$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-Q5_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.092.491 I srv llama_server: initializing ... 0.00.092.498 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.092.610 I srv init_listene: The UI is disabled 0.00.092.612 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.092.725 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) 0.00.110.059 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-Q5_K_M.gguf' 0.01.036.400 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.01.036.415 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.01.036.441 W model has unused tensor blk.32.attn_q.weight (size = 35651584 bytes) -- ignoring 0.01.036.450 W model has unused tensor blk.32.attn_k.weight (size = 4456448 bytes) -- ignoring 0.01.036.460 W model has unused tensor blk.32.attn_v.weight (size = 4456448 bytes) -- ignoring 0.01.036.493 W model has unused tensor blk.32.attn_output.weight (size = 17825792 bytes) -- ignoring 0.01.036.503 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.01.036.512 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.01.036.521 W model has unused tensor blk.32.ffn_gate.weight (size = 53477376 bytes) -- ignoring 0.01.036.530 W model has unused tensor blk.32.ffn_down.weight (size = 53477376 bytes) -- ignoring 0.01.036.539 W model has unused tensor blk.32.ffn_up.weight (size = 53477376 bytes) -- ignoring 0.01.036.549 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring 0.01.036.559 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.01.036.569 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.01.036.597 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.03.145.662 I cmn init: llama threadpool init, n_threads = 8 0.03.233.822 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.03.238.525 I srv llama_server: model loaded 0.03.238.530 I srv llama_server: listening on http://127.0.0.1:8089 0.04.551.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.551.825 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.400.202 I slot print_timing: id 0 | task 0 | prompt eval time = 237.28 ms / 368 tokens ( 0.64 ms per token, 1550.92 tokens per second) 0.05.400.208 I slot print_timing: id 0 | task 0 | eval time = 611.08 ms / 53 tokens ( 11.75 ms per token, 85.10 tokens per second) 0.05.400.209 I slot print_timing: id 0 | task 0 | total time = 848.36 ms / 421 tokens 0.05.400.216 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.400.217 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.400.249 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.416.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5309767 0.05.443.976 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.06.052.505 I slot print_timing: id 0 | task 56 | prompt eval time = 127.41 ms / 322 tokens ( 0.40 ms per token, 2527.37 tokens per second) 0.06.052.510 I slot print_timing: id 0 | task 56 | eval time = 481.11 ms / 42 tokens ( 11.73 ms per token, 85.22 tokens per second) 0.06.052.511 I slot print_timing: id 0 | task 56 | total time = 608.51 ms / 364 tokens 0.06.052.512 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.06.052.513 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.052.538 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.06.072.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5962055 0.06.099.690 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.06.710.312 I slot print_timing: id 0 | task 101 | prompt eval time = 130.31 ms / 365 tokens ( 0.36 ms per token, 2800.99 tokens per second) 0.06.710.317 I slot print_timing: id 0 | task 101 | eval time = 480.29 ms / 42 tokens ( 11.71 ms per token, 85.36 tokens per second) 0.06.710.319 I slot print_timing: id 0 | task 101 | total time = 610.61 ms / 407 tokens 0.06.710.319 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.06.710.320 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.710.348 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.06.729.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6619865 0.06.756.421 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.07.381.897 I slot print_timing: id 0 | task 146 | prompt eval time = 134.61 ms / 397 tokens ( 0.34 ms per token, 2949.35 tokens per second) 0.07.381.903 I slot print_timing: id 0 | task 146 | eval time = 490.85 ms / 43 tokens ( 11.69 ms per token, 85.57 tokens per second) 0.07.381.904 I slot print_timing: id 0 | task 146 | total time = 625.46 ms / 440 tokens 0.07.381.905 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.07.381.906 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.381.935 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.07.397.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.07.424.101 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.08.204.588 I slot print_timing: id 0 | task 192 | prompt eval time = 135.03 ms / 383 tokens ( 0.35 ms per token, 2836.43 tokens per second) 0.08.204.594 I slot print_timing: id 0 | task 192 | eval time = 645.44 ms / 55 tokens ( 11.95 ms per token, 83.66 tokens per second) 0.08.204.595 I slot print_timing: id 0 | task 192 | total time = 780.47 ms / 438 tokens 0.08.204.596 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.08.204.596 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.204.624 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.08.224.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8114142 0.08.250.909 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.09.020.801 I slot print_timing: id 0 | task 250 | prompt eval time = 135.85 ms / 372 tokens ( 0.37 ms per token, 2738.27 tokens per second) 0.09.020.807 I slot print_timing: id 0 | task 250 | eval time = 634.02 ms / 55 tokens ( 11.74 ms per token, 85.17 tokens per second) 0.09.020.808 I slot print_timing: id 0 | task 250 | total time = 769.87 ms / 427 tokens 0.09.020.809 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.09.020.809 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.020.838 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.09.024.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8930355 0.09.057.860 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.09.844.208 I slot print_timing: id 0 | task 308 | prompt eval time = 151.01 ms / 422 tokens ( 0.36 ms per token, 2794.42 tokens per second) 0.09.844.214 I slot print_timing: id 0 | task 308 | eval time = 635.32 ms / 55 tokens ( 11.77 ms per token, 85.00 tokens per second) 0.09.844.215 I slot print_timing: id 0 | task 308 | total time = 786.33 ms / 477 tokens 0.09.844.216 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.09.844.217 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.844.246 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.09.867.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 9753764 0.09.893.310 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.10.883.095 I slot print_timing: id 0 | task 366 | prompt eval time = 153.05 ms / 470 tokens ( 0.33 ms per token, 3070.87 tokens per second) 0.10.883.101 I slot print_timing: id 0 | task 366 | eval time = 836.72 ms / 72 tokens ( 11.78 ms per token, 84.86 tokens per second) 0.10.883.102 I slot print_timing: id 0 | task 366 | total time = 989.77 ms / 542 tokens 0.10.883.103 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.10.883.103 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.883.134 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.10.911.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 10792651 0.10.947.525 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.11.614.749 I slot print_timing: id 0 | task 441 | prompt eval time = 127.17 ms / 345 tokens ( 0.37 ms per token, 2712.90 tokens per second) 0.11.614.755 I slot print_timing: id 0 | task 441 | eval time = 540.04 ms / 47 tokens ( 11.74 ms per token, 85.18 tokens per second) 0.11.614.756 I slot print_timing: id 0 | task 441 | total time = 667.21 ms / 392 tokens 0.11.614.757 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.11.614.758 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.614.786 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.11.643.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 11524303 0.11.668.666 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.12.272.090 I slot print_timing: id 0 | task 491 | prompt eval time = 134.38 ms / 364 tokens ( 0.37 ms per token, 2708.64 tokens per second) 0.12.272.095 I slot print_timing: id 0 | task 491 | eval time = 469.02 ms / 41 tokens ( 11.73 ms per token, 85.28 tokens per second) 0.12.272.097 I slot print_timing: id 0 | task 491 | total time = 603.40 ms / 405 tokens 0.12.272.098 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.12.272.098 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.272.125 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.12.296.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 12181642 0.12.322.486 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.13.201.619 I slot print_timing: id 0 | task 535 | prompt eval time = 134.01 ms / 376 tokens ( 0.36 ms per token, 2805.74 tokens per second) 0.13.201.625 I slot print_timing: id 0 | task 535 | eval time = 745.10 ms / 62 tokens ( 12.21 ms per token, 81.87 tokens per second) 0.13.201.627 I slot print_timing: id 0 | task 535 | total time = 879.11 ms / 438 tokens 0.13.201.628 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.13.201.629 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.201.658 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.13.219.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13111175 0.13.244.794 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.13.929.358 I slot print_timing: id 0 | task 600 | prompt eval time = 137.49 ms / 412 tokens ( 0.33 ms per token, 2996.49 tokens per second) 0.13.929.364 I slot print_timing: id 0 | task 600 | eval time = 547.05 ms / 47 tokens ( 11.89 ms per token, 84.09 tokens per second) 0.13.929.366 I slot print_timing: id 0 | task 600 | total time = 684.54 ms / 459 tokens 0.13.929.368 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.13.929.369 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.929.404 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.13.947.593 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 13838921 0.13.978.298 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.14.832.721 I slot print_timing: id 0 | task 650 | prompt eval time = 137.20 ms / 376 tokens ( 0.36 ms per token, 2740.54 tokens per second) 0.14.832.727 I slot print_timing: id 0 | task 650 | eval time = 717.21 ms / 62 tokens ( 11.76 ms per token, 85.05 tokens per second) 0.14.832.728 I slot print_timing: id 0 | task 650 | total time = 854.40 ms / 438 tokens 0.14.832.729 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.14.832.730 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.832.757 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.14.854.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 14742274 0.14.882.267 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.15.615.653 I slot print_timing: id 0 | task 715 | prompt eval time = 133.27 ms / 378 tokens ( 0.35 ms per token, 2836.39 tokens per second) 0.15.615.658 I slot print_timing: id 0 | task 715 | eval time = 600.10 ms / 52 tokens ( 11.77 ms per token, 84.99 tokens per second) 0.15.615.659 I slot print_timing: id 0 | task 715 | total time = 733.37 ms / 430 tokens 0.15.615.660 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.15.615.661 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.615.689 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.15.631.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 15525206 0.15.657.552 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.16.486.574 I slot print_timing: id 0 | task 770 | prompt eval time = 132.42 ms / 367 tokens ( 0.36 ms per token, 2771.55 tokens per second) 0.16.486.580 I slot print_timing: id 0 | task 770 | eval time = 696.58 ms / 58 tokens ( 12.22 ms per token, 81.83 tokens per second) 0.16.486.582 I slot print_timing: id 0 | task 770 | total time = 829.00 ms / 425 tokens 0.16.486.583 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.16.486.583 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.486.619 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.16.506.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 16396136 0.16.532.447 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.17.259.798 I slot print_timing: id 0 | task 831 | prompt eval time = 132.39 ms / 347 tokens ( 0.38 ms per token, 2621.08 tokens per second) 0.17.259.804 I slot print_timing: id 0 | task 831 | eval time = 594.94 ms / 51 tokens ( 11.90 ms per token, 84.04 tokens per second) 0.17.259.805 I slot print_timing: id 0 | task 831 | total time = 727.33 ms / 398 tokens 0.17.259.806 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.17.259.807 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.259.837 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.17.285.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 17169355 0.17.323.207 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.17.922.529 I slot print_timing: id 0 | task 885 | prompt eval time = 129.23 ms / 369 tokens ( 0.35 ms per token, 2855.46 tokens per second) 0.17.922.535 I slot print_timing: id 0 | task 885 | eval time = 470.08 ms / 41 tokens ( 11.75 ms per token, 85.09 tokens per second) 0.17.922.536 I slot print_timing: id 0 | task 885 | total time = 599.30 ms / 410 tokens 0.17.922.536 I slot print_timing: id 0 | task 885 | graphs reused = 844 0.17.922.537 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.922.564 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 0.17.940.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 17832081 0.17.966.331 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 0.18.570.388 I slot print_timing: id 0 | task 929 | prompt eval time = 133.55 ms / 352 tokens ( 0.38 ms per token, 2635.74 tokens per second) 0.18.570.396 I slot print_timing: id 0 | task 929 | eval time = 470.49 ms / 41 tokens ( 11.76 ms per token, 85.02 tokens per second) 0.18.570.397 I slot print_timing: id 0 | task 929 | total time = 604.03 ms / 393 tokens 0.18.570.398 I slot print_timing: id 0 | task 929 | graphs reused = 883 0.18.570.399 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.570.427 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 0.18.593.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 18479945 0.18.621.232 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 0.19.211.300 I slot print_timing: id 0 | task 973 | prompt eval time = 129.15 ms / 349 tokens ( 0.37 ms per token, 2702.37 tokens per second) 0.19.211.306 I slot print_timing: id 0 | task 973 | eval time = 460.90 ms / 40 tokens ( 11.82 ms per token, 84.62 tokens per second) 0.19.211.307 I slot print_timing: id 0 | task 973 | total time = 590.05 ms / 389 tokens 0.19.211.308 I slot print_timing: id 0 | task 973 | graphs reused = 921 0.19.211.308 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.211.335 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 0.19.215.265 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 19120852 0.19.246.158 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.20.138.423 I slot print_timing: id 0 | task 1016 | prompt eval time = 134.42 ms / 384 tokens ( 0.35 ms per token, 2856.70 tokens per second) 0.20.138.430 I slot print_timing: id 0 | task 1016 | eval time = 757.83 ms / 63 tokens ( 12.22 ms per token, 81.81 tokens per second) 0.20.138.431 I slot print_timing: id 0 | task 1016 | total time = 892.25 ms / 447 tokens 0.20.138.432 I slot print_timing: id 0 | task 1016 | graphs reused = 982 0.20.138.432 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.138.462 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 0.20.164.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 20047979 0.20.191.453 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.20.940.738 I slot print_timing: id 0 | task 1082 | prompt eval time = 129.06 ms / 356 tokens ( 0.36 ms per token, 2758.45 tokens per second) 0.20.940.744 I slot print_timing: id 0 | task 1082 | eval time = 620.21 ms / 54 tokens ( 11.70 ms per token, 85.46 tokens per second) 0.20.940.745 I slot print_timing: id 0 | task 1082 | total time = 749.27 ms / 410 tokens 0.20.940.746 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 0.20.940.747 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.940.775 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 0.20.956.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 20850292 0.20.982.297 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 0.21.927.810 I slot print_timing: id 0 | task 1139 | prompt eval time = 137.81 ms / 410 tokens ( 0.34 ms per token, 2975.22 tokens per second) 0.21.927.816 I slot print_timing: id 0 | task 1139 | eval time = 807.69 ms / 70 tokens ( 11.71 ms per token, 85.43 tokens per second) 0.21.927.817 I slot print_timing: id 0 | task 1139 | total time = 945.49 ms / 480 tokens 0.21.927.818 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 0.21.927.818 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.927.847 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 0.21.953.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 21837364 0.21.980.032 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 0.22.781.502 I slot print_timing: id 0 | task 1212 | prompt eval time = 134.52 ms / 385 tokens ( 0.35 ms per token, 2862.07 tokens per second) 0.22.781.508 I slot print_timing: id 0 | task 1212 | eval time = 666.93 ms / 58 tokens ( 11.70 ms per token, 85.47 tokens per second) 0.22.781.509 I slot print_timing: id 0 | task 1212 | total time = 801.45 ms / 443 tokens 0.22.781.510 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 0.22.781.511 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.781.542 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 0.22.785.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 22691060 0.22.812.674 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.23.766.160 I slot print_timing: id 0 | task 1273 | prompt eval time = 137.22 ms / 395 tokens ( 0.35 ms per token, 2878.65 tokens per second) 0.23.766.166 I slot print_timing: id 0 | task 1273 | eval time = 816.25 ms / 71 tokens ( 11.66 ms per token, 85.76 tokens per second) 0.23.766.167 I slot print_timing: id 0 | task 1273 | total time = 953.46 ms / 466 tokens 0.23.766.167 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.23.766.168 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.766.200 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.23.795.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 23675717 0.23.820.988 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.24.670.018 I slot print_timing: id 0 | task 1347 | prompt eval time = 136.72 ms / 430 tokens ( 0.32 ms per token, 3145.11 tokens per second) 0.24.670.024 I slot print_timing: id 0 | task 1347 | eval time = 712.29 ms / 62 tokens ( 11.68 ms per token, 85.64 tokens per second) 0.24.670.025 I slot print_timing: id 0 | task 1347 | total time = 849.01 ms / 492 tokens 0.24.670.025 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 0.24.670.027 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.670.058 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 0.24.684.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 24579576 0.24.716.989 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 0.25.564.757 I slot print_timing: id 0 | task 1412 | prompt eval time = 136.15 ms / 392 tokens ( 0.35 ms per token, 2879.16 tokens per second) 0.25.564.762 I slot print_timing: id 0 | task 1412 | eval time = 711.60 ms / 62 tokens ( 11.67 ms per token, 85.72 tokens per second) 0.25.564.763 I slot print_timing: id 0 | task 1412 | total time = 847.75 ms / 454 tokens 0.25.564.764 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 0.25.564.765 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.564.792 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 0.25.586.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 25474309 0.25.614.381 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 0.26.339.145 I slot print_timing: id 0 | task 1477 | prompt eval time = 127.98 ms / 350 tokens ( 0.37 ms per token, 2734.82 tokens per second) 0.26.339.150 I slot print_timing: id 0 | task 1477 | eval time = 596.77 ms / 52 tokens ( 11.70 ms per token, 85.46 tokens per second) 0.26.339.151 I slot print_timing: id 0 | task 1477 | total time = 724.75 ms / 402 tokens 0.26.339.153 I slot print_timing: id 0 | task 1477 | graphs reused = 1397 0.26.339.153 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.339.180 I slot release: id 0 | task 1477 | stop processing: n_tokens = 401, truncated = 0 0.26.354.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 26248698 0.26.379.662 I slot launch_slot_: id 0 | task 1532 | processing task, is_child = 0 0.27.213.361 I slot print_timing: id 0 | task 1532 | prompt eval time = 133.12 ms / 380 tokens ( 0.35 ms per token, 2854.48 tokens per second) 0.27.213.366 I slot print_timing: id 0 | task 1532 | eval time = 700.56 ms / 61 tokens ( 11.68 ms per token, 85.65 tokens per second) 0.27.213.368 I slot print_timing: id 0 | task 1532 | total time = 833.68 ms / 441 tokens 0.27.213.368 I slot print_timing: id 0 | task 1532 | graphs reused = 1456 0.27.213.369 I slot print_timing: id 0 | task 1532 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.213.398 I slot release: id 0 | task 1532 | stop processing: n_tokens = 440, truncated = 0 0.27.227.