$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-UD-Q4_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.093.716 I srv llama_server: initializing ... 0.00.093.722 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.093.836 I srv init_listene: The UI is disabled 0.00.093.838 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.093.918 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) 0.00.103.070 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-UD-Q4_K_XL.gguf' 0.02.793.511 I cmn init: llama threadpool init, n_threads = 8 0.02.874.379 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.879.000 I srv llama_server: model loaded 0.02.879.008 I srv llama_server: listening on http://127.0.0.1:8089 0.04.567.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.567.539 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.327.495 I slot print_timing: id 0 | task 0 | prompt eval time = 197.02 ms / 368 tokens ( 0.54 ms per token, 1867.86 tokens per second) 0.05.327.501 I slot print_timing: id 0 | task 0 | eval time = 562.92 ms / 53 tokens ( 10.83 ms per token, 92.38 tokens per second) 0.05.327.502 I slot print_timing: id 0 | task 0 | total time = 759.94 ms / 421 tokens 0.05.327.508 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.327.509 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.327.537 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.347.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5235775 0.05.371.778 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.05.926.423 I slot print_timing: id 0 | task 56 | prompt eval time = 120.60 ms / 322 tokens ( 0.37 ms per token, 2670.05 tokens per second) 0.05.926.429 I slot print_timing: id 0 | task 56 | eval time = 434.03 ms / 42 tokens ( 10.59 ms per token, 94.46 tokens per second) 0.05.926.430 I slot print_timing: id 0 | task 56 | total time = 554.63 ms / 364 tokens 0.05.926.431 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.05.926.431 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.926.457 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.05.951.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5834695 0.05.975.222 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.06.533.357 I slot print_timing: id 0 | task 101 | prompt eval time = 120.79 ms / 365 tokens ( 0.33 ms per token, 3021.67 tokens per second) 0.06.533.362 I slot print_timing: id 0 | task 101 | eval time = 437.32 ms / 42 tokens ( 10.67 ms per token, 93.75 tokens per second) 0.06.533.364 I slot print_timing: id 0 | task 101 | total time = 558.12 ms / 407 tokens 0.06.533.364 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.06.533.365 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.533.393 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.06.559.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6441631 0.06.585.723 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.07.162.652 I slot print_timing: id 0 | task 146 | prompt eval time = 130.15 ms / 397 tokens ( 0.33 ms per token, 3050.23 tokens per second) 0.07.162.658 I slot print_timing: id 0 | task 146 | eval time = 446.76 ms / 43 tokens ( 10.64 ms per token, 94.01 tokens per second) 0.07.162.659 I slot print_timing: id 0 | task 146 | total time = 576.91 ms / 440 tokens 0.07.162.660 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.07.162.660 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.162.690 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.07.182.342 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 0.07.215.736 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.07.910.185 I slot print_timing: id 0 | task 192 | prompt eval time = 125.31 ms / 383 tokens ( 0.33 ms per token, 3056.52 tokens per second) 0.07.910.191 I slot print_timing: id 0 | task 192 | eval time = 569.12 ms / 55 tokens ( 10.54 ms per token, 94.88 tokens per second) 0.07.910.192 I slot print_timing: id 0 | task 192 | total time = 694.43 ms / 438 tokens 0.07.910.193 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.07.910.194 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.910.220 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.07.926.257 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7818458 0.07.953.969 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.08.653.147 I slot print_timing: id 0 | task 250 | prompt eval time = 129.26 ms / 372 tokens ( 0.35 ms per token, 2877.92 tokens per second) 0.08.653.154 I slot print_timing: id 0 | task 250 | eval time = 569.90 ms / 55 tokens ( 10.55 ms per token, 94.75 tokens per second) 0.08.653.155 I slot print_timing: id 0 | task 250 | total time = 699.16 ms / 427 tokens 0.08.653.156 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.08.653.156 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.653.185 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.08.667.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8561422 0.08.694.694 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.09.408.410 I slot print_timing: id 0 | task 308 | prompt eval time = 144.85 ms / 422 tokens ( 0.34 ms per token, 2913.44 tokens per second) 0.09.408.416 I slot print_timing: id 0 | task 308 | eval time = 568.85 ms / 55 tokens ( 10.53 ms per token, 94.93 tokens per second) 0.09.408.417 I slot print_timing: id 0 | task 308 | total time = 713.70 ms / 477 tokens 0.09.408.418 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.09.408.419 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.408.447 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.09.431.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 9316685 0.09.458.322 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.10.358.331 I slot print_timing: id 0 | task 366 | prompt eval time = 147.47 ms / 470 tokens ( 0.31 ms per token, 3187.11 tokens per second) 0.10.358.337 I slot print_timing: id 0 | task 366 | eval time = 752.52 ms / 72 tokens ( 10.60 ms per token, 94.35 tokens per second) 0.10.358.338 I slot print_timing: id 0 | task 366 | total time = 899.99 ms / 542 tokens 0.10.358.339 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.10.358.340 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.358.370 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.10.382.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 10266607 0.10.408.495 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.11.016.266 I slot print_timing: id 0 | task 441 | prompt eval time = 120.81 ms / 345 tokens ( 0.35 ms per token, 2855.82 tokens per second) 0.11.016.271 I slot print_timing: id 0 | task 441 | eval time = 486.94 ms / 47 tokens ( 10.59 ms per token, 94.47 tokens per second) 0.11.016.272 I slot print_timing: id 0 | task 441 | total time = 607.75 ms / 392 tokens 0.11.016.273 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.11.016.274 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.016.301 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.11.020.192 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 10924539 0.11.045.239 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.11.596.304 I slot print_timing: id 0 | task 491 | prompt eval time = 126.67 ms / 364 tokens ( 0.35 ms per token, 2873.65 tokens per second) 0.11.596.310 I slot print_timing: id 0 | task 491 | eval time = 424.38 ms / 41 tokens ( 10.61 ms per token, 94.26 tokens per second) 0.11.596.311 I slot print_timing: id 0 | task 491 | total time = 551.05 ms / 405 tokens 0.11.596.312 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.11.596.312 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.596.340 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.11.623.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 11504577 0.11.649.191 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.12.453.331 I slot print_timing: id 0 | task 535 | prompt eval time = 126.91 ms / 376 tokens ( 0.34 ms per token, 2962.64 tokens per second) 0.12.453.338 I slot print_timing: id 0 | task 535 | eval time = 677.21 ms / 62 tokens ( 11.10 ms per token, 90.08 tokens per second) 0.12.453.339 I slot print_timing: id 0 | task 535 | total time = 804.12 ms / 438 tokens 0.12.453.340 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.12.453.341 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.453.369 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.12.480.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12361606 0.12.507.519 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.13.125.569 I slot print_timing: id 0 | task 600 | prompt eval time = 131.53 ms / 412 tokens ( 0.32 ms per token, 3132.29 tokens per second) 0.13.125.575 I slot print_timing: id 0 | task 600 | eval time = 486.50 ms / 47 tokens ( 10.58 ms per token, 94.55 tokens per second) 0.13.125.576 I slot print_timing: id 0 | task 600 | total time = 618.03 ms / 459 tokens 0.13.125.577 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.13.125.577 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.125.606 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.13.147.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 13033844 0.13.177.303 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.13.943.363 I slot print_timing: id 0 | task 650 | prompt eval time = 123.13 ms / 376 tokens ( 0.33 ms per token, 3053.58 tokens per second) 0.13.943.368 I slot print_timing: id 0 | task 650 | eval time = 642.91 ms / 62 tokens ( 10.54 ms per token, 94.88 tokens per second) 0.13.943.369 I slot print_timing: id 0 | task 650 | total time = 766.04 ms / 438 tokens 0.13.943.370 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.13.943.371 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.943.398 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.13.959.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13851636 0.13.987.017 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.14.652.416 I slot print_timing: id 0 | task 715 | prompt eval time = 127.01 ms / 378 tokens ( 0.34 ms per token, 2976.10 tokens per second) 0.14.652.421 I slot print_timing: id 0 | task 715 | eval time = 538.37 ms / 52 tokens ( 10.56 ms per token, 94.73 tokens per second) 0.14.652.422 I slot print_timing: id 0 | task 715 | total time = 665.38 ms / 430 tokens 0.14.652.423 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.14.652.424 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.652.451 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.14.678.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 14560689 0.14.708.589 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.15.476.454 I slot print_timing: id 0 | task 770 | prompt eval time = 128.55 ms / 367 tokens ( 0.35 ms per token, 2854.94 tokens per second) 0.15.476.460 I slot print_timing: id 0 | task 770 | eval time = 639.30 ms / 58 tokens ( 11.22 ms per token, 89.16 tokens per second) 0.15.476.462 I slot print_timing: id 0 | task 770 | total time = 767.85 ms / 425 tokens 0.15.476.462 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.15.476.463 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.476.491 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.15.501.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 15384729 0.15.526.725 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.16.181.523 I slot print_timing: id 0 | task 831 | prompt eval time = 124.36 ms / 347 tokens ( 0.36 ms per token, 2790.35 tokens per second) 0.16.181.528 I slot print_timing: id 0 | task 831 | eval time = 530.42 ms / 51 tokens ( 10.61 ms per token, 94.26 tokens per second) 0.16.181.529 I slot print_timing: id 0 | task 831 | total time = 654.78 ms / 398 tokens 0.16.181.530 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.16.181.531 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.181.557 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.16.202.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 16089795 0.16.227.975 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.16.779.680 I slot print_timing: id 0 | task 885 | prompt eval time = 126.83 ms / 369 tokens ( 0.34 ms per token, 2909.41 tokens per second) 0.16.779.686 I slot print_timing: id 0 | task 885 | eval time = 424.86 ms / 41 tokens ( 10.62 ms per token, 94.15 tokens per second) 0.16.779.687 I slot print_timing: id 0 | task 885 | total time = 551.69 ms / 410 tokens 0.16.779.688 I slot print_timing: id 0 | task 885 | graphs reused = 844 0.16.779.689 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.779.718 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 0.16.795.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 16687956 0.16.820.925 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 0.17.369.087 I slot print_timing: id 0 | task 929 | prompt eval time = 122.30 ms / 352 tokens ( 0.35 ms per token, 2878.26 tokens per second) 0.17.369.093 I slot print_timing: id 0 | task 929 | eval time = 425.84 ms / 41 tokens ( 10.65 ms per token, 93.93 tokens per second) 0.17.369.094 I slot print_timing: id 0 | task 929 | total time = 548.14 ms / 393 tokens 0.17.369.095 I slot print_timing: id 0 | task 929 | graphs reused = 883 0.17.369.095 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.369.121 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 0.17.387.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 17277358 0.17.412.447 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 0.17.947.669 I slot print_timing: id 0 | task 973 | prompt eval time = 121.20 ms / 349 tokens ( 0.35 ms per token, 2879.54 tokens per second) 0.17.947.675 I slot print_timing: id 0 | task 973 | eval time = 414.00 ms / 40 tokens ( 10.62 ms per token, 94.20 tokens per second) 0.17.947.676 I slot print_timing: id 0 | task 973 | total time = 535.20 ms / 389 tokens 0.17.947.677 I slot print_timing: id 0 | task 973 | graphs reused = 921 0.17.947.677 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.947.704 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 0.17.968.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 17855941 0.17.995.444 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.18.815.240 I slot print_timing: id 0 | task 1016 | prompt eval time = 130.11 ms / 384 tokens ( 0.34 ms per token, 2951.33 tokens per second) 0.18.815.246 I slot print_timing: id 0 | task 1016 | eval time = 689.67 ms / 63 tokens ( 11.12 ms per token, 89.90 tokens per second) 0.18.815.247 I slot print_timing: id 0 | task 1016 | total time = 819.78 ms / 447 tokens 0.18.815.248 I slot print_timing: id 0 | task 1016 | graphs reused = 982 0.18.815.248 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.815.277 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 0.18.840.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 18723515 0.18.876.019 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.19.561.855 I slot print_timing: id 0 | task 1082 | prompt eval time = 124.74 ms / 356 tokens ( 0.35 ms per token, 2853.94 tokens per second) 0.19.561.861 I slot print_timing: id 0 | task 1082 | eval time = 561.08 ms / 54 tokens ( 10.59 ms per token, 94.46 tokens per second) 0.19.561.862 I slot print_timing: id 0 | task 1082 | total time = 685.82 ms / 410 tokens 0.19.561.863 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 0.19.561.863 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.561.891 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 0.19.586.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 19470128 0.19.611.973 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 0.20.486.479 I slot print_timing: id 0 | task 1139 | prompt eval time = 131.18 ms / 410 tokens ( 0.32 ms per token, 3125.45 tokens per second) 0.20.486.485 I slot print_timing: id 0 | task 1139 | eval time = 743.30 ms / 70 tokens ( 10.77 ms per token, 92.83 tokens per second) 0.20.486.486 I slot print_timing: id 0 | task 1139 | total time = 874.49 ms / 480 tokens 0.20.486.487 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 0.20.486.488 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.486.517 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 0.20.502.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 20394755 0.20.529.384 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 0.21.262.370 I slot print_timing: id 0 | task 1212 | prompt eval time = 128.36 ms / 385 tokens ( 0.33 ms per token, 2999.40 tokens per second) 0.21.262.376 I slot print_timing: id 0 | task 1212 | eval time = 604.61 ms / 58 tokens ( 10.61 ms per token, 94.28 tokens per second) 0.21.262.377 I slot print_timing: id 0 | task 1212 | total time = 732.97 ms / 443 tokens 0.21.262.378 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 0.21.262.379 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.262.408 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 0.21.276.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 21170646 0.21.305.593 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.22.178.121 I slot print_timing: id 0 | task 1273 | prompt eval time = 133.68 ms / 395 tokens ( 0.34 ms per token, 2954.80 tokens per second) 0.22.178.127 I slot print_timing: id 0 | task 1273 | eval time = 738.83 ms / 71 tokens ( 10.55 ms per token, 94.75 tokens per second) 0.22.178.128 I slot print_timing: id 0 | task 1273 | total time = 872.51 ms / 466 tokens 0.22.178.128 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.22.178.129 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.178.159 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.22.191.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 22086396 0.22.224.856 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.23.005.490 I slot print_timing: id 0 | task 1347 | prompt eval time = 134.74 ms / 430 tokens ( 0.31 ms per token, 3191.31 tokens per second) 0.23.005.495 I slot print_timing: id 0 | task 1347 | eval time = 645.87 ms / 62 tokens ( 10.59 ms per token, 94.45 tokens per second) 0.23.005.496 I slot print_timing: id 0 | task 1347 | total time = 780.61 ms / 492 tokens 0.23.005.497 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 0.23.005.498 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.005.527 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 0.23.031.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 22913765 0.23.071.988 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 0.23.846.987 I slot print_timing: id 0 | task 1412 | prompt eval time = 133.40 ms / 392 tokens ( 0.34 ms per token, 2938.49 tokens per second) 0.23.846.993 I slot print_timing: id 0 | task 1412 | eval time = 641.58 ms / 62 tokens ( 10.52 ms per token, 95.08 tokens per second) 0.23.846.994 I slot print_timing: id 0 | task 1412 | total time = 774.98 ms / 454 tokens 0.23.846.995 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 0.23.846.996 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.847.023 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 0.23.867.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 23755261 0.23.902.990 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 0.24.535.082 I slot print_timing: id 0 | task 1477 | prompt eval time = 123.15 ms / 350 tokens ( 0.35 ms per token, 2842.02 tokens per second) 0.24.535.088 I slot print_timing: id 0 | task 1477 | eval time = 508.92 ms / 49 tokens ( 10.60 ms per token, 94.32 tokens per second) 0.24.535.089 I slot print_timing: id 0 | task 1477 | total time = 632.07 ms / 399 tokens 0.24.535.089 I slot print_timing: id 0 | task 1477 | graphs reused = 1394 0.24.535.090 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.535.117 I slot release: id 0 | task 1477 | stop processing: n_tokens = 398, truncated = 0 0.24.550.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 24443355 0.24.585.880 I slot launch_slot_: id 0 | task 1529 | processing task, is_child = 0 0.25.351.833 I slot print_timing: id 0 | task 1529 | prompt eval time = 130.12 ms / 380 tokens ( 0.34 ms per token, 2920.34 tokens per second) 0.25.351.838 I slot print_timing: id 0 | task 1529 | eval time = 635.81 ms / 61 tokens ( 10.60 ms per token, 94.37 tokens per second) 0.25.351.839 I slot print_timing: id 0 | task 1529 | total time = 765.93 ms / 441 tokens 0.25.351.840 I slot print_timing: id 0 | task 1529 | graphs reused = 1453 0.25.351.841 I slot print_timing: id 0 | task 1529 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.351.870 I slot release: id 0 | task 1529 | stop processing: n_tokens = 440, truncated = 0 0.25.355.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 25260108 0.25.391.773 I slot launch_slot_: id 0 | task 1593 | processing task, is_child = 0 0.26.390.473 I slot print_timing: id 0 | task 1593 | prompt eval time = 133.24 ms / 410 tokens ( 0.32 ms per token, 3077.20 tokens per second) 0.26.390.479 I slot print_timing: id 0 | task 1593 | eval time = 865.44 ms / 80 tokens ( 10.95 ms per token, 91.28 tokens per second) 0.26.390.480 I slot print_timing: id 0 | task 1593 | total time = 998.68 ms / 490 tokens 0.26.390.481 I slot print_timing: id 0 | task 1593 | graphs reused = 1531 0.26.390.482 I slot print_timing: id 0 | task 1593 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.390.510 I slot release: id 0 | task 1593 | stop processing: n_tokens = 489, truncated = 0 0.26.394.524 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 26298748 0.26.432.051 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.27.279.080 I slot print_timing: id 0 | task 1676 | prompt eval time = 129.62 ms / 387 tokens ( 0.33 ms per token, 2985.54 tokens per second) 0.27.279.086 I slot print_timing: id 0 | task 1676 | eval time = 717.38 ms / 68 tokens ( 10.71 ms per token, 93.40 tokens per second) 0.27.279.087 I slot print_timing: id 0 | task 1676 | total time = 847.00 ms / 455 tokens 0.27.279.088 I slot print_timing: id 0 | task 1676 | graphs reused = 1597 0.27.279.089 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.279.122 I slot release: id 0 | task 1676 | stop processing: n_tokens = 454, truncated = 0 0.27.282.