$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--mradermacher--granite-4.2-8b-GGUF\snapshots\72e0876f143f0642399a9a0b2565b697706d7c27\granite-4.2-8b.Q5_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.088.086 I srv llama_server: initializing ... 0.00.088.093 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.088.217 I srv init_listene: The UI is disabled 0.00.088.220 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.088.304 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) 0.00.103.054 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--mradermacher--granite-4.2-8b-GGUF\snapshots\72e0876f143f0642399a9a0b2565b697706d7c27\granite-4.2-8b.Q5_K_M.gguf' 0.02.438.391 I cmn init: llama threadpool init, n_threads = 8 0.02.508.183 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.512.885 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.512.902 I srv llama_server: model loaded 0.02.512.905 I srv llama_server: listening on http://127.0.0.1:8089 0.04.551.394 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.551.576 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.326.741 I slot print_timing: id 0 | task 0 | prompt eval time = 104.03 ms / 368 tokens ( 0.28 ms per token, 3537.37 tokens per second) 0.05.326.747 I slot print_timing: id 0 | task 0 | eval time = 671.12 ms / 61 tokens ( 11.19 ms per token, 89.40 tokens per second) 0.05.326.748 I slot print_timing: id 0 | task 0 | total time = 775.15 ms / 429 tokens 0.05.326.754 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.05.326.755 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.326.786 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.05.347.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 5240710 0.05.362.475 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.05.924.600 I slot print_timing: id 0 | task 62 | prompt eval time = 83.06 ms / 292 tokens ( 0.28 ms per token, 3515.74 tokens per second) 0.05.924.605 I slot print_timing: id 0 | task 62 | eval time = 479.05 ms / 44 tokens ( 11.14 ms per token, 89.76 tokens per second) 0.05.924.606 I slot print_timing: id 0 | task 62 | total time = 562.11 ms / 336 tokens 0.05.924.607 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.05.924.608 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.924.637 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.05.939.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 5838562 0.05.951.732 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.06.531.605 I slot print_timing: id 0 | task 107 | prompt eval time = 90.34 ms / 338 tokens ( 0.27 ms per token, 3741.21 tokens per second) 0.06.531.611 I slot print_timing: id 0 | task 107 | eval time = 489.51 ms / 45 tokens ( 11.13 ms per token, 89.89 tokens per second) 0.06.531.612 I slot print_timing: id 0 | task 107 | total time = 579.86 ms / 383 tokens 0.06.531.613 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.06.531.614 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.531.640 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.06.535.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 6445565 0.06.549.704 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.07.141.553 I slot print_timing: id 0 | task 153 | prompt eval time = 90.09 ms / 371 tokens ( 0.24 ms per token, 4118.10 tokens per second) 0.07.141.558 I slot print_timing: id 0 | task 153 | eval time = 501.74 ms / 46 tokens ( 11.15 ms per token, 89.69 tokens per second) 0.07.141.559 I slot print_timing: id 0 | task 153 | total time = 591.83 ms / 417 tokens 0.07.141.560 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.07.141.561 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.141.589 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.07.160.