$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--mradermacher--Qwen3.5-9B-i1-GGUF\snapshots\c5044c600a7e15246d54d13e4532382bc44ef41b\Qwen3.5-9B.i1-IQ4_XS.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.095.313 I srv llama_server: initializing ... 0.00.095.319 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.095.427 I srv init_listene: The UI is disabled 0.00.095.429 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.095.506 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.103.992 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--mradermacher--Qwen3.5-9B-i1-GGUF\snapshots\c5044c600a7e15246d54d13e4532382bc44ef41b\Qwen3.5-9B.i1-IQ4_XS.gguf' 0.02.438.750 I cmn init: llama threadpool init, n_threads = 8 0.02.511.209 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.515.816 I srv llama_server: model loaded 0.02.515.823 I srv llama_server: listening on http://127.0.0.1:8089 0.04.544.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.544.317 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.142.816 I slot print_timing: id 0 | task 0 | prompt eval time = 124.09 ms / 368 tokens ( 0.34 ms per token, 2965.49 tokens per second) 0.05.142.822 I slot print_timing: id 0 | task 0 | eval time = 474.39 ms / 53 tokens ( 9.12 ms per token, 109.61 tokens per second) 0.05.142.822 I slot print_timing: id 0 | task 0 | total time = 598.48 ms / 421 tokens 0.05.142.828 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.142.829 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.142.857 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.157.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5049486 0.05.181.947 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.05.661.961 I slot print_timing: id 0 | task 56 | prompt eval time = 108.37 ms / 322 tokens ( 0.34 ms per token, 2971.38 tokens per second) 0.05.661.966 I slot print_timing: id 0 | task 56 | eval time = 371.63 ms / 42 tokens ( 9.06 ms per token, 110.33 tokens per second) 0.05.661.968 I slot print_timing: id 0 | task 56 | total time = 480.00 ms / 364 tokens 0.05.661.968 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.05.661.969 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.661.994 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.05.686.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5568623 0.05.710.117 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.06.192.260 I slot print_timing: id 0 | task 101 | prompt eval time = 110.25 ms / 365 tokens ( 0.30 ms per token, 3310.78 tokens per second) 0.06.192.266 I slot print_timing: id 0 | task 101 | eval time = 371.88 ms / 42 tokens ( 9.07 ms per token, 110.25 tokens per second) 0.06.192.266 I slot print_timing: id 0 | task 101 | total time = 482.12 ms / 407 tokens 0.06.192.267 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.06.192.268 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.192.297 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.06.216.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6098925 0.06.240.962 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.06.737.317 I slot print_timing: id 0 | task 146 | prompt eval time = 116.04 ms / 397 tokens ( 0.29 ms per token, 3421.23 tokens per second) 0.06.737.323 I slot print_timing: id 0 | task 146 | eval time = 380.30 ms / 43 tokens ( 9.05 ms per token, 110.44 tokens per second) 0.06.737.324 I slot print_timing: id 0 | task 146 | total time = 496.34 ms / 440 tokens 0.06.737.325 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.06.737.326 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.737.352 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.06.763.658 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 0.06.788.109 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.07.389.147 I slot print_timing: id 0 | task 192 | prompt eval time = 112.59 ms / 383 tokens ( 0.29 ms per token, 3401.57 tokens per second) 0.07.389.153 I slot print_timing: id 0 | task 192 | eval time = 488.43 ms / 55 tokens ( 9.04 ms per token, 110.56 tokens per second) 0.07.389.154 I slot print_timing: id 0 | task 192 | total time = 601.02 ms / 438 tokens 0.07.389.154 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.07.389.155 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.389.184 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.07.416.504 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7295812 0.07.440.650 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.08.043.537 I slot print_timing: id 0 | task 250 | prompt eval time = 114.51 ms / 372 tokens ( 0.31 ms per token, 3248.74 tokens per second) 0.08.043.543 I slot print_timing: id 0 | task 250 | eval time = 488.36 ms / 55 tokens ( 9.04 ms per token, 110.57 tokens per second) 0.08.043.544 I slot print_timing: id 0 | task 250 | total time = 602.87 ms / 427 tokens 0.08.043.545 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.08.043.546 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.043.574 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.08.058.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 7950203 0.08.082.830 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.08.703.728 I slot print_timing: id 0 | task 308 | prompt eval time = 129.54 ms / 422 tokens ( 0.31 ms per token, 3257.68 tokens per second) 0.08.703.734 I slot print_timing: id 0 | task 308 | eval time = 491.34 ms / 55 tokens ( 9.10 ms per token, 109.90 tokens per second) 0.08.703.735 I slot print_timing: id 0 | task 308 | total time = 620.88 ms / 477 tokens 0.08.703.737 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.08.703.738 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.703.770 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.08.729.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 8610398 0.08.755.089 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.09.541.656 I slot print_timing: id 0 | task 366 | prompt eval time = 134.53 ms / 470 tokens ( 0.29 ms per token, 3493.57 tokens per second) 0.09.541.661 I slot print_timing: id 0 | task 366 | eval time = 652.01 ms / 72 tokens ( 9.18 ms per token, 108.89 tokens per second) 0.09.541.662 I slot print_timing: id 0 | task 366 | total time = 786.55 ms / 542 tokens 0.09.541.663 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.09.541.664 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.541.695 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.09.557.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 9448324 0.09.582.780 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.10.113.267 I slot print_timing: id 0 | task 441 | prompt eval time = 110.87 ms / 345 tokens ( 0.32 ms per token, 3111.78 tokens per second) 0.10.113.273 I slot print_timing: id 0 | task 441 | eval time = 419.60 ms / 47 tokens ( 9.12 ms per token, 109.63 tokens per second) 0.10.113.274 I slot print_timing: id 0 | task 441 | total time = 530.47 ms / 392 tokens 0.10.113.275 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.10.113.276 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.113.303 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.10.136.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 10019931 0.10.160.851 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.10.640.802 I slot print_timing: id 0 | task 491 | prompt eval time = 113.06 ms / 364 tokens ( 0.31 ms per token, 3219.47 tokens per second) 0.10.640.808 I slot print_timing: id 0 | task 491 | eval time = 366.87 ms / 41 tokens ( 9.17 ms per token, 109.03 tokens per second) 0.10.640.809 I slot print_timing: id 0 | task 491 | total time = 479.93 ms / 405 tokens 0.10.640.810 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.10.640.810 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.640.839 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.10.666.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 10547468 0.10.691.383 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.11.397.051 I slot print_timing: id 0 | task 535 | prompt eval time = 116.02 ms / 376 tokens ( 0.31 ms per token, 3240.82 tokens per second) 0.11.397.056 I slot print_timing: id 0 | task 535 | eval time = 589.63 ms / 62 tokens ( 9.67 ms per token, 103.45 tokens per second) 0.11.397.058 I slot print_timing: id 0 | task 535 | total time = 705.65 ms / 438 tokens 0.11.397.058 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.11.397.060 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.397.102 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.11.412.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 11303731 0.11.439.043 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.11.975.608 I slot print_timing: id 0 | task 600 | prompt eval time = 118.57 ms / 412 tokens ( 0.29 ms per token, 3474.77 tokens per second) 0.11.975.614 I slot print_timing: id 0 | task 600 | eval time = 417.98 ms / 47 tokens ( 9.09 ms per token, 110.05 tokens per second) 0.11.975.615 I slot print_timing: id 0 | task 600 | total time = 536.55 ms / 459 tokens 0.11.975.616 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.11.975.616 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.975.647 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.12.003.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 11882276 0.12.030.878 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.12.697.664 I slot print_timing: id 0 | task 650 | prompt eval time = 113.35 ms / 376 tokens ( 0.30 ms per token, 3317.13 tokens per second) 0.12.697.669 I slot print_timing: id 0 | task 650 | eval time = 553.41 ms / 62 tokens ( 9.07 ms per token, 110.22 tokens per second) 0.12.697.670 I slot print_timing: id 0 | task 650 | total time = 666.77 ms / 438 tokens 0.12.697.671 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.12.697.672 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.697.701 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.12.725.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12604329 0.12.752.933 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.13.333.240 I slot print_timing: id 0 | task 715 | prompt eval time = 116.24 ms / 378 tokens ( 0.31 ms per token, 3251.78 tokens per second) 0.13.333.246 I slot print_timing: id 0 | task 715 | eval time = 464.04 ms / 52 tokens ( 9.10 ms per token, 109.90 tokens per second) 0.13.333.247 I slot print_timing: id 0 | task 715 | total time = 580.29 ms / 430 tokens 0.13.333.248 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.13.333.249 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.333.277 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.13.348.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 13239905 0.13.375.349 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.14.040.602 I slot print_timing: id 0 | task 770 | prompt eval time = 116.43 ms / 367 tokens ( 0.32 ms per token, 3152.22 tokens per second) 0.14.040.608 I slot print_timing: id 0 | task 770 | eval time = 548.80 ms / 58 tokens ( 9.63 ms per token, 103.86 tokens per second) 0.14.040.609 I slot print_timing: id 0 | task 770 | total time = 665.23 ms / 425 tokens 0.14.040.610 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.14.040.611 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.040.643 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.14.068.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 13947271 0.14.093.625 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.14.660.863 I slot print_timing: id 0 | task 831 | prompt eval time = 111.27 ms / 347 tokens ( 0.32 ms per token, 3118.54 tokens per second) 0.14.660.869 I slot print_timing: id 0 | task 831 | eval time = 455.95 ms / 51 tokens ( 9.12 ms per token, 109.66 tokens per second) 0.14.660.870 I slot print_timing: id 0 | task 831 | total time = 567.22 ms / 398 tokens 0.14.660.871 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.14.660.872 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.660.900 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.14.676.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 14567528 0.14.702.108 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.15.180.834 I slot print_timing: id 0 | task 885 | prompt eval time = 113.38 ms / 369 tokens ( 0.31 ms per token, 3254.43 tokens per second) 0.15.180.840 I slot print_timing: id 0 | task 885 | eval time = 365.32 ms / 41 tokens ( 9.13 ms per token, 109.49 tokens per second) 0.15.180.841 I slot print_timing: id 0 | task 885 | total time = 478.71 ms / 410 tokens 0.15.180.841 I slot print_timing: id 0 | task 885 | graphs reused = 844 0.15.180.842 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.180.871 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 0.15.204.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 15087499 0.15.234.306 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 0.15.714.217 I slot print_timing: id 0 | task 929 | prompt eval time = 111.64 ms / 352 tokens ( 0.32 ms per token, 3153.02 tokens per second) 0.15.714.222 I slot print_timing: id 0 | task 929 | eval time = 368.25 ms / 41 tokens ( 9.21 ms per token, 108.62 tokens per second) 0.15.714.223 I slot print_timing: id 0 | task 929 | total time = 479.89 ms / 393 tokens 0.15.714.224 I slot print_timing: id 0 | task 929 | graphs reused = 883 0.15.714.225 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.714.253 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 0.15.736.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 15620881 0.15.762.517 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 0.16.233.693 I slot print_timing: id 0 | task 973 | prompt eval time = 112.42 ms / 349 tokens ( 0.32 ms per token, 3104.51 tokens per second) 0.16.233.699 I slot print_timing: id 0 | task 973 | eval time = 358.74 ms / 40 tokens ( 9.20 ms per token, 108.71 tokens per second) 0.16.233.700 I slot print_timing: id 0 | task 973 | total time = 471.16 ms / 389 tokens 0.16.233.701 I slot print_timing: id 0 | task 973 | graphs reused = 921 0.16.233.702 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.233.732 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 0.16.255.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 16140361 0.16.282.934 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.17.000.390 I slot print_timing: id 0 | task 1016 | prompt eval time = 119.17 ms / 384 tokens ( 0.31 ms per token, 3222.26 tokens per second) 0.17.000.396 I slot print_timing: id 0 | task 1016 | eval time = 598.26 ms / 63 tokens ( 9.65 ms per token, 103.63 tokens per second) 0.17.000.397 I slot print_timing: id 0 | task 1016 | total time = 717.44 ms / 447 tokens 0.17.000.398 I slot print_timing: id 0 | task 1016 | graphs reused = 982 0.17.000.398 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.000.428 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 0.17.024.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 16907057 0.17.060.872 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.17.659.466 I slot print_timing: id 0 | task 1082 | prompt eval time = 113.09 ms / 356 tokens ( 0.32 ms per token, 3147.99 tokens per second) 0.17.659.472 I slot print_timing: id 0 | task 1082 | eval time = 485.48 ms / 54 tokens ( 9.16 ms per token, 109.17 tokens per second) 0.17.659.473 I slot print_timing: id 0 | task 1082 | total time = 598.57 ms / 410 tokens 0.17.659.474 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 0.17.659.475 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.659.508 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 0.17.678.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 17566136 0.17.706.783 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 0.18.459.044 I slot print_timing: id 0 | task 1139 | prompt eval time = 123.84 ms / 410 tokens ( 0.30 ms per token, 3310.62 tokens per second) 0.18.459.050 I slot print_timing: id 0 | task 1139 | eval time = 628.40 ms / 70 tokens ( 9.11 ms per token, 109.80 tokens per second) 0.18.459.051 I slot print_timing: id 0 | task 1139 | total time = 752.24 ms / 480 tokens 0.18.459.051 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 0.18.459.052 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.459.081 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 0.18.485.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 18365710 0.18.533.382 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 0.19.181.671 I slot print_timing: id 0 | task 1212 | prompt eval time = 118.72 ms / 385 tokens ( 0.31 ms per token, 3242.82 tokens per second) 0.19.181.678 I slot print_timing: id 0 | task 1212 | eval time = 529.54 ms / 58 tokens ( 9.29 ms per token, 107.64 tokens per second) 0.19.181.679 I slot print_timing: id 0 | task 1212 | total time = 648.27 ms / 443 tokens 0.19.181.679 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 0.19.181.680 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.181.713 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 0.19.198.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 19088341 0.19.263.485 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.20.035.392 I slot print_timing: id 0 | task 1273 | prompt eval time = 125.24 ms / 395 tokens ( 0.32 ms per token, 3153.87 tokens per second) 0.20.035.398 I slot print_timing: id 0 | task 1273 | eval time = 646.64 ms / 71 tokens ( 9.24 ms per token, 108.25 tokens per second) 0.20.035.399 I slot print_timing: id 0 | task 1273 | total time = 771.88 ms / 466 tokens 0.20.035.400 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.20.035.401 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.035.429 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.20.039.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 19942058 0.20.086.697 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.20.770.594 I slot print_timing: id 0 | task 1347 | prompt eval time = 124.72 ms / 430 tokens ( 0.29 ms per token, 3447.70 tokens per second) 0.20.770.600 I slot print_timing: id 0 | task 1347 | eval time = 559.15 ms / 62 tokens ( 9.17 ms per token, 109.09 tokens per second) 0.20.770.601 I slot print_timing: id 0 | task 1347 | total time = 683.87 ms / 492 tokens 0.20.770.602 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 0.20.770.603 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.770.637 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 0.20.788.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 20677266 0.20.826.622 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 0.21.511.007 I slot print_timing: id 0 | task 1412 | prompt eval time = 122.32 ms / 392 tokens ( 0.31 ms per token, 3204.68 tokens per second) 0.21.511.013 I slot print_timing: id 0 | task 1412 | eval time = 562.04 ms / 62 tokens ( 9.21 ms per token, 108.53 tokens per second) 0.21.511.014 I slot print_timing: id 0 | task 1412 | total time = 684.36 ms / 454 tokens 0.21.511.015 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 0.21.511.015 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.511.045 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 0.21.535.419 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 21417673 0.21.578.771 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 0.22.164.403 I slot print_timing: id 0 | task 1477 | prompt eval time = 115.15 ms / 350 tokens ( 0.33 ms per token, 3039.62 tokens per second) 0.22.164.410 I slot print_timing: id 0 | task 1477 | eval time = 470.46 ms / 52 tokens ( 9.22 ms per token, 108.40 tokens per second) 0.22.164.411 I slot print_timing: id 0 | task 1477 | total time = 585.61 ms / 402 tokens 0.22.164.412 I slot print_timing: id 0 | task 1477 | graphs reused = 1397 0.22.164.413 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.164.443 I slot release: id 0 | task 1477 | stop processing: n_tokens = 401, truncated = 0 0.22.192.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 22071071 0.22.231.857 I slot launch_slot_: id 0 | task 1532 | processing task, is_child = 0 0.22.902.637 I slot print_timing: id 0 | task 1532 | prompt eval time = 120.78 ms / 380 tokens ( 0.32 ms per token, 3146.32 tokens per second) 0.22.902.644 I slot print_timing: id 0 | task 1532 | eval time = 549.98 ms / 61 tokens ( 9.17 ms per token, 109.09 tokens per second) 0.22.902.645 I slot print_timing: id 0 | task 1532 | total time = 670.76 ms / 441 tokens 0.22.902.646 I slot print_timing: id 0 | task 1532 | graphs reused = 1456 0.22.902.647 I slot print_timing: id 0 | task 1532 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.902.681 I slot release: id 0 | task 1532 | stop processing: n_tokens = 440, truncated = 0 0.22.926.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 22809309 0.22.963.809 I slot launch_slot_: id 0 | task 1596 | processing task, is_child = 0 0.23.862.499 I slot print_timing: id 0 | task 1596 | prompt eval time = 129.06 ms / 410 tokens ( 0.31 ms per token, 3176.79 tokens per second) 0.23.862.506 I slot print_timing: id 0 | task 1596 | eval time = 769.61 ms / 80 tokens ( 9.74 ms per token, 102.65 tokens per second) 0.23.862.507 I slot print_timing: id 0 | task 1596 | total time = 898.67 ms / 490 tokens 0.23.862.509 I slot print_timing: id 0 | task 1596 | graphs reused = 1534 0.23.862.510 I slot print_timing: id 0 | task 1596 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.862.551 I slot release: id 0 | task 1596 | stop processing: n_tokens = 489, truncated = 0 0.23.877.