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 27187360 0.27.319.344 I slot launch_slot_: id 0 | task 1747 | processing task, is_child = 0 0.28.056.788 I slot print_timing: id 0 | task 1747 | prompt eval time = 125.25 ms / 358 tokens ( 0.35 ms per token, 2858.21 tokens per second) 0.28.056.794 I slot print_timing: id 0 | task 1747 | eval time = 612.17 ms / 59 tokens ( 10.55 ms per token, 94.74 tokens per second) 0.28.056.795 I slot print_timing: id 0 | task 1747 | total time = 737.43 ms / 417 tokens 0.28.056.796 I slot print_timing: id 0 | task 1747 | graphs reused = 1654 0.28.056.797 I slot print_timing: id 0 | task 1747 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.056.825 I slot release: id 0 | task 1747 | stop processing: n_tokens = 416, truncated = 0 0.28.074.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 27965063 0.28.111.418 I slot launch_slot_: id 0 | task 1809 | processing task, is_child = 0 0.28.847.207 I slot print_timing: id 0 | task 1809 | prompt eval time = 123.94 ms / 359 tokens ( 0.35 ms per token, 2896.49 tokens per second) 0.28.847.213 I slot print_timing: id 0 | task 1809 | eval time = 611.83 ms / 56 tokens ( 11.12 ms per token, 89.89 tokens per second) 0.28.847.214 I slot print_timing: id 0 | task 1809 | total time = 735.77 ms / 415 tokens 0.28.847.214 I slot print_timing: id 0 | task 1809 | graphs reused = 1708 0.28.847.215 I slot print_timing: id 0 | task 1809 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.847.240 I slot release: id 0 | task 1809 | stop processing: n_tokens = 414, truncated = 0 0.28.873.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 28755478 0.28.911.347 I slot launch_slot_: id 0 | task 1868 | processing task, is_child = 0 0.29.672.603 I slot print_timing: id 0 | task 1868 | prompt eval time = 128.92 ms / 387 tokens ( 0.33 ms per token, 3001.88 tokens per second) 0.29.672.609 I slot print_timing: id 0 | task 1868 | eval time = 632.32 ms / 61 tokens ( 10.54 ms per token, 94.89 tokens per second) 0.29.672.610 I slot print_timing: id 0 | task 1868 | total time = 761.23 ms / 448 tokens 0.29.672.611 I slot print_timing: id 0 | task 1868 | graphs reused = 1767 0.29.672.611 I slot print_timing: id 0 | task 1868 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.672.639 I slot release: id 0 | task 1868 | stop processing: n_tokens = 447, truncated = 0 0.29.698.262 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 29580877 0.29.735.000 I slot launch_slot_: id 0 | task 1932 | processing task, is_child = 0 0.30.525.734 I slot print_timing: id 0 | task 1932 | prompt eval time = 130.94 ms / 410 tokens ( 0.32 ms per token, 3131.21 tokens per second) 0.30.525.740 I slot print_timing: id 0 | task 1932 | eval time = 659.77 ms / 61 tokens ( 11.00 ms per token, 90.94 tokens per second) 0.30.525.741 I slot print_timing: id 0 | task 1932 | total time = 790.71 ms / 471 tokens 0.30.525.743 I slot print_timing: id 0 | task 1932 | graphs reused = 1826 0.30.525.743 I slot print_timing: id 0 | task 1932 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.525.772 I slot release: id 0 | task 1932 | stop processing: n_tokens = 470, truncated = 0 0.30.550.704 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 30434010 0.30.587.328 I slot launch_slot_: id 0 | task 1996 | processing task, is_child = 0 0.31.229.740 I slot print_timing: id 0 | task 1996 | prompt eval time = 122.52 ms / 351 tokens ( 0.35 ms per token, 2864.84 tokens per second) 0.31.229.746 I slot print_timing: id 0 | task 1996 | eval time = 519.88 ms / 50 tokens ( 10.61 ms per token, 94.25 tokens per second) 0.31.229.747 I slot print_timing: id 0 | task 1996 | total time = 642.39 ms / 401 tokens 0.31.229.748 I slot print_timing: id 0 | task 1996 | graphs reused = 1874 0.31.229.749 I slot print_timing: id 0 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.229.777 I slot release: id 0 | task 1996 | stop processing: n_tokens = 400, truncated = 0 0.31.252.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 31138014 0.31.287.834 I slot launch_slot_: id 0 | task 2049 | processing task, is_child = 0 0.33.769.592 I slot print_timing: id 0 | task 2049 | prompt eval time = 130.68 ms / 393 tokens ( 0.33 ms per token, 3007.46 tokens per second) 0.33.769.598 I slot print_timing: id 0 | task 2049 | eval time = 2351.06 ms / 224 tokens ( 10.54 ms per token, 94.85 tokens per second) 0.33.769.599 I slot print_timing: id 0 | task 2049 | total time = 2481.74 ms / 617 tokens 0.33.769.599 I slot print_timing: id 0 | task 2049 | graphs reused = 2095 0.33.769.600 I slot print_timing: id 0 | task 2049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.769.630 I slot release: id 0 | task 2049 | stop processing: n_tokens = 616, truncated = 0 0.33.792.070 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 33677868 0.33.828.499 I slot launch_slot_: id 0 | task 2276 | processing task, is_child = 0 0.34.280.098 I slot print_timing: id 0 | task 2276 | prompt eval time = 120.39 ms / 321 tokens ( 0.38 ms per token, 2666.25 tokens per second) 0.34.280.104 I slot print_timing: id 0 | task 2276 | eval time = 331.19 ms / 32 tokens ( 10.68 ms per token, 93.60 tokens per second) 0.34.280.105 I slot print_timing: id 0 | task 2276 | total time = 451.58 ms / 353 tokens 0.34.280.105 I slot print_timing: id 0 | task 2276 | graphs reused = 2125 0.34.280.106 I slot print_timing: id 0 | task 2276 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.280.131 I slot release: id 0 | task 2276 | stop processing: n_tokens = 352, truncated = 0 0.34.283.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 34188369 0.34.337.045 I slot launch_slot_: id 0 | task 2311 | processing task, is_child = 0 0.35.013.075 I slot print_timing: id 0 | task 2311 | prompt eval time = 126.05 ms / 330 tokens ( 0.38 ms per token, 2617.95 tokens per second) 0.35.013.081 I slot print_timing: id 0 | task 2311 | eval time = 549.96 ms / 53 tokens ( 10.58 ms per token, 94.55 tokens per second) 0.35.013.082 I slot print_timing: id 0 | task 2311 | total time = 676.01 ms / 383 tokens 0.35.013.083 I slot print_timing: id 0 | task 2311 | graphs reused = 2176 0.35.013.083 I slot print_timing: id 0 | task 2311 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.013.111 I slot release: id 0 | task 2311 | stop processing: n_tokens = 382, truncated = 0 0.35.039.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 34921349 0.35.075.339 I slot launch_slot_: id 0 | task 2367 | processing task, is_child = 0 0.35.528.757 I slot print_timing: id 0 | task 2367 | prompt eval time = 123.50 ms / 341 tokens ( 0.36 ms per token, 2761.11 tokens per second) 0.35.528.763 I slot print_timing: id 0 | task 2367 | eval time = 329.90 ms / 32 tokens ( 10.64 ms per token, 93.97 tokens per second) 0.35.528.764 I slot print_timing: id 0 | task 2367 | total time = 453.40 ms / 373 tokens 0.35.528.764 I slot print_timing: id 0 | task 2367 | graphs reused = 2206 0.35.528.766 I slot print_timing: id 0 | task 2367 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.528.794 I slot release: id 0 | task 2367 | stop processing: n_tokens = 372, truncated = 0 0.35.548.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 35437031 0.35.584.750 I slot launch_slot_: id 0 | task 2402 | processing task, is_child = 0 0.36.208.066 I slot print_timing: id 0 | task 2402 | prompt eval time = 125.67 ms / 338 tokens ( 0.37 ms per token, 2689.56 tokens per second) 0.36.208.072 I slot print_timing: id 0 | task 2402 | eval time = 497.63 ms / 48 tokens ( 10.59 ms per token, 94.45 tokens per second) 0.36.208.073 I slot print_timing: id 0 | task 2402 | total time = 623.30 ms / 386 tokens 0.36.208.074 I slot print_timing: id 0 | task 2402 | graphs reused = 2252 0.36.208.074 I slot print_timing: id 0 | task 2402 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.208.101 I slot release: id 0 | task 2402 | stop processing: n_tokens = 385, truncated = 0 0.36.233.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 36116339 0.36.269.158 I slot launch_slot_: id 0 | task 2453 | processing task, is_child = 0 0.36.982.176 I slot print_timing: id 0 | task 2453 | prompt eval time = 131.69 ms / 395 tokens ( 0.33 ms per token, 2999.49 tokens per second) 0.36.982.182 I slot print_timing: id 0 | task 2453 | eval time = 581.31 ms / 56 tokens ( 10.57 ms per token, 94.61 tokens per second) 0.36.982.183 I slot print_timing: id 0 | task 2453 | total time = 713.00 ms / 451 tokens 0.36.982.184 I slot print_timing: id 0 | task 2453 | graphs reused = 2306 0.36.982.184 I slot print_timing: id 0 | task 2453 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.982.214 I slot release: id 0 | task 2453 | stop processing: n_tokens = 450, truncated = 0 0.36.986.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 36890452 0.37.022.173 I slot launch_slot_: id 0 | task 2512 | processing task, is_child = 0 0.38.078.129 I slot print_timing: id 0 | task 2512 | prompt eval time = 188.52 ms / 528 tokens ( 0.36 ms per token, 2800.82 tokens per second) 0.38.078.135 I slot print_timing: id 0 | task 2512 | eval time = 867.42 ms / 83 tokens ( 10.58 ms per token, 94.53 tokens per second) 0.38.078.136 I slot print_timing: id 0 | task 2512 | total time = 1055.94 ms / 611 tokens 0.38.078.137 I slot print_timing: id 0 | task 2512 | graphs reused = 2387 0.38.078.138 I slot print_timing: id 0 | task 2512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.078.171 I slot release: id 0 | task 2512 | stop processing: n_tokens = 610, truncated = 0 0.38.099.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 37986409 0.38.145.800 I slot launch_slot_: id 0 | task 2599 | processing task, is_child = 0 0.38.754.906 I slot print_timing: id 0 | task 2599 | prompt eval time = 143.59 ms / 331 tokens ( 0.43 ms per token, 2305.24 tokens per second) 0.38.754.912 I slot print_timing: id 0 | task 2599 | eval time = 465.50 ms / 45 tokens ( 10.58 ms per token, 94.52 tokens per second) 0.38.754.914 I slot print_timing: id 0 | task 2599 | total time = 609.09 ms / 376 tokens 0.38.754.915 I slot print_timing: id 0 | task 2599 | graphs reused = 2430 0.38.754.916 I slot print_timing: id 0 | task 2599 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.754.945 I slot release: id 0 | task 2599 | stop processing: n_tokens = 387, truncated = 0 0.38.771.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 38663183 0.38.815.123 I slot launch_slot_: id 0 | task 2647 | processing task, is_child = 0 0.39.513.052 I slot print_timing: id 0 | task 2647 | prompt eval time = 148.66 ms / 362 tokens ( 0.41 ms per token, 2435.07 tokens per second) 0.39.513.058 I slot print_timing: id 0 | task 2647 | eval time = 549.25 ms / 53 tokens ( 10.56 ms per token, 94.68 tokens per second) 0.39.513.059 I slot print_timing: id 0 | task 2647 | total time = 697.91 ms / 415 tokens 0.39.513.060 I slot print_timing: id 0 | task 2647 | graphs reused = 2481 0.39.513.060 I slot print_timing: id 0 | task 2647 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.513.089 I slot release: id 0 | task 2647 | stop processing: n_tokens = 426, truncated = 0 0.39.529.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 39421326 0.39.579.012 I slot launch_slot_: id 0 | task 2703 | processing task, is_child = 0 0.40.448.553 I slot print_timing: id 0 | task 2703 | prompt eval time = 153.45 ms / 419 tokens ( 0.37 ms per token, 2730.57 tokens per second) 0.40.448.558 I slot print_timing: id 0 | task 2703 | eval time = 716.07 ms / 69 tokens ( 10.53 ms per token, 94.96 tokens per second) 0.40.448.559 I slot print_timing: id 0 | task 2703 | total time = 869.52 ms / 488 tokens 0.40.448.560 I slot print_timing: id 0 | task 2703 | graphs reused = 2548 0.40.448.561 I slot print_timing: id 0 | task 2703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.448.590 I slot release: id 0 | task 2703 | stop processing: n_tokens = 499, truncated = 0 0.40.464.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 40356828 0.40.510.510 I slot launch_slot_: id 0 | task 2775 | processing task, is_child = 0 0.41.137.816 I slot print_timing: id 0 | task 2775 | prompt eval time = 171.88 ms / 423 tokens ( 0.41 ms per token, 2460.96 tokens per second) 0.41.137.822 I slot print_timing: id 0 | task 2775 | eval time = 455.40 ms / 44 tokens ( 10.59 ms per token, 94.42 tokens per second) 0.41.137.823 I slot print_timing: id 0 | task 2775 | total time = 627.29 ms / 467 tokens 0.41.137.824 I slot print_timing: id 0 | task 2775 | graphs reused = 2590 0.41.137.825 I slot print_timing: id 0 | task 2775 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.137.857 I slot release: id 0 | task 2775 | stop processing: n_tokens = 478, truncated = 0 0.41.164.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 41046095 0.41.209.495 I slot launch_slot_: id 0 | task 2822 | processing task, is_child = 0 0.41.795.392 I slot print_timing: id 0 | task 2822 | prompt eval time = 141.93 ms / 341 tokens ( 0.42 ms per token, 2402.53 tokens per second) 0.41.795.398 I slot print_timing: id 0 | task 2822 | eval time = 443.94 ms / 43 tokens ( 10.57 ms per token, 94.61 tokens per second) 0.41.795.399 I slot print_timing: id 0 | task 2822 | total time = 585.88 ms / 384 tokens 0.41.795.400 I slot print_timing: id 0 | task 2822 | graphs reused = 2631 0.41.795.401 I slot print_timing: id 0 | task 2822 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.795.428 I slot release: id 0 | task 2822 | stop processing: n_tokens = 395, truncated = 0 0.41.822.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 41703666 0.41.871.322 I slot launch_slot_: id 0 | task 2868 | processing task, is_child = 0 0.42.501.496 I slot print_timing: id 0 | task 2868 | prompt eval time = 143.73 ms / 356 tokens ( 0.40 ms per token, 2476.85 tokens per second) 0.42.501.502 I slot print_timing: id 0 | task 2868 | eval time = 486.42 ms / 47 tokens ( 10.57 ms per token, 94.57 tokens per second) 0.42.501.503 I slot print_timing: id 0 | task 2868 | total time = 630.15 ms / 403 tokens 0.42.501.504 I slot print_timing: id 0 | task 2868 | graphs reused = 2676 0.42.501.505 I slot print_timing: id 0 | task 2868 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.501.532 I slot release: id 0 | task 2868 | stop processing: n_tokens = 414, truncated = 0 0.42.517.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 42409770 0.42.517.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.42.558.744 I slot launch_slot_: id 0 | task 2918 | processing task, is_child = 0 0.43.183.434 I slot print_timing: id 0 | task 2918 | prompt eval time = 149.21 ms / 362 tokens ( 0.41 ms per token, 2426.06 tokens per second) 0.43.183.440 I slot print_timing: id 0 | task 2918 | eval time = 475.46 ms / 46 tokens ( 10.57 ms per token, 94.65 tokens per second) 0.43.183.440 I slot print_timing: id 0 | task 2918 | total time = 624.67 ms / 408 tokens 0.43.183.441 I slot print_timing: id 0 | task 2918 | graphs reused = 2720 0.43.183.442 I slot print_timing: id 0 | task 2918 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.183.473 I slot release: id 0 | task 2918 | stop processing: n_tokens = 419, truncated = 0 0.43.187.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 43091711 0.43.187.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.43.228.246 I slot launch_slot_: id 0 | task 2967 | processing task, is_child = 0 0.44.086.059 I slot print_timing: id 0 | task 2967 | prompt eval time = 152.21 ms / 391 tokens ( 0.39 ms per token, 2568.80 tokens per second) 0.44.086.065 I slot print_timing: id 0 | task 2967 | eval time = 705.58 ms / 68 tokens ( 10.53 ms per token, 94.96 tokens per second) 0.44.086.066 I slot print_timing: id 0 | task 2967 | total time = 857.79 ms / 459 tokens 0.44.086.066 I slot print_timing: id 0 | task 2967 | graphs reused = 2786 0.44.086.067 I slot print_timing: id 0 | task 2967 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.086.096 I slot release: id 0 | task 2967 | stop processing: n_tokens = 470, truncated = 0 0.44.089.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 43994334 0.44.090.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.44.131.225 I slot launch_slot_: id 0 | task 3038 | processing task, is_child = 0 0.44.839.339 I slot print_timing: id 0 | task 3038 | prompt eval time = 146.46 ms / 343 tokens ( 0.43 ms per token, 2341.95 tokens per second) 0.44.839.345 I slot print_timing: id 0 | task 3038 | eval time = 561.64 ms / 54 tokens ( 10.60 ms per token, 94.37 tokens per second) 0.44.839.346 I slot print_timing: id 0 | task 3038 | total time = 708.10 ms / 397 tokens 0.44.839.347 I slot print_timing: id 0 | task 3038 | graphs reused = 2838 0.44.839.348 I slot print_timing: id 0 | task 3038 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.839.375 I slot release: id 0 | task 3038 | stop processing: n_tokens = 408, truncated = 0 0.44.867.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 44747613 0.44.867.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.44.877.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.44.938.581 I slot launch_slot_: id 0 | task 3095 | processing task, is_child = 0 0.45.570.108 I slot print_timing: id 0 | task 3095 | prompt eval time = 153.85 ms / 401 tokens ( 0.38 ms per token, 2606.47 tokens per second) 0.45.570.114 I slot print_timing: id 0 | task 3095 | eval time = 477.66 ms / 46 tokens ( 10.61 ms per token, 94.21 tokens per second) 0.45.570.115 I slot print_timing: id 0 | task 3095 | total time = 631.51 ms / 447 tokens 0.45.570.116 I slot print_timing: id 0 | task 3095 | graphs reused = 2882 0.45.570.117 I slot print_timing: id 0 | task 3095 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.570.146 I slot release: id 0 | task 3095 | stop processing: n_tokens = 458, truncated = 0 0.45.585.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 45478384 0.45.585.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.45.638.657 I slot launch_slot_: id 0 | task 3144 | processing task, is_child = 0 0.46.492.474 I slot print_timing: id 0 | task 3144 | prompt eval time = 145.93 ms / 355 tokens ( 0.41 ms per token, 2432.66 tokens per second) 0.46.492.480 I slot print_timing: id 0 | task 3144 | eval time = 707.87 ms / 68 tokens ( 10.57 ms per token, 94.65 tokens per second) 0.46.492.480 I slot print_timing: id 0 | task 3144 | total time = 853.80 ms / 423 tokens 0.46.492.481 I slot print_timing: id 0 | task 3144 | graphs reused = 2948 0.46.492.482 I slot print_timing: id 0 | task 3144 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.492.509 I slot release: id 0 | task 3144 | stop processing: n_tokens = 434, truncated = 0 0.46.517.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 46400747 0.46.517.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.46.575.218 I slot launch_slot_: id 0 | task 3215 | processing task, is_child = 0 0.47.349.523 I slot print_timing: id 0 | task 3215 | prompt eval time = 145.24 ms / 351 tokens ( 0.41 ms per token, 2416.69 tokens per second) 0.47.349.529 I slot print_timing: id 0 | task 3215 | eval time = 629.05 ms / 57 tokens ( 11.23 ms per token, 89.02 tokens per second) 0.47.349.530 I slot print_timing: id 0 | task 3215 | total time = 774.29 ms / 408 tokens 0.47.349.530 I slot print_timing: id 0 | task 3215 | graphs reused = 3003 0.47.349.531 I slot print_timing: id 0 | task 3215 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.349.559 I slot release: id 0 | task 3215 | stop processing: n_tokens = 419, truncated = 0 0.47.371.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 47257797 0.47.371.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.47.381.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.47.438.420 I slot launch_slot_: id 0 | task 3275 | processing task, is_child = 0 0.48.579.575 I slot print_timing: id 0 | task 3275 | prompt eval time = 170.00 ms / 475 tokens ( 0.36 ms per token, 2794.18 tokens per second) 0.48.579.582 I slot print_timing: id 0 | task 3275 | eval time = 971.14 ms / 93 tokens ( 10.56 ms per token, 94.73 tokens per second) 0.48.579.583 I slot print_timing: id 0 | task 3275 | total time = 1141.13 ms / 568 tokens 0.48.579.583 I slot print_timing: id 0 | task 3275 | graphs reused = 3093 0.48.579.584 I slot print_timing: id 0 | task 3275 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.579.618 I slot release: id 0 | task 3275 | stop processing: n_tokens = 579, truncated = 0 0.48.594.