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 27122915 0.27.256.804 I slot launch_slot_: id 0 | task 1596 | processing task, is_child = 0 0.28.355.217 I slot print_timing: id 0 | task 1596 | prompt eval time = 139.47 ms / 410 tokens ( 0.34 ms per token, 2939.64 tokens per second) 0.28.355.224 I slot print_timing: id 0 | task 1596 | eval time = 958.92 ms / 80 tokens ( 12.14 ms per token, 82.38 tokens per second) 0.28.355.225 I slot print_timing: id 0 | task 1596 | total time = 1098.39 ms / 490 tokens 0.28.355.225 I slot print_timing: id 0 | task 1596 | graphs reused = 1534 0.28.355.226 I slot print_timing: id 0 | task 1596 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.355.255 I slot release: id 0 | task 1596 | stop processing: n_tokens = 489, truncated = 0 0.28.380.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 28264772 0.28.410.540 I slot launch_slot_: id 0 | task 1679 | processing task, is_child = 0 0.29.329.564 I slot print_timing: id 0 | task 1679 | prompt eval time = 136.38 ms / 387 tokens ( 0.35 ms per token, 2837.70 tokens per second) 0.29.329.570 I slot print_timing: id 0 | task 1679 | eval time = 782.63 ms / 68 tokens ( 11.68 ms per token, 85.61 tokens per second) 0.29.329.571 I slot print_timing: id 0 | task 1679 | total time = 919.00 ms / 455 tokens 0.29.329.572 I slot print_timing: id 0 | task 1679 | graphs reused = 1600 0.29.329.572 I slot print_timing: id 0 | task 1679 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.329.601 I slot release: id 0 | task 1679 | stop processing: n_tokens = 454, truncated = 0 0.29.343.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 29239118 0.29.379.759 I slot launch_slot_: id 0 | task 1750 | processing task, is_child = 0 0.30.185.541 I slot print_timing: id 0 | task 1750 | prompt eval time = 126.89 ms / 358 tokens ( 0.35 ms per token, 2821.41 tokens per second) 0.30.185.547 I slot print_timing: id 0 | task 1750 | eval time = 678.88 ms / 59 tokens ( 11.70 ms per token, 85.44 tokens per second) 0.30.185.548 I slot print_timing: id 0 | task 1750 | total time = 805.76 ms / 417 tokens 0.30.185.548 I slot print_timing: id 0 | task 1750 | graphs reused = 1657 0.30.185.549 I slot print_timing: id 0 | task 1750 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.185.576 I slot release: id 0 | task 1750 | stop processing: n_tokens = 416, truncated = 0 0.30.207.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 30095094 0.30.243.553 I slot launch_slot_: id 0 | task 1812 | processing task, is_child = 0 0.31.045.123 I slot print_timing: id 0 | task 1812 | prompt eval time = 127.98 ms / 359 tokens ( 0.36 ms per token, 2805.15 tokens per second) 0.31.045.129 I slot print_timing: id 0 | task 1812 | eval time = 673.57 ms / 56 tokens ( 12.25 ms per token, 81.65 tokens per second) 0.31.045.130 I slot print_timing: id 0 | task 1812 | total time = 801.55 ms / 415 tokens 0.31.045.131 I slot print_timing: id 0 | task 1812 | graphs reused = 1711 0.31.045.132 I slot print_timing: id 0 | task 1812 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.045.165 I slot release: id 0 | task 1812 | stop processing: n_tokens = 414, truncated = 0 0.31.063.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 30954683 0.31.099.212 I slot launch_slot_: id 0 | task 1871 | processing task, is_child = 0 0.31.932.701 I slot print_timing: id 0 | task 1871 | prompt eval time = 132.72 ms / 387 tokens ( 0.34 ms per token, 2915.87 tokens per second) 0.31.932.706 I slot print_timing: id 0 | task 1871 | eval time = 700.75 ms / 61 tokens ( 11.68 ms per token, 85.62 tokens per second) 0.31.932.707 I slot print_timing: id 0 | task 1871 | total time = 833.47 ms / 448 tokens 0.31.932.708 I slot print_timing: id 0 | task 1871 | graphs reused = 1770 0.31.932.709 I slot print_timing: id 0 | task 1871 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.932.738 I slot release: id 0 | task 1871 | stop processing: n_tokens = 447, truncated = 0 0.31.952.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 31842255 0.31.990.214 I slot launch_slot_: id 0 | task 1935 | processing task, is_child = 0 0.32.826.338 I slot print_timing: id 0 | task 1935 | prompt eval time = 135.53 ms / 410 tokens ( 0.33 ms per token, 3025.07 tokens per second) 0.32.826.344 I slot print_timing: id 0 | task 1935 | eval time = 700.57 ms / 61 tokens ( 11.68 ms per token, 85.64 tokens per second) 0.32.826.345 I slot print_timing: id 0 | task 1935 | total time = 836.10 ms / 471 tokens 0.32.826.345 I slot print_timing: id 0 | task 1935 | graphs reused = 1829 0.32.826.346 I slot print_timing: id 0 | task 1935 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.826.375 I slot release: id 0 | task 1935 | stop processing: n_tokens = 470, truncated = 0 0.32.854.997 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 32735893 0.32.893.039 I slot launch_slot_: id 0 | task 1999 | processing task, is_child = 0 0.33.610.471 I slot print_timing: id 0 | task 1999 | prompt eval time = 131.31 ms / 351 tokens ( 0.37 ms per token, 2673.00 tokens per second) 0.33.610.476 I slot print_timing: id 0 | task 1999 | eval time = 586.10 ms / 50 tokens ( 11.96 ms per token, 83.60 tokens per second) 0.33.610.477 I slot print_timing: id 0 | task 1999 | total time = 717.41 ms / 401 tokens 0.33.610.478 I slot print_timing: id 0 | task 1999 | graphs reused = 1877 0.33.610.479 I slot print_timing: id 0 | task 1999 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.610.507 I slot release: id 0 | task 1999 | stop processing: n_tokens = 400, truncated = 0 0.33.636.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 33520024 0.33.670.949 I slot launch_slot_: id 0 | task 2052 | processing task, is_child = 0 0.36.422.189 I slot print_timing: id 0 | task 2052 | prompt eval time = 134.78 ms / 393 tokens ( 0.34 ms per token, 2915.80 tokens per second) 0.36.422.195 I slot print_timing: id 0 | task 2052 | eval time = 2616.44 ms / 224 tokens ( 11.73 ms per token, 85.23 tokens per second) 0.36.422.196 I slot print_timing: id 0 | task 2052 | total time = 2751.22 ms / 617 tokens 0.36.422.197 I slot print_timing: id 0 | task 2052 | graphs reused = 2098 0.36.422.198 I slot print_timing: id 0 | task 2052 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.422.227 I slot release: id 0 | task 2052 | stop processing: n_tokens = 616, truncated = 0 0.36.438.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 36331744 0.36.475.261 I slot launch_slot_: id 0 | task 2279 | processing task, is_child = 0 0.36.968.806 I slot print_timing: id 0 | task 2279 | prompt eval time = 127.91 ms / 321 tokens ( 0.40 ms per token, 2509.66 tokens per second) 0.36.968.811 I slot print_timing: id 0 | task 2279 | eval time = 365.62 ms / 32 tokens ( 11.79 ms per token, 84.79 tokens per second) 0.36.968.812 I slot print_timing: id 0 | task 2279 | total time = 493.52 ms / 353 tokens 0.36.968.813 I slot print_timing: id 0 | task 2279 | graphs reused = 2128 0.36.968.814 I slot print_timing: id 0 | task 2279 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.968.840 I slot release: id 0 | task 2279 | stop processing: n_tokens = 352, truncated = 0 0.36.986.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 36878357 0.37.029.180 I slot launch_slot_: id 0 | task 2314 | processing task, is_child = 0 0.37.890.294 I slot print_timing: id 0 | task 2314 | prompt eval time = 125.47 ms / 330 tokens ( 0.38 ms per token, 2630.19 tokens per second) 0.37.890.299 I slot print_timing: id 0 | task 2314 | eval time = 735.63 ms / 64 tokens ( 11.68 ms per token, 85.64 tokens per second) 0.37.890.300 I slot print_timing: id 0 | task 2314 | total time = 861.10 ms / 394 tokens 0.37.890.303 I slot print_timing: id 0 | task 2314 | graphs reused = 2190 0.37.890.304 I slot print_timing: id 0 | task 2314 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.890.331 I slot release: id 0 | task 2314 | stop processing: n_tokens = 393, truncated = 0 0.37.918.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 37799848 0.37.954.469 I slot launch_slot_: id 0 | task 2381 | processing task, is_child = 0 0.38.448.790 I slot print_timing: id 0 | task 2381 | prompt eval time = 128.15 ms / 341 tokens ( 0.38 ms per token, 2661.01 tokens per second) 0.38.448.796 I slot print_timing: id 0 | task 2381 | eval time = 366.15 ms / 32 tokens ( 11.81 ms per token, 84.66 tokens per second) 0.38.448.797 I slot print_timing: id 0 | task 2381 | total time = 494.30 ms / 373 tokens 0.38.448.798 I slot print_timing: id 0 | task 2381 | graphs reused = 2220 0.38.448.799 I slot print_timing: id 0 | task 2381 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.448.830 I slot release: id 0 | task 2381 | stop processing: n_tokens = 372, truncated = 0 0.38.464.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 38358347 0.38.497.018 I slot launch_slot_: id 0 | task 2416 | processing task, is_child = 0 0.39.180.205 I slot print_timing: id 0 | task 2416 | prompt eval time = 130.10 ms / 338 tokens ( 0.38 ms per token, 2598.06 tokens per second) 0.39.180.210 I slot print_timing: id 0 | task 2416 | eval time = 553.07 ms / 48 tokens ( 11.77 ms per token, 84.98 tokens per second) 0.39.180.211 I slot print_timing: id 0 | task 2416 | total time = 683.17 ms / 386 tokens 0.39.180.212 I slot print_timing: id 0 | task 2416 | graphs reused = 2266 0.39.180.213 I slot print_timing: id 0 | task 2416 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.180.240 I slot release: id 0 | task 2416 | stop processing: n_tokens = 385, truncated = 0 0.39.202.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 39089758 0.39.238.707 I slot launch_slot_: id 0 | task 2467 | processing task, is_child = 0 0.40.023.042 I slot print_timing: id 0 | task 2467 | prompt eval time = 137.51 ms / 395 tokens ( 0.35 ms per token, 2872.54 tokens per second) 0.40.023.049 I slot print_timing: id 0 | task 2467 | eval time = 646.81 ms / 56 tokens ( 11.76 ms per token, 85.03 tokens per second) 0.40.023.050 I slot print_timing: id 0 | task 2467 | total time = 784.32 ms / 451 tokens 0.40.023.050 I slot print_timing: id 0 | task 2467 | graphs reused = 2320 0.40.023.051 I slot print_timing: id 0 | task 2467 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.023.079 I slot release: id 0 | task 2467 | stop processing: n_tokens = 450, truncated = 0 0.40.044.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 39932597 0.40.080.468 I slot launch_slot_: id 0 | task 2526 | processing task, is_child = 0 0.41.230.782 I slot print_timing: id 0 | task 2526 | prompt eval time = 190.57 ms / 528 tokens ( 0.36 ms per token, 2770.66 tokens per second) 0.41.230.788 I slot print_timing: id 0 | task 2526 | eval time = 959.73 ms / 83 tokens ( 11.70 ms per token, 85.44 tokens per second) 0.41.230.789 I slot print_timing: id 0 | task 2526 | total time = 1150.30 ms / 611 tokens 0.41.230.790 I slot print_timing: id 0 | task 2526 | graphs reused = 2401 0.41.230.791 I slot print_timing: id 0 | task 2526 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.230.824 I slot release: id 0 | task 2526 | stop processing: n_tokens = 610, truncated = 0 0.41.259.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 41140341 0.41.305.581 I slot launch_slot_: id 0 | task 2613 | processing task, is_child = 0 0.41.969.169 I slot print_timing: id 0 | task 2613 | prompt eval time = 148.28 ms / 331 tokens ( 0.45 ms per token, 2232.28 tokens per second) 0.41.969.175 I slot print_timing: id 0 | task 2613 | eval time = 515.29 ms / 45 tokens ( 11.71 ms per token, 85.39 tokens per second) 0.41.969.176 I slot print_timing: id 0 | task 2613 | total time = 663.57 ms / 376 tokens 0.41.969.177 I slot print_timing: id 0 | task 2613 | graphs reused = 2444 0.41.969.178 I slot print_timing: id 0 | task 2613 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.969.206 I slot release: id 0 | task 2613 | stop processing: n_tokens = 387, truncated = 0 0.41.996.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 41878723 0.42.040.076 I slot launch_slot_: id 0 | task 2661 | processing task, is_child = 0 0.42.806.121 I slot print_timing: id 0 | task 2661 | prompt eval time = 156.24 ms / 362 tokens ( 0.43 ms per token, 2316.92 tokens per second) 0.42.806.126 I slot print_timing: id 0 | task 2661 | eval time = 609.78 ms / 53 tokens ( 11.73 ms per token, 85.28 tokens per second) 0.42.806.128 I slot print_timing: id 0 | task 2661 | total time = 766.02 ms / 415 tokens 0.42.806.129 I slot print_timing: id 0 | task 2661 | graphs reused = 2495 0.42.806.130 I slot print_timing: id 0 | task 2661 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.806.157 I slot release: id 0 | task 2661 | stop processing: n_tokens = 426, truncated = 0 0.42.821.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 42715675 0.42.866.704 I slot launch_slot_: id 0 | task 2717 | processing task, is_child = 0 0.43.820.890 I slot print_timing: id 0 | task 2717 | prompt eval time = 159.70 ms / 419 tokens ( 0.38 ms per token, 2623.74 tokens per second) 0.43.820.896 I slot print_timing: id 0 | task 2717 | eval time = 794.47 ms / 69 tokens ( 11.68 ms per token, 85.59 tokens per second) 0.43.820.897 I slot print_timing: id 0 | task 2717 | total time = 954.17 ms / 488 tokens 0.43.820.898 I slot print_timing: id 0 | task 2717 | graphs reused = 2562 0.43.820.899 I slot print_timing: id 0 | task 2717 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.820.932 I slot release: id 0 | task 2717 | stop processing: n_tokens = 499, truncated = 0 0.43.846.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 43730449 0.43.892.361 I slot launch_slot_: id 0 | task 2789 | processing task, is_child = 0 0.44.571.669 I slot print_timing: id 0 | task 2789 | prompt eval time = 172.79 ms / 423 tokens ( 0.41 ms per token, 2447.99 tokens per second) 0.44.571.675 I slot print_timing: id 0 | task 2789 | eval time = 506.49 ms / 44 tokens ( 11.78 ms per token, 84.90 tokens per second) 0.44.571.676 I slot print_timing: id 0 | task 2789 | total time = 679.29 ms / 467 tokens 0.44.571.677 I slot print_timing: id 0 | task 2789 | graphs reused = 2604 0.44.571.677 I slot print_timing: id 0 | task 2789 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.571.710 I slot release: id 0 | task 2789 | stop processing: n_tokens = 478, truncated = 0 0.44.592.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 44481227 0.44.639.015 I slot launch_slot_: id 0 | task 2836 | processing task, is_child = 0 0.45.284.645 I slot print_timing: id 0 | task 2836 | prompt eval time = 152.66 ms / 341 tokens ( 0.45 ms per token, 2233.71 tokens per second) 0.45.284.651 I slot print_timing: id 0 | task 2836 | eval time = 492.95 ms / 43 tokens ( 11.74 ms per token, 85.20 tokens per second) 0.45.284.652 I slot print_timing: id 0 | task 2836 | total time = 645.61 ms / 384 tokens 0.45.284.653 I slot print_timing: id 0 | task 2836 | graphs reused = 2645 0.45.284.653 I slot print_timing: id 0 | task 2836 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.284.682 I slot release: id 0 | task 2836 | stop processing: n_tokens = 395, truncated = 0 0.45.307.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 45194199 0.45.351.774 I slot launch_slot_: id 0 | task 2882 | processing task, is_child = 0 0.46.040.672 I slot print_timing: id 0 | task 2882 | prompt eval time = 150.50 ms / 356 tokens ( 0.42 ms per token, 2365.40 tokens per second) 0.46.040.677 I slot print_timing: id 0 | task 2882 | eval time = 538.37 ms / 47 tokens ( 11.70 ms per token, 85.44 tokens per second) 0.46.040.679 I slot print_timing: id 0 | task 2882 | total time = 688.88 ms / 403 tokens 0.46.040.679 I slot print_timing: id 0 | task 2882 | graphs reused = 2690 0.46.040.681 I slot print_timing: id 0 | task 2882 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.040.709 I slot release: id 0 | task 2882 | stop processing: n_tokens = 414, truncated = 0 0.46.057.631 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 45950227 0.46.057.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.46.120.846 I slot launch_slot_: id 0 | task 2932 | processing task, is_child = 0 0.46.806.987 I slot print_timing: id 0 | task 2932 | prompt eval time = 154.62 ms / 362 tokens ( 0.43 ms per token, 2341.25 tokens per second) 0.46.806.993 I slot print_timing: id 0 | task 2932 | eval time = 531.50 ms / 46 tokens ( 11.81 ms per token, 84.67 tokens per second) 0.46.806.993 I slot print_timing: id 0 | task 2932 | total time = 686.12 ms / 408 tokens 0.46.806.994 I slot print_timing: id 0 | task 2932 | graphs reused = 2734 0.46.806.995 I slot print_timing: id 0 | task 2932 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.807.023 I slot release: id 0 | task 2932 | stop processing: n_tokens = 419, truncated = 0 0.46.820.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 46716541 0.46.820.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.46.888.673 I slot launch_slot_: id 0 | task 2981 | processing task, is_child = 0 0.47.837.149 I slot print_timing: id 0 | task 2981 | prompt eval time = 166.04 ms / 391 tokens ( 0.42 ms per token, 2354.85 tokens per second) 0.47.837.155 I slot print_timing: id 0 | task 2981 | eval time = 782.42 ms / 68 tokens ( 11.68 ms per token, 85.63 tokens per second) 0.47.837.156 I slot print_timing: id 0 | task 2981 | total time = 948.46 ms / 459 tokens 0.47.837.157 I slot print_timing: id 0 | task 2981 | graphs reused = 2800 0.47.837.158 I slot print_timing: id 0 | task 2981 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.837.189 I slot release: id 0 | task 2981 | stop processing: n_tokens = 470, truncated = 0 0.47.850.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 47746706 0.47.850.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.47.910.179 I slot launch_slot_: id 0 | task 3052 | processing task, is_child = 0 0.48.679.062 I slot print_timing: id 0 | task 3052 | prompt eval time = 149.66 ms / 343 tokens ( 0.44 ms per token, 2291.86 tokens per second) 0.48.679.067 I slot print_timing: id 0 | task 3052 | eval time = 619.20 ms / 54 tokens ( 11.68 ms per token, 85.59 tokens per second) 0.48.679.068 I slot print_timing: id 0 | task 3052 | total time = 768.86 ms / 397 tokens 0.48.679.069 I slot print_timing: id 0 | task 3052 | graphs reused = 2852 0.48.679.070 I slot print_timing: id 0 | task 3052 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.679.096 I slot release: id 0 | task 3052 | stop processing: n_tokens = 408, truncated = 0 0.48.706.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 48588614 0.48.706.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.48.716.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.48.775.686 I slot launch_slot_: id 0 | task 3109 | processing task, is_child = 0 0.49.464.203 I slot print_timing: id 0 | task 3109 | prompt eval time = 160.84 ms / 401 tokens ( 0.40 ms per token, 2493.08 tokens per second) 0.49.464.209 I slot print_timing: id 0 | task 3109 | eval time = 527.65 ms / 46 tokens ( 11.73 ms per token, 85.28 tokens per second) 0.49.464.210 I slot print_timing: id 0 | task 3109 | total time = 688.50 ms / 447 tokens 0.49.464.210 I slot print_timing: id 0 | task 3109 | graphs reused = 2896 0.49.464.211 I slot print_timing: id 0 | task 3109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.464.241 I slot release: id 0 | task 3109 | stop processing: n_tokens = 458, truncated = 0 0.49.468.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 49373758 0.49.468.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.49.524.303 I slot launch_slot_: id 0 | task 3158 | processing task, is_child = 0 0.50.456.691 I slot print_timing: id 0 | task 3158 | prompt eval time = 149.93 ms / 355 tokens ( 0.42 ms per token, 2367.80 tokens per second) 0.50.456.696 I slot print_timing: id 0 | task 3158 | eval time = 782.44 ms / 68 tokens ( 11.68 ms per token, 85.63 tokens per second) 0.50.456.697 I slot print_timing: id 0 | task 3158 | total time = 932.37 ms / 423 tokens 0.50.456.698 I slot print_timing: id 0 | task 3158 | graphs reused = 2962 0.50.456.699 I slot print_timing: id 0 | task 3158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.456.727 I slot release: id 0 | task 3158 | stop processing: n_tokens = 434, truncated = 0 0.50.460.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 50366244 0.50.460.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.50.522.254 I slot launch_slot_: id 0 | task 3229 | processing task, is_child = 0 0.51.364.199 I slot print_timing: id 0 | task 3229 | prompt eval time = 151.77 ms / 351 tokens ( 0.43 ms per token, 2312.65 tokens per second) 0.51.364.205 I slot print_timing: id 0 | task 3229 | eval time = 690.15 ms / 57 tokens ( 12.32 ms per token, 81.14 tokens per second) 0.51.364.206 I slot print_timing: id 0 | task 3229 | total time = 841.93 ms / 408 tokens 0.51.364.207 I slot print_timing: id 0 | task 3229 | graphs reused = 3017 0.51.364.208 I slot print_timing: id 0 | task 3229 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.364.236 I slot release: id 0 | task 3229 | stop processing: n_tokens = 419, truncated = 0 0.51.389.