340 | stop processing: n_tokens = 664, truncated = 0 3.23.725.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 664, t_last = 203627132 3.23.725.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.395 MiB) 3.23.788.917 I slot launch_slot_: id 0 | task 11518 | processing task, is_child = 0 3.26.957.371 I slot print_timing: id 0 | task 11518 | n_gen = 193, tg = 63.90 t/s, tg_3s = 64.24 t/s 3.26.988.887 I slot print_timing: id 0 | task 11518 | prompt eval time = 163.94 ms / 458 tokens ( 0.36 ms per token, 2793.67 tokens per second) 3.26.988.892 I slot print_timing: id 0 | task 11518 | eval time = 3036.01 ms / 195 tokens ( 15.65 ms per token, 63.90 tokens per second) 3.26.988.893 I slot print_timing: id 0 | task 11518 | total time = 3199.95 ms / 653 tokens 3.26.988.894 I slot print_timing: id 0 | task 11518 | graphs reused = 11031 3.26.988.895 I slot print_timing: id 0 | task 11518 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.988.927 I slot release: id 0 | task 11518 | stop processing: n_tokens = 684, truncated = 0 3.27.028.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 206895171 3.27.028.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.304 MiB) 3.27.090.276 I slot launch_slot_: id 0 | task 11716 | processing task, is_child = 0 3.30.248.630 I slot print_timing: id 0 | task 11716 | n_gen = 193, tg = 63.98 t/s, tg_3s = 64.31 t/s 3.30.871.674 I slot print_timing: id 0 | task 11716 | prompt eval time = 157.47 ms / 452 tokens ( 0.35 ms per token, 2870.37 tokens per second) 3.30.871.680 I slot print_timing: id 0 | task 11716 | eval time = 3623.91 ms / 234 tokens ( 15.55 ms per token, 64.30 tokens per second) 3.30.871.681 I slot print_timing: id 0 | task 11716 | total time = 3781.38 ms / 686 tokens 3.30.871.683 I slot print_timing: id 0 | task 11716 | graphs reused = 11262 3.30.871.684 I slot print_timing: id 0 | task 11716 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.871.717 I slot release: id 0 | task 11716 | stop processing: n_tokens = 717, truncated = 0 3.30.913.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 210777961 3.30.913.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.276 MiB) 3.30.972.637 I slot launch_slot_: id 0 | task 11953 | processing task, is_child = 0 3.33.123.517 I slot print_timing: id 0 | task 11953 | prompt eval time = 152.29 ms / 404 tokens ( 0.38 ms per token, 2652.89 tokens per second) 3.33.123.523 I slot print_timing: id 0 | task 11953 | eval time = 1998.57 ms / 127 tokens ( 15.86 ms per token, 63.04 tokens per second) 3.33.123.524 I slot print_timing: id 0 | task 11953 | total time = 2150.86 ms / 531 tokens 3.33.123.525 I slot print_timing: id 0 | task 11953 | graphs reused = 11386 3.33.123.525 I slot print_timing: id 0 | task 11953 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.123.555 I slot release: id 0 | task 11953 | stop processing: n_tokens = 562, truncated = 0 3.33.161.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 213029798 3.33.161.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.797 MiB) 3.33.217.319 I slot launch_slot_: id 0 | task 12083 | processing task, is_child = 0 3.35.247.294 I slot print_timing: id 0 | task 12083 | prompt eval time = 143.98 ms / 345 tokens ( 0.42 ms per token, 2396.10 tokens per second) 3.35.247.300 I slot print_timing: id 0 | task 12083 | eval time = 1885.97 ms / 124 tokens ( 15.33 ms per token, 65.22 tokens per second) 3.35.247.302 I slot print_timing: id 0 | task 12083 | total time = 2029.95 ms / 469 tokens 3.35.247.302 I slot print_timing: id 0 | task 12083 | graphs reused = 11508 3.35.247.303 I slot print_timing: id 0 | task 12083 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.247.333 I slot release: id 0 | task 12083 | stop processing: n_tokens = 500, truncated = 0 3.35.251.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 215153577 3.35.252.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 3.35.306.673 I slot launch_slot_: id 0 | task 12210 | processing task, is_child = 0 3.37.322.077 I slot print_timing: id 0 | task 12210 | prompt eval time = 162.75 ms / 430 tokens ( 0.38 ms per token, 2642.04 tokens per second) 3.37.322.082 I slot print_timing: id 0 | task 12210 | eval time = 1852.63 ms / 118 tokens ( 15.83 ms per token, 63.15 tokens per second) 3.37.322.083 I slot print_timing: id 0 | task 12210 | total time = 2015.38 ms / 548 tokens 3.37.322.084 I slot print_timing: id 0 | task 12210 | graphs reused = 11623 3.37.322.085 I slot print_timing: id 0 | task 12210 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.322.115 I slot release: id 0 | task 12210 | stop processing: n_tokens = 579, truncated = 0 3.37.358.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 217228359 3.37.358.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.110 MiB) 3.37.413.008 I slot launch_slot_: id 0 | task 12331 | processing task, is_child = 0 3.38.828.280 I slot print_timing: id 0 | task 12331 | prompt eval time = 137.09 ms / 316 tokens ( 0.43 ms per token, 2305.09 tokens per second) 3.38.828.286 I slot print_timing: id 0 | task 12331 | eval time = 1278.16 ms / 85 tokens ( 15.22 ms per token, 65.72 tokens per second) 3.38.828.286 I slot print_timing: id 0 | task 12331 | total time = 1415.25 ms / 401 tokens 3.38.828.287 I slot print_timing: id 0 | task 12331 | graphs reused = 11706 3.38.828.288 I slot print_timing: id 0 | task 12331 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.828.314 I slot release: id 0 | task 12331 | stop processing: n_tokens = 432, truncated = 0 3.38.870.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 218734558 3.38.870.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 3.38.919.479 I slot launch_slot_: id 0 | task 12419 | processing task, is_child = 0 3.41.043.536 I slot print_timing: id 0 | task 12419 | prompt eval time = 144.33 ms / 354 tokens ( 0.41 ms per token, 2452.71 tokens per second) 3.41.043.542 I slot print_timing: id 0 | task 12419 | eval time = 1979.71 ms / 126 tokens ( 15.84 ms per token, 63.14 tokens per second) 3.41.043.543 I slot print_timing: id 0 | task 12419 | total time = 2124.04 ms / 480 tokens 3.41.043.544 I slot print_timing: id 0 | task 12419 | graphs reused = 11830 3.41.043.545 I slot print_timing: id 0 | task 12419 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.043.574 I slot release: id 0 | task 12419 | stop processing: n_tokens = 511, truncated = 0 3.41.071.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 220949818 3.41.071.860 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.205 MiB) 3.41.127.985 I slot launch_slot_: id 0 | task 12548 | processing task, is_child = 0 3.43.037.898 I slot print_timing: id 0 | task 12548 | prompt eval time = 167.91 ms / 438 tokens ( 0.38 ms per token, 2608.56 tokens per second) 3.43.037.904 I slot print_timing: id 0 | task 12548 | eval time = 1741.98 ms / 114 tokens ( 15.42 ms per token, 64.87 tokens per second) 3.43.037.905 I slot print_timing: id 0 | task 12548 | total time = 1909.89 ms / 552 tokens 3.43.037.906 I slot print_timing: id 0 | task 12548 | graphs reused = 11941 3.43.037.907 I slot print_timing: id 0 | task 12548 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.037.938 I slot release: id 0 | task 12548 | stop processing: n_tokens = 583, truncated = 0 3.43.055.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 222944181 3.43.055.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.456 MiB) 3.43.116.841 I slot launch_slot_: id 0 | task 12665 | processing task, is_child = 0 3.44.853.199 I slot print_timing: id 0 | task 12665 | prompt eval time = 167.99 ms / 457 tokens ( 0.37 ms per token, 2720.45 tokens per second) 3.44.853.204 I slot print_timing: id 0 | task 12665 | eval time = 1568.35 ms / 100 tokens ( 15.84 ms per token, 63.12 tokens per second) 3.44.853.205 I slot print_timing: id 0 | task 12665 | total time = 1736.34 ms / 557 tokens 3.44.853.206 I slot print_timing: id 0 | task 12665 | graphs reused = 12038 3.44.853.207 I slot print_timing: id 0 | task 12665 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.853.239 I slot release: id 0 | task 12665 | stop processing: n_tokens = 588, truncated = 0 3.44.896.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 224759482 3.44.896.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 3.44.957.608 I slot launch_slot_: id 0 | task 12768 | processing task, is_child = 0 3.46.845.331 I slot print_timing: id 0 | task 12768 | prompt eval time = 171.76 ms / 473 tokens ( 0.36 ms per token, 2753.89 tokens per second) 3.46.845.336 I slot print_timing: id 0 | task 12768 | eval time = 1715.94 ms / 112 tokens ( 15.46 ms per token, 64.69 tokens per second) 3.46.845.337 I slot print_timing: id 0 | task 12768 | total time = 1887.70 ms / 585 tokens 3.46.845.338 I slot print_timing: id 0 | task 12768 | graphs reused = 12147 3.46.845.338 I slot print_timing: id 0 | task 12768 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.845.370 I slot release: id 0 | task 12768 | stop processing: n_tokens = 616, truncated = 0 3.46.865.