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 48487856 0.48.594.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.48.645.921 I slot launch_slot_: id 0 | task 3371 | processing task, is_child = 0 0.49.928.919 I slot print_timing: id 0 | task 3371 | prompt eval time = 166.53 ms / 440 tokens ( 0.38 ms per token, 2642.13 tokens per second) 0.49.928.924 I slot print_timing: id 0 | task 3371 | eval time = 1116.45 ms / 106 tokens ( 10.63 ms per token, 94.05 tokens per second) 0.49.928.925 I slot print_timing: id 0 | task 3371 | total time = 1282.98 ms / 546 tokens 0.49.928.927 I slot print_timing: id 0 | task 3371 | graphs reused = 3196 0.49.928.928 I slot print_timing: id 0 | task 3371 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.928.960 I slot release: id 0 | task 3371 | stop processing: n_tokens = 557, truncated = 0 0.49.948.909 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 49837198 0.49.948.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.50.007.227 I slot launch_slot_: id 0 | task 3480 | processing task, is_child = 0 0.50.721.528 I slot print_timing: id 0 | task 3480 | prompt eval time = 144.01 ms / 345 tokens ( 0.42 ms per token, 2395.67 tokens per second) 0.50.721.533 I slot print_timing: id 0 | task 3480 | eval time = 570.27 ms / 55 tokens ( 10.56 ms per token, 94.69 tokens per second) 0.50.721.535 I slot print_timing: id 0 | task 3480 | total time = 714.28 ms / 400 tokens 0.50.721.535 I slot print_timing: id 0 | task 3480 | graphs reused = 3249 0.50.721.536 I slot print_timing: id 0 | task 3480 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.721.563 I slot release: id 0 | task 3480 | stop processing: n_tokens = 411, truncated = 0 0.50.741.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 50629801 0.50.741.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.50.750.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.50.810.041 I slot launch_slot_: id 0 | task 3538 | processing task, is_child = 0 0.51.532.059 I slot print_timing: id 0 | task 3538 | prompt eval time = 151.40 ms / 382 tokens ( 0.40 ms per token, 2523.15 tokens per second) 0.51.532.065 I slot print_timing: id 0 | task 3538 | eval time = 570.60 ms / 55 tokens ( 10.57 ms per token, 94.64 tokens per second) 0.51.532.066 I slot print_timing: id 0 | task 3538 | total time = 722.00 ms / 437 tokens 0.51.532.067 I slot print_timing: id 0 | task 3538 | graphs reused = 3302 0.51.532.067 I slot print_timing: id 0 | task 3538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.532.097 I slot release: id 0 | task 3538 | stop processing: n_tokens = 448, truncated = 0 0.51.547.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 51440335 0.51.547.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.51.600.003 I slot launch_slot_: id 0 | task 3596 | processing task, is_child = 0 0.52.208.626 I slot print_timing: id 0 | task 3596 | prompt eval time = 143.29 ms / 337 tokens ( 0.43 ms per token, 2351.92 tokens per second) 0.52.208.632 I slot print_timing: id 0 | task 3596 | eval time = 465.32 ms / 45 tokens ( 10.58 ms per token, 94.56 tokens per second) 0.52.208.633 I slot print_timing: id 0 | task 3596 | total time = 608.60 ms / 382 tokens 0.52.208.634 I slot print_timing: id 0 | task 3596 | graphs reused = 3345 0.52.208.634 I slot print_timing: id 0 | task 3596 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.208.661 I slot release: id 0 | task 3596 | stop processing: n_tokens = 393, truncated = 0 0.52.229.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 52116899 0.52.229.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.52.292.323 I slot launch_slot_: id 0 | task 3644 | processing task, is_child = 0 0.53.204.753 I slot print_timing: id 0 | task 3644 | prompt eval time = 152.44 ms / 402 tokens ( 0.38 ms per token, 2637.17 tokens per second) 0.53.204.759 I slot print_timing: id 0 | task 3644 | eval time = 759.98 ms / 70 tokens ( 11.01 ms per token, 90.79 tokens per second) 0.53.204.760 I slot print_timing: id 0 | task 3644 | total time = 912.41 ms / 472 tokens 0.53.204.761 I slot print_timing: id 0 | task 3644 | graphs reused = 3413 0.53.204.762 I slot print_timing: id 0 | task 3644 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.204.794 I slot release: id 0 | task 3644 | stop processing: n_tokens = 483, truncated = 0 0.53.226.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 53113032 0.53.226.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.53.236.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.53.295.841 I slot launch_slot_: id 0 | task 3717 | processing task, is_child = 0 0.54.079.480 I slot print_timing: id 0 | task 3717 | prompt eval time = 188.56 ms / 549 tokens ( 0.34 ms per token, 2911.60 tokens per second) 0.54.079.486 I slot print_timing: id 0 | task 3717 | eval time = 595.06 ms / 57 tokens ( 10.63 ms per token, 94.11 tokens per second) 0.54.079.487 I slot print_timing: id 0 | task 3717 | total time = 783.62 ms / 606 tokens 0.54.079.488 I slot print_timing: id 0 | task 3717 | graphs reused = 3468 0.54.079.489 I slot print_timing: id 0 | task 3717 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.079.522 I slot release: id 0 | task 3717 | stop processing: n_tokens = 617, truncated = 0 0.54.096.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 53987759 0.54.096.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.54.170.317 I slot launch_slot_: id 0 | task 3778 | processing task, is_child = 0 0.54.978.550 I slot print_timing: id 0 | task 3778 | prompt eval time = 205.68 ms / 616 tokens ( 0.33 ms per token, 2994.97 tokens per second) 0.54.978.556 I slot print_timing: id 0 | task 3778 | eval time = 602.53 ms / 58 tokens ( 10.57 ms per token, 94.60 tokens per second) 0.54.978.557 I slot print_timing: id 0 | task 3778 | total time = 808.21 ms / 674 tokens 0.54.978.558 I slot print_timing: id 0 | task 3778 | graphs reused = 3524 0.54.978.559 I slot print_timing: id 0 | task 3778 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.978.596 I slot release: id 0 | task 3778 | stop processing: n_tokens = 685, truncated = 0 0.55.002.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 54886834 0.55.002.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.55.011.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.55.087.654 I slot launch_slot_: id 0 | task 3840 | processing task, is_child = 0 0.55.951.202 I slot print_timing: id 0 | task 3840 | prompt eval time = 219.42 ms / 665 tokens ( 0.33 ms per token, 3030.69 tokens per second) 0.55.951.207 I slot print_timing: id 0 | task 3840 | eval time = 644.11 ms / 62 tokens ( 10.56 ms per token, 94.70 tokens per second) 0.55.951.208 I slot print_timing: id 0 | task 3840 | total time = 863.53 ms / 727 tokens 0.55.951.209 I slot print_timing: id 0 | task 3840 | graphs reused = 3584 0.55.951.210 I slot print_timing: id 0 | task 3840 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.951.247 I slot release: id 0 | task 3840 | stop processing: n_tokens = 738, truncated = 0 0.55.955.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 55859485 0.55.956.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.55.965.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.56.043.006 I slot launch_slot_: id 0 | task 3906 | processing task, is_child = 0 0.56.836.488 I slot print_timing: id 0 | task 3906 | prompt eval time = 215.76 ms / 645 tokens ( 0.33 ms per token, 2989.42 tokens per second) 0.56.836.493 I slot print_timing: id 0 | task 3906 | eval time = 577.70 ms / 55 tokens ( 10.70 ms per token, 93.47 tokens per second) 0.56.836.494 I slot print_timing: id 0 | task 3906 | total time = 793.46 ms / 700 tokens 0.56.836.495 I slot print_timing: id 0 | task 3906 | graphs reused = 3637 0.56.836.496 I slot print_timing: id 0 | task 3906 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.836.532 I slot release: id 0 | task 3906 | stop processing: n_tokens = 711, truncated = 0 0.56.864.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 56744770 0.56.865.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.56.942.856 I slot launch_slot_: id 0 | task 3965 | processing task, is_child = 0 0.57.675.829 I slot print_timing: id 0 | task 3965 | prompt eval time = 174.56 ms / 474 tokens ( 0.37 ms per token, 2715.32 tokens per second) 0.57.675.835 I slot print_timing: id 0 | task 3965 | eval time = 558.39 ms / 52 tokens ( 10.95 ms per token, 91.33 tokens per second) 0.57.675.836 I slot print_timing: id 0 | task 3965 | total time = 732.95 ms / 526 tokens 0.57.675.837 I slot print_timing: id 0 | task 3965 | graphs reused = 3686 0.57.675.837 I slot print_timing: id 0 | task 3965 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.675.869 I slot release: id 0 | task 3965 | stop processing: n_tokens = 537, truncated = 0 0.57.690.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 57584106 0.57.691.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.57.700.093 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.57.760.877 I slot launch_slot_: id 0 | task 4020 | processing task, is_child = 0 0.58.400.024 I slot print_timing: id 0 | task 4020 | prompt eval time = 200.96 ms / 617 tokens ( 0.33 ms per token, 3070.31 tokens per second) 0.58.400.030 I slot print_timing: id 0 | task 4020 | eval time = 438.17 ms / 42 tokens ( 10.69 ms per token, 93.57 tokens per second) 0.58.400.031 I slot print_timing: id 0 | task 4020 | total time = 639.13 ms / 659 tokens 0.58.400.033 I slot print_timing: id 0 | task 4020 | graphs reused = 3726 0.58.400.034 I slot print_timing: id 0 | task 4020 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.400.068 I slot release: id 0 | task 4020 | stop processing: n_tokens = 670, truncated = 0 0.58.425.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 58308305 0.58.425.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.58.495.595 I slot launch_slot_: id 0 | task 4066 | processing task, is_child = 0 0.59.220.388 I slot print_timing: id 0 | task 4066 | prompt eval time = 203.93 ms / 601 tokens ( 0.34 ms per token, 2947.10 tokens per second) 0.59.220.395 I slot print_timing: id 0 | task 4066 | eval time = 520.84 ms / 48 tokens ( 11.08 ms per token, 90.24 tokens per second) 0.59.220.396 I slot print_timing: id 0 | task 4066 | total time = 724.77 ms / 649 tokens 0.59.220.399 I slot print_timing: id 0 | task 4066 | graphs reused = 3772 0.59.220.400 I slot print_timing: id 0 | task 4066 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.220.440 I slot release: id 0 | task 4066 | stop processing: n_tokens = 660, truncated = 0 0.59.247.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 59128678 0.59.247.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.59.257.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.59.318.965 I slot launch_slot_: id 0 | task 4118 | processing task, is_child = 0 0.59.999.168 I slot print_timing: id 0 | task 4118 | prompt eval time = 189.51 ms / 533 tokens ( 0.36 ms per token, 2812.56 tokens per second) 0.59.999.176 I slot print_timing: id 0 | task 4118 | eval time = 490.66 ms / 47 tokens ( 10.67 ms per token, 93.75 tokens per second) 0.59.999.178 I slot print_timing: id 0 | task 4118 | total time = 680.16 ms / 580 tokens 0.59.999.180 I slot print_timing: id 0 | task 4118 | graphs reused = 3817 0.59.999.182 I slot print_timing: id 0 | task 4118 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.999.247 I slot release: id 0 | task 4118 | stop processing: n_tokens = 591, truncated = 0 1.00.005.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 59907485 1.00.005.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 1.00.075.878 I slot launch_slot_: id 0 | task 4169 | processing task, is_child = 0 1.00.798.763 I slot print_timing: id 0 | task 4169 | prompt eval time = 177.93 ms / 480 tokens ( 0.37 ms per token, 2697.67 tokens per second) 1.00.798.769 I slot print_timing: id 0 | task 4169 | eval time = 544.93 ms / 52 tokens ( 10.68 ms per token, 93.59 tokens per second) 1.00.798.769 I slot print_timing: id 0 | task 4169 | total time = 722.86 ms / 532 tokens 1.00.798.771 I slot print_timing: id 0 | task 4169 | graphs reused = 3866 1.00.798.771 I slot print_timing: id 0 | task 4169 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.798.801 I slot release: id 0 | task 4169 | stop processing: n_tokens = 560, truncated = 0 1.00.822.257 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 60707038 1.00.822.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.00.831.811 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.00.888.074 I slot launch_slot_: id 0 | task 4224 | processing task, is_child = 0 1.01.518.318 I slot print_timing: id 0 | task 4224 | prompt eval time = 194.32 ms / 567 tokens ( 0.34 ms per token, 2917.84 tokens per second) 1.01.518.324 I slot print_timing: id 0 | task 4224 | eval time = 435.90 ms / 42 tokens ( 10.63 ms per token, 94.06 tokens per second) 1.01.518.325 I slot print_timing: id 0 | task 4224 | total time = 630.22 ms / 609 tokens 1.01.518.326 I slot print_timing: id 0 | task 4224 | graphs reused = 3906 1.01.518.326 I slot print_timing: id 0 | task 4224 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.518.362 I slot release: id 0 | task 4224 | stop processing: n_tokens = 637, truncated = 0 1.01.535.738 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 61426600 1.01.535.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 1.01.544.384 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.01.607.645 I slot launch_slot_: id 0 | task 4270 | processing task, is_child = 0 1.02.446.873 I slot print_timing: id 0 | task 4270 | prompt eval time = 184.00 ms / 506 tokens ( 0.36 ms per token, 2750.06 tokens per second) 1.02.446.879 I slot print_timing: id 0 | task 4270 | eval time = 655.21 ms / 63 tokens ( 10.57 ms per token, 94.63 tokens per second) 1.02.446.880 I slot print_timing: id 0 | task 4270 | total time = 839.21 ms / 569 tokens 1.02.446.881 I slot print_timing: id 0 | task 4270 | graphs reused = 3967 1.02.446.882 I slot print_timing: id 0 | task 4270 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.446.914 I slot release: id 0 | task 4270 | stop processing: n_tokens = 597, truncated = 0 1.02.471.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 62355152 1.02.471.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.02.480.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.02.538.747 I slot launch_slot_: id 0 | task 4336 | processing task, is_child = 0 1.03.116.195 I slot print_timing: id 0 | task 4336 | prompt eval time = 164.76 ms / 436 tokens ( 0.38 ms per token, 2646.34 tokens per second) 1.03.116.202 I slot print_timing: id 0 | task 4336 | eval time = 412.67 ms / 40 tokens ( 10.58 ms per token, 94.51 tokens per second) 1.03.116.203 I slot print_timing: id 0 | task 4336 | total time = 577.43 ms / 476 tokens 1.03.116.205 I slot print_timing: id 0 | task 4336 | graphs reused = 4005 1.03.116.206 I slot print_timing: id 0 | task 4336 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.116.238 I slot release: id 0 | task 4336 | stop processing: n_tokens = 504, truncated = 0 1.03.120.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 63024475 1.03.120.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.03.189.940 I slot launch_slot_: id 0 | task 4379 | processing task, is_child = 0 1.04.025.722 I slot print_timing: id 0 | task 4379 | prompt eval time = 189.78 ms / 519 tokens ( 0.37 ms per token, 2734.73 tokens per second) 1.04.025.728 I slot print_timing: id 0 | task 4379 | eval time = 645.98 ms / 62 tokens ( 10.59 ms per token, 94.43 tokens per second) 1.04.025.729 I slot print_timing: id 0 | task 4379 | total time = 835.76 ms / 581 tokens 1.04.025.730 I slot print_timing: id 0 | task 4379 | graphs reused = 4065 1.04.025.731 I slot print_timing: id 0 | task 4379 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.025.764 I slot release: id 0 | task 4379 | stop processing: n_tokens = 609, truncated = 0 1.04.054.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 63934002 1.04.054.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.04.063.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.698 MiB) 1.04.124.727 I slot launch_slot_: id 0 | task 4445 | processing task, is_child = 0 1.04.781.231 I slot print_timing: id 0 | task 4445 | prompt eval time = 173.67 ms / 465 tokens ( 0.37 ms per token, 2677.51 tokens per second) 1.04.781.237 I slot print_timing: id 0 | task 4445 | eval time = 482.81 ms / 46 tokens ( 10.73 ms per token, 93.20 tokens per second) 1.04.781.238 I slot print_timing: id 0 | task 4445 | total time = 656.48 ms / 511 tokens 1.04.781.238 I slot print_timing: id 0 | task 4445 | graphs reused = 4108 1.04.781.239 I slot print_timing: id 0 | task 4445 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.781.271 I slot release: id 0 | task 4445 | stop processing: n_tokens = 542, truncated = 0 1.04.801.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 64689509 1.04.801.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.04.810.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.04.874.667 I slot launch_slot_: id 0 | task 4494 | processing task, is_child = 0 1.05.468.058 I slot print_timing: id 0 | task 4494 | prompt eval time = 168.79 ms / 431 tokens ( 0.39 ms per token, 2553.41 tokens per second) 1.05.468.063 I slot print_timing: id 0 | task 4494 | eval time = 424.58 ms / 41 tokens ( 10.61 ms per token, 94.21 tokens per second) 1.05.468.064 I slot print_timing: id 0 | task 4494 | total time = 593.37 ms / 472 tokens 1.05.468.065 I slot print_timing: id 0 | task 4494 | graphs reused = 4147 1.05.468.066 I slot print_timing: id 0 | task 4494 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.468.098 I slot release: id 0 | task 4494 | stop processing: n_tokens = 503, truncated = 0 1.05.486.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 65376335 1.05.487.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.05.495.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.05.561.342 I slot launch_slot_: id 0 | task 4538 | processing task, is_child = 0 1.06.188.053 I slot print_timing: id 0 | task 4538 | prompt eval time = 166.43 ms / 457 tokens ( 0.36 ms per token, 2745.98 tokens per second) 1.06.188.059 I slot print_timing: id 0 | task 4538 | eval time = 460.26 ms / 44 tokens ( 10.70 ms per token, 93.42 tokens per second) 1.06.188.060 I slot print_timing: id 0 | task 4538 | total time = 626.69 ms / 501 tokens 1.06.188.062 I slot print_timing: id 0 | task 4538 | graphs reused = 4188 1.06.188.063 I slot print_timing: id 0 | task 4538 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.188.095 I slot release: id 0 | task 4538 | stop processing: n_tokens = 532, truncated = 0 1.06.216.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 66096333 1.06.217.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.06.277.683 I slot launch_slot_: id 0 | task 4585 | processing task, is_child = 0 1.07.407.449 I slot print_timing: id 0 | task 4585 | prompt eval time = 172.03 ms / 439 tokens ( 0.39 ms per token, 2551.87 tokens per second) 1.07.407.455 I slot print_timing: id 0 | task 4585 | eval time = 957.71 ms / 91 tokens ( 10.64 ms per token, 93.97 tokens per second) 1.07.407.456 I slot print_timing: id 0 | task 4585 | total time = 1129.75 ms / 530 tokens 1.07.407.457 I slot print_timing: id 0 | task 4585 | graphs reused = 4276 1.07.407.458 I slot print_timing: id 0 | task 4585 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.407.494 I slot release: id 0 | task 4585 | stop processing: n_tokens = 561, truncated = 0 1.07.434.605 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 67315731 1.07.434.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.07.446.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.07.518.258 I slot launch_slot_: id 0 | task 4679 | processing task, is_child = 0 1.08.299.108 I slot print_timing: id 0 | task 4679 | prompt eval time = 197.86 ms / 606 tokens ( 0.33 ms per token, 3062.79 tokens per second) 1.08.299.114 I slot print_timing: id 0 | task 4679 | eval time = 582.97 ms / 56 tokens ( 10.60 ms per token, 94.34 tokens per second) 1.08.299.115 I slot print_timing: id 0 | task 4679 | total time = 780.83 ms / 662 tokens 1.08.299.116 I slot print_timing: id 0 | task 4679 | graphs reused = 4330 1.08.299.117 I slot print_timing: id 0 | task 4679 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.299.156 I slot release: id 0 | task 4679 | stop processing: n_tokens = 693, truncated = 0 1.08.323.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 68207394 1.08.323.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.08.334.839 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.08.431.691 I slot launch_slot_: id 0 | task 4739 | processing task, is_child = 0 1.09.036.278 I slot print_timing: id 0 | task 4739 | prompt eval time = 175.96 ms / 477 tokens ( 0.37 ms per token, 2710.89 tokens per second) 1.09.036.284 I slot print_timing: id 0 | task 4739 | eval time = 428.61 ms / 41 tokens ( 10.72 ms per token, 93.32 tokens per second) 1.09.036.285 I slot print_timing: id 0 | task 4739 | total time = 604.57 ms / 518 tokens 1.09.036.286 I slot print_timing: id 0 | task 4739 | graphs reused = 4368 1.09.036.287 I slot print_timing: id 0 | task 4739 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.036.319 I slot release: id 0 | task 4739 | stop processing: n_tokens = 549, truncated = 0 1.09.041.