$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-Q8_0.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.099.704 I srv llama_server: initializing ... 0.00.099.710 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.099.819 I srv init_listene: The UI is disabled 0.00.099.821 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.099.898 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) 0.00.106.171 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-Q8_0.gguf' 0.02.580.713 I cmn init: llama threadpool init, n_threads = 8 0.02.655.762 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.660.492 I srv llama_server: model loaded 0.02.660.498 I srv llama_server: listening on http://127.0.0.1:8089 0.04.563.806 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.563.978 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.150.676 I slot print_timing: id 0 | task 0 | prompt eval time = 97.27 ms / 368 tokens ( 0.26 ms per token, 3783.40 tokens per second) 0.05.150.681 I slot print_timing: id 0 | task 0 | eval time = 489.41 ms / 53 tokens ( 9.41 ms per token, 106.25 tokens per second) 0.05.150.682 I slot print_timing: id 0 | task 0 | total time = 586.68 ms / 421 tokens 0.05.150.689 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.150.690 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.150.732 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.176.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5052957 0.05.201.911 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.05.676.788 I slot print_timing: id 0 | task 56 | prompt eval time = 91.70 ms / 322 tokens ( 0.28 ms per token, 3511.53 tokens per second) 0.05.676.793 I slot print_timing: id 0 | task 56 | eval time = 383.16 ms / 42 tokens ( 9.35 ms per token, 107.01 tokens per second) 0.05.676.795 I slot print_timing: id 0 | task 56 | total time = 474.85 ms / 364 tokens 0.05.676.796 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.05.676.796 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.676.826 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.05.700.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5579050 0.05.726.073 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.06.199.899 I slot print_timing: id 0 | task 101 | prompt eval time = 95.99 ms / 365 tokens ( 0.26 ms per token, 3802.32 tokens per second) 0.06.199.904 I slot print_timing: id 0 | task 101 | eval time = 377.81 ms / 42 tokens ( 9.21 ms per token, 108.52 tokens per second) 0.06.199.905 I slot print_timing: id 0 | task 101 | total time = 473.80 ms / 407 tokens 0.06.199.906 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.06.199.907 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.199.935 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.06.218.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6102160 0.06.245.214 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.06.729.398 I slot print_timing: id 0 | task 146 | prompt eval time = 95.10 ms / 397 tokens ( 0.24 ms per token, 4174.73 tokens per second) 0.06.729.403 I slot print_timing: id 0 | task 146 | eval time = 389.07 ms / 43 tokens ( 9.26 ms per token, 107.95 tokens per second) 0.06.729.404 I slot print_timing: id 0 | task 146 | total time = 484.16 ms / 440 tokens 0.06.729.405 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.06.729.406 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.729.438 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.06.750.155 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 0.06.778.545 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.07.369.905 I slot print_timing: id 0 | task 192 | prompt eval time = 93.68 ms / 383 tokens ( 0.24 ms per token, 4088.56 tokens per second) 0.07.369.911 I slot print_timing: id 0 | task 192 | eval time = 497.66 ms / 55 tokens ( 9.22 ms per token, 108.51 tokens per second) 0.07.369.912 I slot print_timing: id 0 | task 192 | total time = 591.34 ms / 438 tokens 0.07.369.913 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.07.369.914 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.369.941 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.07.386.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7272166 0.07.415.825 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.07.998.700 I slot print_timing: id 0 | task 250 | prompt eval time = 92.67 ms / 372 tokens ( 0.25 ms per token, 4014.24 tokens per second) 0.07.998.706 I slot print_timing: id 0 | task 250 | eval time = 490.19 ms / 55 tokens ( 9.08 ms per token, 110.16 tokens per second) 0.07.998.707 I slot print_timing: id 0 | task 250 | total time = 582.86 ms / 427 tokens 0.07.998.708 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.07.998.708 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.998.735 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.08.024.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 7900960 0.08.050.753 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.08.646.896 I slot print_timing: id 0 | task 308 | prompt eval time = 101.04 ms / 422 tokens ( 0.24 ms per token, 4176.56 tokens per second) 0.08.646.902 I slot print_timing: id 0 | task 308 | eval time = 495.08 ms / 55 tokens ( 9.17 ms per token, 109.07 tokens per second) 0.08.646.903 I slot print_timing: id 0 | task 308 | total time = 596.12 ms / 477 tokens 0.08.646.904 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.08.646.904 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.646.935 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.08.651.045 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 8549160 0.08.677.079 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.09.448.021 I slot print_timing: id 0 | task 366 | prompt eval time = 106.74 ms / 470 tokens ( 0.23 ms per token, 4403.18 tokens per second) 0.09.448.027 I slot print_timing: id 0 | task 366 | eval time = 664.18 ms / 72 tokens ( 9.35 ms per token, 106.90 tokens per second) 0.09.448.028 I slot print_timing: id 0 | task 366 | total time = 770.92 ms / 542 tokens 0.09.448.028 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.09.448.030 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.448.064 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.09.475.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 9350288 0.09.501.727 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.10.024.219 I slot print_timing: id 0 | task 441 | prompt eval time = 91.05 ms / 345 tokens ( 0.26 ms per token, 3789.04 tokens per second) 0.10.024.224 I slot print_timing: id 0 | task 441 | eval time = 431.42 ms / 47 tokens ( 9.38 ms per token, 106.62 tokens per second) 0.10.024.225 I slot print_timing: id 0 | task 441 | total time = 522.47 ms / 392 tokens 0.10.024.226 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.10.024.227 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.024.258 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.10.037.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 9926482 0.10.069.542 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.10.658.274 I slot print_timing: id 0 | task 491 | prompt eval time = 90.51 ms / 364 tokens ( 0.25 ms per token, 4021.79 tokens per second) 0.10.658.279 I slot print_timing: id 0 | task 491 | eval time = 498.20 ms / 55 tokens ( 9.23 ms per token, 108.39 tokens per second) 0.10.658.280 I slot print_timing: id 0 | task 491 | total time = 588.71 ms / 419 tokens 0.10.658.281 I slot print_timing: id 0 | task 491 | graphs reused = 499 0.10.658.281 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.658.310 I slot release: id 0 | task 491 | stop processing: n_tokens = 418, truncated = 0 0.10.682.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 10560535 0.10.707.946 I slot launch_slot_: id 0 | task 549 | processing task, is_child = 0 0.11.399.579 I slot print_timing: id 0 | task 549 | prompt eval time = 95.70 ms / 376 tokens ( 0.25 ms per token, 3928.86 tokens per second) 0.11.399.585 I slot print_timing: id 0 | task 549 | eval time = 595.91 ms / 62 tokens ( 9.77 ms per token, 102.36 tokens per second) 0.11.399.586 I slot print_timing: id 0 | task 549 | total time = 691.61 ms / 438 tokens 0.11.399.587 I slot print_timing: id 0 | task 549 | graphs reused = 559 0.11.399.587 I slot print_timing: id 0 | task 549 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.399.615 I slot release: id 0 | task 549 | stop processing: n_tokens = 437, truncated = 0 0.11.413.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 11301840 0.11.439.333 I slot launch_slot_: id 0 | task 614 | processing task, is_child = 0 0.11.952.634 I slot print_timing: id 0 | task 614 | prompt eval time = 94.68 ms / 412 tokens ( 0.23 ms per token, 4351.41 tokens per second) 0.11.952.640 I slot print_timing: id 0 | task 614 | eval time = 418.60 ms / 47 tokens ( 9.10 ms per token, 109.89 tokens per second) 0.11.952.641 I slot print_timing: id 0 | task 614 | total time = 513.28 ms / 459 tokens 0.11.952.641 I slot print_timing: id 0 | task 614 | graphs reused = 604 0.11.952.642 I slot print_timing: id 0 | task 614 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.952.672 I slot release: id 0 | task 614 | stop processing: n_tokens = 458, truncated = 0 0.11.973.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 11854897 0.11.999.393 I slot launch_slot_: id 0 | task 664 | processing task, is_child = 0 0.12.649.978 I slot print_timing: id 0 | task 664 | prompt eval time = 93.00 ms / 376 tokens ( 0.25 ms per token, 4043.01 tokens per second) 0.12.649.984 I slot print_timing: id 0 | task 664 | eval time = 557.57 ms / 62 tokens ( 9.14 ms per token, 109.40 tokens per second) 0.12.649.985 I slot print_timing: id 0 | task 664 | total time = 650.57 ms / 438 tokens 0.12.649.986 I slot print_timing: id 0 | task 664 | graphs reused = 664 0.12.649.987 I slot print_timing: id 0 | task 664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.650.015 I slot release: id 0 | task 664 | stop processing: n_tokens = 437, truncated = 0 0.12.666.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12552240 0.12.692.292 I slot launch_slot_: id 0 | task 729 | processing task, is_child = 0 0.13.263.480 I slot print_timing: id 0 | task 729 | prompt eval time = 96.30 ms / 378 tokens ( 0.25 ms per token, 3925.07 tokens per second) 0.13.263.486 I slot print_timing: id 0 | task 729 | eval time = 474.86 ms / 52 tokens ( 9.31 ms per token, 107.40 tokens per second) 0.13.263.487 I slot print_timing: id 0 | task 729 | total time = 571.17 ms / 430 tokens 0.13.263.489 I slot print_timing: id 0 | task 729 | graphs reused = 714 0.13.263.490 I slot print_timing: id 0 | task 729 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.263.518 I slot release: id 0 | task 729 | stop processing: n_tokens = 429, truncated = 0 0.13.282.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 13165742 0.13.308.869 I slot launch_slot_: id 0 | task 784 | processing task, is_child = 0 0.13.962.381 I slot print_timing: id 0 | task 784 | prompt eval time = 98.28 ms / 367 tokens ( 0.27 ms per token, 3734.38 tokens per second) 0.13.962.386 I slot print_timing: id 0 | task 784 | eval time = 555.22 ms / 58 tokens ( 9.74 ms per token, 102.66 tokens per second) 0.13.962.387 I slot print_timing: id 0 | task 784 | total time = 653.49 ms / 425 tokens 0.13.962.388 I slot print_timing: id 0 | task 784 | graphs reused = 770 0.13.962.389 I slot print_timing: id 0 | task 784 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.962.417 I slot release: id 0 | task 784 | stop processing: n_tokens = 424, truncated = 0 0.13.988.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 13864642 0.14.013.791 I slot launch_slot_: id 0 | task 845 | processing task, is_child = 0 0.14.557.110 I slot print_timing: id 0 | task 845 | prompt eval time = 90.49 ms / 347 tokens ( 0.26 ms per token, 3834.68 tokens per second) 0.14.557.116 I slot print_timing: id 0 | task 845 | eval time = 452.81 ms / 51 tokens ( 9.06 ms per token, 110.42 tokens per second) 0.14.557.117 I slot print_timing: id 0 | task 845 | total time = 543.30 ms / 398 tokens 0.14.557.118 I slot print_timing: id 0 | task 845 | graphs reused = 819 0.14.557.119 I slot print_timing: id 0 | task 845 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.557.144 I slot release: id 0 | task 845 | stop processing: n_tokens = 397, truncated = 0 0.14.580.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 14459368 0.14.605.917 I slot launch_slot_: id 0 | task 899 | processing task, is_child = 0 0.16.740.172 I slot print_timing: id 0 | task 899 | prompt eval time = 91.06 ms / 369 tokens ( 0.25 ms per token, 4052.27 tokens per second) 0.16.740.178 I slot print_timing: id 0 | task 899 | eval time = 2043.17 ms / 228 tokens ( 9.00 ms per token, 111.10 tokens per second) 0.16.740.179 I slot print_timing: id 0 | task 899 | total time = 2134.24 ms / 597 tokens 0.16.740.180 I slot print_timing: id 0 | task 899 | graphs reused = 1044 0.16.740.181 I slot print_timing: id 0 | task 899 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.740.206 I slot release: id 0 | task 899 | stop processing: n_tokens = 596, truncated = 0 0.16.763.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 596, t_last = 16642431 0.16.789.494 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.17.241.838 I slot print_timing: id 0 | task 1130 | prompt eval time = 89.49 ms / 352 tokens ( 0.25 ms per token, 3933.31 tokens per second) 0.17.241.843 I slot print_timing: id 0 | task 1130 | eval time = 362.83 ms / 41 tokens ( 9.07 ms per token, 110.24 tokens per second) 0.17.241.844 I slot print_timing: id 0 | task 1130 | total time = 452.32 ms / 393 tokens 0.17.241.845 I slot print_timing: id 0 | task 1130 | graphs reused = 1083 0.17.241.846 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.241.872 I slot release: id 0 | task 1130 | stop processing: n_tokens = 392, truncated = 0 0.17.260.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 17144097 0.17.286.010 I slot launch_slot_: id 0 | task 1174 | processing task, is_child = 0 0.17.737.569 I slot print_timing: id 0 | task 1174 | prompt eval time = 89.05 ms / 349 tokens ( 0.26 ms per token, 3919.15 tokens per second) 0.17.737.574 I slot print_timing: id 0 | task 1174 | eval time = 362.49 ms / 41 tokens ( 9.06 ms per token, 110.35 tokens per second) 0.17.737.576 I slot print_timing: id 0 | task 1174 | total time = 451.54 ms / 390 tokens 0.17.737.576 I slot print_timing: id 0 | task 1174 | graphs reused = 1122 0.17.737.577 I slot print_timing: id 0 | task 1174 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.737.603 I slot release: id 0 | task 1174 | stop processing: n_tokens = 389, truncated = 0 0.17.758.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 17639828 0.17.785.234 I slot launch_slot_: id 0 | task 1218 | processing task, is_child = 0 0.18.469.620 I slot print_timing: id 0 | task 1218 | prompt eval time = 95.59 ms / 384 tokens ( 0.25 ms per token, 4017.03 tokens per second) 0.18.469.625 I slot print_timing: id 0 | task 1218 | eval time = 588.77 ms / 63 tokens ( 9.50 ms per token, 105.30 tokens per second) 0.18.469.627 I slot print_timing: id 0 | task 1218 | total time = 684.37 ms / 447 tokens 0.18.469.628 I slot print_timing: id 0 | task 1218 | graphs reused = 1183 0.18.469.628 I slot print_timing: id 0 | task 1218 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.469.656 I slot release: id 0 | task 1218 | stop processing: n_tokens = 446, truncated = 0 0.18.490.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 18371881 0.18.517.078 I slot launch_slot_: id 0 | task 1284 | processing task, is_child = 0 0.19.086.275 I slot print_timing: id 0 | task 1284 | prompt eval time = 89.55 ms / 356 tokens ( 0.25 ms per token, 3975.48 tokens per second) 0.19.086.281 I slot print_timing: id 0 | task 1284 | eval time = 479.63 ms / 54 tokens ( 9.05 ms per token, 110.50 tokens per second) 0.19.086.282 I slot print_timing: id 0 | task 1284 | total time = 569.18 ms / 410 tokens 0.19.086.283 I slot print_timing: id 0 | task 1284 | graphs reused = 1235 0.19.086.283 I slot print_timing: id 0 | task 1284 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.086.310 I slot release: id 0 | task 1284 | stop processing: n_tokens = 409, truncated = 0 0.19.103.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 18988535 0.19.128.524 I slot launch_slot_: id 0 | task 1341 | processing task, is_child = 0 0.19.846.068 I slot print_timing: id 0 | task 1341 | prompt eval time = 94.28 ms / 410 tokens ( 0.23 ms per token, 4348.66 tokens per second) 0.19.846.074 I slot print_timing: id 0 | task 1341 | eval time = 623.24 ms / 70 tokens ( 9.03 ms per token, 110.71 tokens per second) 0.19.846.075 I slot print_timing: id 0 | task 1341 | total time = 717.52 ms / 480 tokens 0.19.846.076 I slot print_timing: id 0 | task 1341 | graphs reused = 1303 0.19.846.076 I slot print_timing: id 0 | task 1341 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.846.104 I slot release: id 0 | task 1341 | stop processing: n_tokens = 479, truncated = 0 0.19.874.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 19748329 0.19.901.253 I slot launch_slot_: id 0 | task 1414 | processing task, is_child = 0 0.20.509.831 I slot print_timing: id 0 | task 1414 | prompt eval time = 93.04 ms / 385 tokens ( 0.24 ms per token, 4138.05 tokens per second) 0.20.509.836 I slot print_timing: id 0 | task 1414 | eval time = 515.52 ms / 58 tokens ( 9.04 ms per token, 110.57 tokens per second) 0.20.509.837 I slot print_timing: id 0 | task 1414 | total time = 608.56 ms / 443 tokens 0.20.509.838 I slot print_timing: id 0 | task 1414 | graphs reused = 1359 0.20.509.839 I slot print_timing: id 0 | task 1414 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.509.867 I slot release: id 0 | task 1414 | stop processing: n_tokens = 442, truncated = 0 0.20.529.468 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 20412091 0.20.556.713 I slot launch_slot_: id 0 | task 1475 | processing task, is_child = 0 0.21.283.709 I slot print_timing: id 0 | task 1475 | prompt eval time = 95.09 ms / 395 tokens ( 0.24 ms per token, 4154.00 tokens per second) 0.21.283.714 I slot print_timing: id 0 | task 1475 | eval time = 631.89 ms / 71 tokens ( 9.03 ms per token, 110.78 tokens per second) 0.21.283.716 I slot print_timing: id 0 | task 1475 | total time = 726.98 ms / 466 tokens 0.21.283.717 I slot print_timing: id 0 | task 1475 | graphs reused = 1428 0.21.283.718 I slot print_timing: id 0 | task 1475 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.283.746 I slot release: id 0 | task 1475 | stop processing: n_tokens = 465, truncated = 0 0.21.301.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 21185971 0.21.326.871 I slot launch_slot_: id 0 | task 1549 | processing task, is_child = 0 0.21.946.288 I slot print_timing: id 0 | task 1549 | prompt eval time = 95.42 ms / 430 tokens ( 0.22 ms per token, 4506.25 tokens per second) 0.21.946.294 I slot print_timing: id 0 | task 1549 | eval time = 523.97 ms / 59 tokens ( 9.03 ms per token, 110.69 tokens per second) 0.21.946.296 I slot print_timing: id 0 | task 1549 | total time = 619.40 ms / 489 tokens 0.21.946.296 I slot print_timing: id 0 | task 1549 | graphs reused = 1485 0.21.946.297 I slot print_timing: id 0 | task 1549 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.946.326 I slot release: id 0 | task 1549 | stop processing: n_tokens = 488, truncated = 0 0.21.960.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 21848551 0.21.986.045 I slot launch_slot_: id 0 | task 1611 | processing task, is_child = 0 0.22.633.357 I slot print_timing: id 0 | task 1611 | prompt eval time = 95.53 ms / 392 tokens ( 0.24 ms per token, 4103.51 tokens per second) 0.22.633.362 I slot print_timing: id 0 | task 1611 | eval time = 551.76 ms / 62 tokens ( 9.05 ms per token, 110.55 tokens per second) 0.22.633.363 I slot print_timing: id 0 | task 1611 | total time = 647.29 ms / 454 tokens 0.22.633.364 I slot print_timing: id 0 | task 1611 | graphs reused = 1545 0.22.633.365 I slot print_timing: id 0 | task 1611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.633.393 I slot release: id 0 | task 1611 | stop processing: n_tokens = 453, truncated = 0 0.22.648.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 22535617 0.22.673.561 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.23.198.079 I slot print_timing: id 0 | task 1676 | prompt eval time = 89.64 ms / 350 tokens ( 0.26 ms per token, 3904.38 tokens per second) 0.23.198.084 I slot print_timing: id 0 | task 1676 | eval time = 434.86 ms / 49 tokens ( 9.06 ms per token, 110.38 tokens per second) 0.23.198.085 I slot print_timing: id 0 | task 1676 | total time = 524.50 ms / 399 tokens 0.23.198.086 I slot print_timing: id 0 | task 1676 | graphs reused = 1592 0.23.198.087 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.198.112 I slot release: id 0 | task 1676 | stop processing: n_tokens = 398, truncated = 0 0.23.221.265 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 23100336 0.23.246.519 I slot launch_slot_: id 0 | task 1728 | processing task, is_child = 0 0.23.882.373 I slot print_timing: id 0 | task 1728 | prompt eval time = 93.24 ms / 380 tokens ( 0.25 ms per token, 4075.33 tokens per second) 0.23.882.380 I slot print_timing: id 0 | task 1728 | eval time = 542.59 ms / 61 tokens ( 9.04 ms per token, 110.58 tokens per second) 0.23.882.381 I slot print_timing: id 0 | task 1728 | total time = 635.84 ms / 441 tokens 0.23.882.382 I slot print_timing: id 0 | task 1728 | graphs reused = 1651 0.23.882.382 I slot print_timing: id 0 | task 1728 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.882.410 I slot release: id 0 | task 1728 | stop processing: n_tokens = 440, truncated = 0 0.23.910.