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 226751613 3.46.865.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 3.46.920.072 I slot launch_slot_: id 0 | task 12883 | processing task, is_child = 0 3.47.945.260 I slot print_timing: id 0 | task 12883 | prompt eval time = 165.35 ms / 476 tokens ( 0.35 ms per token, 2878.69 tokens per second) 3.47.945.265 I slot print_timing: id 0 | task 12883 | eval time = 859.82 ms / 55 tokens ( 15.92 ms per token, 62.80 tokens per second) 3.47.945.266 I slot print_timing: id 0 | task 12883 | total time = 1025.17 ms / 531 tokens 3.47.945.267 I slot print_timing: id 0 | task 12883 | graphs reused = 12199 3.47.945.267 I slot print_timing: id 0 | task 12883 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.945.301 I slot release: id 0 | task 12883 | stop processing: n_tokens = 562, truncated = 0 3.47.974.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 227851544 3.47.974.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.173 MiB) 3.48.035.888 I slot launch_slot_: id 0 | task 12941 | processing task, is_child = 0 3.50.058.183 I slot print_timing: id 0 | task 12941 | prompt eval time = 172.55 ms / 466 tokens ( 0.37 ms per token, 2700.60 tokens per second) 3.50.058.189 I slot print_timing: id 0 | task 12941 | eval time = 1849.72 ms / 118 tokens ( 15.81 ms per token, 63.25 tokens per second) 3.50.058.190 I slot print_timing: id 0 | task 12941 | total time = 2022.28 ms / 584 tokens 3.50.058.191 I slot print_timing: id 0 | task 12941 | graphs reused = 12314 3.50.058.192 I slot print_timing: id 0 | task 12941 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.058.223 I slot release: id 0 | task 12941 | stop processing: n_tokens = 615, truncated = 0 3.50.077.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 229964466 3.50.077.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.50.138.303 I slot launch_slot_: id 0 | task 13062 | processing task, is_child = 0 3.51.779.703 I slot print_timing: id 0 | task 13062 | prompt eval time = 147.09 ms / 415 tokens ( 0.35 ms per token, 2821.38 tokens per second) 3.51.779.710 I slot print_timing: id 0 | task 13062 | eval time = 1494.28 ms / 97 tokens ( 15.57 ms per token, 64.24 tokens per second) 3.51.779.712 I slot print_timing: id 0 | task 13062 | total time = 1641.38 ms / 512 tokens 3.51.779.713 I slot print_timing: id 0 | task 13062 | graphs reused = 12408 3.51.779.715 I slot print_timing: id 0 | task 13062 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.779.760 I slot release: id 0 | task 13062 | stop processing: n_tokens = 543, truncated = 0 3.51.784.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 231686004 3.51.784.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 3.51.845.222 I slot launch_slot_: id 0 | task 13162 | processing task, is_child = 0 3.53.432.495 I slot print_timing: id 0 | task 13162 | prompt eval time = 145.69 ms / 352 tokens ( 0.41 ms per token, 2416.04 tokens per second) 3.53.432.500 I slot print_timing: id 0 | task 13162 | eval time = 1441.56 ms / 92 tokens ( 15.84 ms per token, 63.13 tokens per second) 3.53.432.501 I slot print_timing: id 0 | task 13162 | total time = 1587.25 ms / 444 tokens 3.53.432.502 I slot print_timing: id 0 | task 13162 | graphs reused = 12498 3.53.432.503 I slot print_timing: id 0 | task 13162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.432.533 I slot release: id 0 | task 13162 | stop processing: n_tokens = 475, truncated = 0 3.53.455.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 233338776 3.53.455.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 3.53.513.333 I slot launch_slot_: id 0 | task 13257 | processing task, is_child = 0 3.56.049.429 I slot print_timing: id 0 | task 13257 | prompt eval time = 192.41 ms / 550 tokens ( 0.35 ms per token, 2858.48 tokens per second) 3.56.049.434 I slot print_timing: id 0 | task 13257 | eval time = 2343.66 ms / 153 tokens ( 15.42 ms per token, 64.86 tokens per second) 3.56.049.435 I slot print_timing: id 0 | task 13257 | total time = 2536.07 ms / 703 tokens 3.56.049.436 I slot print_timing: id 0 | task 13257 | graphs reused = 12649 3.56.049.438 I slot print_timing: id 0 | task 13257 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.049.474 I slot release: id 0 | task 13257 | stop processing: n_tokens = 734, truncated = 0 3.56.092.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 734, t_last = 235955717 3.56.092.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.56.160.181 I slot launch_slot_: id 0 | task 13414 | processing task, is_child = 0 3.59.384.197 I slot print_timing: id 0 | task 13414 | n_gen = 195, tg = 64.54 t/s, tg_3s = 64.87 t/s 4.00.273.077 I slot print_timing: id 0 | task 13414 | prompt eval time = 218.05 ms / 772 tokens ( 0.28 ms per token, 3540.41 tokens per second) 4.00.273.083 I slot print_timing: id 0 | task 13414 | eval time = 3894.82 ms / 251 tokens ( 15.58 ms per token, 64.19 tokens per second) 4.00.273.084 I slot print_timing: id 0 | task 13414 | total time = 4112.88 ms / 1023 tokens 4.00.273.084 I slot print_timing: id 0 | task 13414 | graphs reused = 12897 4.00.273.085 I slot print_timing: id 0 | task 13414 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.273.126 I slot release: id 0 | task 13414 | stop processing: n_tokens = 1054, truncated = 0 4.00.312.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1054, t_last = 240179369 4.00.312.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.206 MiB) 4.00.381.419 I slot launch_slot_: id 0 | task 13669 | processing task, is_child = 0 4.03.390.330 I slot print_timing: id 0 | task 13669 | prompt eval time = 216.43 ms / 683 tokens ( 0.32 ms per token, 3155.75 tokens per second) 4.03.390.336 I slot print_timing: id 0 | task 13669 | eval time = 2792.46 ms / 181 tokens ( 15.51 ms per token, 64.46 tokens per second) 4.03.390.337 I slot print_timing: id 0 | task 13669 | total time = 3008.89 ms / 864 tokens 4.03.390.338 I slot print_timing: id 0 | task 13669 | graphs reused = 13075 4.03.390.338 I slot print_timing: id 0 | task 13669 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.390.376 I slot release: id 0 | task 13669 | stop processing: n_tokens = 895, truncated = 0 4.03.423.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 243296619 4.03.423.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.859 MiB) 4.03.491.143 I slot launch_slot_: id 0 | task 13854 | processing task, is_child = 0 4.06.694.076 I slot print_timing: id 0 | task 13854 | n_gen = 193, tg = 63.85 t/s, tg_3s = 64.18 t/s 4.07.332.039 I slot print_timing: id 0 | task 13854 | prompt eval time = 195.70 ms / 579 tokens ( 0.34 ms per token, 2958.66 tokens per second) 4.07.332.044 I slot print_timing: id 0 | task 13854 | eval time = 3645.18 ms / 235 tokens ( 15.58 ms per token, 64.19 tokens per second) 4.07.332.046 I slot print_timing: id 0 | task 13854 | total time = 3840.88 ms / 814 tokens 4.07.332.047 I slot print_timing: id 0 | task 13854 | graphs reused = 13307 4.07.332.048 I slot print_timing: id 0 | task 13854 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.332.084 I slot release: id 0 | task 13854 | stop processing: n_tokens = 845, truncated = 0 4.07.353.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 247238327 4.07.353.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.677 MiB) 4.07.358.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.703 MiB) 4.07.428.900 I slot launch_slot_: id 0 | task 14093 | processing task, is_child = 0 4.09.801.712 I slot print_timing: id 0 | task 14093 | prompt eval time = 178.29 ms / 500 tokens ( 0.36 ms per token, 2804.47 tokens per second) 4.09.801.718 I slot print_timing: id 0 | task 14093 | eval time = 2194.51 ms / 140 tokens ( 15.79 ms per token, 63.34 tokens per second) 4.09.801.719 I slot print_timing: id 0 | task 14093 | total time = 2372.79 ms / 640 tokens 4.09.801.719 I slot print_timing: id 0 | task 14093 | graphs reused = 13445 4.09.801.721 I slot print_timing: id 0 | task 14093 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.801.754 I slot release: id 0 | task 14093 | stop processing: n_tokens = 671, truncated = 0 4.09.824.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 671, t_last = 249707997 4.09.824.