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 68944556 1.09.041.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.09.098.871 I slot launch_slot_: id 0 | task 4783 | processing task, is_child = 0 1.09.970.730 I slot print_timing: id 0 | task 4783 | prompt eval time = 246.11 ms / 845 tokens ( 0.29 ms per token, 3433.41 tokens per second) 1.09.970.736 I slot print_timing: id 0 | task 4783 | eval time = 625.73 ms / 60 tokens ( 10.61 ms per token, 94.29 tokens per second) 1.09.970.737 I slot print_timing: id 0 | task 4783 | total time = 871.84 ms / 905 tokens 1.09.970.738 I slot print_timing: id 0 | task 4783 | graphs reused = 4426 1.09.970.739 I slot print_timing: id 0 | task 4783 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.970.783 I slot release: id 0 | task 4783 | stop processing: n_tokens = 936, truncated = 0 1.09.987.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 69879021 1.09.987.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.09.996.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.10.062.665 I slot launch_slot_: id 0 | task 4847 | processing task, is_child = 0 1.10.684.128 I slot print_timing: id 0 | task 4847 | prompt eval time = 172.15 ms / 459 tokens ( 0.38 ms per token, 2666.31 tokens per second) 1.10.684.134 I slot print_timing: id 0 | task 4847 | eval time = 449.30 ms / 43 tokens ( 10.70 ms per token, 93.48 tokens per second) 1.10.684.135 I slot print_timing: id 0 | task 4847 | total time = 621.44 ms / 502 tokens 1.10.684.136 I slot print_timing: id 0 | task 4847 | graphs reused = 4466 1.10.684.137 I slot print_timing: id 0 | task 4847 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.684.170 I slot release: id 0 | task 4847 | stop processing: n_tokens = 533, truncated = 0 1.10.702.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 70592407 1.10.702.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.10.782.163 I slot launch_slot_: id 0 | task 4893 | processing task, is_child = 0 1.11.479.126 I slot print_timing: id 0 | task 4893 | prompt eval time = 210.28 ms / 670 tokens ( 0.31 ms per token, 3186.17 tokens per second) 1.11.479.132 I slot print_timing: id 0 | task 4893 | eval time = 486.66 ms / 47 tokens ( 10.58 ms per token, 94.52 tokens per second) 1.11.479.133 I slot print_timing: id 0 | task 4893 | total time = 696.94 ms / 717 tokens 1.11.479.134 I slot print_timing: id 0 | task 4893 | graphs reused = 4511 1.11.479.135 I slot print_timing: id 0 | task 4893 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.479.176 I slot release: id 0 | task 4893 | stop processing: n_tokens = 748, truncated = 0 1.11.496.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 71387413 1.11.496.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.11.508.504 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.11.601.704 I slot launch_slot_: id 0 | task 4944 | processing task, is_child = 0 1.12.525.428 I slot print_timing: id 0 | task 4944 | prompt eval time = 238.32 ms / 775 tokens ( 0.31 ms per token, 3251.94 tokens per second) 1.12.525.433 I slot print_timing: id 0 | task 4944 | eval time = 685.38 ms / 63 tokens ( 11.05 ms per token, 90.46 tokens per second) 1.12.525.434 I slot print_timing: id 0 | task 4944 | total time = 923.70 ms / 838 tokens 1.12.525.436 I slot print_timing: id 0 | task 4944 | graphs reused = 4572 1.12.525.436 I slot print_timing: id 0 | task 4944 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.525.478 I slot release: id 0 | task 4944 | stop processing: n_tokens = 869, truncated = 0 1.12.540.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 72433715 1.12.541.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.12.553.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.12.647.616 I slot launch_slot_: id 0 | task 5011 | processing task, is_child = 0 1.13.597.930 I slot print_timing: id 0 | task 5011 | prompt eval time = 206.42 ms / 573 tokens ( 0.36 ms per token, 2775.87 tokens per second) 1.13.597.935 I slot print_timing: id 0 | task 5011 | eval time = 743.87 ms / 71 tokens ( 10.63 ms per token, 94.10 tokens per second) 1.13.597.936 I slot print_timing: id 0 | task 5011 | total time = 950.30 ms / 644 tokens 1.13.597.938 I slot print_timing: id 0 | task 5011 | graphs reused = 4641 1.13.597.939 I slot print_timing: id 0 | task 5011 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.597.974 I slot release: id 0 | task 5011 | stop processing: n_tokens = 675, truncated = 0 1.13.602.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 73506212 1.13.602.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.13.615.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.13.709.839 I slot launch_slot_: id 0 | task 5086 | processing task, is_child = 0 1.14.551.835 I slot print_timing: id 0 | task 5086 | prompt eval time = 173.12 ms / 461 tokens ( 0.38 ms per token, 2662.88 tokens per second) 1.14.551.843 I slot print_timing: id 0 | task 5086 | eval time = 668.85 ms / 64 tokens ( 10.62 ms per token, 94.19 tokens per second) 1.14.551.844 I slot print_timing: id 0 | task 5086 | total time = 841.98 ms / 525 tokens 1.14.551.845 I slot print_timing: id 0 | task 5086 | graphs reused = 4702 1.14.551.846 I slot print_timing: id 0 | task 5086 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.551.879 I slot release: id 0 | task 5086 | stop processing: n_tokens = 556, truncated = 0 1.14.556.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 74460117 1.14.556.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.14.640.802 I slot launch_slot_: id 0 | task 5153 | processing task, is_child = 0 1.15.430.377 I slot print_timing: id 0 | task 5153 | prompt eval time = 196.24 ms / 609 tokens ( 0.32 ms per token, 3103.42 tokens per second) 1.15.430.383 I slot print_timing: id 0 | task 5153 | eval time = 593.32 ms / 57 tokens ( 10.59 ms per token, 94.38 tokens per second) 1.15.430.384 I slot print_timing: id 0 | task 5153 | total time = 789.55 ms / 666 tokens 1.15.430.385 I slot print_timing: id 0 | task 5153 | graphs reused = 4757 1.15.430.386 I slot print_timing: id 0 | task 5153 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.430.428 I slot release: id 0 | task 5153 | stop processing: n_tokens = 697, truncated = 0 1.15.450.466 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 697, t_last = 75338666 1.15.450.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.15.462.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.15.597.605 I slot launch_slot_: id 0 | task 5214 | processing task, is_child = 0 1.16.472.466 I slot print_timing: id 0 | task 5214 | prompt eval time = 239.57 ms / 791 tokens ( 0.30 ms per token, 3301.71 tokens per second) 1.16.472.472 I slot print_timing: id 0 | task 5214 | eval time = 635.27 ms / 61 tokens ( 10.59 ms per token, 94.45 tokens per second) 1.16.472.473 I slot print_timing: id 0 | task 5214 | total time = 874.84 ms / 852 tokens 1.16.472.474 I slot print_timing: id 0 | task 5214 | graphs reused = 4816 1.16.472.475 I slot print_timing: id 0 | task 5214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.472.519 I slot release: id 0 | task 5214 | stop processing: n_tokens = 883, truncated = 0 1.16.488.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 76380757 1.16.488.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.16.622.287 I slot launch_slot_: id 0 | task 5279 | processing task, is_child = 0 1.17.394.029 I slot print_timing: id 0 | task 5279 | prompt eval time = 188.50 ms / 533 tokens ( 0.35 ms per token, 2827.66 tokens per second) 1.17.394.034 I slot print_timing: id 0 | task 5279 | eval time = 583.23 ms / 56 tokens ( 10.60 ms per token, 94.30 tokens per second) 1.17.394.035 I slot print_timing: id 0 | task 5279 | total time = 771.72 ms / 589 tokens 1.17.394.037 I slot print_timing: id 0 | task 5279 | graphs reused = 4870 1.17.394.038 I slot print_timing: id 0 | task 5279 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.394.074 I slot release: id 0 | task 5279 | stop processing: n_tokens = 677, truncated = 0 1.17.398.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 77302312 1.17.398.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.17.488.654 I slot launch_slot_: id 0 | task 5339 | processing task, is_child = 0 1.18.197.760 I slot print_timing: id 0 | task 5339 | prompt eval time = 201.21 ms / 566 tokens ( 0.36 ms per token, 2813.02 tokens per second) 1.18.197.765 I slot print_timing: id 0 | task 5339 | eval time = 507.88 ms / 46 tokens ( 11.29 ms per token, 88.60 tokens per second) 1.18.197.766 I slot print_timing: id 0 | task 5339 | total time = 709.09 ms / 612 tokens 1.18.197.767 I slot print_timing: id 0 | task 5339 | graphs reused = 4914 1.18.197.767 I slot print_timing: id 0 | task 5339 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.197.804 I slot release: id 0 | task 5339 | stop processing: n_tokens = 643, truncated = 0 1.18.219.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 78106042 1.18.219.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.18.307.322 I slot launch_slot_: id 0 | task 5389 | processing task, is_child = 0 1.18.930.650 I slot print_timing: id 0 | task 5389 | prompt eval time = 171.41 ms / 443 tokens ( 0.39 ms per token, 2584.48 tokens per second) 1.18.930.655 I slot print_timing: id 0 | task 5389 | eval time = 451.90 ms / 43 tokens ( 10.76 ms per token, 92.94 tokens per second) 1.18.930.656 I slot print_timing: id 0 | task 5389 | total time = 623.31 ms / 486 tokens 1.18.930.657 I slot print_timing: id 0 | task 5389 | graphs reused = 4954 1.18.930.658 I slot print_timing: id 0 | task 5389 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.930.694 I slot release: id 0 | task 5389 | stop processing: n_tokens = 517, truncated = 0 1.18.934.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 78838931 1.18.934.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.19.038.619 I slot launch_slot_: id 0 | task 5435 | processing task, is_child = 0 1.19.893.757 I slot print_timing: id 0 | task 5435 | prompt eval time = 174.79 ms / 487 tokens ( 0.36 ms per token, 2786.26 tokens per second) 1.19.893.763 I slot print_timing: id 0 | task 5435 | eval time = 680.33 ms / 65 tokens ( 10.63 ms per token, 94.07 tokens per second) 1.19.893.764 I slot print_timing: id 0 | task 5435 | total time = 855.12 ms / 552 tokens 1.19.893.766 I slot print_timing: id 0 | task 5435 | graphs reused = 5017 1.19.893.767 I slot print_timing: id 0 | task 5435 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.893.801 I slot release: id 0 | task 5435 | stop processing: n_tokens = 583, truncated = 0 1.19.915.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 79802039 1.19.915.769 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.20.006.687 I slot launch_slot_: id 0 | task 5503 | processing task, is_child = 0 1.20.674.060 I slot print_timing: id 0 | task 5503 | prompt eval time = 179.66 ms / 507 tokens ( 0.35 ms per token, 2821.95 tokens per second) 1.20.674.066 I slot print_timing: id 0 | task 5503 | eval time = 487.69 ms / 47 tokens ( 10.60 ms per token, 94.32 tokens per second) 1.20.674.067 I slot print_timing: id 0 | task 5503 | total time = 667.35 ms / 554 tokens 1.20.674.068 I slot print_timing: id 0 | task 5503 | graphs reused = 5062 1.20.674.068 I slot print_timing: id 0 | task 5503 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.674.103 I slot release: id 0 | task 5503 | stop processing: n_tokens = 585, truncated = 0 1.20.694.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 80582341 1.20.694.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.20.709.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.20.784.288 I slot launch_slot_: id 0 | task 5553 | processing task, is_child = 0 1.21.677.064 I slot print_timing: id 0 | task 5553 | prompt eval time = 202.01 ms / 633 tokens ( 0.32 ms per token, 3133.43 tokens per second) 1.21.677.070 I slot print_timing: id 0 | task 5553 | eval time = 690.74 ms / 66 tokens ( 10.63 ms per token, 94.10 tokens per second) 1.21.677.071 I slot print_timing: id 0 | task 5553 | total time = 892.75 ms / 699 tokens 1.21.677.072 I slot print_timing: id 0 | task 5553 | graphs reused = 5126 1.21.677.073 I slot print_timing: id 0 | task 5553 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.677.120 I slot release: id 0 | task 5553 | stop processing: n_tokens = 730, truncated = 0 1.21.703.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 81585358 1.21.703.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.21.785.371 I slot launch_slot_: id 0 | task 5623 | processing task, is_child = 0 1.22.471.000 I slot print_timing: id 0 | task 5623 | prompt eval time = 195.86 ms / 571 tokens ( 0.34 ms per token, 2915.39 tokens per second) 1.22.471.005 I slot print_timing: id 0 | task 5623 | eval time = 489.75 ms / 47 tokens ( 10.65 ms per token, 93.93 tokens per second) 1.22.471.006 I slot print_timing: id 0 | task 5623 | total time = 685.61 ms / 618 tokens 1.22.471.007 I slot print_timing: id 0 | task 5623 | graphs reused = 5171 1.22.471.008 I slot print_timing: id 0 | task 5623 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.471.045 I slot release: id 0 | task 5623 | stop processing: n_tokens = 649, truncated = 0 1.22.497.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 82379283 1.22.497.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.22.601.047 I slot launch_slot_: id 0 | task 5674 | processing task, is_child = 0 1.23.300.662 I slot print_timing: id 0 | task 5674 | prompt eval time = 238.66 ms / 798 tokens ( 0.30 ms per token, 3343.74 tokens per second) 1.23.300.668 I slot print_timing: id 0 | task 5674 | eval time = 460.94 ms / 44 tokens ( 10.72 ms per token, 93.29 tokens per second) 1.23.300.669 I slot print_timing: id 0 | task 5674 | total time = 699.60 ms / 842 tokens 1.23.300.670 I slot print_timing: id 0 | task 5674 | graphs reused = 5213 1.23.300.671 I slot print_timing: id 0 | task 5674 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.300.713 I slot release: id 0 | task 5674 | stop processing: n_tokens = 873, truncated = 0 1.23.321.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 83208951 1.23.321.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.23.338.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.23.427.072 I slot launch_slot_: id 0 | task 5722 | processing task, is_child = 0 1.24.072.967 I slot print_timing: id 0 | task 5722 | prompt eval time = 194.62 ms / 572 tokens ( 0.34 ms per token, 2939.06 tokens per second) 1.24.072.973 I slot print_timing: id 0 | task 5722 | eval time = 451.26 ms / 43 tokens ( 10.74 ms per token, 93.07 tokens per second) 1.24.072.974 I slot print_timing: id 0 | task 5722 | total time = 645.88 ms / 615 tokens 1.24.072.975 I slot print_timing: id 0 | task 5722 | graphs reused = 5254 1.24.072.976 I slot print_timing: id 0 | task 5722 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.073.011 I slot release: id 0 | task 5722 | stop processing: n_tokens = 646, truncated = 0 1.24.100.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 83981248 1.24.100.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.24.191.739 I slot launch_slot_: id 0 | task 5769 | processing task, is_child = 0 1.24.905.074 I slot print_timing: id 0 | task 5769 | prompt eval time = 203.05 ms / 613 tokens ( 0.33 ms per token, 3018.90 tokens per second) 1.24.905.079 I slot print_timing: id 0 | task 5769 | eval time = 510.26 ms / 49 tokens ( 10.63 ms per token, 94.07 tokens per second) 1.24.905.081 I slot print_timing: id 0 | task 5769 | total time = 713.32 ms / 662 tokens 1.24.905.082 I slot print_timing: id 0 | task 5769 | graphs reused = 5301 1.24.905.083 I slot print_timing: id 0 | task 5769 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.905.120 I slot release: id 0 | task 5769 | stop processing: n_tokens = 693, truncated = 0 1.24.926.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 84813358 1.24.926.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.25.002.316 I slot launch_slot_: id 0 | task 5822 | processing task, is_child = 0 1.25.989.848 I slot print_timing: id 0 | task 5822 | prompt eval time = 194.11 ms / 580 tokens ( 0.33 ms per token, 2988.01 tokens per second) 1.25.989.853 I slot print_timing: id 0 | task 5822 | eval time = 793.40 ms / 76 tokens ( 10.58 ms per token, 94.53 tokens per second) 1.25.989.854 I slot print_timing: id 0 | task 5822 | total time = 987.51 ms / 656 tokens 1.25.989.855 I slot print_timing: id 0 | task 5822 | graphs reused = 5375 1.25.989.855 I slot print_timing: id 0 | task 5822 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.989.890 I slot release: id 0 | task 5822 | stop processing: n_tokens = 687, truncated = 0 1.26.016.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 85898128 1.26.016.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.26.091.175 I slot launch_slot_: id 0 | task 5902 | processing task, is_child = 0 1.26.838.098 I slot print_timing: id 0 | task 5902 | prompt eval time = 222.15 ms / 716 tokens ( 0.31 ms per token, 3223.11 tokens per second) 1.26.838.104 I slot print_timing: id 0 | task 5902 | eval time = 524.76 ms / 50 tokens ( 10.71 ms per token, 93.38 tokens per second) 1.26.838.105 I slot print_timing: id 0 | task 5902 | total time = 746.90 ms / 766 tokens 1.26.838.105 I slot print_timing: id 0 | task 5902 | graphs reused = 5422 1.26.838.106 I slot print_timing: id 0 | task 5902 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.838.145 I slot release: id 0 | task 5902 | stop processing: n_tokens = 797, truncated = 0 1.26.859.992 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 86746383 1.26.860.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.26.877.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.26.954.624 I slot launch_slot_: id 0 | task 5956 | processing task, is_child = 0 1.28.280.511 I slot print_timing: id 0 | task 5956 | prompt eval time = 238.80 ms / 799 tokens ( 0.30 ms per token, 3345.95 tokens per second) 1.28.280.517 I slot print_timing: id 0 | task 5956 | eval time = 1087.07 ms / 102 tokens ( 10.76 ms per token, 92.91 tokens per second) 1.28.280.519 I slot print_timing: id 0 | task 5956 | total time = 1325.86 ms / 901 tokens 1.28.280.520 I slot print_timing: id 0 | task 5956 | graphs reused = 5522 1.28.280.521 I slot print_timing: id 0 | task 5956 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.280.566 I slot release: id 0 | task 5956 | stop processing: n_tokens = 932, truncated = 0 1.28.305.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 88188803 1.28.305.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 1.28.383.028 I slot launch_slot_: id 0 | task 6062 | processing task, is_child = 0 1.29.708.656 I slot print_timing: id 0 | task 6062 | prompt eval time = 149.67 ms / 361 tokens ( 0.41 ms per token, 2412.01 tokens per second) 1.29.708.662 I slot print_timing: id 0 | task 6062 | eval time = 1175.94 ms / 112 tokens ( 10.59 ms per token, 94.39 tokens per second) 1.29.708.662 I slot print_timing: id 0 | task 6062 | total time = 1325.61 ms / 473 tokens 1.29.708.664 I slot print_timing: id 0 | task 6062 | graphs reused = 5632 1.29.708.664 I slot print_timing: id 0 | task 6062 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.708.694 I slot release: id 0 | task 6062 | stop processing: n_tokens = 504, truncated = 0 1.29.732.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 89616932 1.29.732.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.29.809.922 I slot launch_slot_: id 0 | task 6177 | processing task, is_child = 0 1.31.097.600 I slot print_timing: id 0 | task 6177 | prompt eval time = 150.22 ms / 381 tokens ( 0.39 ms per token, 2536.35 tokens per second) 1.31.097.606 I slot print_timing: id 0 | task 6177 | eval time = 1137.44 ms / 108 tokens ( 10.63 ms per token, 94.07 tokens per second) 1.31.097.607 I slot print_timing: id 0 | task 6177 | total time = 1287.66 ms / 489 tokens 1.31.097.608 I slot print_timing: id 0 | task 6177 | graphs reused = 5737 1.31.097.609 I slot print_timing: id 0 | task 6177 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.097.642 I slot release: id 0 | task 6177 | stop processing: n_tokens = 520, truncated = 0 1.31.112.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 91005879 1.31.112.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.31.175.309 I slot launch_slot_: id 0 | task 6288 | processing task, is_child = 0 1.32.628.988 I slot print_timing: id 0 | task 6288 | prompt eval time = 149.80 ms / 365 tokens ( 0.41 ms per token, 2436.58 tokens per second) 1.32.628.994 I slot print_timing: id 0 | task 6288 | eval time = 1303.86 ms / 124 tokens ( 10.60 ms per token, 94.34 tokens per second) 1.32.628.995 I slot print_timing: id 0 | task 6288 | total time = 1453.66 ms / 489 tokens 1.32.628.995 I slot print_timing: id 0 | task 6288 | graphs reused = 5858 1.32.628.996 I slot print_timing: id 0 | task 6288 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.629.025 I slot release: id 0 | task 6288 | stop processing: n_tokens = 520, truncated = 0 1.32.652.