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 23769179 0.23.912.908 I slot launch_slot_: id 0 | task 1679 | processing task, is_child = 0 0.24.647.520 I slot print_timing: id 0 | task 1679 | prompt eval time = 122.32 ms / 387 tokens ( 0.32 ms per token, 3163.86 tokens per second) 0.24.647.527 I slot print_timing: id 0 | task 1679 | eval time = 612.27 ms / 68 tokens ( 9.14 ms per token, 109.43 tokens per second) 0.24.647.528 I slot print_timing: id 0 | task 1679 | total time = 734.59 ms / 455 tokens 0.24.647.529 I slot print_timing: id 0 | task 1679 | graphs reused = 1600 0.24.647.530 I slot print_timing: id 0 | task 1679 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.647.566 I slot release: id 0 | task 1679 | stop processing: n_tokens = 454, truncated = 0 0.24.669.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 24554194 0.24.705.817 I slot launch_slot_: id 0 | task 1750 | processing task, is_child = 0 0.25.372.168 I slot print_timing: id 0 | task 1750 | prompt eval time = 125.37 ms / 358 tokens ( 0.35 ms per token, 2855.46 tokens per second) 0.25.372.176 I slot print_timing: id 0 | task 1750 | eval time = 540.95 ms / 59 tokens ( 9.33 ms per token, 107.22 tokens per second) 0.25.372.177 I slot print_timing: id 0 | task 1750 | total time = 666.32 ms / 417 tokens 0.25.372.178 I slot print_timing: id 0 | task 1750 | graphs reused = 1657 0.25.372.180 I slot print_timing: id 0 | task 1750 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.372.216 I slot release: id 0 | task 1750 | stop processing: n_tokens = 416, truncated = 0 0.25.389.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 25278844 0.25.427.385 I slot launch_slot_: id 0 | task 1812 | processing task, is_child = 0 0.26.118.575 I slot print_timing: id 0 | task 1812 | prompt eval time = 125.76 ms / 359 tokens ( 0.35 ms per token, 2854.69 tokens per second) 0.26.118.582 I slot print_timing: id 0 | task 1812 | eval time = 565.41 ms / 56 tokens ( 10.28 ms per token, 97.27 tokens per second) 0.26.118.583 I slot print_timing: id 0 | task 1812 | total time = 691.17 ms / 415 tokens 0.26.118.585 I slot print_timing: id 0 | task 1812 | graphs reused = 1711 0.26.118.586 I slot print_timing: id 0 | task 1812 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.118.619 I slot release: id 0 | task 1812 | stop processing: n_tokens = 414, truncated = 0 0.26.146.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 26025247 0.26.178.649 I slot launch_slot_: id 0 | task 1871 | processing task, is_child = 0 0.26.862.784 I slot print_timing: id 0 | task 1871 | prompt eval time = 124.17 ms / 387 tokens ( 0.32 ms per token, 3116.69 tokens per second) 0.26.862.791 I slot print_timing: id 0 | task 1871 | eval time = 559.94 ms / 61 tokens ( 9.33 ms per token, 107.15 tokens per second) 0.26.862.792 I slot print_timing: id 0 | task 1871 | total time = 684.11 ms / 448 tokens 0.26.862.793 I slot print_timing: id 0 | task 1871 | graphs reused = 1770 0.26.862.794 I slot print_timing: id 0 | task 1871 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.862.826 I slot release: id 0 | task 1871 | stop processing: n_tokens = 447, truncated = 0 0.26.867.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 26769454 0.26.897.129 I slot launch_slot_: id 0 | task 1935 | processing task, is_child = 0 0.27.634.082 I slot print_timing: id 0 | task 1935 | prompt eval time = 129.53 ms / 410 tokens ( 0.32 ms per token, 3165.29 tokens per second) 0.27.634.090 I slot print_timing: id 0 | task 1935 | eval time = 607.40 ms / 61 tokens ( 10.12 ms per token, 98.78 tokens per second) 0.27.634.091 I slot print_timing: id 0 | task 1935 | total time = 736.93 ms / 471 tokens 0.27.634.092 I slot print_timing: id 0 | task 1935 | graphs reused = 1829 0.27.634.094 I slot print_timing: id 0 | task 1935 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.634.138 I slot release: id 0 | task 1935 | stop processing: n_tokens = 470, truncated = 0 0.27.639.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 27540766 0.27.675.377 I slot launch_slot_: id 0 | task 1999 | processing task, is_child = 0 0.28.256.427 I slot print_timing: id 0 | task 1999 | prompt eval time = 120.77 ms / 351 tokens ( 0.34 ms per token, 2906.35 tokens per second) 0.28.256.436 I slot print_timing: id 0 | task 1999 | eval time = 460.25 ms / 50 tokens ( 9.39 ms per token, 106.46 tokens per second) 0.28.256.438 I slot print_timing: id 0 | task 1999 | total time = 581.02 ms / 401 tokens 0.28.256.440 I slot print_timing: id 0 | task 1999 | graphs reused = 1877 0.28.256.441 I slot print_timing: id 0 | task 1999 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.256.501 I slot release: id 0 | task 1999 | stop processing: n_tokens = 400, truncated = 0 0.28.285.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 28163130 0.28.314.710 I slot launch_slot_: id 0 | task 2052 | processing task, is_child = 0 0.30.528.445 I slot print_timing: id 0 | task 2052 | prompt eval time = 130.64 ms / 393 tokens ( 0.33 ms per token, 3008.22 tokens per second) 0.30.528.452 I slot print_timing: id 0 | task 2052 | eval time = 2083.07 ms / 224 tokens ( 9.34 ms per token, 107.05 tokens per second) 0.30.528.453 I slot print_timing: id 0 | task 2052 | total time = 2213.71 ms / 617 tokens 0.30.528.453 I slot print_timing: id 0 | task 2052 | graphs reused = 2098 0.30.528.454 I slot print_timing: id 0 | task 2052 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.528.487 I slot release: id 0 | task 2052 | stop processing: n_tokens = 616, truncated = 0 0.30.554.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 30435115 0.30.592.507 I slot launch_slot_: id 0 | task 2279 | processing task, is_child = 0 0.31.000.136 I slot print_timing: id 0 | task 2279 | prompt eval time = 126.94 ms / 321 tokens ( 0.40 ms per token, 2528.65 tokens per second) 0.31.000.144 I slot print_timing: id 0 | task 2279 | eval time = 280.65 ms / 30 tokens ( 9.68 ms per token, 103.33 tokens per second) 0.31.000.146 I slot print_timing: id 0 | task 2279 | total time = 407.59 ms / 351 tokens 0.31.000.146 I slot print_timing: id 0 | task 2279 | graphs reused = 2126 0.31.000.148 I slot print_timing: id 0 | task 2279 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.000.178 I slot release: id 0 | task 2279 | stop processing: n_tokens = 350, truncated = 0 0.31.004.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 30906807 0.31.037.136 I slot launch_slot_: id 0 | task 2312 | processing task, is_child = 0 0.31.669.592 I slot print_timing: id 0 | task 2312 | prompt eval time = 117.30 ms / 330 tokens ( 0.36 ms per token, 2813.28 tokens per second) 0.31.669.600 I slot print_timing: id 0 | task 2312 | eval time = 515.13 ms / 56 tokens ( 9.37 ms per token, 106.77 tokens per second) 0.31.669.602 I slot print_timing: id 0 | task 2312 | total time = 632.43 ms / 386 tokens 0.31.669.604 I slot print_timing: id 0 | task 2312 | graphs reused = 2180 0.31.669.605 I slot print_timing: id 0 | task 2312 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.669.652 I slot release: id 0 | task 2312 | stop processing: n_tokens = 385, truncated = 0 0.31.673.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 31576281 0.31.704.036 I slot launch_slot_: id 0 | task 2371 | processing task, is_child = 0 0.32.120.087 I slot print_timing: id 0 | task 2371 | prompt eval time = 122.41 ms / 341 tokens ( 0.36 ms per token, 2785.63 tokens per second) 0.32.120.093 I slot print_timing: id 0 | task 2371 | eval time = 293.61 ms / 32 tokens ( 9.47 ms per token, 105.58 tokens per second) 0.32.120.094 I slot print_timing: id 0 | task 2371 | total time = 416.03 ms / 373 tokens 0.32.120.095 I slot print_timing: id 0 | task 2371 | graphs reused = 2210 0.32.120.096 I slot print_timing: id 0 | task 2371 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.120.127 I slot release: id 0 | task 2371 | stop processing: n_tokens = 372, truncated = 0 0.32.141.013 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 32026755 0.32.196.730 I slot launch_slot_: id 0 | task 2406 | processing task, is_child = 0 0.32.757.094 I slot print_timing: id 0 | task 2406 | prompt eval time = 119.56 ms / 338 tokens ( 0.35 ms per token, 2827.08 tokens per second) 0.32.757.101 I slot print_timing: id 0 | task 2406 | eval time = 440.78 ms / 48 tokens ( 9.38 ms per token, 106.63 tokens per second) 0.32.757.102 I slot print_timing: id 0 | task 2406 | total time = 560.34 ms / 386 tokens 0.32.757.103 I slot print_timing: id 0 | task 2406 | graphs reused = 2256 0.32.757.104 I slot print_timing: id 0 | task 2406 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.757.132 I slot release: id 0 | task 2406 | stop processing: n_tokens = 385, truncated = 0 0.32.761.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 32663761 0.32.804.926 I slot launch_slot_: id 0 | task 2457 | processing task, is_child = 0 0.33.448.197 I slot print_timing: id 0 | task 2457 | prompt eval time = 127.33 ms / 395 tokens ( 0.32 ms per token, 3102.05 tokens per second) 0.33.448.204 I slot print_timing: id 0 | task 2457 | eval time = 515.91 ms / 56 tokens ( 9.38 ms per token, 106.61 tokens per second) 0.33.448.206 I slot print_timing: id 0 | task 2457 | total time = 643.24 ms / 451 tokens 0.33.448.208 I slot print_timing: id 0 | task 2457 | graphs reused = 2310 0.33.448.209 I slot print_timing: id 0 | task 2457 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.448.244 I slot release: id 0 | task 2457 | stop processing: n_tokens = 450, truncated = 0 0.33.472.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 33354872 0.33.514.220 I slot launch_slot_: id 0 | task 2516 | processing task, is_child = 0 0.34.464.909 I slot print_timing: id 0 | task 2516 | prompt eval time = 174.80 ms / 528 tokens ( 0.33 ms per token, 3020.63 tokens per second) 0.34.464.916 I slot print_timing: id 0 | task 2516 | eval time = 775.86 ms / 83 tokens ( 9.46 ms per token, 105.69 tokens per second) 0.34.464.918 I slot print_timing: id 0 | task 2516 | total time = 950.66 ms / 611 tokens 0.34.464.919 I slot print_timing: id 0 | task 2516 | graphs reused = 2391 0.34.464.921 I slot print_timing: id 0 | task 2516 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.464.993 I slot release: id 0 | task 2516 | stop processing: n_tokens = 610, truncated = 0 0.34.468.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 34371621 0.34.523.042 I slot launch_slot_: id 0 | task 2603 | processing task, is_child = 0 0.35.088.116 I slot print_timing: id 0 | task 2603 | prompt eval time = 146.64 ms / 331 tokens ( 0.44 ms per token, 2257.29 tokens per second) 0.35.088.122 I slot print_timing: id 0 | task 2603 | eval time = 418.41 ms / 45 tokens ( 9.51 ms per token, 105.16 tokens per second) 0.35.088.123 I slot print_timing: id 0 | task 2603 | total time = 565.05 ms / 376 tokens 0.35.088.124 I slot print_timing: id 0 | task 2603 | graphs reused = 2434 0.35.088.125 I slot print_timing: id 0 | task 2603 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.088.154 I slot release: id 0 | task 2603 | stop processing: n_tokens = 387, truncated = 0 0.35.107.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 34994783 0.35.158.114 I slot launch_slot_: id 0 | task 2651 | processing task, is_child = 0 0.35.804.020 I slot print_timing: id 0 | task 2651 | prompt eval time = 159.96 ms / 362 tokens ( 0.44 ms per token, 2263.08 tokens per second) 0.35.804.028 I slot print_timing: id 0 | task 2651 | eval time = 485.92 ms / 53 tokens ( 9.34 ms per token, 107.01 tokens per second) 0.35.804.030 I slot print_timing: id 0 | task 2651 | total time = 645.88 ms / 415 tokens 0.35.804.031 I slot print_timing: id 0 | task 2651 | graphs reused = 2485 0.35.804.032 I slot print_timing: id 0 | task 2651 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.804.078 I slot release: id 0 | task 2651 | stop processing: n_tokens = 426, truncated = 0 0.35.820.255 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 35710706 0.35.876.186 I slot launch_slot_: id 0 | task 2707 | processing task, is_child = 0 0.36.669.877 I slot print_timing: id 0 | task 2707 | prompt eval time = 157.88 ms / 419 tokens ( 0.38 ms per token, 2653.96 tokens per second) 0.36.669.884 I slot print_timing: id 0 | task 2707 | eval time = 635.79 ms / 69 tokens ( 9.35 ms per token, 106.95 tokens per second) 0.36.669.885 I slot print_timing: id 0 | task 2707 | total time = 793.66 ms / 488 tokens 0.36.669.887 I slot print_timing: id 0 | task 2707 | graphs reused = 2552 0.36.669.888 I slot print_timing: id 0 | task 2707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.669.934 I slot release: id 0 | task 2707 | stop processing: n_tokens = 499, truncated = 0 0.36.689.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 36576562 0.36.738.125 I slot launch_slot_: id 0 | task 2779 | processing task, is_child = 0 0.37.307.955 I slot print_timing: id 0 | task 2779 | prompt eval time = 161.86 ms / 423 tokens ( 0.38 ms per token, 2613.34 tokens per second) 0.37.307.962 I slot print_timing: id 0 | task 2779 | eval time = 407.94 ms / 44 tokens ( 9.49 ms per token, 105.41 tokens per second) 0.37.307.963 I slot print_timing: id 0 | task 2779 | total time = 569.80 ms / 467 tokens 0.37.307.965 I slot print_timing: id 0 | task 2779 | graphs reused = 2594 0.37.307.966 I slot print_timing: id 0 | task 2779 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.308.005 I slot release: id 0 | task 2779 | stop processing: n_tokens = 478, truncated = 0 0.37.328.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 37214633 0.37.382.215 I slot launch_slot_: id 0 | task 2826 | processing task, is_child = 0 0.37.919.178 I slot print_timing: id 0 | task 2826 | prompt eval time = 144.89 ms / 341 tokens ( 0.42 ms per token, 2353.46 tokens per second) 0.37.919.184 I slot print_timing: id 0 | task 2826 | eval time = 392.05 ms / 43 tokens ( 9.33 ms per token, 107.13 tokens per second) 0.37.919.185 I slot print_timing: id 0 | task 2826 | total time = 536.94 ms / 384 tokens 0.37.919.186 I slot print_timing: id 0 | task 2826 | graphs reused = 2635 0.37.919.187 I slot print_timing: id 0 | task 2826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.919.227 I slot release: id 0 | task 2826 | stop processing: n_tokens = 395, truncated = 0 0.37.947.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 37825855 0.38.000.053 I slot launch_slot_: id 0 | task 2872 | processing task, is_child = 0 0.38.579.418 I slot print_timing: id 0 | task 2872 | prompt eval time = 150.77 ms / 356 tokens ( 0.42 ms per token, 2361.18 tokens per second) 0.38.579.424 I slot print_timing: id 0 | task 2872 | eval time = 428.57 ms / 47 tokens ( 9.32 ms per token, 107.33 tokens per second) 0.38.579.425 I slot print_timing: id 0 | task 2872 | total time = 579.34 ms / 403 tokens 0.38.579.426 I slot print_timing: id 0 | task 2872 | graphs reused = 2680 0.38.579.427 I slot print_timing: id 0 | task 2872 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.579.459 I slot release: id 0 | task 2872 | stop processing: n_tokens = 414, truncated = 0 0.38.594.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 38486088 0.38.594.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.38.645.414 I slot launch_slot_: id 0 | task 2922 | processing task, is_child = 0 0.39.195.536 I slot print_timing: id 0 | task 2922 | prompt eval time = 149.01 ms / 362 tokens ( 0.41 ms per token, 2429.37 tokens per second) 0.39.195.542 I slot print_timing: id 0 | task 2922 | eval time = 401.07 ms / 44 tokens ( 9.33 ms per token, 107.21 tokens per second) 0.39.195.543 I slot print_timing: id 0 | task 2922 | total time = 550.09 ms / 406 tokens 0.39.195.544 I slot print_timing: id 0 | task 2922 | graphs reused = 2722 0.39.195.545 I slot print_timing: id 0 | task 2922 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.195.578 I slot release: id 0 | task 2922 | stop processing: n_tokens = 417, truncated = 0 0.39.217.262 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 39102207 0.39.217.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.39.276.396 I slot launch_slot_: id 0 | task 2969 | processing task, is_child = 0 0.40.054.637 I slot print_timing: id 0 | task 2969 | prompt eval time = 154.10 ms / 391 tokens ( 0.39 ms per token, 2537.28 tokens per second) 0.40.054.643 I slot print_timing: id 0 | task 2969 | eval time = 624.11 ms / 68 tokens ( 9.32 ms per token, 107.35 tokens per second) 0.40.054.645 I slot print_timing: id 0 | task 2969 | total time = 778.22 ms / 459 tokens 0.40.054.646 I slot print_timing: id 0 | task 2969 | graphs reused = 2788 0.40.054.647 I slot print_timing: id 0 | task 2969 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.054.689 I slot release: id 0 | task 2969 | stop processing: n_tokens = 470, truncated = 0 0.40.059.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 39961317 0.40.059.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.40.106.224 I slot launch_slot_: id 0 | task 3040 | processing task, is_child = 0 0.40.743.785 I slot print_timing: id 0 | task 3040 | prompt eval time = 145.74 ms / 343 tokens ( 0.42 ms per token, 2353.44 tokens per second) 0.40.743.791 I slot print_timing: id 0 | task 3040 | eval time = 491.79 ms / 54 tokens ( 9.28 ms per token, 107.77 tokens per second) 0.40.743.792 I slot print_timing: id 0 | task 3040 | total time = 637.53 ms / 397 tokens 0.40.743.793 I slot print_timing: id 0 | task 3040 | graphs reused = 2840 0.40.743.794 I slot print_timing: id 0 | task 3040 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.743.834 I slot release: id 0 | task 3040 | stop processing: n_tokens = 408, truncated = 0 0.40.759.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 40650462 0.40.759.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.40.762.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.40.807.393 I slot launch_slot_: id 0 | task 3097 | processing task, is_child = 0 0.41.384.050 I slot print_timing: id 0 | task 3097 | prompt eval time = 148.77 ms / 401 tokens ( 0.37 ms per token, 2695.51 tokens per second) 0.41.384.057 I slot print_timing: id 0 | task 3097 | eval time = 427.86 ms / 46 tokens ( 9.51 ms per token, 105.17 tokens per second) 0.41.384.092 I slot print_timing: id 0 | task 3097 | total time = 576.63 ms / 447 tokens 0.41.384.093 I slot print_timing: id 0 | task 3097 | graphs reused = 2884 0.41.384.094 I slot print_timing: id 0 | task 3097 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.384.141 I slot release: id 0 | task 3097 | stop processing: n_tokens = 458, truncated = 0 0.41.389.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 41290769 0.41.389.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.41.454.507 I slot launch_slot_: id 0 | task 3146 | processing task, is_child = 0 0.42.228.340 I slot print_timing: id 0 | task 3146 | prompt eval time = 142.31 ms / 355 tokens ( 0.40 ms per token, 2494.50 tokens per second) 0.42.228.346 I slot print_timing: id 0 | task 3146 | eval time = 631.49 ms / 68 tokens ( 9.43 ms per token, 106.10 tokens per second) 0.42.228.347 I slot print_timing: id 0 | task 3146 | total time = 773.80 ms / 423 tokens 0.42.228.349 I slot print_timing: id 0 | task 3146 | graphs reused = 2950 0.42.228.350 I slot print_timing: id 0 | task 3146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.228.392 I slot release: id 0 | task 3146 | stop processing: n_tokens = 434, truncated = 0 0.42.253.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 42135021 0.42.253.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.42.299.605 I slot launch_slot_: id 0 | task 3217 | processing task, is_child = 0 0.42.997.736 I slot print_timing: id 0 | task 3217 | prompt eval time = 139.57 ms / 351 tokens ( 0.40 ms per token, 2514.78 tokens per second) 0.42.997.742 I slot print_timing: id 0 | task 3217 | eval time = 558.53 ms / 57 tokens ( 9.97 ms per token, 100.26 tokens per second) 0.42.997.743 I slot print_timing: id 0 | task 3217 | total time = 698.11 ms / 408 tokens 0.42.997.744 I slot print_timing: id 0 | task 3217 | graphs reused = 3005 0.42.997.745 I slot print_timing: id 0 | task 3217 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.997.774 I slot release: id 0 | task 3217 | stop processing: n_tokens = 419, truncated = 0 0.43.018.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 42904403 0.43.018.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.43.024.632 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.43.070.343 I slot launch_slot_: id 0 | task 3277 | processing task, is_child = 0 0.44.091.843 I slot print_timing: id 0 | task 3277 | prompt eval time = 159.70 ms / 475 tokens ( 0.34 ms per token, 2974.31 tokens per second) 0.44.091.850 I slot print_timing: id 0 | task 3277 | eval time = 861.77 ms / 93 tokens ( 9.37 ms per token, 106.76 tokens per second) 0.44.091.851 I slot print_timing: id 0 | task 3277 | total time = 1021.47 ms / 568 tokens 0.44.091.852 I slot print_timing: id 0 | task 3277 | graphs reused = 3095 0.44.091.853 I slot print_timing: id 0 | task 3277 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.091.900 I slot release: id 0 | task 3277 | stop processing: n_tokens = 579, truncated = 0 0.44.096.