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.859 MiB) 4.09.880.456 I slot launch_slot_: id 0 | task 14236 | processing task, is_child = 0 4.13.117.827 I slot print_timing: id 0 | task 14236 | n_gen = 195, tg = 64.44 t/s, tg_3s = 64.77 t/s 4.13.705.387 I slot print_timing: id 0 | task 14236 | prompt eval time = 226.75 ms / 776 tokens ( 0.29 ms per token, 3422.24 tokens per second) 4.13.705.393 I slot print_timing: id 0 | task 14236 | eval time = 3598.15 ms / 232 tokens ( 15.58 ms per token, 64.20 tokens per second) 4.13.705.394 I slot print_timing: id 0 | task 14236 | total time = 3824.90 ms / 1008 tokens 4.13.705.394 I slot print_timing: id 0 | task 14236 | graphs reused = 13674 4.13.705.395 I slot print_timing: id 0 | task 14236 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.705.436 I slot release: id 0 | task 14236 | stop processing: n_tokens = 1039, truncated = 0 4.13.735.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1039, t_last = 253611679 4.13.736.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.800 MiB) 4.13.798.752 I slot launch_slot_: id 0 | task 14472 | processing task, is_child = 0 4.16.974.026 I slot print_timing: id 0 | task 14472 | n_gen = 195, tg = 64.64 t/s, tg_3s = 64.98 t/s 4.17.320.491 I slot print_timing: id 0 | task 14472 | prompt eval time = 174.18 ms / 504 tokens ( 0.35 ms per token, 2893.53 tokens per second) 4.17.320.497 I slot print_timing: id 0 | task 14472 | eval time = 3347.54 ms / 217 tokens ( 15.50 ms per token, 64.53 tokens per second) 4.17.320.498 I slot print_timing: id 0 | task 14472 | total time = 3521.72 ms / 721 tokens 4.17.320.499 I slot print_timing: id 0 | task 14472 | graphs reused = 13889 4.17.320.500 I slot print_timing: id 0 | task 14472 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.320.535 I slot release: id 0 | task 14472 | stop processing: n_tokens = 752, truncated = 0 4.17.339.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 257226778 4.17.339.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.266 MiB) 4.17.392.464 I slot launch_slot_: id 0 | task 14692 | processing task, is_child = 0 4.20.605.428 I slot print_timing: id 0 | task 14692 | n_gen = 195, tg = 64.45 t/s, tg_3s = 64.79 t/s 4.21.141.931 I slot print_timing: id 0 | task 14692 | prompt eval time = 203.09 ms / 633 tokens ( 0.32 ms per token, 3116.92 tokens per second) 4.21.141.937 I slot print_timing: id 0 | task 14692 | eval time = 3546.36 ms / 229 tokens ( 15.55 ms per token, 64.29 tokens per second) 4.21.141.938 I slot print_timing: id 0 | task 14692 | total time = 3749.45 ms / 862 tokens 4.21.141.939 I slot print_timing: id 0 | task 14692 | graphs reused = 14115 4.21.141.939 I slot print_timing: id 0 | task 14692 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.141.977 I slot release: id 0 | task 14692 | stop processing: n_tokens = 893, truncated = 0 4.21.147.096 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 893, t_last = 261048220 4.21.147.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.928 MiB) 4.21.212.192 I slot launch_slot_: id 0 | task 14925 | processing task, is_child = 0 4.23.654.116 I slot print_timing: id 0 | task 14925 | prompt eval time = 152.90 ms / 395 tokens ( 0.39 ms per token, 2583.46 tokens per second) 4.23.654.122 I slot print_timing: id 0 | task 14925 | eval time = 2289.01 ms / 149 tokens ( 15.47 ms per token, 64.66 tokens per second) 4.23.654.123 I slot print_timing: id 0 | task 14925 | total time = 2441.90 ms / 544 tokens 4.23.654.123 I slot print_timing: id 0 | task 14925 | graphs reused = 14261 4.23.654.124 I slot print_timing: id 0 | task 14925 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.654.154 I slot release: id 0 | task 14925 | stop processing: n_tokens = 575, truncated = 0 4.23.699.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 263560397 4.23.699.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.704 MiB) 4.23.753.919 I slot launch_slot_: id 0 | task 15077 | processing task, is_child = 0 4.26.949.729 I slot print_timing: id 0 | task 15077 | n_gen = 192, tg = 63.67 t/s, tg_3s = 64.00 t/s 4.27.497.232 I slot print_timing: id 0 | task 15077 | prompt eval time = 195.76 ms / 584 tokens ( 0.34 ms per token, 2983.23 tokens per second) 4.27.497.238 I slot print_timing: id 0 | task 15077 | eval time = 3547.53 ms / 228 tokens ( 15.63 ms per token, 63.99 tokens per second) 4.27.497.240 I slot print_timing: id 0 | task 15077 | total time = 3743.29 ms / 812 tokens 4.27.497.241 I slot print_timing: id 0 | task 15077 | graphs reused = 14486 4.27.497.241 I slot print_timing: id 0 | task 15077 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.497.281 I slot release: id 0 | task 15077 | stop processing: n_tokens = 843, truncated = 0 4.27.535.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 267403524 4.27.535.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.269 MiB) 4.27.602.114 I slot launch_slot_: id 0 | task 15309 | processing task, is_child = 0 4.30.814.479 I slot print_timing: id 0 | task 15309 | n_gen = 192, tg = 63.56 t/s, tg_3s = 63.89 t/s 4.31.771.304 I slot print_timing: id 0 | task 15309 | prompt eval time = 207.28 ms / 695 tokens ( 0.30 ms per token, 3352.89 tokens per second) 4.31.771.310 I slot print_timing: id 0 | task 15309 | eval time = 3961.89 ms / 255 tokens ( 15.60 ms per token, 64.11 tokens per second) 4.31.771.311 I slot print_timing: id 0 | task 15309 | total time = 4169.17 ms / 950 tokens 4.31.771.312 I slot print_timing: id 0 | task 15309 | graphs reused = 14738 4.31.771.313 I slot print_timing: id 0 | task 15309 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.771.350 I slot release: id 0 | task 15309 | stop processing: n_tokens = 981, truncated = 0 4.31.795.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 981, t_last = 271677594 4.31.795.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.894 MiB) 4.31.864.776 I slot launch_slot_: id 0 | task 15568 | processing task, is_child = 0 4.35.103.879 I slot print_timing: id 0 | task 15568 | n_gen = 193, tg = 63.76 t/s, tg_3s = 64.09 t/s 4.35.346.699 I slot print_timing: id 0 | task 15568 | prompt eval time = 227.70 ms / 769 tokens ( 0.30 ms per token, 3377.27 tokens per second) 4.35.346.704 I slot print_timing: id 0 | task 15568 | eval time = 3254.21 ms / 209 tokens ( 15.65 ms per token, 63.92 tokens per second) 4.35.346.705 I slot print_timing: id 0 | task 15568 | total time = 3481.91 ms / 978 tokens 4.35.346.706 I slot print_timing: id 0 | task 15568 | graphs reused = 14945 4.35.346.706 I slot print_timing: id 0 | task 15568 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.346.746 I slot release: id 0 | task 15568 | stop processing: n_tokens = 1009, truncated = 0 4.35.352.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1009, t_last = 275252989 4.35.352.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.926 MiB) 4.35.358.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.079 MiB) 4.35.429.536 I slot launch_slot_: id 0 | task 15781 | processing task, is_child = 0 4.38.228.827 I slot print_timing: id 0 | task 15781 | prompt eval time = 188.31 ms / 576 tokens ( 0.33 ms per token, 3058.74 tokens per second) 4.38.228.832 I slot print_timing: id 0 | task 15781 | eval time = 2610.96 ms / 167 tokens ( 15.73 ms per token, 63.58 tokens per second) 4.38.228.833 I slot print_timing: id 0 | task 15781 | total time = 2799.27 ms / 743 tokens 4.38.228.834 I slot print_timing: id 0 | task 15781 | graphs reused = 15109 4.38.228.835 I slot print_timing: id 0 | task 15781 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.228.871 I slot release: id 0 | task 15781 | stop processing: n_tokens = 774, truncated = 0 4.38.266.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 774, t_last = 278135114 4.38.266.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 4.38.325.736 I slot launch_slot_: id 0 | task 15952 | processing task, is_child = 0 4.41.540.380 I slot print_timing: id 0 | task 15952 | n_gen = 194, tg = 64.17 t/s, tg_3s = 64.50 t/s 4.43.179.220 I slot print_timing: id 0 | task 15952 | prompt eval time = 206.97 ms / 655 tokens ( 0.32 ms per token, 3164.63 tokens per second) 4.43.179.226 I slot print_timing: id 0 | task 15952 | eval time = 4646.49 ms / 299 tokens ( 15.59 ms per token, 64.13 tokens per second) 4.43.179.227 I slot print_timing: id 0 | task 15952 | total time = 4853.46 ms / 954 tokens 4.43.179.228 I slot print_timing: id 0 | task 15952 | graphs reused = 15405 4.43.179.229 I slot print_timing: id 0 | task 15952 | graph reallocs = 0 / 0 (same size) / (changed size) 4.43.179.266 I slot release: id 0 | task 15952 | stop processing: n_tokens = 985, truncated = 0 4.43.201.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 985, t_last = 283085510 4.43.201.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 4.43.263.765 I slot launch_slot_: id 0 | task 16255 | processing task, is_child = 0 4.45.875.597 I slot print_timing: id 0 | task 16255 | prompt eval time = 196.56 ms / 621 tokens ( 0.32 ms per token, 3159.39 tokens per second) 4.45.875.603 I slot print_timing: id 0 | task 16255 | eval time = 2415.26 ms / 155 tokens ( 15.68 ms per token, 63.76 tokens per second) 4.45.875.604 I slot print_timing: id 0 | task 16255 | total time = 2611.81 ms / 776 tokens 4.45.875.604 I slot print_timing: id 0 | task 16255 | graphs reused = 15557 4.45.875.605 I slot print_timing: id 0 | task 16255 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.875.644 I slot release: id 0 | task 16255 | stop processing: n_tokens = 807, truncated = 0 4.45.881.