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 23784635 0.23.936.195 I slot launch_slot_: id 0 | task 1792 | processing task, is_child = 0 0.24.776.204 I slot print_timing: id 0 | task 1792 | prompt eval time = 95.73 ms / 410 tokens ( 0.23 ms per token, 4282.92 tokens per second) 0.24.776.210 I slot print_timing: id 0 | task 1792 | eval time = 744.26 ms / 80 tokens ( 9.42 ms per token, 106.15 tokens per second) 0.24.776.211 I slot print_timing: id 0 | task 1792 | total time = 839.99 ms / 490 tokens 0.24.776.211 I slot print_timing: id 0 | task 1792 | graphs reused = 1729 0.24.776.212 I slot print_timing: id 0 | task 1792 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.776.240 I slot release: id 0 | task 1792 | stop processing: n_tokens = 489, truncated = 0 0.24.795.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 24678464 0.24.823.254 I slot launch_slot_: id 0 | task 1875 | processing task, is_child = 0 0.25.521.550 I slot print_timing: id 0 | task 1875 | prompt eval time = 93.02 ms / 387 tokens ( 0.24 ms per token, 4160.62 tokens per second) 0.25.521.555 I slot print_timing: id 0 | task 1875 | eval time = 605.26 ms / 68 tokens ( 9.03 ms per token, 110.70 tokens per second) 0.25.521.556 I slot print_timing: id 0 | task 1875 | total time = 698.28 ms / 455 tokens 0.25.521.557 I slot print_timing: id 0 | task 1875 | graphs reused = 1795 0.25.521.558 I slot print_timing: id 0 | task 1875 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.521.584 I slot release: id 0 | task 1875 | stop processing: n_tokens = 454, truncated = 0 0.25.548.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 25423809 0.25.574.095 I slot launch_slot_: id 0 | task 1946 | processing task, is_child = 0 0.26.190.155 I slot print_timing: id 0 | task 1946 | prompt eval time = 91.00 ms / 358 tokens ( 0.25 ms per token, 3934.02 tokens per second) 0.26.190.161 I slot print_timing: id 0 | task 1946 | eval time = 525.04 ms / 59 tokens ( 9.05 ms per token, 110.47 tokens per second) 0.26.190.162 I slot print_timing: id 0 | task 1946 | total time = 616.04 ms / 417 tokens 0.26.190.162 I slot print_timing: id 0 | task 1946 | graphs reused = 1852 0.26.190.163 I slot print_timing: id 0 | task 1946 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.190.189 I slot release: id 0 | task 1946 | stop processing: n_tokens = 416, truncated = 0 0.26.217.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 26092414 0.26.242.801 I slot launch_slot_: id 0 | task 2008 | processing task, is_child = 0 0.26.857.333 I slot print_timing: id 0 | task 2008 | prompt eval time = 89.70 ms / 359 tokens ( 0.25 ms per token, 4002.27 tokens per second) 0.26.857.339 I slot print_timing: id 0 | task 2008 | eval time = 524.81 ms / 56 tokens ( 9.54 ms per token, 104.80 tokens per second) 0.26.857.340 I slot print_timing: id 0 | task 2008 | total time = 614.51 ms / 415 tokens 0.26.857.341 I slot print_timing: id 0 | task 2008 | graphs reused = 1906 0.26.857.341 I slot print_timing: id 0 | task 2008 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.857.367 I slot release: id 0 | task 2008 | stop processing: n_tokens = 414, truncated = 0 0.26.872.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 26759592 0.26.898.061 I slot launch_slot_: id 0 | task 2067 | processing task, is_child = 0 0.27.533.171 I slot print_timing: id 0 | task 2067 | prompt eval time = 92.68 ms / 387 tokens ( 0.24 ms per token, 4175.75 tokens per second) 0.27.533.177 I slot print_timing: id 0 | task 2067 | eval time = 542.41 ms / 61 tokens ( 9.04 ms per token, 110.62 tokens per second) 0.27.533.178 I slot print_timing: id 0 | task 2067 | total time = 635.09 ms / 448 tokens 0.27.533.179 I slot print_timing: id 0 | task 2067 | graphs reused = 1965 0.27.533.179 I slot print_timing: id 0 | task 2067 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.533.208 I slot release: id 0 | task 2067 | stop processing: n_tokens = 447, truncated = 0 0.27.547.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 27435432 0.27.572.825 I slot launch_slot_: id 0 | task 2131 | processing task, is_child = 0 0.28.208.975 I slot print_timing: id 0 | task 2131 | prompt eval time = 93.94 ms / 410 tokens ( 0.23 ms per token, 4364.49 tokens per second) 0.28.208.981 I slot print_timing: id 0 | task 2131 | eval time = 542.19 ms / 61 tokens ( 9.04 ms per token, 110.66 tokens per second) 0.28.208.982 I slot print_timing: id 0 | task 2131 | total time = 636.13 ms / 471 tokens 0.28.208.983 I slot print_timing: id 0 | task 2131 | graphs reused = 2024 0.28.208.983 I slot print_timing: id 0 | task 2131 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.209.014 I slot release: id 0 | task 2131 | stop processing: n_tokens = 470, truncated = 0 0.28.232.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 28111239 0.28.266.183 I slot launch_slot_: id 0 | task 2195 | processing task, is_child = 0 0.28.799.897 I slot print_timing: id 0 | task 2195 | prompt eval time = 89.36 ms / 351 tokens ( 0.25 ms per token, 3927.76 tokens per second) 0.28.799.902 I slot print_timing: id 0 | task 2195 | eval time = 444.33 ms / 50 tokens ( 9.07 ms per token, 110.28 tokens per second) 0.28.799.903 I slot print_timing: id 0 | task 2195 | total time = 533.69 ms / 401 tokens 0.28.799.904 I slot print_timing: id 0 | task 2195 | graphs reused = 2072 0.28.799.905 I slot print_timing: id 0 | task 2195 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.799.932 I slot release: id 0 | task 2195 | stop processing: n_tokens = 400, truncated = 0 0.28.823.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 28702157 0.28.850.936 I slot launch_slot_: id 0 | task 2248 | processing task, is_child = 0 0.30.956.331 I slot print_timing: id 0 | task 2248 | prompt eval time = 92.82 ms / 393 tokens ( 0.24 ms per token, 4233.82 tokens per second) 0.30.956.336 I slot print_timing: id 0 | task 2248 | eval time = 2012.55 ms / 224 tokens ( 9.02 ms per token, 110.80 tokens per second) 0.30.956.337 I slot print_timing: id 0 | task 2248 | total time = 2105.38 ms / 617 tokens 0.30.956.338 I slot print_timing: id 0 | task 2248 | graphs reused = 2293 0.30.956.339 I slot print_timing: id 0 | task 2248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.956.368 I slot release: id 0 | task 2248 | stop processing: n_tokens = 616, truncated = 0 0.30.974.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 30858593 0.31.001.471 I slot launch_slot_: id 0 | task 2475 | processing task, is_child = 0 0.31.355.458 I slot print_timing: id 0 | task 2475 | prompt eval time = 88.96 ms / 321 tokens ( 0.28 ms per token, 3608.53 tokens per second) 0.31.355.464 I slot print_timing: id 0 | task 2475 | eval time = 265.01 ms / 30 tokens ( 9.14 ms per token, 109.43 tokens per second) 0.31.355.465 I slot print_timing: id 0 | task 2475 | total time = 353.97 ms / 351 tokens 0.31.355.465 I slot print_timing: id 0 | task 2475 | graphs reused = 2321 0.31.355.466 I slot print_timing: id 0 | task 2475 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.355.492 I slot release: id 0 | task 2475 | stop processing: n_tokens = 350, truncated = 0 0.31.358.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 31257717 0.31.385.482 I slot launch_slot_: id 0 | task 2508 | processing task, is_child = 0 0.31.883.646 I slot print_timing: id 0 | task 2508 | prompt eval time = 88.95 ms / 330 tokens ( 0.27 ms per token, 3710.12 tokens per second) 0.31.883.652 I slot print_timing: id 0 | task 2508 | eval time = 409.20 ms / 46 tokens ( 9.09 ms per token, 109.97 tokens per second) 0.31.883.653 I slot print_timing: id 0 | task 2508 | total time = 498.14 ms / 376 tokens 0.31.883.654 I slot print_timing: id 0 | task 2508 | graphs reused = 2365 0.31.883.655 I slot print_timing: id 0 | task 2508 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.883.681 I slot release: id 0 | task 2508 | stop processing: n_tokens = 375, truncated = 0 0.31.907.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 31785906 0.31.934.416 I slot launch_slot_: id 0 | task 2557 | processing task, is_child = 0 0.32.307.320 I slot print_timing: id 0 | task 2557 | prompt eval time = 89.94 ms / 341 tokens ( 0.26 ms per token, 3791.63 tokens per second) 0.32.307.326 I slot print_timing: id 0 | task 2557 | eval time = 282.95 ms / 32 tokens ( 9.13 ms per token, 109.56 tokens per second) 0.32.307.327 I slot print_timing: id 0 | task 2557 | total time = 372.88 ms / 373 tokens 0.32.307.328 I slot print_timing: id 0 | task 2557 | graphs reused = 2395 0.32.307.329 I slot print_timing: id 0 | task 2557 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.307.356 I slot release: id 0 | task 2557 | stop processing: n_tokens = 372, truncated = 0 0.32.331.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 32209581 0.32.359.297 I slot launch_slot_: id 0 | task 2592 | processing task, is_child = 0 0.32.874.738 I slot print_timing: id 0 | task 2592 | prompt eval time = 89.10 ms / 338 tokens ( 0.26 ms per token, 3793.62 tokens per second) 0.32.874.743 I slot print_timing: id 0 | task 2592 | eval time = 426.32 ms / 48 tokens ( 9.07 ms per token, 110.25 tokens per second) 0.32.874.744 I slot print_timing: id 0 | task 2592 | total time = 515.42 ms / 386 tokens 0.32.874.745 I slot print_timing: id 0 | task 2592 | graphs reused = 2441 0.32.874.746 I slot print_timing: id 0 | task 2592 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.874.772 I slot release: id 0 | task 2592 | stop processing: n_tokens = 385, truncated = 0 0.32.895.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 32776997 0.32.920.305 I slot launch_slot_: id 0 | task 2643 | processing task, is_child = 0 0.33.512.395 I slot print_timing: id 0 | task 2643 | prompt eval time = 94.49 ms / 395 tokens ( 0.24 ms per token, 4180.25 tokens per second) 0.33.512.401 I slot print_timing: id 0 | task 2643 | eval time = 497.58 ms / 56 tokens ( 9.05 ms per token, 110.54 tokens per second) 0.33.512.402 I slot print_timing: id 0 | task 2643 | total time = 592.07 ms / 451 tokens 0.33.512.403 I slot print_timing: id 0 | task 2643 | graphs reused = 2495 0.33.512.403 I slot print_timing: id 0 | task 2643 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.512.432 I slot release: id 0 | task 2643 | stop processing: n_tokens = 450, truncated = 0 0.33.533.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 33414656 0.33.559.027 I slot launch_slot_: id 0 | task 2702 | processing task, is_child = 0 0.34.427.720 I slot print_timing: id 0 | task 2702 | prompt eval time = 127.31 ms / 528 tokens ( 0.24 ms per token, 4147.42 tokens per second) 0.34.427.726 I slot print_timing: id 0 | task 2702 | eval time = 741.36 ms / 83 tokens ( 9.04 ms per token, 110.61 tokens per second) 0.34.427.727 I slot print_timing: id 0 | task 2702 | total time = 868.67 ms / 611 tokens 0.34.427.728 I slot print_timing: id 0 | task 2702 | graphs reused = 2576 0.34.427.729 I slot print_timing: id 0 | task 2702 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.427.763 I slot release: id 0 | task 2702 | stop processing: n_tokens = 610, truncated = 0 0.34.450.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 34329988 0.34.482.343 I slot launch_slot_: id 0 | task 2789 | processing task, is_child = 0 0.34.995.782 I slot print_timing: id 0 | task 2789 | prompt eval time = 109.14 ms / 331 tokens ( 0.33 ms per token, 3032.94 tokens per second) 0.34.995.788 I slot print_timing: id 0 | task 2789 | eval time = 404.28 ms / 45 tokens ( 9.19 ms per token, 108.83 tokens per second) 0.34.995.789 I slot print_timing: id 0 | task 2789 | total time = 513.42 ms / 376 tokens 0.34.995.790 I slot print_timing: id 0 | task 2789 | graphs reused = 2619 0.34.995.790 I slot print_timing: id 0 | task 2789 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.995.818 I slot release: id 0 | task 2789 | stop processing: n_tokens = 387, truncated = 0 0.35.014.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 34898043 0.35.061.359 I slot launch_slot_: id 0 | task 2837 | processing task, is_child = 0 0.35.653.025 I slot print_timing: id 0 | task 2837 | prompt eval time = 118.25 ms / 362 tokens ( 0.33 ms per token, 3061.36 tokens per second) 0.35.653.032 I slot print_timing: id 0 | task 2837 | eval time = 473.40 ms / 53 tokens ( 9.10 ms per token, 109.84 tokens per second) 0.35.653.033 I slot print_timing: id 0 | task 2837 | total time = 591.64 ms / 415 tokens 0.35.653.035 I slot print_timing: id 0 | task 2837 | graphs reused = 2670 0.35.653.036 I slot print_timing: id 0 | task 2837 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.653.068 I slot release: id 0 | task 2837 | stop processing: n_tokens = 426, truncated = 0 0.35.682.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 35555292 0.35.726.312 I slot launch_slot_: id 0 | task 2893 | processing task, is_child = 0 0.36.463.426 I slot print_timing: id 0 | task 2893 | prompt eval time = 122.31 ms / 419 tokens ( 0.29 ms per token, 3425.58 tokens per second) 0.36.463.432 I slot print_timing: id 0 | task 2893 | eval time = 614.78 ms / 69 tokens ( 9.04 ms per token, 110.61 tokens per second) 0.36.463.433 I slot print_timing: id 0 | task 2893 | total time = 737.09 ms / 488 tokens 0.36.463.434 I slot print_timing: id 0 | task 2893 | graphs reused = 2737 0.36.463.435 I slot print_timing: id 0 | task 2893 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.463.465 I slot release: id 0 | task 2893 | stop processing: n_tokens = 499, truncated = 0 0.36.477.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 36365689 0.36.519.935 I slot launch_slot_: id 0 | task 2965 | processing task, is_child = 0 0.37.353.063 I slot print_timing: id 0 | task 2965 | prompt eval time = 133.11 ms / 423 tokens ( 0.31 ms per token, 3177.87 tokens per second) 0.37.353.069 I slot print_timing: id 0 | task 2965 | eval time = 700.00 ms / 72 tokens ( 9.86 ms per token, 101.43 tokens per second) 0.37.353.070 I slot print_timing: id 0 | task 2965 | total time = 833.11 ms / 495 tokens 0.37.353.071 I slot print_timing: id 0 | task 2965 | graphs reused = 2807 0.37.353.072 I slot print_timing: id 0 | task 2965 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.353.102 I slot release: id 0 | task 2965 | stop processing: n_tokens = 506, truncated = 0 0.37.380.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 37255326 0.37.425.382 I slot launch_slot_: id 0 | task 3040 | processing task, is_child = 0 0.37.917.555 I slot print_timing: id 0 | task 3040 | prompt eval time = 110.97 ms / 341 tokens ( 0.33 ms per token, 3072.79 tokens per second) 0.37.917.560 I slot print_timing: id 0 | task 3040 | eval time = 381.18 ms / 43 tokens ( 9.08 ms per token, 110.18 tokens per second) 0.37.917.561 I slot print_timing: id 0 | task 3040 | total time = 492.15 ms / 384 tokens 0.37.917.562 I slot print_timing: id 0 | task 3040 | graphs reused = 2848 0.37.917.563 I slot print_timing: id 0 | task 3040 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.917.594 I slot release: id 0 | task 3040 | stop processing: n_tokens = 395, truncated = 0 0.37.940.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 37819818 0.37.985.025 I slot launch_slot_: id 0 | task 3086 | processing task, is_child = 0 0.38.515.504 I slot print_timing: id 0 | task 3086 | prompt eval time = 112.89 ms / 356 tokens ( 0.32 ms per token, 3153.46 tokens per second) 0.38.515.510 I slot print_timing: id 0 | task 3086 | eval time = 417.57 ms / 47 tokens ( 9.08 ms per token, 110.16 tokens per second) 0.38.515.511 I slot print_timing: id 0 | task 3086 | total time = 530.46 ms / 403 tokens 0.38.515.511 I slot print_timing: id 0 | task 3086 | graphs reused = 2893 0.38.515.512 I slot print_timing: id 0 | task 3086 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.515.542 I slot release: id 0 | task 3086 | stop processing: n_tokens = 414, truncated = 0 0.38.536.383 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 38417766 0.38.536.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.38.592.891 I slot launch_slot_: id 0 | task 3136 | processing task, is_child = 0 0.39.116.501 I slot print_timing: id 0 | task 3136 | prompt eval time = 115.30 ms / 362 tokens ( 0.32 ms per token, 3139.64 tokens per second) 0.39.116.507 I slot print_timing: id 0 | task 3136 | eval time = 408.29 ms / 46 tokens ( 9.07 ms per token, 110.21 tokens per second) 0.39.116.508 I slot print_timing: id 0 | task 3136 | total time = 523.59 ms / 408 tokens 0.39.116.509 I slot print_timing: id 0 | task 3136 | graphs reused = 2937 0.39.116.510 I slot print_timing: id 0 | task 3136 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.116.538 I slot release: id 0 | task 3136 | stop processing: n_tokens = 419, truncated = 0 0.39.144.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 39018762 0.39.144.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.39.200.653 I slot launch_slot_: id 0 | task 3185 | processing task, is_child = 0 0.39.921.508 I slot print_timing: id 0 | task 3185 | prompt eval time = 115.65 ms / 391 tokens ( 0.30 ms per token, 3380.92 tokens per second) 0.39.921.514 I slot print_timing: id 0 | task 3185 | eval time = 605.19 ms / 68 tokens ( 9.03 ms per token, 110.71 tokens per second) 0.39.921.515 I slot print_timing: id 0 | task 3185 | total time = 720.84 ms / 459 tokens 0.39.921.516 I slot print_timing: id 0 | task 3185 | graphs reused = 3003 0.39.921.517 I slot print_timing: id 0 | task 3185 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.921.547 I slot release: id 0 | task 3185 | stop processing: n_tokens = 470, truncated = 0 0.39.938.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 39823772 0.39.938.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.39.997.493 I slot launch_slot_: id 0 | task 3256 | processing task, is_child = 0 0.40.589.177 I slot print_timing: id 0 | task 3256 | prompt eval time = 111.53 ms / 343 tokens ( 0.33 ms per token, 3075.43 tokens per second) 0.40.589.183 I slot print_timing: id 0 | task 3256 | eval time = 480.14 ms / 54 tokens ( 9.06 ms per token, 110.39 tokens per second) 0.40.589.184 I slot print_timing: id 0 | task 3256 | total time = 591.66 ms / 397 tokens 0.40.589.185 I slot print_timing: id 0 | task 3256 | graphs reused = 3055 0.40.589.186 I slot print_timing: id 0 | task 3256 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.589.213 I slot release: id 0 | task 3256 | stop processing: n_tokens = 408, truncated = 0 0.40.609.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 40491438 0.40.609.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.40.619.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.40.684.503 I slot launch_slot_: id 0 | task 3313 | processing task, is_child = 0 0.41.210.553 I slot print_timing: id 0 | task 3313 | prompt eval time = 117.48 ms / 401 tokens ( 0.29 ms per token, 3413.20 tokens per second) 0.41.210.560 I slot print_timing: id 0 | task 3313 | eval time = 408.55 ms / 46 tokens ( 9.08 ms per token, 110.15 tokens per second) 0.41.210.561 I slot print_timing: id 0 | task 3313 | total time = 526.03 ms / 447 tokens 0.41.210.562 I slot print_timing: id 0 | task 3313 | graphs reused = 3099 0.41.210.563 I slot print_timing: id 0 | task 3313 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.210.595 I slot release: id 0 | task 3313 | stop processing: n_tokens = 458, truncated = 0 0.41.234.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 41112820 0.41.234.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.41.284.427 I slot launch_slot_: id 0 | task 3362 | processing task, is_child = 0 0.42.003.409 I slot print_timing: id 0 | task 3362 | prompt eval time = 112.56 ms / 355 tokens ( 0.32 ms per token, 3154.01 tokens per second) 0.42.003.416 I slot print_timing: id 0 | task 3362 | eval time = 606.41 ms / 68 tokens ( 9.05 ms per token, 110.49 tokens per second) 0.42.003.417 I slot print_timing: id 0 | task 3362 | total time = 718.96 ms / 423 tokens 0.42.003.419 I slot print_timing: id 0 | task 3362 | graphs reused = 3165 0.42.003.420 I slot print_timing: id 0 | task 3362 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.003.452 I slot release: id 0 | task 3362 | stop processing: n_tokens = 434, truncated = 0 0.42.030.551 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 41905676 0.42.030.599 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.42.084.288 I slot launch_slot_: id 0 | task 3433 | processing task, is_child = 0 0.42.734.233 I slot print_timing: id 0 | task 3433 | prompt eval time = 113.13 ms / 351 tokens ( 0.32 ms per token, 3102.68 tokens per second) 0.42.734.240 I slot print_timing: id 0 | task 3433 | eval time = 536.80 ms / 57 tokens ( 9.59 ms per token, 104.32 tokens per second) 0.42.734.241 I slot print_timing: id 0 | task 3433 | total time = 649.93 ms / 408 tokens 0.42.734.242 I slot print_timing: id 0 | task 3433 | graphs reused = 3220 0.42.734.243 I slot print_timing: id 0 | task 3433 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.734.274 I slot release: id 0 | task 3433 | stop processing: n_tokens = 419, truncated = 0 0.42.749.