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 43998528 0.44.096.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.44.151.999 I slot launch_slot_: id 0 | task 3373 | processing task, is_child = 0 0.45.299.945 I slot print_timing: id 0 | task 3373 | prompt eval time = 166.93 ms / 440 tokens ( 0.38 ms per token, 2635.79 tokens per second) 0.45.299.953 I slot print_timing: id 0 | task 3373 | eval time = 980.97 ms / 106 tokens ( 9.34 ms per token, 107.04 tokens per second) 0.45.299.955 I slot print_timing: id 0 | task 3373 | total time = 1147.91 ms / 546 tokens 0.45.299.956 I slot print_timing: id 0 | task 3373 | graphs reused = 3198 0.45.299.958 I slot print_timing: id 0 | task 3373 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.300.008 I slot release: id 0 | task 3373 | stop processing: n_tokens = 557, truncated = 0 0.45.304.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 45206637 0.45.304.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.45.373.232 I slot launch_slot_: id 0 | task 3482 | processing task, is_child = 0 0.46.015.644 I slot print_timing: id 0 | task 3482 | prompt eval time = 139.47 ms / 345 tokens ( 0.40 ms per token, 2473.61 tokens per second) 0.46.015.650 I slot print_timing: id 0 | task 3482 | eval time = 502.92 ms / 55 tokens ( 9.31 ms per token, 107.37 tokens per second) 0.46.015.651 I slot print_timing: id 0 | task 3482 | total time = 642.39 ms / 400 tokens 0.46.015.652 I slot print_timing: id 0 | task 3482 | graphs reused = 3251 0.46.015.653 I slot print_timing: id 0 | task 3482 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.015.684 I slot release: id 0 | task 3482 | stop processing: n_tokens = 411, truncated = 0 0.46.037.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 45922313 0.46.037.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.46.048.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.46.108.397 I slot launch_slot_: id 0 | task 3540 | processing task, is_child = 0 0.46.754.933 I slot print_timing: id 0 | task 3540 | prompt eval time = 144.63 ms / 382 tokens ( 0.38 ms per token, 2641.15 tokens per second) 0.46.754.940 I slot print_timing: id 0 | task 3540 | eval time = 501.88 ms / 55 tokens ( 9.29 ms per token, 107.60 tokens per second) 0.46.754.941 I slot print_timing: id 0 | task 3540 | total time = 646.51 ms / 437 tokens 0.46.754.942 I slot print_timing: id 0 | task 3540 | graphs reused = 3304 0.46.754.943 I slot print_timing: id 0 | task 3540 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.754.975 I slot release: id 0 | task 3540 | stop processing: n_tokens = 448, truncated = 0 0.46.758.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 46661603 0.46.758.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.46.827.571 I slot launch_slot_: id 0 | task 3598 | processing task, is_child = 0 0.47.381.153 I slot print_timing: id 0 | task 3598 | prompt eval time = 140.80 ms / 337 tokens ( 0.42 ms per token, 2393.41 tokens per second) 0.47.381.161 I slot print_timing: id 0 | task 3598 | eval time = 412.75 ms / 45 tokens ( 9.38 ms per token, 106.60 tokens per second) 0.47.381.163 I slot print_timing: id 0 | task 3598 | total time = 553.55 ms / 382 tokens 0.47.381.164 I slot print_timing: id 0 | task 3598 | graphs reused = 3347 0.47.381.164 I slot print_timing: id 0 | task 3598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.381.192 I slot release: id 0 | task 3598 | stop processing: n_tokens = 393, truncated = 0 0.47.385.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 47287821 0.47.385.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.47.452.390 I slot launch_slot_: id 0 | task 3646 | processing task, is_child = 0 0.48.296.240 I slot print_timing: id 0 | task 3646 | prompt eval time = 145.73 ms / 402 tokens ( 0.36 ms per token, 2758.58 tokens per second) 0.48.296.246 I slot print_timing: id 0 | task 3646 | eval time = 698.09 ms / 70 tokens ( 10.12 ms per token, 98.84 tokens per second) 0.48.296.248 I slot print_timing: id 0 | task 3646 | total time = 843.82 ms / 472 tokens 0.48.296.249 I slot print_timing: id 0 | task 3646 | graphs reused = 3415 0.48.296.250 I slot print_timing: id 0 | task 3646 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.296.294 I slot release: id 0 | task 3646 | stop processing: n_tokens = 483, truncated = 0 0.48.300.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 48202923 0.48.300.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.48.311.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.48.385.861 I slot launch_slot_: id 0 | task 3719 | processing task, is_child = 0 0.49.088.388 I slot print_timing: id 0 | task 3719 | prompt eval time = 177.78 ms / 549 tokens ( 0.32 ms per token, 3088.17 tokens per second) 0.49.088.396 I slot print_timing: id 0 | task 3719 | eval time = 524.72 ms / 57 tokens ( 9.37 ms per token, 106.72 tokens per second) 0.49.088.398 I slot print_timing: id 0 | task 3719 | total time = 702.50 ms / 606 tokens 0.49.088.399 I slot print_timing: id 0 | task 3719 | graphs reused = 3470 0.49.088.400 I slot print_timing: id 0 | task 3719 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.088.457 I slot release: id 0 | task 3719 | stop processing: n_tokens = 617, truncated = 0 0.49.094.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 48995085 0.49.094.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.49.194.897 I slot launch_slot_: id 0 | task 3780 | processing task, is_child = 0 0.49.925.202 I slot print_timing: id 0 | task 3780 | prompt eval time = 197.29 ms / 616 tokens ( 0.32 ms per token, 3122.31 tokens per second) 0.49.925.207 I slot print_timing: id 0 | task 3780 | eval time = 532.99 ms / 58 tokens ( 9.35 ms per token, 106.94 tokens per second) 0.49.925.208 I slot print_timing: id 0 | task 3780 | total time = 730.28 ms / 674 tokens 0.49.925.209 I slot print_timing: id 0 | task 3780 | graphs reused = 3526 0.49.925.210 I slot print_timing: id 0 | task 3780 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.925.258 I slot release: id 0 | task 3780 | stop processing: n_tokens = 685, truncated = 0 0.49.949.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 49831887 0.49.949.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.49.971.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.50.065.081 I slot launch_slot_: id 0 | task 3842 | processing task, is_child = 0 0.50.841.214 I slot print_timing: id 0 | task 3842 | prompt eval time = 205.43 ms / 665 tokens ( 0.31 ms per token, 3237.10 tokens per second) 0.50.841.221 I slot print_timing: id 0 | task 3842 | eval time = 570.68 ms / 62 tokens ( 9.36 ms per token, 106.89 tokens per second) 0.50.841.222 I slot print_timing: id 0 | task 3842 | total time = 776.11 ms / 727 tokens 0.50.841.222 I slot print_timing: id 0 | task 3842 | graphs reused = 3586 0.50.841.223 I slot print_timing: id 0 | task 3842 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.841.262 I slot release: id 0 | task 3842 | stop processing: n_tokens = 738, truncated = 0 0.50.866.488 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 50747890 0.50.866.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.50.877.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.50.969.490 I slot launch_slot_: id 0 | task 3908 | processing task, is_child = 0 0.51.679.795 I slot print_timing: id 0 | task 3908 | prompt eval time = 202.58 ms / 645 tokens ( 0.31 ms per token, 3183.96 tokens per second) 0.51.679.800 I slot print_timing: id 0 | task 3908 | eval time = 507.70 ms / 55 tokens ( 9.40 ms per token, 106.36 tokens per second) 0.51.679.802 I slot print_timing: id 0 | task 3908 | total time = 710.28 ms / 700 tokens 0.51.679.803 I slot print_timing: id 0 | task 3908 | graphs reused = 3639 0.51.679.804 I slot print_timing: id 0 | task 3908 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.679.850 I slot release: id 0 | task 3908 | stop processing: n_tokens = 711, truncated = 0 0.51.684.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 51586479 0.51.684.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.51.763.771 I slot launch_slot_: id 0 | task 3967 | processing task, is_child = 0 0.52.412.249 I slot print_timing: id 0 | task 3967 | prompt eval time = 163.24 ms / 474 tokens ( 0.34 ms per token, 2903.63 tokens per second) 0.52.412.255 I slot print_timing: id 0 | task 3967 | eval time = 485.21 ms / 52 tokens ( 9.51 ms per token, 105.11 tokens per second) 0.52.412.256 I slot print_timing: id 0 | task 3967 | total time = 648.45 ms / 526 tokens 0.52.412.257 I slot print_timing: id 0 | task 3967 | graphs reused = 3688 0.52.412.257 I slot print_timing: id 0 | task 3967 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.412.296 I slot release: id 0 | task 3967 | stop processing: n_tokens = 537, truncated = 0 0.52.416.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 52318924 0.52.416.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.52.429.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.52.503.436 I slot launch_slot_: id 0 | task 4022 | processing task, is_child = 0 0.53.079.095 I slot print_timing: id 0 | task 4022 | prompt eval time = 191.37 ms / 617 tokens ( 0.31 ms per token, 3224.07 tokens per second) 0.53.079.102 I slot print_timing: id 0 | task 4022 | eval time = 384.26 ms / 42 tokens ( 9.37 ms per token, 106.70 tokens per second) 0.53.079.103 I slot print_timing: id 0 | task 4022 | total time = 575.63 ms / 659 tokens 0.53.079.104 I slot print_timing: id 0 | task 4022 | graphs reused = 3728 0.53.079.105 I slot print_timing: id 0 | task 4022 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.079.143 I slot release: id 0 | task 4022 | stop processing: n_tokens = 670, truncated = 0 0.53.105.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 52985771 0.53.105.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.53.176.528 I slot launch_slot_: id 0 | task 4068 | processing task, is_child = 0 0.53.823.520 I slot print_timing: id 0 | task 4068 | prompt eval time = 200.78 ms / 601 tokens ( 0.33 ms per token, 2993.36 tokens per second) 0.53.823.526 I slot print_timing: id 0 | task 4068 | eval time = 446.19 ms / 48 tokens ( 9.49 ms per token, 105.34 tokens per second) 0.53.823.528 I slot print_timing: id 0 | task 4068 | total time = 646.96 ms / 649 tokens 0.53.823.528 I slot print_timing: id 0 | task 4068 | graphs reused = 3774 0.53.823.530 I slot print_timing: id 0 | task 4068 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.823.567 I slot release: id 0 | task 4068 | stop processing: n_tokens = 660, truncated = 0 0.53.849.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 53730196 0.53.849.425 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.292 MiB) 0.53.860.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.53.945.558 I slot launch_slot_: id 0 | task 4120 | processing task, is_child = 0 0.54.564.045 I slot print_timing: id 0 | task 4120 | prompt eval time = 183.45 ms / 533 tokens ( 0.34 ms per token, 2905.47 tokens per second) 0.54.564.054 I slot print_timing: id 0 | task 4120 | eval time = 435.01 ms / 47 tokens ( 9.46 ms per token, 105.74 tokens per second) 0.54.564.055 I slot print_timing: id 0 | task 4120 | total time = 618.46 ms / 580 tokens 0.54.564.058 I slot print_timing: id 0 | task 4120 | graphs reused = 3819 0.54.564.059 I slot print_timing: id 0 | task 4120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.564.112 I slot release: id 0 | task 4120 | stop processing: n_tokens = 591, truncated = 0 0.54.569.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 54470743 0.54.569.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.54.638.578 I slot launch_slot_: id 0 | task 4171 | processing task, is_child = 0 0.55.300.737 I slot print_timing: id 0 | task 4171 | prompt eval time = 175.27 ms / 480 tokens ( 0.37 ms per token, 2738.60 tokens per second) 0.55.300.743 I slot print_timing: id 0 | task 4171 | eval time = 486.86 ms / 52 tokens ( 9.55 ms per token, 104.75 tokens per second) 0.55.300.745 I slot print_timing: id 0 | task 4171 | total time = 662.13 ms / 532 tokens 0.55.300.746 I slot print_timing: id 0 | task 4171 | graphs reused = 3868 0.55.300.747 I slot print_timing: id 0 | task 4171 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.300.791 I slot release: id 0 | task 4171 | stop processing: n_tokens = 560, truncated = 0 0.55.331.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 55207420 0.55.331.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.55.344.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.55.425.557 I slot launch_slot_: id 0 | task 4226 | processing task, is_child = 0 0.56.009.332 I slot print_timing: id 0 | task 4226 | prompt eval time = 198.33 ms / 567 tokens ( 0.35 ms per token, 2858.89 tokens per second) 0.56.009.338 I slot print_timing: id 0 | task 4226 | eval time = 385.42 ms / 42 tokens ( 9.40 ms per token, 106.38 tokens per second) 0.56.009.339 I slot print_timing: id 0 | task 4226 | total time = 583.75 ms / 609 tokens 0.56.009.341 I slot print_timing: id 0 | task 4226 | graphs reused = 3908 0.56.009.342 I slot print_timing: id 0 | task 4226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.009.381 I slot release: id 0 | task 4226 | stop processing: n_tokens = 637, truncated = 0 0.56.024.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 55916010 0.56.024.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.56.036.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.56.130.021 I slot launch_slot_: id 0 | task 4272 | processing task, is_child = 0 0.56.883.282 I slot print_timing: id 0 | task 4272 | prompt eval time = 176.75 ms / 506 tokens ( 0.35 ms per token, 2862.85 tokens per second) 0.56.883.290 I slot print_timing: id 0 | task 4272 | eval time = 576.49 ms / 63 tokens ( 9.30 ms per token, 107.55 tokens per second) 0.56.883.292 I slot print_timing: id 0 | task 4272 | total time = 753.24 ms / 569 tokens 0.56.883.293 I slot print_timing: id 0 | task 4272 | graphs reused = 3969 0.56.883.294 I slot print_timing: id 0 | task 4272 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.883.341 I slot release: id 0 | task 4272 | stop processing: n_tokens = 597, truncated = 0 0.56.887.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 56789969 0.56.887.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.56.898.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.56.977.144 I slot launch_slot_: id 0 | task 4338 | processing task, is_child = 0 0.57.510.675 I slot print_timing: id 0 | task 4338 | prompt eval time = 165.19 ms / 436 tokens ( 0.38 ms per token, 2639.43 tokens per second) 0.57.510.682 I slot print_timing: id 0 | task 4338 | eval time = 368.32 ms / 40 tokens ( 9.44 ms per token, 105.89 tokens per second) 0.57.510.684 I slot print_timing: id 0 | task 4338 | total time = 533.51 ms / 476 tokens 0.57.510.685 I slot print_timing: id 0 | task 4338 | graphs reused = 4007 0.57.510.686 I slot print_timing: id 0 | task 4338 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.510.721 I slot release: id 0 | task 4338 | stop processing: n_tokens = 504, truncated = 0 0.57.532.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 57417349 0.57.532.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.57.616.233 I slot launch_slot_: id 0 | task 4381 | processing task, is_child = 0 0.58.372.518 I slot print_timing: id 0 | task 4381 | prompt eval time = 187.34 ms / 519 tokens ( 0.36 ms per token, 2770.42 tokens per second) 0.58.372.524 I slot print_timing: id 0 | task 4381 | eval time = 568.93 ms / 62 tokens ( 9.33 ms per token, 107.22 tokens per second) 0.58.372.525 I slot print_timing: id 0 | task 4381 | total time = 756.26 ms / 581 tokens 0.58.372.526 I slot print_timing: id 0 | task 4381 | graphs reused = 4067 0.58.372.527 I slot print_timing: id 0 | task 4381 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.372.566 I slot release: id 0 | task 4381 | stop processing: n_tokens = 609, truncated = 0 0.58.401.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 58279194 0.58.401.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.58.412.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.58.508.576 I slot launch_slot_: id 0 | task 4447 | processing task, is_child = 0 0.59.115.410 I slot print_timing: id 0 | task 4447 | prompt eval time = 177.83 ms / 465 tokens ( 0.38 ms per token, 2614.80 tokens per second) 0.59.115.418 I slot print_timing: id 0 | task 4447 | eval time = 428.97 ms / 46 tokens ( 9.53 ms per token, 104.90 tokens per second) 0.59.115.420 I slot print_timing: id 0 | task 4447 | total time = 606.81 ms / 511 tokens 0.59.115.421 I slot print_timing: id 0 | task 4447 | graphs reused = 4110 0.59.115.422 I slot print_timing: id 0 | task 4447 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.115.471 I slot release: id 0 | task 4447 | stop processing: n_tokens = 542, truncated = 0 0.59.131.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 59022100 0.59.131.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.59.141.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.59.220.198 I slot launch_slot_: id 0 | task 4496 | processing task, is_child = 0 0.59.760.072 I slot print_timing: id 0 | task 4496 | prompt eval time = 165.21 ms / 431 tokens ( 0.38 ms per token, 2608.82 tokens per second) 0.59.760.079 I slot print_timing: id 0 | task 4496 | eval time = 374.64 ms / 41 tokens ( 9.37 ms per token, 106.77 tokens per second) 0.59.760.081 I slot print_timing: id 0 | task 4496 | total time = 539.85 ms / 472 tokens 0.59.760.081 I slot print_timing: id 0 | task 4496 | graphs reused = 4149 0.59.760.082 I slot print_timing: id 0 | task 4496 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.760.129 I slot release: id 0 | task 4496 | stop processing: n_tokens = 503, truncated = 0 0.59.782.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 59666758 0.59.782.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.59.794.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.59.904.089 I slot launch_slot_: id 0 | task 4540 | processing task, is_child = 0 1.00.479.154 I slot print_timing: id 0 | task 4540 | prompt eval time = 165.88 ms / 457 tokens ( 0.36 ms per token, 2754.94 tokens per second) 1.00.479.161 I slot print_timing: id 0 | task 4540 | eval time = 409.14 ms / 44 tokens ( 9.51 ms per token, 105.10 tokens per second) 1.00.479.163 I slot print_timing: id 0 | task 4540 | total time = 575.02 ms / 501 tokens 1.00.479.165 I slot print_timing: id 0 | task 4540 | graphs reused = 4190 1.00.479.166 I slot print_timing: id 0 | task 4540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.479.211 I slot release: id 0 | task 4540 | stop processing: n_tokens = 532, truncated = 0 1.00.499.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 60385840 1.00.499.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.00.602.615 I slot launch_slot_: id 0 | task 4587 | processing task, is_child = 0 1.01.172.614 I slot print_timing: id 0 | task 4587 | prompt eval time = 179.49 ms / 439 tokens ( 0.41 ms per token, 2445.82 tokens per second) 1.01.172.622 I slot print_timing: id 0 | task 4587 | eval time = 390.49 ms / 42 tokens ( 9.52 ms per token, 105.00 tokens per second) 1.01.172.623 I slot print_timing: id 0 | task 4587 | total time = 569.98 ms / 481 tokens 1.01.172.624 I slot print_timing: id 0 | task 4587 | graphs reused = 4230 1.01.172.626 I slot print_timing: id 0 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.172.670 I slot release: id 0 | task 4587 | stop processing: n_tokens = 512, truncated = 0 1.01.197.341 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 61079299 1.01.197.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.01.211.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.01.310.225 I slot launch_slot_: id 0 | task 4632 | processing task, is_child = 0 1.02.026.538 I slot print_timing: id 0 | task 4632 | prompt eval time = 193.49 ms / 606 tokens ( 0.32 ms per token, 3131.90 tokens per second) 1.02.026.545 I slot print_timing: id 0 | task 4632 | eval time = 522.79 ms / 56 tokens ( 9.51 ms per token, 105.20 tokens per second) 1.02.026.546 I slot print_timing: id 0 | task 4632 | total time = 716.29 ms / 662 tokens 1.02.026.547 I slot print_timing: id 0 | task 4632 | graphs reused = 4284 1.02.026.548 I slot print_timing: id 0 | task 4632 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.026.590 I slot release: id 0 | task 4632 | stop processing: n_tokens = 693, truncated = 0 1.02.044.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 61933218 1.02.044.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.02.058.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.02.174.009 I slot launch_slot_: id 0 | task 4692 | processing task, is_child = 0 1.02.745.470 I slot print_timing: id 0 | task 4692 | prompt eval time = 179.40 ms / 477 tokens ( 0.38 ms per token, 2658.83 tokens per second) 1.02.745.475 I slot print_timing: id 0 | task 4692 | eval time = 392.03 ms / 41 tokens ( 9.80 ms per token, 102.03 tokens per second) 1.02.745.476 I slot print_timing: id 0 | task 4692 | total time = 571.43 ms / 518 tokens 1.02.745.477 I slot print_timing: id 0 | task 4692 | graphs reused = 4322 1.02.745.478 I slot print_timing: id 0 | task 4692 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.745.512 I slot release: id 0 | task 4692 | stop processing: n_tokens = 549, truncated = 0 1.02.751.