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.091 0.07.175.760 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.07.933.449 I slot print_timing: id 0 | task 200 | prompt eval time = 89.86 ms / 345 tokens ( 0.26 ms per token, 3839.52 tokens per second) 0.07.933.455 I slot print_timing: id 0 | task 200 | eval time = 667.82 ms / 61 tokens ( 11.13 ms per token, 89.84 tokens per second) 0.07.933.456 I slot print_timing: id 0 | task 200 | total time = 757.68 ms / 406 tokens 0.07.933.456 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.07.933.457 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.933.484 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.07.957.968 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 7847408 0.07.973.533 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.08.765.560 I slot print_timing: id 0 | task 262 | prompt eval time = 90.11 ms / 351 tokens ( 0.26 ms per token, 3895.20 tokens per second) 0.08.765.566 I slot print_timing: id 0 | task 262 | eval time = 701.90 ms / 64 tokens ( 11.14 ms per token, 89.76 tokens per second) 0.08.765.567 I slot print_timing: id 0 | task 262 | total time = 792.01 ms / 415 tokens 0.08.765.568 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.08.765.569 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.765.597 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.08.783.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 8679521 0.08.799.054 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.09.553.473 I slot print_timing: id 0 | task 327 | prompt eval time = 110.83 ms / 395 tokens ( 0.28 ms per token, 3564.05 tokens per second) 0.09.553.479 I slot print_timing: id 0 | task 327 | eval time = 643.58 ms / 58 tokens ( 11.29 ms per token, 88.57 tokens per second) 0.09.553.480 I slot print_timing: id 0 | task 327 | total time = 754.40 ms / 453 tokens 0.09.553.481 I slot print_timing: id 0 | task 327 | graphs reused = 366 0.09.553.482 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.553.510 I slot release: id 0 | task 327 | stop processing: n_tokens = 477, truncated = 0 0.09.579.868 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 9467435 0.09.596.026 I slot launch_slot_: id 0 | task 386 | processing task, is_child = 0 0.10.504.104 I slot print_timing: id 0 | task 386 | prompt eval time = 113.36 ms / 446 tokens ( 0.25 ms per token, 3934.44 tokens per second) 0.10.504.110 I slot print_timing: id 0 | task 386 | eval time = 794.70 ms / 72 tokens ( 11.19 ms per token, 89.34 tokens per second) 0.10.504.111 I slot print_timing: id 0 | task 386 | total time = 908.06 ms / 518 tokens 0.10.504.112 I slot print_timing: id 0 | task 386 | graphs reused = 435 0.10.504.112 I slot print_timing: id 0 | task 386 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.504.143 I slot release: id 0 | task 386 | stop processing: n_tokens = 542, truncated = 0 0.10.520.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 10418068 0.10.538.545 I slot launch_slot_: id 0 | task 459 | processing task, is_child = 0 0.11.189.366 I slot print_timing: id 0 | task 459 | prompt eval time = 83.46 ms / 319 tokens ( 0.26 ms per token, 3822.37 tokens per second) 0.11.189.371 I slot print_timing: id 0 | task 459 | eval time = 567.35 ms / 52 tokens ( 11.12 ms per token, 89.89 tokens per second) 0.11.189.372 I slot print_timing: id 0 | task 459 | total time = 650.81 ms / 371 tokens 0.11.189.373 I slot print_timing: id 0 | task 459 | graphs reused = 485 0.11.189.374 I slot print_timing: id 0 | task 459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.189.400 I slot release: id 0 | task 459 | stop processing: n_tokens = 395, truncated = 0 0.11.193.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 11103325 0.11.207.172 I slot launch_slot_: id 0 | task 512 | processing task, is_child = 0 0.11.747.210 I slot print_timing: id 0 | task 512 | prompt eval time = 83.88 ms / 336 tokens ( 0.25 ms per token, 4005.87 tokens per second) 0.11.747.216 I slot print_timing: id 0 | task 512 | eval time = 456.15 ms / 42 tokens ( 11.13 ms per token, 89.88 tokens per second) 0.11.747.218 I slot print_timing: id 0 | task 512 | total time = 540.02 ms / 378 tokens 0.11.747.219 I slot print_timing: id 0 | task 512 | graphs reused = 525 0.11.747.220 I slot print_timing: id 0 | task 512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.747.248 I slot release: id 0 | task 512 | stop processing: n_tokens = 402, truncated = 0 0.11.751.