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 51273753 0.51.389.779 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.51.399.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.51.455.376 I slot launch_slot_: id 0 | task 3289 | processing task, is_child = 0 0.52.710.789 I slot print_timing: id 0 | task 3289 | prompt eval time = 176.56 ms / 475 tokens ( 0.37 ms per token, 2690.24 tokens per second) 0.52.710.795 I slot print_timing: id 0 | task 3289 | eval time = 1078.83 ms / 93 tokens ( 11.73 ms per token, 85.28 tokens per second) 0.52.710.796 I slot print_timing: id 0 | task 3289 | total time = 1255.39 ms / 568 tokens 0.52.710.796 I slot print_timing: id 0 | task 3289 | graphs reused = 3107 0.52.710.797 I slot print_timing: id 0 | task 3289 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.710.830 I slot release: id 0 | task 3289 | stop processing: n_tokens = 579, truncated = 0 0.52.730.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 52620347 0.52.730.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.52.780.411 I slot launch_slot_: id 0 | task 3385 | processing task, is_child = 0 0.54.184.046 I slot print_timing: id 0 | task 3385 | prompt eval time = 174.06 ms / 440 tokens ( 0.40 ms per token, 2527.86 tokens per second) 0.54.184.052 I slot print_timing: id 0 | task 3385 | eval time = 1229.55 ms / 106 tokens ( 11.71 ms per token, 85.40 tokens per second) 0.54.184.053 I slot print_timing: id 0 | task 3385 | total time = 1403.61 ms / 546 tokens 0.54.184.054 I slot print_timing: id 0 | task 3385 | graphs reused = 3210 0.54.184.055 I slot print_timing: id 0 | task 3385 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.184.088 I slot release: id 0 | task 3385 | stop processing: n_tokens = 557, truncated = 0 0.54.207.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 54093605 0.54.207.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.54.263.958 I slot launch_slot_: id 0 | task 3494 | processing task, is_child = 0 0.55.046.010 I slot print_timing: id 0 | task 3494 | prompt eval time = 150.13 ms / 345 tokens ( 0.44 ms per token, 2298.04 tokens per second) 0.55.046.016 I slot print_timing: id 0 | task 3494 | eval time = 631.91 ms / 55 tokens ( 11.70 ms per token, 85.46 tokens per second) 0.55.046.017 I slot print_timing: id 0 | task 3494 | total time = 782.03 ms / 400 tokens 0.55.046.018 I slot print_timing: id 0 | task 3494 | graphs reused = 3263 0.55.046.018 I slot print_timing: id 0 | task 3494 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.046.046 I slot release: id 0 | task 3494 | stop processing: n_tokens = 411, truncated = 0 0.55.068.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 54955564 0.55.068.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.55.077.662 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.55.121.938 I slot launch_slot_: id 0 | task 3552 | processing task, is_child = 0 0.55.908.003 I slot print_timing: id 0 | task 3552 | prompt eval time = 152.75 ms / 382 tokens ( 0.40 ms per token, 2500.75 tokens per second) 0.55.908.008 I slot print_timing: id 0 | task 3552 | eval time = 633.29 ms / 55 tokens ( 11.73 ms per token, 85.27 tokens per second) 0.55.908.009 I slot print_timing: id 0 | task 3552 | total time = 786.05 ms / 437 tokens 0.55.908.010 I slot print_timing: id 0 | task 3552 | graphs reused = 3316 0.55.908.011 I slot print_timing: id 0 | task 3552 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.908.042 I slot release: id 0 | task 3552 | stop processing: n_tokens = 448, truncated = 0 0.55.911.684 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 55817559 0.55.911.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.55.967.559 I slot launch_slot_: id 0 | task 3610 | processing task, is_child = 0 0.56.631.086 I slot print_timing: id 0 | task 3610 | prompt eval time = 148.73 ms / 337 tokens ( 0.44 ms per token, 2265.82 tokens per second) 0.56.631.092 I slot print_timing: id 0 | task 3610 | eval time = 514.77 ms / 45 tokens ( 11.70 ms per token, 85.47 tokens per second) 0.56.631.093 I slot print_timing: id 0 | task 3610 | total time = 663.51 ms / 382 tokens 0.56.631.093 I slot print_timing: id 0 | task 3610 | graphs reused = 3359 0.56.631.094 I slot print_timing: id 0 | task 3610 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.631.123 I slot release: id 0 | task 3610 | stop processing: n_tokens = 393, truncated = 0 0.56.659.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 56540640 0.56.659.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.56.729.114 I slot launch_slot_: id 0 | task 3658 | processing task, is_child = 0 0.57.722.373 I slot print_timing: id 0 | task 3658 | prompt eval time = 157.13 ms / 402 tokens ( 0.39 ms per token, 2558.46 tokens per second) 0.57.722.379 I slot print_timing: id 0 | task 3658 | eval time = 836.11 ms / 70 tokens ( 12.12 ms per token, 82.52 tokens per second) 0.57.722.380 I slot print_timing: id 0 | task 3658 | total time = 993.24 ms / 472 tokens 0.57.722.381 I slot print_timing: id 0 | task 3658 | graphs reused = 3427 0.57.722.382 I slot print_timing: id 0 | task 3658 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.722.415 I slot release: id 0 | task 3658 | stop processing: n_tokens = 483, truncated = 0 0.57.750.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 57631932 0.57.750.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.57.760.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.57.822.538 I slot launch_slot_: id 0 | task 3731 | processing task, is_child = 0 0.58.670.097 I slot print_timing: id 0 | task 3731 | prompt eval time = 192.45 ms / 549 tokens ( 0.35 ms per token, 2852.64 tokens per second) 0.58.670.104 I slot print_timing: id 0 | task 3731 | eval time = 655.09 ms / 57 tokens ( 11.70 ms per token, 85.48 tokens per second) 0.58.670.105 I slot print_timing: id 0 | task 3731 | total time = 847.54 ms / 606 tokens 0.58.670.105 I slot print_timing: id 0 | task 3731 | graphs reused = 3482 0.58.670.106 I slot print_timing: id 0 | task 3731 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.670.138 I slot release: id 0 | task 3731 | stop processing: n_tokens = 617, truncated = 0 0.58.687.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 58579656 0.58.687.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.58.756.136 I slot launch_slot_: id 0 | task 3792 | processing task, is_child = 0 0.59.633.052 I slot print_timing: id 0 | task 3792 | prompt eval time = 209.22 ms / 616 tokens ( 0.34 ms per token, 2944.31 tokens per second) 0.59.633.057 I slot print_timing: id 0 | task 3792 | eval time = 667.68 ms / 58 tokens ( 11.71 ms per token, 85.37 tokens per second) 0.59.633.059 I slot print_timing: id 0 | task 3792 | total time = 876.90 ms / 674 tokens 0.59.633.059 I slot print_timing: id 0 | task 3792 | graphs reused = 3538 0.59.633.060 I slot print_timing: id 0 | task 3792 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.633.095 I slot release: id 0 | task 3792 | stop processing: n_tokens = 685, truncated = 0 0.59.654.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 59542612 0.59.654.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.59.664.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.59.735.699 I slot launch_slot_: id 0 | task 3854 | processing task, is_child = 0 1.00.678.261 I slot print_timing: id 0 | task 3854 | prompt eval time = 219.72 ms / 665 tokens ( 0.33 ms per token, 3026.65 tokens per second) 1.00.678.267 I slot print_timing: id 0 | task 3854 | eval time = 722.83 ms / 62 tokens ( 11.85 ms per token, 84.39 tokens per second) 1.00.678.268 I slot print_timing: id 0 | task 3854 | total time = 942.54 ms / 727 tokens 1.00.678.268 I slot print_timing: id 0 | task 3854 | graphs reused = 3598 1.00.678.269 I slot print_timing: id 0 | task 3854 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.678.306 I slot release: id 0 | task 3854 | stop processing: n_tokens = 738, truncated = 0 1.00.698.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 60587823 1.00.698.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 1.00.708.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 1.00.787.786 I slot launch_slot_: id 0 | task 3920 | processing task, is_child = 0 1.01.641.081 I slot print_timing: id 0 | task 3920 | prompt eval time = 220.33 ms / 645 tokens ( 0.34 ms per token, 2927.39 tokens per second) 1.01.641.087 I slot print_timing: id 0 | task 3920 | eval time = 632.94 ms / 55 tokens ( 11.72 ms per token, 85.32 tokens per second) 1.01.641.088 I slot print_timing: id 0 | task 3920 | total time = 853.27 ms / 700 tokens 1.01.641.089 I slot print_timing: id 0 | task 3920 | graphs reused = 3651 1.01.641.089 I slot print_timing: id 0 | task 3920 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.641.124 I slot release: id 0 | task 3920 | stop processing: n_tokens = 711, truncated = 0 1.01.661.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 61550641 1.01.661.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 1.01.736.033 I slot launch_slot_: id 0 | task 3979 | processing task, is_child = 0 1.02.514.402 I slot print_timing: id 0 | task 3979 | prompt eval time = 177.69 ms / 474 tokens ( 0.37 ms per token, 2667.49 tokens per second) 1.02.514.408 I slot print_timing: id 0 | task 3979 | eval time = 600.66 ms / 52 tokens ( 11.78 ms per token, 84.91 tokens per second) 1.02.514.409 I slot print_timing: id 0 | task 3979 | total time = 778.35 ms / 526 tokens 1.02.514.410 I slot print_timing: id 0 | task 3979 | graphs reused = 3700 1.02.514.410 I slot print_timing: id 0 | task 3979 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.514.442 I slot release: id 0 | task 3979 | stop processing: n_tokens = 537, truncated = 0 1.02.536.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 62423959 1.02.536.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 1.02.546.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 1.02.605.280 I slot launch_slot_: id 0 | task 4034 | processing task, is_child = 0 1.03.288.352 I slot print_timing: id 0 | task 4034 | prompt eval time = 202.73 ms / 617 tokens ( 0.33 ms per token, 3043.44 tokens per second) 1.03.288.357 I slot print_timing: id 0 | task 4034 | eval time = 480.32 ms / 42 tokens ( 11.72 ms per token, 85.36 tokens per second) 1.03.288.358 I slot print_timing: id 0 | task 4034 | total time = 683.05 ms / 659 tokens 1.03.288.359 I slot print_timing: id 0 | task 4034 | graphs reused = 3740 1.03.288.360 I slot print_timing: id 0 | task 4034 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.288.394 I slot release: id 0 | task 4034 | stop processing: n_tokens = 670, truncated = 0 1.03.315.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 63197911 1.03.315.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.03.376.687 I slot launch_slot_: id 0 | task 4080 | processing task, is_child = 0 1.04.130.666 I slot print_timing: id 0 | task 4080 | prompt eval time = 204.00 ms / 601 tokens ( 0.34 ms per token, 2946.15 tokens per second) 1.04.130.672 I slot print_timing: id 0 | task 4080 | eval time = 549.96 ms / 48 tokens ( 11.70 ms per token, 85.46 tokens per second) 1.04.130.673 I slot print_timing: id 0 | task 4080 | total time = 753.96 ms / 649 tokens 1.04.130.674 I slot print_timing: id 0 | task 4080 | graphs reused = 3786 1.04.130.675 I slot print_timing: id 0 | task 4080 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.130.715 I slot release: id 0 | task 4080 | stop processing: n_tokens = 660, truncated = 0 1.04.145.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 64040232 1.04.145.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.292 MiB) 1.04.155.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 1.04.241.932 I slot launch_slot_: id 0 | task 4132 | processing task, is_child = 0 1.04.971.000 I slot print_timing: id 0 | task 4132 | prompt eval time = 191.40 ms / 533 tokens ( 0.36 ms per token, 2784.71 tokens per second) 1.04.971.005 I slot print_timing: id 0 | task 4132 | eval time = 537.64 ms / 47 tokens ( 11.69 ms per token, 85.56 tokens per second) 1.04.971.006 I slot print_timing: id 0 | task 4132 | total time = 729.05 ms / 580 tokens 1.04.971.007 I slot print_timing: id 0 | task 4132 | graphs reused = 3831 1.04.971.008 I slot print_timing: id 0 | task 4132 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.971.040 I slot release: id 0 | task 4132 | stop processing: n_tokens = 591, truncated = 0 1.04.984.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 64880557 1.04.984.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 1.05.064.853 I slot launch_slot_: id 0 | task 4183 | processing task, is_child = 0 1.05.846.980 I slot print_timing: id 0 | task 4183 | prompt eval time = 181.09 ms / 480 tokens ( 0.38 ms per token, 2650.56 tokens per second) 1.05.846.987 I slot print_timing: id 0 | task 4183 | eval time = 601.01 ms / 52 tokens ( 11.78 ms per token, 84.86 tokens per second) 1.05.846.988 I slot print_timing: id 0 | task 4183 | total time = 782.11 ms / 532 tokens 1.05.846.988 I slot print_timing: id 0 | task 4183 | graphs reused = 3880 1.05.846.989 I slot print_timing: id 0 | task 4183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.847.020 I slot release: id 0 | task 4183 | stop processing: n_tokens = 560, truncated = 0 1.05.851.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 65756537 1.05.851.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.05.861.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.05.932.977 I slot launch_slot_: id 0 | task 4238 | processing task, is_child = 0 1.06.609.398 I slot print_timing: id 0 | task 4238 | prompt eval time = 194.22 ms / 567 tokens ( 0.34 ms per token, 2919.43 tokens per second) 1.06.609.404 I slot print_timing: id 0 | task 4238 | eval time = 482.18 ms / 42 tokens ( 11.76 ms per token, 85.03 tokens per second) 1.06.609.405 I slot print_timing: id 0 | task 4238 | total time = 676.40 ms / 609 tokens 1.06.609.406 I slot print_timing: id 0 | task 4238 | graphs reused = 3920 1.06.609.407 I slot print_timing: id 0 | task 4238 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.609.443 I slot release: id 0 | task 4238 | stop processing: n_tokens = 637, truncated = 0 1.06.613.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 66518960 1.06.614.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 1.06.624.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.06.700.383 I slot launch_slot_: id 0 | task 4284 | processing task, is_child = 0 1.07.618.731 I slot print_timing: id 0 | task 4284 | prompt eval time = 188.99 ms / 506 tokens ( 0.37 ms per token, 2677.42 tokens per second) 1.07.618.737 I slot print_timing: id 0 | task 4284 | eval time = 729.34 ms / 63 tokens ( 11.76 ms per token, 85.01 tokens per second) 1.07.618.738 I slot print_timing: id 0 | task 4284 | total time = 918.33 ms / 569 tokens 1.07.618.739 I slot print_timing: id 0 | task 4284 | graphs reused = 3981 1.07.618.740 I slot print_timing: id 0 | task 4284 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.618.771 I slot release: id 0 | task 4284 | stop processing: n_tokens = 597, truncated = 0 1.07.633.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 67528289 1.07.633.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.07.643.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.07.710.306 I slot launch_slot_: id 0 | task 4350 | processing task, is_child = 0 1.08.338.972 I slot print_timing: id 0 | task 4350 | prompt eval time = 172.48 ms / 436 tokens ( 0.40 ms per token, 2527.77 tokens per second) 1.08.338.978 I slot print_timing: id 0 | task 4350 | eval time = 456.16 ms / 40 tokens ( 11.70 ms per token, 85.50 tokens per second) 1.08.338.979 I slot print_timing: id 0 | task 4350 | total time = 628.65 ms / 476 tokens 1.08.338.979 I slot print_timing: id 0 | task 4350 | graphs reused = 4019 1.08.338.980 I slot print_timing: id 0 | task 4350 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.339.011 I slot release: id 0 | task 4350 | stop processing: n_tokens = 504, truncated = 0 1.08.354.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 68248528 1.08.354.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.08.415.556 I slot launch_slot_: id 0 | task 4393 | processing task, is_child = 0 1.09.314.600 I slot print_timing: id 0 | task 4393 | prompt eval time = 185.87 ms / 519 tokens ( 0.36 ms per token, 2792.35 tokens per second) 1.09.314.605 I slot print_timing: id 0 | task 4393 | eval time = 713.16 ms / 62 tokens ( 11.69 ms per token, 85.53 tokens per second) 1.09.314.606 I slot print_timing: id 0 | task 4393 | total time = 899.02 ms / 581 tokens 1.09.314.607 I slot print_timing: id 0 | task 4393 | graphs reused = 4079 1.09.314.608 I slot print_timing: id 0 | task 4393 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.314.645 I slot release: id 0 | task 4393 | stop processing: n_tokens = 609, truncated = 0 1.09.333.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 69224162 1.09.333.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.09.342.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.042 MiB) 1.09.426.154 I slot launch_slot_: id 0 | task 4459 | processing task, is_child = 0 1.10.132.042 I slot print_timing: id 0 | task 4459 | prompt eval time = 174.25 ms / 465 tokens ( 0.37 ms per token, 2668.63 tokens per second) 1.10.132.047 I slot print_timing: id 0 | task 4459 | eval time = 531.62 ms / 46 tokens ( 11.81 ms per token, 84.65 tokens per second) 1.10.132.048 I slot print_timing: id 0 | task 4459 | total time = 705.87 ms / 511 tokens 1.10.132.049 I slot print_timing: id 0 | task 4459 | graphs reused = 4122 1.10.132.050 I slot print_timing: id 0 | task 4459 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.132.080 I slot release: id 0 | task 4459 | stop processing: n_tokens = 542, truncated = 0 1.10.157.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 70041598 1.10.158.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.10.167.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.10.247.660 I slot launch_slot_: id 0 | task 4508 | processing task, is_child = 0 1.10.892.460 I slot print_timing: id 0 | task 4508 | prompt eval time = 173.90 ms / 431 tokens ( 0.40 ms per token, 2478.44 tokens per second) 1.10.892.465 I slot print_timing: id 0 | task 4508 | eval time = 470.88 ms / 41 tokens ( 11.77 ms per token, 84.95 tokens per second) 1.10.892.466 I slot print_timing: id 0 | task 4508 | total time = 644.78 ms / 472 tokens 1.10.892.467 I slot print_timing: id 0 | task 4508 | graphs reused = 4161 1.10.892.468 I slot print_timing: id 0 | task 4508 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.892.501 I slot release: id 0 | task 4508 | stop processing: n_tokens = 503, truncated = 0 1.10.907.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 70802019 1.10.907.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.10.919.169 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.10.999.073 I slot launch_slot_: id 0 | task 4552 | processing task, is_child = 0 1.11.682.147 I slot print_timing: id 0 | task 4552 | prompt eval time = 176.09 ms / 457 tokens ( 0.39 ms per token, 2595.25 tokens per second) 1.11.682.153 I slot print_timing: id 0 | task 4552 | eval time = 506.96 ms / 44 tokens ( 11.79 ms per token, 84.82 tokens per second) 1.11.682.154 I slot print_timing: id 0 | task 4552 | total time = 683.05 ms / 501 tokens 1.11.682.155 I slot print_timing: id 0 | task 4552 | graphs reused = 4202 1.11.682.155 I slot print_timing: id 0 | task 4552 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.682.186 I slot release: id 0 | task 4552 | stop processing: n_tokens = 532, truncated = 0 1.11.703.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 71591704 1.11.703.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.11.778.138 I slot launch_slot_: id 0 | task 4599 | processing task, is_child = 0 1.12.430.656 I slot print_timing: id 0 | task 4599 | prompt eval time = 172.25 ms / 439 tokens ( 0.39 ms per token, 2548.68 tokens per second) 1.12.430.661 I slot print_timing: id 0 | task 4599 | eval time = 480.25 ms / 42 tokens ( 11.71 ms per token, 85.37 tokens per second) 1.12.430.662 I slot print_timing: id 0 | task 4599 | total time = 652.50 ms / 481 tokens 1.12.430.663 I slot print_timing: id 0 | task 4599 | graphs reused = 4242 1.12.430.664 I slot print_timing: id 0 | task 4599 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.430.694 I slot release: id 0 | task 4599 | stop processing: n_tokens = 512, truncated = 0 1.12.454.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 72340212 1.12.454.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.12.467.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.12.552.366 I slot launch_slot_: id 0 | task 4644 | processing task, is_child = 0 1.13.399.130 I slot print_timing: id 0 | task 4644 | prompt eval time = 202.23 ms / 606 tokens ( 0.33 ms per token, 2996.54 tokens per second) 1.13.399.135 I slot print_timing: id 0 | task 4644 | eval time = 644.51 ms / 56 tokens ( 11.72 ms per token, 85.34 tokens per second) 1.13.399.136 I slot print_timing: id 0 | task 4644 | total time = 846.74 ms / 662 tokens 1.13.399.137 I slot print_timing: id 0 | task 4644 | graphs reused = 4296 1.13.399.138 I slot print_timing: id 0 | task 4644 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.399.176 I slot release: id 0 | task 4644 | stop processing: n_tokens = 693, truncated = 0 1.13.423.