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 62652141 1.02.751.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.02.831.923 I slot launch_slot_: id 0 | task 4736 | processing task, is_child = 0 1.03.633.303 I slot print_timing: id 0 | task 4736 | prompt eval time = 247.18 ms / 845 tokens ( 0.29 ms per token, 3418.56 tokens per second) 1.03.633.310 I slot print_timing: id 0 | task 4736 | eval time = 554.17 ms / 60 tokens ( 9.39 ms per token, 106.46 tokens per second) 1.03.633.311 I slot print_timing: id 0 | task 4736 | total time = 801.36 ms / 905 tokens 1.03.633.312 I slot print_timing: id 0 | task 4736 | graphs reused = 4380 1.03.633.313 I slot print_timing: id 0 | task 4736 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.633.374 I slot release: id 0 | task 4736 | stop processing: n_tokens = 936, truncated = 0 1.03.637.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 63540002 1.03.637.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.043 MiB) 1.03.648.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.03.724.031 I slot launch_slot_: id 0 | task 4800 | processing task, is_child = 0 1.04.293.375 I slot print_timing: id 0 | task 4800 | prompt eval time = 169.77 ms / 459 tokens ( 0.37 ms per token, 2703.64 tokens per second) 1.04.293.381 I slot print_timing: id 0 | task 4800 | eval time = 399.55 ms / 43 tokens ( 9.51 ms per token, 105.12 tokens per second) 1.04.293.382 I slot print_timing: id 0 | task 4800 | total time = 569.32 ms / 502 tokens 1.04.293.383 I slot print_timing: id 0 | task 4800 | graphs reused = 4420 1.04.293.384 I slot print_timing: id 0 | task 4800 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.293.423 I slot release: id 0 | task 4800 | stop processing: n_tokens = 533, truncated = 0 1.04.322.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 64200052 1.04.323.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.04.386.378 I slot launch_slot_: id 0 | task 4846 | processing task, is_child = 0 1.05.001.521 I slot print_timing: id 0 | task 4846 | prompt eval time = 194.56 ms / 670 tokens ( 0.29 ms per token, 3443.63 tokens per second) 1.05.001.527 I slot print_timing: id 0 | task 4846 | eval time = 420.56 ms / 47 tokens ( 9.14 ms per token, 109.38 tokens per second) 1.05.001.528 I slot print_timing: id 0 | task 4846 | total time = 615.12 ms / 717 tokens 1.05.001.529 I slot print_timing: id 0 | task 4846 | graphs reused = 4465 1.05.001.530 I slot print_timing: id 0 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.001.572 I slot release: id 0 | task 4846 | stop processing: n_tokens = 748, truncated = 0 1.05.024.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 64908200 1.05.024.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.05.032.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.05.111.609 I slot launch_slot_: id 0 | task 4897 | processing task, is_child = 0 1.05.936.245 I slot print_timing: id 0 | task 4897 | prompt eval time = 221.45 ms / 775 tokens ( 0.29 ms per token, 3499.72 tokens per second) 1.05.936.251 I slot print_timing: id 0 | task 4897 | eval time = 603.17 ms / 63 tokens ( 9.73 ms per token, 102.79 tokens per second) 1.05.936.253 I slot print_timing: id 0 | task 4897 | total time = 824.61 ms / 838 tokens 1.05.936.253 I slot print_timing: id 0 | task 4897 | graphs reused = 4526 1.05.936.255 I slot print_timing: id 0 | task 4897 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.936.305 I slot release: id 0 | task 4897 | stop processing: n_tokens = 869, truncated = 0 1.05.956.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 65842935 1.05.956.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.05.960.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.06.041.682 I slot launch_slot_: id 0 | task 4964 | processing task, is_child = 0 1.06.858.156 I slot print_timing: id 0 | task 4964 | prompt eval time = 179.66 ms / 573 tokens ( 0.31 ms per token, 3189.43 tokens per second) 1.06.858.162 I slot print_timing: id 0 | task 4964 | eval time = 636.80 ms / 71 tokens ( 9.10 ms per token, 109.93 tokens per second) 1.06.858.164 I slot print_timing: id 0 | task 4964 | total time = 816.45 ms / 644 tokens 1.06.858.164 I slot print_timing: id 0 | task 4964 | graphs reused = 4595 1.06.858.165 I slot print_timing: id 0 | task 4964 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.858.206 I slot release: id 0 | task 4964 | stop processing: n_tokens = 675, truncated = 0 1.06.884.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 66764835 1.06.884.866 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.06.899.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.06.983.950 I slot launch_slot_: id 0 | task 5039 | processing task, is_child = 0 1.07.720.877 I slot print_timing: id 0 | task 5039 | prompt eval time = 158.32 ms / 461 tokens ( 0.34 ms per token, 2911.90 tokens per second) 1.07.720.882 I slot print_timing: id 0 | task 5039 | eval time = 578.59 ms / 64 tokens ( 9.18 ms per token, 108.89 tokens per second) 1.07.720.883 I slot print_timing: id 0 | task 5039 | total time = 736.91 ms / 525 tokens 1.07.720.884 I slot print_timing: id 0 | task 5039 | graphs reused = 4656 1.07.720.885 I slot print_timing: id 0 | task 5039 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.720.917 I slot release: id 0 | task 5039 | stop processing: n_tokens = 556, truncated = 0 1.07.749.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 67627546 1.07.749.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.07.827.256 I slot launch_slot_: id 0 | task 5106 | processing task, is_child = 0 1.08.544.496 I slot print_timing: id 0 | task 5106 | prompt eval time = 181.55 ms / 609 tokens ( 0.30 ms per token, 3354.50 tokens per second) 1.08.544.502 I slot print_timing: id 0 | task 5106 | eval time = 535.67 ms / 60 tokens ( 9.08 ms per token, 110.14 tokens per second) 1.08.544.503 I slot print_timing: id 0 | task 5106 | total time = 717.22 ms / 669 tokens 1.08.544.504 I slot print_timing: id 0 | task 5106 | graphs reused = 4714 1.08.544.504 I slot print_timing: id 0 | task 5106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.544.542 I slot release: id 0 | task 5106 | stop processing: n_tokens = 700, truncated = 0 1.08.569.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 700, t_last = 68451171 1.08.569.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.08.583.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.08.655.516 I slot launch_slot_: id 0 | task 5170 | processing task, is_child = 0 1.09.420.153 I slot print_timing: id 0 | task 5170 | prompt eval time = 218.62 ms / 791 tokens ( 0.28 ms per token, 3618.17 tokens per second) 1.09.420.159 I slot print_timing: id 0 | task 5170 | eval time = 545.99 ms / 61 tokens ( 9.10 ms per token, 109.89 tokens per second) 1.09.420.160 I slot print_timing: id 0 | task 5170 | total time = 764.61 ms / 852 tokens 1.09.420.161 I slot print_timing: id 0 | task 5170 | graphs reused = 4773 1.09.420.162 I slot print_timing: id 0 | task 5170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.420.203 I slot release: id 0 | task 5170 | stop processing: n_tokens = 883, truncated = 0 1.09.436.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 69326832 1.09.436.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.09.558.254 I slot launch_slot_: id 0 | task 5235 | processing task, is_child = 0 1.10.234.677 I slot print_timing: id 0 | task 5235 | prompt eval time = 174.90 ms / 533 tokens ( 0.33 ms per token, 3047.47 tokens per second) 1.10.234.683 I slot print_timing: id 0 | task 5235 | eval time = 501.50 ms / 56 tokens ( 9.12 ms per token, 109.67 tokens per second) 1.10.234.684 I slot print_timing: id 0 | task 5235 | total time = 676.40 ms / 589 tokens 1.10.234.685 I slot print_timing: id 0 | task 5235 | graphs reused = 4827 1.10.234.686 I slot print_timing: id 0 | task 5235 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.234.721 I slot release: id 0 | task 5235 | stop processing: n_tokens = 677, truncated = 0 1.10.256.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 70141350 1.10.256.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.10.336.086 I slot launch_slot_: id 0 | task 5295 | processing task, is_child = 0 1.10.952.138 I slot print_timing: id 0 | task 5295 | prompt eval time = 177.59 ms / 566 tokens ( 0.31 ms per token, 3187.12 tokens per second) 1.10.952.143 I slot print_timing: id 0 | task 5295 | eval time = 438.44 ms / 46 tokens ( 9.74 ms per token, 102.64 tokens per second) 1.10.952.144 I slot print_timing: id 0 | task 5295 | total time = 616.03 ms / 612 tokens 1.10.952.145 I slot print_timing: id 0 | task 5295 | graphs reused = 4871 1.10.952.146 I slot print_timing: id 0 | task 5295 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.952.186 I slot release: id 0 | task 5295 | stop processing: n_tokens = 643, truncated = 0 1.10.974.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 70858815 1.10.974.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.11.054.453 I slot launch_slot_: id 0 | task 5345 | processing task, is_child = 0 1.11.595.611 I slot print_timing: id 0 | task 5345 | prompt eval time = 153.72 ms / 443 tokens ( 0.35 ms per token, 2881.94 tokens per second) 1.11.595.617 I slot print_timing: id 0 | task 5345 | eval time = 387.42 ms / 43 tokens ( 9.22 ms per token, 108.41 tokens per second) 1.11.595.619 I slot print_timing: id 0 | task 5345 | total time = 541.14 ms / 486 tokens 1.11.595.619 I slot print_timing: id 0 | task 5345 | graphs reused = 4911 1.11.595.620 I slot print_timing: id 0 | task 5345 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.595.650 I slot release: id 0 | task 5345 | stop processing: n_tokens = 517, truncated = 0 1.11.615.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 71502279 1.11.615.417 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.11.680.158 I slot launch_slot_: id 0 | task 5391 | processing task, is_child = 0 1.12.413.558 I slot print_timing: id 0 | task 5391 | prompt eval time = 152.59 ms / 487 tokens ( 0.31 ms per token, 3191.66 tokens per second) 1.12.413.564 I slot print_timing: id 0 | task 5391 | eval time = 580.79 ms / 65 tokens ( 9.07 ms per token, 110.19 tokens per second) 1.12.413.565 I slot print_timing: id 0 | task 5391 | total time = 733.38 ms / 552 tokens 1.12.413.567 I slot print_timing: id 0 | task 5391 | graphs reused = 4974 1.12.413.568 I slot print_timing: id 0 | task 5391 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.413.601 I slot release: id 0 | task 5391 | stop processing: n_tokens = 583, truncated = 0 1.12.417.900 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 72320230 1.12.417.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.12.488.764 I slot launch_slot_: id 0 | task 5459 | processing task, is_child = 0 1.13.068.568 I slot print_timing: id 0 | task 5459 | prompt eval time = 160.73 ms / 507 tokens ( 0.32 ms per token, 3154.28 tokens per second) 1.13.068.573 I slot print_timing: id 0 | task 5459 | eval time = 419.05 ms / 47 tokens ( 9.11 ms per token, 109.77 tokens per second) 1.13.068.574 I slot print_timing: id 0 | task 5459 | total time = 579.78 ms / 554 tokens 1.13.068.575 I slot print_timing: id 0 | task 5459 | graphs reused = 5019 1.13.068.576 I slot print_timing: id 0 | task 5459 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.068.612 I slot release: id 0 | task 5459 | stop processing: n_tokens = 585, truncated = 0 1.13.087.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 72975240 1.13.087.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.13.105.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.13.175.950 I slot launch_slot_: id 0 | task 5509 | processing task, is_child = 0 1.13.946.566 I slot print_timing: id 0 | task 5509 | prompt eval time = 181.49 ms / 633 tokens ( 0.29 ms per token, 3487.78 tokens per second) 1.13.946.572 I slot print_timing: id 0 | task 5509 | eval time = 589.11 ms / 66 tokens ( 9.06 ms per token, 110.34 tokens per second) 1.13.946.573 I slot print_timing: id 0 | task 5509 | total time = 770.60 ms / 699 tokens 1.13.946.574 I slot print_timing: id 0 | task 5509 | graphs reused = 5083 1.13.946.575 I slot print_timing: id 0 | task 5509 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.946.616 I slot release: id 0 | task 5509 | stop processing: n_tokens = 730, truncated = 0 1.13.966.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 73853244 1.13.966.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.14.041.204 I slot launch_slot_: id 0 | task 5579 | processing task, is_child = 0 1.14.637.653 I slot print_timing: id 0 | task 5579 | prompt eval time = 177.36 ms / 571 tokens ( 0.31 ms per token, 3219.44 tokens per second) 1.14.637.658 I slot print_timing: id 0 | task 5579 | eval time = 419.07 ms / 47 tokens ( 9.11 ms per token, 109.77 tokens per second) 1.14.637.660 I slot print_timing: id 0 | task 5579 | total time = 596.43 ms / 618 tokens 1.14.637.660 I slot print_timing: id 0 | task 5579 | graphs reused = 5128 1.14.637.661 I slot print_timing: id 0 | task 5579 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.637.696 I slot release: id 0 | task 5579 | stop processing: n_tokens = 649, truncated = 0 1.14.667.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 74544324 1.14.667.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.14.737.373 I slot launch_slot_: id 0 | task 5630 | processing task, is_child = 0 1.15.347.197 I slot print_timing: id 0 | task 5630 | prompt eval time = 217.11 ms / 798 tokens ( 0.27 ms per token, 3675.51 tokens per second) 1.15.347.203 I slot print_timing: id 0 | task 5630 | eval time = 392.69 ms / 44 tokens ( 9.13 ms per token, 109.50 tokens per second) 1.15.347.204 I slot print_timing: id 0 | task 5630 | total time = 609.80 ms / 842 tokens 1.15.347.205 I slot print_timing: id 0 | task 5630 | graphs reused = 5170 1.15.347.207 I slot print_timing: id 0 | task 5630 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.347.250 I slot release: id 0 | task 5630 | stop processing: n_tokens = 873, truncated = 0 1.15.363.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 75253878 1.15.363.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.15.385.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.15.465.220 I slot launch_slot_: id 0 | task 5678 | processing task, is_child = 0 1.16.024.848 I slot print_timing: id 0 | task 5678 | prompt eval time = 176.90 ms / 572 tokens ( 0.31 ms per token, 3233.50 tokens per second) 1.16.024.853 I slot print_timing: id 0 | task 5678 | eval time = 382.71 ms / 43 tokens ( 9.11 ms per token, 109.74 tokens per second) 1.16.024.854 I slot print_timing: id 0 | task 5678 | total time = 559.61 ms / 615 tokens 1.16.024.855 I slot print_timing: id 0 | task 5678 | graphs reused = 5211 1.16.024.856 I slot print_timing: id 0 | task 5678 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.024.891 I slot release: id 0 | task 5678 | stop processing: n_tokens = 646, truncated = 0 1.16.049.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 75931519 1.16.049.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.16.118.919 I slot launch_slot_: id 0 | task 5725 | processing task, is_child = 0 1.16.877.153 I slot print_timing: id 0 | task 5725 | prompt eval time = 186.14 ms / 613 tokens ( 0.30 ms per token, 3293.22 tokens per second) 1.16.877.159 I slot print_timing: id 0 | task 5725 | eval time = 572.07 ms / 64 tokens ( 9.08 ms per token, 110.13 tokens per second) 1.16.877.160 I slot print_timing: id 0 | task 5725 | total time = 758.21 ms / 677 tokens 1.16.877.161 I slot print_timing: id 0 | task 5725 | graphs reused = 5273 1.16.877.162 I slot print_timing: id 0 | task 5725 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.877.197 I slot release: id 0 | task 5725 | stop processing: n_tokens = 708, truncated = 0 1.16.890.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 76783825 1.16.890.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.16.972.594 I slot launch_slot_: id 0 | task 5793 | processing task, is_child = 0 1.17.831.889 I slot print_timing: id 0 | task 5793 | prompt eval time = 177.03 ms / 580 tokens ( 0.31 ms per token, 3276.30 tokens per second) 1.17.831.894 I slot print_timing: id 0 | task 5793 | eval time = 682.25 ms / 76 tokens ( 9.10 ms per token, 109.93 tokens per second) 1.17.831.895 I slot print_timing: id 0 | task 5793 | total time = 859.27 ms / 656 tokens 1.17.831.897 I slot print_timing: id 0 | task 5793 | graphs reused = 5347 1.17.831.897 I slot print_timing: id 0 | task 5793 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.831.932 I slot release: id 0 | task 5793 | stop processing: n_tokens = 687, truncated = 0 1.17.847.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 77738560 1.17.847.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.17.927.975 I slot launch_slot_: id 0 | task 5873 | processing task, is_child = 0 1.18.582.870 I slot print_timing: id 0 | task 5873 | prompt eval time = 202.25 ms / 716 tokens ( 0.28 ms per token, 3540.23 tokens per second) 1.18.582.875 I slot print_timing: id 0 | task 5873 | eval time = 452.63 ms / 50 tokens ( 9.24 ms per token, 108.26 tokens per second) 1.18.582.877 I slot print_timing: id 0 | task 5873 | total time = 654.87 ms / 766 tokens 1.18.582.878 I slot print_timing: id 0 | task 5873 | graphs reused = 5394 1.18.582.879 I slot print_timing: id 0 | task 5873 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.582.918 I slot release: id 0 | task 5873 | stop processing: n_tokens = 797, truncated = 0 1.18.612.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 78489546 1.18.612.357 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.18.632.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.18.734.824 I slot launch_slot_: id 0 | task 5927 | processing task, is_child = 0 1.19.864.768 I slot print_timing: id 0 | task 5927 | prompt eval time = 214.68 ms / 799 tokens ( 0.27 ms per token, 3721.75 tokens per second) 1.19.864.774 I slot print_timing: id 0 | task 5927 | eval time = 915.24 ms / 102 tokens ( 9.06 ms per token, 110.35 tokens per second) 1.19.864.776 I slot print_timing: id 0 | task 5927 | total time = 1129.92 ms / 901 tokens 1.19.864.776 I slot print_timing: id 0 | task 5927 | graphs reused = 5494 1.19.864.777 I slot print_timing: id 0 | task 5927 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.864.819 I slot release: id 0 | task 5927 | stop processing: n_tokens = 932, truncated = 0 1.19.883.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 79771447 1.19.883.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.19.960.147 I slot launch_slot_: id 0 | task 6033 | processing task, is_child = 0 1.21.099.231 I slot print_timing: id 0 | task 6033 | prompt eval time = 134.90 ms / 361 tokens ( 0.37 ms per token, 2676.16 tokens per second) 1.21.099.237 I slot print_timing: id 0 | task 6033 | eval time = 1004.17 ms / 112 tokens ( 9.05 ms per token, 110.54 tokens per second) 1.21.099.238 I slot print_timing: id 0 | task 6033 | total time = 1139.07 ms / 473 tokens 1.21.099.239 I slot print_timing: id 0 | task 6033 | graphs reused = 5604 1.21.099.240 I slot print_timing: id 0 | task 6033 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.099.270 I slot release: id 0 | task 6033 | stop processing: n_tokens = 504, truncated = 0 1.21.113.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 81005898 1.21.113.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.21.184.886 I slot launch_slot_: id 0 | task 6148 | processing task, is_child = 0 1.22.307.612 I slot print_timing: id 0 | task 6148 | prompt eval time = 134.68 ms / 381 tokens ( 0.35 ms per token, 2828.93 tokens per second) 1.22.307.618 I slot print_timing: id 0 | task 6148 | eval time = 988.02 ms / 108 tokens ( 9.23 ms per token, 108.30 tokens per second) 1.22.307.619 I slot print_timing: id 0 | task 6148 | total time = 1122.70 ms / 489 tokens 1.22.307.620 I slot print_timing: id 0 | task 6148 | graphs reused = 5709 1.22.307.621 I slot print_timing: id 0 | task 6148 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.307.657 I slot release: id 0 | task 6148 | stop processing: n_tokens = 520, truncated = 0 1.22.336.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 82214285 1.22.336.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.22.403.074 I slot launch_slot_: id 0 | task 6259 | processing task, is_child = 0 1.23.652.660 I slot print_timing: id 0 | task 6259 | prompt eval time = 130.50 ms / 365 tokens ( 0.36 ms per token, 2796.83 tokens per second) 1.23.652.666 I slot print_timing: id 0 | task 6259 | eval time = 1119.06 ms / 124 tokens ( 9.10 ms per token, 109.91 tokens per second) 1.23.652.667 I slot print_timing: id 0 | task 6259 | total time = 1249.57 ms / 489 tokens 1.23.652.667 I slot print_timing: id 0 | task 6259 | graphs reused = 5830 1.23.652.668 I slot print_timing: id 0 | task 6259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.652.697 I slot release: id 0 | task 6259 | stop processing: n_tokens = 520, truncated = 0 1.23.675.839 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 83559325 1.23.675.