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 11661173 0.11.766.952 I slot launch_slot_: id 0 | task 555 | processing task, is_child = 0 0.12.614.444 I slot print_timing: id 0 | task 555 | prompt eval time = 93.05 ms / 352 tokens ( 0.26 ms per token, 3782.79 tokens per second) 0.12.614.449 I slot print_timing: id 0 | task 555 | eval time = 754.41 ms / 68 tokens ( 11.26 ms per token, 88.81 tokens per second) 0.12.614.450 I slot print_timing: id 0 | task 555 | total time = 847.47 ms / 420 tokens 0.12.614.451 I slot print_timing: id 0 | task 555 | graphs reused = 591 0.12.614.452 I slot print_timing: id 0 | task 555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.614.480 I slot release: id 0 | task 555 | stop processing: n_tokens = 444, truncated = 0 0.12.643.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 12528405 0.12.659.027 I slot launch_slot_: id 0 | task 624 | processing task, is_child = 0 0.13.335.813 I slot print_timing: id 0 | task 624 | prompt eval time = 110.74 ms / 387 tokens ( 0.29 ms per token, 3494.80 tokens per second) 0.13.335.819 I slot print_timing: id 0 | task 624 | eval time = 566.04 ms / 52 tokens ( 11.10 ms per token, 90.10 tokens per second) 0.13.335.820 I slot print_timing: id 0 | task 624 | total time = 676.77 ms / 439 tokens 0.13.335.821 I slot print_timing: id 0 | task 624 | graphs reused = 641 0.13.335.822 I slot print_timing: id 0 | task 624 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.335.851 I slot release: id 0 | task 624 | stop processing: n_tokens = 463, truncated = 0 0.13.339.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 13249776 0.13.355.820 I slot launch_slot_: id 0 | task 677 | processing task, is_child = 0 0.14.144.998 I slot print_timing: id 0 | task 677 | prompt eval time = 89.87 ms / 349 tokens ( 0.26 ms per token, 3883.21 tokens per second) 0.14.145.004 I slot print_timing: id 0 | task 677 | eval time = 699.29 ms / 64 tokens ( 11.10 ms per token, 90.09 tokens per second) 0.14.145.005 I slot print_timing: id 0 | task 677 | total time = 789.16 ms / 413 tokens 0.14.145.005 I slot print_timing: id 0 | task 677 | graphs reused = 703 0.14.145.006 I slot print_timing: id 0 | task 677 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.145.032 I slot release: id 0 | task 677 | stop processing: n_tokens = 437, truncated = 0 0.14.149.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 14058957 0.14.164.388 I slot launch_slot_: id 0 | task 742 | processing task, is_child = 0 0.14.893.302 I slot print_timing: id 0 | task 742 | prompt eval time = 90.54 ms / 352 tokens ( 0.26 ms per token, 3887.66 tokens per second) 0.14.893.308 I slot print_timing: id 0 | task 742 | eval time = 638.36 ms / 57 tokens ( 11.40 ms per token, 87.73 tokens per second) 0.14.893.309 I slot print_timing: id 0 | task 742 | total time = 728.90 ms / 409 tokens 0.14.893.310 I slot print_timing: id 0 | task 742 | graphs reused = 758 0.14.893.311 I slot print_timing: id 0 | task 742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.893.338 I slot release: id 0 | task 742 | stop processing: n_tokens = 433, truncated = 0 0.14.910.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 14807263 0.14.924.969 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 0.15.766.272 I slot print_timing: id 0 | task 800 | prompt eval time = 90.21 ms / 347 tokens ( 0.26 ms per token, 3846.75 tokens per second) 0.15.766.278 I slot print_timing: id 0 | task 800 | eval time = 751.08 ms / 68 tokens ( 11.21 ms per token, 89.20 tokens per second) 0.15.766.279 I slot print_timing: id 0 | task 800 | total time = 841.29 ms / 415 tokens 0.15.766.280 I slot print_timing: id 0 | task 800 | graphs reused = 824 0.15.766.281 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.766.308 I slot release: id 0 | task 800 | stop processing: n_tokens = 439, truncated = 0 0.15.785.