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 92537263 1.32.652.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.32.710.993 I slot launch_slot_: id 0 | task 6415 | processing task, is_child = 0 1.33.970.848 I slot print_timing: id 0 | task 6415 | prompt eval time = 144.06 ms / 333 tokens ( 0.43 ms per token, 2311.47 tokens per second) 1.33.970.854 I slot print_timing: id 0 | task 6415 | eval time = 1115.77 ms / 107 tokens ( 10.53 ms per token, 95.00 tokens per second) 1.33.970.855 I slot print_timing: id 0 | task 6415 | total time = 1259.84 ms / 440 tokens 1.33.970.856 I slot print_timing: id 0 | task 6415 | graphs reused = 5963 1.33.970.857 I slot print_timing: id 0 | task 6415 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.970.884 I slot release: id 0 | task 6415 | stop processing: n_tokens = 471, truncated = 0 1.33.990.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 93879122 1.34.043.826 I slot launch_slot_: id 0 | task 6525 | processing task, is_child = 0 1.35.646.600 I slot print_timing: id 0 | task 6525 | prompt eval time = 153.40 ms / 403 tokens ( 0.38 ms per token, 2627.14 tokens per second) 1.35.646.606 I slot print_timing: id 0 | task 6525 | eval time = 1449.36 ms / 138 tokens ( 10.58 ms per token, 94.52 tokens per second) 1.35.646.607 I slot print_timing: id 0 | task 6525 | total time = 1602.75 ms / 541 tokens 1.35.646.608 I slot print_timing: id 0 | task 6525 | graphs reused = 6098 1.35.646.608 I slot print_timing: id 0 | task 6525 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.646.640 I slot release: id 0 | task 6525 | stop processing: n_tokens = 572, truncated = 0 1.35.674.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 95554877 1.35.674.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.35.775.894 I slot launch_slot_: id 0 | task 6666 | processing task, is_child = 0 1.37.875.863 I slot print_timing: id 0 | task 6666 | prompt eval time = 152.39 ms / 411 tokens ( 0.37 ms per token, 2697.03 tokens per second) 1.37.875.869 I slot print_timing: id 0 | task 6666 | eval time = 1947.56 ms / 185 tokens ( 10.58 ms per token, 94.48 tokens per second) 1.37.875.870 I slot print_timing: id 0 | task 6666 | total time = 2099.95 ms / 596 tokens 1.37.875.871 I slot print_timing: id 0 | task 6666 | graphs reused = 6280 1.37.875.872 I slot print_timing: id 0 | task 6666 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.875.903 I slot release: id 0 | task 6666 | stop processing: n_tokens = 627, truncated = 0 1.37.890.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 97784141 1.37.890.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.37.989.609 I slot launch_slot_: id 0 | task 6854 | processing task, is_child = 0 1.40.535.760 I slot print_timing: id 0 | task 6854 | prompt eval time = 181.66 ms / 490 tokens ( 0.37 ms per token, 2697.39 tokens per second) 1.40.535.765 I slot print_timing: id 0 | task 6854 | eval time = 2364.47 ms / 225 tokens ( 10.56 ms per token, 94.74 tokens per second) 1.40.535.766 I slot print_timing: id 0 | task 6854 | total time = 2546.13 ms / 715 tokens 1.40.535.767 I slot print_timing: id 0 | task 6854 | graphs reused = 6503 1.40.535.768 I slot print_timing: id 0 | task 6854 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.535.800 I slot release: id 0 | task 6854 | stop processing: n_tokens = 746, truncated = 0 1.40.552.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 100444038 1.40.552.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.40.648.679 I slot launch_slot_: id 0 | task 7082 | processing task, is_child = 0 1.42.588.993 I slot print_timing: id 0 | task 7082 | prompt eval time = 144.60 ms / 344 tokens ( 0.42 ms per token, 2378.91 tokens per second) 1.42.588.999 I slot print_timing: id 0 | task 7082 | eval time = 1795.69 ms / 171 tokens ( 10.56 ms per token, 94.67 tokens per second) 1.42.589.000 I slot print_timing: id 0 | task 7082 | total time = 1940.30 ms / 515 tokens 1.42.589.000 I slot print_timing: id 0 | task 7082 | graphs reused = 6671 1.42.589.001 I slot print_timing: id 0 | task 7082 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.589.029 I slot release: id 0 | task 7082 | stop processing: n_tokens = 546, truncated = 0 1.42.606.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 102497267 1.42.606.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.42.699.794 I slot launch_slot_: id 0 | task 7256 | processing task, is_child = 0 1.44.646.405 I slot print_timing: id 0 | task 7256 | prompt eval time = 147.41 ms / 347 tokens ( 0.42 ms per token, 2354.01 tokens per second) 1.44.646.411 I slot print_timing: id 0 | task 7256 | eval time = 1799.18 ms / 171 tokens ( 10.58 ms per token, 94.49 tokens per second) 1.44.646.412 I slot print_timing: id 0 | task 7256 | total time = 1946.59 ms / 518 tokens 1.44.646.413 I slot print_timing: id 0 | task 7256 | graphs reused = 6839 1.44.646.414 I slot print_timing: id 0 | task 7256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.646.445 I slot release: id 0 | task 7256 | stop processing: n_tokens = 549, truncated = 0 1.44.671.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 104554682 1.44.671.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.551 MiB) 1.44.769.632 I slot launch_slot_: id 0 | task 7430 | processing task, is_child = 0 1.46.245.970 I slot print_timing: id 0 | task 7430 | prompt eval time = 154.15 ms / 401 tokens ( 0.38 ms per token, 2601.35 tokens per second) 1.46.245.976 I slot print_timing: id 0 | task 7430 | eval time = 1322.16 ms / 126 tokens ( 10.58 ms per token, 94.54 tokens per second) 1.46.245.977 I slot print_timing: id 0 | task 7430 | total time = 1476.32 ms / 527 tokens 1.46.245.978 I slot print_timing: id 0 | task 7430 | graphs reused = 6962 1.46.245.979 I slot print_timing: id 0 | task 7430 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.246.010 I slot release: id 0 | task 7430 | stop processing: n_tokens = 558, truncated = 0 1.46.261.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 106154247 1.46.261.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.46.355.053 I slot launch_slot_: id 0 | task 7559 | processing task, is_child = 0 1.47.753.109 I slot print_timing: id 0 | task 7559 | prompt eval time = 164.58 ms / 456 tokens ( 0.36 ms per token, 2770.66 tokens per second) 1.47.753.114 I slot print_timing: id 0 | task 7559 | eval time = 1233.46 ms / 115 tokens ( 10.82 ms per token, 92.42 tokens per second) 1.47.753.116 I slot print_timing: id 0 | task 7559 | total time = 1398.04 ms / 571 tokens 1.47.753.116 I slot print_timing: id 0 | task 7559 | graphs reused = 7074 1.47.753.117 I slot print_timing: id 0 | task 7559 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.753.149 I slot release: id 0 | task 7559 | stop processing: n_tokens = 602, truncated = 0 1.47.756.880 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 1.47.756.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.47.854.380 I slot launch_slot_: id 0 | task 7677 | processing task, is_child = 0 1.49.188.507 I slot print_timing: id 0 | task 7677 | prompt eval time = 160.16 ms / 406 tokens ( 0.39 ms per token, 2535.04 tokens per second) 1.49.188.512 I slot print_timing: id 0 | task 7677 | eval time = 1173.95 ms / 112 tokens ( 10.58 ms per token, 94.55 tokens per second) 1.49.188.514 I slot print_timing: id 0 | task 7677 | total time = 1334.11 ms / 518 tokens 1.49.188.514 I slot print_timing: id 0 | task 7677 | graphs reused = 7183 1.49.188.516 I slot print_timing: id 0 | task 7677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.188.546 I slot release: id 0 | task 7677 | stop processing: n_tokens = 549, truncated = 0 1.49.212.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 109096783 1.49.294.068 I slot launch_slot_: id 0 | task 7792 | processing task, is_child = 0 1.51.328.863 I slot print_timing: id 0 | task 7792 | prompt eval time = 156.53 ms / 406 tokens ( 0.39 ms per token, 2593.79 tokens per second) 1.51.328.869 I slot print_timing: id 0 | task 7792 | eval time = 1878.25 ms / 179 tokens ( 10.55 ms per token, 94.77 tokens per second) 1.51.328.870 I slot print_timing: id 0 | task 7792 | total time = 2034.77 ms / 585 tokens 1.51.328.871 I slot print_timing: id 0 | task 7792 | graphs reused = 7359 1.51.328.872 I slot print_timing: id 0 | task 7792 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.328.901 I slot release: id 0 | task 7792 | stop processing: n_tokens = 616, truncated = 0 1.51.357.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 111237139 1.51.357.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.51.453.404 I slot launch_slot_: id 0 | task 7974 | processing task, is_child = 0 1.53.130.963 I slot print_timing: id 0 | task 7974 | prompt eval time = 160.82 ms / 444 tokens ( 0.36 ms per token, 2760.82 tokens per second) 1.53.130.970 I slot print_timing: id 0 | task 7974 | eval time = 1516.72 ms / 144 tokens ( 10.61 ms per token, 94.28 tokens per second) 1.53.130.971 I slot print_timing: id 0 | task 7974 | total time = 1677.54 ms / 588 tokens 1.53.130.972 I slot print_timing: id 0 | task 7974 | graphs reused = 7500 1.53.130.973 I slot print_timing: id 0 | task 7974 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.131.004 I slot release: id 0 | task 7974 | stop processing: n_tokens = 619, truncated = 0 1.53.134.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 113039242 1.53.134.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.53.226.411 I slot launch_slot_: id 0 | task 8121 | processing task, is_child = 0 1.54.455.694 I slot print_timing: id 0 | task 8121 | prompt eval time = 150.11 ms / 372 tokens ( 0.40 ms per token, 2478.12 tokens per second) 1.54.455.699 I slot print_timing: id 0 | task 8121 | eval time = 1079.15 ms / 103 tokens ( 10.58 ms per token, 94.52 tokens per second) 1.54.455.700 I slot print_timing: id 0 | task 8121 | total time = 1229.26 ms / 475 tokens 1.54.455.701 I slot print_timing: id 0 | task 8121 | graphs reused = 7601 1.54.455.702 I slot print_timing: id 0 | task 8121 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.455.735 I slot release: id 0 | task 8121 | stop processing: n_tokens = 506, truncated = 0 1.54.459.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 114363972 1.54.459.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.54.555.025 I slot launch_slot_: id 0 | task 8227 | processing task, is_child = 0 1.57.133.477 I slot print_timing: id 0 | task 8227 | prompt eval time = 161.73 ms / 454 tokens ( 0.36 ms per token, 2807.11 tokens per second) 1.57.133.483 I slot print_timing: id 0 | task 8227 | eval time = 2416.70 ms / 230 tokens ( 10.55 ms per token, 94.76 tokens per second) 1.57.133.484 I slot print_timing: id 0 | task 8227 | total time = 2578.43 ms / 684 tokens 1.57.133.485 I slot print_timing: id 0 | task 8227 | graphs reused = 7828 1.57.133.486 I slot print_timing: id 0 | task 8227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.133.522 I slot release: id 0 | task 8227 | stop processing: n_tokens = 715, truncated = 0 1.57.156.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 117041759 1.57.156.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.57.235.540 I slot launch_slot_: id 0 | task 8460 | processing task, is_child = 0 1.59.759.640 I slot print_timing: id 0 | task 8460 | prompt eval time = 150.61 ms / 354 tokens ( 0.43 ms per token, 2350.43 tokens per second) 1.59.759.645 I slot print_timing: id 0 | task 8460 | eval time = 2373.47 ms / 226 tokens ( 10.55 ms per token, 94.80 tokens per second) 1.59.759.646 I slot print_timing: id 0 | task 8460 | total time = 2524.08 ms / 580 tokens 1.59.759.647 I slot print_timing: id 0 | task 8460 | graphs reused = 8051 1.59.759.648 I slot print_timing: id 0 | task 8460 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.759.677 I slot release: id 0 | task 8460 | stop processing: n_tokens = 611, truncated = 0 1.59.763.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 119667915 1.59.763.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.59.837.961 I slot launch_slot_: id 0 | task 8689 | processing task, is_child = 0 2.01.447.979 I slot print_timing: id 0 | task 8689 | prompt eval time = 145.74 ms / 334 tokens ( 0.44 ms per token, 2291.83 tokens per second) 2.01.447.984 I slot print_timing: id 0 | task 8689 | eval time = 1464.26 ms / 140 tokens ( 10.53 ms per token, 94.93 tokens per second) 2.01.447.985 I slot print_timing: id 0 | task 8689 | total time = 1610.00 ms / 474 tokens 2.01.447.986 I slot print_timing: id 0 | task 8689 | graphs reused = 8189 2.01.447.987 I slot print_timing: id 0 | task 8689 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.448.016 I slot release: id 0 | task 8689 | stop processing: n_tokens = 505, truncated = 0 2.01.474.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 121356253 2.01.474.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 2.01.546.634 I slot launch_slot_: id 0 | task 8832 | processing task, is_child = 0 2.03.544.987 I slot print_timing: id 0 | task 8832 | prompt eval time = 159.04 ms / 426 tokens ( 0.37 ms per token, 2678.61 tokens per second) 2.03.544.996 I slot print_timing: id 0 | task 8832 | eval time = 1839.29 ms / 175 tokens ( 10.57 ms per token, 94.60 tokens per second) 2.03.544.997 I slot print_timing: id 0 | task 8832 | total time = 1998.33 ms / 601 tokens 2.03.544.998 I slot print_timing: id 0 | task 8832 | graphs reused = 8361 2.03.544.999 I slot print_timing: id 0 | task 8832 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.545.031 I slot release: id 0 | task 8832 | stop processing: n_tokens = 632, truncated = 0 2.03.561.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 123453269 2.03.561.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.03.634.341 I slot launch_slot_: id 0 | task 9010 | processing task, is_child = 0 2.05.008.171 I slot print_timing: id 0 | task 9010 | prompt eval time = 147.45 ms / 366 tokens ( 0.40 ms per token, 2482.18 tokens per second) 2.05.008.177 I slot print_timing: id 0 | task 9010 | eval time = 1226.36 ms / 117 tokens ( 10.57 ms per token, 94.59 tokens per second) 2.05.008.178 I slot print_timing: id 0 | task 9010 | total time = 1373.81 ms / 483 tokens 2.05.008.178 I slot print_timing: id 0 | task 9010 | graphs reused = 8475 2.05.008.180 I slot print_timing: id 0 | task 9010 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.008.209 I slot release: id 0 | task 9010 | stop processing: n_tokens = 514, truncated = 0 2.05.028.009 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 124916447 2.05.028.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.05.101.031 I slot launch_slot_: id 0 | task 9130 | processing task, is_child = 0 2.08.025.136 I slot print_timing: id 0 | task 9130 | prompt eval time = 166.18 ms / 462 tokens ( 0.36 ms per token, 2780.13 tokens per second) 2.08.025.142 I slot print_timing: id 0 | task 9130 | eval time = 2757.91 ms / 263 tokens ( 10.53 ms per token, 95.00 tokens per second) 2.08.025.143 I slot print_timing: id 0 | task 9130 | total time = 2924.09 ms / 725 tokens 2.08.025.145 I slot print_timing: id 0 | task 9130 | graphs reused = 8735 2.08.025.146 I slot print_timing: id 0 | task 9130 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.025.178 I slot release: id 0 | task 9130 | stop processing: n_tokens = 756, truncated = 0 2.08.039.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 127933416 2.08.039.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.08.111.640 I slot launch_slot_: id 0 | task 9396 | processing task, is_child = 0 2.09.720.362 I slot print_timing: id 0 | task 9396 | prompt eval time = 152.99 ms / 396 tokens ( 0.39 ms per token, 2588.46 tokens per second) 2.09.720.367 I slot print_timing: id 0 | task 9396 | eval time = 1455.72 ms / 139 tokens ( 10.55 ms per token, 94.80 tokens per second) 2.09.720.368 I slot print_timing: id 0 | task 9396 | total time = 1608.70 ms / 535 tokens 2.09.720.369 I slot print_timing: id 0 | task 9396 | graphs reused = 8871 2.09.720.369 I slot print_timing: id 0 | task 9396 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.720.400 I slot release: id 0 | task 9396 | stop processing: n_tokens = 566, truncated = 0 2.09.742.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 129628638 2.09.801.564 I slot launch_slot_: id 0 | task 9538 | processing task, is_child = 0 2.11.661.608 I slot print_timing: id 0 | task 9538 | prompt eval time = 166.19 ms / 458 tokens ( 0.36 ms per token, 2755.88 tokens per second) 2.11.661.613 I slot print_timing: id 0 | task 9538 | eval time = 1693.83 ms / 161 tokens ( 10.59 ms per token, 94.46 tokens per second) 2.11.661.614 I slot print_timing: id 0 | task 9538 | total time = 1860.02 ms / 619 tokens 2.11.661.615 I slot print_timing: id 0 | task 9538 | graphs reused = 9029 2.11.661.616 I slot print_timing: id 0 | task 9538 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.661.649 I slot release: id 0 | task 9538 | stop processing: n_tokens = 650, truncated = 0 2.11.680.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 131569887 2.11.681.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.11.766.750 I slot launch_slot_: id 0 | task 9702 | processing task, is_child = 0 2.13.663.387 I slot print_timing: id 0 | task 9702 | prompt eval time = 166.94 ms / 458 tokens ( 0.36 ms per token, 2743.58 tokens per second) 2.13.663.393 I slot print_timing: id 0 | task 9702 | eval time = 1729.68 ms / 165 tokens ( 10.55 ms per token, 94.82 tokens per second) 2.13.663.394 I slot print_timing: id 0 | task 9702 | total time = 1896.62 ms / 623 tokens 2.13.663.395 I slot print_timing: id 0 | task 9702 | graphs reused = 9191 2.13.663.395 I slot print_timing: id 0 | task 9702 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.663.429 I slot release: id 0 | task 9702 | stop processing: n_tokens = 654, truncated = 0 2.13.690.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 654, t_last = 133571666 2.13.690.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.13.758.129 I slot launch_slot_: id 0 | task 9870 | processing task, is_child = 0 2.16.126.366 I slot print_timing: id 0 | task 9870 | prompt eval time = 163.18 ms / 452 tokens ( 0.36 ms per token, 2770.03 tokens per second) 2.16.126.372 I slot print_timing: id 0 | task 9870 | eval time = 2205.04 ms / 210 tokens ( 10.55 ms per token, 94.78 tokens per second) 2.16.126.373 I slot print_timing: id 0 | task 9870 | total time = 2368.22 ms / 662 tokens 2.16.126.375 I slot print_timing: id 0 | task 9870 | graphs reused = 9398 2.16.126.376 I slot print_timing: id 0 | task 9870 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.126.409 I slot release: id 0 | task 9870 | stop processing: n_tokens = 693, truncated = 0 2.16.143.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 136034647 2.16.143.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.16.216.503 I slot launch_slot_: id 0 | task 10083 | processing task, is_child = 0 2.17.633.505 I slot print_timing: id 0 | task 10083 | prompt eval time = 157.37 ms / 404 tokens ( 0.39 ms per token, 2567.28 tokens per second) 2.17.633.511 I slot print_timing: id 0 | task 10083 | eval time = 1259.62 ms / 120 tokens ( 10.59 ms per token, 94.47 tokens per second) 2.17.633.512 I slot print_timing: id 0 | task 10083 | total time = 1416.98 ms / 524 tokens 2.17.633.513 I slot print_timing: id 0 | task 10083 | graphs reused = 9515 2.17.633.514 I slot print_timing: id 0 | task 10083 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.633.546 I slot release: id 0 | task 10083 | stop processing: n_tokens = 555, truncated = 0 2.17.649.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 137541783 2.17.649.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.17.739.507 I slot launch_slot_: id 0 | task 10206 | processing task, is_child = 0 2.19.001.957 I slot print_timing: id 0 | task 10206 | prompt eval time = 154.84 ms / 345 tokens ( 0.45 ms per token, 2228.05 tokens per second) 2.19.001.962 I slot print_timing: id 0 | task 10206 | eval time = 1107.59 ms / 106 tokens ( 10.55 ms per token, 94.80 tokens per second) 2.19.001.963 I slot print_timing: id 0 | task 10206 | total time = 1262.43 ms / 451 tokens 2.19.001.965 I slot print_timing: id 0 | task 10206 | graphs reused = 9619 2.19.001.965 I slot print_timing: id 0 | task 10206 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.001.994 I slot release: id 0 | task 10206 | stop processing: n_tokens = 482, truncated = 0 2.19.021.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 138910231 2.19.021.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.19.083.068 I slot launch_slot_: id 0 | task 10315 | processing task, is_child = 0 2.20.358.470 I slot print_timing: id 0 | task 10315 | prompt eval time = 167.41 ms / 430 tokens ( 0.39 ms per token, 2568.59 tokens per second) 2.20.358.477 I slot print_timing: id 0 | task 10315 | eval time = 1107.97 ms / 105 tokens ( 10.65 ms per token, 93.87 tokens per second) 2.20.358.478 I slot print_timing: id 0 | task 10315 | total time = 1275.38 ms / 535 tokens 2.20.358.479 I slot print_timing: id 0 | task 10315 | graphs reused = 9721 2.20.358.479 I slot print_timing: id 0 | task 10315 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.358.514 I slot release: id 0 | task 10315 | stop processing: n_tokens = 566, truncated = 0 2.20.375.