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.23.737.618 I slot launch_slot_: id 0 | task 6386 | processing task, is_child = 0 1.24.832.126 I slot print_timing: id 0 | task 6386 | prompt eval time = 130.97 ms / 333 tokens ( 0.39 ms per token, 2542.64 tokens per second) 1.24.832.133 I slot print_timing: id 0 | task 6386 | eval time = 963.52 ms / 107 tokens ( 9.09 ms per token, 110.01 tokens per second) 1.24.832.134 I slot print_timing: id 0 | task 6386 | total time = 1094.48 ms / 440 tokens 1.24.832.135 I slot print_timing: id 0 | task 6386 | graphs reused = 5935 1.24.832.136 I slot print_timing: id 0 | task 6386 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.832.168 I slot release: id 0 | task 6386 | stop processing: n_tokens = 471, truncated = 0 1.24.850.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 84738797 1.24.893.147 I slot launch_slot_: id 0 | task 6496 | processing task, is_child = 0 1.26.275.443 I slot print_timing: id 0 | task 6496 | prompt eval time = 136.25 ms / 403 tokens ( 0.34 ms per token, 2957.91 tokens per second) 1.26.275.449 I slot print_timing: id 0 | task 6496 | eval time = 1246.03 ms / 138 tokens ( 9.10 ms per token, 109.95 tokens per second) 1.26.275.450 I slot print_timing: id 0 | task 6496 | total time = 1382.28 ms / 541 tokens 1.26.275.451 I slot print_timing: id 0 | task 6496 | graphs reused = 6070 1.26.275.452 I slot print_timing: id 0 | task 6496 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.275.482 I slot release: id 0 | task 6496 | stop processing: n_tokens = 572, truncated = 0 1.26.296.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 86182111 1.26.296.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.26.363.121 I slot launch_slot_: id 0 | task 6637 | processing task, is_child = 0 1.28.169.563 I slot print_timing: id 0 | task 6637 | prompt eval time = 138.51 ms / 411 tokens ( 0.34 ms per token, 2967.29 tokens per second) 1.28.169.569 I slot print_timing: id 0 | task 6637 | eval time = 1667.91 ms / 185 tokens ( 9.06 ms per token, 110.32 tokens per second) 1.28.169.570 I slot print_timing: id 0 | task 6637 | total time = 1806.42 ms / 596 tokens 1.28.169.571 I slot print_timing: id 0 | task 6637 | graphs reused = 6252 1.28.169.572 I slot print_timing: id 0 | task 6637 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.169.604 I slot release: id 0 | task 6637 | stop processing: n_tokens = 627, truncated = 0 1.28.189.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 88076232 1.28.189.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.28.247.834 I slot launch_slot_: id 0 | task 6825 | processing task, is_child = 0 1.30.442.923 I slot print_timing: id 0 | task 6825 | prompt eval time = 160.04 ms / 490 tokens ( 0.33 ms per token, 3061.81 tokens per second) 1.30.442.928 I slot print_timing: id 0 | task 6825 | eval time = 2035.03 ms / 225 tokens ( 9.08 ms per token, 110.07 tokens per second) 1.30.442.929 I slot print_timing: id 0 | task 6825 | total time = 2195.07 ms / 715 tokens 1.30.442.930 I slot print_timing: id 0 | task 6825 | graphs reused = 6475 1.30.442.931 I slot print_timing: id 0 | task 6825 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.442.962 I slot release: id 0 | task 6825 | stop processing: n_tokens = 746, truncated = 0 1.30.461.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 90349591 1.30.461.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.30.522.265 I slot launch_slot_: id 0 | task 7053 | processing task, is_child = 0 1.33.657.736 I slot print_timing: id 0 | task 7053 | n_gen = 333, tg = 110.42 t/s, tg_3s = 110.76 t/s 1.34.035.598 I slot print_timing: id 0 | task 7053 | prompt eval time = 128.82 ms / 344 tokens ( 0.37 ms per token, 2670.43 tokens per second) 1.34.035.603 I slot print_timing: id 0 | task 7053 | eval time = 3384.49 ms / 375 tokens ( 9.05 ms per token, 110.50 tokens per second) 1.34.035.604 I slot print_timing: id 0 | task 7053 | total time = 3513.31 ms / 719 tokens 1.34.035.605 I slot print_timing: id 0 | task 7053 | graphs reused = 6847 1.34.035.606 I slot print_timing: id 0 | task 7053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.035.635 I slot release: id 0 | task 7053 | stop processing: n_tokens = 750, truncated = 0 1.34.055.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 93942264 1.34.055.134 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.34.123.794 I slot launch_slot_: id 0 | task 7431 | processing task, is_child = 0 1.35.791.884 I slot print_timing: id 0 | task 7431 | prompt eval time = 129.54 ms / 347 tokens ( 0.37 ms per token, 2678.75 tokens per second) 1.35.791.890 I slot print_timing: id 0 | task 7431 | eval time = 1538.53 ms / 171 tokens ( 9.05 ms per token, 110.49 tokens per second) 1.35.791.891 I slot print_timing: id 0 | task 7431 | total time = 1668.07 ms / 518 tokens 1.35.791.892 I slot print_timing: id 0 | task 7431 | graphs reused = 7015 1.35.791.893 I slot print_timing: id 0 | task 7431 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.791.920 I slot release: id 0 | task 7431 | stop processing: n_tokens = 549, truncated = 0 1.35.819.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 95698549 1.35.819.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.645 MiB) 1.35.890.911 I slot launch_slot_: id 0 | task 7605 | processing task, is_child = 0 1.37.167.608 I slot print_timing: id 0 | task 7605 | prompt eval time = 139.61 ms / 401 tokens ( 0.35 ms per token, 2872.23 tokens per second) 1.37.167.614 I slot print_timing: id 0 | task 7605 | eval time = 1137.06 ms / 126 tokens ( 9.10 ms per token, 109.93 tokens per second) 1.37.167.615 I slot print_timing: id 0 | task 7605 | total time = 1276.68 ms / 527 tokens 1.37.167.616 I slot print_timing: id 0 | task 7605 | graphs reused = 7138 1.37.167.617 I slot print_timing: id 0 | task 7605 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.167.647 I slot release: id 0 | task 7605 | stop processing: n_tokens = 558, truncated = 0 1.37.186.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 97074276 1.37.186.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.37.264.009 I slot launch_slot_: id 0 | task 7734 | processing task, is_child = 0 1.38.477.425 I slot print_timing: id 0 | task 7734 | prompt eval time = 150.08 ms / 456 tokens ( 0.33 ms per token, 3038.30 tokens per second) 1.38.477.430 I slot print_timing: id 0 | task 7734 | eval time = 1063.31 ms / 115 tokens ( 9.33 ms per token, 107.21 tokens per second) 1.38.477.431 I slot print_timing: id 0 | task 7734 | total time = 1213.40 ms / 571 tokens 1.38.477.433 I slot print_timing: id 0 | task 7734 | graphs reused = 7250 1.38.477.434 I slot print_timing: id 0 | task 7734 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.477.465 I slot release: id 0 | task 7734 | stop processing: n_tokens = 602, truncated = 0 1.38.491.616 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 1.38.491.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.38.572.838 I slot launch_slot_: id 0 | task 7852 | processing task, is_child = 0 1.39.721.251 I slot print_timing: id 0 | task 7852 | prompt eval time = 140.52 ms / 406 tokens ( 0.35 ms per token, 2889.27 tokens per second) 1.39.721.257 I slot print_timing: id 0 | task 7852 | eval time = 1007.87 ms / 112 tokens ( 9.08 ms per token, 110.13 tokens per second) 1.39.721.258 I slot print_timing: id 0 | task 7852 | total time = 1148.39 ms / 518 tokens 1.39.721.259 I slot print_timing: id 0 | task 7852 | graphs reused = 7359 1.39.721.260 I slot print_timing: id 0 | task 7852 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.721.291 I slot release: id 0 | task 7852 | stop processing: n_tokens = 549, truncated = 0 1.39.738.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 99627920 1.39.793.030 I slot launch_slot_: id 0 | task 7967 | processing task, is_child = 0 1.41.710.030 I slot print_timing: id 0 | task 7967 | prompt eval time = 140.99 ms / 406 tokens ( 0.35 ms per token, 2879.62 tokens per second) 1.41.710.036 I slot print_timing: id 0 | task 7967 | eval time = 1775.99 ms / 197 tokens ( 9.06 ms per token, 110.36 tokens per second) 1.41.710.037 I slot print_timing: id 0 | task 7967 | total time = 1916.98 ms / 603 tokens 1.41.710.038 I slot print_timing: id 0 | task 7967 | graphs reused = 7553 1.41.710.039 I slot print_timing: id 0 | task 7967 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.710.071 I slot release: id 0 | task 7967 | stop processing: n_tokens = 634, truncated = 0 1.41.736.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 634, t_last = 101616700 1.41.736.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.41.807.960 I slot launch_slot_: id 0 | task 8167 | processing task, is_child = 0 1.43.252.754 I slot print_timing: id 0 | task 8167 | prompt eval time = 144.59 ms / 444 tokens ( 0.33 ms per token, 3070.69 tokens per second) 1.43.252.760 I slot print_timing: id 0 | task 8167 | eval time = 1300.18 ms / 144 tokens ( 9.09 ms per token, 109.98 tokens per second) 1.43.252.761 I slot print_timing: id 0 | task 8167 | total time = 1444.77 ms / 588 tokens 1.43.252.762 I slot print_timing: id 0 | task 8167 | graphs reused = 7694 1.43.252.763 I slot print_timing: id 0 | task 8167 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.252.793 I slot release: id 0 | task 8167 | stop processing: n_tokens = 619, truncated = 0 1.43.256.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 103159422 1.43.256.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.43.323.800 I slot launch_slot_: id 0 | task 8314 | processing task, is_child = 0 1.44.383.093 I slot print_timing: id 0 | task 8314 | prompt eval time = 136.73 ms / 372 tokens ( 0.37 ms per token, 2720.61 tokens per second) 1.44.383.099 I slot print_timing: id 0 | task 8314 | eval time = 922.54 ms / 103 tokens ( 9.04 ms per token, 110.56 tokens per second) 1.44.383.100 I slot print_timing: id 0 | task 8314 | total time = 1059.27 ms / 475 tokens 1.44.383.101 I slot print_timing: id 0 | task 8314 | graphs reused = 7795 1.44.383.101 I slot print_timing: id 0 | task 8314 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.383.132 I slot release: id 0 | task 8314 | stop processing: n_tokens = 506, truncated = 0 1.44.403.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 104289761 1.44.403.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.44.475.800 I slot launch_slot_: id 0 | task 8420 | processing task, is_child = 0 1.46.700.434 I slot print_timing: id 0 | task 8420 | prompt eval time = 144.89 ms / 454 tokens ( 0.32 ms per token, 3133.41 tokens per second) 1.46.700.440 I slot print_timing: id 0 | task 8420 | eval time = 2079.72 ms / 230 tokens ( 9.08 ms per token, 110.11 tokens per second) 1.46.700.441 I slot print_timing: id 0 | task 8420 | total time = 2224.61 ms / 684 tokens 1.46.700.442 I slot print_timing: id 0 | task 8420 | graphs reused = 8022 1.46.700.443 I slot print_timing: id 0 | task 8420 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.700.474 I slot release: id 0 | task 8420 | stop processing: n_tokens = 715, truncated = 0 1.46.715.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 106607102 1.46.715.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.46.786.127 I slot launch_slot_: id 0 | task 8653 | processing task, is_child = 0 1.48.960.813 I slot print_timing: id 0 | task 8653 | prompt eval time = 133.73 ms / 354 tokens ( 0.38 ms per token, 2647.14 tokens per second) 1.48.960.819 I slot print_timing: id 0 | task 8653 | eval time = 2040.94 ms / 226 tokens ( 9.07 ms per token, 110.24 tokens per second) 1.48.960.820 I slot print_timing: id 0 | task 8653 | total time = 2174.67 ms / 580 tokens 1.48.960.821 I slot print_timing: id 0 | task 8653 | graphs reused = 8245 1.48.960.821 I slot print_timing: id 0 | task 8653 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.960.850 I slot release: id 0 | task 8653 | stop processing: n_tokens = 611, truncated = 0 1.48.988.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 108867478 1.48.988.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.49.061.111 I slot launch_slot_: id 0 | task 8882 | processing task, is_child = 0 1.50.444.928 I slot print_timing: id 0 | task 8882 | prompt eval time = 128.32 ms / 334 tokens ( 0.38 ms per token, 2602.77 tokens per second) 1.50.444.934 I slot print_timing: id 0 | task 8882 | eval time = 1255.47 ms / 140 tokens ( 9.03 ms per token, 110.72 tokens per second) 1.50.444.935 I slot print_timing: id 0 | task 8882 | total time = 1383.80 ms / 474 tokens 1.50.444.936 I slot print_timing: id 0 | task 8882 | graphs reused = 8383 1.50.444.938 I slot print_timing: id 0 | task 8882 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.444.965 I slot release: id 0 | task 8882 | stop processing: n_tokens = 505, truncated = 0 1.50.468.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 110351594 1.50.468.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.50.548.951 I slot launch_slot_: id 0 | task 9025 | processing task, is_child = 0 1.52.274.162 I slot print_timing: id 0 | task 9025 | prompt eval time = 144.36 ms / 426 tokens ( 0.34 ms per token, 2950.96 tokens per second) 1.52.274.168 I slot print_timing: id 0 | task 9025 | eval time = 1580.83 ms / 175 tokens ( 9.09 ms per token, 110.07 tokens per second) 1.52.274.169 I slot print_timing: id 0 | task 9025 | total time = 1725.19 ms / 601 tokens 1.52.274.169 I slot print_timing: id 0 | task 9025 | graphs reused = 8555 1.52.274.170 I slot print_timing: id 0 | task 9025 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.274.203 I slot release: id 0 | task 9025 | stop processing: n_tokens = 632, truncated = 0 1.52.287.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 112180831 1.52.287.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.52.360.836 I slot launch_slot_: id 0 | task 9203 | processing task, is_child = 0 1.53.547.338 I slot print_timing: id 0 | task 9203 | prompt eval time = 131.86 ms / 366 tokens ( 0.36 ms per token, 2775.61 tokens per second) 1.53.547.343 I slot print_timing: id 0 | task 9203 | eval time = 1054.62 ms / 117 tokens ( 9.09 ms per token, 109.99 tokens per second) 1.53.547.344 I slot print_timing: id 0 | task 9203 | total time = 1186.48 ms / 483 tokens 1.53.547.345 I slot print_timing: id 0 | task 9203 | graphs reused = 8669 1.53.547.346 I slot print_timing: id 0 | task 9203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.547.376 I slot release: id 0 | task 9203 | stop processing: n_tokens = 514, truncated = 0 1.53.551.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 113454004 1.53.551.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.53.638.159 I slot launch_slot_: id 0 | task 9323 | processing task, is_child = 0 1.56.796.942 I slot print_timing: id 0 | task 9323 | n_gen = 333, tg = 110.45 t/s, tg_3s = 110.79 t/s 1.56.986.249 I slot print_timing: id 0 | task 9323 | prompt eval time = 152.96 ms / 462 tokens ( 0.33 ms per token, 3020.38 tokens per second) 1.56.986.255 I slot print_timing: id 0 | task 9323 | eval time = 3195.11 ms / 354 tokens ( 9.05 ms per token, 110.48 tokens per second) 1.56.986.256 I slot print_timing: id 0 | task 9323 | total time = 3348.07 ms / 816 tokens 1.56.986.257 I slot print_timing: id 0 | task 9323 | graphs reused = 9019 1.56.986.257 I slot print_timing: id 0 | task 9323 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.986.288 I slot release: id 0 | task 9323 | stop processing: n_tokens = 847, truncated = 0 1.57.014.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 847, t_last = 116892916 1.57.014.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.57.088.291 I slot launch_slot_: id 0 | task 9680 | processing task, is_child = 0 1.58.486.059 I slot print_timing: id 0 | task 9680 | prompt eval time = 139.72 ms / 396 tokens ( 0.35 ms per token, 2834.26 tokens per second) 1.58.486.064 I slot print_timing: id 0 | task 9680 | eval time = 1258.03 ms / 139 tokens ( 9.12 ms per token, 109.70 tokens per second) 1.58.486.066 I slot print_timing: id 0 | task 9680 | total time = 1397.75 ms / 535 tokens 1.58.486.066 I slot print_timing: id 0 | task 9680 | graphs reused = 9155 1.58.486.067 I slot print_timing: id 0 | task 9680 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.486.099 I slot release: id 0 | task 9680 | stop processing: n_tokens = 566, truncated = 0 1.58.508.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 118392728 1.58.556.110 I slot launch_slot_: id 0 | task 9822 | processing task, is_child = 0 2.00.174.172 I slot print_timing: id 0 | task 9822 | prompt eval time = 156.43 ms / 458 tokens ( 0.34 ms per token, 2927.92 tokens per second) 2.00.174.178 I slot print_timing: id 0 | task 9822 | eval time = 1461.61 ms / 161 tokens ( 9.14 ms per token, 109.47 tokens per second) 2.00.174.179 I slot print_timing: id 0 | task 9822 | total time = 1618.04 ms / 619 tokens 2.00.174.181 I slot print_timing: id 0 | task 9822 | graphs reused = 9313 2.00.174.182 I slot print_timing: id 0 | task 9822 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.174.219 I slot release: id 0 | task 9822 | stop processing: n_tokens = 650, truncated = 0 2.00.201.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 120080847 2.00.201.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.00.287.526 I slot launch_slot_: id 0 | task 9986 | processing task, is_child = 0 2.02.051.916 I slot print_timing: id 0 | task 9986 | prompt eval time = 158.75 ms / 458 tokens ( 0.35 ms per token, 2885.06 tokens per second) 2.02.051.922 I slot print_timing: id 0 | task 9986 | eval time = 1605.62 ms / 177 tokens ( 9.12 ms per token, 109.61 tokens per second) 2.02.051.923 I slot print_timing: id 0 | task 9986 | total time = 1764.37 ms / 635 tokens 2.02.051.924 I slot print_timing: id 0 | task 9986 | graphs reused = 9487 2.02.051.925 I slot print_timing: id 0 | task 9986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.051.956 I slot release: id 0 | task 9986 | stop processing: n_tokens = 666, truncated = 0 2.02.065.898 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 666, t_last = 121958585 2.02.065.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.02.148.347 I slot launch_slot_: id 0 | task 10166 | processing task, is_child = 0 2.04.194.040 I slot print_timing: id 0 | task 10166 | prompt eval time = 149.42 ms / 452 tokens ( 0.33 ms per token, 3024.97 tokens per second) 2.04.194.046 I slot print_timing: id 0 | task 10166 | eval time = 1896.25 ms / 210 tokens ( 9.07 ms per token, 110.22 tokens per second) 2.04.194.047 I slot print_timing: id 0 | task 10166 | total time = 2045.67 ms / 662 tokens 2.04.194.048 I slot print_timing: id 0 | task 10166 | graphs reused = 9694 2.04.194.049 I slot print_timing: id 0 | task 10166 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.194.080 I slot release: id 0 | task 10166 | stop processing: n_tokens = 693, truncated = 0 2.04.197.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 124100708 2.04.198.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.04.281.124 I slot launch_slot_: id 0 | task 10379 | processing task, is_child = 0 2.05.508.700 I slot print_timing: id 0 | task 10379 | prompt eval time = 143.31 ms / 404 tokens ( 0.35 ms per token, 2819.00 tokens per second) 2.05.508.706 I slot print_timing: id 0 | task 10379 | eval time = 1084.24 ms / 120 tokens ( 9.11 ms per token, 109.75 tokens per second) 2.05.508.706 I slot print_timing: id 0 | task 10379 | total time = 1227.55 ms / 524 tokens 2.05.508.707 I slot print_timing: id 0 | task 10379 | graphs reused = 9811 2.05.508.708 I slot print_timing: id 0 | task 10379 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.508.738 I slot release: id 0 | task 10379 | stop processing: n_tokens = 555, truncated = 0 2.05.533.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 125415367 2.05.533.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.05.610.653 I slot launch_slot_: id 0 | task 10502 | processing task, is_child = 0 2.06.696.594 I slot print_timing: id 0 | task 10502 | prompt eval time = 134.51 ms / 345 tokens ( 0.39 ms per token, 2564.92 tokens per second) 2.06.696.600 I slot print_timing: id 0 | task 10502 | eval time = 951.41 ms / 106 tokens ( 9.06 ms per token, 110.36 tokens per second) 2.06.696.601 I slot print_timing: id 0 | task 10502 | total time = 1085.92 ms / 451 tokens 2.06.696.603 I slot print_timing: id 0 | task 10502 | graphs reused = 9915 2.06.696.603 I slot print_timing: id 0 | task 10502 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.696.631 I slot release: id 0 | task 10502 | stop processing: n_tokens = 482, truncated = 0 2.06.715.