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 15680233 0.15.801.134 I slot launch_slot_: id 0 | task 869 | processing task, is_child = 0 0.16.495.226 I slot print_timing: id 0 | task 869 | prompt eval time = 83.44 ms / 320 tokens ( 0.26 ms per token, 3835.00 tokens per second) 0.16.495.232 I slot print_timing: id 0 | task 869 | eval time = 610.64 ms / 56 tokens ( 11.10 ms per token, 90.07 tokens per second) 0.16.495.233 I slot print_timing: id 0 | task 869 | total time = 694.08 ms / 376 tokens 0.16.495.234 I slot print_timing: id 0 | task 869 | graphs reused = 878 0.16.495.235 I slot print_timing: id 0 | task 869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.495.263 I slot release: id 0 | task 869 | stop processing: n_tokens = 400, truncated = 0 0.16.523.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 16409188 0.16.537.023 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 0.17.104.716 I slot print_timing: id 0 | task 926 | prompt eval time = 89.66 ms / 343 tokens ( 0.26 ms per token, 3825.65 tokens per second) 0.17.104.723 I slot print_timing: id 0 | task 926 | eval time = 478.02 ms / 44 tokens ( 11.12 ms per token, 89.95 tokens per second) 0.17.104.725 I slot print_timing: id 0 | task 926 | total time = 567.68 ms / 387 tokens 0.17.104.726 I slot print_timing: id 0 | task 926 | graphs reused = 920 0.17.104.727 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.104.755 I slot release: id 0 | task 926 | stop processing: n_tokens = 411, truncated = 0 0.17.123.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 17018680 0.17.136.957 I slot launch_slot_: id 0 | task 971 | processing task, is_child = 0 0.17.698.771 I slot print_timing: id 0 | task 971 | prompt eval time = 83.82 ms / 325 tokens ( 0.26 ms per token, 3877.36 tokens per second) 0.17.698.778 I slot print_timing: id 0 | task 971 | eval time = 477.98 ms / 44 tokens ( 11.12 ms per token, 89.96 tokens per second) 0.17.698.779 I slot print_timing: id 0 | task 971 | total time = 561.80 ms / 369 tokens 0.17.698.779 I slot print_timing: id 0 | task 971 | graphs reused = 962 0.17.698.780 I slot print_timing: id 0 | task 971 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.698.807 I slot release: id 0 | task 971 | stop processing: n_tokens = 393, truncated = 0 0.17.726.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 17612732 0.17.740.226 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.18.290.986 I slot print_timing: id 0 | task 1016 | prompt eval time = 83.62 ms / 323 tokens ( 0.26 ms per token, 3862.80 tokens per second) 0.18.290.992 I slot print_timing: id 0 | task 1016 | eval time = 467.13 ms / 43 tokens ( 11.12 ms per token, 89.91 tokens per second) 0.18.290.993 I slot print_timing: id 0 | task 1016 | total time = 550.74 ms / 366 tokens 0.18.290.994 I slot print_timing: id 0 | task 1016 | graphs reused = 1003 0.18.290.994 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.291.022 I slot release: id 0 | task 1016 | stop processing: n_tokens = 390, truncated = 0 0.18.318.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 18204947 0.18.331.877 I slot launch_slot_: id 0 | task 1060 | processing task, is_child = 0 0.19.202.775 I slot print_timing: id 0 | task 1060 | prompt eval time = 90.46 ms / 359 tokens ( 0.25 ms per token, 3968.65 tokens per second) 0.19.202.780 I slot print_timing: id 0 | task 1060 | eval time = 780.42 ms / 69 tokens ( 11.48 ms per token, 87.13 tokens per second) 0.19.202.781 I slot print_timing: id 0 | task 1060 | total time = 870.88 ms / 428 tokens 0.19.202.782 I slot print_timing: id 0 | task 1060 | graphs reused = 1070 0.19.202.783 I slot print_timing: id 0 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.202.812 I slot release: id 0 | task 1060 | stop processing: n_tokens = 452, truncated = 0 0.19.222.419 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 19116737 0.19.238.132 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.20.010.540 I slot print_timing: id 0 | task 1130 | prompt eval time = 84.22 ms / 334 tokens ( 0.25 ms per token, 3965.76 tokens per second) 0.20.010.545 I slot print_timing: id 0 | task 1130 | eval time = 688.17 ms / 63 tokens ( 11.10 ms per token, 90.09 tokens per second) 0.20.010.546 I slot print_timing: id 0 | task 1130 | total time = 772.39 ms / 397 tokens 0.20.010.547 I slot print_timing: id 0 | task 1130 | graphs reused = 1131 0.20.010.548 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.010.576 I slot release: id 0 | task 1130 | stop processing: n_tokens = 421, truncated = 0 0.20.029.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 19924500 0.20.043.561 I slot launch_slot_: id 0 | task 1194 | processing task, is_child = 0 0.20.931.172 I slot print_timing: id 0 | task 1194 | prompt eval time = 90.33 ms / 382 tokens ( 0.24 ms per token, 4229.13 tokens per second) 0.20.931.178 I slot print_timing: id 0 | task 1194 | eval time = 797.27 ms / 73 tokens ( 11.07 ms per token, 90.31 tokens per second) 0.20.931.179 I slot print_timing: id 0 | task 1194 | total time = 887.60 ms / 455 tokens 0.20.931.180 I slot print_timing: id 0 | task 1194 | graphs reused = 1202 0.20.931.181 I slot print_timing: id 0 | task 1194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.931.212 I slot release: id 0 | task 1194 | stop processing: n_tokens = 479, truncated = 0 0.20.947.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 20845137 0.20.963.914 I slot launch_slot_: id 0 | task 1268 | processing task, is_child = 0 0.21.763.652 I slot print_timing: id 0 | task 1268 | prompt eval time = 90.63 ms / 368 tokens ( 0.25 ms per token, 4060.29 tokens per second) 0.21.763.657 I slot print_timing: id 0 | task 1268 | eval time = 709.09 ms / 65 tokens ( 11.08 ms per token, 90.26 tokens per second) 0.21.763.658 I slot print_timing: id 0 | task 1268 | total time = 799.72 ms / 433 tokens 0.21.763.659 I slot print_timing: id 0 | task 1268 | graphs reused = 1265 0.21.763.660 I slot print_timing: id 0 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.763.687 I slot release: id 0 | task 1268 | stop processing: n_tokens = 457, truncated = 0 0.21.789.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 21677612 0.21.804.682 I slot launch_slot_: id 0 | task 1334 | processing task, is_child = 0 0.22.847.048 I slot print_timing: id 0 | task 1334 | prompt eval time = 90.43 ms / 382 tokens ( 0.24 ms per token, 4224.26 tokens per second) 0.22.847.053 I slot print_timing: id 0 | task 1334 | eval time = 951.92 ms / 87 tokens ( 11.07 ms per token, 90.34 tokens per second) 0.22.847.054 I slot print_timing: id 0 | task 1334 | total time = 1042.35 ms / 469 tokens 0.22.847.055 I slot print_timing: id 0 | task 1334 | graphs reused = 1350 0.22.847.056 I slot print_timing: id 0 | task 1334 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.847.085 I slot release: id 0 | task 1334 | stop processing: n_tokens = 493, truncated = 0 0.22.864.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 22761009 0.22.880.619 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 0.23.724.214 I slot print_timing: id 0 | task 1422 | prompt eval time = 111.83 ms / 410 tokens ( 0.27 ms per token, 3666.31 tokens per second) 0.23.724.220 I slot print_timing: id 0 | task 1422 | eval time = 731.75 ms / 67 tokens ( 11.09 ms per token, 90.19 tokens per second) 0.23.724.221 I slot print_timing: id 0 | task 1422 | total time = 843.58 ms / 477 tokens 0.23.724.222 I slot print_timing: id 0 | task 1422 | graphs reused = 1415 0.23.724.222 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.724.254 I slot release: id 0 | task 1422 | stop processing: n_tokens = 501, truncated = 0 0.23.741.