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 140266752 2.20.375.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.20.431.100 I slot launch_slot_: id 0 | task 10423 | processing task, is_child = 0 2.21.490.568 I slot print_timing: id 0 | task 10423 | prompt eval time = 141.88 ms / 316 tokens ( 0.45 ms per token, 2227.31 tokens per second) 2.21.490.573 I slot print_timing: id 0 | task 10423 | eval time = 917.57 ms / 85 tokens ( 10.92 ms per token, 91.55 tokens per second) 2.21.490.574 I slot print_timing: id 0 | task 10423 | total time = 1059.45 ms / 401 tokens 2.21.490.575 I slot print_timing: id 0 | task 10423 | graphs reused = 9804 2.21.490.576 I slot print_timing: id 0 | task 10423 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.490.603 I slot release: id 0 | task 10423 | stop processing: n_tokens = 432, truncated = 0 2.21.512.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 141398840 2.21.512.084 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.21.608.955 I slot launch_slot_: id 0 | task 10511 | processing task, is_child = 0 2.22.877.336 I slot print_timing: id 0 | task 10511 | prompt eval time = 148.83 ms / 354 tokens ( 0.42 ms per token, 2378.54 tokens per second) 2.22.877.342 I slot print_timing: id 0 | task 10511 | eval time = 1119.53 ms / 107 tokens ( 10.56 ms per token, 94.68 tokens per second) 2.22.877.344 I slot print_timing: id 0 | task 10511 | total time = 1268.36 ms / 461 tokens 2.22.877.344 I slot print_timing: id 0 | task 10511 | graphs reused = 9909 2.22.877.345 I slot print_timing: id 0 | task 10511 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.877.374 I slot release: id 0 | task 10511 | stop processing: n_tokens = 492, truncated = 0 2.22.893.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 142785611 2.22.893.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.22.987.337 I slot launch_slot_: id 0 | task 10621 | processing task, is_child = 0 2.24.183.967 I slot print_timing: id 0 | task 10621 | prompt eval time = 168.08 ms / 438 tokens ( 0.38 ms per token, 2605.93 tokens per second) 2.24.183.973 I slot print_timing: id 0 | task 10621 | eval time = 1028.53 ms / 98 tokens ( 10.60 ms per token, 94.31 tokens per second) 2.24.183.974 I slot print_timing: id 0 | task 10621 | total time = 1196.61 ms / 536 tokens 2.24.183.975 I slot print_timing: id 0 | task 10621 | graphs reused = 10004 2.24.183.976 I slot print_timing: id 0 | task 10621 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.184.007 I slot release: id 0 | task 10621 | stop processing: n_tokens = 567, truncated = 0 2.24.205.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 144092245 2.24.205.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.24.297.201 I slot launch_slot_: id 0 | task 10722 | processing task, is_child = 0 2.25.199.182 I slot print_timing: id 0 | task 10722 | prompt eval time = 169.62 ms / 457 tokens ( 0.37 ms per token, 2694.19 tokens per second) 2.25.199.187 I slot print_timing: id 0 | task 10722 | eval time = 732.34 ms / 70 tokens ( 10.61 ms per token, 94.22 tokens per second) 2.25.199.189 I slot print_timing: id 0 | task 10722 | total time = 901.96 ms / 527 tokens 2.25.199.190 I slot print_timing: id 0 | task 10722 | graphs reused = 10071 2.25.199.191 I slot print_timing: id 0 | task 10722 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.199.223 I slot release: id 0 | task 10722 | stop processing: n_tokens = 558, truncated = 0 2.25.219.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 145107460 2.25.219.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.25.319.046 I slot launch_slot_: id 0 | task 10795 | processing task, is_child = 0 2.26.519.023 I slot print_timing: id 0 | task 10795 | prompt eval time = 174.72 ms / 473 tokens ( 0.37 ms per token, 2707.19 tokens per second) 2.26.519.029 I slot print_timing: id 0 | task 10795 | eval time = 1025.24 ms / 98 tokens ( 10.57 ms per token, 94.61 tokens per second) 2.26.519.030 I slot print_timing: id 0 | task 10795 | total time = 1199.96 ms / 571 tokens 2.26.519.031 I slot print_timing: id 0 | task 10795 | graphs reused = 10166 2.26.519.032 I slot print_timing: id 0 | task 10795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.519.063 I slot release: id 0 | task 10795 | stop processing: n_tokens = 602, truncated = 0 2.26.545.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 146427301 2.26.545.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.26.634.145 I slot launch_slot_: id 0 | task 10896 | processing task, is_child = 0 2.27.538.014 I slot print_timing: id 0 | task 10896 | prompt eval time = 170.87 ms / 476 tokens ( 0.36 ms per token, 2785.74 tokens per second) 2.27.538.019 I slot print_timing: id 0 | task 10896 | eval time = 732.98 ms / 70 tokens ( 10.62 ms per token, 94.14 tokens per second) 2.27.538.020 I slot print_timing: id 0 | task 10896 | total time = 903.85 ms / 546 tokens 2.27.538.021 I slot print_timing: id 0 | task 10896 | graphs reused = 10233 2.27.538.022 I slot print_timing: id 0 | task 10896 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.538.054 I slot release: id 0 | task 10896 | stop processing: n_tokens = 577, truncated = 0 2.27.559.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 147446292 2.27.559.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.27.651.785 I slot launch_slot_: id 0 | task 10969 | processing task, is_child = 0 2.28.947.338 I slot print_timing: id 0 | task 10969 | prompt eval time = 174.56 ms / 466 tokens ( 0.37 ms per token, 2669.58 tokens per second) 2.28.947.344 I slot print_timing: id 0 | task 10969 | eval time = 1120.97 ms / 107 tokens ( 10.58 ms per token, 94.56 tokens per second) 2.28.947.345 I slot print_timing: id 0 | task 10969 | total time = 1295.53 ms / 573 tokens 2.28.947.345 I slot print_timing: id 0 | task 10969 | graphs reused = 10337 2.28.947.346 I slot print_timing: id 0 | task 10969 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.947.376 I slot release: id 0 | task 10969 | stop processing: n_tokens = 604, truncated = 0 2.28.964.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 148855614 2.28.964.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.29.063.132 I slot launch_slot_: id 0 | task 11079 | processing task, is_child = 0 2.30.037.263 I slot print_timing: id 0 | task 11079 | prompt eval time = 155.51 ms / 415 tokens ( 0.37 ms per token, 2668.59 tokens per second) 2.30.037.269 I slot print_timing: id 0 | task 11079 | eval time = 818.60 ms / 78 tokens ( 10.63 ms per token, 94.06 tokens per second) 2.30.037.270 I slot print_timing: id 0 | task 11079 | total time = 974.11 ms / 493 tokens 2.30.037.271 I slot print_timing: id 0 | task 11079 | graphs reused = 10412 2.30.037.271 I slot print_timing: id 0 | task 11079 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.037.303 I slot release: id 0 | task 11079 | stop processing: n_tokens = 524, truncated = 0 2.30.055.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 149945541 2.30.056.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.30.147.281 I slot launch_slot_: id 0 | task 11160 | processing task, is_child = 0 2.30.958.745 I slot print_timing: id 0 | task 11160 | prompt eval time = 146.82 ms / 352 tokens ( 0.42 ms per token, 2397.43 tokens per second) 2.30.958.751 I slot print_timing: id 0 | task 11160 | eval time = 664.62 ms / 64 tokens ( 10.55 ms per token, 94.79 tokens per second) 2.30.958.752 I slot print_timing: id 0 | task 11160 | total time = 811.44 ms / 416 tokens 2.30.958.753 I slot print_timing: id 0 | task 11160 | graphs reused = 10474 2.30.958.754 I slot print_timing: id 0 | task 11160 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.958.781 I slot release: id 0 | task 11160 | stop processing: n_tokens = 447, truncated = 0 2.30.974.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 150867019 2.30.974.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.31.066.102 I slot launch_slot_: id 0 | task 11227 | processing task, is_child = 0 2.32.644.930 I slot print_timing: id 0 | task 11227 | prompt eval time = 188.97 ms / 550 tokens ( 0.34 ms per token, 2910.44 tokens per second) 2.32.644.935 I slot print_timing: id 0 | task 11227 | eval time = 1389.83 ms / 133 tokens ( 10.53 ms per token, 94.98 tokens per second) 2.32.644.936 I slot print_timing: id 0 | task 11227 | total time = 1578.81 ms / 683 tokens 2.32.644.937 I slot print_timing: id 0 | task 11227 | graphs reused = 10605 2.32.644.938 I slot print_timing: id 0 | task 11227 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.644.973 I slot release: id 0 | task 11227 | stop processing: n_tokens = 714, truncated = 0 2.32.669.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 152553210 2.32.669.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.32.781.227 I slot launch_slot_: id 0 | task 11364 | processing task, is_child = 0 2.35.380.297 I slot print_timing: id 0 | task 11364 | prompt eval time = 226.38 ms / 772 tokens ( 0.29 ms per token, 3410.18 tokens per second) 2.35.380.303 I slot print_timing: id 0 | task 11364 | eval time = 2372.67 ms / 226 tokens ( 10.55 ms per token, 94.83 tokens per second) 2.35.380.304 I slot print_timing: id 0 | task 11364 | total time = 2599.05 ms / 998 tokens 2.35.380.305 I slot print_timing: id 0 | task 11364 | graphs reused = 10828 2.35.380.306 I slot print_timing: id 0 | task 11364 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.380.345 I slot release: id 0 | task 11364 | stop processing: n_tokens = 1029, truncated = 0 2.35.409.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 155288582 2.35.409.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.35.516.477 I slot launch_slot_: id 0 | task 11594 | processing task, is_child = 0 2.37.639.430 I slot print_timing: id 0 | task 11594 | prompt eval time = 222.07 ms / 683 tokens ( 0.33 ms per token, 3075.55 tokens per second) 2.37.639.435 I slot print_timing: id 0 | task 11594 | eval time = 1900.86 ms / 181 tokens ( 10.56 ms per token, 94.69 tokens per second) 2.37.639.436 I slot print_timing: id 0 | task 11594 | total time = 2122.93 ms / 864 tokens 2.37.639.437 I slot print_timing: id 0 | task 11594 | graphs reused = 11006 2.37.639.438 I slot print_timing: id 0 | task 11594 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.639.476 I slot release: id 0 | task 11594 | stop processing: n_tokens = 895, truncated = 0 2.37.668.710 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 157547714 2.37.668.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.37.784.914 I slot launch_slot_: id 0 | task 11779 | processing task, is_child = 0 2.40.276.982 I slot print_timing: id 0 | task 11779 | prompt eval time = 198.60 ms / 579 tokens ( 0.34 ms per token, 2915.47 tokens per second) 2.40.276.987 I slot print_timing: id 0 | task 11779 | eval time = 2293.45 ms / 218 tokens ( 10.57 ms per token, 94.62 tokens per second) 2.40.276.988 I slot print_timing: id 0 | task 11779 | total time = 2492.05 ms / 797 tokens 2.40.276.989 I slot print_timing: id 0 | task 11779 | graphs reused = 11221 2.40.276.990 I slot print_timing: id 0 | task 11779 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.277.026 I slot release: id 0 | task 11779 | stop processing: n_tokens = 828, truncated = 0 2.40.281.551 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 160185263 2.40.281.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.40.302.913 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.40.387.649 I slot launch_slot_: id 0 | task 12001 | processing task, is_child = 0 2.41.680.281 I slot print_timing: id 0 | task 12001 | prompt eval time = 181.02 ms / 500 tokens ( 0.36 ms per token, 2762.14 tokens per second) 2.41.680.287 I slot print_timing: id 0 | task 12001 | eval time = 1111.59 ms / 106 tokens ( 10.59 ms per token, 94.46 tokens per second) 2.41.680.288 I slot print_timing: id 0 | task 12001 | total time = 1292.61 ms / 606 tokens 2.41.680.288 I slot print_timing: id 0 | task 12001 | graphs reused = 11325 2.41.680.289 I slot print_timing: id 0 | task 12001 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.680.322 I slot release: id 0 | task 12001 | stop processing: n_tokens = 637, truncated = 0 2.41.698.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 161588560 2.41.698.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.41.777.807 I slot launch_slot_: id 0 | task 12110 | processing task, is_child = 0 2.44.212.232 I slot print_timing: id 0 | task 12110 | prompt eval time = 231.94 ms / 776 tokens ( 0.30 ms per token, 3345.76 tokens per second) 2.44.212.238 I slot print_timing: id 0 | task 12110 | eval time = 2202.47 ms / 209 tokens ( 10.59 ms per token, 94.44 tokens per second) 2.44.212.239 I slot print_timing: id 0 | task 12110 | total time = 2434.40 ms / 985 tokens 2.44.212.239 I slot print_timing: id 0 | task 12110 | graphs reused = 11532 2.44.212.240 I slot print_timing: id 0 | task 12110 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.212.280 I slot release: id 0 | task 12110 | stop processing: n_tokens = 1016, truncated = 0 2.44.239.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 164120518 2.44.239.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.44.315.510 I slot launch_slot_: id 0 | task 12323 | processing task, is_child = 0 2.46.557.139 I slot print_timing: id 0 | task 12323 | prompt eval time = 177.70 ms / 504 tokens ( 0.35 ms per token, 2836.26 tokens per second) 2.46.557.145 I slot print_timing: id 0 | task 12323 | eval time = 2063.91 ms / 197 tokens ( 10.53 ms per token, 94.97 tokens per second) 2.46.557.146 I slot print_timing: id 0 | task 12323 | total time = 2241.61 ms / 701 tokens 2.46.557.147 I slot print_timing: id 0 | task 12323 | graphs reused = 11727 2.46.557.148 I slot print_timing: id 0 | task 12323 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.557.183 I slot release: id 0 | task 12323 | stop processing: n_tokens = 732, truncated = 0 2.46.573.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 166465421 2.46.573.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.46.657.866 I slot launch_slot_: id 0 | task 12523 | processing task, is_child = 0 2.49.049.438 I slot print_timing: id 0 | task 12523 | prompt eval time = 210.73 ms / 633 tokens ( 0.33 ms per token, 3003.87 tokens per second) 2.49.049.443 I slot print_timing: id 0 | task 12523 | eval time = 2180.82 ms / 207 tokens ( 10.59 ms per token, 94.46 tokens per second) 2.49.049.445 I slot print_timing: id 0 | task 12523 | total time = 2391.55 ms / 840 tokens 2.49.049.446 I slot print_timing: id 0 | task 12523 | graphs reused = 11931 2.49.049.446 I slot print_timing: id 0 | task 12523 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.049.483 I slot release: id 0 | task 12523 | stop processing: n_tokens = 871, truncated = 0 2.49.071.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 168957720 2.49.071.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 2.49.145.225 I slot launch_slot_: id 0 | task 12734 | processing task, is_child = 0 2.50.705.644 I slot print_timing: id 0 | task 12734 | prompt eval time = 158.42 ms / 395 tokens ( 0.40 ms per token, 2493.36 tokens per second) 2.50.705.650 I slot print_timing: id 0 | task 12734 | eval time = 1401.98 ms / 134 tokens ( 10.54 ms per token, 94.87 tokens per second) 2.50.705.651 I slot print_timing: id 0 | task 12734 | total time = 1560.40 ms / 529 tokens 2.50.705.652 I slot print_timing: id 0 | task 12734 | graphs reused = 12062 2.50.705.653 I slot print_timing: id 0 | task 12734 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.705.682 I slot release: id 0 | task 12734 | stop processing: n_tokens = 560, truncated = 0 2.50.730.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 170613920 2.50.730.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.50.821.700 I slot launch_slot_: id 0 | task 12871 | processing task, is_child = 0 2.53.220.975 I slot print_timing: id 0 | task 12871 | prompt eval time = 194.40 ms / 584 tokens ( 0.33 ms per token, 3004.10 tokens per second) 2.53.220.981 I slot print_timing: id 0 | task 12871 | eval time = 2204.85 ms / 209 tokens ( 10.60 ms per token, 94.34 tokens per second) 2.53.220.982 I slot print_timing: id 0 | task 12871 | total time = 2399.25 ms / 793 tokens 2.53.220.983 I slot print_timing: id 0 | task 12871 | graphs reused = 12268 2.53.220.984 I slot print_timing: id 0 | task 12871 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.221.019 I slot release: id 0 | task 12871 | stop processing: n_tokens = 824, truncated = 0 2.53.238.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 173129257 2.53.238.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.53.316.988 I slot launch_slot_: id 0 | task 13084 | processing task, is_child = 0 2.55.967.839 I slot print_timing: id 0 | task 13084 | prompt eval time = 220.03 ms / 695 tokens ( 0.32 ms per token, 3158.67 tokens per second) 2.55.967.845 I slot print_timing: id 0 | task 13084 | eval time = 2430.80 ms / 230 tokens ( 10.61 ms per token, 94.21 tokens per second) 2.55.967.846 I slot print_timing: id 0 | task 13084 | total time = 2650.83 ms / 925 tokens 2.55.967.847 I slot print_timing: id 0 | task 13084 | graphs reused = 12495 2.55.967.848 I slot print_timing: id 0 | task 13084 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.967.886 I slot release: id 0 | task 13084 | stop processing: n_tokens = 956, truncated = 0 2.55.994.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 175876124 2.55.994.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.956 MiB) 2.56.073.816 I slot launch_slot_: id 0 | task 13318 | processing task, is_child = 0 2.58.314.917 I slot print_timing: id 0 | task 13318 | prompt eval time = 233.52 ms / 769 tokens ( 0.30 ms per token, 3293.02 tokens per second) 2.58.314.923 I slot print_timing: id 0 | task 13318 | eval time = 2007.56 ms / 191 tokens ( 10.57 ms per token, 94.64 tokens per second) 2.58.314.924 I slot print_timing: id 0 | task 13318 | total time = 2241.08 ms / 960 tokens 2.58.314.925 I slot print_timing: id 0 | task 13318 | graphs reused = 12684 2.58.314.925 I slot print_timing: id 0 | task 13318 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.314.966 I slot release: id 0 | task 13318 | stop processing: n_tokens = 991, truncated = 0 2.58.331.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 178223204 2.58.331.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.58.349.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 2.58.448.899 I slot launch_slot_: id 0 | task 13513 | processing task, is_child = 0 2.59.935.759 I slot print_timing: id 0 | task 13513 | prompt eval time = 193.02 ms / 576 tokens ( 0.34 ms per token, 2984.15 tokens per second) 2.59.935.765 I slot print_timing: id 0 | task 13513 | eval time = 1293.82 ms / 124 tokens ( 10.52 ms per token, 95.07 tokens per second) 2.59.935.766 I slot print_timing: id 0 | task 13513 | total time = 1486.84 ms / 700 tokens 2.59.935.767 I slot print_timing: id 0 | task 13513 | graphs reused = 12806 2.59.935.768 I slot print_timing: id 0 | task 13513 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.935.807 I slot release: id 0 | task 13513 | stop processing: n_tokens = 731, truncated = 0 2.59.961.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 179844045 2.59.961.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 3.00.034.001 I slot launch_slot_: id 0 | task 13641 | processing task, is_child = 0 3.03.135.438 I slot print_timing: id 0 | task 13641 | prompt eval time = 213.55 ms / 655 tokens ( 0.33 ms per token, 3067.18 tokens per second) 3.03.135.444 I slot print_timing: id 0 | task 13641 | eval time = 2887.86 ms / 275 tokens ( 10.54 ms per token, 94.88 tokens per second) 3.03.135.446 I slot print_timing: id 0 | task 13641 | total time = 3101.42 ms / 930 tokens 3.03.135.447 I slot print_timing: id 0 | task 13641 | graphs reused = 13078 3.03.135.448 I slot print_timing: id 0 | task 13641 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.135.504 I slot release: id 0 | task 13641 | stop processing: n_tokens = 961, truncated = 0 3.03.153.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 183043742 3.03.153.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.03.218.180 I slot launch_slot_: id 0 | task 13920 | processing task, is_child = 0 3.04.696.360 I slot print_timing: id 0 | task 13920 | prompt eval time = 204.52 ms / 621 tokens ( 0.33 ms per token, 3036.42 tokens per second) 3.04.696.365 I slot print_timing: id 0 | task 13920 | eval time = 1273.64 ms / 121 tokens ( 10.61 ms per token, 94.22 tokens per second) 3.04.696.366 I slot print_timing: id 0 | task 13920 | total time = 1478.16 ms / 742 tokens 3.04.696.367 I slot print_timing: id 0 | task 13920 | graphs reused = 13196 3.04.696.368 I slot print_timing: id 0 | task 13920 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.696.404 I slot release: id 0 | task 13920 | stop processing: n_tokens = 773, truncated = 0 3.04.713.