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 126603260 2.06.715.698 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.06.782.520 I slot launch_slot_: id 0 | task 10611 | processing task, is_child = 0 2.07.884.984 I slot print_timing: id 0 | task 10611 | prompt eval time = 150.89 ms / 430 tokens ( 0.35 ms per token, 2849.68 tokens per second) 2.07.884.990 I slot print_timing: id 0 | task 10611 | eval time = 951.55 ms / 105 tokens ( 9.15 ms per token, 109.30 tokens per second) 2.07.884.992 I slot print_timing: id 0 | task 10611 | total time = 1102.44 ms / 535 tokens 2.07.884.993 I slot print_timing: id 0 | task 10611 | graphs reused = 10017 2.07.884.994 I slot print_timing: id 0 | task 10611 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.885.026 I slot release: id 0 | task 10611 | stop processing: n_tokens = 566, truncated = 0 2.07.903.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 127791655 2.07.903.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.07.959.448 I slot launch_slot_: id 0 | task 10719 | processing task, is_child = 0 2.08.883.479 I slot print_timing: id 0 | task 10719 | prompt eval time = 125.57 ms / 316 tokens ( 0.40 ms per token, 2516.48 tokens per second) 2.08.883.484 I slot print_timing: id 0 | task 10719 | eval time = 798.44 ms / 85 tokens ( 9.51 ms per token, 105.21 tokens per second) 2.08.883.486 I slot print_timing: id 0 | task 10719 | total time = 924.01 ms / 401 tokens 2.08.883.487 I slot print_timing: id 0 | task 10719 | graphs reused = 10100 2.08.883.488 I slot print_timing: id 0 | task 10719 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.883.521 I slot release: id 0 | task 10719 | stop processing: n_tokens = 432, truncated = 0 2.08.887.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 128790149 2.08.887.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.08.955.534 I slot launch_slot_: id 0 | task 10807 | processing task, is_child = 0 2.10.053.081 I slot print_timing: id 0 | task 10807 | prompt eval time = 137.85 ms / 354 tokens ( 0.39 ms per token, 2567.97 tokens per second) 2.10.053.087 I slot print_timing: id 0 | task 10807 | eval time = 959.67 ms / 107 tokens ( 9.05 ms per token, 110.45 tokens per second) 2.10.053.088 I slot print_timing: id 0 | task 10807 | total time = 1097.53 ms / 461 tokens 2.10.053.089 I slot print_timing: id 0 | task 10807 | graphs reused = 10205 2.10.053.090 I slot print_timing: id 0 | task 10807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.053.118 I slot release: id 0 | task 10807 | stop processing: n_tokens = 492, truncated = 0 2.10.081.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 129959747 2.10.081.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.10.145.800 I slot launch_slot_: id 0 | task 10917 | processing task, is_child = 0 2.11.183.253 I slot print_timing: id 0 | task 10917 | prompt eval time = 152.68 ms / 438 tokens ( 0.35 ms per token, 2868.80 tokens per second) 2.11.183.258 I slot print_timing: id 0 | task 10917 | eval time = 884.75 ms / 98 tokens ( 9.12 ms per token, 109.63 tokens per second) 2.11.183.259 I slot print_timing: id 0 | task 10917 | total time = 1037.43 ms / 536 tokens 2.11.183.260 I slot print_timing: id 0 | task 10917 | graphs reused = 10300 2.11.183.261 I slot print_timing: id 0 | task 10917 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.183.292 I slot release: id 0 | task 10917 | stop processing: n_tokens = 567, truncated = 0 2.11.187.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 131089920 2.11.187.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.11.243.079 I slot launch_slot_: id 0 | task 11018 | processing task, is_child = 0 2.12.026.581 I slot print_timing: id 0 | task 11018 | prompt eval time = 151.73 ms / 457 tokens ( 0.33 ms per token, 3011.95 tokens per second) 2.12.026.587 I slot print_timing: id 0 | task 11018 | eval time = 631.75 ms / 70 tokens ( 9.16 ms per token, 109.22 tokens per second) 2.12.026.588 I slot print_timing: id 0 | task 11018 | total time = 783.48 ms / 527 tokens 2.12.026.589 I slot print_timing: id 0 | task 11018 | graphs reused = 10367 2.12.026.590 I slot print_timing: id 0 | task 11018 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.026.620 I slot release: id 0 | task 11018 | stop processing: n_tokens = 558, truncated = 0 2.12.044.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 131933248 2.12.044.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.12.100.353 I slot launch_slot_: id 0 | task 11091 | processing task, is_child = 0 2.13.142.165 I slot print_timing: id 0 | task 11091 | prompt eval time = 157.53 ms / 473 tokens ( 0.33 ms per token, 3002.56 tokens per second) 2.13.142.172 I slot print_timing: id 0 | task 11091 | eval time = 884.26 ms / 98 tokens ( 9.12 ms per token, 109.70 tokens per second) 2.13.142.173 I slot print_timing: id 0 | task 11091 | total time = 1041.79 ms / 571 tokens 2.13.142.174 I slot print_timing: id 0 | task 11091 | graphs reused = 10462 2.13.142.175 I slot print_timing: id 0 | task 11091 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.142.206 I slot release: id 0 | task 11091 | stop processing: n_tokens = 602, truncated = 0 2.13.159.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 133048834 2.13.159.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.958 MiB) 2.13.228.097 I slot launch_slot_: id 0 | task 11192 | processing task, is_child = 0 2.14.005.968 I slot print_timing: id 0 | task 11192 | prompt eval time = 155.83 ms / 476 tokens ( 0.33 ms per token, 3054.53 tokens per second) 2.14.005.973 I slot print_timing: id 0 | task 11192 | eval time = 622.02 ms / 69 tokens ( 9.15 ms per token, 109.32 tokens per second) 2.14.005.975 I slot print_timing: id 0 | task 11192 | total time = 777.85 ms / 545 tokens 2.14.005.976 I slot print_timing: id 0 | task 11192 | graphs reused = 10528 2.14.005.976 I slot print_timing: id 0 | task 11192 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.006.008 I slot release: id 0 | task 11192 | stop processing: n_tokens = 576, truncated = 0 2.14.030.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 133912636 2.14.030.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.14.101.088 I slot launch_slot_: id 0 | task 11264 | processing task, is_child = 0 2.15.237.515 I slot print_timing: id 0 | task 11264 | prompt eval time = 167.25 ms / 466 tokens ( 0.36 ms per token, 2786.25 tokens per second) 2.15.237.521 I slot print_timing: id 0 | task 11264 | eval time = 969.15 ms / 107 tokens ( 9.14 ms per token, 109.37 tokens per second) 2.15.237.522 I slot print_timing: id 0 | task 11264 | total time = 1136.40 ms / 573 tokens 2.15.237.523 I slot print_timing: id 0 | task 11264 | graphs reused = 10632 2.15.237.524 I slot print_timing: id 0 | task 11264 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.237.556 I slot release: id 0 | task 11264 | stop processing: n_tokens = 604, truncated = 0 2.15.259.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 135144184 2.15.259.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.15.338.222 I slot launch_slot_: id 0 | task 11374 | processing task, is_child = 0 2.16.184.736 I slot print_timing: id 0 | task 11374 | prompt eval time = 139.10 ms / 415 tokens ( 0.34 ms per token, 2983.42 tokens per second) 2.16.184.742 I slot print_timing: id 0 | task 11374 | eval time = 707.39 ms / 78 tokens ( 9.19 ms per token, 108.85 tokens per second) 2.16.184.743 I slot print_timing: id 0 | task 11374 | total time = 846.49 ms / 493 tokens 2.16.184.744 I slot print_timing: id 0 | task 11374 | graphs reused = 10707 2.16.184.745 I slot print_timing: id 0 | task 11374 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.184.775 I slot release: id 0 | task 11374 | stop processing: n_tokens = 524, truncated = 0 2.16.212.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 136091404 2.16.212.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.16.283.008 I slot launch_slot_: id 0 | task 11455 | processing task, is_child = 0 2.16.986.087 I slot print_timing: id 0 | task 11455 | prompt eval time = 131.40 ms / 352 tokens ( 0.37 ms per token, 2678.90 tokens per second) 2.16.986.092 I slot print_timing: id 0 | task 11455 | eval time = 571.66 ms / 64 tokens ( 9.07 ms per token, 110.20 tokens per second) 2.16.986.094 I slot print_timing: id 0 | task 11455 | total time = 703.06 ms / 416 tokens 2.16.986.094 I slot print_timing: id 0 | task 11455 | graphs reused = 10769 2.16.986.095 I slot print_timing: id 0 | task 11455 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.986.122 I slot release: id 0 | task 11455 | stop processing: n_tokens = 447, truncated = 0 2.17.011.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 136892750 2.17.011.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.17.080.620 I slot launch_slot_: id 0 | task 11522 | processing task, is_child = 0 2.18.449.701 I slot print_timing: id 0 | task 11522 | prompt eval time = 174.22 ms / 550 tokens ( 0.32 ms per token, 3156.91 tokens per second) 2.18.449.706 I slot print_timing: id 0 | task 11522 | eval time = 1194.84 ms / 133 tokens ( 9.05 ms per token, 110.48 tokens per second) 2.18.449.707 I slot print_timing: id 0 | task 11522 | total time = 1369.06 ms / 683 tokens 2.18.449.708 I slot print_timing: id 0 | task 11522 | graphs reused = 10900 2.18.449.709 I slot print_timing: id 0 | task 11522 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.449.745 I slot release: id 0 | task 11522 | stop processing: n_tokens = 714, truncated = 0 2.18.479.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 138356373 2.18.479.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.331 MiB) 2.18.559.447 I slot launch_slot_: id 0 | task 11659 | processing task, is_child = 0 2.20.825.388 I slot print_timing: id 0 | task 11659 | prompt eval time = 209.32 ms / 772 tokens ( 0.27 ms per token, 3688.13 tokens per second) 2.20.825.394 I slot print_timing: id 0 | task 11659 | eval time = 2056.60 ms / 226 tokens ( 9.14 ms per token, 109.40 tokens per second) 2.20.825.395 I slot print_timing: id 0 | task 11659 | total time = 2265.92 ms / 998 tokens 2.20.825.396 I slot print_timing: id 0 | task 11659 | graphs reused = 11123 2.20.825.396 I slot print_timing: id 0 | task 11659 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.825.435 I slot release: id 0 | task 11659 | stop processing: n_tokens = 1029, truncated = 0 2.20.847.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 140732064 2.20.847.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.20.924.728 I slot launch_slot_: id 0 | task 11889 | processing task, is_child = 0 2.22.768.936 I slot print_timing: id 0 | task 11889 | prompt eval time = 203.03 ms / 683 tokens ( 0.30 ms per token, 3364.12 tokens per second) 2.22.768.942 I slot print_timing: id 0 | task 11889 | eval time = 1641.16 ms / 181 tokens ( 9.12 ms per token, 109.68 tokens per second) 2.22.768.944 I slot print_timing: id 0 | task 11889 | total time = 1844.19 ms / 864 tokens 2.22.768.945 I slot print_timing: id 0 | task 11889 | graphs reused = 11301 2.22.768.946 I slot print_timing: id 0 | task 11889 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.768.989 I slot release: id 0 | task 11889 | stop processing: n_tokens = 895, truncated = 0 2.22.773.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 142675618 2.22.773.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.22.855.388 I slot launch_slot_: id 0 | task 12074 | processing task, is_child = 0 2.25.011.480 I slot print_timing: id 0 | task 12074 | prompt eval time = 183.29 ms / 579 tokens ( 0.32 ms per token, 3158.89 tokens per second) 2.25.011.486 I slot print_timing: id 0 | task 12074 | eval time = 1972.78 ms / 218 tokens ( 9.09 ms per token, 110.00 tokens per second) 2.25.011.487 I slot print_timing: id 0 | task 12074 | total time = 2156.07 ms / 797 tokens 2.25.011.488 I slot print_timing: id 0 | task 12074 | graphs reused = 11516 2.25.011.488 I slot print_timing: id 0 | task 12074 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.011.524 I slot release: id 0 | task 12074 | stop processing: n_tokens = 828, truncated = 0 2.25.026.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 144918152 2.25.026.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.25.049.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.25.129.628 I slot launch_slot_: id 0 | task 12296 | processing task, is_child = 0 2.26.253.334 I slot print_timing: id 0 | task 12296 | prompt eval time = 170.67 ms / 500 tokens ( 0.34 ms per token, 2929.70 tokens per second) 2.26.253.339 I slot print_timing: id 0 | task 12296 | eval time = 953.02 ms / 106 tokens ( 9.08 ms per token, 110.18 tokens per second) 2.26.253.340 I slot print_timing: id 0 | task 12296 | total time = 1123.68 ms / 606 tokens 2.26.253.341 I slot print_timing: id 0 | task 12296 | graphs reused = 11620 2.26.253.341 I slot print_timing: id 0 | task 12296 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.253.375 I slot release: id 0 | task 12296 | stop processing: n_tokens = 637, truncated = 0 2.26.277.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 146160004 2.26.277.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.26.350.708 I slot launch_slot_: id 0 | task 12405 | processing task, is_child = 0 2.28.449.984 I slot print_timing: id 0 | task 12405 | prompt eval time = 211.25 ms / 776 tokens ( 0.27 ms per token, 3673.34 tokens per second) 2.28.449.990 I slot print_timing: id 0 | task 12405 | eval time = 1888.00 ms / 209 tokens ( 9.08 ms per token, 110.17 tokens per second) 2.28.449.992 I slot print_timing: id 0 | task 12405 | total time = 2099.26 ms / 985 tokens 2.28.449.993 I slot print_timing: id 0 | task 12405 | graphs reused = 11827 2.28.449.994 I slot print_timing: id 0 | task 12405 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.450.039 I slot release: id 0 | task 12405 | stop processing: n_tokens = 1016, truncated = 0 2.28.472.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 148356667 2.28.472.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.28.554.883 I slot launch_slot_: id 0 | task 12618 | processing task, is_child = 0 2.30.500.083 I slot print_timing: id 0 | task 12618 | prompt eval time = 165.56 ms / 504 tokens ( 0.33 ms per token, 3044.16 tokens per second) 2.30.500.088 I slot print_timing: id 0 | task 12618 | eval time = 1779.62 ms / 197 tokens ( 9.08 ms per token, 110.14 tokens per second) 2.30.500.090 I slot print_timing: id 0 | task 12618 | total time = 1945.18 ms / 701 tokens 2.30.500.091 I slot print_timing: id 0 | task 12618 | graphs reused = 12022 2.30.500.091 I slot print_timing: id 0 | task 12618 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.500.122 I slot release: id 0 | task 12618 | stop processing: n_tokens = 732, truncated = 0 2.30.520.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 150406751 2.30.520.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.30.589.556 I slot launch_slot_: id 0 | task 12818 | processing task, is_child = 0 2.32.650.831 I slot print_timing: id 0 | task 12818 | prompt eval time = 191.54 ms / 633 tokens ( 0.30 ms per token, 3304.84 tokens per second) 2.32.650.840 I slot print_timing: id 0 | task 12818 | eval time = 1869.71 ms / 207 tokens ( 9.08 ms per token, 110.18 tokens per second) 2.32.650.841 I slot print_timing: id 0 | task 12818 | total time = 2061.25 ms / 840 tokens 2.32.650.842 I slot print_timing: id 0 | task 12818 | graphs reused = 12226 2.32.650.844 I slot print_timing: id 0 | task 12818 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.650.892 I slot release: id 0 | task 12818 | stop processing: n_tokens = 871, truncated = 0 2.32.665.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 152557520 2.32.665.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.992 MiB) 2.32.744.472 I slot launch_slot_: id 0 | task 13029 | processing task, is_child = 0 2.34.102.185 I slot print_timing: id 0 | task 13029 | prompt eval time = 146.80 ms / 395 tokens ( 0.37 ms per token, 2690.68 tokens per second) 2.34.102.191 I slot print_timing: id 0 | task 13029 | eval time = 1210.89 ms / 134 tokens ( 9.10 ms per token, 109.84 tokens per second) 2.34.102.192 I slot print_timing: id 0 | task 13029 | total time = 1357.69 ms / 529 tokens 2.34.102.193 I slot print_timing: id 0 | task 13029 | graphs reused = 12357 2.34.102.193 I slot print_timing: id 0 | task 13029 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.102.224 I slot release: id 0 | task 13029 | stop processing: n_tokens = 560, truncated = 0 2.34.124.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 154008852 2.34.124.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.34.192.119 I slot launch_slot_: id 0 | task 13166 | processing task, is_child = 0 2.36.265.100 I slot print_timing: id 0 | task 13166 | prompt eval time = 181.76 ms / 584 tokens ( 0.31 ms per token, 3213.08 tokens per second) 2.36.265.105 I slot print_timing: id 0 | task 13166 | eval time = 1891.20 ms / 209 tokens ( 9.09 ms per token, 109.98 tokens per second) 2.36.265.107 I slot print_timing: id 0 | task 13166 | total time = 2072.96 ms / 793 tokens 2.36.265.108 I slot print_timing: id 0 | task 13166 | graphs reused = 12563 2.36.265.108 I slot print_timing: id 0 | task 13166 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.265.145 I slot release: id 0 | task 13166 | stop processing: n_tokens = 824, truncated = 0 2.36.293.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 156171773 2.36.293.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.36.379.529 I slot launch_slot_: id 0 | task 13379 | processing task, is_child = 0 2.38.660.048 I slot print_timing: id 0 | task 13379 | prompt eval time = 203.28 ms / 695 tokens ( 0.29 ms per token, 3418.85 tokens per second) 2.38.660.054 I slot print_timing: id 0 | task 13379 | eval time = 2077.21 ms / 230 tokens ( 9.07 ms per token, 110.24 tokens per second) 2.38.660.055 I slot print_timing: id 0 | task 13379 | total time = 2280.50 ms / 925 tokens 2.38.660.056 I slot print_timing: id 0 | task 13379 | graphs reused = 12790 2.38.660.057 I slot print_timing: id 0 | task 13379 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.660.095 I slot release: id 0 | task 13379 | stop processing: n_tokens = 956, truncated = 0 2.38.678.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 158566724 2.38.678.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.331 MiB) 2.38.754.125 I slot launch_slot_: id 0 | task 13613 | processing task, is_child = 0 2.40.691.814 I slot print_timing: id 0 | task 13613 | prompt eval time = 214.39 ms / 769 tokens ( 0.28 ms per token, 3586.99 tokens per second) 2.40.691.820 I slot print_timing: id 0 | task 13613 | eval time = 1723.28 ms / 191 tokens ( 9.07 ms per token, 110.25 tokens per second) 2.40.691.821 I slot print_timing: id 0 | task 13613 | total time = 1937.67 ms / 960 tokens 2.40.691.822 I slot print_timing: id 0 | task 13613 | graphs reused = 12979 2.40.691.823 I slot print_timing: id 0 | task 13613 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.691.863 I slot release: id 0 | task 13613 | stop processing: n_tokens = 991, truncated = 0 2.40.696.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 160598492 2.40.696.800 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.40.718.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 2.40.793.131 I slot launch_slot_: id 0 | task 13808 | processing task, is_child = 0 2.42.086.407 I slot print_timing: id 0 | task 13808 | prompt eval time = 179.21 ms / 576 tokens ( 0.31 ms per token, 3214.18 tokens per second) 2.42.086.412 I slot print_timing: id 0 | task 13808 | eval time = 1114.05 ms / 124 tokens ( 9.06 ms per token, 110.41 tokens per second) 2.42.086.414 I slot print_timing: id 0 | task 13808 | total time = 1293.25 ms / 700 tokens 2.42.086.415 I slot print_timing: id 0 | task 13808 | graphs reused = 13101 2.42.086.416 I slot print_timing: id 0 | task 13808 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.086.453 I slot release: id 0 | task 13808 | stop processing: n_tokens = 731, truncated = 0 2.42.105.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 161993082 2.42.105.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.42.185.497 I slot launch_slot_: id 0 | task 13936 | processing task, is_child = 0 2.44.866.369 I slot print_timing: id 0 | task 13936 | prompt eval time = 197.34 ms / 655 tokens ( 0.30 ms per token, 3319.09 tokens per second) 2.44.866.374 I slot print_timing: id 0 | task 13936 | eval time = 2483.51 ms / 275 tokens ( 9.06 ms per token, 110.33 tokens per second) 2.44.866.376 I slot print_timing: id 0 | task 13936 | total time = 2680.85 ms / 930 tokens 2.44.866.376 I slot print_timing: id 0 | task 13936 | graphs reused = 13373 2.44.866.377 I slot print_timing: id 0 | task 13936 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.866.414 I slot release: id 0 | task 13936 | stop processing: n_tokens = 961, truncated = 0 2.44.885.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 164773042 2.44.885.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.44.950.329 I slot launch_slot_: id 0 | task 14215 | processing task, is_child = 0 2.46.232.108 I slot print_timing: id 0 | task 14215 | prompt eval time = 189.07 ms / 621 tokens ( 0.30 ms per token, 3284.46 tokens per second) 2.46.232.114 I slot print_timing: id 0 | task 14215 | eval time = 1092.69 ms / 121 tokens ( 9.11 ms per token, 109.82 tokens per second) 2.46.232.115 I slot print_timing: id 0 | task 14215 | total time = 1281.76 ms / 742 tokens 2.46.232.116 I slot print_timing: id 0 | task 14215 | graphs reused = 13491 2.46.232.117 I slot print_timing: id 0 | task 14215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.232.160 I slot release: id 0 | task 14215 | stop processing: n_tokens = 773, truncated = 0 2.46.252.