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 23638179 0.23.758.382 I slot launch_slot_: id 0 | task 1490 | processing task, is_child = 0 0.24.558.809 I slot print_timing: id 0 | task 1490 | prompt eval time = 90.90 ms / 367 tokens ( 0.25 ms per token, 4037.36 tokens per second) 0.24.558.814 I slot print_timing: id 0 | task 1490 | eval time = 709.51 ms / 65 tokens ( 11.09 ms per token, 90.20 tokens per second) 0.24.558.815 I slot print_timing: id 0 | task 1490 | total time = 800.41 ms / 432 tokens 0.24.558.816 I slot print_timing: id 0 | task 1490 | graphs reused = 1478 0.24.558.817 I slot print_timing: id 0 | task 1490 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.558.845 I slot release: id 0 | task 1490 | stop processing: n_tokens = 458, truncated = 0 0.24.563.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 24472770 0.24.578.631 I slot launch_slot_: id 0 | task 1556 | processing task, is_child = 0 0.25.250.233 I slot print_timing: id 0 | task 1556 | prompt eval time = 83.68 ms / 326 tokens ( 0.26 ms per token, 3895.84 tokens per second) 0.25.250.239 I slot print_timing: id 0 | task 1556 | eval time = 587.91 ms / 54 tokens ( 11.09 ms per token, 90.15 tokens per second) 0.25.250.240 I slot print_timing: id 0 | task 1556 | total time = 671.59 ms / 380 tokens 0.25.250.240 I slot print_timing: id 0 | task 1556 | graphs reused = 1530 0.25.250.241 I slot print_timing: id 0 | task 1556 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.250.268 I slot release: id 0 | task 1556 | stop processing: n_tokens = 404, truncated = 0 0.25.269.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 25164193 0.25.283.645 I slot launch_slot_: id 0 | task 1611 | processing task, is_child = 0 0.26.071.729 I slot print_timing: id 0 | task 1611 | prompt eval time = 90.20 ms / 351 tokens ( 0.26 ms per token, 3891.44 tokens per second) 0.26.071.735 I slot print_timing: id 0 | task 1611 | eval time = 697.87 ms / 64 tokens ( 11.08 ms per token, 90.27 tokens per second) 0.26.071.736 I slot print_timing: id 0 | task 1611 | total time = 788.07 ms / 415 tokens 0.26.071.737 I slot print_timing: id 0 | task 1611 | graphs reused = 1592 0.26.071.738 I slot print_timing: id 0 | task 1611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.071.767 I slot release: id 0 | task 1611 | stop processing: n_tokens = 441, truncated = 0 0.26.095.388 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 25985692 0.26.110.445 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.27.063.737 I slot print_timing: id 0 | task 1676 | prompt eval time = 90.61 ms / 379 tokens ( 0.24 ms per token, 4182.90 tokens per second) 0.27.063.743 I slot print_timing: id 0 | task 1676 | eval time = 862.67 ms / 78 tokens ( 11.20 ms per token, 89.26 tokens per second) 0.27.063.744 I slot print_timing: id 0 | task 1676 | total time = 953.28 ms / 457 tokens 0.27.063.745 I slot print_timing: id 0 | task 1676 | graphs reused = 1668 0.27.063.745 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.063.774 I slot release: id 0 | task 1676 | stop processing: n_tokens = 481, truncated = 0 0.27.081.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 26977699 0.27.097.194 I slot launch_slot_: id 0 | task 1755 | processing task, is_child = 0 0.27.960.250 I slot print_timing: id 0 | task 1755 | prompt eval time = 90.71 ms / 356 tokens ( 0.25 ms per token, 3924.72 tokens per second) 0.27.960.256 I slot print_timing: id 0 | task 1755 | eval time = 772.33 ms / 70 tokens ( 11.19 ms per token, 89.34 tokens per second) 0.27.960.257 I slot print_timing: id 0 | task 1755 | total time = 863.04 ms / 426 tokens 0.27.960.258 I slot print_timing: id 0 | task 1755 | graphs reused = 1736 0.27.960.259 I slot print_timing: id 0 | task 1755 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.960.288 I slot release: id 0 | task 1755 | stop processing: n_tokens = 450, truncated = 0 0.27.964.419 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 27874213 0.27.979.526 I slot