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 42636499 0.42.749.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.42.760.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.42.811.720 I slot launch_slot_: id 0 | task 3493 | processing task, is_child = 0 0.43.772.842 I slot print_timing: id 0 | task 3493 | prompt eval time = 121.35 ms / 475 tokens ( 0.26 ms per token, 3914.39 tokens per second) 0.43.772.852 I slot print_timing: id 0 | task 3493 | eval time = 839.75 ms / 93 tokens ( 9.13 ms per token, 109.56 tokens per second) 0.43.772.855 I slot print_timing: id 0 | task 3493 | total time = 961.10 ms / 568 tokens 0.43.772.856 I slot print_timing: id 0 | task 3493 | graphs reused = 3310 0.43.772.857 I slot print_timing: id 0 | task 3493 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.772.915 I slot release: id 0 | task 3493 | stop processing: n_tokens = 579, truncated = 0 0.43.791.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 43675142 0.43.791.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.824 MiB) 0.43.846.279 I slot launch_slot_: id 0 | task 3589 | processing task, is_child = 0 0.44.965.890 I slot print_timing: id 0 | task 3589 | prompt eval time = 140.08 ms / 440 tokens ( 0.32 ms per token, 3141.04 tokens per second) 0.44.965.896 I slot print_timing: id 0 | task 3589 | eval time = 979.51 ms / 106 tokens ( 9.33 ms per token, 107.20 tokens per second) 0.44.965.897 I slot print_timing: id 0 | task 3589 | total time = 1119.59 ms / 546 tokens 0.44.965.897 I slot print_timing: id 0 | task 3589 | graphs reused = 3413 0.44.965.898 I slot print_timing: id 0 | task 3589 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.965.929 I slot release: id 0 | task 3589 | stop processing: n_tokens = 557, truncated = 0 0.44.969.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 44868154 0.44.969.893 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.45.027.948 I slot launch_slot_: id 0 | task 3698 | processing task, is_child = 0 0.45.670.996 I slot print_timing: id 0 | task 3698 | prompt eval time = 127.95 ms / 345 tokens ( 0.37 ms per token, 2696.30 tokens per second) 0.45.671.001 I slot print_timing: id 0 | task 3698 | eval time = 515.08 ms / 57 tokens ( 9.20 ms per token, 108.72 tokens per second) 0.45.671.002 I slot print_timing: id 0 | task 3698 | total time = 643.03 ms / 402 tokens 0.45.671.003 I slot print_timing: id 0 | task 3698 | graphs reused = 3468 0.45.671.004 I slot print_timing: id 0 | task 3698 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.671.032 I slot release: id 0 | task 3698 | stop processing: n_tokens = 413, truncated = 0 0.45.688.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 45573256 0.45.688.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.45.699.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.45.761.505 I slot launch_slot_: id 0 | task 3758 | processing task, is_child = 0 0.46.373.005 I slot print_timing: id 0 | task 3758 | prompt eval time = 120.50 ms / 382 tokens ( 0.32 ms per token, 3170.23 tokens per second) 0.46.373.011 I slot print_timing: id 0 | task 3758 | eval time = 490.98 ms / 55 tokens ( 9.09 ms per token, 109.98 tokens per second) 0.46.373.012 I slot print_timing: id 0 | task 3758 | total time = 611.48 ms / 437 tokens 0.46.373.013 I slot print_timing: id 0 | task 3758 | graphs reused = 3521 0.46.373.014 I slot print_timing: id 0 | task 3758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.373.045 I slot release: id 0 | task 3758 | stop processing: n_tokens = 448, truncated = 0 0.46.392.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 46275270 0.46.392.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.46.443.769 I slot launch_slot_: id 0 | task 3816 | processing task, is_child = 0 0.46.961.810 I slot print_timing: id 0 | task 3816 | prompt eval time = 112.07 ms / 337 tokens ( 0.33 ms per token, 3006.94 tokens per second) 0.46.961.815 I slot print_timing: id 0 | task 3816 | eval time = 405.95 ms / 45 tokens ( 9.23 ms per token, 108.39 tokens per second) 0.46.961.816 I slot print_timing: id 0 | task 3816 | total time = 518.02 ms / 382 tokens 0.46.961.817 I slot print_timing: id 0 | task 3816 | graphs reused = 3564 0.46.961.818 I slot print_timing: id 0 | task 3816 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.961.845 I slot release: id 0 | task 3816 | stop processing: n_tokens = 393, truncated = 0 0.46.987.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 46864069 0.46.988.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.47.041.512 I slot launch_slot_: id 0 | task 3864 | processing task, is_child = 0 0.47.837.182 I slot print_timing: id 0 | task 3864 | prompt eval time = 117.65 ms / 402 tokens ( 0.29 ms per token, 3417.03 tokens per second) 0.47.837.189 I slot print_timing: id 0 | task 3864 | eval time = 678.00 ms / 70 tokens ( 9.83 ms per token, 101.77 tokens per second) 0.47.837.190 I slot print_timing: id 0 | task 3864 | total time = 795.64 ms / 472 tokens 0.47.837.191 I slot print_timing: id 0 | task 3864 | graphs reused = 3632 0.47.837.192 I slot print_timing: id 0 | task 3864 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.837.230 I slot release: id 0 | task 3864 | stop processing: n_tokens = 483, truncated = 0 0.47.859.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 47739454 0.47.859.976 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.47.870.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.391 MiB) 0.47.929.741 I slot launch_slot_: id 0 | task 3937 | processing task, is_child = 0 0.48.588.519 I slot print_timing: id 0 | task 3937 | prompt eval time = 139.24 ms / 549 tokens ( 0.25 ms per token, 3942.78 tokens per second) 0.48.588.524 I slot print_timing: id 0 | task 3937 | eval time = 519.51 ms / 57 tokens ( 9.28 ms per token, 107.79 tokens per second) 0.48.588.525 I slot print_timing: id 0 | task 3937 | total time = 658.76 ms / 606 tokens 0.48.588.526 I slot print_timing: id 0 | task 3937 | graphs reused = 3687 0.48.588.527 I slot print_timing: id 0 | task 3937 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.588.561 I slot release: id 0 | task 3937 | stop processing: n_tokens = 617, truncated = 0 0.48.606.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 48490786 0.48.606.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.48.678.797 I slot launch_slot_: id 0 | task 3998 | processing task, is_child = 0 0.49.354.253 I slot print_timing: id 0 | task 3998 | prompt eval time = 145.83 ms / 616 tokens ( 0.24 ms per token, 4224.01 tokens per second) 0.49.354.259 I slot print_timing: id 0 | task 3998 | eval time = 529.60 ms / 58 tokens ( 9.29 ms per token, 107.63 tokens per second) 0.49.354.260 I slot print_timing: id 0 | task 3998 | total time = 675.43 ms / 674 tokens 0.49.354.261 I slot print_timing: id 0 | task 3998 | graphs reused = 3743 0.49.354.261 I slot print_timing: id 0 | task 3998 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.354.299 I slot release: id 0 | task 3998 | stop processing: n_tokens = 685, truncated = 0 0.49.372.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 49256523 0.49.372.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.917 MiB) 0.49.382.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.49.452.735 I slot launch_slot_: id 0 | task 4060 | processing task, is_child = 0 0.50.156.166 I slot print_timing: id 0 | task 4060 | prompt eval time = 149.34 ms / 665 tokens ( 0.22 ms per token, 4452.90 tokens per second) 0.50.156.172 I slot print_timing: id 0 | task 4060 | eval time = 554.07 ms / 61 tokens ( 9.23 ms per token, 108.29 tokens per second) 0.50.156.173 I slot print_timing: id 0 | task 4060 | total time = 703.41 ms / 726 tokens 0.50.156.174 I slot print_timing: id 0 | task 4060 | graphs reused = 3802 0.50.156.175 I slot print_timing: id 0 | task 4060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.156.213 I slot release: id 0 | task 4060 | stop processing: n_tokens = 737, truncated = 0 0.50.183.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 50058438 0.50.183.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.50.193.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.50.260.188 I slot launch_slot_: id 0 | task 4125 | processing task, is_child = 0 0.50.901.651 I slot print_timing: id 0 | task 4125 | prompt eval time = 148.57 ms / 645 tokens ( 0.23 ms per token, 4341.45 tokens per second) 0.50.901.657 I slot print_timing: id 0 | task 4125 | eval time = 492.88 ms / 55 tokens ( 9.13 ms per token, 109.56 tokens per second) 0.50.901.658 I slot print_timing: id 0 | task 4125 | total time = 641.44 ms / 700 tokens 0.50.901.659 I slot print_timing: id 0 | task 4125 | graphs reused = 3855 0.50.901.660 I slot print_timing: id 0 | task 4125 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.901.696 I slot release: id 0 | task 4125 | stop processing: n_tokens = 711, truncated = 0 0.50.916.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 50803920 0.50.916.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.50.978.535 I slot launch_slot_: id 0 | task 4184 | processing task, is_child = 0 0.51.585.469 I slot print_timing: id 0 | task 4184 | prompt eval time = 129.42 ms / 474 tokens ( 0.27 ms per token, 3662.58 tokens per second) 0.51.585.474 I slot print_timing: id 0 | task 4184 | eval time = 477.50 ms / 52 tokens ( 9.36 ms per token, 106.81 tokens per second) 0.51.585.475 I slot print_timing: id 0 | task 4184 | total time = 606.91 ms / 526 tokens 0.51.585.476 I slot print_timing: id 0 | task 4184 | graphs reused = 3904 0.51.585.477 I slot print_timing: id 0 | task 4184 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.585.507 I slot release: id 0 | task 4184 | stop processing: n_tokens = 537, truncated = 0 0.51.601.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 51487732 0.51.601.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.51.612.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.51.676.707 I slot launch_slot_: id 0 | task 4239 | processing task, is_child = 0 0.52.202.524 I slot print_timing: id 0 | task 4239 | prompt eval time = 143.90 ms / 617 tokens ( 0.23 ms per token, 4287.85 tokens per second) 0.52.202.529 I slot print_timing: id 0 | task 4239 | eval time = 381.90 ms / 42 tokens ( 9.31 ms per token, 107.36 tokens per second) 0.52.202.530 I slot print_timing: id 0 | task 4239 | total time = 525.79 ms / 659 tokens 0.52.202.531 I slot print_timing: id 0 | task 4239 | graphs reused = 3944 0.52.202.532 I slot print_timing: id 0 | task 4239 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.202.570 I slot release: id 0 | task 4239 | stop processing: n_tokens = 670, truncated = 0 0.52.227.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 52104795 0.52.227.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.52.302.962 I slot launch_slot_: id 0 | task 4285 | processing task, is_child = 0 0.52.878.695 I slot print_timing: id 0 | task 4285 | prompt eval time = 143.46 ms / 601 tokens ( 0.24 ms per token, 4189.35 tokens per second) 0.52.878.701 I slot print_timing: id 0 | task 4285 | eval time = 432.26 ms / 48 tokens ( 9.20 ms per token, 108.73 tokens per second) 0.52.878.702 I slot print_timing: id 0 | task 4285 | total time = 575.71 ms / 649 tokens 0.52.878.703 I slot print_timing: id 0 | task 4285 | graphs reused = 3990 0.52.878.704 I slot print_timing: id 0 | task 4285 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.878.740 I slot release: id 0 | task 4285 | stop processing: n_tokens = 660, truncated = 0 0.52.894.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 52780964 0.52.894.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.52.904.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.52.973.063 I slot launch_slot_: id 0 | task 4337 | processing task, is_child = 0 0.53.537.637 I slot print_timing: id 0 | task 4337 | prompt eval time = 140.23 ms / 533 tokens ( 0.26 ms per token, 3800.87 tokens per second) 0.53.537.642 I slot print_timing: id 0 | task 4337 | eval time = 424.32 ms / 47 tokens ( 9.22 ms per token, 108.41 tokens per second) 0.53.537.643 I slot print_timing: id 0 | task 4337 | total time = 564.55 ms / 580 tokens 0.53.537.644 I slot print_timing: id 0 | task 4337 | graphs reused = 4035 0.53.537.644 I slot print_timing: id 0 | task 4337 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.537.679 I slot release: id 0 | task 4337 | stop processing: n_tokens = 591, truncated = 0 0.53.553.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 53439903 0.53.553.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.53.625.307 I slot launch_slot_: id 0 | task 4388 | processing task, is_child = 0 0.54.230.496 I slot print_timing: id 0 | task 4388 | prompt eval time = 132.29 ms / 480 tokens ( 0.28 ms per token, 3628.36 tokens per second) 0.54.230.501 I slot print_timing: id 0 | task 4388 | eval time = 472.88 ms / 52 tokens ( 9.27 ms per token, 107.85 tokens per second) 0.54.230.503 I slot print_timing: id 0 | task 4388 | total time = 605.17 ms / 532 tokens 0.54.230.503 I slot print_timing: id 0 | task 4388 | graphs reused = 4084 0.54.230.504 I slot print_timing: id 0 | task 4388 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.230.536 I slot release: id 0 | task 4388 | stop processing: n_tokens = 560, truncated = 0 0.54.251.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 54132760 0.54.251.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.54.261.216 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.54.330.926 I slot launch_slot_: id 0 | task 4443 | processing task, is_child = 0 0.54.843.371 I slot print_timing: id 0 | task 4443 | prompt eval time = 136.16 ms / 567 tokens ( 0.24 ms per token, 4164.22 tokens per second) 0.54.843.377 I slot print_timing: id 0 | task 4443 | eval time = 376.27 ms / 42 tokens ( 9.18 ms per token, 108.97 tokens per second) 0.54.843.378 I slot print_timing: id 0 | task 4443 | total time = 512.43 ms / 609 tokens 0.54.843.379 I slot print_timing: id 0 | task 4443 | graphs reused = 4124 0.54.843.380 I slot print_timing: id 0 | task 4443 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.843.413 I slot release: id 0 | task 4443 | stop processing: n_tokens = 637, truncated = 0 0.54.871.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 54745638 0.54.871.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.54.881.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.54.967.324 I slot launch_slot_: id 0 | task 4489 | processing task, is_child = 0 0.55.678.330 I slot print_timing: id 0 | task 4489 | prompt eval time = 133.31 ms / 506 tokens ( 0.26 ms per token, 3795.78 tokens per second) 0.55.678.335 I slot print_timing: id 0 | task 4489 | eval time = 577.68 ms / 63 tokens ( 9.32 ms per token, 107.33 tokens per second) 0.55.678.336 I slot print_timing: id 0 | task 4489 | total time = 710.99 ms / 569 tokens 0.55.678.337 I slot print_timing: id 0 | task 4489 | graphs reused = 4185 0.55.678.338 I slot print_timing: id 0 | task 4489 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.678.370 I slot release: id 0 | task 4489 | stop processing: n_tokens = 597, truncated = 0 0.55.699.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 55580595 0.55.699.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.55.709.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.55.783.328 I slot launch_slot_: id 0 | task 4555 | processing task, is_child = 0 0.56.268.521 I slot print_timing: id 0 | task 4555 | prompt eval time = 122.59 ms / 436 tokens ( 0.28 ms per token, 3556.60 tokens per second) 0.56.268.526 I slot print_timing: id 0 | task 4555 | eval time = 362.58 ms / 40 tokens ( 9.30 ms per token, 107.56 tokens per second) 0.56.268.527 I slot print_timing: id 0 | task 4555 | total time = 485.17 ms / 476 tokens 0.56.268.528 I slot print_timing: id 0 | task 4555 | graphs reused = 4223 0.56.268.529 I slot print_timing: id 0 | task 4555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.268.560 I slot release: id 0 | task 4555 | stop processing: n_tokens = 504, truncated = 0 0.56.291.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 56170785 0.56.291.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.56.374.770 I slot launch_slot_: id 0 | task 4598 | processing task, is_child = 0 0.57.067.879 I slot print_timing: id 0 | task 4598 | prompt eval time = 131.27 ms / 519 tokens ( 0.25 ms per token, 3953.65 tokens per second) 0.57.067.885 I slot print_timing: id 0 | task 4598 | eval time = 561.82 ms / 62 tokens ( 9.21 ms per token, 108.58 tokens per second) 0.57.067.886 I slot print_timing: id 0 | task 4598 | total time = 693.09 ms / 581 tokens 0.57.067.886 I slot print_timing: id 0 | task 4598 | graphs reused = 4283 0.57.067.887 I slot print_timing: id 0 | task 4598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.067.921 I slot release: id 0 | task 4598 | stop processing: n_tokens = 609, truncated = 0 0.57.095.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 56970146 0.57.095.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.57.105.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.479 MiB) 0.57.192.974 I slot launch_slot_: id 0 | task 4664 | processing task, is_child = 0 0.57.739.726 I slot print_timing: id 0 | task 4664 | prompt eval time = 125.76 ms / 465 tokens ( 0.27 ms per token, 3697.40 tokens per second) 0.57.739.732 I slot print_timing: id 0 | task 4664 | eval time = 420.97 ms / 46 tokens ( 9.35 ms per token, 106.90 tokens per second) 0.57.739.733 I slot print_timing: id 0 | task 4664 | total time = 546.73 ms / 511 tokens 0.57.739.734 I slot print_timing: id 0 | task 4664 | graphs reused = 4326 0.57.739.735 I slot print_timing: id 0 | task 4664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.739.769 I slot release: id 0 | task 4664 | stop processing: n_tokens = 542, truncated = 0 0.57.756.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 57641993 0.57.756.556 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.57.766.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.57.847.294 I slot launch_slot_: id 0 | task 4713 | processing task, is_child = 0 0.58.340.794 I slot print_timing: id 0 | task 4713 | prompt eval time = 128.29 ms / 431 tokens ( 0.30 ms per token, 3359.58 tokens per second) 0.58.340.800 I slot print_timing: id 0 | task 4713 | eval time = 365.19 ms / 41 tokens ( 9.13 ms per token, 109.53 tokens per second) 0.58.340.801 I slot print_timing: id 0 | task 4713 | total time = 493.48 ms / 472 tokens 0.58.340.802 I slot print_timing: id 0 | task 4713 | graphs reused = 4365 0.58.340.803 I slot print_timing: id 0 | task 4713 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.340.835 I slot release: id 0 | task 4713 | stop processing: n_tokens = 503, truncated = 0 0.58.366.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 58243060 0.58.367.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.58.377.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.58.471.750 I slot launch_slot_: id 0 | task 4757 | processing task, is_child = 0 0.58.997.775 I slot print_timing: id 0 | task 4757 | prompt eval time = 125.54 ms / 457 tokens ( 0.27 ms per token, 3640.27 tokens per second) 0.58.997.780 I slot print_timing: id 0 | task 4757 | eval time = 400.46 ms / 44 tokens ( 9.31 ms per token, 107.38 tokens per second) 0.58.997.782 I slot print_timing: id 0 | task 4757 | total time = 526.00 ms / 501 tokens 0.58.997.782 I slot print_timing: id 0 | task 4757 | graphs reused = 4406 0.58.997.783 I slot print_timing: id 0 | task 4757 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.997.816 I slot release: id 0 | task 4757 | stop processing: n_tokens = 532, truncated = 0 0.59.022.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 58900041 0.59.022.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.59.105.771 I slot launch_slot_: id 0 | task 4804 | processing task, is_child = 0 0.59.619.139 I slot print_timing: id 0 | task 4804 | prompt eval time = 133.12 ms / 439 tokens ( 0.30 ms per token, 3297.90 tokens per second) 0.59.619.145 I slot print_timing: id 0 | task 4804 | eval time = 380.23 ms / 42 tokens ( 9.27 ms per token, 107.83 tokens per second) 0.59.619.146 I slot print_timing: id 0 | task 4804 | total time = 513.35 ms / 481 tokens 0.59.619.147 I slot print_timing: id 0 | task 4804 | graphs reused = 4446 0.59.619.148 I slot print_timing: id 0 | task 4804 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.619.178 I slot release: id 0 | task 4804 | stop processing: n_tokens = 512, truncated = 0 0.59.645.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 59521402 0.59.645.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.59.655.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.59.716.574 I slot launch_slot_: id 0 | task 4849 | processing task, is_child = 0 1.00.353.350 I slot print_timing: id 0 | task 4849 | prompt eval time = 137.44 ms / 606 tokens ( 0.23 ms per token, 4409.13 tokens per second) 1.00.353.355 I slot print_timing: id 0 | task 4849 | eval time = 499.32 ms / 56 tokens ( 9.08 ms per token, 110.15 tokens per second) 1.00.353.357 I slot print_timing: id 0 | task 4849 | total time = 636.76 ms / 662 tokens 1.00.353.358 I slot print_timing: id 0 | task 4849 | graphs reused = 4500 1.00.353.358 I slot print_timing: id 0 | task 4849 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.353.395 I slot release: id 0 | task 4849 | stop processing: n_tokens = 693, truncated = 0 1.00.375.