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 807, t_last = 285781887 4.45.881.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 4.45.947.522 I slot launch_slot_: id 0 | task 16414 | processing task, is_child = 0 4.48.786.590 I slot print_timing: id 0 | task 16414 | prompt eval time = 222.45 ms / 767 tokens ( 0.29 ms per token, 3447.95 tokens per second) 4.48.786.596 I slot print_timing: id 0 | task 16414 | eval time = 2616.60 ms / 170 tokens ( 15.48 ms per token, 64.59 tokens per second) 4.48.786.597 I slot print_timing: id 0 | task 16414 | total time = 2839.05 ms / 937 tokens 4.48.786.598 I slot print_timing: id 0 | task 16414 | graphs reused = 15725 4.48.786.598 I slot print_timing: id 0 | task 16414 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.786.642 I slot release: id 0 | task 16414 | stop processing: n_tokens = 968, truncated = 0 4.48.805.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 968, t_last = 288692885 4.48.805.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.484 MiB) 4.48.871.717 I slot launch_slot_: id 0 | task 16588 | processing task, is_child = 0 4.52.124.863 I slot print_timing: id 0 | task 16588 | n_gen = 194, tg = 64.14 t/s, tg_3s = 64.47 t/s 4.52.751.796 I slot print_timing: id 0 | task 16588 | prompt eval time = 244.13 ms / 864 tokens ( 0.28 ms per token, 3539.05 tokens per second) 4.52.751.801 I slot print_timing: id 0 | task 16588 | eval time = 3635.93 ms / 234 tokens ( 15.60 ms per token, 64.08 tokens per second) 4.52.751.803 I slot print_timing: id 0 | task 16588 | total time = 3880.06 ms / 1098 tokens 4.52.751.803 I slot print_timing: id 0 | task 16588 | graphs reused = 15956 4.52.751.804 I slot print_timing: id 0 | task 16588 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.751.849 I slot release: id 0 | task 16588 | stop processing: n_tokens = 1129, truncated = 0 4.52.769.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1129, t_last = 292658092 4.52.769.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 4.52.775.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.892 MiB) 4.52.848.566 I slot launch_slot_: id 0 | task 16826 | processing task, is_child = 0 4.55.522.874 I slot print_timing: id 0 | task 16826 | prompt eval time = 213.93 ms / 646 tokens ( 0.33 ms per token, 3019.69 tokens per second) 4.55.522.880 I slot print_timing: id 0 | task 16826 | eval time = 2460.36 ms / 158 tokens ( 15.67 ms per token, 63.81 tokens per second) 4.55.522.881 I slot print_timing: id 0 | task 16826 | total time = 2674.29 ms / 804 tokens 4.55.522.881 I slot print_timing: id 0 | task 16826 | graphs reused = 16111 4.55.522.882 I slot print_timing: id 0 | task 16826 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.522.921 I slot release: id 0 | task 16826 | stop processing: n_tokens = 835, truncated = 0 4.55.528.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 835, t_last = 295429164 4.55.528.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 4.55.587.476 I slot launch_slot_: id 0 | task 16988 | processing task, is_child = 0 4.58.812.128 I slot print_timing: id 0 | task 16988 | n_gen = 192, tg = 63.41 t/s, tg_3s = 63.74 t/s 4.59.551.878 I slot print_timing: id 0 | task 16988 | prompt eval time = 212.39 ms / 720 tokens ( 0.29 ms per token, 3390.04 tokens per second) 4.59.551.884 I slot print_timing: id 0 | task 16988 | eval time = 3751.99 ms / 240 tokens ( 15.70 ms per token, 63.70 tokens per second) 4.59.551.885 I slot print_timing: id 0 | task 16988 | total time = 3964.38 ms / 960 tokens 4.59.551.886 I slot print_timing: id 0 | task 16988 | graphs reused = 16348 4.59.551.886 I slot print_timing: id 0 | task 16988 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.551.926 I slot release: id 0 | task 16988 | stop processing: n_tokens = 991, truncated = 0 4.59.593.408 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 299458169 4.59.593.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.079 MiB) 4.59.656.894 I slot launch_slot_: id 0 | task 17232 | processing task, is_child = 0 5.02.830.889 I slot print_timing: id 0 | task 17232 | n_gen = 193, tg = 63.96 t/s, tg_3s = 64.30 t/s 5.03.455.946 I slot print_timing: id 0 | task 17232 | prompt eval time = 172.32 ms / 509 tokens ( 0.34 ms per token, 2953.76 tokens per second) 5.03.455.952 I slot print_timing: id 0 | task 17232 | eval time = 3626.71 ms / 233 tokens ( 15.63 ms per token, 63.97 tokens per second) 5.03.455.953 I slot print_timing: id 0 | task 17232 | total time = 3799.03 ms / 742 tokens 5.03.455.953 I slot print_timing: id 0 | task 17232 | graphs reused = 16578 5.03.455.954 I slot print_timing: id 0 | task 17232 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.455.987 I slot release: id 0 | task 17232 | stop processing: n_tokens = 773, truncated = 0 5.03.488.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 303362230 5.03.488.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.736 MiB) 5.03.542.220 I slot launch_slot_: id 0 | task 17468 | processing task, is_child = 0 5.06.746.320 I slot print_timing: id 0 | task 17468 | n_gen = 194, tg = 64.02 t/s, tg_3s = 64.36 t/s 5.07.812.160 I slot print_timing: id 0 | task 17468 | prompt eval time = 189.63 ms / 581 tokens ( 0.33 ms per token, 3063.83 tokens per second) 5.07.812.166 I slot print_timing: id 0 | task 17468 | eval time = 4080.29 ms / 263 tokens ( 15.57 ms per token, 64.21 tokens per second) 5.07.812.167 I slot print_timing: id 0 | task 17468 | total time = 4269.92 ms / 844 tokens 5.07.812.168 I slot print_timing: id 0 | task 17468 | graphs reused = 16838 5.07.812.169 I slot print_timing: id 0 | task 17468 | graph reallocs = 0 / 0 (same size) / (changed size) 5.07.812.206 I slot release: id 0 | task 17468 | stop processing: n_tokens = 875, truncated = 0 5.07.855.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 875, t_last = 307718450 5.07.855.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.485 MiB) 5.07.919.422 I slot launch_slot_: id 0 | task 17735 | processing task, is_child = 0 5.11.183.968 I slot print_timing: id 0 | task 17735 | n_gen = 193, tg = 63.68 t/s, tg_3s = 64.01 t/s 5.11.888.237 I slot print_timing: id 0 | task 17735 | prompt eval time = 249.37 ms / 925 tokens ( 0.27 ms per token, 3709.39 tokens per second) 5.11.888.243 I slot print_timing: id 0 | task 17735 | eval time = 3719.43 ms / 239 tokens ( 15.63 ms per token, 63.99 tokens per second) 5.11.888.244 I slot print_timing: id 0 | task 17735 | total time = 3968.80 ms / 1164 tokens 5.11.888.245 I slot print_timing: id 0 | task 17735 | graphs reused = 17074 5.11.888.245 I slot print_timing: id 0 | task 17735 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.888.292 I slot release: id 0 | task 17735 | stop processing: n_tokens = 1195, truncated = 0 5.11.925.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1195, t_last = 311794535 5.11.925.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.358 MiB) 5.11.992.721 I slot launch_slot_: id 0 | task 17978 | processing task, is_child = 0 5.15.240.116 I slot print_timing: id 0 | task 17978 | n_gen = 192, tg = 63.39 t/s, tg_3s = 63.72 t/s 5.16.959.760 I slot print_timing: id 0 | task 17978 | prompt eval time = 234.42 ms / 885 tokens ( 0.26 ms per token, 3775.26 tokens per second) 5.16.959.766 I slot print_timing: id 0 | task 17978 | eval time = 4732.60 ms / 304 tokens ( 15.62 ms per token, 64.02 tokens per second) 5.16.959.767 I slot print_timing: id 0 | task 17978 | total time = 4967.02 ms / 1189 tokens 5.16.959.768 I slot print_timing: id 0 | task 17978 | graphs reused = 17375 5.16.959.769 I slot print_timing: id 0 | task 17978 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.959.815 I slot release: id 0 | task 17978 | stop processing: n_tokens = 1220, truncated = 0 5.16.965.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1220, t_last = 316866059 5.16.965.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.709 MiB) 5.17.036.457 I slot launch_slot_: id 0 | task 18286 | processing task, is_child = 0 5.19.381.210 I slot print_timing: id 0 | task 18286 | prompt eval time = 149.43 ms / 392 tokens ( 0.38 ms per token, 2623.23 tokens per second) 5.19.381.216 I slot print_timing: id 0 | task 18286 | eval time = 2195.30 ms / 140 tokens ( 15.79 ms per token, 63.32 tokens per second) 5.19.381.217 I slot print_timing: id 0 | task 18286 | total time = 2344.73 ms / 532 tokens 5.19.381.218 I slot print_timing: id 0 | task 18286 | graphs reused = 17512 5.19.381.218 I slot print_timing: id 0 | task 18286 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.381.249 I slot release: id 0 | task 18286 | stop processing: n_tokens = 563, truncated = 0 5.19.398.