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 184604642 3.04.713.116 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 3.04.820.790 I slot launch_slot_: id 0 | task 14045 | processing task, is_child = 0 3.06.947.262 I slot print_timing: id 0 | task 14045 | prompt eval time = 226.94 ms / 767 tokens ( 0.30 ms per token, 3379.72 tokens per second) 3.06.947.268 I slot print_timing: id 0 | task 14045 | eval time = 1899.51 ms / 178 tokens ( 10.73 ms per token, 93.18 tokens per second) 3.06.947.269 I slot print_timing: id 0 | task 14045 | total time = 2126.45 ms / 945 tokens 3.06.947.270 I slot print_timing: id 0 | task 14045 | graphs reused = 13372 3.06.947.270 I slot print_timing: id 0 | task 14045 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.947.312 I slot release: id 0 | task 14045 | stop processing: n_tokens = 976, truncated = 0 3.06.977.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 186855550 3.06.977.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 3.07.095.867 I slot launch_slot_: id 0 | task 14227 | processing task, is_child = 0 3.09.515.644 I slot print_timing: id 0 | task 14227 | prompt eval time = 253.17 ms / 864 tokens ( 0.29 ms per token, 3412.69 tokens per second) 3.09.515.649 I slot print_timing: id 0 | task 14227 | eval time = 2166.59 ms / 203 tokens ( 10.73 ms per token, 93.23 tokens per second) 3.09.515.650 I slot print_timing: id 0 | task 14227 | total time = 2419.76 ms / 1067 tokens 3.09.515.651 I slot print_timing: id 0 | task 14227 | graphs reused = 13572 3.09.515.652 I slot print_timing: id 0 | task 14227 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.515.697 I slot release: id 0 | task 14227 | stop processing: n_tokens = 1098, truncated = 0 3.09.544.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 189423934 3.09.544.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.09.562.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.09.668.501 I slot launch_slot_: id 0 | task 14434 | processing task, is_child = 0 3.11.236.348 I slot print_timing: id 0 | task 14434 | prompt eval time = 216.08 ms / 646 tokens ( 0.33 ms per token, 2989.58 tokens per second) 3.11.236.353 I slot print_timing: id 0 | task 14434 | eval time = 1351.74 ms / 129 tokens ( 10.56 ms per token, 94.69 tokens per second) 3.11.236.355 I slot print_timing: id 0 | task 14434 | total time = 1567.83 ms / 775 tokens 3.11.236.355 I slot print_timing: id 0 | task 14434 | graphs reused = 13698 3.11.236.356 I slot print_timing: id 0 | task 14434 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.236.396 I slot release: id 0 | task 14434 | stop processing: n_tokens = 806, truncated = 0 3.11.251.266 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 191144633 3.11.251.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.11.344.319 I slot launch_slot_: id 0 | task 14567 | processing task, is_child = 0 3.13.951.865 I slot print_timing: id 0 | task 14567 | prompt eval time = 221.03 ms / 720 tokens ( 0.31 ms per token, 3257.45 tokens per second) 3.13.951.870 I slot print_timing: id 0 | task 14567 | eval time = 2386.49 ms / 219 tokens ( 10.95 ms per token, 91.35 tokens per second) 3.13.951.871 I slot print_timing: id 0 | task 14567 | total time = 2607.53 ms / 939 tokens 3.13.951.872 I slot print_timing: id 0 | task 14567 | graphs reused = 13914 3.13.951.872 I slot print_timing: id 0 | task 14567 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.951.913 I slot release: id 0 | task 14567 | stop processing: n_tokens = 970, truncated = 0 3.13.977.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 193860150 3.13.977.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.548 MiB) 3.14.090.578 I slot launch_slot_: id 0 | task 14790 | processing task, is_child = 0 3.16.525.098 I slot print_timing: id 0 | task 14790 | prompt eval time = 182.26 ms / 509 tokens ( 0.36 ms per token, 2792.73 tokens per second) 3.16.525.104 I slot print_timing: id 0 | task 14790 | eval time = 2252.24 ms / 214 tokens ( 10.57 ms per token, 94.57 tokens per second) 3.16.525.105 I slot print_timing: id 0 | task 14790 | total time = 2434.50 ms / 723 tokens 3.16.525.106 I slot print_timing: id 0 | task 14790 | graphs reused = 14126 3.16.525.106 I slot print_timing: id 0 | task 14790 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.525.140 I slot release: id 0 | task 14790 | stop processing: n_tokens = 754, truncated = 0 3.16.529.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 196433378 3.16.529.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 3.16.622.756 I slot launch_slot_: id 0 | task 15007 | processing task, is_child = 0 3.19.364.104 I slot print_timing: id 0 | task 15007 | prompt eval time = 197.02 ms / 581 tokens ( 0.34 ms per token, 2948.98 tokens per second) 3.19.364.110 I slot print_timing: id 0 | task 15007 | eval time = 2544.31 ms / 242 tokens ( 10.56 ms per token, 94.72 tokens per second) 3.19.364.111 I slot print_timing: id 0 | task 15007 | total time = 2741.33 ms / 823 tokens 3.19.364.111 I slot print_timing: id 0 | task 15007 | graphs reused = 14365 3.19.364.112 I slot print_timing: id 0 | task 15007 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.364.149 I slot release: id 0 | task 15007 | stop processing: n_tokens = 854, truncated = 0 3.19.384.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 199272387 3.19.384.857 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.19.494.188 I slot launch_slot_: id 0 | task 15253 | processing task, is_child = 0 3.22.078.831 I slot print_timing: id 0 | task 15253 | prompt eval time = 266.49 ms / 925 tokens ( 0.29 ms per token, 3471.00 tokens per second) 3.22.078.837 I slot print_timing: id 0 | task 15253 | eval time = 2318.13 ms / 220 tokens ( 10.59 ms per token, 94.47 tokens per second) 3.22.078.838 I slot print_timing: id 0 | task 15253 | total time = 2584.62 ms / 1145 tokens 3.22.078.839 I slot print_timing: id 0 | task 15253 | graphs reused = 14582 3.22.078.839 I slot print_timing: id 0 | task 15253 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.078.887 I slot release: id 0 | task 15253 | stop processing: n_tokens = 1176, truncated = 0 3.22.103.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 201987124 3.22.103.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.22.212.115 I slot launch_slot_: id 0 | task 15477 | processing task, is_child = 0 3.25.079.541 I slot print_timing: id 0 | task 15477 | prompt eval time = 251.07 ms / 885 tokens ( 0.28 ms per token, 3524.89 tokens per second) 3.25.079.547 I slot print_timing: id 0 | task 15477 | eval time = 2616.34 ms / 245 tokens ( 10.72 ms per token, 93.26 tokens per second) 3.25.079.548 I slot print_timing: id 0 | task 15477 | total time = 2867.41 ms / 1130 tokens 3.25.079.549 I slot print_timing: id 0 | task 15477 | graphs reused = 14824 3.25.079.550 I slot print_timing: id 0 | task 15477 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.079.595 I slot release: id 0 | task 15477 | stop processing: n_tokens = 1161, truncated = 0 3.25.102.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 204987833 3.25.102.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.25.213.346 I slot launch_slot_: id 0 | task 15726 | processing task, is_child = 0 3.26.091.376 I slot print_timing: id 0 | task 15726 | prompt eval time = 151.91 ms / 392 tokens ( 0.39 ms per token, 2580.46 tokens per second) 3.26.091.382 I slot print_timing: id 0 | task 15726 | eval time = 726.10 ms / 70 tokens ( 10.52 ms per token, 95.03 tokens per second) 3.26.091.383 I slot print_timing: id 0 | task 15726 | total time = 878.01 ms / 462 tokens 3.26.091.384 I slot print_timing: id 0 | task 15726 | graphs reused = 14892 3.26.091.385 I slot print_timing: id 0 | task 15726 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.091.417 I slot release: id 0 | task 15726 | stop processing: n_tokens = 493, truncated = 0 3.26.109.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 205999654 3.26.109.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.26.205.830 I slot launch_slot_: id 0 | task 15799 | processing task, is_child = 0 3.27.710.053 I slot print_timing: id 0 | task 15799 | prompt eval time = 147.55 ms / 331 tokens ( 0.45 ms per token, 2243.35 tokens per second) 3.27.710.060 I slot print_timing: id 0 | task 15799 | eval time = 1356.66 ms / 129 tokens ( 10.60 ms per token, 94.35 tokens per second) 3.27.710.061 I slot print_timing: id 0 | task 15799 | total time = 1504.20 ms / 460 tokens 3.27.710.063 I slot print_timing: id 0 | task 15799 | graphs reused = 15019 3.27.710.064 I slot print_timing: id 0 | task 15799 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.710.096 I slot release: id 0 | task 15799 | stop processing: n_tokens = 491, truncated = 0 3.27.727.205 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 207618334 3.27.727.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.27.822.266 I slot launch_slot_: id 0 | task 15931 | processing task, is_child = 0 3.29.629.632 I slot print_timing: id 0 | task 15931 | prompt eval time = 144.05 ms / 357 tokens ( 0.40 ms per token, 2478.31 tokens per second) 3.29.629.637 I slot print_timing: id 0 | task 15931 | eval time = 1663.30 ms / 159 tokens ( 10.53 ms per token, 94.99 tokens per second) 3.29.629.639 I slot print_timing: id 0 | task 15931 | total time = 1807.35 ms / 516 tokens 3.29.629.640 I slot print_timing: id 0 | task 15931 | graphs reused = 15175 3.29.629.640 I slot print_timing: id 0 | task 15931 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.629.668 I slot release: id 0 | task 15931 | stop processing: n_tokens = 547, truncated = 0 3.29.644.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 209537906 3.29.645.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.29.715.676 I slot launch_slot_: id 0 | task 16093 | processing task, is_child = 0 3.30.401.664 I slot print_timing: id 0 | task 16093 | prompt eval time = 145.85 ms / 315 tokens ( 0.46 ms per token, 2159.69 tokens per second) 3.30.401.670 I slot print_timing: id 0 | task 16093 | eval time = 540.12 ms / 52 tokens ( 10.59 ms per token, 94.42 tokens per second) 3.30.401.671 I slot print_timing: id 0 | task 16093 | total time = 685.97 ms / 367 tokens 3.30.401.672 I slot print_timing: id 0 | task 16093 | graphs reused = 15225 3.30.401.672 I slot print_timing: id 0 | task 16093 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.401.701 I slot release: id 0 | task 16093 | stop processing: n_tokens = 398, truncated = 0 3.30.423.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 210309939 3.30.423.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.30.492.543 I slot launch_slot_: id 0 | task 16148 | processing task, is_child = 0 3.31.759.485 I slot print_timing: id 0 | task 16148 | prompt eval time = 145.45 ms / 378 tokens ( 0.38 ms per token, 2598.83 tokens per second) 3.31.759.490 I slot print_timing: id 0 | task 16148 | eval time = 1121.47 ms / 107 tokens ( 10.58 ms per token, 94.52 tokens per second) 3.31.759.491 I slot print_timing: id 0 | task 16148 | total time = 1266.92 ms / 485 tokens 3.31.759.492 I slot print_timing: id 0 | task 16148 | graphs reused = 15329 3.31.759.493 I slot print_timing: id 0 | task 16148 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.759.522 I slot release: id 0 | task 16148 | stop processing: n_tokens = 516, truncated = 0 3.31.773.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 516, t_last = 211667760 3.31.773.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.31.845.556 I slot launch_slot_: id 0 | task 16258 | processing task, is_child = 0 3.32.268.071 I slot print_timing: id 0 | task 16258 | prompt eval time = 134.33 ms / 295 tokens ( 0.46 ms per token, 2196.07 tokens per second) 3.32.268.077 I slot print_timing: id 0 | task 16258 | eval time = 288.17 ms / 28 tokens ( 10.67 ms per token, 93.70 tokens per second) 3.32.268.078 I slot print_timing: id 0 | task 16258 | total time = 422.50 ms / 323 tokens 3.32.268.079 I slot print_timing: id 0 | task 16258 | graphs reused = 15355 3.32.268.080 I slot print_timing: id 0 | task 16258 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.268.108 I slot release: id 0 | task 16258 | stop processing: n_tokens = 354, truncated = 0 3.32.290.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 212176345 3.32.291.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.32.357.284 I slot launch_slot_: id 0 | task 16289 | processing task, is_child = 0 3.33.120.622 I slot print_timing: id 0 | task 16289 | prompt eval time = 141.36 ms / 337 tokens ( 0.42 ms per token, 2384.00 tokens per second) 3.33.120.627 I slot print_timing: id 0 | task 16289 | eval time = 621.96 ms / 60 tokens ( 10.54 ms per token, 94.86 tokens per second) 3.33.120.629 I slot print_timing: id 0 | task 16289 | total time = 763.32 ms / 397 tokens 3.33.120.629 I slot print_timing: id 0 | task 16289 | graphs reused = 15413 3.33.120.630 I slot print_timing: id 0 | task 16289 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.120.659 I slot release: id 0 | task 16289 | stop processing: n_tokens = 428, truncated = 0 3.33.148.525 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 213028897 3.33.206.047 I slot launch_slot_: id 0 | task 16352 | processing task, is_child = 0 3.34.293.171 I slot print_timing: id 0 | task 16352 | prompt eval time = 140.71 ms / 325 tokens ( 0.43 ms per token, 2309.65 tokens per second) 3.34.293.177 I slot print_timing: id 0 | task 16352 | eval time = 946.39 ms / 91 tokens ( 10.52 ms per token, 95.10 tokens per second) 3.34.293.178 I slot print_timing: id 0 | task 16352 | total time = 1087.11 ms / 416 tokens 3.34.293.179 I slot print_timing: id 0 | task 16352 | graphs reused = 15502 3.34.293.180 I slot print_timing: id 0 | task 16352 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.293.209 I slot release: id 0 | task 16352 | stop processing: n_tokens = 447, truncated = 0 3.34.312.648 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.072 3.34.312.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.34.385.228 I slot launch_slot_: id 0 | task 16446 | processing task, is_child = 0 3.35.437.973 I slot print_timing: id 0 | task 16446 | prompt eval time = 127.81 ms / 264 tokens ( 0.48 ms per token, 2065.61 tokens per second) 3.35.437.978 I slot print_timing: id 0 | task 16446 | eval time = 924.92 ms / 89 tokens ( 10.51 ms per token, 95.14 tokens per second) 3.35.437.979 I slot print_timing: id 0 | task 16446 | total time = 1052.73 ms / 353 tokens 3.35.437.980 I slot print_timing: id 0 | task 16446 | graphs reused = 15589 3.35.437.981 I slot print_timing: id 0 | task 16446 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.438.006 I slot release: id 0 | task 16446 | stop processing: n_tokens = 384, truncated = 0 3.35.441.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 384, t_last = 215346244 3.35.441.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.35.527.633 I slot launch_slot_: id 0 | task 16538 | processing task, is_child = 0 3.36.071.750 I slot print_timing: id 0 | task 16538 | prompt eval time = 142.15 ms / 331 tokens ( 0.43 ms per token, 2328.61 tokens per second) 3.36.071.755 I slot print_timing: id 0 | task 16538 | eval time = 401.95 ms / 39 tokens ( 10.58 ms per token, 94.54 tokens per second) 3.36.071.757 I slot print_timing: id 0 | task 16538 | total time = 544.10 ms / 370 tokens 3.36.071.757 I slot print_timing: id 0 | task 16538 | graphs reused = 15626 3.36.071.758 I slot print_timing: id 0 | task 16538 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.071.789 I slot release: id 0 | task 16538 | stop processing: n_tokens = 401, truncated = 0 3.36.087.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 215980027 3.36.087.086 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.36.158.094 I slot launch_slot_: id 0 | task 16580 | processing task, is_child = 0 3.37.360.737 I slot print_timing: id 0 | task 16580 | prompt eval time = 141.12 ms / 333 tokens ( 0.42 ms per token, 2359.61 tokens per second) 3.37.360.742 I slot print_timing: id 0 | task 16580 | eval time = 1061.50 ms / 102 tokens ( 10.51 ms per token, 95.15 tokens per second) 3.37.360.743 I slot print_timing: id 0 | task 16580 | total time = 1202.62 ms / 435 tokens 3.37.360.744 I slot print_timing: id 0 | task 16580 | graphs reused = 15726 3.37.360.745 I slot print_timing: id 0 | task 16580 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.360.772 I slot release: id 0 | task 16580 | stop processing: n_tokens = 466, truncated = 0 3.37.378.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 217269009 3.37.378.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.37.447.916 I slot launch_slot_: id 0 | task 16685 | processing task, is_child = 0 3.38.141.437 I slot print_timing: id 0 | task 16685 | prompt eval time = 143.33 ms / 346 tokens ( 0.41 ms per token, 2413.98 tokens per second) 3.38.141.442 I slot print_timing: id 0 | task 16685 | eval time = 550.17 ms / 53 tokens ( 10.58 ms per token, 94.52 tokens per second) 3.38.141.443 I slot print_timing: id 0 | task 16685 | total time = 693.50 ms / 399 tokens 3.38.141.444 I slot print_timing: id 0 | task 16685 | graphs reused = 15777 3.38.141.444 I slot print_timing: id 0 | task 16685 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.141.473 I slot release: id 0 | task 16685 | stop processing: n_tokens = 430, truncated = 0 3.38.168.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 218049711 3.38.168.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.38.242.945 I slot launch_slot_: id 0 | task 16741 | processing task, is_child = 0 3.38.933.094 I slot print_timing: id 0 | task 16741 | prompt eval time = 139.32 ms / 325 tokens ( 0.43 ms per token, 2332.74 tokens per second) 3.38.933.099 I slot print_timing: id 0 | task 16741 | eval time = 550.81 ms / 53 tokens ( 10.59 ms per token, 94.41 tokens per second) 3.38.933.100 I slot print_timing: id 0 | task 16741 | total time = 690.13 ms / 378 tokens 3.38.933.101 I slot print_timing: id 0 | task 16741 | graphs reused = 15828 3.38.933.102 I slot print_timing: id 0 | task 16741 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.933.132 I slot release: id 0 | task 16741 | stop processing: n_tokens = 409, truncated = 0 3.38.949.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 218841370 3.38.949.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.39.015.245 I slot launch_slot_: id 0 | task 16797 | processing task, is_child = 0 3.41.997.647 I slot print_timing: id 0 | task 16797 | prompt eval time = 142.90 ms / 322 tokens ( 0.44 ms per token, 2253.34 tokens per second) 3.41.997.653 I slot print_timing: id 0 | task 16797 | eval time = 2839.48 ms / 271 tokens ( 10.52 ms per token, 95.09 tokens per second) 3.41.997.654 I slot print_timing: id 0 | task 16797 | total time = 2982.38 ms / 593 tokens 3.41.997.655 I slot print_timing: id 0 | task 16797 | graphs reused = 16096 3.41.997.655 I slot print_timing: id 0 | task 16797 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.997.683 I slot release: id 0 | task 16797 | stop processing: n_tokens = 624, truncated = 0 3.42.024.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 624, t_last = 221905921 3.42.082.779 I slot launch_slot_: id 0 | task 17071 | processing task, is_child = 0 3.45.227.594 I slot print_timing: id 0 | task 17071 | n_gen = 286, tg = 94.94 t/s, tg_3s = 95.27 t/s 3.45.983.137 I slot print_timing: id 0 | task 17071 | prompt eval time = 142.76 ms / 338 tokens ( 0.42 ms per token, 2367.54 tokens per second) 3.45.983.143 I slot print_timing: id 0 | task 17071 | eval time = 3757.57 ms / 358 tokens ( 10.53 ms per token, 95.01 tokens per second) 3.45.983.144 I slot print_timing: id 0 | task 17071 | total time = 3900.34 ms / 696 tokens 3.45.983.145 I slot print_timing: id 0 | task 17071 | graphs reused = 16451 3.45.983.145 I slot print_timing: id 0 | task 17071 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.983.174 I slot release: id 0 | task 17071 | stop processing: n_tokens = 727, truncated = 0 3.45.999.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 225891411 3.46.000.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.46.060.711 I slot launch_slot_: id 0 | task 17432 | processing task, is_child = 0 3.49.203.559 I slot print_timing: id 0 | task 17432 | n_gen = 286, tg = 94.96 t/s, tg_3s = 95.30 t/s 3.49.402.667 I slot print_timing: id 0 | task 17432 | prompt eval time = 141.71 ms / 347 tokens ( 0.41 ms per token, 2448.70 tokens per second) 3.49.402.673 I slot print_timing: id 0 | task 17432 | eval time = 3200.23 ms / 305 tokens ( 10.53 ms per token, 94.99 tokens per second) 3.49.402.675 I slot print_timing: id 0 | task 17432 | total time = 3341.93 ms / 652 tokens 3.49.402.676 I slot print_timing: id 0 | task 17432 | graphs reused = 16753 3.49.402.677 I slot print_timing: id 0 | task 17432 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.402.706 I slot release: id 0 | task 17432 | stop processing: n_tokens = 683, truncated = 0 3.49.422.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 229310944 3.49.422.