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 60255620 1.00.375.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 1.00.384.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.00.452.334 I slot launch_slot_: id 0 | task 4909 | processing task, is_child = 0 1.00.943.228 I slot print_timing: id 0 | task 4909 | prompt eval time = 123.14 ms / 477 tokens ( 0.26 ms per token, 3873.55 tokens per second) 1.00.943.234 I slot print_timing: id 0 | task 4909 | eval time = 367.73 ms / 41 tokens ( 9.19 ms per token, 108.77 tokens per second) 1.00.943.235 I slot print_timing: id 0 | task 4909 | total time = 490.88 ms / 518 tokens 1.00.943.235 I slot print_timing: id 0 | task 4909 | graphs reused = 4538 1.00.943.236 I slot print_timing: id 0 | task 4909 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.943.269 I slot release: id 0 | task 4909 | stop processing: n_tokens = 549, truncated = 0 1.00.970.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 60845493 1.00.971.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.01.031.401 I slot launch_slot_: id 0 | task 4953 | processing task, is_child = 0 1.01.730.204 I slot print_timing: id 0 | task 4953 | prompt eval time = 163.27 ms / 845 tokens ( 0.19 ms per token, 5175.60 tokens per second) 1.01.730.210 I slot print_timing: id 0 | task 4953 | eval time = 535.52 ms / 60 tokens ( 9.08 ms per token, 110.17 tokens per second) 1.01.730.212 I slot print_timing: id 0 | task 4953 | total time = 698.78 ms / 905 tokens 1.01.730.212 I slot print_timing: id 0 | task 4953 | graphs reused = 4596 1.01.730.214 I slot print_timing: id 0 | task 4953 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.730.260 I slot release: id 0 | task 4953 | stop processing: n_tokens = 936, truncated = 0 1.01.747.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 61632485 1.01.747.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.01.759.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.01.836.486 I slot launch_slot_: id 0 | task 5017 | processing task, is_child = 0 1.02.345.073 I slot print_timing: id 0 | task 5017 | prompt eval time = 122.56 ms / 459 tokens ( 0.27 ms per token, 3745.07 tokens per second) 1.02.345.080 I slot print_timing: id 0 | task 5017 | eval time = 386.01 ms / 43 tokens ( 9.19 ms per token, 108.81 tokens per second) 1.02.345.081 I slot print_timing: id 0 | task 5017 | total time = 508.57 ms / 502 tokens 1.02.345.081 I slot print_timing: id 0 | task 5017 | graphs reused = 4636 1.02.345.082 I slot print_timing: id 0 | task 5017 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.345.114 I slot release: id 0 | task 5017 | stop processing: n_tokens = 533, truncated = 0 1.02.373.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 62247339 1.02.373.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.02.463.279 I slot launch_slot_: id 0 | task 5063 | processing task, is_child = 0 1.03.027.463 I slot print_timing: id 0 | task 5063 | prompt eval time = 145.55 ms / 670 tokens ( 0.22 ms per token, 4603.23 tokens per second) 1.03.027.469 I slot print_timing: id 0 | task 5063 | eval time = 418.61 ms / 47 tokens ( 9.10 ms per token, 109.89 tokens per second) 1.03.027.470 I slot print_timing: id 0 | task 5063 | total time = 564.16 ms / 717 tokens 1.03.027.471 I slot print_timing: id 0 | task 5063 | graphs reused = 4681 1.03.027.471 I slot print_timing: id 0 | task 5063 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.027.510 I slot release: id 0 | task 5063 | stop processing: n_tokens = 748, truncated = 0 1.03.043.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 62929735 1.03.043.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.03.056.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.03.149.395 I slot launch_slot_: id 0 | task 5114 | processing task, is_child = 0 1.03.898.878 I slot print_timing: id 0 | task 5114 | prompt eval time = 160.41 ms / 775 tokens ( 0.21 ms per token, 4831.37 tokens per second) 1.03.898.884 I slot print_timing: id 0 | task 5114 | eval time = 589.05 ms / 63 tokens ( 9.50 ms per token, 105.25 tokens per second) 1.03.898.885 I slot print_timing: id 0 | task 5114 | total time = 749.46 ms / 838 tokens 1.03.898.886 I slot print_timing: id 0 | task 5114 | graphs reused = 4742 1.03.898.887 I slot print_timing: id 0 | task 5114 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.898.930 I slot release: id 0 | task 5114 | stop processing: n_tokens = 869, truncated = 0 1.03.903.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 63801155 1.03.903.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.03.916.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.04.017.207 I slot launch_slot_: id 0 | task 5181 | processing task, is_child = 0 1.04.789.487 I slot print_timing: id 0 | task 5181 | prompt eval time = 138.75 ms / 573 tokens ( 0.24 ms per token, 4129.85 tokens per second) 1.04.789.493 I slot print_timing: id 0 | task 5181 | eval time = 633.51 ms / 71 tokens ( 9.05 ms per token, 110.49 tokens per second) 1.04.789.494 I slot print_timing: id 0 | task 5181 | total time = 772.26 ms / 644 tokens 1.04.789.495 I slot print_timing: id 0 | task 5181 | graphs reused = 4811 1.04.789.495 I slot print_timing: id 0 | task 5181 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.789.532 I slot release: id 0 | task 5181 | stop processing: n_tokens = 675, truncated = 0 1.04.813.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 64691756 1.04.813.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.04.826.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.918 MiB) 1.04.915.180 I slot launch_slot_: id 0 | task 5256 | processing task, is_child = 0 1.05.592.204 I slot print_timing: id 0 | task 5256 | prompt eval time = 129.68 ms / 461 tokens ( 0.28 ms per token, 3555.01 tokens per second) 1.05.592.210 I slot print_timing: id 0 | task 5256 | eval time = 547.33 ms / 61 tokens ( 9.12 ms per token, 109.62 tokens per second) 1.05.592.211 I slot print_timing: id 0 | task 5256 | total time = 677.01 ms / 522 tokens 1.05.592.211 I slot print_timing: id 0 | task 5256 | graphs reused = 4869 1.05.592.212 I slot print_timing: id 0 | task 5256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.592.244 I slot release: id 0 | task 5256 | stop processing: n_tokens = 553, truncated = 0 1.05.620.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 553, t_last = 65494469 1.05.620.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.05.707.185 I slot launch_slot_: id 0 | task 5320 | processing task, is_child = 0 1.07.128.815 I slot print_timing: id 0 | task 5320 | prompt eval time = 137.19 ms / 609 tokens ( 0.23 ms per token, 4439.07 tokens per second) 1.07.128.821 I slot print_timing: id 0 | task 5320 | eval time = 1284.42 ms / 140 tokens ( 9.24 ms per token, 108.22 tokens per second) 1.07.128.822 I slot print_timing: id 0 | task 5320 | total time = 1421.61 ms / 749 tokens 1.07.128.823 I slot print_timing: id 0 | task 5320 | graphs reused = 5006 1.07.128.823 I slot print_timing: id 0 | task 5320 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.128.861 I slot release: id 0 | task 5320 | stop processing: n_tokens = 780, truncated = 0 1.07.155.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 67031086 1.07.155.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.07.169.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.07.264.563 I slot launch_slot_: id 0 | task 5464 | processing task, is_child = 0 1.07.969.830 I slot print_timing: id 0 | task 5464 | prompt eval time = 161.82 ms / 791 tokens ( 0.20 ms per token, 4888.06 tokens per second) 1.07.969.835 I slot print_timing: id 0 | task 5464 | eval time = 543.42 ms / 61 tokens ( 9.06 ms per token, 110.41 tokens per second) 1.07.969.837 I slot print_timing: id 0 | task 5464 | total time = 705.25 ms / 852 tokens 1.07.969.837 I slot print_timing: id 0 | task 5464 | graphs reused = 5065 1.07.969.838 I slot print_timing: id 0 | task 5464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.969.879 I slot release: id 0 | task 5464 | stop processing: n_tokens = 883, truncated = 0 1.07.997.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 67872104 1.07.998.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.08.130.461 I slot launch_slot_: id 0 | task 5529 | processing task, is_child = 0 1.08.763.291 I slot print_timing: id 0 | task 5529 | prompt eval time = 133.63 ms / 533 tokens ( 0.25 ms per token, 3988.69 tokens per second) 1.08.763.297 I slot print_timing: id 0 | task 5529 | eval time = 499.18 ms / 56 tokens ( 9.08 ms per token, 110.18 tokens per second) 1.08.763.298 I slot print_timing: id 0 | task 5529 | total time = 632.81 ms / 589 tokens 1.08.763.299 I slot print_timing: id 0 | task 5529 | graphs reused = 5119 1.08.763.299 I slot print_timing: id 0 | task 5529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.763.334 I slot release: id 0 | task 5529 | stop processing: n_tokens = 677, truncated = 0 1.08.791.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 68665558 1.08.791.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.08.878.743 I slot launch_slot_: id 0 | task 5589 | processing task, is_child = 0 1.09.467.915 I slot print_timing: id 0 | task 5589 | prompt eval time = 143.31 ms / 566 tokens ( 0.25 ms per token, 3949.62 tokens per second) 1.09.467.920 I slot print_timing: id 0 | task 5589 | eval time = 445.85 ms / 46 tokens ( 9.91 ms per token, 100.93 tokens per second) 1.09.467.921 I slot print_timing: id 0 | task 5589 | total time = 589.15 ms / 612 tokens 1.09.467.922 I slot print_timing: id 0 | task 5589 | graphs reused = 5163 1.09.467.923 I slot print_timing: id 0 | task 5589 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.467.957 I slot release: id 0 | task 5589 | stop processing: n_tokens = 643, truncated = 0 1.09.491.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 69370181 1.09.491.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 1.09.579.023 I slot launch_slot_: id 0 | task 5639 | processing task, is_child = 0 1.10.090.951 I slot print_timing: id 0 | task 5639 | prompt eval time = 126.37 ms / 443 tokens ( 0.29 ms per token, 3505.55 tokens per second) 1.10.090.956 I slot print_timing: id 0 | task 5639 | eval time = 385.54 ms / 43 tokens ( 9.18 ms per token, 108.94 tokens per second) 1.10.090.958 I slot print_timing: id 0 | task 5639 | total time = 511.91 ms / 486 tokens 1.10.090.958 I slot print_timing: id 0 | task 5639 | graphs reused = 5203 1.10.090.959 I slot print_timing: id 0 | task 5639 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.090.990 I slot release: id 0 | task 5639 | stop processing: n_tokens = 517, truncated = 0 1.10.095.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 69993215 1.10.095.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.10.168.916 I slot launch_slot_: id 0 | task 5685 | processing task, is_child = 0 1.10.874.427 I slot print_timing: id 0 | task 5685 | prompt eval time = 125.86 ms / 487 tokens ( 0.26 ms per token, 3869.29 tokens per second) 1.10.874.432 I slot print_timing: id 0 | task 5685 | eval time = 579.63 ms / 65 tokens ( 9.06 ms per token, 110.42 tokens per second) 1.10.874.433 I slot print_timing: id 0 | task 5685 | total time = 705.49 ms / 552 tokens 1.10.874.434 I slot print_timing: id 0 | task 5685 | graphs reused = 5266 1.10.874.434 I slot print_timing: id 0 | task 5685 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.874.467 I slot release: id 0 | task 5685 | stop processing: n_tokens = 583, truncated = 0 1.10.898.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 70776692 1.10.898.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.10.971.515 I slot launch_slot_: id 0 | task 5753 | processing task, is_child = 0 1.11.518.408 I slot print_timing: id 0 | task 5753 | prompt eval time = 129.25 ms / 507 tokens ( 0.25 ms per token, 3922.54 tokens per second) 1.11.518.414 I slot print_timing: id 0 | task 5753 | eval time = 417.62 ms / 47 tokens ( 9.08 ms per token, 110.15 tokens per second) 1.11.518.415 I slot print_timing: id 0 | task 5753 | total time = 546.87 ms / 554 tokens 1.11.518.416 I slot print_timing: id 0 | task 5753 | graphs reused = 5311 1.11.518.417 I slot print_timing: id 0 | task 5753 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.518.450 I slot release: id 0 | task 5753 | stop processing: n_tokens = 585, truncated = 0 1.11.541.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 71420675 1.11.541.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.11.558.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.11.643.113 I slot launch_slot_: id 0 | task 5803 | processing task, is_child = 0 1.12.373.716 I slot print_timing: id 0 | task 5803 | prompt eval time = 142.00 ms / 633 tokens ( 0.22 ms per token, 4457.72 tokens per second) 1.12.373.722 I slot print_timing: id 0 | task 5803 | eval time = 588.58 ms / 66 tokens ( 9.06 ms per token, 110.43 tokens per second) 1.12.373.723 I slot print_timing: id 0 | task 5803 | total time = 730.58 ms / 699 tokens 1.12.373.724 I slot print_timing: id 0 | task 5803 | graphs reused = 5375 1.12.373.725 I slot print_timing: id 0 | task 5803 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.373.763 I slot release: id 0 | task 5803 | stop processing: n_tokens = 730, truncated = 0 1.12.391.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 72275988 1.12.391.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.12.476.125 I slot launch_slot_: id 0 | task 5873 | processing task, is_child = 0 1.13.138.785 I slot print_timing: id 0 | task 5873 | prompt eval time = 137.83 ms / 571 tokens ( 0.24 ms per token, 4142.81 tokens per second) 1.13.138.791 I slot print_timing: id 0 | task 5873 | eval time = 524.81 ms / 59 tokens ( 9.05 ms per token, 110.52 tokens per second) 1.13.138.791 I slot print_timing: id 0 | task 5873 | total time = 662.64 ms / 630 tokens 1.13.138.792 I slot print_timing: id 0 | task 5873 | graphs reused = 5432 1.13.138.793 I slot print_timing: id 0 | task 5873 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.138.827 I slot release: id 0 | task 5873 | stop processing: n_tokens = 661, truncated = 0 1.13.164.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 73041052 1.13.164.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.13.254.837 I slot launch_slot_: id 0 | task 5936 | processing task, is_child = 0 1.13.807.030 I slot print_timing: id 0 | task 5936 | prompt eval time = 161.09 ms / 798 tokens ( 0.20 ms per token, 4953.60 tokens per second) 1.13.807.036 I slot print_timing: id 0 | task 5936 | eval time = 391.08 ms / 44 tokens ( 9.09 ms per token, 109.95 tokens per second) 1.13.807.037 I slot print_timing: id 0 | task 5936 | total time = 552.17 ms / 842 tokens 1.13.807.038 I slot print_timing: id 0 | task 5936 | graphs reused = 5474 1.13.807.038 I slot print_timing: id 0 | task 5936 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.807.081 I slot release: id 0 | task 5936 | stop processing: n_tokens = 873, truncated = 0 1.13.820.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 73709306 1.13.820.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.13.840.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.13.939.351 I slot launch_slot_: id 0 | task 5984 | processing task, is_child = 0 1.14.460.115 I slot print_timing: id 0 | task 5984 | prompt eval time = 138.91 ms / 572 tokens ( 0.24 ms per token, 4117.63 tokens per second) 1.14.460.121 I slot print_timing: id 0 | task 5984 | eval time = 381.83 ms / 43 tokens ( 9.09 ms per token, 110.00 tokens per second) 1.14.460.122 I slot print_timing: id 0 | task 5984 | total time = 520.74 ms / 615 tokens 1.14.460.123 I slot print_timing: id 0 | task 5984 | graphs reused = 5515 1.14.460.124 I slot print_timing: id 0 | task 5984 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.460.163 I slot release: id 0 | task 5984 | stop processing: n_tokens = 646, truncated = 0 1.14.478.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 74362387 1.14.478.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.14.576.792 I slot launch_slot_: id 0 | task 6031 | processing task, is_child = 0 1.15.290.407 I slot print_timing: id 0 | task 6031 | prompt eval time = 142.84 ms / 613 tokens ( 0.23 ms per token, 4291.55 tokens per second) 1.15.290.412 I slot print_timing: id 0 | task 6031 | eval time = 570.76 ms / 64 tokens ( 9.06 ms per token, 110.38 tokens per second) 1.15.290.414 I slot print_timing: id 0 | task 6031 | total time = 713.60 ms / 677 tokens 1.15.290.415 I slot print_timing: id 0 | task 6031 | graphs reused = 5577 1.15.290.416 I slot print_timing: id 0 | task 6031 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.290.453 I slot release: id 0 | task 6031 | stop processing: n_tokens = 708, truncated = 0 1.15.319.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 75192677 1.15.319.198 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.15.394.860 I slot launch_slot_: id 0 | task 6099 | processing task, is_child = 0 1.16.103.053 I slot print_timing: id 0 | task 6099 | prompt eval time = 137.94 ms / 580 tokens ( 0.24 ms per token, 4204.79 tokens per second) 1.16.103.058 I slot print_timing: id 0 | task 6099 | eval time = 570.23 ms / 64 tokens ( 9.05 ms per token, 110.48 tokens per second) 1.16.103.059 I slot print_timing: id 0 | task 6099 | total time = 708.17 ms / 644 tokens 1.16.103.060 I slot print_timing: id 0 | task 6099 | graphs reused = 5639 1.16.103.061 I slot print_timing: id 0 | task 6099 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.103.097 I slot release: id 0 | task 6099 | stop processing: n_tokens = 675, truncated = 0 1.16.130.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 76005321 1.16.130.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.16.226.241 I slot launch_slot_: id 0 | task 6167 | processing task, is_child = 0 1.16.832.822 I slot print_timing: id 0 | task 6167 | prompt eval time = 154.65 ms / 716 tokens ( 0.22 ms per token, 4629.69 tokens per second) 1.16.832.828 I slot print_timing: id 0 | task 6167 | eval time = 451.91 ms / 50 tokens ( 9.22 ms per token, 108.43 tokens per second) 1.16.832.830 I slot print_timing: id 0 | task 6167 | total time = 606.56 ms / 766 tokens 1.16.832.831 I slot print_timing: id 0 | task 6167 | graphs reused = 5686 1.16.832.832 I slot print_timing: id 0 | task 6167 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.832.878 I slot release: id 0 | task 6167 | stop processing: n_tokens = 797, truncated = 0 1.16.852.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 76735102 1.16.852.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.16.871.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.16.968.732 I slot launch_slot_: id 0 | task 6221 | processing task, is_child = 0 1.18.044.814 I slot print_timing: id 0 | task 6221 | prompt eval time = 162.59 ms / 799 tokens ( 0.20 ms per token, 4914.08 tokens per second) 1.18.044.820 I slot print_timing: id 0 | task 6221 | eval time = 913.47 ms / 102 tokens ( 9.04 ms per token, 110.57 tokens per second) 1.18.044.822 I slot print_timing: id 0 | task 6221 | total time = 1076.06 ms / 901 tokens 1.18.044.822 I slot print_timing: id 0 | task 6221 | graphs reused = 5786 1.18.044.823 I slot print_timing: id 0 | task 6221 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.044.863 I slot release: id 0 | task 6221 | stop processing: n_tokens = 932, truncated = 0 1.18.062.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 77947088 1.18.062.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.18.131.623 I slot launch_slot_: id 0 | task 6327 | processing task, is_child = 0 1.19.244.845 I slot print_timing: id 0 | task 6327 | prompt eval time = 114.21 ms / 361 tokens ( 0.32 ms per token, 3160.76 tokens per second) 1.19.244.851 I slot print_timing: id 0 | task 6327 | eval time = 998.99 ms / 112 tokens ( 9.00 ms per token, 111.11 tokens per second) 1.19.244.852 I slot print_timing: id 0 | task 6327 | total time = 1113.20 ms / 473 tokens 1.19.244.853 I slot print_timing: id 0 | task 6327 | graphs reused = 5896 1.19.244.854 I slot print_timing: id 0 | task 6327 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.244.883 I slot release: id 0 | task 6327 | stop processing: n_tokens = 504, truncated = 0 1.19.261.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 79147107 1.19.261.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.19.325.503 I slot launch_slot_: id 0 | task 6442 | processing task, is_child = 0 1.20.407.652 I slot print_timing: id 0 | task 6442 | prompt eval time = 112.73 ms / 381 tokens ( 0.30 ms per token, 3379.73 tokens per second) 1.20.407.658 I slot print_timing: id 0 | task 6442 | eval time = 969.40 ms / 108 tokens ( 9.06 ms per token, 110.38 tokens per second) 1.20.407.659 I slot print_timing: id 0 | task 6442 | total time = 1082.13 ms / 489 tokens 1.20.407.660 I slot print_timing: id 0 | task 6442 | graphs reused = 6001 1.20.407.661 I slot print_timing: id 0 | task 6442 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.407.691 I slot release: id 0 | task 6442 | stop processing: n_tokens = 520, truncated = 0 1.20.434.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 80309915 1.20.434.