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 166138789 2.46.252.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.46.330.933 I slot launch_slot_: id 0 | task 14340 | processing task, is_child = 0 2.48.231.332 I slot print_timing: id 0 | task 14340 | prompt eval time = 212.25 ms / 767 tokens ( 0.28 ms per token, 3613.68 tokens per second) 2.48.231.337 I slot print_timing: id 0 | task 14340 | eval time = 1688.13 ms / 184 tokens ( 9.22 ms per token, 108.40 tokens per second) 2.48.231.338 I slot print_timing: id 0 | task 14340 | total time = 1900.38 ms / 951 tokens 2.48.231.339 I slot print_timing: id 0 | task 14340 | graphs reused = 13673 2.48.231.340 I slot print_timing: id 0 | task 14340 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.231.381 I slot release: id 0 | task 14340 | stop processing: n_tokens = 982, truncated = 0 2.48.236.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 168138010 2.48.236.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.48.315.217 I slot launch_slot_: id 0 | task 14528 | processing task, is_child = 0 2.50.413.043 I slot print_timing: id 0 | task 14528 | prompt eval time = 233.03 ms / 864 tokens ( 0.27 ms per token, 3707.61 tokens per second) 2.50.413.049 I slot print_timing: id 0 | task 14528 | eval time = 1864.77 ms / 203 tokens ( 9.23 ms per token, 108.32 tokens per second) 2.50.413.050 I slot print_timing: id 0 | task 14528 | total time = 2097.81 ms / 1067 tokens 2.50.413.051 I slot print_timing: id 0 | task 14528 | graphs reused = 13873 2.50.413.052 I slot print_timing: id 0 | task 14528 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.413.096 I slot release: id 0 | task 14528 | stop processing: n_tokens = 1098, truncated = 0 2.50.417.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 170319725 2.50.417.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.50.427.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.50.495.353 I slot launch_slot_: id 0 | task 14735 | processing task, is_child = 0 2.51.861.435 I slot print_timing: id 0 | task 14735 | prompt eval time = 199.87 ms / 646 tokens ( 0.31 ms per token, 3232.15 tokens per second) 2.51.861.440 I slot print_timing: id 0 | task 14735 | eval time = 1166.19 ms / 129 tokens ( 9.11 ms per token, 109.76 tokens per second) 2.51.861.442 I slot print_timing: id 0 | task 14735 | total time = 1366.06 ms / 775 tokens 2.51.861.442 I slot print_timing: id 0 | task 14735 | graphs reused = 13999 2.51.861.443 I slot print_timing: id 0 | task 14735 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.861.481 I slot release: id 0 | task 14735 | stop processing: n_tokens = 806, truncated = 0 2.51.879.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 171768110 2.51.879.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.51.956.369 I slot launch_slot_: id 0 | task 14868 | processing task, is_child = 0 2.54.223.928 I slot print_timing: id 0 | task 14868 | prompt eval time = 200.36 ms / 720 tokens ( 0.28 ms per token, 3593.48 tokens per second) 2.54.223.935 I slot print_timing: id 0 | task 14868 | eval time = 2067.18 ms / 222 tokens ( 9.35 ms per token, 106.91 tokens per second) 2.54.223.936 I slot print_timing: id 0 | task 14868 | total time = 2267.54 ms / 942 tokens 2.54.223.937 I slot print_timing: id 0 | task 14868 | graphs reused = 14218 2.54.223.938 I slot print_timing: id 0 | task 14868 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.223.977 I slot release: id 0 | task 14868 | stop processing: n_tokens = 973, truncated = 0 2.54.243.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 174130605 2.54.243.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.517 MiB) 2.54.321.076 I slot launch_slot_: id 0 | task 15094 | processing task, is_child = 0 2.56.411.336 I slot print_timing: id 0 | task 15094 | prompt eval time = 163.55 ms / 509 tokens ( 0.32 ms per token, 3112.22 tokens per second) 2.56.411.342 I slot print_timing: id 0 | task 15094 | eval time = 1926.69 ms / 214 tokens ( 9.05 ms per token, 110.55 tokens per second) 2.56.411.343 I slot print_timing: id 0 | task 15094 | total time = 2090.24 ms / 723 tokens 2.56.411.344 I slot print_timing: id 0 | task 15094 | graphs reused = 14430 2.56.411.345 I slot print_timing: id 0 | task 15094 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.411.379 I slot release: id 0 | task 15094 | stop processing: n_tokens = 754, truncated = 0 2.56.434.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 176318007 2.56.434.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.56.504.429 I slot launch_slot_: id 0 | task 15311 | processing task, is_child = 0 2.58.882.358 I slot print_timing: id 0 | task 15311 | prompt eval time = 180.90 ms / 581 tokens ( 0.31 ms per token, 3211.79 tokens per second) 2.58.882.364 I slot print_timing: id 0 | task 15311 | eval time = 2197.01 ms / 242 tokens ( 9.12 ms per token, 109.69 tokens per second) 2.58.882.365 I slot print_timing: id 0 | task 15311 | total time = 2377.91 ms / 823 tokens 2.58.882.366 I slot print_timing: id 0 | task 15311 | graphs reused = 14669 2.58.882.367 I slot print_timing: id 0 | task 15311 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.882.403 I slot release: id 0 | task 15311 | stop processing: n_tokens = 854, truncated = 0 2.58.908.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 178789031 2.58.908.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.58.988.748 I slot launch_slot_: id 0 | task 15557 | processing task, is_child = 0 3.01.215.439 I slot print_timing: id 0 | task 15557 | prompt eval time = 237.25 ms / 925 tokens ( 0.26 ms per token, 3898.76 tokens per second) 3.01.215.445 I slot print_timing: id 0 | task 15557 | eval time = 1989.42 ms / 220 tokens ( 9.08 ms per token, 110.08 tokens per second) 3.01.215.446 I slot print_timing: id 0 | task 15557 | total time = 2226.67 ms / 1145 tokens 3.01.215.447 I slot print_timing: id 0 | task 15557 | graphs reused = 14886 3.01.215.448 I slot print_timing: id 0 | task 15557 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.215.494 I slot release: id 0 | task 15557 | stop processing: n_tokens = 1176, truncated = 0 3.01.241.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 181122122 3.01.241.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.01.317.560 I slot launch_slot_: id 0 | task 15781 | processing task, is_child = 0 3.03.789.772 I slot print_timing: id 0 | task 15781 | prompt eval time = 228.46 ms / 885 tokens ( 0.26 ms per token, 3873.73 tokens per second) 3.03.789.778 I slot print_timing: id 0 | task 15781 | eval time = 2243.73 ms / 245 tokens ( 9.20 ms per token, 108.75 tokens per second) 3.03.789.779 I slot print_timing: id 0 | task 15781 | total time = 2472.19 ms / 1130 tokens 3.03.789.780 I slot print_timing: id 0 | task 15781 | graphs reused = 15128 3.03.789.781 I slot print_timing: id 0 | task 15781 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.789.827 I slot release: id 0 | task 15781 | stop processing: n_tokens = 1161, truncated = 0 3.03.817.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 183696455 3.03.817.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.03.897.373 I slot launch_slot_: id 0 | task 16030 | processing task, is_child = 0 3.06.005.508 I slot print_timing: id 0 | task 16030 | prompt eval time = 138.88 ms / 392 tokens ( 0.35 ms per token, 2822.68 tokens per second) 3.06.005.513 I slot print_timing: id 0 | task 16030 | eval time = 1969.24 ms / 219 tokens ( 9.03 ms per token, 110.70 tokens per second) 3.06.005.514 I slot print_timing: id 0 | task 16030 | total time = 2108.11 ms / 611 tokens 3.06.005.515 I slot print_timing: id 0 | task 16030 | graphs reused = 15344 3.06.005.515 I slot print_timing: id 0 | task 16030 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.005.546 I slot release: id 0 | task 16030 | stop processing: n_tokens = 642, truncated = 0 3.06.022.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 642, t_last = 185912174 3.06.022.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.06.093.684 I slot launch_slot_: id 0 | task 16252 | processing task, is_child = 0 3.06.675.396 I slot print_timing: id 0 | task 16252 | prompt eval time = 127.58 ms / 331 tokens ( 0.39 ms per token, 2594.55 tokens per second) 3.06.675.403 I slot print_timing: id 0 | task 16252 | eval time = 454.12 ms / 51 tokens ( 9.08 ms per token, 110.10 tokens per second) 3.06.675.404 I slot print_timing: id 0 | task 16252 | total time = 581.69 ms / 382 tokens 3.06.675.404 I slot print_timing: id 0 | task 16252 | graphs reused = 15393 3.06.675.406 I slot print_timing: id 0 | task 16252 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.675.437 I slot release: id 0 | task 16252 | stop processing: n_tokens = 413, truncated = 0 3.06.692.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 186582066 3.06.692.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.06.771.072 I slot launch_slot_: id 0 | task 16306 | processing task, is_child = 0 3.08.411.541 I slot print_timing: id 0 | task 16306 | prompt eval time = 130.87 ms / 357 tokens ( 0.37 ms per token, 2727.86 tokens per second) 3.08.411.546 I slot print_timing: id 0 | task 16306 | eval time = 1509.58 ms / 168 tokens ( 9.04 ms per token, 110.63 tokens per second) 3.08.411.547 I slot print_timing: id 0 | task 16306 | total time = 1640.45 ms / 525 tokens 3.08.411.548 I slot print_timing: id 0 | task 16306 | graphs reused = 15558 3.08.411.549 I slot print_timing: id 0 | task 16306 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.411.577 I slot release: id 0 | task 16306 | stop processing: n_tokens = 556, truncated = 0 3.08.438.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 188318206 3.08.438.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.08.508.197 I slot launch_slot_: id 0 | task 16477 | processing task, is_child = 0 3.09.080.293 I slot print_timing: id 0 | task 16477 | prompt eval time = 126.22 ms / 315 tokens ( 0.40 ms per token, 2495.56 tokens per second) 3.09.080.298 I slot print_timing: id 0 | task 16477 | eval time = 445.85 ms / 50 tokens ( 9.10 ms per token, 109.90 tokens per second) 3.09.080.299 I slot print_timing: id 0 | task 16477 | total time = 572.08 ms / 365 tokens 3.09.080.300 I slot print_timing: id 0 | task 16477 | graphs reused = 15606 3.09.080.301 I slot print_timing: id 0 | task 16477 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.080.327 I slot release: id 0 | task 16477 | stop processing: n_tokens = 396, truncated = 0 3.09.096.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 188986956 3.09.096.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.09.164.323 I slot launch_slot_: id 0 | task 16530 | processing task, is_child = 0 3.10.108.113 I slot print_timing: id 0 | task 16530 | prompt eval time = 130.45 ms / 378 tokens ( 0.35 ms per token, 2897.62 tokens per second) 3.10.108.119 I slot print_timing: id 0 | task 16530 | eval time = 813.32 ms / 91 tokens ( 9.04 ms per token, 110.66 tokens per second) 3.10.108.120 I slot print_timing: id 0 | task 16530 | total time = 943.77 ms / 469 tokens 3.10.108.121 I slot print_timing: id 0 | task 16530 | graphs reused = 15695 3.10.108.122 I slot print_timing: id 0 | task 16530 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.108.152 I slot release: id 0 | task 16530 | stop processing: n_tokens = 500, truncated = 0 3.10.127.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 190014780 3.10.127.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.10.200.667 I slot launch_slot_: id 0 | task 16624 | processing task, is_child = 0 3.10.568.069 I slot print_timing: id 0 | task 16624 | prompt eval time = 120.15 ms / 295 tokens ( 0.41 ms per token, 2455.20 tokens per second) 3.10.568.075 I slot print_timing: id 0 | task 16624 | eval time = 247.22 ms / 28 tokens ( 9.16 ms per token, 109.21 tokens per second) 3.10.568.076 I slot print_timing: id 0 | task 16624 | total time = 367.38 ms / 323 tokens 3.10.568.077 I slot print_timing: id 0 | task 16624 | graphs reused = 15721 3.10.568.077 I slot print_timing: id 0 | task 16624 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.568.105 I slot release: id 0 | task 16624 | stop processing: n_tokens = 354, truncated = 0 3.10.594.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 190474733 3.10.594.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.10.662.784 I slot launch_slot_: id 0 | task 16655 | processing task, is_child = 0 3.11.262.889 I slot print_timing: id 0 | task 16655 | prompt eval time = 128.47 ms / 337 tokens ( 0.38 ms per token, 2623.10 tokens per second) 3.11.262.895 I slot print_timing: id 0 | task 16655 | eval time = 471.61 ms / 53 tokens ( 9.07 ms per token, 110.26 tokens per second) 3.11.262.896 I slot print_timing: id 0 | task 16655 | total time = 600.09 ms / 390 tokens 3.11.262.897 I slot print_timing: id 0 | task 16655 | graphs reused = 15772 3.11.262.898 I slot print_timing: id 0 | task 16655 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.262.925 I slot release: id 0 | task 16655 | stop processing: n_tokens = 421, truncated = 0 3.11.285.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 191169553 3.11.285.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.11.355.290 I slot launch_slot_: id 0 | task 16711 | processing task, is_child = 0 3.12.407.325 I slot print_timing: id 0 | task 16711 | prompt eval time = 127.26 ms / 325 tokens ( 0.39 ms per token, 2553.91 tokens per second) 3.12.407.330 I slot print_timing: id 0 | task 16711 | eval time = 924.76 ms / 103 tokens ( 9.07 ms per token, 110.30 tokens per second) 3.12.407.331 I slot print_timing: id 0 | task 16711 | total time = 1052.02 ms / 428 tokens 3.12.407.332 I slot print_timing: id 0 | task 16711 | graphs reused = 15873 3.12.407.333 I slot print_timing: id 0 | task 16711 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.407.362 I slot release: id 0 | task 16711 | stop processing: n_tokens = 459, truncated = 0 3.12.434.465 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.070 3.12.484.735 I slot launch_slot_: id 0 | task 16817 | processing task, is_child = 0 3.13.766.782 I slot print_timing: id 0 | task 16817 | prompt eval time = 120.32 ms / 264 tokens ( 0.46 ms per token, 2194.08 tokens per second) 3.13.766.787 I slot print_timing: id 0 | task 16817 | eval time = 1161.70 ms / 129 tokens ( 9.08 ms per token, 110.18 tokens per second) 3.13.766.788 I slot print_timing: id 0 | task 16817 | total time = 1282.03 ms / 393 tokens 3.13.766.789 I slot print_timing: id 0 | task 16817 | graphs reused = 16000 3.13.766.790 I slot print_timing: id 0 | task 16817 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.766.816 I slot release: id 0 | task 16817 | stop processing: n_tokens = 424, truncated = 0 3.13.790.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 193673444 3.13.790.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.13.854.437 I slot launch_slot_: id 0 | task 16949 | processing task, is_child = 0 3.14.516.141 I slot print_timing: id 0 | task 16949 | prompt eval time = 128.34 ms / 331 tokens ( 0.39 ms per token, 2579.05 tokens per second) 3.14.516.147 I slot print_timing: id 0 | task 16949 | eval time = 533.34 ms / 60 tokens ( 9.04 ms per token, 110.62 tokens per second) 3.14.516.148 I slot print_timing: id 0 | task 16949 | total time = 661.68 ms / 391 tokens 3.14.516.149 I slot print_timing: id 0 | task 16949 | graphs reused = 16058 3.14.516.149 I slot print_timing: id 0 | task 16949 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.516.178 I slot release: id 0 | task 16949 | stop processing: n_tokens = 422, truncated = 0 3.14.535.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 194422807 3.14.535.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.14.606.861 I slot launch_slot_: id 0 | task 17012 | processing task, is_child = 0 3.16.117.121 I slot print_timing: id 0 | task 17012 | prompt eval time = 128.60 ms / 333 tokens ( 0.39 ms per token, 2589.40 tokens per second) 3.16.117.128 I slot print_timing: id 0 | task 17012 | eval time = 1381.64 ms / 153 tokens ( 9.09 ms per token, 110.01 tokens per second) 3.16.117.129 I slot print_timing: id 0 | task 17012 | total time = 1510.24 ms / 486 tokens 3.16.117.131 I slot print_timing: id 0 | task 17012 | graphs reused = 16208 3.16.117.132 I slot print_timing: id 0 | task 17012 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.117.162 I slot release: id 0 | task 17012 | stop processing: n_tokens = 517, truncated = 0 3.16.120.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 196023790 3.16.120.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.16.193.349 I slot launch_slot_: id 0 | task 17168 | processing task, is_child = 0 3.19.333.955 I slot print_timing: id 0 | task 17168 | n_gen = 333, tg = 110.41 t/s, tg_3s = 110.74 t/s 3.19.414.860 I slot print_timing: id 0 | task 17168 | prompt eval time = 133.58 ms / 346 tokens ( 0.39 ms per token, 2590.27 tokens per second) 3.19.414.865 I slot print_timing: id 0 | task 17168 | eval time = 3087.91 ms / 342 tokens ( 9.06 ms per token, 110.43 tokens per second) 3.19.414.866 I slot print_timing: id 0 | task 17168 | total time = 3221.49 ms / 688 tokens 3.19.414.867 I slot print_timing: id 0 | task 17168 | graphs reused = 16547 3.19.414.868 I slot print_timing: id 0 | task 17168 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.414.897 I slot release: id 0 | task 17168 | stop processing: n_tokens = 719, truncated = 0 3.19.442.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 719, t_last = 199321526 3.19.442.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.19.514.158 I slot launch_slot_: id 0 | task 17513 | processing task, is_child = 0 3.20.168.466 I slot print_timing: id 0 | task 17513 | prompt eval time = 128.74 ms / 325 tokens ( 0.40 ms per token, 2524.43 tokens per second) 3.20.168.472 I slot print_timing: id 0 | task 17513 | eval time = 525.55 ms / 59 tokens ( 9.06 ms per token, 110.36 tokens per second) 3.20.168.473 I slot print_timing: id 0 | task 17513 | total time = 654.29 ms / 384 tokens 3.20.168.474 I slot print_timing: id 0 | task 17513 | graphs reused = 16604 3.20.168.475 I slot print_timing: id 0 | task 17513 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.168.502 I slot release: id 0 | task 17513 | stop processing: n_tokens = 415, truncated = 0 3.20.196.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 200075131 3.20.196.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.20.267.099 I slot launch_slot_: id 0 | task 17575 | processing task, is_child = 0 3.22.801.813 I slot print_timing: id 0 | task 17575 | prompt eval time = 126.95 ms / 322 tokens ( 0.39 ms per token, 2536.35 tokens per second) 3.22.801.819 I slot print_timing: id 0 | task 17575 | eval time = 2407.74 ms / 268 tokens ( 9.02 ms per token, 110.89 tokens per second) 3.22.801.820 I slot print_timing: id 0 | task 17575 | total time = 2534.69 ms / 590 tokens 3.22.801.821 I slot print_timing: id 0 | task 17575 | graphs reused = 16869 3.22.801.822 I slot print_timing: id 0 | task 17575 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.801.851 I slot release: id 0 | task 17575 | stop processing: n_tokens = 621, truncated = 0 3.22.822.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 202708479 3.22.822.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.22.884.343 I slot launch_slot_: id 0 | task 17846 | processing task, is_child = 0 3.25.510.616 I slot print_timing: id 0 | task 17846 | prompt eval time = 127.23 ms / 338 tokens ( 0.38 ms per token, 2656.50 tokens per second) 3.25.510.622 I slot print_timing: id 0 | task 17846 | eval time = 2499.02 ms / 278 tokens ( 9.02 ms per token, 110.84 tokens per second) 3.25.510.623 I slot print_timing: id 0 | task 17846 | total time = 2626.25 ms / 616 tokens 3.25.510.624 I slot print_timing: id 0 | task 17846 | graphs reused = 17144 3.25.510.625 I slot print_timing: id 0 | task 17846 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.510.653 I slot release: id 0 | task 17846 | stop processing: n_tokens = 647, truncated = 0 3.25.528.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 205417282 3.25.578.425 I slot launch_slot_: id 0 | task 18127 | processing task, is_child = 0 3.28.710.216 I slot print_timing: id 0 | task 18127 | n_gen = 334, tg = 110.87 t/s, tg_3s = 111.20 t/s 3.31.714.958 I slot print_timing: id 0 | task 18127 | n_gen = 667, tg = 110.85 t/s, tg_3s = 110.82 t/s 3.34.718.187 I slot print_timing: id 0 | task 18127 | n_gen = 999, tg = 110.75 t/s, tg_3s = 110.55 t/s 3.34.943.570 I slot print_timing: id 0 | task 18127 | prompt eval time = 128.15 ms / 347 tokens ( 0.37 ms per token, 2707.79 tokens per second) 3.34.943.576 I slot print_timing: id 0 | task 18127 | eval time = 9236.98 ms / 1024 tokens ( 9.03 ms per token, 110.75 tokens per second) 3.34.943.577 I slot print_timing: id 0 | task 18127 | total time = 9365.13 ms / 1371 tokens 3.34.943.578 I slot print_timing: id 0 | task 18127 | graphs reused = 18162 3.34.943.579 I slot print_timing: id 0 | task 18127 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.943.607 I slot release: id 0 | task 18127 | stop processing: n_tokens = 1402, truncated = 0 3.34.947.