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 319287492 5.19.398.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.716 MiB) 5.19.458.807 I slot launch_slot_: id 0 | task 18429 | processing task, is_child = 0 5.22.403.507 I slot print_timing: id 0 | task 18429 | prompt eval time = 139.13 ms / 331 tokens ( 0.42 ms per token, 2379.10 tokens per second) 5.22.403.513 I slot print_timing: id 0 | task 18429 | eval time = 2805.55 ms / 182 tokens ( 15.50 ms per token, 64.51 tokens per second) 5.22.403.513 I slot print_timing: id 0 | task 18429 | total time = 2944.68 ms / 513 tokens 5.22.403.515 I slot print_timing: id 0 | task 18429 | graphs reused = 17691 5.22.403.515 I slot print_timing: id 0 | task 18429 | graph reallocs = 0 / 0 (same size) / (changed size) 5.22.403.544 I slot release: id 0 | task 18429 | stop processing: n_tokens = 544, truncated = 0 5.22.428.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 544, t_last = 322309787 5.22.428.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 5.22.487.783 I slot launch_slot_: id 0 | task 18614 | processing task, is_child = 0 5.23.866.670 I slot print_timing: id 0 | task 18614 | prompt eval time = 143.63 ms / 357 tokens ( 0.40 ms per token, 2485.50 tokens per second) 5.23.866.676 I slot print_timing: id 0 | task 18614 | eval time = 1235.23 ms / 80 tokens ( 15.64 ms per token, 63.96 tokens per second) 5.23.866.677 I slot print_timing: id 0 | task 18614 | total time = 1378.87 ms / 437 tokens 5.23.866.678 I slot print_timing: id 0 | task 18614 | graphs reused = 17769 5.23.866.679 I slot print_timing: id 0 | task 18614 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.866.709 I slot release: id 0 | task 18614 | stop processing: n_tokens = 468, truncated = 0 5.23.871.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 323772953 5.23.871.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.180 MiB) 5.23.930.238 I slot launch_slot_: id 0 | task 18697 | processing task, is_child = 0 5.26.699.967 I slot print_timing: id 0 | task 18697 | prompt eval time = 137.05 ms / 315 tokens ( 0.44 ms per token, 2298.43 tokens per second) 5.26.699.973 I slot print_timing: id 0 | task 18697 | eval time = 2632.66 ms / 170 tokens ( 15.58 ms per token, 64.19 tokens per second) 5.26.699.974 I slot print_timing: id 0 | task 18697 | total time = 2769.71 ms / 485 tokens 5.26.699.975 I slot print_timing: id 0 | task 18697 | graphs reused = 17936 5.26.699.976 I slot print_timing: id 0 | task 18697 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.700.008 I slot release: id 0 | task 18697 | stop processing: n_tokens = 516, truncated = 0 5.26.736.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 516, t_last = 326606251 5.26.736.665 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.488 MiB) 5.26.792.660 I slot launch_slot_: id 0 | task 18870 | processing task, is_child = 0 5.28.073.569 I slot print_timing: id 0 | task 18870 | prompt eval time = 144.98 ms / 378 tokens ( 0.38 ms per token, 2607.24 tokens per second) 5.28.073.574 I slot print_timing: id 0 | task 18870 | eval time = 1135.91 ms / 74 tokens ( 15.56 ms per token, 64.27 tokens per second) 5.28.073.575 I slot print_timing: id 0 | task 18870 | total time = 1280.89 ms / 452 tokens 5.28.073.576 I slot print_timing: id 0 | task 18870 | graphs reused = 18008 5.28.073.576 I slot print_timing: id 0 | task 18870 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.073.606 I slot release: id 0 | task 18870 | stop processing: n_tokens = 483, truncated = 0 5.28.111.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 327979849 5.28.111.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.247 MiB) 5.28.167.969 I slot launch_slot_: id 0 | task 18947 | processing task, is_child = 0 5.29.251.025 I slot print_timing: id 0 | task 18947 | prompt eval time = 131.79 ms / 295 tokens ( 0.45 ms per token, 2238.48 tokens per second) 5.29.251.031 I slot print_timing: id 0 | task 18947 | eval time = 951.25 ms / 63 tokens ( 15.34 ms per token, 65.18 tokens per second) 5.29.251.032 I slot print_timing: id 0 | task 18947 | total time = 1083.04 ms / 358 tokens 5.29.251.033 I slot print_timing: id 0 | task 18947 | graphs reused = 18069 5.29.251.034 I slot print_timing: id 0 | task 18947 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.251.060 I slot release: id 0 | task 18947 | stop processing: n_tokens = 389, truncated = 0 5.29.295.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 329157304 5.29.295.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.021 MiB) 5.29.346.814 I slot launch_slot_: id 0 | task 19013 | processing task, is_child = 0 5.30.721.496 I slot print_timing: id 0 | task 19013 | prompt eval time = 141.24 ms / 337 tokens ( 0.42 ms per token, 2385.99 tokens per second) 5.30.721.502 I slot print_timing: id 0 | task 19013 | eval time = 1233.42 ms / 79 tokens ( 15.81 ms per token, 63.24 tokens per second) 5.30.721.503 I slot print_timing: id 0 | task 19013 | total time = 1374.66 ms / 416 tokens 5.30.721.504 I slot print_timing: id 0 | task 19013 | graphs reused = 18146 5.30.721.505 I slot print_timing: id 0 | task 19013 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.721.538 I slot release: id 0 | task 19013 | stop processing: n_tokens = 447, truncated = 0 5.30.726.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 330627781 5.30.726.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.681 MiB) 5.30.779.109 I slot launch_slot_: id 0 | task 19095 | processing task, is_child = 0 5.33.186.327 I slot print_timing: id 0 | task 19095 | prompt eval time = 145.69 ms / 325 tokens ( 0.45 ms per token, 2230.83 tokens per second) 5.33.186.332 I slot print_timing: id 0 | task 19095 | eval time = 2261.51 ms / 148 tokens ( 15.38 ms per token, 65.00 tokens per second) 5.33.186.333 I slot print_timing: id 0 | task 19095 | total time = 2407.20 ms / 473 tokens 5.33.186.334 I slot print_timing: id 0 | task 19095 | graphs reused = 18292 5.33.186.335 I slot print_timing: id 0 | task 19095 | graph reallocs = 0 / 0 (same size) / (changed size) 5.33.186.362 I slot release: id 0 | task 19095 | stop processing: n_tokens = 504, truncated = 0 5.33.204.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.063 5.33.244.917 I slot launch_slot_: id 0 | task 19246 | processing task, is_child = 0 5.34.260.472 I slot print_timing: id 0 | task 19246 | prompt eval time = 128.84 ms / 264 tokens ( 0.49 ms per token, 2049.04 tokens per second) 5.34.260.477 I slot print_timing: id 0 | task 19246 | eval time = 886.69 ms / 57 tokens ( 15.83 ms per token, 63.16 tokens per second) 5.34.260.478 I slot print_timing: id 0 | task 19246 | total time = 1015.53 ms / 321 tokens 5.34.260.479 I slot print_timing: id 0 | task 19246 | graphs reused = 18347 5.34.260.480 I slot print_timing: id 0 | task 19246 | graph reallocs = 0 / 0 (same size) / (changed size) 5.34.260.507 I slot release: id 0 | task 19246 | stop processing: n_tokens = 352, truncated = 0 5.34.280.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 334166750 5.34.280.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.486 MiB) 5.34.340.215 I slot launch_slot_: id 0 | task 19306 | processing task, is_child = 0 5.36.368.227 I slot print_timing: id 0 | task 19306 | prompt eval time = 142.23 ms / 331 tokens ( 0.43 ms per token, 2327.27 tokens per second) 5.36.368.232 I slot print_timing: id 0 | task 19306 | eval time = 1885.77 ms / 122 tokens ( 15.58 ms per token, 64.16 tokens per second) 5.36.368.233 I slot print_timing: id 0 | task 19306 | total time = 2027.99 ms / 453 tokens 5.36.368.234 I slot print_timing: id 0 | task 19306 | graphs reused = 18467 5.36.368.235 I slot print_timing: id 0 | task 19306 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.368.264 I slot release: id 0 | task 19306 | stop processing: n_tokens = 484, truncated = 0 5.36.384.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 336274507 5.36.384.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.117 MiB) 5.36.445.336 I slot launch_slot_: id 0 | task 19431 | processing task, is_child = 0 5.39.510.449 I slot print_timing: id 0 | task 19431 | prompt eval time = 138.52 ms / 333 tokens ( 0.42 ms per token, 2403.95 tokens per second) 5.39.510.454 I slot print_timing: id 0 | task 19431 | eval time = 2926.57 ms / 188 tokens ( 15.65 ms per token, 63.90 tokens per second) 5.39.510.455 I slot print_timing: id 0 | task 19431 | total time = 3065.09 ms / 521 tokens 5.39.510.456 I slot print_timing: id 0 | task 19431 | graphs reused = 18652 5.39.510.457 I slot print_timing: id 0 | task 19431 | graph reallocs = 0 / 0 (same size) / (changed size) 5.39.510.484 I slot release: id 0 | task 19431 | stop processing: n_tokens = 552, truncated = 0 5.39.525.