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 73308693 1.13.423.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.13.437.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.13.533.021 I slot launch_slot_: id 0 | task 4704 | processing task, is_child = 0 1.14.189.416 I slot print_timing: id 0 | task 4704 | prompt eval time = 180.77 ms / 477 tokens ( 0.38 ms per token, 2638.77 tokens per second) 1.14.189.422 I slot print_timing: id 0 | task 4704 | eval time = 475.61 ms / 41 tokens ( 11.89 ms per token, 84.10 tokens per second) 1.14.189.423 I slot print_timing: id 0 | task 4704 | total time = 656.37 ms / 518 tokens 1.14.189.424 I slot print_timing: id 0 | task 4704 | graphs reused = 4334 1.14.189.425 I slot print_timing: id 0 | task 4704 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.189.457 I slot release: id 0 | task 4704 | stop processing: n_tokens = 549, truncated = 0 1.14.215.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 74098975 1.14.215.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.14.289.896 I slot launch_slot_: id 0 | task 4748 | processing task, is_child = 0 1.15.234.126 I slot print_timing: id 0 | task 4748 | prompt eval time = 252.49 ms / 845 tokens ( 0.30 ms per token, 3346.61 tokens per second) 1.15.234.132 I slot print_timing: id 0 | task 4748 | eval time = 691.72 ms / 60 tokens ( 11.72 ms per token, 85.30 tokens per second) 1.15.234.133 I slot print_timing: id 0 | task 4748 | total time = 944.21 ms / 905 tokens 1.15.234.134 I slot print_timing: id 0 | task 4748 | graphs reused = 4392 1.15.234.137 I slot print_timing: id 0 | task 4748 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.234.181 I slot release: id 0 | task 4748 | stop processing: n_tokens = 936, truncated = 0 1.15.256.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 75143699 1.15.256.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.15.269.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.15.362.421 I slot launch_slot_: id 0 | task 4812 | processing task, is_child = 0 1.16.042.512 I slot print_timing: id 0 | task 4812 | prompt eval time = 181.16 ms / 459 tokens ( 0.39 ms per token, 2533.66 tokens per second) 1.16.042.518 I slot print_timing: id 0 | task 4812 | eval time = 498.91 ms / 43 tokens ( 11.88 ms per token, 84.18 tokens per second) 1.16.042.519 I slot print_timing: id 0 | task 4812 | total time = 680.07 ms / 502 tokens 1.16.042.520 I slot print_timing: id 0 | task 4812 | graphs reused = 4432 1.16.042.521 I slot print_timing: id 0 | task 4812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.042.552 I slot release: id 0 | task 4812 | stop processing: n_tokens = 533, truncated = 0 1.16.063.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 75952069 1.16.063.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.16.148.617 I slot launch_slot_: id 0 | task 4858 | processing task, is_child = 0 1.16.913.296 I slot print_timing: id 0 | task 4858 | prompt eval time = 220.57 ms / 670 tokens ( 0.33 ms per token, 3037.56 tokens per second) 1.16.913.303 I slot print_timing: id 0 | task 4858 | eval time = 544.09 ms / 47 tokens ( 11.83 ms per token, 84.55 tokens per second) 1.16.913.304 I slot print_timing: id 0 | task 4858 | total time = 764.66 ms / 717 tokens 1.16.913.305 I slot print_timing: id 0 | task 4858 | graphs reused = 4477 1.16.913.306 I slot print_timing: id 0 | task 4858 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.913.350 I slot release: id 0 | task 4858 | stop processing: n_tokens = 748, truncated = 0 1.16.936.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 76822867 1.16.937.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.16.950.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.17.049.008 I slot launch_slot_: id 0 | task 4909 | processing task, is_child = 0 1.18.061.279 I slot print_timing: id 0 | task 4909 | prompt eval time = 246.87 ms / 775 tokens ( 0.32 ms per token, 3139.33 tokens per second) 1.18.061.285 I slot print_timing: id 0 | task 4909 | eval time = 765.38 ms / 63 tokens ( 12.34 ms per token, 81.01 tokens per second) 1.18.061.286 I slot print_timing: id 0 | task 4909 | total time = 1012.25 ms / 838 tokens 1.18.061.287 I slot print_timing: id 0 | task 4909 | graphs reused = 4538 1.18.061.288 I slot print_timing: id 0 | task 4909 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.061.333 I slot release: id 0 | task 4909 | stop processing: n_tokens = 869, truncated = 0 1.18.076.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 77970850 1.18.076.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.18.089.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.18.190.887 I slot launch_slot_: id 0 | task 4976 | processing task, is_child = 0 1.19.216.284 I slot print_timing: id 0 | task 4976 | prompt eval time = 199.78 ms / 573 tokens ( 0.35 ms per token, 2868.23 tokens per second) 1.19.216.290 I slot print_timing: id 0 | task 4976 | eval time = 825.60 ms / 71 tokens ( 11.79 ms per token, 84.79 tokens per second) 1.19.216.291 I slot print_timing: id 0 | task 4976 | total time = 1025.38 ms / 644 tokens 1.19.216.292 I slot print_timing: id 0 | task 4976 | graphs reused = 4607 1.19.216.292 I slot print_timing: id 0 | task 4976 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.216.328 I slot release: id 0 | task 4976 | stop processing: n_tokens = 675, truncated = 0 1.19.241.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 79125845 1.19.241.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.19.254.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.19.330.781 I slot launch_slot_: id 0 | task 5051 | processing task, is_child = 0 1.20.254.836 I slot print_timing: id 0 | task 5051 | prompt eval time = 178.13 ms / 461 tokens ( 0.39 ms per token, 2588.06 tokens per second) 1.20.254.842 I slot print_timing: id 0 | task 5051 | eval time = 745.91 ms / 64 tokens ( 11.84 ms per token, 84.46 tokens per second) 1.20.254.843 I slot print_timing: id 0 | task 5051 | total time = 924.03 ms / 525 tokens 1.20.254.844 I slot print_timing: id 0 | task 5051 | graphs reused = 4668 1.20.254.845 I slot print_timing: id 0 | task 5051 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.254.880 I slot release: id 0 | task 5051 | stop processing: n_tokens = 556, truncated = 0 1.20.282.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 80164397 1.20.282.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.20.353.438 I slot launch_slot_: id 0 | task 5118 | processing task, is_child = 0 1.21.088.261 I slot print_timing: id 0 | task 5118 | prompt eval time = 208.52 ms / 609 tokens ( 0.34 ms per token, 2920.53 tokens per second) 1.21.088.267 I slot print_timing: id 0 | task 5118 | eval time = 526.28 ms / 43 tokens ( 12.53 ms per token, 79.81 tokens per second) 1.21.088.268 I slot print_timing: id 0 | task 5118 | total time = 734.80 ms / 652 tokens 1.21.088.269 I slot print_timing: id 0 | task 5118 | graphs reused = 4709 1.21.088.269 I slot print_timing: id 0 | task 5118 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.088.307 I slot release: id 0 | task 5118 | stop processing: n_tokens = 683, truncated = 0 1.21.116.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 80997825 1.21.116.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.21.130.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.21.234.354 I slot launch_slot_: id 0 | task 5165 | processing task, is_child = 0 1.22.186.389 I slot print_timing: id 0 | task 5165 | prompt eval time = 249.49 ms / 791 tokens ( 0.32 ms per token, 3170.51 tokens per second) 1.22.186.395 I slot print_timing: id 0 | task 5165 | eval time = 702.52 ms / 61 tokens ( 11.71 ms per token, 85.41 tokens per second) 1.22.186.396 I slot print_timing: id 0 | task 5165 | total time = 952.01 ms / 852 tokens 1.22.186.396 I slot print_timing: id 0 | task 5165 | graphs reused = 4768 1.22.186.397 I slot print_timing: id 0 | task 5165 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.186.438 I slot release: id 0 | task 5165 | stop processing: n_tokens = 883, truncated = 0 1.22.207.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 82095956 1.22.207.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.22.334.779 I slot launch_slot_: id 0 | task 5230 | processing task, is_child = 0 1.23.175.157 I slot print_timing: id 0 | task 5230 | prompt eval time = 195.64 ms / 533 tokens ( 0.37 ms per token, 2724.35 tokens per second) 1.23.175.164 I slot print_timing: id 0 | task 5230 | eval time = 644.71 ms / 56 tokens ( 11.72 ms per token, 85.31 tokens per second) 1.23.175.165 I slot print_timing: id 0 | task 5230 | total time = 840.36 ms / 589 tokens 1.23.175.166 I slot print_timing: id 0 | task 5230 | graphs reused = 4822 1.23.175.166 I slot print_timing: id 0 | task 5230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.175.204 I slot release: id 0 | task 5230 | stop processing: n_tokens = 677, truncated = 0 1.23.202.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 83084721 1.23.202.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.23.290.321 I slot launch_slot_: id 0 | task 5290 | processing task, is_child = 0 1.24.054.097 I slot print_timing: id 0 | task 5290 | prompt eval time = 200.89 ms / 566 tokens ( 0.35 ms per token, 2817.46 tokens per second) 1.24.054.103 I slot print_timing: id 0 | task 5290 | eval time = 562.87 ms / 46 tokens ( 12.51 ms per token, 79.95 tokens per second) 1.24.054.104 I slot print_timing: id 0 | task 5290 | total time = 763.76 ms / 612 tokens 1.24.054.104 I slot print_timing: id 0 | task 5290 | graphs reused = 4866 1.24.054.105 I slot print_timing: id 0 | task 5290 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.054.140 I slot release: id 0 | task 5290 | stop processing: n_tokens = 643, truncated = 0 1.24.072.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 83963657 1.24.072.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.24.168.390 I slot launch_slot_: id 0 | task 5340 | processing task, is_child = 0 1.24.838.730 I slot print_timing: id 0 | task 5340 | prompt eval time = 173.39 ms / 443 tokens ( 0.39 ms per token, 2554.96 tokens per second) 1.24.838.736 I slot print_timing: id 0 | task 5340 | eval time = 496.93 ms / 43 tokens ( 11.83 ms per token, 84.52 tokens per second) 1.24.838.737 I slot print_timing: id 0 | task 5340 | total time = 670.32 ms / 486 tokens 1.24.838.738 I slot print_timing: id 0 | task 5340 | graphs reused = 4906 1.24.838.739 I slot print_timing: id 0 | task 5340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.838.770 I slot release: id 0 | task 5340 | stop processing: n_tokens = 517, truncated = 0 1.24.865.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 84748287 1.24.865.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.24.963.821 I slot launch_slot_: id 0 | task 5386 | processing task, is_child = 0 1.25.885.672 I slot print_timing: id 0 | task 5386 | prompt eval time = 173.12 ms / 487 tokens ( 0.36 ms per token, 2813.01 tokens per second) 1.25.885.678 I slot print_timing: id 0 | task 5386 | eval time = 748.71 ms / 65 tokens ( 11.70 ms per token, 85.48 tokens per second) 1.25.885.679 I slot print_timing: id 0 | task 5386 | total time = 921.83 ms / 552 tokens 1.25.885.680 I slot print_timing: id 0 | task 5386 | graphs reused = 4969 1.25.885.680 I slot print_timing: id 0 | task 5386 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.885.712 I slot release: id 0 | task 5386 | stop processing: n_tokens = 583, truncated = 0 1.25.890.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 85795230 1.25.890.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.25.974.704 I slot launch_slot_: id 0 | task 5454 | processing task, is_child = 0 1.26.691.534 I slot print_timing: id 0 | task 5454 | prompt eval time = 177.08 ms / 507 tokens ( 0.35 ms per token, 2863.15 tokens per second) 1.26.691.540 I slot print_timing: id 0 | task 5454 | eval time = 539.73 ms / 47 tokens ( 11.73 ms per token, 85.23 tokens per second) 1.26.691.541 I slot print_timing: id 0 | task 5454 | total time = 716.81 ms / 554 tokens 1.26.691.541 I slot print_timing: id 0 | task 5454 | graphs reused = 5014 1.26.691.542 I slot print_timing: id 0 | task 5454 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.691.577 I slot release: id 0 | task 5454 | stop processing: n_tokens = 585, truncated = 0 1.26.716.084 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 86601094 1.26.716.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.26.732.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.26.821.909 I slot launch_slot_: id 0 | task 5504 | processing task, is_child = 0 1.27.790.130 I slot print_timing: id 0 | task 5504 | prompt eval time = 205.71 ms / 633 tokens ( 0.32 ms per token, 3077.13 tokens per second) 1.27.790.135 I slot print_timing: id 0 | task 5504 | eval time = 762.49 ms / 66 tokens ( 11.73 ms per token, 85.25 tokens per second) 1.27.790.136 I slot print_timing: id 0 | task 5504 | total time = 968.20 ms / 699 tokens 1.27.790.137 I slot print_timing: id 0 | task 5504 | graphs reused = 5078 1.27.790.138 I slot print_timing: id 0 | task 5504 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.790.177 I slot release: id 0 | task 5504 | stop processing: n_tokens = 730, truncated = 0 1.27.807.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 87699694 1.27.807.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.27.901.658 I slot launch_slot_: id 0 | task 5574 | processing task, is_child = 0 1.28.641.150 I slot print_timing: id 0 | task 5574 | prompt eval time = 198.24 ms / 571 tokens ( 0.35 ms per token, 2880.36 tokens per second) 1.28.641.156 I slot print_timing: id 0 | task 5574 | eval time = 541.23 ms / 47 tokens ( 11.77 ms per token, 84.99 tokens per second) 1.28.641.157 I slot print_timing: id 0 | task 5574 | total time = 739.47 ms / 618 tokens 1.28.641.158 I slot print_timing: id 0 | task 5574 | graphs reused = 5123 1.28.641.159 I slot print_timing: id 0 | task 5574 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.641.196 I slot release: id 0 | task 5574 | stop processing: n_tokens = 649, truncated = 0 1.28.661.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 88550713 1.28.661.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.28.787.074 I slot launch_slot_: id 0 | task 5625 | processing task, is_child = 0 1.29.540.455 I slot print_timing: id 0 | task 5625 | prompt eval time = 248.56 ms / 798 tokens ( 0.31 ms per token, 3210.54 tokens per second) 1.29.540.461 I slot print_timing: id 0 | task 5625 | eval time = 504.81 ms / 44 tokens ( 11.74 ms per token, 85.18 tokens per second) 1.29.540.462 I slot print_timing: id 0 | task 5625 | total time = 753.36 ms / 842 tokens 1.29.540.463 I slot print_timing: id 0 | task 5625 | graphs reused = 5165 1.29.540.463 I slot print_timing: id 0 | task 5625 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.540.508 I slot release: id 0 | task 5625 | stop processing: n_tokens = 873, truncated = 0 1.29.545.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 89450025 1.29.545.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.29.565.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.29.654.377 I slot launch_slot_: id 0 | task 5673 | processing task, is_child = 0 1.30.346.576 I slot print_timing: id 0 | task 5673 | prompt eval time = 198.96 ms / 572 tokens ( 0.35 ms per token, 2874.99 tokens per second) 1.30.346.582 I slot print_timing: id 0 | task 5673 | eval time = 493.22 ms / 43 tokens ( 11.74 ms per token, 85.15 tokens per second) 1.30.346.583 I slot print_timing: id 0 | task 5673 | total time = 692.18 ms / 615 tokens 1.30.346.584 I slot print_timing: id 0 | task 5673 | graphs reused = 5206 1.30.346.585 I slot print_timing: id 0 | task 5673 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.346.620 I slot release: id 0 | task 5673 | stop processing: n_tokens = 646, truncated = 0 1.30.365.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 90256138 1.30.365.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.30.465.562 I slot launch_slot_: id 0 | task 5720 | processing task, is_child = 0 1.31.245.038 I slot print_timing: id 0 | task 5720 | prompt eval time = 206.68 ms / 613 tokens ( 0.34 ms per token, 2966.00 tokens per second) 1.31.245.045 I slot print_timing: id 0 | task 5720 | eval time = 572.78 ms / 49 tokens ( 11.93 ms per token, 83.80 tokens per second) 1.31.245.046 I slot print_timing: id 0 | task 5720 | total time = 779.45 ms / 662 tokens 1.31.245.047 I slot print_timing: id 0 | task 5720 | graphs reused = 5253 1.31.245.048 I slot print_timing: id 0 | task 5720 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.245.089 I slot release: id 0 | task 5720 | stop processing: n_tokens = 693, truncated = 0 1.31.269.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 91154606 1.31.269.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.31.391.935 I slot launch_slot_: id 0 | task 5773 | processing task, is_child = 0 1.32.336.477 I slot print_timing: id 0 | task 5773 | prompt eval time = 202.36 ms / 580 tokens ( 0.35 ms per token, 2866.24 tokens per second) 1.32.336.483 I slot print_timing: id 0 | task 5773 | eval time = 742.17 ms / 64 tokens ( 11.78 ms per token, 84.89 tokens per second) 1.32.336.484 I slot print_timing: id 0 | task 5773 | total time = 944.52 ms / 644 tokens 1.32.336.485 I slot print_timing: id 0 | task 5773 | graphs reused = 5315 1.32.336.487 I slot print_timing: id 0 | task 5773 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.336.522 I slot release: id 0 | task 5773 | stop processing: n_tokens = 675, truncated = 0 1.32.356.779 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 92246040 1.32.356.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.32.457.175 I slot launch_slot_: id 0 | task 5841 | processing task, is_child = 0 1.33.269.217 I slot print_timing: id 0 | task 5841 | prompt eval time = 230.16 ms / 716 tokens ( 0.32 ms per token, 3110.88 tokens per second) 1.33.269.222 I slot print_timing: id 0 | task 5841 | eval time = 581.86 ms / 50 tokens ( 11.87 ms per token, 84.21 tokens per second) 1.33.269.223 I slot print_timing: id 0 | task 5841 | total time = 812.02 ms / 766 tokens 1.33.269.224 I slot print_timing: id 0 | task 5841 | graphs reused = 5362 1.33.269.225 I slot print_timing: id 0 | task 5841 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.269.267 I slot release: id 0 | task 5841 | stop processing: n_tokens = 797, truncated = 0 1.33.274.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 93178785 1.33.274.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.33.295.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.33.384.927 I slot launch_slot_: id 0 | task 5895 | processing task, is_child = 0 1.34.814.507 I slot print_timing: id 0 | task 5895 | prompt eval time = 245.61 ms / 799 tokens ( 0.31 ms per token, 3253.18 tokens per second) 1.34.814.513 I slot print_timing: id 0 | task 5895 | eval time = 1183.95 ms / 102 tokens ( 11.72 ms per token, 85.31 tokens per second) 1.34.814.514 I slot print_timing: id 0 | task 5895 | total time = 1429.56 ms / 901 tokens 1.34.814.514 I slot print_timing: id 0 | task 5895 | graphs reused = 5462 1.34.814.515 I slot print_timing: id 0 | task 5895 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.814.558 I slot release: id 0 | task 5895 | stop processing: n_tokens = 932, truncated = 0 1.34.834.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 94724075 1.34.834.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.34.934.944 I slot launch_slot_: id 0 | task 6001 | processing task, is_child = 0 1.36.388.648 I slot print_timing: id 0 | task 6001 | prompt eval time = 155.52 ms / 361 tokens ( 0.43 ms per token, 2321.22 tokens per second) 1.36.388.654 I slot print_timing: id 0 | task 6001 | eval time = 1298.16 ms / 112 tokens ( 11.70 ms per token, 85.51 tokens per second) 1.36.388.655 I slot print_timing: id 0 | task 6001 | total time = 1453.68 ms / 473 tokens 1.36.388.656 I slot print_timing: id 0 | task 6001 | graphs reused = 5572 1.36.388.656 I slot print_timing: id 0 | task 6001 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.388.686 I slot release: id 0 | task 6001 | stop processing: n_tokens = 504, truncated = 0 1.36.408.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 96298203 1.36.408.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.36.519.973 I slot launch_slot_: id 0 | task 6116 | processing task, is_child = 0 1.37.930.183 I slot print_timing: id 0 | task 6116 | prompt eval time = 152.56 ms / 381 tokens ( 0.40 ms per token, 2497.30 tokens per second) 1.37.930.190 I slot print_timing: id 0 | task 6116 | eval time = 1257.63 ms / 108 tokens ( 11.75 ms per token, 85.08 tokens per second) 1.37.930.191 I slot print_timing: id 0 | task 6116 | total time = 1410.19 ms / 489 tokens 1.37.930.191 I slot print_timing: id 0 | task 6116 | graphs reused = 5677 1.37.930.192 I slot print_timing: id 0 | task 6116 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.930.223 I slot release: id 0 | task 6116 | stop processing: n_tokens = 520, truncated = 0 1.37.947.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 97839740 1.37.947.