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.20.498.879 I slot launch_slot_: id 0 | task 6553 | processing task, is_child = 0 1.21.724.094 I slot print_timing: id 0 | task 6553 | prompt eval time = 112.07 ms / 365 tokens ( 0.31 ms per token, 3256.89 tokens per second) 1.21.724.099 I slot print_timing: id 0 | task 6553 | eval time = 1113.12 ms / 124 tokens ( 9.05 ms per token, 110.50 tokens per second) 1.21.724.100 I slot print_timing: id 0 | task 6553 | total time = 1225.19 ms / 489 tokens 1.21.724.101 I slot print_timing: id 0 | task 6553 | graphs reused = 6122 1.21.724.102 I slot print_timing: id 0 | task 6553 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.724.131 I slot release: id 0 | task 6553 | stop processing: n_tokens = 520, truncated = 0 1.21.749.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 81626356 1.21.749.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.21.819.295 I slot launch_slot_: id 0 | task 6680 | processing task, is_child = 0 1.22.882.619 I slot print_timing: id 0 | task 6680 | prompt eval time = 108.88 ms / 333 tokens ( 0.33 ms per token, 3058.41 tokens per second) 1.22.882.625 I slot print_timing: id 0 | task 6680 | eval time = 954.43 ms / 107 tokens ( 9.00 ms per token, 111.06 tokens per second) 1.22.882.626 I slot print_timing: id 0 | task 6680 | total time = 1063.31 ms / 440 tokens 1.22.882.627 I slot print_timing: id 0 | task 6680 | graphs reused = 6227 1.22.882.627 I slot print_timing: id 0 | task 6680 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.882.655 I slot release: id 0 | task 6680 | stop processing: n_tokens = 471, truncated = 0 1.22.897.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 82784880 1.22.940.413 I slot launch_slot_: id 0 | task 6790 | processing task, is_child = 0 1.24.293.782 I slot print_timing: id 0 | task 6790 | prompt eval time = 114.14 ms / 403 tokens ( 0.28 ms per token, 3530.78 tokens per second) 1.24.293.788 I slot print_timing: id 0 | task 6790 | eval time = 1239.21 ms / 138 tokens ( 9.05 ms per token, 110.55 tokens per second) 1.24.293.789 I slot print_timing: id 0 | task 6790 | total time = 1353.35 ms / 541 tokens 1.24.293.790 I slot print_timing: id 0 | task 6790 | graphs reused = 6362 1.24.293.790 I slot print_timing: id 0 | task 6790 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.293.820 I slot release: id 0 | task 6790 | stop processing: n_tokens = 572, truncated = 0 1.24.315.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 84196045 1.24.315.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.24.403.437 I slot launch_slot_: id 0 | task 6931 | processing task, is_child = 0 1.26.181.264 I slot print_timing: id 0 | task 6931 | prompt eval time = 117.22 ms / 411 tokens ( 0.29 ms per token, 3506.14 tokens per second) 1.26.181.269 I slot print_timing: id 0 | task 6931 | eval time = 1660.58 ms / 185 tokens ( 9.02 ms per token, 110.80 tokens per second) 1.26.181.270 I slot print_timing: id 0 | task 6931 | total time = 1777.81 ms / 596 tokens 1.26.181.271 I slot print_timing: id 0 | task 6931 | graphs reused = 6544 1.26.181.272 I slot print_timing: id 0 | task 6931 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.181.303 I slot release: id 0 | task 6931 | stop processing: n_tokens = 627, truncated = 0 1.26.205.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 86083527 1.26.205.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.26.298.369 I slot launch_slot_: id 0 | task 7119 | processing task, is_child = 0 1.28.444.922 I slot print_timing: id 0 | task 7119 | prompt eval time = 130.56 ms / 490 tokens ( 0.27 ms per token, 3753.18 tokens per second) 1.28.444.927 I slot print_timing: id 0 | task 7119 | eval time = 2015.98 ms / 225 tokens ( 9.00 ms per token, 111.11 tokens per second) 1.28.444.929 I slot print_timing: id 0 | task 7119 | total time = 2146.53 ms / 715 tokens 1.28.444.929 I slot print_timing: id 0 | task 7119 | graphs reused = 6767 1.28.444.930 I slot print_timing: id 0 | task 7119 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.444.961 I slot release: id 0 | task 7119 | stop processing: n_tokens = 746, truncated = 0 1.28.470.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 88347185 1.28.470.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.28.557.052 I slot launch_slot_: id 0 | task 7347 | processing task, is_child = 0 1.31.671.972 I slot print_timing: id 0 | task 7347 | n_gen = 335, tg = 111.25 t/s, tg_3s = 111.59 t/s 1.31.734.633 I slot print_timing: id 0 | task 7347 | prompt eval time = 112.78 ms / 344 tokens ( 0.33 ms per token, 3050.08 tokens per second) 1.31.734.638 I slot print_timing: id 0 | task 7347 | eval time = 3064.78 ms / 342 tokens ( 8.99 ms per token, 111.26 tokens per second) 1.31.734.639 I slot print_timing: id 0 | task 7347 | total time = 3177.56 ms / 686 tokens 1.31.734.639 I slot print_timing: id 0 | task 7347 | graphs reused = 7106 1.31.734.640 I slot print_timing: id 0 | task 7347 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.734.667 I slot release: id 0 | task 7347 | stop processing: n_tokens = 717, truncated = 0 1.31.756.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 91636892 1.31.757.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.798 MiB) 1.31.835.218 I slot launch_slot_: id 0 | task 7692 | processing task, is_child = 0 1.34.746.779 I slot print_timing: id 0 | task 7692 | prompt eval time = 114.03 ms / 347 tokens ( 0.33 ms per token, 3043.09 tokens per second) 1.34.746.785 I slot print_timing: id 0 | task 7692 | eval time = 2797.51 ms / 312 tokens ( 9.00 ms per token, 111.17 tokens per second) 1.34.746.786 I slot print_timing: id 0 | task 7692 | total time = 2911.54 ms / 659 tokens 1.34.746.787 I slot print_timing: id 0 | task 7692 | graphs reused = 7415 1.34.746.788 I slot print_timing: id 0 | task 7692 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.746.816 I slot release: id 0 | task 7692 | stop processing: n_tokens = 690, truncated = 0 1.34.760.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 690, t_last = 94649041 1.34.760.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.147 MiB) 1.34.840.781 I slot launch_slot_: id 0 | task 8007 | processing task, is_child = 0 1.36.090.016 I slot print_timing: id 0 | task 8007 | prompt eval time = 118.57 ms / 401 tokens ( 0.30 ms per token, 3382.08 tokens per second) 1.36.090.022 I slot print_timing: id 0 | task 8007 | eval time = 1130.65 ms / 126 tokens ( 9.05 ms per token, 110.56 tokens per second) 1.36.090.023 I slot print_timing: id 0 | task 8007 | total time = 1249.22 ms / 527 tokens 1.36.090.024 I slot print_timing: id 0 | task 8007 | graphs reused = 7538 1.36.090.024 I slot print_timing: id 0 | task 8007 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.090.052 I slot release: id 0 | task 8007 | stop processing: n_tokens = 558, truncated = 0 1.36.114.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 95992277 1.36.114.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.36.192.698 I slot launch_slot_: id 0 | task 8136 | processing task, is_child = 0 1.37.367.585 I slot print_timing: id 0 | task 8136 | prompt eval time = 125.56 ms / 456 tokens ( 0.28 ms per token, 3631.61 tokens per second) 1.37.367.591 I slot print_timing: id 0 | task 8136 | eval time = 1049.30 ms / 114 tokens ( 9.29 ms per token, 107.69 tokens per second) 1.37.367.592 I slot print_timing: id 0 | task 8136 | total time = 1174.87 ms / 570 tokens 1.37.367.593 I slot print_timing: id 0 | task 8136 | graphs reused = 7649 1.37.367.594 I slot print_timing: id 0 | task 8136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.367.625 I slot release: id 0 | task 8136 | stop processing: n_tokens = 601, truncated = 0 1.37.390.613 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 1.37.390.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.37.473.650 I slot launch_slot_: id 0 | task 8253 | processing task, is_child = 0 1.38.599.186 I slot print_timing: id 0 | task 8253 | prompt eval time = 119.82 ms / 406 tokens ( 0.30 ms per token, 3388.44 tokens per second) 1.38.599.192 I slot print_timing: id 0 | task 8253 | eval time = 1005.70 ms / 112 tokens ( 9.06 ms per token, 110.37 tokens per second) 1.38.599.193 I slot print_timing: id 0 | task 8253 | total time = 1125.52 ms / 518 tokens 1.38.599.194 I slot print_timing: id 0 | task 8253 | graphs reused = 7758 1.38.599.195 I slot print_timing: id 0 | task 8253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.599.226 I slot release: id 0 | task 8253 | stop processing: n_tokens = 549, truncated = 0 1.38.624.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 98501450 1.38.673.929 I slot launch_slot_: id 0 | task 8368 | processing task, is_child = 0 1.40.396.206 I slot print_timing: id 0 | task 8368 | prompt eval time = 115.58 ms / 406 tokens ( 0.28 ms per token, 3512.57 tokens per second) 1.40.396.211 I slot print_timing: id 0 | task 8368 | eval time = 1606.67 ms / 179 tokens ( 9.03 ms per token, 110.79 tokens per second) 1.40.396.212 I slot print_timing: id 0 | task 8368 | total time = 1722.26 ms / 585 tokens 1.40.396.213 I slot print_timing: id 0 | task 8368 | graphs reused = 7934 1.40.396.214 I slot print_timing: id 0 | task 8368 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.396.242 I slot release: id 0 | task 8368 | stop processing: n_tokens = 616, truncated = 0 1.40.419.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 100298467 1.40.419.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.40.507.730 I slot launch_slot_: id 0 | task 8550 | processing task, is_child = 0 1.41.867.365 I slot print_timing: id 0 | task 8550 | prompt eval time = 121.29 ms / 444 tokens ( 0.27 ms per token, 3660.68 tokens per second) 1.41.867.371 I slot print_timing: id 0 | task 8550 | eval time = 1238.33 ms / 134 tokens ( 9.31 ms per token, 107.40 tokens per second) 1.41.867.372 I slot print_timing: id 0 | task 8550 | total time = 1359.62 ms / 578 tokens 1.41.867.373 I slot print_timing: id 0 | task 8550 | graphs reused = 8065 1.41.867.373 I slot print_timing: id 0 | task 8550 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.867.405 I slot release: id 0 | task 8550 | stop processing: n_tokens = 609, truncated = 0 1.41.882.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 101769629 1.41.882.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.41.966.944 I slot launch_slot_: id 0 | task 8687 | processing task, is_child = 0 1.43.034.989 I slot print_timing: id 0 | task 8687 | prompt eval time = 119.66 ms / 372 tokens ( 0.32 ms per token, 3108.91 tokens per second) 1.43.034.995 I slot print_timing: id 0 | task 8687 | eval time = 948.37 ms / 103 tokens ( 9.30 ms per token, 107.55 tokens per second) 1.43.034.996 I slot print_timing: id 0 | task 8687 | total time = 1068.02 ms / 475 tokens 1.43.034.997 I slot print_timing: id 0 | task 8687 | graphs reused = 8166 1.43.034.997 I slot print_timing: id 0 | task 8687 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.035.031 I slot release: id 0 | task 8687 | stop processing: n_tokens = 506, truncated = 0 1.43.051.374 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 102937255 1.43.051.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.43.136.235 I slot launch_slot_: id 0 | task 8793 | processing task, is_child = 0 1.45.362.390 I slot print_timing: id 0 | task 8793 | prompt eval time = 123.13 ms / 454 tokens ( 0.27 ms per token, 3687.22 tokens per second) 1.45.362.397 I slot print_timing: id 0 | task 8793 | eval time = 2103.01 ms / 230 tokens ( 9.18 ms per token, 108.89 tokens per second) 1.45.362.398 I slot print_timing: id 0 | task 8793 | total time = 2226.13 ms / 684 tokens 1.45.362.399 I slot print_timing: id 0 | task 8793 | graphs reused = 8393 1.45.362.400 I slot print_timing: id 0 | task 8793 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.362.434 I slot release: id 0 | task 8793 | stop processing: n_tokens = 715, truncated = 0 1.45.387.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 105264659 1.45.387.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.45.479.569 I slot launch_slot_: id 0 | task 9026 | processing task, is_child = 0 1.47.686.096 I slot print_timing: id 0 | task 9026 | prompt eval time = 119.04 ms / 354 tokens ( 0.34 ms per token, 2973.69 tokens per second) 1.47.686.102 I slot print_timing: id 0 | task 9026 | eval time = 2087.46 ms / 226 tokens ( 9.28 ms per token, 107.79 tokens per second) 1.47.686.103 I slot print_timing: id 0 | task 9026 | total time = 2206.50 ms / 580 tokens 1.47.686.104 I slot print_timing: id 0 | task 9026 | graphs reused = 8616 1.47.686.105 I slot print_timing: id 0 | task 9026 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.686.133 I slot release: id 0 | task 9026 | stop processing: n_tokens = 611, truncated = 0 1.47.690.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 107588358 1.47.690.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.47.778.074 I slot launch_slot_: id 0 | task 9255 | processing task, is_child = 0 1.49.153.310 I slot print_timing: id 0 | task 9255 | prompt eval time = 113.04 ms / 334 tokens ( 0.34 ms per token, 2954.73 tokens per second) 1.49.153.316 I slot print_timing: id 0 | task 9255 | eval time = 1262.17 ms / 140 tokens ( 9.08 ms per token, 110.13 tokens per second) 1.49.153.317 I slot print_timing: id 0 | task 9255 | total time = 1375.21 ms / 474 tokens 1.49.153.317 I slot print_timing: id 0 | task 9255 | graphs reused = 8754 1.49.153.318 I slot print_timing: id 0 | task 9255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.153.346 I slot release: id 0 | task 9255 | stop processing: n_tokens = 505, truncated = 0 1.49.170.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 109055571 1.49.170.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 1.49.262.774 I slot launch_slot_: id 0 | task 9398 | processing task, is_child = 0 1.50.995.725 I slot print_timing: id 0 | task 9398 | prompt eval time = 122.76 ms / 426 tokens ( 0.29 ms per token, 3470.24 tokens per second) 1.50.995.731 I slot print_timing: id 0 | task 9398 | eval time = 1610.17 ms / 175 tokens ( 9.25 ms per token, 108.06 tokens per second) 1.50.995.732 I slot print_timing: id 0 | task 9398 | total time = 1732.93 ms / 601 tokens 1.50.995.733 I slot print_timing: id 0 | task 9398 | graphs reused = 8926 1.50.995.734 I slot print_timing: id 0 | task 9398 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.995.768 I slot release: id 0 | task 9398 | stop processing: n_tokens = 632, truncated = 0 1.51.018.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 110897993 1.51.018.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.51.100.100 I slot launch_slot_: id 0 | task 9576 | processing task, is_child = 0 1.52.289.345 I slot print_timing: id 0 | task 9576 | prompt eval time = 117.74 ms / 366 tokens ( 0.32 ms per token, 3108.65 tokens per second) 1.52.289.351 I slot print_timing: id 0 | task 9576 | eval time = 1071.49 ms / 117 tokens ( 9.24 ms per token, 108.26 tokens per second) 1.52.289.352 I slot print_timing: id 0 | task 9576 | total time = 1189.23 ms / 483 tokens 1.52.289.353 I slot print_timing: id 0 | task 9576 | graphs reused = 9040 1.52.289.353 I slot print_timing: id 0 | task 9576 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.289.383 I slot release: id 0 | task 9576 | stop processing: n_tokens = 514, truncated = 0 1.52.304.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 112191607 1.52.305.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.52.381.402 I slot launch_slot_: id 0 | task 9696 | processing task, is_child = 0 1.55.269.633 I slot print_timing: id 0 | task 9696 | prompt eval time = 126.89 ms / 462 tokens ( 0.27 ms per token, 3640.98 tokens per second) 1.55.269.639 I slot print_timing: id 0 | task 9696 | eval time = 2761.32 ms / 302 tokens ( 9.17 ms per token, 109.01 tokens per second) 1.55.269.640 I slot print_timing: id 0 | task 9696 | total time = 2888.21 ms / 764 tokens 1.55.269.641 I slot print_timing: id 0 | task 9696 | graphs reused = 9338 1.55.269.642 I slot print_timing: id 0 | task 9696 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.269.673 I slot release: id 0 | task 9696 | stop processing: n_tokens = 795, truncated = 0 1.55.296.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 795, t_last = 115171898 1.55.296.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.55.371.994 I slot launch_slot_: id 0 | task 10001 | processing task, is_child = 0 1.56.753.273 I slot print_timing: id 0 | task 10001 | prompt eval time = 116.04 ms / 396 tokens ( 0.29 ms per token, 3412.62 tokens per second) 1.56.753.280 I slot print_timing: id 0 | task 10001 | eval time = 1265.22 ms / 139 tokens ( 9.17 ms per token, 109.07 tokens per second) 1.56.753.281 I slot print_timing: id 0 | task 10001 | total time = 1381.26 ms / 535 tokens 1.56.753.282 I slot print_timing: id 0 | task 10001 | graphs reused = 9474 1.56.753.282 I slot print_timing: id 0 | task 10001 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.753.312 I slot release: id 0 | task 10001 | stop processing: n_tokens = 566, truncated = 0 1.56.782.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 116655537 1.56.825.773 I slot launch_slot_: id 0 | task 10143 | processing task, is_child = 0 1.58.420.412 I slot print_timing: id 0 | task 10143 | prompt eval time = 123.09 ms / 458 tokens ( 0.27 ms per token, 3720.85 tokens per second) 1.58.420.418 I slot print_timing: id 0 | task 10143 | eval time = 1471.53 ms / 161 tokens ( 9.20 ms per token, 108.73 tokens per second) 1.58.420.419 I slot print_timing: id 0 | task 10143 | total time = 1594.62 ms / 619 tokens 1.58.420.420 I slot print_timing: id 0 | task 10143 | graphs reused = 9632 1.58.420.421 I slot print_timing: id 0 | task 10143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.420.456 I slot release: id 0 | task 10143 | stop processing: n_tokens = 650, truncated = 0 1.58.448.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 118322681 1.58.448.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.58.539.907 I slot launch_slot_: id 0 | task 10307 | processing task, is_child = 0 2.00.314.754 I slot print_timing: id 0 | task 10307 | prompt eval time = 127.89 ms / 458 tokens ( 0.28 ms per token, 3581.31 tokens per second) 2.00.314.760 I slot print_timing: id 0 | task 10307 | eval time = 1646.94 ms / 176 tokens ( 9.41 ms per token, 106.26 tokens per second) 2.00.314.761 I slot print_timing: id 0 | task 10307 | total time = 1774.83 ms / 634 tokens 2.00.314.762 I slot print_timing: id 0 | task 10307 | graphs reused = 9805 2.00.314.763 I slot print_timing: id 0 | task 10307 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.314.794 I slot release: id 0 | task 10307 | stop processing: n_tokens = 665, truncated = 0 2.00.339.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 120217019 2.00.340.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.00.416.757 I slot launch_slot_: id 0 | task 10486 | processing task, is_child = 0 2.02.461.830 I slot print_timing: id 0 | task 10486 | prompt eval time = 123.33 ms / 452 tokens ( 0.27 ms per token, 3664.93 tokens per second) 2.02.461.836 I slot print_timing: id 0 | task 10486 | eval time = 1921.72 ms / 210 tokens ( 9.19 ms per token, 108.76 tokens per second) 2.02.461.837 I slot print_timing: id 0 | task 10486 | total time = 2045.05 ms / 662 tokens 2.02.461.838 I slot print_timing: id 0 | task 10486 | graphs reused = 10012 2.02.461.838 I slot print_timing: id 0 | task 10486 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.461.870 I slot release: id 0 | task 10486 | stop processing: n_tokens = 693, truncated = 0 2.02.479.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 122364095 2.02.479.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.02.546.499 I slot launch_slot_: id 0 | task 10699 | processing task, is_child = 0 2.03.714.117 I slot print_timing: id 0 | task 10699 | prompt eval time = 118.96 ms / 404 tokens ( 0.29 ms per token, 3396.07 tokens per second) 2.03.714.124 I slot print_timing: id 0 | task 10699 | eval time = 1048.64 ms / 114 tokens ( 9.28 ms per token, 107.76 tokens per second) 2.03.714.125 I slot print_timing: id 0 | task 10699 | total time = 1167.60 ms / 518 tokens 2.03.714.126 I slot print_timing: id 0 | task 10699 | graphs reused = 10123 2.03.714.128 I slot print_timing: id 0 | task 10699 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.714.162 I slot release: id 0 | task 10699 | stop processing: n_tokens = 549, truncated = 0 2.03.739.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 123616386 2.03.739.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.03.803.261 I slot launch_slot_: id 0 | task 10816 | processing task, is_child = 0 2.04.872.018 I slot print_timing: id 0 | task 10816 | prompt eval time = 110.30 ms / 345 tokens ( 0.32 ms per token, 3127.86 tokens per second) 2.04.872.024 I slot print_timing: id 0 | task 10816 | eval time = 958.44 ms / 106 tokens ( 9.13 ms per token, 109.55 tokens per second) 2.04.872.025 I slot print_timing: id 0 | task 10816 | total time = 1068.74 ms / 451 tokens 2.04.872.026 I slot print_timing: id 0 | task 10816 | graphs reused = 10227 2.04.872.027 I slot print_timing: id 0 | task 10816 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.872.055 I slot release: id 0 | task 10816 | stop processing: n_tokens = 482, truncated = 0 2.04.896.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 124774280 2.04.896.