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 552, t_last = 339416727 5.39.525.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.433 MiB) 5.39.585.157 I slot launch_slot_: id 0 | task 19622 | processing task, is_child = 0 5.41.884.762 I slot print_timing: id 0 | task 19622 | prompt eval time = 143.87 ms / 346 tokens ( 0.42 ms per token, 2405.02 tokens per second) 5.41.884.768 I slot print_timing: id 0 | task 19622 | eval time = 2155.72 ms / 141 tokens ( 15.40 ms per token, 64.94 tokens per second) 5.41.884.769 I slot print_timing: id 0 | task 19622 | total time = 2299.59 ms / 487 tokens 5.41.884.769 I slot print_timing: id 0 | task 19622 | graphs reused = 18790 5.41.884.771 I slot print_timing: id 0 | task 19622 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.884.799 I slot release: id 0 | task 19622 | stop processing: n_tokens = 518, truncated = 0 5.41.911.151 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 341791042 5.41.911.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.309 MiB) 5.41.968.027 I slot launch_slot_: id 0 | task 19766 | processing task, is_child = 0 5.43.800.124 I slot print_timing: id 0 | task 19766 | prompt eval time = 141.33 ms / 325 tokens ( 0.43 ms per token, 2299.55 tokens per second) 5.43.800.130 I slot print_timing: id 0 | task 19766 | eval time = 1690.75 ms / 108 tokens ( 15.80 ms per token, 63.29 tokens per second) 5.43.800.131 I slot print_timing: id 0 | task 19766 | total time = 1832.08 ms / 433 tokens 5.43.800.131 I slot print_timing: id 0 | task 19766 | graphs reused = 18896 5.43.800.132 I slot print_timing: id 0 | task 19766 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.800.160 I slot release: id 0 | task 19766 | stop processing: n_tokens = 464, truncated = 0 5.43.827.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 464, t_last = 343706403 5.43.827.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.959 MiB) 5.43.887.850 I slot launch_slot_: id 0 | task 19877 | processing task, is_child = 0 5.45.289.046 I slot print_timing: id 0 | task 19877 | prompt eval time = 138.50 ms / 322 tokens ( 0.43 ms per token, 2324.98 tokens per second) 5.45.289.052 I slot print_timing: id 0 | task 19877 | eval time = 1262.68 ms / 84 tokens ( 15.21 ms per token, 65.73 tokens per second) 5.45.289.053 I slot print_timing: id 0 | task 19877 | total time = 1401.18 ms / 406 tokens 5.45.289.054 I slot print_timing: id 0 | task 19877 | graphs reused = 18978 5.45.289.055 I slot print_timing: id 0 | task 19877 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.289.083 I slot release: id 0 | task 19877 | stop processing: n_tokens = 437, truncated = 0 5.45.307.997 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 345195326 5.45.308.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.558 MiB) 5.45.358.718 I slot launch_slot_: id 0 | task 19964 | processing task, is_child = 0 5.48.509.999 I slot print_timing: id 0 | task 19964 | n_gen = 193, tg = 63.81 t/s, tg_3s = 64.14 t/s 5.51.008.061 I slot print_timing: id 0 | task 19964 | prompt eval time = 142.32 ms / 338 tokens ( 0.42 ms per token, 2374.86 tokens per second) 5.51.008.066 I slot print_timing: id 0 | task 19964 | eval time = 5507.00 ms / 354 tokens ( 15.60 ms per token, 64.10 tokens per second) 5.51.008.067 I slot print_timing: id 0 | task 19964 | total time = 5649.32 ms / 692 tokens 5.51.008.067 I slot print_timing: id 0 | task 19964 | graphs reused = 19329 5.51.008.068 I slot print_timing: id 0 | task 19964 | graph reallocs = 0 / 0 (same size) / (changed size) 5.51.008.098 I slot release: id 0 | task 19964 | stop processing: n_tokens = 723, truncated = 0 5.51.012.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 723, t_last = 350914341 5.51.054.282 I slot launch_slot_: id 0 | task 20321 | processing task, is_child = 0 5.54.207.362 I slot print_timing: id 0 | task 20321 | n_gen = 195, tg = 64.46 t/s, tg_3s = 64.79 t/s 5.56.217.828 I slot print_timing: id 0 | task 20321 | prompt eval time = 143.37 ms / 347 tokens ( 0.41 ms per token, 2420.33 tokens per second) 5.56.217.834 I slot print_timing: id 0 | task 20321 | eval time = 5020.16 ms / 323 tokens ( 15.59 ms per token, 64.14 tokens per second) 5.56.217.835 I slot print_timing: id 0 | task 20321 | total time = 5163.53 ms / 670 tokens 5.56.217.836 I slot print_timing: id 0 | task 20321 | graphs reused = 19649 5.56.217.837 I slot print_timing: id 0 | task 20321 | graph reallocs = 0 / 0 (same size) / (changed size) 5.56.217.868 I slot release: id 0 | task 20321 | stop processing: n_tokens = 701, truncated = 0 5.56.242.753 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 701, t_last = 356124111 5.56.242.811 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.991 MiB) 5.56.305.385 I slot launch_slot_: id 0 | task 20647 | processing task, is_child = 0 5.59.454.964 I slot print_timing: id 0 | task 20647 | n_gen = 199, tg = 65.75 t/s, tg_3s = 66.08 t/s 6.01.806.254 I slot print_timing: id 0 | task 20647 | prompt eval time = 137.98 ms / 331 tokens ( 0.42 ms per token, 2398.86 tokens per second) 6.01.806.259 I slot print_timing: id 0 | task 20647 | eval time = 5362.87 ms / 354 tokens ( 15.19 ms per token, 65.82 tokens per second) 6.01.806.260 I slot print_timing: id 0 | task 20647 | total time = 5500.85 ms / 685 tokens 6.01.806.261 I slot print_timing: id 0 | task 20647 | graphs reused = 20000 6.01.806.262 I slot print_timing: id 0 | task 20647 | graph reallocs = 0 / 0 (same size) / (changed size) 6.01.806.288 I slot release: id 0 | task 20647 | stop processing: n_tokens = 716, truncated = 0 6.01.820.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 361712532 6.01.821.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.026 MiB) 6.01.880.199 I slot launch_slot_: id 0 | task 21004 | processing task, is_child = 0 6.04.683.868 I slot print_timing: id 0 | task 21004 | prompt eval time = 138.60 ms / 345 tokens ( 0.40 ms per token, 2489.12 tokens per second) 6.04.683.874 I slot print_timing: id 0 | task 21004 | eval time = 2665.05 ms / 176 tokens ( 15.23 ms per token, 65.66 tokens per second) 6.04.683.875 I slot print_timing: id 0 | task 21004 | total time = 2803.65 ms / 521 tokens 6.04.683.876 I slot print_timing: id 0 | task 21004 | graphs reused = 20173 6.04.683.876 I slot print_timing: id 0 | task 21004 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.683.909 I slot release: id 0 | task 21004 | stop processing: n_tokens = 552, truncated = 0 6.04.710.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 552, t_last = 364590152 6.04.710.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.061 MiB) 6.04.772.659 I slot launch_slot_: id 0 | task 21183 | processing task, is_child = 0 6.07.113.294 I slot print_timing: id 0 | task 21183 | prompt eval time = 137.93 ms / 320 tokens ( 0.43 ms per token, 2320.10 tokens per second) 6.07.113.300 I slot print_timing: id 0 | task 21183 | eval time = 2202.69 ms / 146 tokens ( 15.19 ms per token, 65.83 tokens per second) 6.07.113.301 I slot print_timing: id 0 | task 21183 | total time = 2340.62 ms / 466 tokens 6.07.113.302 I slot print_timing: id 0 | task 21183 | graphs reused = 20317 6.07.113.303 I slot print_timing: id 0 | task 21183 | graph reallocs = 0 / 0 (same size) / (changed size) 6.07.113.332 I slot release: id 0 | task 21183 | stop processing: n_tokens = 497, truncated = 0 6.07.117.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 497, t_last = 367019575 6.07.117.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.867 MiB) 6.07.175.805 I slot launch_slot_: id 0 | task 21332 | processing task, is_child = 0 6.08.191.230 I slot print_timing: id 0 | task 21332 | prompt eval time = 131.48 ms / 297 tokens ( 0.44 ms per token, 2258.88 tokens per second) 6.08.191.236 I slot print_timing: id 0 | task 21332 | eval time = 883.93 ms / 59 tokens ( 15.24 ms per token, 65.62 tokens per second) 6.08.191.237 I slot print_timing: id 0 | task 21332 | total time = 1015.41 ms / 356 tokens 6.08.191.239 I slot print_timing: id 0 | task 21332 | graphs reused = 20374 6.08.191.240 I slot print_timing: id 0 | task 21332 | graph reallocs = 0 / 0 (same size) / (changed size) 6.08.191.267 I slot release: id 0 | task 21332 | stop processing: n_tokens = 387, truncated = 0 6.08.206.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 368097510 6.08.207.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 6.08.262.197 I slot launch_slot_: id 0 | task 21394 | processing task, is_child = 0 6.11.412.132 I slot print_timing: id 0 | task 21394 | n_gen = 199, tg = 65.75 t/s, tg_3s = 66.08 t/s 6.11.700.286 I slot print_timing: id 0 | task 21394 | prompt eval time = 138.36 ms / 343 tokens ( 0.40 ms per token, 2479.00 tokens per second) 6.11.700.292 I slot print_timing: id 0 | task 21394 | eval time = 3299.71 ms / 218 tokens ( 15.21 ms per token, 65.76 tokens per second) 6.11.700.293 I slot print_timing: id 0 | task 21394 | total time = 3438.07 ms / 561 tokens 6.11.700.294 I slot print_timing: id 0 | task 21394 | graphs reused = 20589 6.11.700.295 I slot print_timing: id 0 | task 21394 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.700.323 I slot release: id 0 | task 21394 | stop processing: n_tokens = 592, truncated = 0 6.11.724.