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.38.029.920 I slot launch_slot_: id 0 | task 6227 | processing task, is_child = 0 1.39.626.444 I slot print_timing: id 0 | task 6227 | prompt eval time = 152.68 ms / 365 tokens ( 0.42 ms per token, 2390.64 tokens per second) 1.39.626.450 I slot print_timing: id 0 | task 6227 | eval time = 1443.83 ms / 124 tokens ( 11.74 ms per token, 85.19 tokens per second) 1.39.626.451 I slot print_timing: id 0 | task 6227 | total time = 1596.50 ms / 489 tokens 1.39.626.452 I slot print_timing: id 0 | task 6227 | graphs reused = 5798 1.39.626.453 I slot print_timing: id 0 | task 6227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.626.482 I slot release: id 0 | task 6227 | stop processing: n_tokens = 520, truncated = 0 1.39.641.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 99535999 1.39.641.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.39.725.389 I slot launch_slot_: id 0 | task 6354 | processing task, is_child = 0 1.41.113.838 I slot print_timing: id 0 | task 6354 | prompt eval time = 148.95 ms / 333 tokens ( 0.45 ms per token, 2235.71 tokens per second) 1.41.113.843 I slot print_timing: id 0 | task 6354 | eval time = 1239.48 ms / 107 tokens ( 11.69 ms per token, 85.52 tokens per second) 1.41.113.844 I slot print_timing: id 0 | task 6354 | total time = 1388.43 ms / 440 tokens 1.41.113.845 I slot print_timing: id 0 | task 6354 | graphs reused = 5903 1.41.113.846 I slot print_timing: id 0 | task 6354 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.113.877 I slot release: id 0 | task 6354 | stop processing: n_tokens = 471, truncated = 0 1.41.135.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 101023395 1.41.194.555 I slot launch_slot_: id 0 | task 6464 | processing task, is_child = 0 1.42.955.628 I slot print_timing: id 0 | task 6464 | prompt eval time = 155.79 ms / 403 tokens ( 0.39 ms per token, 2586.78 tokens per second) 1.42.955.634 I slot print_timing: id 0 | task 6464 | eval time = 1605.26 ms / 138 tokens ( 11.72 ms per token, 85.34 tokens per second) 1.42.955.635 I slot print_timing: id 0 | task 6464 | total time = 1761.05 ms / 541 tokens 1.42.955.636 I slot print_timing: id 0 | task 6464 | graphs reused = 6038 1.42.955.637 I slot print_timing: id 0 | task 6464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.955.669 I slot release: id 0 | task 6464 | stop processing: n_tokens = 572, truncated = 0 1.42.969.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 102865186 1.42.969.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.43.061.843 I slot launch_slot_: id 0 | task 6605 | processing task, is_child = 0 1.45.368.941 I slot print_timing: id 0 | task 6605 | prompt eval time = 156.16 ms / 411 tokens ( 0.38 ms per token, 2632.00 tokens per second) 1.45.368.947 I slot print_timing: id 0 | task 6605 | eval time = 2150.92 ms / 185 tokens ( 11.69 ms per token, 85.54 tokens per second) 1.45.368.948 I slot print_timing: id 0 | task 6605 | total time = 2307.08 ms / 596 tokens 1.45.368.949 I slot print_timing: id 0 | task 6605 | graphs reused = 6220 1.45.368.950 I slot print_timing: id 0 | task 6605 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.368.980 I slot release: id 0 | task 6605 | stop processing: n_tokens = 627, truncated = 0 1.45.389.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 105278497 1.45.389.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.45.486.011 I slot launch_slot_: id 0 | task 6793 | processing task, is_child = 0 1.48.296.107 I slot print_timing: id 0 | task 6793 | prompt eval time = 183.06 ms / 490 tokens ( 0.37 ms per token, 2676.76 tokens per second) 1.48.296.112 I slot print_timing: id 0 | task 6793 | eval time = 2627.02 ms / 225 tokens ( 11.73 ms per token, 85.27 tokens per second) 1.48.296.113 I slot print_timing: id 0 | task 6793 | total time = 2810.07 ms / 715 tokens 1.48.296.114 I slot print_timing: id 0 | task 6793 | graphs reused = 6443 1.48.296.115 I slot print_timing: id 0 | task 6793 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.296.148 I slot release: id 0 | task 6793 | stop processing: n_tokens = 746, truncated = 0 1.48.319.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 108205666 1.48.319.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.48.426.880 I slot launch_slot_: id 0 | task 7021 | processing task, is_child = 0 1.50.563.852 I slot print_timing: id 0 | task 7021 | prompt eval time = 148.75 ms / 344 tokens ( 0.43 ms per token, 2312.57 tokens per second) 1.50.563.858 I slot print_timing: id 0 | task 7021 | eval time = 1988.20 ms / 171 tokens ( 11.70 ms per token, 85.50 tokens per second) 1.50.563.859 I slot print_timing: id 0 | task 7021 | total time = 2136.95 ms / 515 tokens 1.50.563.860 I slot print_timing: id 0 | task 7021 | graphs reused = 6611 1.50.563.863 I slot print_timing: id 0 | task 7021 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.563.892 I slot release: id 0 | task 7021 | stop processing: n_tokens = 546, truncated = 0 1.50.591.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 110473410 1.50.591.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.50.683.734 I slot launch_slot_: id 0 | task 7195 | processing task, is_child = 0 1.52.817.320 I slot print_timing: id 0 | task 7195 | prompt eval time = 149.68 ms / 347 tokens ( 0.43 ms per token, 2318.31 tokens per second) 1.52.817.326 I slot print_timing: id 0 | task 7195 | eval time = 1983.89 ms / 171 tokens ( 11.67 ms per token, 85.69 tokens per second) 1.52.817.327 I slot print_timing: id 0 | task 7195 | total time = 2133.57 ms / 518 tokens 1.52.817.329 I slot print_timing: id 0 | task 7195 | graphs reused = 6779 1.52.817.330 I slot print_timing: id 0 | task 7195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.817.358 I slot release: id 0 | task 7195 | stop processing: n_tokens = 549, truncated = 0 1.52.833.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 112726875 1.52.833.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 1.52.928.103 I slot launch_slot_: id 0 | task 7369 | processing task, is_child = 0 1.54.549.359 I slot print_timing: id 0 | task 7369 | prompt eval time = 156.81 ms / 401 tokens ( 0.39 ms per token, 2557.20 tokens per second) 1.54.549.365 I slot print_timing: id 0 | task 7369 | eval time = 1464.42 ms / 126 tokens ( 11.72 ms per token, 85.36 tokens per second) 1.54.549.366 I slot print_timing: id 0 | task 7369 | total time = 1621.24 ms / 527 tokens 1.54.549.367 I slot print_timing: id 0 | task 7369 | graphs reused = 6902 1.54.549.368 I slot print_timing: id 0 | task 7369 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.549.399 I slot release: id 0 | task 7369 | stop processing: n_tokens = 558, truncated = 0 1.54.553.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 114458916 1.54.553.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.54.648.463 I slot launch_slot_: id 0 | task 7498 | processing task, is_child = 0 1.56.184.570 I slot print_timing: id 0 | task 7498 | prompt eval time = 172.68 ms / 456 tokens ( 0.38 ms per token, 2640.69 tokens per second) 1.56.184.576 I slot print_timing: id 0 | task 7498 | eval time = 1363.40 ms / 115 tokens ( 11.96 ms per token, 83.61 tokens per second) 1.56.184.577 I slot print_timing: id 0 | task 7498 | total time = 1536.09 ms / 571 tokens 1.56.184.578 I slot print_timing: id 0 | task 7498 | graphs reused = 7014 1.56.184.578 I slot print_timing: id 0 | task 7498 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.184.612 I slot release: id 0 | task 7498 | stop processing: n_tokens = 602, truncated = 0 1.56.208.107 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 1.56.208.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.56.306.212 I slot launch_slot_: id 0 | task 7616 | processing task, is_child = 0 1.57.766.771 I slot print_timing: id 0 | task 7616 | prompt eval time = 161.45 ms / 406 tokens ( 0.40 ms per token, 2514.65 tokens per second) 1.57.766.777 I slot print_timing: id 0 | task 7616 | eval time = 1299.09 ms / 112 tokens ( 11.70 ms per token, 85.44 tokens per second) 1.57.766.778 I slot print_timing: id 0 | task 7616 | total time = 1460.54 ms / 518 tokens 1.57.766.779 I slot print_timing: id 0 | task 7616 | graphs reused = 7123 1.57.766.780 I slot print_timing: id 0 | task 7616 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.766.809 I slot release: id 0 | task 7616 | stop processing: n_tokens = 549, truncated = 0 1.57.786.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 117676327 1.57.856.040 I slot launch_slot_: id 0 | task 7731 | processing task, is_child = 0 2.00.091.965 I slot print_timing: id 0 | task 7731 | prompt eval time = 159.26 ms / 406 tokens ( 0.39 ms per token, 2549.31 tokens per second) 2.00.091.971 I slot print_timing: id 0 | task 7731 | eval time = 2076.65 ms / 179 tokens ( 11.67 ms per token, 85.72 tokens per second) 2.00.091.972 I slot print_timing: id 0 | task 7731 | total time = 2235.91 ms / 585 tokens 2.00.091.973 I slot print_timing: id 0 | task 7731 | graphs reused = 7299 2.00.091.974 I slot print_timing: id 0 | task 7731 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.092.005 I slot release: id 0 | task 7731 | stop processing: n_tokens = 616, truncated = 0 2.00.121.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 120001523 2.00.121.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 2.00.216.586 I slot launch_slot_: id 0 | task 7913 | processing task, is_child = 0 2.02.051.273 I slot print_timing: id 0 | task 7913 | prompt eval time = 161.92 ms / 444 tokens ( 0.36 ms per token, 2742.13 tokens per second) 2.02.051.279 I slot print_timing: id 0 | task 7913 | eval time = 1672.75 ms / 144 tokens ( 11.70 ms per token, 85.49 tokens per second) 2.02.051.280 I slot print_timing: id 0 | task 7913 | total time = 1834.67 ms / 588 tokens 2.02.051.280 I slot print_timing: id 0 | task 7913 | graphs reused = 7440 2.02.051.282 I slot print_timing: id 0 | task 7913 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.051.313 I slot release: id 0 | task 7913 | stop processing: n_tokens = 619, truncated = 0 2.02.054.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 121960830 2.02.054.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 2.02.151.397 I slot launch_slot_: id 0 | task 8060 | processing task, is_child = 0 2.03.493.888 I slot print_timing: id 0 | task 8060 | prompt eval time = 154.72 ms / 372 tokens ( 0.42 ms per token, 2404.42 tokens per second) 2.03.493.893 I slot print_timing: id 0 | task 8060 | eval time = 1187.76 ms / 103 tokens ( 11.64 ms per token, 85.88 tokens per second) 2.03.493.894 I slot print_timing: id 0 | task 8060 | total time = 1342.47 ms / 475 tokens 2.03.493.895 I slot print_timing: id 0 | task 8060 | graphs reused = 7541 2.03.493.896 I slot print_timing: id 0 | task 8060 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.493.924 I slot release: id 0 | task 8060 | stop processing: n_tokens = 506, truncated = 0 2.03.511.201 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 123403442 2.03.511.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 2.03.603.863 I slot launch_slot_: id 0 | task 8166 | processing task, is_child = 0 2.06.446.210 I slot print_timing: id 0 | task 8166 | prompt eval time = 164.54 ms / 454 tokens ( 0.36 ms per token, 2759.26 tokens per second) 2.06.446.215 I slot print_timing: id 0 | task 8166 | eval time = 2677.79 ms / 230 tokens ( 11.69 ms per token, 85.52 tokens per second) 2.06.446.216 I slot print_timing: id 0 | task 8166 | total time = 2842.33 ms / 684 tokens 2.06.446.217 I slot print_timing: id 0 | task 8166 | graphs reused = 7768 2.06.446.218 I slot print_timing: id 0 | task 8166 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.446.252 I slot release: id 0 | task 8166 | stop processing: n_tokens = 715, truncated = 0 2.06.463.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 126355769 2.06.463.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 2.06.559.804 I slot launch_slot_: id 0 | task 8399 | processing task, is_child = 0 2.09.335.155 I slot print_timing: id 0 | task 8399 | prompt eval time = 150.41 ms / 354 tokens ( 0.42 ms per token, 2353.60 tokens per second) 2.09.335.161 I slot print_timing: id 0 | task 8399 | eval time = 2624.92 ms / 226 tokens ( 11.67 ms per token, 85.72 tokens per second) 2.09.335.162 I slot print_timing: id 0 | task 8399 | total time = 2775.33 ms / 580 tokens 2.09.335.162 I slot print_timing: id 0 | task 8399 | graphs reused = 7991 2.09.335.163 I slot print_timing: id 0 | task 8399 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.335.194 I slot release: id 0 | task 8399 | stop processing: n_tokens = 611, truncated = 0 2.09.339.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 129244711 2.09.339.078 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.09.445.386 I slot launch_slot_: id 0 | task 8628 | processing task, is_child = 0 2.11.220.189 I slot print_timing: id 0 | task 8628 | prompt eval time = 153.19 ms / 334 tokens ( 0.46 ms per token, 2180.26 tokens per second) 2.11.220.195 I slot print_timing: id 0 | task 8628 | eval time = 1621.59 ms / 140 tokens ( 11.67 ms per token, 85.72 tokens per second) 2.11.220.196 I slot print_timing: id 0 | task 8628 | total time = 1774.78 ms / 474 tokens 2.11.220.197 I slot print_timing: id 0 | task 8628 | graphs reused = 8129 2.11.220.198 I slot print_timing: id 0 | task 8628 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.220.226 I slot release: id 0 | task 8628 | stop processing: n_tokens = 505, truncated = 0 2.11.241.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 131129743 2.11.241.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 2.11.335.564 I slot launch_slot_: id 0 | task 8771 | processing task, is_child = 0 2.13.531.397 I slot print_timing: id 0 | task 8771 | prompt eval time = 162.78 ms / 426 tokens ( 0.38 ms per token, 2617.00 tokens per second) 2.13.531.403 I slot print_timing: id 0 | task 8771 | eval time = 2033.03 ms / 175 tokens ( 11.68 ms per token, 85.59 tokens per second) 2.13.531.404 I slot print_timing: id 0 | task 8771 | total time = 2195.81 ms / 601 tokens 2.13.531.404 I slot print_timing: id 0 | task 8771 | graphs reused = 8301 2.13.531.405 I slot print_timing: id 0 | task 8771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.531.437 I slot release: id 0 | task 8771 | stop processing: n_tokens = 632, truncated = 0 2.13.535.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 133440955 2.13.535.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.13.608.733 I slot launch_slot_: id 0 | task 8949 | processing task, is_child = 0 2.15.117.576 I slot print_timing: id 0 | task 8949 | prompt eval time = 152.38 ms / 366 tokens ( 0.42 ms per token, 2401.87 tokens per second) 2.15.117.582 I slot print_timing: id 0 | task 8949 | eval time = 1356.44 ms / 117 tokens ( 11.69 ms per token, 85.52 tokens per second) 2.15.117.583 I slot print_timing: id 0 | task 8949 | total time = 1508.82 ms / 483 tokens 2.15.117.583 I slot print_timing: id 0 | task 8949 | graphs reused = 8415 2.15.117.584 I slot print_timing: id 0 | task 8949 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.117.613 I slot release: id 0 | task 8949 | stop processing: n_tokens = 514, truncated = 0 2.15.135.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 135027130 2.15.135.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.15.227.693 I slot launch_slot_: id 0 | task 9069 | processing task, is_child = 0 2.18.400.077 I slot print_timing: id 0 | task 9069 | n_gen = 258, tg = 85.62 t/s, tg_3s = 85.95 t/s 2.18.458.382 I slot print_timing: id 0 | task 9069 | prompt eval time = 170.63 ms / 462 tokens ( 0.37 ms per token, 2707.55 tokens per second) 2.18.458.387 I slot print_timing: id 0 | task 9069 | eval time = 3060.03 ms / 263 tokens ( 11.68 ms per token, 85.62 tokens per second) 2.18.458.388 I slot print_timing: id 0 | task 9069 | total time = 3230.67 ms / 725 tokens 2.18.458.389 I slot print_timing: id 0 | task 9069 | graphs reused = 8675 2.18.458.390 I slot print_timing: id 0 | task 9069 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.458.423 I slot release: id 0 | task 9069 | stop processing: n_tokens = 756, truncated = 0 2.18.485.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 138367940 2.18.485.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.18.581.414 I slot launch_slot_: id 0 | task 9335 | processing task, is_child = 0 2.20.348.625 I slot print_timing: id 0 | task 9335 | prompt eval time = 154.78 ms / 396 tokens ( 0.39 ms per token, 2558.40 tokens per second) 2.20.348.631 I slot print_timing: id 0 | task 9335 | eval time = 1612.41 ms / 139 tokens ( 11.68 ms per token, 85.59 tokens per second) 2.20.348.632 I slot print_timing: id 0 | task 9335 | total time = 1767.19 ms / 535 tokens 2.20.348.633 I slot print_timing: id 0 | task 9335 | graphs reused = 8811 2.20.348.634 I slot print_timing: id 0 | task 9335 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.348.666 I slot release: id 0 | task 9335 | stop processing: n_tokens = 566, truncated = 0 2.20.363.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 140258184 2.20.426.697 I slot launch_slot_: id 0 | task 9477 | processing task, is_child = 0 2.22.462.960 I slot print_timing: id 0 | task 9477 | prompt eval time = 165.65 ms / 458 tokens ( 0.36 ms per token, 2764.82 tokens per second) 2.22.462.966 I slot print_timing: id 0 | task 9477 | eval time = 1870.59 ms / 161 tokens ( 11.69 ms per token, 85.53 tokens per second) 2.22.462.967 I slot print_timing: id 0 | task 9477 | total time = 2036.24 ms / 619 tokens 2.22.462.968 I slot print_timing: id 0 | task 9477 | graphs reused = 8969 2.22.462.969 I slot print_timing: id 0 | task 9477 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.463.002 I slot release: id 0 | task 9477 | stop processing: n_tokens = 650, truncated = 0 2.22.482.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 142372519 2.22.482.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 2.22.579.046 I slot launch_slot_: id 0 | task 9641 | processing task, is_child = 0 2.24.834.008 I slot print_timing: id 0 | task 9641 | prompt eval time = 173.85 ms / 458 tokens ( 0.38 ms per token, 2634.39 tokens per second) 2.24.834.014 I slot print_timing: id 0 | task 9641 | eval time = 2081.09 ms / 176 tokens ( 11.89 ms per token, 84.09 tokens per second) 2.24.834.015 I slot print_timing: id 0 | task 9641 | total time = 2254.94 ms / 634 tokens 2.24.834.016 I slot print_timing: id 0 | task 9641 | graphs reused = 9142 2.24.834.016 I slot print_timing: id 0 | task 9641 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.834.047 I slot release: id 0 | task 9641 | stop processing: n_tokens = 665, truncated = 0 2.24.851.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 144743565 2.24.851.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.24.932.963 I slot launch_slot_: id 0 | task 9820 | processing task, is_child = 0 2.27.538.206 I slot print_timing: id 0 | task 9820 | prompt eval time = 164.51 ms / 452 tokens ( 0.36 ms per token, 2747.62 tokens per second) 2.27.538.212 I slot print_timing: id 0 | task 9820 | eval time = 2440.72 ms / 210 tokens ( 11.68 ms per token, 85.63 tokens per second) 2.27.538.213 I slot print_timing: id 0 | task 9820 | total time = 2605.22 ms / 662 tokens 2.27.538.214 I slot print_timing: id 0 | task 9820 | graphs reused = 9349 2.27.538.215 I slot print_timing: id 0 | task 9820 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.538.247 I slot release: id 0 | task 9820 | stop processing: n_tokens = 693, truncated = 0 2.27.565.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 147447764 2.27.565.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.27.664.520 I slot launch_slot_: id 0 | task 10033 | processing task, is_child = 0 2.29.219.622 I slot print_timing: id 0 | task 10033 | prompt eval time = 158.84 ms / 404 tokens ( 0.39 ms per token, 2543.42 tokens per second) 2.29.219.628 I slot print_timing: id 0 | task 10033 | eval time = 1396.24 ms / 120 tokens ( 11.73 ms per token, 85.23 tokens per second) 2.29.219.629 I slot print_timing: id 0 | task 10033 | total time = 1555.08 ms / 524 tokens 2.29.219.630 I slot print_timing: id 0 | task 10033 | graphs reused = 9466 2.29.219.631 I slot print_timing: id 0 | task 10033 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.219.662 I slot release: id 0 | task 10033 | stop processing: n_tokens = 555, truncated = 0 2.29.233.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 149129179 2.29.233.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.29.327.281 I slot launch_slot_: id 0 | task 10156 | processing task, is_child = 0 2.30.713.865 I slot print_timing: id 0 | task 10156 | prompt eval time = 149.81 ms / 345 tokens ( 0.43 ms per token, 2302.96 tokens per second) 2.30.713.871 I slot print_timing: id 0 | task 10156 | eval time = 1236.76 ms / 106 tokens ( 11.78 ms per token, 84.90 tokens per second) 2.30.713.872 I slot print_timing: id 0 | task 10156 | total time = 1386.56 ms / 451 tokens 2.30.713.873 I slot print_timing: id 0 | task 10156 | graphs reused = 9570 2.30.713.873 I slot print_timing: id 0 | task 10156 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.713.900 I slot release: id 0 | task 10156 | stop processing: n_tokens = 482, truncated = 0 2.30.727.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 150623417 2.30.727.