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.04.966.480 I slot launch_slot_: id 0 | task 10925 | processing task, is_child = 0 2.06.045.267 I slot print_timing: id 0 | task 10925 | prompt eval time = 121.44 ms / 430 tokens ( 0.28 ms per token, 3540.90 tokens per second) 2.06.045.273 I slot print_timing: id 0 | task 10925 | eval time = 957.33 ms / 105 tokens ( 9.21 ms per token, 108.64 tokens per second) 2.06.045.274 I slot print_timing: id 0 | task 10925 | total time = 1078.77 ms / 535 tokens 2.06.045.275 I slot print_timing: id 0 | task 10925 | graphs reused = 10329 2.06.045.276 I slot print_timing: id 0 | task 10925 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.045.306 I slot release: id 0 | task 10925 | stop processing: n_tokens = 566, truncated = 0 2.06.070.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 125947531 2.06.070.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.06.138.693 I slot launch_slot_: id 0 | task 11033 | processing task, is_child = 0 2.07.070.323 I slot print_timing: id 0 | task 11033 | prompt eval time = 117.35 ms / 316 tokens ( 0.37 ms per token, 2692.85 tokens per second) 2.07.070.329 I slot print_timing: id 0 | task 11033 | eval time = 814.26 ms / 85 tokens ( 9.69 ms per token, 103.16 tokens per second) 2.07.070.330 I slot print_timing: id 0 | task 11033 | total time = 931.61 ms / 401 tokens 2.07.070.331 I slot print_timing: id 0 | task 11033 | graphs reused = 10412 2.07.070.332 I slot print_timing: id 0 | task 11033 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.070.358 I slot release: id 0 | task 11033 | stop processing: n_tokens = 432, truncated = 0 2.07.099.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 126972583 2.07.099.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.07.171.450 I slot launch_slot_: id 0 | task 11121 | processing task, is_child = 0 2.08.263.994 I slot print_timing: id 0 | task 11121 | prompt eval time = 117.11 ms / 354 tokens ( 0.33 ms per token, 3022.77 tokens per second) 2.08.264.000 I slot print_timing: id 0 | task 11121 | eval time = 975.41 ms / 107 tokens ( 9.20 ms per token, 108.67 tokens per second) 2.08.264.001 I slot print_timing: id 0 | task 11121 | total time = 1092.52 ms / 461 tokens 2.08.264.002 I slot print_timing: id 0 | task 11121 | graphs reused = 10517 2.08.264.002 I slot print_timing: id 0 | task 11121 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.264.030 I slot release: id 0 | task 11121 | stop processing: n_tokens = 492, truncated = 0 2.08.288.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 128166254 2.08.288.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.08.360.905 I slot launch_slot_: id 0 | task 11231 | processing task, is_child = 0 2.09.371.758 I slot print_timing: id 0 | task 11231 | prompt eval time = 124.95 ms / 438 tokens ( 0.29 ms per token, 3505.37 tokens per second) 2.09.371.766 I slot print_timing: id 0 | task 11231 | eval time = 885.88 ms / 98 tokens ( 9.13 ms per token, 109.50 tokens per second) 2.09.371.767 I slot print_timing: id 0 | task 11231 | total time = 1010.83 ms / 536 tokens 2.09.371.768 I slot print_timing: id 0 | task 11231 | graphs reused = 10612 2.09.371.768 I slot print_timing: id 0 | task 11231 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.371.800 I slot release: id 0 | task 11231 | stop processing: n_tokens = 567, truncated = 0 2.09.397.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 129274025 2.09.397.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.09.469.749 I slot launch_slot_: id 0 | task 11332 | processing task, is_child = 0 2.10.237.378 I slot print_timing: id 0 | task 11332 | prompt eval time = 125.96 ms / 457 tokens ( 0.28 ms per token, 3628.16 tokens per second) 2.10.237.383 I slot print_timing: id 0 | task 11332 | eval time = 641.65 ms / 70 tokens ( 9.30 ms per token, 107.54 tokens per second) 2.10.237.385 I slot print_timing: id 0 | task 11332 | total time = 767.61 ms / 527 tokens 2.10.237.385 I slot print_timing: id 0 | task 11332 | graphs reused = 10679 2.10.237.386 I slot print_timing: id 0 | task 11332 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.237.418 I slot release: id 0 | task 11332 | stop processing: n_tokens = 558, truncated = 0 2.10.260.638 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 130139643 2.10.260.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.10.337.042 I slot launch_slot_: id 0 | task 11405 | processing task, is_child = 0 2.11.364.557 I slot print_timing: id 0 | task 11405 | prompt eval time = 128.51 ms / 473 tokens ( 0.27 ms per token, 3680.70 tokens per second) 2.11.364.562 I slot print_timing: id 0 | task 11405 | eval time = 898.99 ms / 98 tokens ( 9.27 ms per token, 107.90 tokens per second) 2.11.364.563 I slot print_timing: id 0 | task 11405 | total time = 1027.49 ms / 571 tokens 2.11.364.564 I slot print_timing: id 0 | task 11405 | graphs reused = 10774 2.11.364.565 I slot print_timing: id 0 | task 11405 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.364.597 I slot release: id 0 | task 11405 | stop processing: n_tokens = 602, truncated = 0 2.11.382.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 131266821 2.11.382.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.926 MiB) 2.11.457.005 I slot launch_slot_: id 0 | task 11506 | processing task, is_child = 0 2.11.834.938 I slot print_timing: id 0 | task 11506 | prompt eval time = 129.48 ms / 476 tokens ( 0.27 ms per token, 3676.27 tokens per second) 2.11.834.944 I slot print_timing: id 0 | task 11506 | eval time = 248.44 ms / 27 tokens ( 9.56 ms per token, 104.65 tokens per second) 2.11.834.945 I slot print_timing: id 0 | task 11506 | total time = 377.92 ms / 503 tokens 2.11.834.946 I slot print_timing: id 0 | task 11506 | graphs reused = 10798 2.11.834.947 I slot print_timing: id 0 | task 11506 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.834.980 I slot release: id 0 | task 11506 | stop processing: n_tokens = 534, truncated = 0 2.11.849.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 131737205 2.11.849.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.082 MiB) 2.11.920.165 I slot launch_slot_: id 0 | task 11536 | processing task, is_child = 0 2.13.020.547 I slot print_timing: id 0 | task 11536 | prompt eval time = 128.48 ms / 466 tokens ( 0.28 ms per token, 3627.05 tokens per second) 2.13.020.554 I slot print_timing: id 0 | task 11536 | eval time = 971.88 ms / 107 tokens ( 9.17 ms per token, 109.07 tokens per second) 2.13.020.555 I slot print_timing: id 0 | task 11536 | total time = 1100.36 ms / 573 tokens 2.13.020.555 I slot print_timing: id 0 | task 11536 | graphs reused = 10902 2.13.020.556 I slot print_timing: id 0 | task 11536 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.020.588 I slot release: id 0 | task 11536 | stop processing: n_tokens = 604, truncated = 0 2.13.036.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 132922812 2.13.036.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.13.108.575 I slot launch_slot_: id 0 | task 11646 | processing task, is_child = 0 2.13.943.345 I slot print_timing: id 0 | task 11646 | prompt eval time = 120.37 ms / 415 tokens ( 0.29 ms per token, 3447.76 tokens per second) 2.13.943.351 I slot print_timing: id 0 | task 11646 | eval time = 714.38 ms / 78 tokens ( 9.28 ms per token, 107.79 tokens per second) 2.13.943.354 I slot print_timing: id 0 | task 11646 | total time = 834.75 ms / 493 tokens 2.13.943.355 I slot print_timing: id 0 | task 11646 | graphs reused = 10977 2.13.943.356 I slot print_timing: id 0 | task 11646 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.943.390 I slot release: id 0 | task 11646 | stop processing: n_tokens = 524, truncated = 0 2.13.958.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 133845615 2.13.958.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.299 MiB) 2.14.029.554 I slot launch_slot_: id 0 | task 11727 | processing task, is_child = 0 2.14.730.661 I slot print_timing: id 0 | task 11727 | prompt eval time = 116.53 ms / 352 tokens ( 0.33 ms per token, 3020.71 tokens per second) 2.14.730.667 I slot print_timing: id 0 | task 11727 | eval time = 584.56 ms / 64 tokens ( 9.28 ms per token, 107.77 tokens per second) 2.14.730.668 I slot print_timing: id 0 | task 11727 | total time = 701.09 ms / 416 tokens 2.14.730.669 I slot print_timing: id 0 | task 11727 | graphs reused = 11039 2.14.730.669 I slot print_timing: id 0 | task 11727 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.730.699 I slot release: id 0 | task 11727 | stop processing: n_tokens = 447, truncated = 0 2.14.756.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 134632924 2.14.756.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.14.829.868 I slot launch_slot_: id 0 | task 11794 | processing task, is_child = 0 2.16.175.391 I slot print_timing: id 0 | task 11794 | prompt eval time = 137.57 ms / 550 tokens ( 0.25 ms per token, 3997.91 tokens per second) 2.16.175.397 I slot print_timing: id 0 | task 11794 | eval time = 1207.93 ms / 133 tokens ( 9.15 ms per token, 109.28 tokens per second) 2.16.175.398 I slot print_timing: id 0 | task 11794 | total time = 1345.50 ms / 683 tokens 2.16.175.399 I slot print_timing: id 0 | task 11794 | graphs reused = 11170 2.16.175.399 I slot print_timing: id 0 | task 11794 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.175.436 I slot release: id 0 | task 11794 | stop processing: n_tokens = 714, truncated = 0 2.16.190.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 136077660 2.16.190.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.16.275.939 I slot launch_slot_: id 0 | task 11931 | processing task, is_child = 0 2.18.495.007 I slot print_timing: id 0 | task 11931 | prompt eval time = 156.90 ms / 772 tokens ( 0.20 ms per token, 4920.33 tokens per second) 2.18.495.013 I slot print_timing: id 0 | task 11931 | eval time = 2062.15 ms / 226 tokens ( 9.17 ms per token, 109.11 tokens per second) 2.18.495.014 I slot print_timing: id 0 | task 11931 | total time = 2219.05 ms / 998 tokens 2.18.495.015 I slot print_timing: id 0 | task 11931 | graphs reused = 11393 2.18.495.016 I slot print_timing: id 0 | task 11931 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.495.056 I slot release: id 0 | task 11931 | stop processing: n_tokens = 1029, truncated = 0 2.18.500.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 138397280 2.18.500.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 2.18.597.409 I slot launch_slot_: id 0 | task 12161 | processing task, is_child = 0 2.20.409.265 I slot print_timing: id 0 | task 12161 | prompt eval time = 155.67 ms / 683 tokens ( 0.23 ms per token, 4387.51 tokens per second) 2.20.409.271 I slot print_timing: id 0 | task 12161 | eval time = 1656.17 ms / 181 tokens ( 9.20 ms per token, 108.68 tokens per second) 2.20.409.272 I slot print_timing: id 0 | task 12161 | total time = 1811.84 ms / 864 tokens 2.20.409.273 I slot print_timing: id 0 | task 12161 | graphs reused = 11571 2.20.409.274 I slot print_timing: id 0 | task 12161 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.409.312 I slot release: id 0 | task 12161 | stop processing: n_tokens = 895, truncated = 0 2.20.430.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 140311536 2.20.431.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.20.528.984 I slot launch_slot_: id 0 | task 12346 | processing task, is_child = 0 2.21.509.251 I slot print_timing: id 0 | task 12346 | prompt eval time = 141.25 ms / 579 tokens ( 0.24 ms per token, 4099.06 tokens per second) 2.21.509.257 I slot print_timing: id 0 | task 12346 | eval time = 838.99 ms / 93 tokens ( 9.12 ms per token, 109.66 tokens per second) 2.21.509.258 I slot print_timing: id 0 | task 12346 | total time = 980.25 ms / 672 tokens 2.21.509.259 I slot print_timing: id 0 | task 12346 | graphs reused = 11662 2.21.509.260 I slot print_timing: id 0 | task 12346 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.509.297 I slot release: id 0 | task 12346 | stop processing: n_tokens = 703, truncated = 0 2.21.536.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 141411522 2.21.536.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.21.555.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.21.653.769 I slot launch_slot_: id 0 | task 12443 | processing task, is_child = 0 2.22.764.136 I slot print_timing: id 0 | task 12443 | prompt eval time = 136.36 ms / 500 tokens ( 0.27 ms per token, 3666.68 tokens per second) 2.22.764.141 I slot print_timing: id 0 | task 12443 | eval time = 973.98 ms / 106 tokens ( 9.28 ms per token, 107.80 tokens per second) 2.22.764.142 I slot print_timing: id 0 | task 12443 | total time = 1110.35 ms / 606 tokens 2.22.764.143 I slot print_timing: id 0 | task 12443 | graphs reused = 11766 2.22.764.144 I slot print_timing: id 0 | task 12443 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.764.176 I slot release: id 0 | task 12443 | stop processing: n_tokens = 637, truncated = 0 2.22.783.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 142666401 2.22.783.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.22.856.275 I slot launch_slot_: id 0 | task 12552 | processing task, is_child = 0 2.24.919.138 I slot print_timing: id 0 | task 12552 | prompt eval time = 158.92 ms / 776 tokens ( 0.20 ms per token, 4883.05 tokens per second) 2.24.919.144 I slot print_timing: id 0 | task 12552 | eval time = 1903.92 ms / 209 tokens ( 9.15 ms per token, 109.25 tokens per second) 2.24.919.145 I slot print_timing: id 0 | task 12552 | total time = 2062.84 ms / 985 tokens 2.24.919.145 I slot print_timing: id 0 | task 12552 | graphs reused = 11973 2.24.919.146 I slot print_timing: id 0 | task 12552 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.919.187 I slot release: id 0 | task 12552 | stop processing: n_tokens = 1016, truncated = 0 2.24.941.387 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 144821412 2.24.941.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.25.023.622 I slot launch_slot_: id 0 | task 12765 | processing task, is_child = 0 2.26.962.927 I slot print_timing: id 0 | task 12765 | prompt eval time = 133.11 ms / 504 tokens ( 0.26 ms per token, 3786.40 tokens per second) 2.26.962.934 I slot print_timing: id 0 | task 12765 | eval time = 1806.17 ms / 197 tokens ( 9.22 ms per token, 108.52 tokens per second) 2.26.962.936 I slot print_timing: id 0 | task 12765 | total time = 1939.28 ms / 701 tokens 2.26.962.937 I slot print_timing: id 0 | task 12765 | graphs reused = 12168 2.26.962.937 I slot print_timing: id 0 | task 12765 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.962.974 I slot release: id 0 | task 12765 | stop processing: n_tokens = 732, truncated = 0 2.26.987.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 146865198 2.26.987.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.27.060.347 I slot launch_slot_: id 0 | task 12965 | processing task, is_child = 0 2.29.089.944 I slot print_timing: id 0 | task 12965 | prompt eval time = 144.79 ms / 633 tokens ( 0.23 ms per token, 4371.88 tokens per second) 2.29.089.950 I slot print_timing: id 0 | task 12965 | eval time = 1884.79 ms / 207 tokens ( 9.15 ms per token, 109.30 tokens per second) 2.29.089.951 I slot print_timing: id 0 | task 12965 | total time = 2029.58 ms / 840 tokens 2.29.089.952 I slot print_timing: id 0 | task 12965 | graphs reused = 12372 2.29.089.952 I slot print_timing: id 0 | task 12965 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.089.989 I slot release: id 0 | task 12965 | stop processing: n_tokens = 871, truncated = 0 2.29.114.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 148992214 2.29.114.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.366 MiB) 2.29.201.414 I slot launch_slot_: id 0 | task 13176 | processing task, is_child = 0 2.30.531.265 I slot print_timing: id 0 | task 13176 | prompt eval time = 124.31 ms / 395 tokens ( 0.31 ms per token, 3177.54 tokens per second) 2.30.531.271 I slot print_timing: id 0 | task 13176 | eval time = 1205.52 ms / 134 tokens ( 9.06 ms per token, 110.33 tokens per second) 2.30.531.272 I slot print_timing: id 0 | task 13176 | total time = 1329.83 ms / 529 tokens 2.30.531.272 I slot print_timing: id 0 | task 13176 | graphs reused = 12503 2.30.531.273 I slot print_timing: id 0 | task 13176 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.531.301 I slot release: id 0 | task 13176 | stop processing: n_tokens = 560, truncated = 0 2.30.549.210 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 150433525 2.30.549.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.30.623.357 I slot launch_slot_: id 0 | task 13313 | processing task, is_child = 0 2.32.638.326 I slot print_timing: id 0 | task 13313 | prompt eval time = 137.73 ms / 584 tokens ( 0.24 ms per token, 4240.27 tokens per second) 2.32.638.332 I slot print_timing: id 0 | task 13313 | eval time = 1877.22 ms / 209 tokens ( 9.03 ms per token, 110.80 tokens per second) 2.32.638.333 I slot print_timing: id 0 | task 13313 | total time = 2014.95 ms / 793 tokens 2.32.638.334 I slot print_timing: id 0 | task 13313 | graphs reused = 12709 2.32.638.334 I slot print_timing: id 0 | task 13313 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.638.371 I slot release: id 0 | task 13313 | stop processing: n_tokens = 824, truncated = 0 2.32.656.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 152540595 2.32.656.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.32.745.288 I slot launch_slot_: id 0 | task 13526 | processing task, is_child = 0 2.34.965.809 I slot print_timing: id 0 | task 13526 | prompt eval time = 152.59 ms / 695 tokens ( 0.22 ms per token, 4554.72 tokens per second) 2.34.965.814 I slot print_timing: id 0 | task 13526 | eval time = 2067.91 ms / 230 tokens ( 9.03 ms per token, 110.74 tokens per second) 2.34.965.815 I slot print_timing: id 0 | task 13526 | total time = 2220.50 ms / 925 tokens 2.34.965.816 I slot print_timing: id 0 | task 13526 | graphs reused = 12936 2.34.965.817 I slot print_timing: id 0 | task 13526 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.965.854 I slot release: id 0 | task 13526 | stop processing: n_tokens = 956, truncated = 0 2.34.988.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 154868079 2.34.988.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.35.065.405 I slot launch_slot_: id 0 | task 13760 | processing task, is_child = 0 2.36.935.697 I slot print_timing: id 0 | task 13760 | prompt eval time = 158.08 ms / 769 tokens ( 0.21 ms per token, 4864.53 tokens per second) 2.36.935.703 I slot print_timing: id 0 | task 13760 | eval time = 1712.19 ms / 191 tokens ( 9.01 ms per token, 110.97 tokens per second) 2.36.935.704 I slot print_timing: id 0 | task 13760 | total time = 1870.27 ms / 960 tokens 2.36.935.704 I slot print_timing: id 0 | task 13760 | graphs reused = 13125 2.36.935.705 I slot print_timing: id 0 | task 13760 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.935.744 I slot release: id 0 | task 13760 | stop processing: n_tokens = 991, truncated = 0 2.36.955.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 156837968 2.36.955.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.36.973.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.37.047.205 I slot launch_slot_: id 0 | task 13955 | processing task, is_child = 0 2.38.294.907 I slot print_timing: id 0 | task 13955 | prompt eval time = 138.36 ms / 576 tokens ( 0.24 ms per token, 4163.11 tokens per second) 2.38.294.912 I slot print_timing: id 0 | task 13955 | eval time = 1109.33 ms / 124 tokens ( 9.02 ms per token, 110.88 tokens per second) 2.38.294.914 I slot print_timing: id 0 | task 13955 | total time = 1247.68 ms / 700 tokens 2.38.294.915 I slot print_timing: id 0 | task 13955 | graphs reused = 13247 2.38.294.915 I slot print_timing: id 0 | task 13955 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.294.951 I slot release: id 0 | task 13955 | stop processing: n_tokens = 731, truncated = 0 2.38.318.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 158197175 2.38.318.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.38.391.880 I slot launch_slot_: id 0 | task 14083 | processing task, is_child = 0 2.41.010.453 I slot print_timing: id 0 | task 14083 | prompt eval time = 147.13 ms / 655 tokens ( 0.22 ms per token, 4451.94 tokens per second) 2.41.010.459 I slot print_timing: id 0 | task 14083 | eval time = 2471.43 ms / 275 tokens ( 9.02 ms per token, 110.87 tokens per second) 2.41.010.459 I slot print_timing: id 0 | task 14083 | total time = 2618.55 ms / 930 tokens 2.41.010.460 I slot print_timing: id 0 | task 14083 | graphs reused = 13519 2.41.010.461 I slot print_timing: id 0 | task 14083 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.010.499 I slot release: id 0 | task 14083 | stop processing: n_tokens = 961, truncated = 0 2.41.029.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 160912724 2.41.029.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.41.105.715 I slot launch_slot_: id 0 | task 14362 | processing task, is_child = 0 2.42.338.270 I slot print_timing: id 0 | task 14362 | prompt eval time = 144.57 ms / 621 tokens ( 0.23 ms per token, 4295.47 tokens per second) 2.42.338.276 I slot print_timing: id 0 | task 14362 | eval time = 1087.96 ms / 121 tokens ( 9.07 ms per token, 110.30 tokens per second) 2.42.338.277 I slot print_timing: id 0 | task 14362 | total time = 1232.54 ms / 742 tokens 2.42.338.278 I slot print_timing: id 0 | task 14362 | graphs reused = 13637 2.42.338.279 I slot print_timing: id 0 | task 14362 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.338.315 I slot release: id 0 | task 14362 | stop processing: n_tokens = 773, truncated = 0 2.42.353.