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 214850236 3.34.947.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.35.022.874 I slot launch_slot_: id 0 | task 19154 | processing task, is_child = 0 3.37.224.589 I slot print_timing: id 0 | task 19154 | prompt eval time = 128.09 ms / 331 tokens ( 0.39 ms per token, 2584.10 tokens per second) 3.37.224.595 I slot print_timing: id 0 | task 19154 | eval time = 2073.61 ms / 231 tokens ( 9.02 ms per token, 110.92 tokens per second) 3.37.224.596 I slot print_timing: id 0 | task 19154 | total time = 2201.70 ms / 562 tokens 3.37.224.596 I slot print_timing: id 0 | task 19154 | graphs reused = 18390 3.37.224.597 I slot print_timing: id 0 | task 19154 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.224.625 I slot release: id 0 | task 19154 | stop processing: n_tokens = 593, truncated = 0 3.37.239.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 217131254 3.37.239.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.464 MiB) 3.37.304.554 I slot launch_slot_: id 0 | task 19388 | processing task, is_child = 0 3.37.823.718 I slot print_timing: id 0 | task 19388 | prompt eval time = 128.58 ms / 345 tokens ( 0.37 ms per token, 2683.15 tokens per second) 3.37.823.724 I slot print_timing: id 0 | task 19388 | eval time = 390.56 ms / 44 tokens ( 9.08 ms per token, 110.10 tokens per second) 3.37.823.725 I slot print_timing: id 0 | task 19388 | total time = 519.14 ms / 389 tokens 3.37.823.725 I slot print_timing: id 0 | task 19388 | graphs reused = 18432 3.37.823.728 I slot print_timing: id 0 | task 19388 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.823.756 I slot release: id 0 | task 19388 | stop processing: n_tokens = 420, truncated = 0 3.37.849.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 217730384 3.37.849.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.37.906.935 I slot launch_slot_: id 0 | task 19435 | processing task, is_child = 0 3.38.892.641 I slot print_timing: id 0 | task 19435 | prompt eval time = 127.95 ms / 320 tokens ( 0.40 ms per token, 2500.88 tokens per second) 3.38.892.647 I slot print_timing: id 0 | task 19435 | eval time = 857.73 ms / 96 tokens ( 9.03 ms per token, 110.76 tokens per second) 3.38.892.648 I slot print_timing: id 0 | task 19435 | total time = 985.69 ms / 416 tokens 3.38.892.648 I slot print_timing: id 0 | task 19435 | graphs reused = 18526 3.38.892.649 I slot print_timing: id 0 | task 19435 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.892.676 I slot release: id 0 | task 19435 | stop processing: n_tokens = 447, truncated = 0 3.38.914.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 218799305 3.38.914.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.38.983.127 I slot launch_slot_: id 0 | task 19534 | processing task, is_child = 0 3.39.564.827 I slot print_timing: id 0 | task 19534 | prompt eval time = 120.54 ms / 297 tokens ( 0.41 ms per token, 2463.83 tokens per second) 3.39.564.833 I slot print_timing: id 0 | task 19534 | eval time = 461.13 ms / 47 tokens ( 10.02 ms per token, 99.75 tokens per second) 3.39.564.835 I slot print_timing: id 0 | task 19534 | total time = 581.68 ms / 344 tokens 3.39.564.835 I slot print_timing: id 0 | task 19534 | graphs reused = 18571 3.39.564.836 I slot print_timing: id 0 | task 19534 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.564.862 I slot release: id 0 | task 19534 | stop processing: n_tokens = 375, truncated = 0 3.39.585.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 219471491 3.39.585.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.183 MiB) 3.39.661.285 I slot launch_slot_: id 0 | task 19584 | processing task, is_child = 0 3.40.897.468 I slot print_timing: id 0 | task 19584 | prompt eval time = 127.88 ms / 343 tokens ( 0.37 ms per token, 2682.29 tokens per second) 3.40.897.473 I slot print_timing: id 0 | task 19584 | eval time = 1108.29 ms / 124 tokens ( 9.01 ms per token, 110.98 tokens per second) 3.40.897.474 I slot print_timing: id 0 | task 19584 | total time = 1236.16 ms / 467 tokens 3.40.897.475 I slot print_timing: id 0 | task 19584 | graphs reused = 18693 3.40.897.476 I slot print_timing: id 0 | task 19584 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.897.504 I slot release: id 0 | task 19584 | stop processing: n_tokens = 498, truncated = 0 3.40.922.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 220804132 3.40.973.782 I slot launch_slot_: id 0 | task 19711 | processing task, is_child = 0 3.41.828.686 I slot print_timing: id 0 | task 19711 | prompt eval time = 135.82 ms / 371 tokens ( 0.37 ms per token, 2731.52 tokens per second) 3.41.828.692 I slot print_timing: id 0 | task 19711 | eval time = 719.06 ms / 79 tokens ( 9.22 ms per token, 108.47 tokens per second) 3.41.828.693 I slot print_timing: id 0 | task 19711 | total time = 854.88 ms / 450 tokens 3.41.828.693 I slot print_timing: id 0 | task 19711 | graphs reused = 18770 3.41.828.694 I slot print_timing: id 0 | task 19711 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.828.727 I slot release: id 0 | task 19711 | stop processing: n_tokens = 481, truncated = 0 3.41.854.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 221735356 3.41.854.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.41.921.912 I slot launch_slot_: id 0 | task 19793 | processing task, is_child = 0 3.43.167.937 I slot print_timing: id 0 | task 19793 | prompt eval time = 123.48 ms / 292 tokens ( 0.42 ms per token, 2364.77 tokens per second) 3.43.167.942 I slot print_timing: id 0 | task 19793 | eval time = 1122.53 ms / 125 tokens ( 9.05 ms per token, 110.47 tokens per second) 3.43.167.943 I slot print_timing: id 0 | task 19793 | total time = 1246.01 ms / 417 tokens 3.43.167.944 I slot print_timing: id 0 | task 19793 | graphs reused = 18893 3.43.167.945 I slot print_timing: id 0 | task 19793 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.167.972 I slot release: id 0 | task 19793 | stop processing: n_tokens = 448, truncated = 0 3.43.192.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 223074600 3.43.192.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.43.264.244 I slot launch_slot_: id 0 | task 19921 | processing task, is_child = 0 3.44.022.275 I slot print_timing: id 0 | task 19921 | prompt eval time = 132.63 ms / 301 tokens ( 0.44 ms per token, 2269.42 tokens per second) 3.44.022.281 I slot print_timing: id 0 | task 19921 | eval time = 625.38 ms / 70 tokens ( 9.06 ms per token, 110.33 tokens per second) 3.44.022.282 I slot print_timing: id 0 | task 19921 | total time = 758.01 ms / 371 tokens 3.44.022.282 I slot print_timing: id 0 | task 19921 | graphs reused = 18961 3.44.022.283 I slot print_timing: id 0 | task 19921 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.022.311 I slot release: id 0 | task 19921 | stop processing: n_tokens = 402, truncated = 0 3.44.048.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 223928940 3.44.048.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 3.44.128.610 I slot launch_slot_: id 0 | task 19994 | processing task, is_child = 0 3.46.286.134 I slot print_timing: id 0 | task 19994 | prompt eval time = 125.52 ms / 303 tokens ( 0.41 ms per token, 2413.96 tokens per second) 3.46.286.139 I slot print_timing: id 0 | task 19994 | eval time = 2031.98 ms / 226 tokens ( 9.03 ms per token, 110.73 tokens per second) 3.46.286.140 I slot print_timing: id 0 | task 19994 | total time = 2157.50 ms / 529 tokens 3.46.286.141 I slot print_timing: id 0 | task 19994 | graphs reused = 19184 3.46.286.142 I slot print_timing: id 0 | task 19994 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.286.167 I slot release: id 0 | task 19994 | stop processing: n_tokens = 560, truncated = 0 3.46.302.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 226192795 3.46.302.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 3.46.372.307 I slot launch_slot_: id 0 | task 20223 | processing task, is_child = 0 3.46.855.622 I slot print_timing: id 0 | task 20223 | prompt eval time = 127.90 ms / 321 tokens ( 0.40 ms per token, 2509.73 tokens per second) 3.46.855.627 I slot print_timing: id 0 | task 20223 | eval time = 355.39 ms / 40 tokens ( 9.11 ms per token, 109.74 tokens per second) 3.46.855.628 I slot print_timing: id 0 | task 20223 | total time = 483.29 ms / 361 tokens 3.46.855.629 I slot print_timing: id 0 | task 20223 | graphs reused = 19222 3.46.855.630 I slot print_timing: id 0 | task 20223 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.855.657 I slot release: id 0 | task 20223 | stop processing: n_tokens = 392, truncated = 0 3.46.879.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 226762286 3.46.879.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.581 MiB) 3.46.944.438 I slot launch_slot_: id 0 | task 20266 | processing task, is_child = 0 3.47.694.203 I slot print_timing: id 0 | task 20266 | prompt eval time = 126.58 ms / 322 tokens ( 0.39 ms per token, 2543.83 tokens per second) 3.47.694.209 I slot print_timing: id 0 | task 20266 | eval time = 623.16 ms / 70 tokens ( 9.03 ms per token, 110.73 tokens per second) 3.47.694.210 I slot print_timing: id 0 | task 20266 | total time = 749.75 ms / 392 tokens 3.47.694.211 I slot print_timing: id 0 | task 20266 | graphs reused = 19290 3.47.694.211 I slot print_timing: id 0 | task 20266 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.694.240 I slot release: id 0 | task 20266 | stop processing: n_tokens = 423, truncated = 0 3.47.719.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 227600869 3.47.719.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.419 MiB) 3.47.788.965 I slot launch_slot_: id 0 | task 20339 | processing task, is_child = 0 3.49.207.183 I slot print_timing: id 0 | task 20339 | prompt eval time = 127.44 ms / 323 tokens ( 0.39 ms per token, 2534.55 tokens per second) 3.49.207.188 I slot print_timing: id 0 | task 20339 | eval time = 1290.76 ms / 144 tokens ( 9.03 ms per token, 110.79 tokens per second) 3.49.207.189 I slot print_timing: id 0 | task 20339 | total time = 1418.20 ms / 467 tokens 3.49.207.190 I slot print_timing: id 0 | task 20339 | graphs reused = 19432 3.49.207.191 I slot print_timing: id 0 | task 20339 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.207.217 I slot release: id 0 | task 20339 | stop processing: n_tokens = 498, truncated = 0 3.49.235.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 229113846 3.49.235.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 3.49.300.755 I slot launch_slot_: id 0 | task 20486 | processing task, is_child = 0 3.52.433.727 I slot print_timing: id 0 | task 20486 | n_gen = 334, tg = 110.80 t/s, tg_3s = 111.14 t/s 3.52.928.972 I slot print_timing: id 0 | task 20486 | prompt eval time = 127.64 ms / 321 tokens ( 0.40 ms per token, 2514.94 tokens per second) 3.52.928.978 I slot print_timing: id 0 | task 20486 | eval time = 3500.56 ms / 389 tokens ( 9.02 ms per token, 110.84 tokens per second) 3.52.928.979 I slot print_timing: id 0 | task 20486 | total time = 3628.20 ms / 710 tokens 3.52.928.980 I slot print_timing: id 0 | task 20486 | graphs reused = 19818 3.52.928.981 I slot print_timing: id 0 | task 20486 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.929.009 I slot release: id 0 | task 20486 | stop processing: n_tokens = 741, truncated = 0 3.52.950.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 232835638 3.52.950.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 3.53.019.473 I slot launch_slot_: id 0 | task 20878 | processing task, is_child = 0 3.55.654.434 I slot print_timing: id 0 | task 20878 | prompt eval time = 125.57 ms / 322 tokens ( 0.39 ms per token, 2564.37 tokens per second) 3.55.654.440 I slot print_timing: id 0 | task 20878 | eval time = 2509.38 ms / 279 tokens ( 9.03 ms per token, 110.78 tokens per second) 3.55.654.441 I slot print_timing: id 0 | task 20878 | total time = 2634.94 ms / 601 tokens 3.55.654.443 I slot print_timing: id 0 | task 20878 | graphs reused = 20094 3.55.654.444 I slot print_timing: id 0 | task 20878 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.654.470 I slot release: id 0 | task 20878 | stop processing: n_tokens = 632, truncated = 0 3.55.670.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 235561099 3.55.670.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 3.55.739.907 I slot launch_slot_: id 0 | task 21160 | processing task, is_child = 0 3.56.277.898 I slot print_timing: id 0 | task 21160 | prompt eval time = 127.79 ms / 337 tokens ( 0.38 ms per token, 2637.20 tokens per second) 3.56.277.904 I slot print_timing: id 0 | task 21160 | eval time = 410.18 ms / 46 tokens ( 9.12 ms per token, 109.71 tokens per second) 3.56.277.905 I slot print_timing: id 0 | task 21160 | total time = 537.97 ms / 383 tokens 3.56.277.905 I slot print_timing: id 0 | task 21160 | graphs reused = 20138 3.56.277.906 I slot print_timing: id 0 | task 21160 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.277.935 I slot release: id 0 | task 21160 | stop processing: n_tokens = 414, truncated = 0 3.56.292.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 236184563 3.56.292.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.56.365.940 I slot launch_slot_: id 0 | task 21209 | processing task, is_child = 0 3.56.912.064 I slot print_timing: id 0 | task 21209 | prompt eval time = 128.13 ms / 325 tokens ( 0.39 ms per token, 2536.43 tokens per second) 3.56.912.070 I slot print_timing: id 0 | task 21209 | eval time = 417.97 ms / 47 tokens ( 9.09 ms per token, 110.06 tokens per second) 3.56.912.071 I slot print_timing: id 0 | task 21209 | total time = 546.10 ms / 372 tokens 3.56.912.072 I slot print_timing: id 0 | task 21209 | graphs reused = 20183 3.56.912.073 I slot print_timing: id 0 | task 21209 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.912.100 I slot release: id 0 | task 21209 | stop processing: n_tokens = 403, truncated = 0 3.56.929.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 236818728 3.56.929.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.670 MiB) 3.56.995.406 I slot launch_slot_: id 0 | task 21259 | processing task, is_child = 0 3.57.875.122 I slot print_timing: id 0 | task 21259 | prompt eval time = 128.46 ms / 331 tokens ( 0.39 ms per token, 2576.64 tokens per second) 3.57.875.127 I slot print_timing: id 0 | task 21259 | eval time = 751.23 ms / 84 tokens ( 9.05 ms per token, 110.48 tokens per second) 3.57.875.128 I slot print_timing: id 0 | task 21259 | total time = 879.70 ms / 415 tokens 3.57.875.129 I slot print_timing: id 0 | task 21259 | graphs reused = 20265 3.57.875.130 I slot print_timing: id 0 | task 21259 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.875.159 I slot release: id 0 | task 21259 | stop processing: n_tokens = 446, truncated = 0 3.57.892.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 237781787 3.57.892.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.858 MiB) 3.57.954.678 I slot launch_slot_: id 0 | task 21346 | processing task, is_child = 0 3.58.428.954 I slot print_timing: id 0 | task 21346 | prompt eval time = 128.89 ms / 336 tokens ( 0.38 ms per token, 2606.91 tokens per second) 3.58.428.960 I slot print_timing: id 0 | task 21346 | eval time = 345.37 ms / 39 tokens ( 9.09 ms per token, 110.03 tokens per second) 3.58.428.961 I slot print_timing: id 0 | task 21346 | total time = 474.25 ms / 375 tokens 3.58.428.962 I slot print_timing: id 0 | task 21346 | graphs reused = 20302 3.58.428.963 I slot print_timing: id 0 | task 21346 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.428.991 I slot release: id 0 | task 21346 | stop processing: n_tokens = 406, truncated = 0 3.58.432.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 238335619 3.58.432.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.763 MiB) 3.58.489.135 I slot launch_slot_: id 0 | task 21388 | processing task, is_child = 0 3.58.892.818 I slot print_timing: id 0 | task 21388 | prompt eval time = 129.99 ms / 349 tokens ( 0.37 ms per token, 2684.93 tokens per second) 3.58.892.826 I slot print_timing: id 0 | task 21388 | eval time = 273.68 ms / 31 tokens ( 9.12 ms per token, 109.62 tokens per second) 3.58.892.827 I slot print_timing: id 0 | task 21388 | total time = 403.66 ms / 380 tokens 3.58.892.828 I slot print_timing: id 0 | task 21388 | graphs reused = 20331 3.58.892.829 I slot print_timing: id 0 | task 21388 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.892.858 I slot release: id 0 | task 21388 | stop processing: n_tokens = 411, truncated = 0 3.58.909.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 238799486 3.58.909.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.701 MiB) 3.58.979.907 I slot launch_slot_: id 0 | task 21422 | processing task, is_child = 0 4.00.209.757 I slot print_timing: id 0 | task 21422 | prompt eval time = 127.76 ms / 336 tokens ( 0.38 ms per token, 2629.97 tokens per second) 4.00.209.763 I slot print_timing: id 0 | task 21422 | eval time = 1102.07 ms / 123 tokens ( 9.03 ms per token, 110.70 tokens per second) 4.00.209.764 I slot print_timing: id 0 | task 21422 | total time = 1229.83 ms / 459 tokens 4.00.209.765 I slot print_timing: id 0 | task 21422 | graphs reused = 20452 4.00.209.766 I slot print_timing: id 0 | task 21422 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.209.797 I slot release: id 0 | task 21422 | stop processing: n_tokens = 490, truncated = 0 4.00.232.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 240116425 4.00.232.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 4.00.298.765 I slot launch_slot_: id 0 | task 21548 | processing task, is_child = 0 4.03.431.787 I slot print_timing: id 0 | task 21548 | n_gen = 333, tg = 110.52 t/s, tg_3s = 110.85 t/s 4.04.860.324 I slot print_timing: id 0 | task 21548 | prompt eval time = 128.95 ms / 349 tokens ( 0.37 ms per token, 2706.41 tokens per second) 4.04.860.330 I slot print_timing: id 0 | task 21548 | eval time = 4432.59 ms / 490 tokens ( 9.06 ms per token, 110.32 tokens per second) 4.04.860.331 I slot print_timing: id 0 | task 21548 | total time = 4561.54 ms / 839 tokens 4.04.860.332 I slot print_timing: id 0 | task 21548 | graphs reused = 20938 4.04.860.333 I slot print_timing: id 0 | task 21548 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.860.362 I slot release: id 0 | task 21548 | stop processing: n_tokens = 870, truncated = 0 4.04.883.704 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 244766990 4.04.883.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.989 MiB) 4.04.964.293 I slot launch_slot_: id 0 | task 22041 | processing task, is_child = 0 4.05.957.157 I slot print_timing: id 0 | task 22041 | prompt eval time = 127.73 ms / 349 tokens ( 0.37 ms per token, 2732.37 tokens per second) 4.05.957.163 I slot print_timing: id 0 | task 22041 | eval time = 865.12 ms / 97 tokens ( 9.01 ms per token, 110.97 tokens per second) 4.05.957.164 I slot print_timing: id 0 | task 22041 | total time = 992.84 ms / 446 tokens 4.05.957.165 I slot print_timing: id 0 | task 22041 | graphs reused = 21033 4.05.957.166 I slot print_timing: id 0 | task 22041 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.957.193 I slot release: id 0 | task 22041 | stop processing: n_tokens = 477, truncated = 0 4.05.960.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 245863821 4.05.960.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.482 MiB) 4.06.023.025 I slot launch_slot_: id 0 | task 22141 | processing task, is_child = 0 4.06.435.429 I slot print_timing: id 0 | task 22141 | prompt eval time = 138.32 ms / 385 tokens ( 0.36 ms per token, 2783.30 tokens per second) 4.06.435.434 I slot print_timing: id 0 | task 22141 | eval time = 274.06 ms / 31 tokens ( 9.14 ms per token, 109.46 tokens per second) 4.06.435.436 I slot print_timing: id 0 | task 22141 | total time = 412.39 ms / 416 tokens 4.06.435.437 I slot print_timing: id 0 | task 22141 | graphs reused = 21062 4.06.435.437 I slot print_timing: id 0 | task 22141 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.435.465 I slot release: id 0 | task 22141 | stop processing: n_tokens = 447, truncated = 0 4.06.459.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 246342094 4.06.459.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.924 MiB) 4.06.515.538 I slot launch_slot_: id 0 | task 22175 | processing task, is_child = 0 4.07.150.296 I slot print_timing: id 0 | task 22175 | prompt eval time = 126.62 ms / 328 tokens ( 0.39 ms per token, 2590.45 tokens per second) 4.07.150.302 I slot print_timing: id 0 | task 22175 | eval time = 508.12 ms / 57 tokens ( 9.07 ms per token, 110.21 tokens per second) 4.07.150.303 I slot print_timing: id 0 | task 22175 | total time = 634.74 ms / 385 tokens 4.07.150.304 I slot print_timing: id 0 | task 22175 | graphs reused = 21117 4.07.150.305 I slot print_timing: id 0 | task 22175 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.150.332 I slot release: id 0 | task 22175 | stop processing: n_tokens = 416, truncated = 0