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.30.817.564 I slot launch_slot_: id 0 | task 10265 | processing task, is_child = 0 2.32.209.159 I slot print_timing: id 0 | task 10265 | prompt eval time = 171.57 ms / 430 tokens ( 0.40 ms per token, 2506.27 tokens per second) 2.32.209.166 I slot print_timing: id 0 | task 10265 | eval time = 1220.00 ms / 105 tokens ( 11.73 ms per token, 85.25 tokens per second) 2.32.209.167 I slot print_timing: id 0 | task 10265 | total time = 1391.57 ms / 535 tokens 2.32.209.168 I slot print_timing: id 0 | task 10265 | graphs reused = 9672 2.32.209.169 I slot print_timing: id 0 | task 10265 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.209.204 I slot release: id 0 | task 10265 | stop processing: n_tokens = 566, truncated = 0 2.32.227.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 152118721 2.32.227.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.32.323.833 I slot launch_slot_: id 0 | task 10373 | processing task, is_child = 0 2.33.485.718 I slot print_timing: id 0 | task 10373 | prompt eval time = 146.10 ms / 316 tokens ( 0.46 ms per token, 2162.95 tokens per second) 2.33.485.725 I slot print_timing: id 0 | task 10373 | eval time = 1015.77 ms / 85 tokens ( 12.09 ms per token, 82.70 tokens per second) 2.33.485.726 I slot print_timing: id 0 | task 10373 | total time = 1161.87 ms / 401 tokens 2.33.485.727 I slot print_timing: id 0 | task 10373 | graphs reused = 9755 2.33.485.727 I slot print_timing: id 0 | task 10373 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.485.757 I slot release: id 0 | task 10373 | stop processing: n_tokens = 432, truncated = 0 2.33.498.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 153395275 2.33.498.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.33.586.619 I slot launch_slot_: id 0 | task 10461 | processing task, is_child = 0 2.34.974.865 I slot print_timing: id 0 | task 10461 | prompt eval time = 150.82 ms / 354 tokens ( 0.43 ms per token, 2347.22 tokens per second) 2.34.974.873 I slot print_timing: id 0 | task 10461 | eval time = 1237.41 ms / 107 tokens ( 11.67 ms per token, 85.66 tokens per second) 2.34.974.874 I slot print_timing: id 0 | task 10461 | total time = 1388.23 ms / 461 tokens 2.34.974.875 I slot print_timing: id 0 | task 10461 | graphs reused = 9860 2.34.974.876 I slot print_timing: id 0 | task 10461 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.974.907 I slot release: id 0 | task 10461 | stop processing: n_tokens = 492, truncated = 0 2.34.979.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 154884424 2.34.979.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.35.087.612 I slot launch_slot_: id 0 | task 10571 | processing task, is_child = 0 2.36.401.930 I slot print_timing: id 0 | task 10571 | prompt eval time = 174.81 ms / 438 tokens ( 0.40 ms per token, 2505.58 tokens per second) 2.36.401.936 I slot print_timing: id 0 | task 10571 | eval time = 1139.49 ms / 98 tokens ( 11.75 ms per token, 85.13 tokens per second) 2.36.401.937 I slot print_timing: id 0 | task 10571 | total time = 1314.30 ms / 536 tokens 2.36.401.938 I slot print_timing: id 0 | task 10571 | graphs reused = 9955 2.36.401.939 I slot print_timing: id 0 | task 10571 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.401.970 I slot release: id 0 | task 10571 | stop processing: n_tokens = 567, truncated = 0 2.36.424.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 156311487 2.36.424.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.36.532.122 I slot launch_slot_: id 0 | task 10672 | processing task, is_child = 0 2.37.518.484 I slot print_timing: id 0 | task 10672 | prompt eval time = 175.06 ms / 457 tokens ( 0.38 ms per token, 2610.49 tokens per second) 2.37.518.490 I slot print_timing: id 0 | task 10672 | eval time = 811.28 ms / 70 tokens ( 11.76 ms per token, 85.05 tokens per second) 2.37.518.491 I slot print_timing: id 0 | task 10672 | total time = 986.34 ms / 527 tokens 2.37.518.492 I slot print_timing: id 0 | task 10672 | graphs reused = 10022 2.37.518.492 I slot print_timing: id 0 | task 10672 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.518.523 I slot release: id 0 | task 10672 | stop processing: n_tokens = 558, truncated = 0 2.37.544.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 157428040 2.37.544.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.37.640.294 I slot launch_slot_: id 0 | task 10745 | processing task, is_child = 0 2.38.954.426 I slot print_timing: id 0 | task 10745 | prompt eval time = 178.46 ms / 473 tokens ( 0.38 ms per token, 2650.41 tokens per second) 2.38.954.431 I slot print_timing: id 0 | task 10745 | eval time = 1135.65 ms / 98 tokens ( 11.71 ms per token, 85.41 tokens per second) 2.38.954.432 I slot print_timing: id 0 | task 10745 | total time = 1314.11 ms / 571 tokens 2.38.954.434 I slot print_timing: id 0 | task 10745 | graphs reused = 10117 2.38.954.434 I slot print_timing: id 0 | task 10745 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.954.465 I slot release: id 0 | task 10745 | stop processing: n_tokens = 602, truncated = 0 2.38.976.351 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 158863983 2.38.976.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.39.079.238 I slot launch_slot_: id 0 | task 10846 | processing task, is_child = 0 2.39.567.699 I slot print_timing: id 0 | task 10846 | prompt eval time = 177.26 ms / 476 tokens ( 0.37 ms per token, 2685.34 tokens per second) 2.39.567.705 I slot print_timing: id 0 | task 10846 | eval time = 311.18 ms / 27 tokens ( 11.97 ms per token, 83.55 tokens per second) 2.39.567.706 I slot print_timing: id 0 | task 10846 | total time = 488.44 ms / 503 tokens 2.39.567.707 I slot print_timing: id 0 | task 10846 | graphs reused = 10141 2.39.567.708 I slot print_timing: id 0 | task 10846 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.567.741 I slot release: id 0 | task 10846 | stop processing: n_tokens = 534, truncated = 0 2.39.581.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 159477258 2.39.581.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.39.677.186 I slot launch_slot_: id 0 | task 10876 | processing task, is_child = 0 2.41.098.509 I slot print_timing: id 0 | task 10876 | prompt eval time = 177.43 ms / 466 tokens ( 0.38 ms per token, 2626.45 tokens per second) 2.41.098.515 I slot print_timing: id 0 | task 10876 | eval time = 1243.88 ms / 107 tokens ( 11.73 ms per token, 85.22 tokens per second) 2.41.098.516 I slot print_timing: id 0 | task 10876 | total time = 1421.30 ms / 573 tokens 2.41.098.517 I slot print_timing: id 0 | task 10876 | graphs reused = 10245 2.41.098.517 I slot print_timing: id 0 | task 10876 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.098.549 I slot release: id 0 | task 10876 | stop processing: n_tokens = 604, truncated = 0 2.41.127.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 161008066 2.41.127.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.41.222.757 I slot launch_slot_: id 0 | task 10986 | processing task, is_child = 0 2.42.283.563 I slot print_timing: id 0 | task 10986 | prompt eval time = 155.08 ms / 415 tokens ( 0.37 ms per token, 2676.06 tokens per second) 2.42.283.569 I slot print_timing: id 0 | task 10986 | eval time = 905.71 ms / 78 tokens ( 11.76 ms per token, 85.02 tokens per second) 2.42.283.570 I slot print_timing: id 0 | task 10986 | total time = 1060.79 ms / 493 tokens 2.42.283.571 I slot print_timing: id 0 | task 10986 | graphs reused = 10320 2.42.283.572 I slot print_timing: id 0 | task 10986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.283.602 I slot release: id 0 | task 10986 | stop processing: n_tokens = 524, truncated = 0 2.42.299.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 162193119 2.42.299.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.42.374.719 I slot launch_slot_: id 0 | task 11067 | processing task, is_child = 0 2.43.262.020 I slot print_timing: id 0 | task 11067 | prompt eval time = 150.49 ms / 352 tokens ( 0.43 ms per token, 2339.07 tokens per second) 2.43.262.026 I slot print_timing: id 0 | task 11067 | eval time = 736.79 ms / 64 tokens ( 11.70 ms per token, 85.51 tokens per second) 2.43.262.027 I slot print_timing: id 0 | task 11067 | total time = 887.28 ms / 416 tokens 2.43.262.028 I slot print_timing: id 0 | task 11067 | graphs reused = 10382 2.43.262.029 I slot print_timing: id 0 | task 11067 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.262.058 I slot release: id 0 | task 11067 | stop processing: n_tokens = 447, truncated = 0 2.43.283.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 163171575 2.43.283.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.43.366.505 I slot launch_slot_: id 0 | task 11134 | processing task, is_child = 0 2.45.099.784 I slot print_timing: id 0 | task 11134 | prompt eval time = 193.41 ms / 550 tokens ( 0.35 ms per token, 2843.70 tokens per second) 2.45.099.790 I slot print_timing: id 0 | task 11134 | eval time = 1539.85 ms / 133 tokens ( 11.67 ms per token, 85.72 tokens per second) 2.45.099.791 I slot print_timing: id 0 | task 11134 | total time = 1733.26 ms / 683 tokens 2.45.099.792 I slot print_timing: id 0 | task 11134 | graphs reused = 10513 2.45.099.793 I slot print_timing: id 0 | task 11134 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.099.830 I slot release: id 0 | task 11134 | stop processing: n_tokens = 714, truncated = 0 2.45.117.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 165009347 2.45.117.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.45.223.527 I slot launch_slot_: id 0 | task 11271 | processing task, is_child = 0 2.48.114.164 I slot print_timing: id 0 | task 11271 | prompt eval time = 232.07 ms / 772 tokens ( 0.30 ms per token, 3326.64 tokens per second) 2.48.114.170 I slot print_timing: id 0 | task 11271 | eval time = 2658.55 ms / 226 tokens ( 11.82 ms per token, 84.63 tokens per second) 2.48.114.171 I slot print_timing: id 0 | task 11271 | total time = 2890.61 ms / 998 tokens 2.48.114.172 I slot print_timing: id 0 | task 11271 | graphs reused = 10736 2.48.114.173 I slot print_timing: id 0 | task 11271 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.114.215 I slot release: id 0 | task 11271 | stop processing: n_tokens = 1029, truncated = 0 2.48.134.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 168023733 2.48.134.800 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.48.244.760 I slot launch_slot_: id 0 | task 11501 | processing task, is_child = 0 2.50.599.157 I slot print_timing: id 0 | task 11501 | prompt eval time = 238.72 ms / 683 tokens ( 0.35 ms per token, 2861.14 tokens per second) 2.50.599.163 I slot print_timing: id 0 | task 11501 | eval time = 2115.66 ms / 181 tokens ( 11.75 ms per token, 85.08 tokens per second) 2.50.599.164 I slot print_timing: id 0 | task 11501 | total time = 2354.38 ms / 864 tokens 2.50.599.165 I slot print_timing: id 0 | task 11501 | graphs reused = 10914 2.50.599.165 I slot print_timing: id 0 | task 11501 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.599.203 I slot release: id 0 | task 11501 | stop processing: n_tokens = 895, truncated = 0 2.50.623.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 170508720 2.50.624.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.50.728.730 I slot launch_slot_: id 0 | task 11686 | processing task, is_child = 0 2.53.474.803 I slot print_timing: id 0 | task 11686 | prompt eval time = 206.69 ms / 579 tokens ( 0.36 ms per token, 2801.35 tokens per second) 2.53.474.809 I slot print_timing: id 0 | task 11686 | eval time = 2539.37 ms / 218 tokens ( 11.70 ms per token, 85.45 tokens per second) 2.53.474.810 I slot print_timing: id 0 | task 11686 | total time = 2746.05 ms / 797 tokens 2.53.474.811 I slot print_timing: id 0 | task 11686 | graphs reused = 11129 2.53.474.812 I slot print_timing: id 0 | task 11686 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.474.846 I slot release: id 0 | task 11686 | stop processing: n_tokens = 828, truncated = 0 2.53.499.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 173384364 2.53.499.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.53.519.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.53.623.151 I slot launch_slot_: id 0 | task 11908 | processing task, is_child = 0 2.55.038.068 I slot print_timing: id 0 | task 11908 | prompt eval time = 185.85 ms / 500 tokens ( 0.37 ms per token, 2690.37 tokens per second) 2.55.038.073 I slot print_timing: id 0 | task 11908 | eval time = 1229.05 ms / 106 tokens ( 11.71 ms per token, 85.43 tokens per second) 2.55.038.075 I slot print_timing: id 0 | task 11908 | total time = 1414.89 ms / 606 tokens 2.55.038.077 I slot print_timing: id 0 | task 11908 | graphs reused = 11233 2.55.038.077 I slot print_timing: id 0 | task 11908 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.038.112 I slot release: id 0 | task 11908 | stop processing: n_tokens = 637, truncated = 0 2.55.056.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 174947629 2.55.056.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.55.137.157 I slot launch_slot_: id 0 | task 12017 | processing task, is_child = 0 2.57.808.550 I slot print_timing: id 0 | task 12017 | prompt eval time = 237.81 ms / 776 tokens ( 0.31 ms per token, 3263.08 tokens per second) 2.57.808.555 I slot print_timing: id 0 | task 12017 | eval time = 2433.56 ms / 209 tokens ( 11.70 ms per token, 85.47 tokens per second) 2.57.808.557 I slot print_timing: id 0 | task 12017 | total time = 2671.37 ms / 985 tokens 2.57.808.557 I slot print_timing: id 0 | task 12017 | graphs reused = 11440 2.57.808.558 I slot print_timing: id 0 | task 12017 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.808.598 I slot release: id 0 | task 12017 | stop processing: n_tokens = 1016, truncated = 0 2.57.812.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 177718115 2.57.813.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.57.893.669 I slot launch_slot_: id 0 | task 12230 | processing task, is_child = 0 3.00.370.084 I slot print_timing: id 0 | task 12230 | prompt eval time = 185.24 ms / 504 tokens ( 0.37 ms per token, 2720.77 tokens per second) 3.00.370.090 I slot print_timing: id 0 | task 12230 | eval time = 2291.15 ms / 197 tokens ( 11.69 ms per token, 85.55 tokens per second) 3.00.370.091 I slot print_timing: id 0 | task 12230 | total time = 2476.39 ms / 701 tokens 3.00.370.091 I slot print_timing: id 0 | task 12230 | graphs reused = 11635 3.00.370.092 I slot print_timing: id 0 | task 12230 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.370.126 I slot release: id 0 | task 12230 | stop processing: n_tokens = 732, truncated = 0 3.00.397.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 180279643 3.00.397.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 3.00.485.537 I slot launch_slot_: id 0 | task 12430 | processing task, is_child = 0 3.03.106.542 I slot print_timing: id 0 | task 12430 | prompt eval time = 210.82 ms / 633 tokens ( 0.33 ms per token, 3002.56 tokens per second) 3.03.106.548 I slot print_timing: id 0 | task 12430 | eval time = 2410.17 ms / 207 tokens ( 11.70 ms per token, 85.47 tokens per second) 3.03.106.549 I slot print_timing: id 0 | task 12430 | total time = 2620.99 ms / 840 tokens 3.03.106.550 I slot print_timing: id 0 | task 12430 | graphs reused = 11839 3.03.106.551 I slot print_timing: id 0 | task 12430 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.106.588 I slot release: id 0 | task 12430 | stop processing: n_tokens = 871, truncated = 0 3.03.132.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 183016105 3.03.132.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 3.03.241.369 I slot launch_slot_: id 0 | task 12641 | processing task, is_child = 0 3.04.967.440 I slot print_timing: id 0 | task 12641 | prompt eval time = 162.75 ms / 395 tokens ( 0.41 ms per token, 2427.04 tokens per second) 3.04.967.446 I slot print_timing: id 0 | task 12641 | eval time = 1563.30 ms / 134 tokens ( 11.75 ms per token, 85.08 tokens per second) 3.04.967.447 I slot print_timing: id 0 | task 12641 | total time = 1726.05 ms / 529 tokens 3.04.967.448 I slot print_timing: id 0 | task 12641 | graphs reused = 11970 3.04.967.448 I slot print_timing: id 0 | task 12641 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.967.477 I slot release: id 0 | task 12641 | stop processing: n_tokens = 560, truncated = 0 3.04.987.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 184876995 3.04.987.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.05.083.731 I slot launch_slot_: id 0 | task 12778 | processing task, is_child = 0 3.07.719.053 I slot print_timing: id 0 | task 12778 | prompt eval time = 201.72 ms / 584 tokens ( 0.35 ms per token, 2895.07 tokens per second) 3.07.719.059 I slot print_timing: id 0 | task 12778 | eval time = 2433.58 ms / 209 tokens ( 11.70 ms per token, 85.47 tokens per second) 3.07.719.060 I slot print_timing: id 0 | task 12778 | total time = 2635.30 ms / 793 tokens 3.07.719.061 I slot print_timing: id 0 | task 12778 | graphs reused = 12176 3.07.719.062 I slot print_timing: id 0 | task 12778 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.719.112 I slot release: id 0 | task 12778 | stop processing: n_tokens = 824, truncated = 0 3.07.738.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 187628630 3.07.738.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 3.07.848.974 I slot launch_slot_: id 0 | task 12991 | processing task, is_child = 0 3.10.762.480 I slot print_timing: id 0 | task 12991 | prompt eval time = 226.53 ms / 695 tokens ( 0.33 ms per token, 3067.97 tokens per second) 3.10.762.486 I slot print_timing: id 0 | task 12991 | eval time = 2686.95 ms / 230 tokens ( 11.73 ms per token, 85.23 tokens per second) 3.10.762.487 I slot print_timing: id 0 | task 12991 | total time = 2913.49 ms / 925 tokens 3.10.762.488 I slot print_timing: id 0 | task 12991 | graphs reused = 12403 3.10.762.489 I slot print_timing: id 0 | task 12991 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.762.527 I slot release: id 0 | task 12991 | stop processing: n_tokens = 956, truncated = 0 3.10.792.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 190672044 3.10.792.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 3.10.874.806 I slot launch_slot_: id 0 | task 13225 | processing task, is_child = 0 3.13.355.716 I slot print_timing: id 0 | task 13225 | prompt eval time = 241.69 ms / 769 tokens ( 0.31 ms per token, 3181.72 tokens per second) 3.13.355.722 I slot print_timing: id 0 | task 13225 | eval time = 2239.20 ms / 191 tokens ( 11.79 ms per token, 84.85 tokens per second) 3.13.355.723 I slot print_timing: id 0 | task 13225 | total time = 2480.89 ms / 960 tokens 3.13.355.724 I slot print_timing: id 0 | task 13225 | graphs reused = 12592 3.13.355.725 I slot print_timing: id 0 | task 13225 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.355.766 I slot release: id 0 | task 13225 | stop processing: n_tokens = 991, truncated = 0 3.13.371.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 193265283 3.13.371.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 3.13.391.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 3.13.516.794 I slot launch_slot_: id 0 | task 13420 | processing task, is_child = 0 3.15.156.009 I slot print_timing: id 0 | task 13420 | prompt eval time = 199.43 ms / 576 tokens ( 0.35 ms per token, 2888.17 tokens per second) 3.15.156.015 I slot print_timing: id 0 | task 13420 | eval time = 1439.76 ms / 124 tokens ( 11.71 ms per token, 85.43 tokens per second) 3.15.156.016 I slot print_timing: id 0 | task 13420 | total time = 1639.19 ms / 700 tokens 3.15.156.017 I slot print_timing: id 0 | task 13420 | graphs reused = 12714 3.15.156.018 I slot print_timing: id 0 | task 13420 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.156.054 I slot release: id 0 | task 13420 | stop processing: n_tokens = 731, truncated = 0 3.15.171.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 195065571 3.15.171.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 3.15.261.390 I slot launch_slot_: id 0 | task 13548 | processing task, is_child = 0 3.18.479.431 I slot print_timing: id 0 | task 13548 | n_gen = 257, tg = 85.30 t/s, tg_3s = 85.63 t/s 3.18.689.130 I slot print_timing: id 0 | task 13548 | prompt eval time = 216.74 ms / 655 tokens ( 0.33 ms per token, 3022.12 tokens per second) 3.18.689.136 I slot print_timing: id 0 | task 13548 | eval time = 3210.99 ms / 275 tokens ( 11.72 ms per token, 85.33 tokens per second) 3.18.689.137 I slot print_timing: id 0 | task 13548 | total time = 3427.72 ms / 930 tokens 3.18.689.138 I slot print_timing: id 0 | task 13548 | graphs reused = 12986 3.18.689.138 I slot print_timing: id 0 | task 13548 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.689.176 I slot release: id 0 | task 13548 | stop processing: n_tokens = 961, truncated = 0 3.18.693.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 198598693 3.18.693.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.18.798.946 I slot launch_slot_: id 0 | task 13827 | processing task, is_child = 0 3.20.416.539 I slot print_timing: id 0 | task 13827 | prompt eval time = 209.68 ms / 621 tokens ( 0.34 ms per token, 2961.71 tokens per second) 3.20.416.545 I slot print_timing: id 0 | task 13827 | eval time = 1407.90 ms / 121 tokens ( 11.73 ms per token, 85.23 tokens per second) 3.20.416.546 I slot print_timing: id 0 | task 13827 | total time = 1617.57 ms / 742 tokens 3.20.416.547 I slot print_timing: id 0 | task 13827 | graphs reused = 13104 3.20.416.548 I slot print_timing: id 0 | task 13827 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.416.586 I slot release: id 0 | task 13827 | stop processing: n_tokens = 773, truncated = 0 3.20.437.