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 162240540 2.42.353.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.42.439.993 I slot launch_slot_: id 0 | task 14487 | processing task, is_child = 0 2.44.219.214 I slot print_timing: id 0 | task 14487 | prompt eval time = 155.75 ms / 767 tokens ( 0.20 ms per token, 4924.53 tokens per second) 2.44.219.220 I slot print_timing: id 0 | task 14487 | eval time = 1623.45 ms / 178 tokens ( 9.17 ms per token, 109.03 tokens per second) 2.44.219.221 I slot print_timing: id 0 | task 14487 | total time = 1779.20 ms / 945 tokens 2.44.219.222 I slot print_timing: id 0 | task 14487 | graphs reused = 13813 2.44.219.222 I slot print_timing: id 0 | task 14487 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.219.266 I slot release: id 0 | task 14487 | stop processing: n_tokens = 976, truncated = 0 2.44.239.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 164121490 2.44.239.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.44.330.830 I slot launch_slot_: id 0 | task 14669 | processing task, is_child = 0 2.46.356.245 I slot print_timing: id 0 | task 14669 | prompt eval time = 170.33 ms / 864 tokens ( 0.20 ms per token, 5072.63 tokens per second) 2.46.356.251 I slot print_timing: id 0 | task 14669 | eval time = 1855.07 ms / 203 tokens ( 9.18 ms per token, 108.89 tokens per second) 2.46.356.252 I slot print_timing: id 0 | task 14669 | total time = 2025.39 ms / 1067 tokens 2.46.356.253 I slot print_timing: id 0 | task 14669 | graphs reused = 14013 2.46.356.254 I slot print_timing: id 0 | task 14669 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.356.298 I slot release: id 0 | task 14669 | stop processing: n_tokens = 1098, truncated = 0 2.46.378.105 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 166258523 2.46.378.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.46.396.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.46.502.337 I slot launch_slot_: id 0 | task 14876 | processing task, is_child = 0 2.47.813.815 I slot print_timing: id 0 | task 14876 | prompt eval time = 150.70 ms / 646 tokens ( 0.23 ms per token, 4286.69 tokens per second) 2.47.813.820 I slot print_timing: id 0 | task 14876 | eval time = 1160.76 ms / 129 tokens ( 9.07 ms per token, 110.27 tokens per second) 2.47.813.821 I slot print_timing: id 0 | task 14876 | total time = 1311.46 ms / 775 tokens 2.47.813.822 I slot print_timing: id 0 | task 14876 | graphs reused = 14139 2.47.813.823 I slot print_timing: id 0 | task 14876 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.813.861 I slot release: id 0 | task 14876 | stop processing: n_tokens = 806, truncated = 0 2.47.841.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 167716085 2.47.841.465 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.47.922.113 I slot launch_slot_: id 0 | task 15009 | processing task, is_child = 0 2.50.101.457 I slot print_timing: id 0 | task 15009 | prompt eval time = 153.94 ms / 720 tokens ( 0.21 ms per token, 4677.15 tokens per second) 2.50.101.463 I slot print_timing: id 0 | task 15009 | eval time = 2025.38 ms / 219 tokens ( 9.29 ms per token, 107.63 tokens per second) 2.50.101.464 I slot print_timing: id 0 | task 15009 | total time = 2179.32 ms / 939 tokens 2.50.101.465 I slot print_timing: id 0 | task 15009 | graphs reused = 14355 2.50.101.465 I slot print_timing: id 0 | task 15009 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.101.507 I slot release: id 0 | task 15009 | stop processing: n_tokens = 970, truncated = 0 2.50.127.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 170003731 2.50.127.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.50.211.066 I slot launch_slot_: id 0 | task 15232 | processing task, is_child = 0 2.52.262.391 I slot print_timing: id 0 | task 15232 | prompt eval time = 133.76 ms / 509 tokens ( 0.26 ms per token, 3805.24 tokens per second) 2.52.262.398 I slot print_timing: id 0 | task 15232 | eval time = 1917.54 ms / 214 tokens ( 9.00 ms per token, 111.08 tokens per second) 2.52.262.399 I slot print_timing: id 0 | task 15232 | total time = 2051.30 ms / 723 tokens 2.52.262.400 I slot print_timing: id 0 | task 15232 | graphs reused = 14567 2.52.262.401 I slot print_timing: id 0 | task 15232 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.262.437 I slot release: id 0 | task 15232 | stop processing: n_tokens = 754, truncated = 0 2.52.277.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 172164662 2.52.277.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.52.348.801 I slot launch_slot_: id 0 | task 15449 | processing task, is_child = 0 2.54.662.304 I slot print_timing: id 0 | task 15449 | prompt eval time = 136.84 ms / 581 tokens ( 0.24 ms per token, 4245.93 tokens per second) 2.54.662.309 I slot print_timing: id 0 | task 15449 | eval time = 2176.65 ms / 242 tokens ( 9.03 ms per token, 110.72 tokens per second) 2.54.662.310 I slot print_timing: id 0 | task 15449 | total time = 2313.48 ms / 823 tokens 2.54.662.311 I slot print_timing: id 0 | task 15449 | graphs reused = 14806 2.54.662.312 I slot print_timing: id 0 | task 15449 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.662.348 I slot release: id 0 | task 15449 | stop processing: n_tokens = 854, truncated = 0 2.54.690.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 174564573 2.54.690.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.54.782.426 I slot launch_slot_: id 0 | task 15695 | processing task, is_child = 0 2.56.939.968 I slot print_timing: id 0 | task 15695 | prompt eval time = 176.86 ms / 925 tokens ( 0.19 ms per token, 5230.16 tokens per second) 2.56.939.974 I slot print_timing: id 0 | task 15695 | eval time = 1980.66 ms / 220 tokens ( 9.04 ms per token, 110.57 tokens per second) 2.56.939.975 I slot print_timing: id 0 | task 15695 | total time = 2157.52 ms / 1145 tokens 2.56.939.975 I slot print_timing: id 0 | task 15695 | graphs reused = 15023 2.56.939.976 I slot print_timing: id 0 | task 15695 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.940.024 I slot release: id 0 | task 15695 | stop processing: n_tokens = 1176, truncated = 0 2.56.961.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 176842249 2.56.961.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.57.058.398 I slot launch_slot_: id 0 | task 15919 | processing task, is_child = 0 2.59.461.130 I slot print_timing: id 0 | task 15919 | prompt eval time = 169.29 ms / 885 tokens ( 0.19 ms per token, 5227.81 tokens per second) 2.59.461.136 I slot print_timing: id 0 | task 15919 | eval time = 2233.43 ms / 245 tokens ( 9.15 ms per token, 109.25 tokens per second) 2.59.461.137 I slot print_timing: id 0 | task 15919 | total time = 2402.71 ms / 1130 tokens 2.59.461.138 I slot print_timing: id 0 | task 15919 | graphs reused = 15265 2.59.461.139 I slot print_timing: id 0 | task 15919 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.461.185 I slot release: id 0 | task 15919 | stop processing: n_tokens = 1161, truncated = 0 2.59.485.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 179363409 2.59.485.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.59.595.022 I slot launch_slot_: id 0 | task 16168 | processing task, is_child = 0 3.00.923.310 I slot print_timing: id 0 | task 16168 | prompt eval time = 119.00 ms / 392 tokens ( 0.30 ms per token, 3294.12 tokens per second) 3.00.923.316 I slot print_timing: id 0 | task 16168 | eval time = 1209.27 ms / 135 tokens ( 9.02 ms per token, 110.81 tokens per second) 3.00.923.317 I slot print_timing: id 0 | task 16168 | total time = 1328.27 ms / 527 tokens 3.00.923.319 I slot print_timing: id 0 | task 16168 | graphs reused = 15397 3.00.923.320 I slot print_timing: id 0 | task 16168 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.923.351 I slot release: id 0 | task 16168 | stop processing: n_tokens = 558, truncated = 0 3.00.938.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 180825575 3.00.938.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.01.023.426 I slot launch_slot_: id 0 | task 16306 | processing task, is_child = 0 3.01.597.973 I slot print_timing: id 0 | task 16306 | prompt eval time = 112.33 ms / 331 tokens ( 0.34 ms per token, 2946.75 tokens per second) 3.01.597.978 I slot print_timing: id 0 | task 16306 | eval time = 462.20 ms / 52 tokens ( 9.06 ms per token, 110.34 tokens per second) 3.01.597.979 I slot print_timing: id 0 | task 16306 | total time = 574.53 ms / 383 tokens 3.01.597.980 I slot print_timing: id 0 | task 16306 | graphs reused = 15447 3.01.597.981 I slot print_timing: id 0 | task 16306 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.598.009 I slot release: id 0 | task 16306 | stop processing: n_tokens = 414, truncated = 0 3.01.622.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 181500233 3.01.622.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.01.702.088 I slot launch_slot_: id 0 | task 16361 | processing task, is_child = 0 3.02.971.479 I slot print_timing: id 0 | task 16361 | prompt eval time = 113.40 ms / 357 tokens ( 0.32 ms per token, 3148.20 tokens per second) 3.02.971.485 I slot print_timing: id 0 | task 16361 | eval time = 1155.97 ms / 129 tokens ( 9.03 ms per token, 110.73 tokens per second) 3.02.971.486 I slot print_timing: id 0 | task 16361 | total time = 1269.37 ms / 486 tokens 3.02.971.486 I slot print_timing: id 0 | task 16361 | graphs reused = 15573 3.02.971.487 I slot print_timing: id 0 | task 16361 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.971.515 I slot release: id 0 | task 16361 | stop processing: n_tokens = 517, truncated = 0 3.02.975.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 182873739 3.02.975.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.739 MiB) 3.03.051.322 I slot launch_slot_: id 0 | task 16493 | processing task, is_child = 0 3.03.589.277 I slot print_timing: id 0 | task 16493 | prompt eval time = 112.34 ms / 315 tokens ( 0.36 ms per token, 2804.06 tokens per second) 3.03.589.282 I slot print_timing: id 0 | task 16493 | eval time = 425.60 ms / 48 tokens ( 9.06 ms per token, 110.43 tokens per second) 3.03.589.284 I slot print_timing: id 0 | task 16493 | total time = 537.94 ms / 363 tokens 3.03.589.285 I slot print_timing: id 0 | task 16493 | graphs reused = 15619 3.03.589.285 I slot print_timing: id 0 | task 16493 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.589.311 I slot release: id 0 | task 16493 | stop processing: n_tokens = 394, truncated = 0 3.03.606.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 183491536 3.03.606.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.03.675.191 I slot launch_slot_: id 0 | task 16544 | processing task, is_child = 0 3.04.322.992 I slot print_timing: id 0 | task 16544 | prompt eval time = 114.39 ms / 378 tokens ( 0.30 ms per token, 3304.51 tokens per second) 3.04.322.997 I slot print_timing: id 0 | task 16544 | eval time = 533.39 ms / 60 tokens ( 9.04 ms per token, 110.61 tokens per second) 3.04.322.998 I slot print_timing: id 0 | task 16544 | total time = 647.78 ms / 438 tokens 3.04.322.999 I slot print_timing: id 0 | task 16544 | graphs reused = 15677 3.04.323.000 I slot print_timing: id 0 | task 16544 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.323.029 I slot release: id 0 | task 16544 | stop processing: n_tokens = 469, truncated = 0 3.04.348.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 184225254 3.04.348.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.04.419.628 I slot launch_slot_: id 0 | task 16607 | processing task, is_child = 0 3.04.784.704 I slot print_timing: id 0 | task 16607 | prompt eval time = 109.63 ms / 295 tokens ( 0.37 ms per token, 2690.87 tokens per second) 3.04.784.710 I slot print_timing: id 0 | task 16607 | eval time = 255.43 ms / 28 tokens ( 9.46 ms per token, 105.71 tokens per second) 3.04.784.711 I slot print_timing: id 0 | task 16607 | total time = 365.06 ms / 323 tokens 3.04.784.712 I slot print_timing: id 0 | task 16607 | graphs reused = 15703 3.04.784.712 I slot print_timing: id 0 | task 16607 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.784.741 I slot release: id 0 | task 16607 | stop processing: n_tokens = 354, truncated = 0 3.04.798.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 184686966 3.04.798.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.04.871.762 I slot launch_slot_: id 0 | task 16638 | processing task, is_child = 0 3.05.856.696 I slot print_timing: id 0 | task 16638 | prompt eval time = 113.42 ms / 337 tokens ( 0.34 ms per token, 2971.39 tokens per second) 3.05.856.703 I slot print_timing: id 0 | task 16638 | eval time = 871.49 ms / 95 tokens ( 9.27 ms per token, 107.86 tokens per second) 3.05.856.705 I slot print_timing: id 0 | task 16638 | total time = 984.91 ms / 432 tokens 3.05.856.706 I slot print_timing: id 0 | task 16638 | graphs reused = 15796 3.05.856.706 I slot print_timing: id 0 | task 16638 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.856.739 I slot release: id 0 | task 16638 | stop processing: n_tokens = 463, truncated = 0 3.05.884.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 185758963 3.05.927.873 I slot launch_slot_: id 0 | task 16736 | processing task, is_child = 0 3.06.524.997 I slot print_timing: id 0 | task 16736 | prompt eval time = 114.61 ms / 325 tokens ( 0.35 ms per token, 2835.75 tokens per second) 3.06.525.003 I slot print_timing: id 0 | task 16736 | eval time = 482.50 ms / 53 tokens ( 9.28 ms per token, 107.77 tokens per second) 3.06.525.004 I slot print_timing: id 0 | task 16736 | total time = 597.10 ms / 378 tokens 3.06.525.004 I slot print_timing: id 0 | task 16736 | graphs reused = 15847 3.06.525.005 I slot print_timing: id 0 | task 16736 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.525.035 I slot release: id 0 | task 16736 | stop processing: n_tokens = 409, truncated = 0 3.06.539.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.078 3.06.539.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.06.616.169 I slot launch_slot_: id 0 | task 16792 | processing task, is_child = 0 3.09.235.062 I slot print_timing: id 0 | task 16792 | prompt eval time = 103.80 ms / 264 tokens ( 0.39 ms per token, 2543.33 tokens per second) 3.09.235.068 I slot print_timing: id 0 | task 16792 | eval time = 2515.07 ms / 276 tokens ( 9.15 ms per token, 109.34 tokens per second) 3.09.235.069 I slot print_timing: id 0 | task 16792 | total time = 2618.87 ms / 540 tokens 3.09.235.069 I slot print_timing: id 0 | task 16792 | graphs reused = 16120 3.09.235.070 I slot print_timing: id 0 | task 16792 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.235.096 I slot release: id 0 | task 16792 | stop processing: n_tokens = 571, truncated = 0 3.09.252.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 571, t_last = 189137320 3.09.252.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.09.334.952 I slot launch_slot_: id 0 | task 17071 | processing task, is_child = 0 3.09.529.469 I slot print_timing: id 0 | task 17071 | prompt eval time = 115.23 ms / 331 tokens ( 0.35 ms per token, 2872.57 tokens per second) 3.09.529.475 I slot print_timing: id 0 | task 17071 | eval time = 79.27 ms / 9 tokens ( 9.91 ms per token, 100.92 tokens per second) 3.09.529.476 I slot print_timing: id 0 | task 17071 | total time = 194.50 ms / 340 tokens 3.09.529.477 I slot print_timing: id 0 | task 17071 | graphs reused = 16127 3.09.529.478 I slot print_timing: id 0 | task 17071 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.529.506 I slot release: id 0 | task 17071 | stop processing: n_tokens = 371, truncated = 0 3.09.548.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 371, t_last = 189431730 3.09.548.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.09.630.611 I slot launch_slot_: id 0 | task 17083 | processing task, is_child = 0 3.10.392.993 I slot print_timing: id 0 | task 17083 | prompt eval time = 114.95 ms / 333 tokens ( 0.35 ms per token, 2896.86 tokens per second) 3.10.392.999 I slot print_timing: id 0 | task 17083 | eval time = 647.41 ms / 71 tokens ( 9.25 ms per token, 108.12 tokens per second) 3.10.393.000 I slot print_timing: id 0 | task 17083 | total time = 762.36 ms / 404 tokens 3.10.393.001 I slot print_timing: id 0 | task 17083 | graphs reused = 16196 3.10.393.002 I slot print_timing: id 0 | task 17083 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.393.030 I slot release: id 0 | task 17083 | stop processing: n_tokens = 435, truncated = 0 3.10.408.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 190295254 3.10.408.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.10.480.733 I slot launch_slot_: id 0 | task 17157 | processing task, is_child = 0 3.13.598.225 I slot print_timing: id 0 | task 17157 | n_gen = 330, tg = 109.49 t/s, tg_3s = 109.83 t/s 3.16.601.327 I slot print_timing: id 0 | task 17157 | n_gen = 663, tg = 110.19 t/s, tg_3s = 110.89 t/s 3.16.727.059 I slot print_timing: id 0 | task 17157 | prompt eval time = 112.71 ms / 346 tokens ( 0.33 ms per token, 3069.80 tokens per second) 3.16.727.064 I slot print_timing: id 0 | task 17157 | eval time = 6133.60 ms / 677 tokens ( 9.07 ms per token, 110.21 tokens per second) 3.16.727.065 I slot print_timing: id 0 | task 17157 | total time = 6246.31 ms / 1023 tokens 3.16.727.066 I slot print_timing: id 0 | task 17157 | graphs reused = 16868 3.16.727.067 I slot print_timing: id 0 | task 17157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.727.094 I slot release: id 0 | task 17157 | stop processing: n_tokens = 1054, truncated = 0 3.16.753.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1054, t_last = 196629319 3.16.754.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.16.816.884 I slot launch_slot_: id 0 | task 17837 | processing task, is_child = 0 3.17.278.497 I slot print_timing: id 0 | task 17837 | prompt eval time = 108.03 ms / 325 tokens ( 0.33 ms per token, 3008.28 tokens per second) 3.17.278.503 I slot print_timing: id 0 | task 17837 | eval time = 353.56 ms / 40 tokens ( 9.07 ms per token, 110.31 tokens per second) 3.17.278.504 I slot print_timing: id 0 | task 17837 | total time = 461.59 ms / 365 tokens 3.17.278.505 I slot print_timing: id 0 | task 17837 | graphs reused = 16906 3.17.278.506 I slot print_timing: id 0 | task 17837 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.278.536 I slot release: id 0 | task 17837 | stop processing: n_tokens = 396, truncated = 0 3.17.298.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 197180761 3.17.299.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.17.370.762 I slot launch_slot_: id 0 | task 17880 | processing task, is_child = 0 3.19.308.650 I slot print_timing: id 0 | task 17880 | prompt eval time = 109.60 ms / 322 tokens ( 0.34 ms per token, 2937.96 tokens per second) 3.19.308.655 I slot print_timing: id 0 | task 17880 | eval time = 1828.27 ms / 204 tokens ( 9.01 ms per token, 111.03 tokens per second) 3.19.308.656 I slot print_timing: id 0 | task 17880 | total time = 1937.87 ms / 526 tokens 3.19.308.657 I slot print_timing: id 0 | task 17880 | graphs reused = 17107 3.19.308.658 I slot print_timing: id 0 | task 17880 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.308.685 I slot release: id 0 | task 17880 | stop processing: n_tokens = 557, truncated = 0 3.19.329.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 199210910 3.19.329.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.19.399.682 I slot launch_slot_: id 0 | task 18087 | processing task, is_child = 0 3.22.182.068 I slot print_timing: id 0 | task 18087 | prompt eval time = 109.55 ms / 338 tokens ( 0.32 ms per token, 3085.24 tokens per second) 3.22.182.073 I slot print_timing: id 0 | task 18087 | eval time = 2672.81 ms / 298 tokens ( 9.00 ms per token, 111.12 tokens per second) 3.22.182.075 I slot print_timing: id 0 | task 18087 | total time = 2782.37 ms / 636 tokens 3.22.182.075 I slot print_timing: id 0 | task 18087 | graphs reused = 17402 3.22.182.076 I slot print_timing: id 0 | task 18087 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.182.106 I slot release: id 0 | task 18087 | stop processing: n_tokens = 667, truncated = 0 3.22.210.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 667, t_last = 202084331 3.22.254.362 I slot launch_slot_: id 0 | task 18388 | processing task, is_child = 0 3.25.367.067 I slot print_timing: id 0 | task 18388 | n_gen = 335, tg = 111.23 t/s, tg_3s = 111.56 t/s 3.28.375.283 I slot print_timing: id 0 | task 18388 | n_gen = 669, tg = 111.13 t/s, tg_3s = 111.03 t/s 3.31.381.783 I slot print_timing: id 0 | task 18388 | n_gen = 1002, tg = 111.01 t/s, tg_3s = 110.76 t/s 3.31.579.923 I slot print_timing: id 0 | task 18388 | prompt eval time = 109.81 ms / 347 tokens ( 0.32 ms per token, 3160.06 tokens per second) 3.31.579.929 I slot print_timing: id 0 | task 18388 | eval time = 9215.73 ms / 1024 tokens ( 9.01 ms per token, 111.01 tokens per second) 3.31.579.929 I slot print_timing: id 0 | task 18388 | total time = 9325.54 ms / 1371 tokens 3.31.579.931 I slot print_timing: id 0 | task 18388 | graphs reused = 18420 3.31.579.931 I slot print_timing: id 0 | task 18388 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.579.960 I slot release: id 0 | task 18388 | stop processing: n_tokens = 1402, truncated = 0 3.31.607.