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 371606566 6.11.765.874 I slot launch_slot_: id 0 | task 21615 | processing task, is_child = 0 6.14.757.973 I slot print_timing: id 0 | task 21615 | prompt eval time = 144.00 ms / 371 tokens ( 0.39 ms per token, 2576.39 tokens per second) 6.14.757.978 I slot print_timing: id 0 | task 21615 | eval time = 2848.08 ms / 188 tokens ( 15.23 ms per token, 65.66 tokens per second) 6.14.757.980 I slot print_timing: id 0 | task 21615 | total time = 2992.08 ms / 559 tokens 6.14.757.980 I slot print_timing: id 0 | task 21615 | graphs reused = 20774 6.14.757.981 I slot print_timing: id 0 | task 21615 | graph reallocs = 0 / 0 (same size) / (changed size) 6.14.758.014 I slot release: id 0 | task 21615 | stop processing: n_tokens = 590, truncated = 0 6.14.784.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 590, t_last = 374664257 6.14.784.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.678 MiB) 6.14.846.087 I slot launch_slot_: id 0 | task 21806 | processing task, is_child = 0 6.17.976.018 I slot print_timing: id 0 | task 21806 | prompt eval time = 133.93 ms / 292 tokens ( 0.46 ms per token, 2180.31 tokens per second) 6.17.976.024 I slot print_timing: id 0 | task 21806 | eval time = 2995.99 ms / 198 tokens ( 15.21 ms per token, 65.75 tokens per second) 6.17.976.025 I slot print_timing: id 0 | task 21806 | total time = 3129.91 ms / 490 tokens 6.17.976.027 I slot print_timing: id 0 | task 21806 | graphs reused = 20969 6.17.976.028 I slot print_timing: id 0 | task 21806 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.976.051 I slot release: id 0 | task 21806 | stop processing: n_tokens = 521, truncated = 0 6.17.995.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 377882295 6.17.995.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.118 MiB) 6.18.057.166 I slot launch_slot_: id 0 | task 22007 | processing task, is_child = 0 6.19.860.071 I slot print_timing: id 0 | task 22007 | prompt eval time = 131.40 ms / 301 tokens ( 0.44 ms per token, 2290.77 tokens per second) 6.19.860.076 I slot print_timing: id 0 | task 22007 | eval time = 1671.49 ms / 111 tokens ( 15.20 ms per token, 65.81 tokens per second) 6.19.860.077 I slot print_timing: id 0 | task 22007 | total time = 1802.89 ms / 412 tokens 6.19.860.078 I slot print_timing: id 0 | task 22007 | graphs reused = 21078 6.19.860.079 I slot print_timing: id 0 | task 22007 | graph reallocs = 0 / 0 (same size) / (changed size) 6.19.860.106 I slot release: id 0 | task 22007 | stop processing: n_tokens = 443, truncated = 0 6.19.887.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 379766349 6.19.887.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.125 MiB) 6.19.944.951 I slot launch_slot_: id 0 | task 22121 | processing task, is_child = 0 6.22.127.129 I slot print_timing: id 0 | task 22121 | prompt eval time = 132.24 ms / 303 tokens ( 0.44 ms per token, 2291.34 tokens per second) 6.22.127.134 I slot print_timing: id 0 | task 22121 | eval time = 2049.92 ms / 136 tokens ( 15.18 ms per token, 65.86 tokens per second) 6.22.127.135 I slot print_timing: id 0 | task 22121 | total time = 2182.16 ms / 439 tokens 6.22.127.136 I slot print_timing: id 0 | task 22121 | graphs reused = 21212 6.22.127.136 I slot print_timing: id 0 | task 22121 | graph reallocs = 0 / 0 (same size) / (changed size) 6.22.127.162 I slot release: id 0 | task 22121 | stop processing: n_tokens = 470, truncated = 0 6.22.143.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 382033406 6.22.143.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.907 MiB) 6.22.200.761 I slot launch_slot_: id 0 | task 22260 | processing task, is_child = 0 6.24.999.709 I slot print_timing: id 0 | task 22260 | prompt eval time = 137.32 ms / 321 tokens ( 0.43 ms per token, 2337.61 tokens per second) 6.24.999.715 I slot print_timing: id 0 | task 22260 | eval time = 2661.61 ms / 176 tokens ( 15.21 ms per token, 65.75 tokens per second) 6.24.999.716 I slot print_timing: id 0 | task 22260 | total time = 2798.93 ms / 497 tokens 6.24.999.717 I slot print_timing: id 0 | task 22260 | graphs reused = 21385 6.24.999.718 I slot print_timing: id 0 | task 22260 | graph reallocs = 0 / 0 (same size) / (changed size) 6.24.999.748 I slot release: id 0 | task 22260 | stop processing: n_tokens = 528, truncated = 0 6.25.027.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 528, t_last = 384905991 6.25.027.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.110 MiB) 6.25.084.577 I slot launch_slot_: id 0 | task 22439 | processing task, is_child = 0 6.26.242.166 I slot print_timing: id 0 | task 22439 | prompt eval time = 137.61 ms / 322 tokens ( 0.43 ms per token, 2339.96 tokens per second) 6.26.242.171 I slot print_timing: id 0 | task 22439 | eval time = 1019.96 ms / 68 tokens ( 15.22 ms per token, 65.69 tokens per second) 6.26.242.172 I slot print_timing: id 0 | task 22439 | total time = 1157.57 ms / 390 tokens 6.26.242.173 I slot print_timing: id 0 | task 22439 | graphs reused = 21451 6.26.242.174 I slot print_timing: id 0 | task 22439 | graph reallocs = 0 / 0 (same size) / (changed size) 6.26.242.202 I slot release: id 0 | task 22439 | stop processing: n_tokens = 421, truncated = 0 6.26.258.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 386148445 6.26.258.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.516 MiB) 6.26.313.842 I slot launch_slot_: id 0 | task 22510 | processing task, is_child = 0 6.28.290.819 I slot print_timing: id 0 | task 22510 | prompt eval time = 137.51 ms / 323 tokens ( 0.43 ms per token, 2348.92 tokens per second) 6.28.290.824 I slot print_timing: id 0 | task 22510 | eval time = 1839.45 ms / 122 tokens ( 15.20 ms per token, 65.78 tokens per second) 6.28.290.825 I slot print_timing: id 0 | task 22510 | total time = 1976.96 ms / 445 tokens 6.28.290.826 I slot print_timing: id 0 | task 22510 | graphs reused = 21571 6.28.290.826 I slot print_timing: id 0 | task 22510 | graph reallocs = 0 / 0 (same size) / (changed size) 6.28.290.852 I slot release: id 0 | task 22510 | stop processing: n_tokens = 476, truncated = 0 6.28.312.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 388197095 6.28.312.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.139 MiB) 6.28.368.591 I slot launch_slot_: id 0 | task 22635 | processing task, is_child = 0 6.31.519.911 I slot print_timing: id 0 | task 22635 | n_gen = 199, tg = 65.77 t/s, tg_3s = 66.10 t/s 6.34.522.527 I slot print_timing: id 0 | task 22635 | n_gen = 397, tg = 65.85 t/s, tg_3s = 65.94 t/s 6.34.613.649 I slot print_timing: id 0 | task 22635 | prompt eval time = 140.70 ms / 321 tokens ( 0.44 ms per token, 2281.39 tokens per second) 6.34.613.654 I slot print_timing: id 0 | task 22635 | eval time = 6104.34 ms / 403 tokens ( 15.18 ms per token, 65.85 tokens per second) 6.34.613.655 I slot print_timing: id 0 | task 22635 | total time = 6245.04 ms / 724 tokens 6.34.613.656 I slot print_timing: id 0 | task 22635 | graphs reused = 21971 6.34.613.657 I slot print_timing: id 0 | task 22635 | graph reallocs = 0 / 0 (same size) / (changed size) 6.34.613.685 I slot release: id 0 | task 22635 | stop processing: n_tokens = 755, truncated = 0 6.34.653.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 755, t_last = 394519928 6.34.653.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.640 MiB) 6.34.711.553 I slot launch_slot_: id 0 | task 23041 | processing task, is_child = 0 6.35.729.957 I slot print_timing: id 0 | task 23041 | prompt eval time = 137.13 ms / 322 tokens ( 0.43 ms per token, 2348.10 tokens per second) 6.35.729.963 I slot print_timing: id 0 | task 23041 | eval time = 881.25 ms / 58 tokens ( 15.46 ms per token, 64.68 tokens per second) 6.35.729.965 I slot print_timing: id 0 | task 23041 | total time = 1018.38 ms / 380 tokens 6.35.729.965 I slot print_timing: id 0 | task 23041 | graphs reused = 22027 6.35.729.966 I slot print_timing: id 0 | task 23041 | graph reallocs = 0 / 0 (same size) / (changed size) 6.35.730.000 I slot release: id 0 | task 23041 | stop processing: n_tokens = 411, truncated = 0 6.35.735.368 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 395636243 6.35.735.