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 200326103 3.20.438.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 3.20.541.754 I slot launch_slot_: id 0 | task 13952 | processing task, is_child = 0 3.22.875.307 I slot print_timing: id 0 | task 13952 | prompt eval time = 231.98 ms / 767 tokens ( 0.30 ms per token, 3306.36 tokens per second) 3.22.875.313 I slot print_timing: id 0 | task 13952 | eval time = 2101.56 ms / 178 tokens ( 11.87 ms per token, 84.22 tokens per second) 3.22.875.314 I slot print_timing: id 0 | task 13952 | total time = 2333.53 ms / 945 tokens 3.22.875.316 I slot print_timing: id 0 | task 13952 | graphs reused = 13280 3.22.875.317 I slot print_timing: id 0 | task 13952 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.875.361 I slot release: id 0 | task 13952 | stop processing: n_tokens = 976, truncated = 0 3.22.889.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 202784879 3.22.889.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 3.22.993.434 I slot launch_slot_: id 0 | task 14134 | processing task, is_child = 0 3.25.670.319 I slot print_timing: id 0 | task 14134 | prompt eval time = 259.61 ms / 864 tokens ( 0.30 ms per token, 3328.08 tokens per second) 3.25.670.324 I slot print_timing: id 0 | task 14134 | eval time = 2417.26 ms / 203 tokens ( 11.97 ms per token, 83.57 tokens per second) 3.25.670.325 I slot print_timing: id 0 | task 14134 | total time = 2676.86 ms / 1067 tokens 3.25.670.326 I slot print_timing: id 0 | task 14134 | graphs reused = 13480 3.25.670.327 I slot print_timing: id 0 | task 14134 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.670.371 I slot release: id 0 | task 14134 | stop processing: n_tokens = 1098, truncated = 0 3.25.687.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 205579889 3.25.687.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.25.707.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.25.822.426 I slot launch_slot_: id 0 | task 14341 | processing task, is_child = 0 3.27.544.094 I slot print_timing: id 0 | task 14341 | prompt eval time = 222.91 ms / 646 tokens ( 0.35 ms per token, 2898.07 tokens per second) 3.27.544.100 I slot print_timing: id 0 | task 14341 | eval time = 1498.74 ms / 129 tokens ( 11.71 ms per token, 85.41 tokens per second) 3.27.544.101 I slot print_timing: id 0 | task 14341 | total time = 1721.65 ms / 775 tokens 3.27.544.101 I slot print_timing: id 0 | task 14341 | graphs reused = 13606 3.27.544.102 I slot print_timing: id 0 | task 14341 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.544.142 I slot release: id 0 | task 14341 | stop processing: n_tokens = 806, truncated = 0 3.27.560.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 207453660 3.27.560.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.27.649.429 I slot launch_slot_: id 0 | task 14474 | processing task, is_child = 0 3.30.514.749 I slot print_timing: id 0 | task 14474 | prompt eval time = 227.62 ms / 720 tokens ( 0.32 ms per token, 3163.22 tokens per second) 3.30.514.755 I slot print_timing: id 0 | task 14474 | eval time = 2637.68 ms / 222 tokens ( 11.94 ms per token, 83.79 tokens per second) 3.30.514.756 I slot print_timing: id 0 | task 14474 | total time = 2865.30 ms / 942 tokens 3.30.514.756 I slot print_timing: id 0 | task 14474 | graphs reused = 13825 3.30.514.757 I slot print_timing: id 0 | task 14474 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.514.798 I slot release: id 0 | task 14474 | stop processing: n_tokens = 973, truncated = 0 3.30.535.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 210424315 3.30.535.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 3.30.641.546 I slot launch_slot_: id 0 | task 14700 | processing task, is_child = 0 3.33.310.467 I slot print_timing: id 0 | task 14700 | prompt eval time = 188.08 ms / 509 tokens ( 0.37 ms per token, 2706.25 tokens per second) 3.33.310.473 I slot print_timing: id 0 | task 14700 | eval time = 2480.82 ms / 214 tokens ( 11.65 ms per token, 85.86 tokens per second) 3.33.310.474 I slot print_timing: id 0 | task 14700 | total time = 2668.90 ms / 723 tokens 3.33.310.475 I slot print_timing: id 0 | task 14700 | graphs reused = 14037 3.33.310.476 I slot print_timing: id 0 | task 14700 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.310.510 I slot release: id 0 | task 14700 | stop processing: n_tokens = 754, truncated = 0 3.33.332.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 213220027 3.33.332.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 3.33.428.416 I slot launch_slot_: id 0 | task 14917 | processing task, is_child = 0 3.36.451.869 I slot print_timing: id 0 | task 14917 | prompt eval time = 200.65 ms / 581 tokens ( 0.35 ms per token, 2895.60 tokens per second) 3.36.451.874 I slot print_timing: id 0 | task 14917 | eval time = 2822.78 ms / 242 tokens ( 11.71 ms per token, 85.38 tokens per second) 3.36.451.875 I slot print_timing: id 0 | task 14917 | total time = 3023.43 ms / 823 tokens 3.36.451.876 I slot print_timing: id 0 | task 14917 | graphs reused = 14276 3.36.451.877 I slot print_timing: id 0 | task 14917 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.451.916 I slot release: id 0 | task 14917 | stop processing: n_tokens = 854, truncated = 0 3.36.469.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 216361434 3.36.469.379 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.36.573.218 I slot launch_slot_: id 0 | task 15163 | processing task, is_child = 0 3.39.406.009 I slot print_timing: id 0 | task 15163 | prompt eval time = 272.14 ms / 925 tokens ( 0.29 ms per token, 3399.04 tokens per second) 3.39.406.015 I slot print_timing: id 0 | task 15163 | eval time = 2560.64 ms / 220 tokens ( 11.69 ms per token, 85.53 tokens per second) 3.39.406.016 I slot print_timing: id 0 | task 15163 | total time = 2832.77 ms / 1145 tokens 3.39.406.017 I slot print_timing: id 0 | task 15163 | graphs reused = 14493 3.39.406.018 I slot print_timing: id 0 | task 15163 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.406.066 I slot release: id 0 | task 15163 | stop processing: n_tokens = 1176, truncated = 0 3.39.422.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 219315583 3.39.422.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.39.528.567 I slot launch_slot_: id 0 | task 15387 | processing task, is_child = 0 3.42.672.993 I slot print_timing: id 0 | task 15387 | prompt eval time = 256.12 ms / 885 tokens ( 0.29 ms per token, 3455.43 tokens per second) 3.42.672.999 I slot print_timing: id 0 | task 15387 | eval time = 2888.29 ms / 245 tokens ( 11.84 ms per token, 84.48 tokens per second) 3.42.673.001 I slot print_timing: id 0 | task 15387 | total time = 3144.41 ms / 1130 tokens 3.42.673.001 I slot print_timing: id 0 | task 15387 | graphs reused = 14735 3.42.673.002 I slot print_timing: id 0 | task 15387 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.673.047 I slot release: id 0 | task 15387 | stop processing: n_tokens = 1161, truncated = 0 3.42.701.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 222582564 3.42.701.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.42.813.383 I slot launch_slot_: id 0 | task 15636 | processing task, is_child = 0 3.44.779.341 I slot print_timing: id 0 | task 15636 | prompt eval time = 156.13 ms / 392 tokens ( 0.40 ms per token, 2510.79 tokens per second) 3.44.779.346 I slot print_timing: id 0 | task 15636 | eval time = 1809.81 ms / 156 tokens ( 11.68 ms per token, 85.64 tokens per second) 3.44.779.347 I slot print_timing: id 0 | task 15636 | total time = 1965.94 ms / 548 tokens 3.44.779.348 I slot print_timing: id 0 | task 15636 | graphs reused = 14888 3.44.779.349 I slot print_timing: id 0 | task 15636 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.779.377 I slot release: id 0 | task 15636 | stop processing: n_tokens = 579, truncated = 0 3.44.800.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 224688895 3.44.800.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.44.896.900 I slot launch_slot_: id 0 | task 15795 | processing task, is_child = 0 3.46.595.695 I slot print_timing: id 0 | task 15795 | prompt eval time = 149.25 ms / 331 tokens ( 0.45 ms per token, 2217.70 tokens per second) 3.46.595.701 I slot print_timing: id 0 | task 15795 | eval time = 1549.52 ms / 134 tokens ( 11.65 ms per token, 85.83 tokens per second) 3.46.595.702 I slot print_timing: id 0 | task 15795 | total time = 1698.77 ms / 465 tokens 3.46.595.702 I slot print_timing: id 0 | task 15795 | graphs reused = 15020 3.46.595.703 I slot print_timing: id 0 | task 15795 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.595.733 I slot release: id 0 | task 15795 | stop processing: n_tokens = 496, truncated = 0 3.46.616.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 226505250 3.46.616.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.46.712.339 I slot launch_slot_: id 0 | task 15932 | processing task, is_child = 0 3.48.729.446 I slot print_timing: id 0 | task 15932 | prompt eval time = 150.05 ms / 357 tokens ( 0.42 ms per token, 2379.19 tokens per second) 3.48.729.452 I slot print_timing: id 0 | task 15932 | eval time = 1867.04 ms / 161 tokens ( 11.67 ms per token, 85.70 tokens per second) 3.48.729.453 I slot print_timing: id 0 | task 15932 | total time = 2017.09 ms / 518 tokens 3.48.729.454 I slot print_timing: id 0 | task 15932 | graphs reused = 15178 3.48.729.455 I slot print_timing: id 0 | task 15932 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.729.487 I slot release: id 0 | task 15932 | stop processing: n_tokens = 549, truncated = 0 3.48.757.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 228639004 3.48.757.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.48.858.706 I slot launch_slot_: id 0 | task 16096 | processing task, is_child = 0 3.49.608.199 I slot print_timing: id 0 | task 16096 | prompt eval time = 152.14 ms / 315 tokens ( 0.48 ms per token, 2070.41 tokens per second) 3.49.608.205 I slot print_timing: id 0 | task 16096 | eval time = 597.33 ms / 52 tokens ( 11.71 ms per token, 85.38 tokens per second) 3.49.608.206 I slot print_timing: id 0 | task 16096 | total time = 749.47 ms / 367 tokens 3.49.608.207 I slot print_timing: id 0 | task 16096 | graphs reused = 15228 3.49.608.207 I slot print_timing: id 0 | task 16096 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.608.237 I slot release: id 0 | task 16096 | stop processing: n_tokens = 398, truncated = 0 3.49.629.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 229517754 3.49.629.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.49.714.151 I slot launch_slot_: id 0 | task 16151 | processing task, is_child = 0 3.50.810.379 I slot print_timing: id 0 | task 16151 | prompt eval time = 149.92 ms / 378 tokens ( 0.40 ms per token, 2521.38 tokens per second) 3.50.810.385 I slot print_timing: id 0 | task 16151 | eval time = 946.29 ms / 82 tokens ( 11.68 ms per token, 85.60 tokens per second) 3.50.810.386 I slot print_timing: id 0 | task 16151 | total time = 1096.21 ms / 460 tokens 3.50.810.387 I slot print_timing: id 0 | task 16151 | graphs reused = 15308 3.50.810.388 I slot print_timing: id 0 | task 16151 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.810.419 I slot release: id 0 | task 16151 | stop processing: n_tokens = 491, truncated = 0 3.50.828.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 230719937 3.50.828.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.50.905.287 I slot launch_slot_: id 0 | task 16236 | processing task, is_child = 0 3.51.364.189 I slot print_timing: id 0 | task 16236 | prompt eval time = 139.46 ms / 295 tokens ( 0.47 ms per token, 2115.38 tokens per second) 3.51.364.195 I slot print_timing: id 0 | task 16236 | eval time = 319.43 ms / 28 tokens ( 11.83 ms per token, 84.53 tokens per second) 3.51.364.196 I slot print_timing: id 0 | task 16236 | total time = 458.88 ms / 323 tokens 3.51.364.197 I slot print_timing: id 0 | task 16236 | graphs reused = 15334 3.51.364.198 I slot print_timing: id 0 | task 16236 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.364.225 I slot release: id 0 | task 16236 | stop processing: n_tokens = 354, truncated = 0 3.51.390.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 231273742 3.51.390.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.51.474.974 I slot launch_slot_: id 0 | task 16267 | processing task, is_child = 0 3.54.367.585 I slot print_timing: id 0 | task 16267 | prompt eval time = 145.17 ms / 337 tokens ( 0.43 ms per token, 2321.45 tokens per second) 3.54.367.591 I slot print_timing: id 0 | task 16267 | eval time = 2747.42 ms / 237 tokens ( 11.64 ms per token, 85.90 tokens per second) 3.54.367.592 I slot print_timing: id 0 | task 16267 | total time = 2892.59 ms / 574 tokens 3.54.367.593 I slot print_timing: id 0 | task 16267 | graphs reused = 15568 3.54.367.594 I slot print_timing: id 0 | task 16267 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.367.622 I slot release: id 0 | task 16267 | stop processing: n_tokens = 605, truncated = 0 3.54.385.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 234277139 3.54.385.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.54.484.849 I slot launch_slot_: id 0 | task 16507 | processing task, is_child = 0 3.55.896.178 I slot print_timing: id 0 | task 16507 | prompt eval time = 153.32 ms / 325 tokens ( 0.47 ms per token, 2119.72 tokens per second) 3.55.896.184 I slot print_timing: id 0 | task 16507 | eval time = 1257.99 ms / 108 tokens ( 11.76 ms per token, 85.06 tokens per second) 3.55.896.187 I slot print_timing: id 0 | task 16507 | total time = 1411.31 ms / 433 tokens 3.55.896.187 I slot print_timing: id 0 | task 16507 | graphs reused = 15674 3.55.896.188 I slot print_timing: id 0 | task 16507 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.896.218 I slot release: id 0 | task 16507 | stop processing: n_tokens = 464, truncated = 0 3.55.910.016 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.069 3.55.970.280 I slot launch_slot_: id 0 | task 16618 | processing task, is_child = 0 3.57.192.243 I slot print_timing: id 0 | task 16618 | prompt eval time = 130.68 ms / 264 tokens ( 0.49 ms per token, 2020.22 tokens per second) 3.57.192.249 I slot print_timing: id 0 | task 16618 | eval time = 1091.26 ms / 94 tokens ( 11.73 ms per token, 85.22 tokens per second) 3.57.192.250 I slot print_timing: id 0 | task 16618 | total time = 1221.94 ms / 358 tokens 3.57.192.250 I slot print_timing: id 0 | task 16618 | graphs reused = 15766 3.57.192.251 I slot print_timing: id 0 | task 16618 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.192.278 I slot release: id 0 | task 16618 | stop processing: n_tokens = 389, truncated = 0 3.57.209.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 237101795 3.57.209.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.57.308.398 I slot launch_slot_: id 0 | task 16715 | processing task, is_child = 0 3.57.693.608 I slot print_timing: id 0 | task 16715 | prompt eval time = 147.69 ms / 331 tokens ( 0.45 ms per token, 2241.17 tokens per second) 3.57.693.614 I slot print_timing: id 0 | task 16715 | eval time = 237.50 ms / 21 tokens ( 11.88 ms per token, 84.21 tokens per second) 3.57.693.615 I slot print_timing: id 0 | task 16715 | total time = 385.19 ms / 352 tokens 3.57.693.616 I slot print_timing: id 0 | task 16715 | graphs reused = 15785 3.57.693.617 I slot print_timing: id 0 | task 16715 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.693.646 I slot release: id 0 | task 16715 | stop processing: n_tokens = 383, truncated = 0 3.57.697.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 237603164 3.57.697.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.57.789.589 I slot launch_slot_: id 0 | task 16739 | processing task, is_child = 0 3.58.777.559 I slot print_timing: id 0 | task 16739 | prompt eval time = 146.54 ms / 333 tokens ( 0.44 ms per token, 2272.36 tokens per second) 3.58.777.564 I slot print_timing: id 0 | task 16739 | eval time = 841.40 ms / 73 tokens ( 11.69 ms per token, 85.57 tokens per second) 3.58.777.565 I slot print_timing: id 0 | task 16739 | total time = 987.95 ms / 406 tokens 3.58.777.566 I slot print_timing: id 0 | task 16739 | graphs reused = 15856 3.58.777.567 I slot print_timing: id 0 | task 16739 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.777.595 I slot release: id 0 | task 16739 | stop processing: n_tokens = 437, truncated = 0 3.58.802.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 238687112 3.58.802.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.58.881.619 I slot launch_slot_: id 0 | task 16815 | processing task, is_child = 0 3.59.639.753 I slot print_timing: id 0 | task 16815 | prompt eval time = 149.37 ms / 346 tokens ( 0.43 ms per token, 2316.38 tokens per second) 3.59.639.759 I slot print_timing: id 0 | task 16815 | eval time = 608.74 ms / 53 tokens ( 11.71 ms per token, 85.42 tokens per second) 3.59.639.760 I slot print_timing: id 0 | task 16815 | total time = 758.11 ms / 399 tokens 3.59.639.760 I slot print_timing: id 0 | task 16815 | graphs reused = 15907 3.59.639.761 I slot print_timing: id 0 | task 16815 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.639.790 I slot release: id 0 | task 16815 | stop processing: n_tokens = 430, truncated = 0 3.59.655.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 239549307 3.59.655.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.59.743.604 I slot launch_slot_: id 0 | task 16871 | processing task, is_child = 0 4.00.505.815 I slot print_timing: id 0 | task 16871 | prompt eval time = 146.88 ms / 325 tokens ( 0.45 ms per token, 2212.71 tokens per second) 4.00.505.821 I slot print_timing: id 0 | task 16871 | eval time = 615.31 ms / 53 tokens ( 11.83 ms per token, 84.51 tokens per second) 4.00.505.822 I slot print_timing: id 0 | task 16871 | total time = 762.19 ms / 378 tokens 4.00.505.823 I slot print_timing: id 0 | task 16871 | graphs reused = 15958 4.00.505.824 I slot print_timing: id 0 | task 16871 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.505.858 I slot release: id 0 | task 16871 | stop processing: n_tokens = 409, truncated = 0 4.00.526.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 240415375 4.00.526.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 4.00.617.288 I slot launch_slot_: id 0 | task 16927 | processing task, is_child = 0 4.03.168.708 I slot print_timing: id 0 | task 16927 | prompt eval time = 147.98 ms / 322 tokens ( 0.46 ms per token, 2176.01 tokens per second) 4.03.168.713 I slot print_timing: id 0 | task 16927 | eval time = 2403.42 ms / 207 tokens ( 11.67 ms per token, 85.71 tokens per second) 4.03.168.715 I slot print_timing: id 0 | task 16927 | total time = 2551.40 ms / 529 tokens 4.03.168.716 I slot print_timing: id 0 | task 16927 | graphs reused = 16162 4.03.168.716 I slot print_timing: id 0 | task 16927 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.168.745 I slot release: id 0 | task 16927 | stop processing: n_tokens = 560, truncated = 0 4.03.184.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 243078262 4.03.245.756 I slot launch_slot_: id 0 | task 17137 | processing task, is_child = 0 4.06.402.271 I slot print_timing: id 0 | task 17137 | n_gen = 259, tg = 85.71 t/s, tg_3s = 86.04 t/s 4.07.866.187 I slot print_timing: id 0 | task 17137 | prompt eval time = 146.24 ms / 338 tokens ( 0.43 ms per token, 2311.21 tokens per second) 4.07.866.193 I slot print_timing: id 0 | task 17137 | eval time = 4474.17 ms / 385 tokens ( 11.65 ms per token, 85.83 tokens per second) 4.07.866.194 I slot print_timing: id 0 | task 17137 | total time = 4620.41 ms / 723 tokens 4.07.866.196 I slot print_timing: id 0 | task 17137 | graphs reused = 16544 4.07.866.197 I slot print_timing: id 0 | task 17137 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.866.224 I slot release: id 0 | task 17137 | stop processing: n_tokens = 754, truncated = 0 4.07.870.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 247775741 4.07.870.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 4.07.966.376 I slot launch_slot_: id 0 | task 17525 | processing task, is_child = 0 4.11.122.450 I slot print_timing: id 0 | task 17525 | n_gen = 259, tg = 85.74 t/s, tg_3s = 86.08 t/s 4.12.236.178 I slot print_timing: id 0 | task 17525 | prompt eval time = 147.07 ms / 347 tokens ( 0.42 ms per token, 2359.47 tokens per second) 4.12.236.185 I slot print_timing: id 0 | task 17525 | eval time = 4122.72 ms / 355 tokens ( 11.65 ms per token, 85.87 tokens per second) 4.12.236.186 I slot print_timing: id 0 | task 17525 | total time = 4269.78 ms / 702 tokens 4.12.236.186 I slot print_timing: id 0 | task 17525 | graphs reused = 16896 4.12.236.187 I slot print_timing: id 0 | task 17525 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.236.220 I slot release: id 0 | task 17525 | stop processing: n_tokens = 733, truncated = 0 4.12.254.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 252145737 4.12.254.