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 211482184 3.31.607.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.31.700.113 I slot launch_slot_: id 0 | task 19415 | processing task, is_child = 0 3.33.417.959 I slot print_timing: id 0 | task 19415 | prompt eval time = 112.07 ms / 331 tokens ( 0.34 ms per token, 2953.41 tokens per second) 3.33.417.965 I slot print_timing: id 0 | task 19415 | eval time = 1605.75 ms / 179 tokens ( 9.02 ms per token, 110.85 tokens per second) 3.33.417.966 I slot print_timing: id 0 | task 19415 | total time = 1717.83 ms / 510 tokens 3.33.417.967 I slot print_timing: id 0 | task 19415 | graphs reused = 18596 3.33.417.968 I slot print_timing: id 0 | task 19415 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.417.995 I slot release: id 0 | task 19415 | stop processing: n_tokens = 541, truncated = 0 3.33.440.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 213320220 3.33.440.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 3.33.519.921 I slot launch_slot_: id 0 | task 19597 | processing task, is_child = 0 3.33.978.772 I slot print_timing: id 0 | task 19597 | prompt eval time = 114.19 ms / 345 tokens ( 0.33 ms per token, 3021.39 tokens per second) 3.33.978.778 I slot print_timing: id 0 | task 19597 | eval time = 344.65 ms / 39 tokens ( 9.07 ms per token, 110.26 tokens per second) 3.33.978.779 I slot print_timing: id 0 | task 19597 | total time = 458.83 ms / 384 tokens 3.33.978.780 I slot print_timing: id 0 | task 19597 | graphs reused = 18633 3.33.978.780 I slot print_timing: id 0 | task 19597 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.978.807 I slot release: id 0 | task 19597 | stop processing: n_tokens = 415, truncated = 0 3.34.000.710 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 213881032 3.34.000.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.34.073.352 I slot launch_slot_: id 0 | task 19639 | processing task, is_child = 0 3.34.727.857 I slot print_timing: id 0 | task 19639 | prompt eval time = 112.67 ms / 320 tokens ( 0.35 ms per token, 2840.18 tokens per second) 3.34.727.863 I slot print_timing: id 0 | task 19639 | eval time = 541.82 ms / 61 tokens ( 9.03 ms per token, 110.74 tokens per second) 3.34.727.864 I slot print_timing: id 0 | task 19639 | total time = 654.49 ms / 381 tokens 3.34.727.865 I slot print_timing: id 0 | task 19639 | graphs reused = 18692 3.34.727.866 I slot print_timing: id 0 | task 19639 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.727.893 I slot release: id 0 | task 19639 | stop processing: n_tokens = 412, truncated = 0 3.34.751.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 214630118 3.34.751.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.34.822.411 I slot launch_slot_: id 0 | task 19703 | processing task, is_child = 0 3.35.376.907 I slot print_timing: id 0 | task 19703 | prompt eval time = 103.98 ms / 297 tokens ( 0.35 ms per token, 2856.40 tokens per second) 3.35.376.913 I slot print_timing: id 0 | task 19703 | eval time = 450.50 ms / 47 tokens ( 9.79 ms per token, 102.11 tokens per second) 3.35.376.914 I slot print_timing: id 0 | task 19703 | total time = 554.48 ms / 344 tokens 3.35.376.915 I slot print_timing: id 0 | task 19703 | graphs reused = 18737 3.35.376.916 I slot print_timing: id 0 | task 19703 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.376.943 I slot release: id 0 | task 19703 | stop processing: n_tokens = 375, truncated = 0 3.35.405.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 215279167 3.35.405.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.35.479.584 I slot launch_slot_: id 0 | task 19753 | processing task, is_child = 0 3.36.582.599 I slot print_timing: id 0 | task 19753 | prompt eval time = 112.70 ms / 343 tokens ( 0.33 ms per token, 3043.59 tokens per second) 3.36.582.605 I slot print_timing: id 0 | task 19753 | eval time = 990.30 ms / 111 tokens ( 9.00 ms per token, 111.08 tokens per second) 3.36.582.606 I slot print_timing: id 0 | task 19753 | total time = 1103.00 ms / 454 tokens 3.36.582.607 I slot print_timing: id 0 | task 19753 | graphs reused = 18846 3.36.582.608 I slot print_timing: id 0 | task 19753 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.582.637 I slot release: id 0 | task 19753 | stop processing: n_tokens = 485, truncated = 0 3.36.604.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 216484862 3.36.648.022 I slot launch_slot_: id 0 | task 19867 | processing task, is_child = 0 3.37.945.739 I slot print_timing: id 0 | task 19867 | prompt eval time = 113.58 ms / 371 tokens ( 0.31 ms per token, 3266.36 tokens per second) 3.37.945.744 I slot print_timing: id 0 | task 19867 | eval time = 1184.11 ms / 132 tokens ( 9.04 ms per token, 110.63 tokens per second) 3.37.945.745 I slot print_timing: id 0 | task 19867 | total time = 1297.70 ms / 503 tokens 3.37.945.746 I slot print_timing: id 0 | task 19867 | graphs reused = 18975 3.37.945.747 I slot print_timing: id 0 | task 19867 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.945.775 I slot release: id 0 | task 19867 | stop processing: n_tokens = 534, truncated = 0 3.37.965.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 217847999 3.37.965.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.38.045.152 I slot launch_slot_: id 0 | task 20002 | processing task, is_child = 0 3.39.447.477 I slot print_timing: id 0 | task 20002 | prompt eval time = 108.34 ms / 292 tokens ( 0.37 ms per token, 2695.29 tokens per second) 3.39.447.483 I slot print_timing: id 0 | task 20002 | eval time = 1293.97 ms / 145 tokens ( 8.99 ms per token, 111.29 tokens per second) 3.39.447.484 I slot print_timing: id 0 | task 20002 | total time = 1402.31 ms / 437 tokens 3.39.447.484 I slot print_timing: id 0 | task 20002 | graphs reused = 19118 3.39.447.485 I slot print_timing: id 0 | task 20002 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.447.510 I slot release: id 0 | task 20002 | stop processing: n_tokens = 468, truncated = 0 3.39.472.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 219349735 3.39.472.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.39.555.922 I slot launch_slot_: id 0 | task 20150 | processing task, is_child = 0 3.40.225.575 I slot print_timing: id 0 | task 20150 | prompt eval time = 109.61 ms / 301 tokens ( 0.36 ms per token, 2746.05 tokens per second) 3.40.225.580 I slot print_timing: id 0 | task 20150 | eval time = 560.02 ms / 63 tokens ( 9.03 ms per token, 110.71 tokens per second) 3.40.225.582 I slot print_timing: id 0 | task 20150 | total time = 669.63 ms / 364 tokens 3.40.225.583 I slot print_timing: id 0 | task 20150 | graphs reused = 19179 3.40.225.583 I slot print_timing: id 0 | task 20150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.225.611 I slot release: id 0 | task 20150 | stop processing: n_tokens = 395, truncated = 0 3.40.250.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 220127836 3.40.250.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 3.40.328.766 I slot launch_slot_: id 0 | task 20216 | processing task, is_child = 0 3.42.534.669 I slot print_timing: id 0 | task 20216 | prompt eval time = 109.36 ms / 303 tokens ( 0.36 ms per token, 2770.62 tokens per second) 3.42.534.675 I slot print_timing: id 0 | task 20216 | eval time = 2096.52 ms / 234 tokens ( 9.00 ms per token, 111.14 tokens per second) 3.42.534.676 I slot print_timing: id 0 | task 20216 | total time = 2205.88 ms / 537 tokens 3.42.534.677 I slot print_timing: id 0 | task 20216 | graphs reused = 19410 3.42.534.678 I slot print_timing: id 0 | task 20216 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.534.705 I slot release: id 0 | task 20216 | stop processing: n_tokens = 568, truncated = 0 3.42.538.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 568, t_last = 222436929 3.42.538.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 3.42.613.406 I slot launch_slot_: id 0 | task 20453 | processing task, is_child = 0 3.43.169.501 I slot print_timing: id 0 | task 20453 | prompt eval time = 112.88 ms / 321 tokens ( 0.35 ms per token, 2843.65 tokens per second) 3.43.169.506 I slot print_timing: id 0 | task 20453 | eval time = 443.19 ms / 50 tokens ( 9.04 ms per token, 110.56 tokens per second) 3.43.169.507 I slot print_timing: id 0 | task 20453 | total time = 556.08 ms / 371 tokens 3.43.169.508 I slot print_timing: id 0 | task 20453 | graphs reused = 19458 3.43.169.509 I slot print_timing: id 0 | task 20453 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.169.536 I slot release: id 0 | task 20453 | stop processing: n_tokens = 402, truncated = 0 3.43.193.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 223071760 3.43.193.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.43.259.904 I slot launch_slot_: id 0 | task 20506 | processing task, is_child = 0 3.43.900.736 I slot print_timing: id 0 | task 20506 | prompt eval time = 110.90 ms / 322 tokens ( 0.34 ms per token, 2903.62 tokens per second) 3.43.900.742 I slot print_timing: id 0 | task 20506 | eval time = 529.91 ms / 59 tokens ( 9.14 ms per token, 109.45 tokens per second) 3.43.900.744 I slot print_timing: id 0 | task 20506 | total time = 640.81 ms / 381 tokens 3.43.900.745 I slot print_timing: id 0 | task 20506 | graphs reused = 19515 3.43.900.746 I slot print_timing: id 0 | task 20506 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.900.776 I slot release: id 0 | task 20506 | stop processing: n_tokens = 412, truncated = 0 3.43.914.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 223803001 3.43.914.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.451 MiB) 3.43.981.265 I slot launch_slot_: id 0 | task 20568 | processing task, is_child = 0 3.45.080.322 I slot print_timing: id 0 | task 20568 | prompt eval time = 111.04 ms / 323 tokens ( 0.34 ms per token, 2908.86 tokens per second) 3.45.080.328 I slot print_timing: id 0 | task 20568 | eval time = 988.00 ms / 107 tokens ( 9.32 ms per token, 107.29 tokens per second) 3.45.080.329 I slot print_timing: id 0 | task 20568 | total time = 1099.04 ms / 430 tokens 3.45.080.330 I slot print_timing: id 0 | task 20568 | graphs reused = 19620 3.45.080.331 I slot print_timing: id 0 | task 20568 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.080.361 I slot release: id 0 | task 20568 | stop processing: n_tokens = 461, truncated = 0 3.45.094.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 224982585 3.45.094.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 3.45.162.809 I slot launch_slot_: id 0 | task 20678 | processing task, is_child = 0 3.48.282.967 I slot print_timing: id 0 | task 20678 | n_gen = 329, tg = 109.15 t/s, tg_3s = 109.48 t/s 3.51.288.566 I slot print_timing: id 0 | task 20678 | n_gen = 657, tg = 109.14 t/s, tg_3s = 109.13 t/s 3.53.747.638 I slot print_timing: id 0 | task 20678 | prompt eval time = 115.07 ms / 321 tokens ( 0.36 ms per token, 2789.58 tokens per second) 3.53.747.644 I slot print_timing: id 0 | task 20678 | eval time = 8469.74 ms / 924 tokens ( 9.18 ms per token, 108.98 tokens per second) 3.53.747.645 I slot print_timing: id 0 | task 20678 | total time = 8584.81 ms / 1245 tokens 3.53.747.646 I slot print_timing: id 0 | task 20678 | graphs reused = 20539 3.53.747.647 I slot print_timing: id 0 | task 20678 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.747.676 I slot release: id 0 | task 20678 | stop processing: n_tokens = 1276, truncated = 0 3.53.772.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1276, t_last = 233649900 3.53.772.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.825 MiB) 3.53.844.785 I slot launch_slot_: id 0 | task 21605 | processing task, is_child = 0 3.56.478.207 I slot print_timing: id 0 | task 21605 | prompt eval time = 111.87 ms / 322 tokens ( 0.35 ms per token, 2878.42 tokens per second) 3.56.478.213 I slot print_timing: id 0 | task 21605 | eval time = 2521.53 ms / 277 tokens ( 9.14 ms per token, 109.46 tokens per second) 3.56.478.214 I slot print_timing: id 0 | task 21605 | total time = 2633.40 ms / 599 tokens 3.56.478.214 I slot print_timing: id 0 | task 21605 | graphs reused = 20813 3.56.478.215 I slot print_timing: id 0 | task 21605 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.478.245 I slot release: id 0 | task 21605 | stop processing: n_tokens = 630, truncated = 0 3.56.482.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 630, t_last = 236380470 3.56.482.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 3.56.551.541 I slot launch_slot_: id 0 | task 21885 | processing task, is_child = 0 3.57.082.546 I slot print_timing: id 0 | task 21885 | prompt eval time = 113.45 ms / 337 tokens ( 0.34 ms per token, 2970.55 tokens per second) 3.57.082.551 I slot print_timing: id 0 | task 21885 | eval time = 417.54 ms / 46 tokens ( 9.28 ms per token, 107.77 tokens per second) 3.57.082.552 I slot print_timing: id 0 | task 21885 | total time = 530.99 ms / 383 tokens 3.57.082.553 I slot print_timing: id 0 | task 21885 | graphs reused = 20857 3.57.082.554 I slot print_timing: id 0 | task 21885 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.082.584 I slot release: id 0 | task 21885 | stop processing: n_tokens = 414, truncated = 0 3.57.098.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 236984809 3.57.098.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.57.163.041 I slot launch_slot_: id 0 | task 21934 | processing task, is_child = 0 3.57.701.698 I slot print_timing: id 0 | task 21934 | prompt eval time = 112.57 ms / 325 tokens ( 0.35 ms per token, 2887.20 tokens per second) 3.57.701.703 I slot print_timing: id 0 | task 21934 | eval time = 426.07 ms / 47 tokens ( 9.26 ms per token, 107.96 tokens per second) 3.57.701.705 I slot print_timing: id 0 | task 21934 | total time = 538.63 ms / 372 tokens 3.57.701.705 I slot print_timing: id 0 | task 21934 | graphs reused = 20902 3.57.701.706 I slot print_timing: id 0 | task 21934 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.701.735 I slot release: id 0 | task 21934 | stop processing: n_tokens = 403, truncated = 0 3.57.718.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 237603960 3.57.718.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.983 MiB) 3.57.789.475 I slot launch_slot_: id 0 | task 21984 | processing task, is_child = 0 3.58.367.684 I slot print_timing: id 0 | task 21984 | prompt eval time = 113.00 ms / 331 tokens ( 0.34 ms per token, 2929.10 tokens per second) 3.58.367.690 I slot print_timing: id 0 | task 21984 | eval time = 465.19 ms / 52 tokens ( 9.12 ms per token, 109.63 tokens per second) 3.58.367.691 I slot print_timing: id 0 | task 21984 | total time = 578.19 ms / 383 tokens 3.58.367.692 I slot print_timing: id 0 | task 21984 | graphs reused = 20952 3.58.367.693 I slot print_timing: id 0 | task 21984 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.367.724 I slot release: id 0 | task 21984 | stop processing: n_tokens = 414, truncated = 0 3.58.389.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 238269948 3.58.389.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.294 MiB) 3.58.455.045 I slot launch_slot_: id 0 | task 22039 | processing task, is_child = 0 3.59.363.762 I slot print_timing: id 0 | task 22039 | prompt eval time = 108.97 ms / 336 tokens ( 0.32 ms per token, 3083.47 tokens per second) 3.59.363.768 I slot print_timing: id 0 | task 22039 | eval time = 799.73 ms / 88 tokens ( 9.19 ms per token, 108.79 tokens per second) 3.59.363.769 I slot print_timing: id 0 | task 22039 | total time = 908.70 ms / 424 tokens 3.59.363.770 I slot print_timing: id 0 | task 22039 | graphs reused = 21038 3.59.363.771 I slot print_timing: id 0 | task 22039 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.363.806 I slot release: id 0 | task 22039 | stop processing: n_tokens = 455, truncated = 0 3.59.389.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 239266031 3.59.389.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.360 MiB) 3.59.467.316 I slot launch_slot_: id 0 | task 22130 | processing task, is_child = 0 3.59.757.292 I slot print_timing: id 0 | task 22130 | prompt eval time = 117.12 ms / 349 tokens ( 0.34 ms per token, 2979.93 tokens per second) 3.59.757.298 I slot print_timing: id 0 | task 22130 | eval time = 172.84 ms / 19 tokens ( 9.60 ms per token, 104.14 tokens per second) 3.59.757.299 I slot print_timing: id 0 | task 22130 | total time = 289.96 ms / 368 tokens 3.59.757.299 I slot print_timing: id 0 | task 22130 | graphs reused = 21055 3.59.757.300 I slot print_timing: id 0 | task 22130 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.757.331 I slot release: id 0 | task 22130 | stop processing: n_tokens = 399, truncated = 0 3.59.785.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 239659556 3.59.785.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.106 MiB) 3.59.858.332 I slot launch_slot_: id 0 | task 22152 | processing task, is_child = 0 4.02.975.970 I slot print_timing: id 0 | task 22152 | n_gen = 328, tg = 108.90 t/s, tg_3s = 109.24 t/s 4.05.979.283 I slot print_timing: id 0 | task 22152 | n_gen = 655, tg = 108.89 t/s, tg_3s = 108.88 t/s 4.06.212.904 I slot print_timing: id 0 | task 22152 | prompt eval time = 114.93 ms / 336 tokens ( 0.34 ms per token, 2923.42 tokens per second) 4.06.212.910 I slot print_timing: id 0 | task 22152 | eval time = 6239.61 ms / 680 tokens ( 9.19 ms per token, 108.82 tokens per second) 4.06.212.911 I slot print_timing: id 0 | task 22152 | total time = 6354.55 ms / 1016 tokens 4.06.212.912 I slot print_timing: id 0 | task 22152 | graphs reused = 21730 4.06.212.912 I slot print_timing: id 0 | task 22152 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.212.942 I slot release: id 0 | task 22152 | stop processing: n_tokens = 1047, truncated = 0 4.06.236.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1047, t_last = 246115166 4.06.236.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.107 MiB) 4.06.306.860 I slot launch_slot_: id 0 | task 22835 | processing task, is_child = 0 4.09.421.261 I slot print_timing: id 0 | task 22835 | n_gen = 330, tg = 109.56 t/s, tg_3s = 109.89 t/s 4.09.549.724 I slot print_timing: id 0 | task 22835 | prompt eval time = 111.51 ms / 349 tokens ( 0.32 ms per token, 3129.68 tokens per second) 4.09.549.730 I slot print_timing: id 0 | task 22835 | eval time = 3131.33 ms / 344 tokens ( 9.13 ms per token, 109.54 tokens per second) 4.09.549.731 I slot print_timing: id 0 | task 22835 | total time = 3242.84 ms / 693 tokens 4.09.549.732 I slot print_timing: id 0 | task 22835 | graphs reused = 22071 4.09.549.732 I slot print_timing: id 0 | task 22835 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.549.762 I slot release: id 0 | task 22835 | stop processing: n_tokens = 724, truncated = 0 4.09.574.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 724, t_last = 249451986 4.09.574.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.465 MiB) 4.09.634.430 I slot launch_slot_: id 0 | task 23182 | processing task, is_child = 0 4.10.237.742 I slot print_timing: id 0 | task 23182 | prompt eval time = 113.20 ms / 349 tokens ( 0.32 ms per token, 3082.93 tokens per second) 4.10.237.748 I slot print_timing: id 0 | task 23182 | eval time = 490.09 ms / 54 tokens ( 9.25 ms per token, 108.14 tokens per second) 4.10.237.749 I slot print_timing: id 0 | task 23182 | total time = 603.29 ms / 403 tokens 4.10.237.750 I slot print_timing: id 0 | task 23182 | graphs reused = 22123 4.10.237.751 I slot print_timing: id 0 | task 23182 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.237.778 I slot release: id 0 | task 23182 | stop processing: n_tokens = 434, truncated = 0 4.10.263.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 250140003 4.10.264.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 4.10.330.558 I slot launch_slot_: id 0 | task 23239 | processing task, is_child = 0 4.10.627.753 I slot print_timing: id 0 | task 23239 | prompt eval time = 115.25 ms / 385 tokens ( 0.30 ms per token, 3340.65 tokens per second) 4.10.627.758 I slot print_timing: id 0 | task 23239 | eval time = 181.93 ms / 20 tokens ( 9.58 ms per token, 104.44 tokens per second) 4.10.627.759 I slot print_timing: id 0 | task 23239 | total time = 297.18 ms / 405 tokens 4.10.627.760 I slot print_timing: id 0 | task 23239 | graphs reused = 22141 4.10.627.761 I slot print_timing: id 0 | task 23239 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.627.790 I slot release: id 0 | task 23239 | stop processing: n_tokens = 436, truncated = 0 4.10.655.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 250530015 4.10.655.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.923 MiB) 4.10.720.422 I slot launch_slot_: id 0 | task 23262 | processing task, is_child = 0 4.11.337.987 I slot print_timing: id 0 | task 23262 | prompt eval time = 108.60 ms / 328 tokens ( 0.33 ms per token, 3020.20 tokens per second) 4.11.337.993 I slot print_timing: id 0 | task 23262 | eval time = 508.94 ms / 57 tokens ( 9.09 ms per token, 110.03 tokens per second) 4.11.337.994 I slot print_timing: id 0 | task 23262 | total time = 617.55 ms / 385 tokens 4.11.337.995 I slot print_timing: id 0 | task 23262 | graphs reused = 22196 4.11.337.995 I slot print_timing: id 0 | task 23262 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.338.023 I slot release: id 0 | task 23262 | stop processing: n_tokens = 416, truncated = 0