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.608 MiB) 6.35.792.922 I slot launch_slot_: id 0 | task 23102 | processing task, is_child = 0 6.36.815.664 I slot print_timing: id 0 | task 23102 | prompt eval time = 138.61 ms / 337 tokens ( 0.41 ms per token, 2431.21 tokens per second) 6.36.815.670 I slot print_timing: id 0 | task 23102 | eval time = 884.11 ms / 59 tokens ( 15.24 ms per token, 65.60 tokens per second) 6.36.815.671 I slot print_timing: id 0 | task 23102 | total time = 1022.72 ms / 396 tokens 6.36.815.673 I slot print_timing: id 0 | task 23102 | graphs reused = 22084 6.36.815.673 I slot print_timing: id 0 | task 23102 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.815.701 I slot release: id 0 | task 23102 | stop processing: n_tokens = 427, truncated = 0 6.36.820.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 396721944 6.36.820.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.669 MiB) 6.36.879.642 I slot launch_slot_: id 0 | task 23164 | processing task, is_child = 0 6.38.043.385 I slot print_timing: id 0 | task 23164 | prompt eval time = 139.63 ms / 325 tokens ( 0.43 ms per token, 2327.50 tokens per second) 6.38.043.391 I slot print_timing: id 0 | task 23164 | eval time = 1024.09 ms / 66 tokens ( 15.76 ms per token, 63.47 tokens per second) 6.38.043.392 I slot print_timing: id 0 | task 23164 | total time = 1163.72 ms / 391 tokens 6.38.043.393 I slot print_timing: id 0 | task 23164 | graphs reused = 22148 6.38.043.394 I slot print_timing: id 0 | task 23164 | graph reallocs = 0 / 0 (same size) / (changed size) 6.38.043.421 I slot release: id 0 | task 23164 | stop processing: n_tokens = 422, truncated = 0 6.38.073.143 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 397949665 6.38.073.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 6.38.129.778 I slot launch_slot_: id 0 | task 23233 | processing task, is_child = 0 6.41.274.799 I slot print_timing: id 0 | task 23233 | n_gen = 194, tg = 64.27 t/s, tg_3s = 64.60 t/s 6.41.525.779 I slot print_timing: id 0 | task 23233 | prompt eval time = 142.01 ms / 331 tokens ( 0.43 ms per token, 2330.81 tokens per second) 6.41.525.784 I slot print_timing: id 0 | task 23233 | eval time = 3253.97 ms / 210 tokens ( 15.57 ms per token, 64.23 tokens per second) 6.41.525.785 I slot print_timing: id 0 | task 23233 | total time = 3395.98 ms / 541 tokens 6.41.525.786 I slot print_timing: id 0 | task 23233 | graphs reused = 22355 6.41.525.787 I slot print_timing: id 0 | task 23233 | graph reallocs = 0 / 0 (same size) / (changed size) 6.41.525.817 I slot release: id 0 | task 23233 | stop processing: n_tokens = 572, truncated = 0 6.41.530.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 401432060 6.41.530.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 6.41.588.972 I slot launch_slot_: id 0 | task 23446 | processing task, is_child = 0 6.43.764.404 I slot print_timing: id 0 | task 23446 | prompt eval time = 142.14 ms / 336 tokens ( 0.42 ms per token, 2363.90 tokens per second) 6.43.764.409 I slot print_timing: id 0 | task 23446 | eval time = 2033.28 ms / 130 tokens ( 15.76 ms per token, 63.44 tokens per second) 6.43.764.410 I slot print_timing: id 0 | task 23446 | total time = 2175.41 ms / 466 tokens 6.43.764.411 I slot print_timing: id 0 | task 23446 | graphs reused = 22483 6.43.764.412 I slot print_timing: id 0 | task 23446 | graph reallocs = 0 / 0 (same size) / (changed size) 6.43.764.440 I slot release: id 0 | task 23446 | stop processing: n_tokens = 497, truncated = 0 6.43.769.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 497, t_last = 403670684 6.43.769.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.512 MiB) 6.43.828.748 I slot launch_slot_: id 0 | task 23579 | processing task, is_child = 0 6.44.654.546 I slot print_timing: id 0 | task 23579 | prompt eval time = 138.90 ms / 349 tokens ( 0.40 ms per token, 2512.65 tokens per second) 6.44.654.551 I slot print_timing: id 0 | task 23579 | eval time = 686.88 ms / 46 tokens ( 15.26 ms per token, 65.51 tokens per second) 6.44.654.552 I slot print_timing: id 0 | task 23579 | total time = 825.78 ms / 395 tokens 6.44.654.553 I slot print_timing: id 0 | task 23579 | graphs reused = 22527 6.44.654.554 I slot print_timing: id 0 | task 23579 | graph reallocs = 0 / 0 (same size) / (changed size) 6.44.654.581 I slot release: id 0 | task 23579 | stop processing: n_tokens = 426, truncated = 0 6.44.672.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 404560824 6.44.672.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.640 MiB) 6.44.731.905 I slot launch_slot_: id 0 | task 23628 | processing task, is_child = 0 6.47.884.418 I slot print_timing: id 0 | task 23628 | n_gen = 193, tg = 63.69 t/s, tg_3s = 64.03 t/s 6.50.899.915 I slot print_timing: id 0 | task 23628 | n_gen = 388, tg = 64.18 t/s, tg_3s = 64.67 t/s 6.52.078.299 I slot print_timing: id 0 | task 23628 | prompt eval time = 138.10 ms / 336 tokens ( 0.41 ms per token, 2432.97 tokens per second) 6.52.078.304 I slot print_timing: id 0 | task 23628 | eval time = 7208.27 ms / 463 tokens ( 15.60 ms per token, 64.09 tokens per second) 6.52.078.305 I slot print_timing: id 0 | task 23628 | total time = 7346.37 ms / 799 tokens 6.52.078.306 I slot print_timing: id 0 | task 23628 | graphs reused = 22986 6.52.078.307 I slot print_timing: id 0 | task 23628 | graph reallocs = 0 / 0 (same size) / (changed size) 6.52.078.336 I slot release: id 0 | task 23628 | stop processing: n_tokens = 830, truncated = 0 6.52.100.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 830, t_last = 411984579 6.52.100.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.766 MiB) 6.52.162.489 I slot launch_slot_: id 0 | task 24094 | processing task, is_child = 0 6.55.310.450 I slot print_timing: id 0 | task 24094 | n_gen = 194, tg = 64.14 t/s, tg_3s = 64.47 t/s 6.56.637.251 I slot print_timing: id 0 | task 24094 | prompt eval time = 138.78 ms / 349 tokens ( 0.40 ms per token, 2514.77 tokens per second) 6.56.637.256 I slot print_timing: id 0 | task 24094 | eval time = 4335.96 ms / 280 tokens ( 15.54 ms per token, 64.35 tokens per second) 6.56.637.257 I slot print_timing: id 0 | task 24094 | total time = 4474.74 ms / 629 tokens 6.56.637.258 I slot print_timing: id 0 | task 24094 | graphs reused = 23263 6.56.637.259 I slot print_timing: id 0 | task 24094 | graph reallocs = 0 / 0 (same size) / (changed size) 6.56.637.287 I slot release: id 0 | task 24094 | stop processing: n_tokens = 660, truncated = 0 6.56.681.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 416543530 6.56.681.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.703 MiB) 6.56.742.162 I slot launch_slot_: id 0 | task 24377 | processing task, is_child = 0 6.57.984.128 I slot print_timing: id 0 | task 24377 | prompt eval time = 138.81 ms / 349 tokens ( 0.40 ms per token, 2514.32 tokens per second) 6.57.984.133 I slot print_timing: id 0 | task 24377 | eval time = 1103.14 ms / 72 tokens ( 15.54 ms per token, 64.36 tokens per second) 6.57.984.134 I slot print_timing: id 0 | task 24377 | total time = 1241.94 ms / 421 tokens 6.57.984.135 I slot print_timing: id 0 | task 24377 | graphs reused = 23333 6.57.984.136 I slot print_timing: id 0 | task 24377 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.984.165 I slot release: id 0 | task 24377 | stop processing: n_tokens = 452, truncated = 0 6.57.988.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 417890408 6.57.988.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.014 MiB) 6.58.048.303 I slot launch_slot_: id 0 | task 24452 | processing task, is_child = 0 7.00.940.978 I slot print_timing: id 0 | task 24452 | prompt eval time = 148.52 ms / 385 tokens ( 0.39 ms per token, 2592.21 tokens per second) 7.00.940.984 I slot print_timing: id 0 | task 24452 | eval time = 2744.13 ms / 177 tokens ( 15.59 ms per token, 64.14 tokens per second) 7.00.940.985 I slot print_timing: id 0 | task 24452 | total time = 2892.65 ms / 562 tokens 7.00.940.986 I slot print_timing: id 0 | task 24452 | graphs reused = 23507 7.00.940.987 I slot print_timing: id 0 | task 24452 | graph reallocs = 0 / 0 (same size) / (changed size) 7.00.941.017 I slot release: id 0 | task 24452 | stop processing: n_tokens = 593, truncated = 0 7.00.956.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 420847260 7.00.956.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.170 MiB) 7.01.017.154 I slot launch_slot_: id 0 | task 24632 | processing task, is_child = 0 7.02.266.764 I slot print_timing: id 0 | task 24632 | prompt eval time = 137.99 ms / 328 tokens ( 0.42 ms per token, 2377.04 tokens per second) 7.02.266.770 I slot print_timing: id 0 | task 24632 | eval time = 1111.60 ms / 72 tokens ( 15.66 ms per token, 63.87 tokens per second) 7.02.266.771 I slot print_timing: id 0 | task 24632 | total time = 1249.59 ms / 400 tokens 7.02.266.772 I slot print_timing: id 0 | task 24632 | graphs reused = 23577 7.02.266.773 I slot print_timing: id 0 | task 24632 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.266.801 I slot release: id 0 | task 24632 | stop processing: n_tokens = 431, truncated = 0