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.49.518.149 I slot launch_slot_: id 0 | task 17740 | processing task, is_child = 0 3.50.501.515 I slot print_timing: id 0 | task 17740 | prompt eval time = 141.51 ms / 331 tokens ( 0.43 ms per token, 2339.02 tokens per second) 3.50.501.521 I slot print_timing: id 0 | task 17740 | eval time = 841.84 ms / 81 tokens ( 10.52 ms per token, 95.03 tokens per second) 3.50.501.522 I slot print_timing: id 0 | task 17740 | total time = 983.35 ms / 412 tokens 3.50.501.523 I slot print_timing: id 0 | task 17740 | graphs reused = 16832 3.50.501.523 I slot print_timing: id 0 | task 17740 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.501.552 I slot release: id 0 | task 17740 | stop processing: n_tokens = 443, truncated = 0 3.50.518.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 230409790 3.50.518.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 3.50.616.250 I slot launch_slot_: id 0 | task 17824 | processing task, is_child = 0 3.52.032.105 I slot print_timing: id 0 | task 17824 | prompt eval time = 143.06 ms / 345 tokens ( 0.41 ms per token, 2411.66 tokens per second) 3.52.032.110 I slot print_timing: id 0 | task 17824 | eval time = 1272.78 ms / 122 tokens ( 10.52 ms per token, 95.07 tokens per second) 3.52.032.111 I slot print_timing: id 0 | task 17824 | total time = 1415.84 ms / 467 tokens 3.52.032.112 I slot print_timing: id 0 | task 17824 | graphs reused = 16952 3.52.032.113 I slot print_timing: id 0 | task 17824 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.032.142 I slot release: id 0 | task 17824 | stop processing: n_tokens = 498, truncated = 0 3.52.051.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 231940379 3.52.051.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.52.141.044 I slot launch_slot_: id 0 | task 17949 | processing task, is_child = 0 3.52.809.210 I slot print_timing: id 0 | task 17949 | prompt eval time = 140.48 ms / 320 tokens ( 0.44 ms per token, 2277.89 tokens per second) 3.52.809.216 I slot print_timing: id 0 | task 17949 | eval time = 527.67 ms / 51 tokens ( 10.55 ms per token, 94.76 tokens per second) 3.52.809.217 I slot print_timing: id 0 | task 17949 | total time = 668.15 ms / 371 tokens 3.52.809.218 I slot print_timing: id 0 | task 17949 | graphs reused = 17001 3.52.809.219 I slot print_timing: id 0 | task 17949 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.809.246 I slot release: id 0 | task 17949 | stop processing: n_tokens = 402, truncated = 0 3.52.832.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 232717483 3.52.832.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.52.916.192 I slot launch_slot_: id 0 | task 18003 | processing task, is_child = 0 3.53.566.797 I slot print_timing: id 0 | task 18003 | prompt eval time = 134.50 ms / 297 tokens ( 0.45 ms per token, 2208.10 tokens per second) 3.53.566.803 I slot print_timing: id 0 | task 18003 | eval time = 516.08 ms / 47 tokens ( 11.22 ms per token, 89.13 tokens per second) 3.53.566.804 I slot print_timing: id 0 | task 18003 | total time = 650.59 ms / 344 tokens 3.53.566.806 I slot print_timing: id 0 | task 18003 | graphs reused = 17046 3.53.566.807 I slot print_timing: id 0 | task 18003 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.566.834 I slot release: id 0 | task 18003 | stop processing: n_tokens = 375, truncated = 0 3.53.570.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 233475072 3.53.643.264 I slot launch_slot_: id 0 | task 18053 | processing task, is_child = 0 3.56.640.691 I slot print_timing: id 0 | task 18053 | prompt eval time = 143.73 ms / 343 tokens ( 0.42 ms per token, 2386.39 tokens per second) 3.56.640.697 I slot print_timing: id 0 | task 18053 | eval time = 2853.68 ms / 272 tokens ( 10.53 ms per token, 94.97 tokens per second) 3.56.640.698 I slot print_timing: id 0 | task 18053 | total time = 2997.41 ms / 615 tokens 3.56.640.699 I slot print_timing: id 0 | task 18053 | graphs reused = 17315 3.56.640.700 I slot print_timing: id 0 | task 18053 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.640.731 I slot release: id 0 | task 18053 | stop processing: n_tokens = 646, truncated = 0 3.56.644.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 236548969 3.56.644.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.56.755.874 I slot launch_slot_: id 0 | task 18328 | processing task, is_child = 0 3.57.854.915 I slot print_timing: id 0 | task 18328 | prompt eval time = 158.18 ms / 371 tokens ( 0.43 ms per token, 2345.46 tokens per second) 3.57.854.923 I slot print_timing: id 0 | task 18328 | eval time = 940.84 ms / 89 tokens ( 10.69 ms per token, 93.53 tokens per second) 3.57.854.924 I slot print_timing: id 0 | task 18328 | total time = 1099.02 ms / 460 tokens 3.57.854.925 I slot print_timing: id 0 | task 18328 | graphs reused = 17402 3.57.854.926 I slot print_timing: id 0 | task 18328 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.854.976 I slot release: id 0 | task 18328 | stop processing: n_tokens = 491, truncated = 0 3.57.880.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 237763214 3.57.880.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.57.991.855 I slot launch_slot_: id 0 | task 18420 | processing task, is_child = 0 3.59.714.643 I slot print_timing: id 0 | task 18420 | prompt eval time = 137.68 ms / 292 tokens ( 0.47 ms per token, 2120.94 tokens per second) 3.59.714.648 I slot print_timing: id 0 | task 18420 | eval time = 1585.09 ms / 151 tokens ( 10.57 ms per token, 94.63 tokens per second) 3.59.714.649 I slot print_timing: id 0 | task 18420 | total time = 1722.77 ms / 443 tokens 3.59.714.650 I slot print_timing: id 0 | task 18420 | graphs reused = 17551 3.59.714.651 I slot print_timing: id 0 | task 18420 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.714.682 I slot release: id 0 | task 18420 | stop processing: n_tokens = 474, truncated = 0 3.59.732.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 239622920 3.59.732.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.59.826.806 I slot launch_slot_: id 0 | task 18574 | processing task, is_child = 0 4.00.669.952 I slot print_timing: id 0 | task 18574 | prompt eval time = 134.86 ms / 301 tokens ( 0.45 ms per token, 2231.88 tokens per second) 4.00.669.957 I slot print_timing: id 0 | task 18574 | eval time = 708.26 ms / 68 tokens ( 10.57 ms per token, 94.60 tokens per second) 4.00.669.958 I slot print_timing: id 0 | task 18574 | total time = 843.12 ms / 369 tokens 4.00.669.959 I slot print_timing: id 0 | task 18574 | graphs reused = 17617 4.00.669.960 I slot print_timing: id 0 | task 18574 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.669.989 I slot release: id 0 | task 18574 | stop processing: n_tokens = 400, truncated = 0 4.00.688.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 240578227 4.00.688.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 4.00.780.471 I slot launch_slot_: id 0 | task 18645 | processing task, is_child = 0 4.02.247.686 I slot print_timing: id 0 | task 18645 | prompt eval time = 137.12 ms / 303 tokens ( 0.45 ms per token, 2209.68 tokens per second) 4.02.247.691 I slot print_timing: id 0 | task 18645 | eval time = 1330.07 ms / 127 tokens ( 10.56 ms per token, 94.73 tokens per second) 4.02.247.692 I slot print_timing: id 0 | task 18645 | total time = 1467.20 ms / 430 tokens 4.02.247.693 I slot print_timing: id 0 | task 18645 | graphs reused = 17742 4.02.247.694 I slot print_timing: id 0 | task 18645 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.247.721 I slot release: id 0 | task 18645 | stop processing: n_tokens = 461, truncated = 0 4.02.251.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 242155959 4.02.251.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 4.02.341.690 I slot launch_slot_: id 0 | task 18775 | processing task, is_child = 0 4.02.858.654 I slot print_timing: id 0 | task 18775 | prompt eval time = 142.91 ms / 321 tokens ( 0.45 ms per token, 2246.18 tokens per second) 4.02.858.659 I slot print_timing: id 0 | task 18775 | eval time = 374.04 ms / 36 tokens ( 10.69 ms per token, 93.57 tokens per second) 4.02.858.661 I slot print_timing: id 0 | task 18775 | total time = 516.94 ms / 357 tokens 4.02.858.662 I slot print_timing: id 0 | task 18775 | graphs reused = 17776 4.02.858.662 I slot print_timing: id 0 | task 18775 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.858.689 I slot release: id 0 | task 18775 | stop processing: n_tokens = 388, truncated = 0 4.02.883.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 242766927 4.02.883.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.921 MiB) 4.02.972.918 I slot launch_slot_: id 0 | task 18814 | processing task, is_child = 0 4.03.697.753 I slot print_timing: id 0 | task 18814 | prompt eval time = 143.32 ms / 322 tokens ( 0.45 ms per token, 2246.74 tokens per second) 4.03.697.758 I slot print_timing: id 0 | task 18814 | eval time = 581.50 ms / 56 tokens ( 10.57 ms per token, 94.58 tokens per second) 4.03.697.759 I slot print_timing: id 0 | task 18814 | total time = 724.81 ms / 378 tokens 4.03.697.760 I slot print_timing: id 0 | task 18814 | graphs reused = 17830 4.03.697.760 I slot print_timing: id 0 | task 18814 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.697.788 I slot release: id 0 | task 18814 | stop processing: n_tokens = 409, truncated = 0 4.03.711.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 243606026 4.03.711.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 4.03.797.355 I slot launch_slot_: id 0 | task 18873 | processing task, is_child = 0 4.05.255.920 I slot print_timing: id 0 | task 18873 | prompt eval time = 142.91 ms / 323 tokens ( 0.44 ms per token, 2260.18 tokens per second) 4.05.255.925 I slot print_timing: id 0 | task 18873 | eval time = 1315.64 ms / 126 tokens ( 10.53 ms per token, 95.01 tokens per second) 4.05.255.926 I slot print_timing: id 0 | task 18873 | total time = 1458.55 ms / 449 tokens 4.05.255.927 I slot print_timing: id 0 | task 18873 | graphs reused = 17954 4.05.255.928 I slot print_timing: id 0 | task 18873 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.255.956 I slot release: id 0 | task 18873 | stop processing: n_tokens = 480, truncated = 0 4.05.282.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 245164194 4.05.282.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.610 MiB) 4.05.349.267 I slot launch_slot_: id 0 | task 19002 | processing task, is_child = 0 4.08.495.631 I slot print_timing: id 0 | task 19002 | n_gen = 287, tg = 95.14 t/s, tg_3s = 95.48 t/s 4.10.648.379 I slot print_timing: id 0 | task 19002 | prompt eval time = 140.38 ms / 321 tokens ( 0.44 ms per token, 2286.62 tokens per second) 4.10.648.384 I slot print_timing: id 0 | task 19002 | eval time = 5158.71 ms / 491 tokens ( 10.53 ms per token, 94.98 tokens per second) 4.10.648.385 I slot print_timing: id 0 | task 19002 | total time = 5299.09 ms / 812 tokens 4.10.648.386 I slot print_timing: id 0 | task 19002 | graphs reused = 18441 4.10.648.387 I slot print_timing: id 0 | task 19002 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.648.413 I slot release: id 0 | task 19002 | stop processing: n_tokens = 843, truncated = 0 4.10.667.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 250556651 4.10.667.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.950 MiB) 4.10.741.603 I slot launch_slot_: id 0 | task 19496 | processing task, is_child = 0 4.13.190.318 I slot print_timing: id 0 | task 19496 | prompt eval time = 145.97 ms / 322 tokens ( 0.45 ms per token, 2205.89 tokens per second) 4.13.190.324 I slot print_timing: id 0 | task 19496 | eval time = 2302.72 ms / 216 tokens ( 10.71 ms per token, 93.37 tokens per second) 4.13.190.324 I slot print_timing: id 0 | task 19496 | total time = 2448.69 ms / 538 tokens 4.13.190.326 I slot print_timing: id 0 | task 19496 | graphs reused = 18654 4.13.190.326 I slot print_timing: id 0 | task 19496 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.190.354 I slot release: id 0 | task 19496 | stop processing: n_tokens = 569, truncated = 0 4.13.211.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 253098591 4.13.211.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.640 MiB) 4.13.282.039 I slot launch_slot_: id 0 | task 19715 | processing task, is_child = 0 4.13.907.562 I slot print_timing: id 0 | task 19715 | prompt eval time = 147.15 ms / 337 tokens ( 0.44 ms per token, 2290.21 tokens per second) 4.13.907.568 I slot print_timing: id 0 | task 19715 | eval time = 478.35 ms / 46 tokens ( 10.63 ms per token, 94.07 tokens per second) 4.13.907.569 I slot print_timing: id 0 | task 19715 | total time = 625.50 ms / 383 tokens 4.13.907.570 I slot print_timing: id 0 | task 19715 | graphs reused = 18698 4.13.907.571 I slot print_timing: id 0 | task 19715 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.907.602 I slot release: id 0 | task 19715 | stop processing: n_tokens = 414, truncated = 0 4.13.926.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 253815839 4.13.926.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.13.993.842 I slot launch_slot_: id 0 | task 19764 | processing task, is_child = 0 4.14.622.257 I slot print_timing: id 0 | task 19764 | prompt eval time = 140.63 ms / 325 tokens ( 0.43 ms per token, 2311.09 tokens per second) 4.14.622.263 I slot print_timing: id 0 | task 19764 | eval time = 487.77 ms / 47 tokens ( 10.60 ms per token, 94.31 tokens per second) 4.14.622.264 I slot print_timing: id 0 | task 19764 | total time = 628.39 ms / 372 tokens 4.14.622.265 I slot print_timing: id 0 | task 19764 | graphs reused = 18743 4.14.622.265 I slot print_timing: id 0 | task 19764 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.622.296 I slot release: id 0 | task 19764 | stop processing: n_tokens = 403, truncated = 0 4.14.638.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 254530534 4.14.638.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.888 MiB) 4.14.732.129 I slot launch_slot_: id 0 | task 19814 | processing task, is_child = 0 4.15.834.972 I slot print_timing: id 0 | task 19814 | prompt eval time = 145.71 ms / 331 tokens ( 0.44 ms per token, 2271.57 tokens per second) 4.15.834.978 I slot print_timing: id 0 | task 19814 | eval time = 957.11 ms / 92 tokens ( 10.52 ms per token, 95.08 tokens per second) 4.15.834.979 I slot print_timing: id 0 | task 19814 | total time = 1102.82 ms / 423 tokens 4.15.834.980 I slot print_timing: id 0 | task 19814 | graphs reused = 18833 4.15.834.980 I slot print_timing: id 0 | task 19814 | graph reallocs = 0 / 0 (same size) / (changed size) 4.15.835.008 I slot release: id 0 | task 19814 | stop processing: n_tokens = 454, truncated = 0 4.15.857.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 255743246 4.15.857.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 4.15.953.708 I slot launch_slot_: id 0 | task 19909 | processing task, is_child = 0 4.16.706.086 I slot print_timing: id 0 | task 19909 | prompt eval time = 140.75 ms / 336 tokens ( 0.42 ms per token, 2387.13 tokens per second) 4.16.706.091 I slot print_timing: id 0 | task 19909 | eval time = 611.60 ms / 59 tokens ( 10.54 ms per token, 94.83 tokens per second) 4.16.706.092 I slot print_timing: id 0 | task 19909 | total time = 752.36 ms / 395 tokens 4.16.706.093 I slot print_timing: id 0 | task 19909 | graphs reused = 18890 4.16.706.093 I slot print_timing: id 0 | task 19909 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.706.122 I slot release: id 0 | task 19909 | stop processing: n_tokens = 426, truncated = 0 4.16.726.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 256614360 4.16.726.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.512 MiB) 4.16.818.587 I slot launch_slot_: id 0 | task 19971 | processing task, is_child = 0 4.17.281.421 I slot print_timing: id 0 | task 19971 | prompt eval time = 144.46 ms / 349 tokens ( 0.41 ms per token, 2415.93 tokens per second) 4.17.281.427 I slot print_timing: id 0 | task 19971 | eval time = 318.36 ms / 31 tokens ( 10.61 ms per token, 94.23 tokens per second) 4.17.281.428 I slot print_timing: id 0 | task 19971 | total time = 462.81 ms / 380 tokens 4.17.281.429 I slot print_timing: id 0 | task 19971 | graphs reused = 18919 4.17.281.430 I slot print_timing: id 0 | task 19971 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.281.461 I slot release: id 0 | task 19971 | stop processing: n_tokens = 411, truncated = 0 4.17.300.943 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 257189698 4.17.300.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.044 MiB) 4.17.369.123 I slot launch_slot_: id 0 | task 20005 | processing task, is_child = 0 4.20.519.770 I slot print_timing: id 0 | task 20005 | n_gen = 285, tg = 94.41 t/s, tg_3s = 94.74 t/s 4.23.530.043 I slot print_timing: id 0 | task 20005 | n_gen = 571, tg = 94.71 t/s, tg_3s = 95.01 t/s 4.24.585.654 I slot print_timing: id 0 | task 20005 | prompt eval time = 142.47 ms / 336 tokens ( 0.42 ms per token, 2358.42 tokens per second) 4.24.585.660 I slot print_timing: id 0 | task 20005 | eval time = 7074.04 ms / 671 tokens ( 10.56 ms per token, 94.71 tokens per second) 4.24.585.661 I slot print_timing: id 0 | task 20005 | total time = 7216.51 ms / 1007 tokens 4.24.585.661 I slot print_timing: id 0 | task 20005 | graphs reused = 19585 4.24.585.662 I slot print_timing: id 0 | task 20005 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.585.691 I slot release: id 0 | task 20005 | stop processing: n_tokens = 1038, truncated = 0 4.24.608.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1038, t_last = 264493928 4.24.608.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.077 MiB) 4.24.676.131 I slot launch_slot_: id 0 | task 20679 | processing task, is_child = 0 4.27.821.995 I slot print_timing: id 0 | task 20679 | n_gen = 286, tg = 94.88 t/s, tg_3s = 95.22 t/s 4.30.268.272 I slot print_timing: id 0 | task 20679 | prompt eval time = 142.15 ms / 349 tokens ( 0.41 ms per token, 2455.24 tokens per second) 4.30.268.277 I slot print_timing: id 0 | task 20679 | eval time = 5449.98 ms / 518 tokens ( 10.54 ms per token, 94.86 tokens per second) 4.30.268.278 I slot print_timing: id 0 | task 20679 | total time = 5592.12 ms / 867 tokens 4.30.268.279 I slot print_timing: id 0 | task 20679 | graphs reused = 20099 4.30.268.280 I slot print_timing: id 0 | task 20679 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.268.313 I slot release: id 0 | task 20679 | stop processing: n_tokens = 898, truncated = 0 4.30.286.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 898, t_last = 270176551 4.30.286.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.30.367.797 I slot launch_slot_: id 0 | task 21200 | processing task, is_child = 0 4.31.000.541 I slot print_timing: id 0 | task 21200 | prompt eval time = 145.54 ms / 349 tokens ( 0.42 ms per token, 2397.88 tokens per second) 4.31.000.547 I slot print_timing: id 0 | task 21200 | eval time = 487.18 ms / 47 tokens ( 10.59 ms per token, 94.42 tokens per second) 4.31.000.548 I slot print_timing: id 0 | task 21200 | total time = 632.73 ms / 396 tokens 4.31.000.549 I slot print_timing: id 0 | task 21200 | graphs reused = 20144 4.31.000.550 I slot print_timing: id 0 | task 21200 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.000.578 I slot release: id 0 | task 21200 | stop processing: n_tokens = 427, truncated = 0 4.31.021.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 270908816 4.31.022.030 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.294 MiB) 4.31.086.603 I slot launch_slot_: id 0 | task 21250 | processing task, is_child = 0 4.31.399.083 I slot print_timing: id 0 | task 21250 | prompt eval time = 149.30 ms / 385 tokens ( 0.39 ms per token, 2578.63 tokens per second) 4.31.399.088 I slot print_timing: id 0 | task 21250 | eval time = 163.16 ms / 16 tokens ( 10.88 ms per token, 91.94 tokens per second) 4.31.399.089 I slot print_timing: id 0 | task 21250 | total time = 312.46 ms / 401 tokens 4.31.399.090 I slot print_timing: id 0 | task 21250 | graphs reused = 20158 4.31.399.090 I slot print_timing: id 0 | task 21250 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.399.120 I slot release: id 0 | task 21250 | stop processing: n_tokens = 432, truncated = 0 4.31.402.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 271307358 4.31.402.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.018 MiB) 4.31.502.307 I slot launch_slot_: id 0 | task 21269 | processing task, is_child = 0 4.32.238.706 I slot print_timing: id 0 | task 21269 | prompt eval time = 141.82 ms / 328 tokens ( 0.43 ms per token, 2312.77 tokens per second) 4.32.238.711 I slot print_timing: id 0 | task 21269 | eval time = 594.56 ms / 57 tokens ( 10.62 ms per token, 94.19 tokens per second) 4.32.238.712 I slot print_timing: id 0 | task 21269 | total time = 736.38 ms / 385 tokens 4.32.238.713 I slot print_timing: id 0 | task 21269 | graphs reused = 20213 4.32.238.714 I slot print_timing: id 0 | task 21269 | graph reallocs = 0 / 0 (same size) / (changed size) 4.32.238.743 I slot release: id 0 | task 21269 | stop processing: n_tokens = 416, truncated = 0