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 4.12.349.832 I slot launch_slot_: id 0 | task 17883 | processing task, is_child = 0 4.13.973.897 I slot print_timing: id 0 | task 17883 | prompt eval time = 147.09 ms / 331 tokens ( 0.44 ms per token, 2250.34 tokens per second) 4.13.973.903 I slot print_timing: id 0 | task 17883 | eval time = 1476.96 ms / 128 tokens ( 11.63 ms per token, 85.99 tokens per second) 4.13.973.904 I slot print_timing: id 0 | task 17883 | total time = 1624.05 ms / 459 tokens 4.13.973.905 I slot print_timing: id 0 | task 17883 | graphs reused = 17022 4.13.973.905 I slot print_timing: id 0 | task 17883 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.973.934 I slot release: id 0 | task 17883 | stop processing: n_tokens = 490, truncated = 0 4.13.999.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 253883452 4.13.999.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 4.14.092.686 I slot launch_slot_: id 0 | task 18014 | processing task, is_child = 0 4.15.177.770 I slot print_timing: id 0 | task 18014 | prompt eval time = 148.88 ms / 345 tokens ( 0.43 ms per token, 2317.32 tokens per second) 4.15.177.776 I slot print_timing: id 0 | task 18014 | eval time = 936.18 ms / 81 tokens ( 11.70 ms per token, 85.45 tokens per second) 4.15.177.777 I slot print_timing: id 0 | task 18014 | total time = 1085.06 ms / 426 tokens 4.15.177.778 I slot print_timing: id 0 | task 18014 | graphs reused = 17101 4.15.177.778 I slot print_timing: id 0 | task 18014 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.177.811 I slot release: id 0 | task 18014 | stop processing: n_tokens = 457, truncated = 0 4.15.194.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 255087329 4.15.195.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 4.15.289.514 I slot launch_slot_: id 0 | task 18098 | processing task, is_child = 0 4.15.847.843 I slot print_timing: id 0 | task 18098 | prompt eval time = 148.22 ms / 320 tokens ( 0.46 ms per token, 2158.92 tokens per second) 4.15.847.849 I slot print_timing: id 0 | task 18098 | eval time = 410.09 ms / 36 tokens ( 11.72 ms per token, 85.35 tokens per second) 4.15.847.850 I slot print_timing: id 0 | task 18098 | total time = 558.31 ms / 356 tokens 4.15.847.851 I slot print_timing: id 0 | task 18098 | graphs reused = 17135 4.15.847.851 I slot print_timing: id 0 | task 18098 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.847.880 I slot release: id 0 | task 18098 | stop processing: n_tokens = 387, truncated = 0 4.15.868.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 255757397 4.15.868.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 4.15.959.604 I slot launch_slot_: id 0 | task 18137 | processing task, is_child = 0 4.16.487.343 I slot print_timing: id 0 | task 18137 | prompt eval time = 139.51 ms / 297 tokens ( 0.47 ms per token, 2128.85 tokens per second) 4.16.487.350 I slot print_timing: id 0 | task 18137 | eval time = 388.21 ms / 34 tokens ( 11.76 ms per token, 85.01 tokens per second) 4.16.487.351 I slot print_timing: id 0 | task 18137 | total time = 527.72 ms / 331 tokens 4.16.487.352 I slot print_timing: id 0 | task 18137 | graphs reused = 17167 4.16.487.353 I slot print_timing: id 0 | task 18137 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.487.380 I slot release: id 0 | task 18137 | stop processing: n_tokens = 362, truncated = 0 4.16.510.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 256396898 4.16.510.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.183 MiB) 4.16.591.676 I slot launch_slot_: id 0 | task 18174 | processing task, is_child = 0 4.19.748.466 I slot print_timing: id 0 | task 18174 | n_gen = 258, tg = 85.50 t/s, tg_3s = 85.83 t/s 4.19.879.972 I slot print_timing: id 0 | task 18174 | prompt eval time = 150.95 ms / 343 tokens ( 0.44 ms per token, 2272.32 tokens per second) 4.19.879.977 I slot print_timing: id 0 | task 18174 | eval time = 3137.33 ms / 269 tokens ( 11.71 ms per token, 85.42 tokens per second) 4.19.879.978 I slot print_timing: id 0 | task 18174 | total time = 3288.28 ms / 612 tokens 4.19.879.979 I slot print_timing: id 0 | task 18174 | graphs reused = 17433 4.19.879.980 I slot print_timing: id 0 | task 18174 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.880.009 I slot release: id 0 | task 18174 | stop processing: n_tokens = 643, truncated = 0 4.19.902.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 259789526 4.19.959.945 I slot launch_slot_: id 0 | task 18446 | processing task, is_child = 0 4.21.321.106 I slot print_timing: id 0 | task 18446 | prompt eval time = 155.30 ms / 371 tokens ( 0.42 ms per token, 2388.97 tokens per second) 4.21.321.113 I slot print_timing: id 0 | task 18446 | eval time = 1205.84 ms / 104 tokens ( 11.71 ms per token, 85.42 tokens per second) 4.21.321.115 I slot print_timing: id 0 | task 18446 | total time = 1361.14 ms / 475 tokens 4.21.321.116 I slot print_timing: id 0 | task 18446 | graphs reused = 17535 4.21.321.117 I slot print_timing: id 0 | task 18446 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.321.153 I slot release: id 0 | task 18446 | stop processing: n_tokens = 506, truncated = 0 4.21.341.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 261230670 4.21.341.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 4.21.436.577 I slot launch_slot_: id 0 | task 18553 | processing task, is_child = 0 4.23.005.660 I slot print_timing: id 0 | task 18553 | prompt eval time = 139.54 ms / 292 tokens ( 0.48 ms per token, 2092.53 tokens per second) 4.23.005.666 I slot print_timing: id 0 | task 18553 | eval time = 1429.52 ms / 123 tokens ( 11.72 ms per token, 85.34 tokens per second) 4.23.005.668 I slot print_timing: id 0 | task 18553 | total time = 1569.06 ms / 415 tokens 4.23.005.668 I slot print_timing: id 0 | task 18553 | graphs reused = 17656 4.23.005.669 I slot print_timing: id 0 | task 18553 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.005.700 I slot release: id 0 | task 18553 | stop processing: n_tokens = 446, truncated = 0 4.23.009.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 262915217 4.23.009.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 4.23.103.232 I slot launch_slot_: id 0 | task 18679 | processing task, is_child = 0 4.23.446.149 I slot print_timing: id 0 | task 18679 | prompt eval time = 141.08 ms / 301 tokens ( 0.47 ms per token, 2133.53 tokens per second) 4.23.446.154 I slot print_timing: id 0 | task 18679 | eval time = 201.81 ms / 18 tokens ( 11.87 ms per token, 84.24 tokens per second) 4.23.446.156 I slot print_timing: id 0 | task 18679 | total time = 342.90 ms / 319 tokens 4.23.446.157 I slot print_timing: id 0 | task 18679 | graphs reused = 17672 4.23.446.158 I slot print_timing: id 0 | task 18679 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.446.186 I slot release: id 0 | task 18679 | stop processing: n_tokens = 350, truncated = 0 4.23.467.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 263355703 4.23.467.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 4.23.556.416 I slot launch_slot_: id 0 | task 18700 | processing task, is_child = 0 4.24.537.915 I slot print_timing: id 0 | task 18700 | prompt eval time = 141.92 ms / 303 tokens ( 0.47 ms per token, 2134.95 tokens per second) 4.24.537.921 I slot print_timing: id 0 | task 18700 | eval time = 839.56 ms / 73 tokens ( 11.66 ms per token, 85.76 tokens per second) 4.24.537.922 I slot print_timing: id 0 | task 18700 | total time = 981.48 ms / 376 tokens 4.24.537.923 I slot print_timing: id 0 | task 18700 | graphs reused = 17743 4.24.537.924 I slot print_timing: id 0 | task 18700 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.537.951 I slot release: id 0 | task 18700 | stop processing: n_tokens = 407, truncated = 0 4.24.555.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 264447469 4.24.555.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 4.24.636.978 I slot launch_slot_: id 0 | task 18776 | processing task, is_child = 0 4.25.135.183 I slot print_timing: id 0 | task 18776 | prompt eval time = 145.76 ms / 321 tokens ( 0.45 ms per token, 2202.28 tokens per second) 4.25.135.189 I slot print_timing: id 0 | task 18776 | eval time = 352.43 ms / 31 tokens ( 11.75 ms per token, 85.12 tokens per second) 4.25.135.190 I slot print_timing: id 0 | task 18776 | total time = 498.19 ms / 352 tokens 4.25.135.190 I slot print_timing: id 0 | task 18776 | graphs reused = 17772 4.25.135.191 I slot print_timing: id 0 | task 18776 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.135.217 I slot release: id 0 | task 18776 | stop processing: n_tokens = 383, truncated = 0 4.25.162.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 265044734 4.25.162.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 4.25.246.914 I slot launch_slot_: id 0 | task 18810 | processing task, is_child = 0 4.25.605.451 I slot print_timing: id 0 | task 18810 | prompt eval time = 145.55 ms / 322 tokens ( 0.45 ms per token, 2212.27 tokens per second) 4.25.605.457 I slot print_timing: id 0 | task 18810 | eval time = 212.97 ms / 19 tokens ( 11.83 ms per token, 84.52 tokens per second) 4.25.605.458 I slot print_timing: id 0 | task 18810 | total time = 358.52 ms / 341 tokens 4.25.605.459 I slot print_timing: id 0 | task 18810 | graphs reused = 17789 4.25.605.460 I slot print_timing: id 0 | task 18810 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.605.487 I slot release: id 0 | task 18810 | stop processing: n_tokens = 372, truncated = 0 4.25.629.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 265515004 4.25.629.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.015 MiB) 4.25.703.009 I slot launch_slot_: id 0 | task 18832 | processing task, is_child = 0 4.27.783.181 I slot print_timing: id 0 | task 18832 | prompt eval time = 145.70 ms / 323 tokens ( 0.45 ms per token, 2216.90 tokens per second) 4.27.783.186 I slot print_timing: id 0 | task 18832 | eval time = 1934.45 ms / 167 tokens ( 11.65 ms per token, 85.81 tokens per second) 4.27.783.187 I slot print_timing: id 0 | task 18832 | total time = 2080.15 ms / 490 tokens 4.27.783.188 I slot print_timing: id 0 | task 18832 | graphs reused = 17953 4.27.783.189 I slot print_timing: id 0 | task 18832 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.783.215 I slot release: id 0 | task 18832 | stop processing: n_tokens = 521, truncated = 0 4.27.786.738 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 267692733 4.27.786.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 4.27.864.737 I slot launch_slot_: id 0 | task 19002 | processing task, is_child = 0 4.31.013.224 I slot print_timing: id 0 | task 19002 | n_gen = 258, tg = 85.57 t/s, tg_3s = 85.90 t/s 4.32.926.311 I slot print_timing: id 0 | task 19002 | prompt eval time = 145.03 ms / 321 tokens ( 0.45 ms per token, 2213.27 tokens per second) 4.32.926.316 I slot print_timing: id 0 | task 19002 | eval time = 4916.52 ms / 420 tokens ( 11.73 ms per token, 85.22 tokens per second) 4.32.926.318 I slot print_timing: id 0 | task 19002 | total time = 5061.55 ms / 741 tokens 4.32.926.318 I slot print_timing: id 0 | task 19002 | graphs reused = 18369 4.32.926.319 I slot print_timing: id 0 | task 19002 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.926.350 I slot release: id 0 | task 19002 | stop processing: n_tokens = 772, truncated = 0 4.32.942.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 272835867 4.32.942.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.950 MiB) 4.33.042.883 I slot launch_slot_: id 0 | task 19425 | processing task, is_child = 0 4.36.152.506 I slot print_timing: id 0 | task 19425 | prompt eval time = 147.01 ms / 322 tokens ( 0.46 ms per token, 2190.28 tokens per second) 4.36.152.512 I slot print_timing: id 0 | task 19425 | eval time = 2962.59 ms / 255 tokens ( 11.66 ms per token, 85.74 tokens per second) 4.36.152.513 I slot print_timing: id 0 | task 19425 | total time = 3109.60 ms / 577 tokens 4.36.152.514 I slot print_timing: id 0 | task 19425 | graphs reused = 18621 4.36.152.515 I slot print_timing: id 0 | task 19425 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.152.542 I slot release: id 0 | task 19425 | stop processing: n_tokens = 608, truncated = 0 4.36.171.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 608, t_last = 276062060 4.36.171.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 4.36.245.392 I slot launch_slot_: id 0 | task 19683 | processing task, is_child = 0 4.36.923.065 I slot print_timing: id 0 | task 19683 | prompt eval time = 147.46 ms / 337 tokens ( 0.44 ms per token, 2285.37 tokens per second) 4.36.923.070 I slot print_timing: id 0 | task 19683 | eval time = 530.19 ms / 46 tokens ( 11.78 ms per token, 84.87 tokens per second) 4.36.923.071 I slot print_timing: id 0 | task 19683 | total time = 677.65 ms / 383 tokens 4.36.923.072 I slot print_timing: id 0 | task 19683 | graphs reused = 18665 4.36.923.073 I slot print_timing: id 0 | task 19683 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.923.101 I slot release: id 0 | task 19683 | stop processing: n_tokens = 414, truncated = 0 4.36.936.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 276832618 4.36.936.647 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.37.025.201 I slot launch_slot_: id 0 | task 19732 | processing task, is_child = 0 4.37.712.333 I slot print_timing: id 0 | task 19732 | prompt eval time = 145.54 ms / 325 tokens ( 0.45 ms per token, 2233.08 tokens per second) 4.37.712.339 I slot print_timing: id 0 | task 19732 | eval time = 541.57 ms / 47 tokens ( 11.77 ms per token, 84.94 tokens per second) 4.37.712.340 I slot print_timing: id 0 | task 19732 | total time = 687.11 ms / 372 tokens 4.37.712.341 I slot print_timing: id 0 | task 19732 | graphs reused = 18710 4.37.712.342 I slot print_timing: id 0 | task 19732 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.712.369 I slot release: id 0 | task 19732 | stop processing: n_tokens = 403, truncated = 0 4.37.729.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 277621887 4.37.729.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.424 MiB) 4.37.826.703 I slot launch_slot_: id 0 | task 19782 | processing task, is_child = 0 4.38.980.009 I slot print_timing: id 0 | task 19782 | prompt eval time = 149.06 ms / 331 tokens ( 0.45 ms per token, 2220.54 tokens per second) 4.38.980.015 I slot print_timing: id 0 | task 19782 | eval time = 1004.22 ms / 87 tokens ( 11.68 ms per token, 85.64 tokens per second) 4.38.980.016 I slot print_timing: id 0 | task 19782 | total time = 1153.29 ms / 418 tokens 4.38.980.017 I slot print_timing: id 0 | task 19782 | graphs reused = 18795 4.38.980.017 I slot print_timing: id 0 | task 19782 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.980.047 I slot release: id 0 | task 19782 | stop processing: n_tokens = 449, truncated = 0 4.39.007.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 278889564 4.39.007.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.014 MiB) 4.39.117.390 I slot launch_slot_: id 0 | task 19872 | processing task, is_child = 0 4.39.942.571 I slot print_timing: id 0 | task 19872 | prompt eval time = 147.59 ms / 336 tokens ( 0.44 ms per token, 2276.55 tokens per second) 4.39.942.576 I slot print_timing: id 0 | task 19872 | eval time = 677.57 ms / 59 tokens ( 11.68 ms per token, 85.60 tokens per second) 4.39.942.578 I slot print_timing: id 0 | task 19872 | total time = 825.16 ms / 395 tokens 4.39.942.578 I slot print_timing: id 0 | task 19872 | graphs reused = 18852 4.39.942.579 I slot print_timing: id 0 | task 19872 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.942.606 I slot release: id 0 | task 19872 | stop processing: n_tokens = 426, truncated = 0 4.39.958.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 279852123 4.39.958.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.669 MiB) 4.40.051.689 I slot launch_slot_: id 0 | task 19934 | processing task, is_child = 0 4.40.552.010 I slot print_timing: id 0 | task 19934 | prompt eval time = 146.83 ms / 349 tokens ( 0.42 ms per token, 2376.93 tokens per second) 4.40.552.016 I slot print_timing: id 0 | task 19934 | eval time = 353.47 ms / 31 tokens ( 11.78 ms per token, 84.87 tokens per second) 4.40.552.017 I slot print_timing: id 0 | task 19934 | total time = 500.30 ms / 380 tokens 4.40.552.018 I slot print_timing: id 0 | task 19934 | graphs reused = 18881 4.40.552.019 I slot print_timing: id 0 | task 19934 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.552.047 I slot release: id 0 | task 19934 | stop processing: n_tokens = 411, truncated = 0 4.40.565.605 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 280461565 4.40.565.648 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.40.654.805 I slot launch_slot_: id 0 | task 19968 | processing task, is_child = 0 4.43.811.916 I slot print_timing: id 0 | task 19968 | n_gen = 259, tg = 85.75 t/s, tg_3s = 86.08 t/s 4.46.818.392 I slot print_timing: id 0 | task 19968 | n_gen = 517, tg = 85.78 t/s, tg_3s = 85.81 t/s 4.49.827.371 I slot print_timing: id 0 | task 19968 | n_gen = 771, tg = 85.33 t/s, tg_3s = 84.41 t/s 4.50.656.762 I slot print_timing: id 0 | task 19968 | prompt eval time = 148.31 ms / 336 tokens ( 0.44 ms per token, 2265.57 tokens per second) 4.50.656.767 I slot print_timing: id 0 | task 19968 | eval time = 9853.63 ms / 842 tokens ( 11.72 ms per token, 85.35 tokens per second) 4.50.656.768 I slot print_timing: id 0 | task 19968 | total time = 10001.94 ms / 1178 tokens 4.50.656.769 I slot print_timing: id 0 | task 19968 | graphs reused = 19718 4.50.656.770 I slot print_timing: id 0 | task 19968 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.656.798 I slot release: id 0 | task 19968 | stop processing: n_tokens = 1209, truncated = 0 4.50.680.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1209, t_last = 290566315 4.50.680.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.170 MiB) 4.50.755.767 I slot launch_slot_: id 0 | task 20813 | processing task, is_child = 0 4.53.912.950 I slot print_timing: id 0 | task 20813 | n_gen = 259, tg = 85.72 t/s, tg_3s = 86.05 t/s 4.55.581.105 I slot print_timing: id 0 | task 20813 | prompt eval time = 147.24 ms / 349 tokens ( 0.42 ms per token, 2370.33 tokens per second) 4.55.581.110 I slot print_timing: id 0 | task 20813 | eval time = 4678.08 ms / 402 tokens ( 11.67 ms per token, 85.72 tokens per second) 4.55.581.111 I slot print_timing: id 0 | task 20813 | total time = 4825.32 ms / 751 tokens 4.55.581.112 I slot print_timing: id 0 | task 20813 | graphs reused = 20116 4.55.581.113 I slot print_timing: id 0 | task 20813 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.581.141 I slot release: id 0 | task 20813 | stop processing: n_tokens = 782, truncated = 0 4.55.605.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 782, t_last = 295490659 4.55.605.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.55.705.868 I slot launch_slot_: id 0 | task 21218 | processing task, is_child = 0 4.56.394.843 I slot print_timing: id 0 | task 21218 | prompt eval time = 149.59 ms / 349 tokens ( 0.43 ms per token, 2333.03 tokens per second) 4.56.394.849 I slot print_timing: id 0 | task 21218 | eval time = 539.37 ms / 47 tokens ( 11.73 ms per token, 85.29 tokens per second) 4.56.394.850 I slot print_timing: id 0 | task 21218 | total time = 688.96 ms / 396 tokens 4.56.394.851 I slot print_timing: id 0 | task 21218 | graphs reused = 20161 4.56.394.851 I slot print_timing: id 0 | task 21218 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.394.877 I slot release: id 0 | task 21218 | stop processing: n_tokens = 427, truncated = 0 4.56.415.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 296304395 4.56.415.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.294 MiB) 4.56.504.978 I slot launch_slot_: id 0 | task 21268 | processing task, is_child = 0 4.56.835.735 I slot print_timing: id 0 | task 21268 | prompt eval time = 152.70 ms / 385 tokens ( 0.40 ms per token, 2521.25 tokens per second) 4.56.835.740 I slot print_timing: id 0 | task 21268 | eval time = 178.04 ms / 16 tokens ( 11.87 ms per token, 84.25 tokens per second) 4.56.835.741 I slot print_timing: id 0 | task 21268 | total time = 330.74 ms / 401 tokens 4.56.835.742 I slot print_timing: id 0 | task 21268 | graphs reused = 20175 4.56.835.743 I slot print_timing: id 0 | task 21268 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.835.772 I slot release: id 0 | task 21268 | stop processing: n_tokens = 432, truncated = 0 4.56.852.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 296745289 4.56.852.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 4.56.951.503 I slot launch_slot_: id 0 | task 21287 | processing task, is_child = 0 4.57.755.168 I slot print_timing: id 0 | task 21287 | prompt eval time = 147.64 ms / 328 tokens ( 0.45 ms per token, 2221.67 tokens per second) 4.57.755.174 I slot print_timing: id 0 | task 21287 | eval time = 656.01 ms / 57 tokens ( 11.71 ms per token, 85.36 tokens per second) 4.57.755.175 I slot print_timing: id 0 | task 21287 | total time = 803.64 ms / 385 tokens 4.57.755.176 I slot print_timing: id 0 | task 21287 | graphs reused = 20230 4.57.755.177 I slot print_timing: id 0 | task 21287 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.755.204 I slot release: id 0 | task 21287 | stop processing: n_tokens = 416, truncated = 0