launch_slot_: id 0 | task 1826 | processing task, is_child = 0 0.28.729.055 I slot print_timing: id 0 | task 1826 | prompt eval time = 83.96 ms / 331 tokens ( 0.25 ms per token, 3942.35 tokens per second) 0.28.729.060 I slot print_timing: id 0 | task 1826 | eval time = 665.55 ms / 61 tokens ( 11.09 ms per token, 90.15 tokens per second) 0.28.729.061 I slot print_timing: id 0 | task 1826 | total time = 749.51 ms / 392 tokens 0.28.729.062 I slot print_timing: id 0 | task 1826 | graphs reused = 1795 0.28.729.063 I slot print_timing: id 0 | task 1826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.729.092 I slot release: id 0 | task 1826 | stop processing: n_tokens = 416, truncated = 0 0.28.756.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 28643017 0.28.771.207 I slot launch_slot_: id 0 | task 1888 | processing task, is_child = 0 0.29.223.837 I slot print_timing: id 0 | task 1888 | prompt eval time = 84.04 ms / 334 tokens ( 0.25 ms per token, 3974.44 tokens per second) 0.29.223.844 I slot print_timing: id 0 | task 1888 | eval time = 368.57 ms / 34 tokens ( 11.17 ms per token, 89.53 tokens per second) 0.29.223.845 I slot print_timing: id 0 | task 1888 | total time = 452.61 ms / 368 tokens 0.29.223.846 I slot print_timing: id 0 | task 1888 | graphs reused = 1827 0.29.223.847 I slot print_timing: id 0 | task 1888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.223.878 I slot release: id 0 | task 1888 | stop processing: n_tokens = 392, truncated = 0 0.29.242.143 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 29137802 0.29.255.795 I slot launch_slot_: id 0 | task 1923 | processing task, is_child = 0 0.30.090.691 I slot print_timing: id 0 | task 1923 | prompt eval time = 91.08 ms / 362 tokens ( 0.25 ms per token, 3974.40 tokens per second) 0.30.090.697 I slot print_timing: id 0 | task 1923 | eval time = 743.79 ms / 68 tokens ( 11.10 ms per token, 90.08 tokens per second) 0.30.090.698 I slot print_timing: id 0 | task 1923 | total time = 834.88 ms / 430 tokens 0.30.090.699 I slot print_timing: id 0 | task 1923 | graphs reused = 1893 0.30.090.700 I slot print_timing: id 0 | task 1923 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.090.731 I slot release: id 0 | task 1923 | stop processing: n_tokens = 454, truncated = 0 0.30.094.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 30004655 0.30.111.562 I slot launch_slot_: id 0 | task 1992 | processing task, is_child = 0 0.30.926.421 I slot print_timing: id 0 | task 1992 | prompt eval time = 91.15 ms / 384 tokens ( 0.24 ms per token, 4212.93 tokens per second) 0.30.926.426 I slot print_timing: id 0 | task 1992 | eval time = 723.69 ms / 66 tokens ( 11.13 ms per token, 89.82 tokens per second) 0.30.926.427 I slot print_timing: id 0 | task 1992 | total time = 814.84 ms / 450 tokens 0.30.926.428 I slot print_timing: id 0 | task 1992 | graphs reused = 1957 0.30.926.429 I slot print_timing: id 0 | task 1992 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.926.460 I slot release: id 0 | task 1992 | stop processing: n_tokens = 474, truncated = 0 0.30.955.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 30840385 0.30.971.691 I slot launch_slot_: id 0 | task 2059 | processing task, is_child = 0 0.31.654.684 I slot print_timing: id 0 | task 2059 | prompt eval time = 83.83 ms / 325 tokens ( 0.26 ms per token, 3877.03 tokens per second) 0.31.654.690 I slot print_timing: id 0 | task 2059 | eval time = 599.15 ms / 55 tokens ( 11.10 ms per token, 90.13 tokens per second) 0.31.654.691 I slot print_timing: id 0 | task 2059 | total time = 682.98 ms / 380 tokens 0.31.654.692 I slot print_timing: id 0 | task 2059 | graphs reused = 2010 0.31.654.693 I slot print_timing: id 0 | task 2059 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.654.722 I slot release: id 0 | task 2059 | stop processing: n_tokens = 404, truncated = 0 0.31.659.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 31568647 0.31.672.786 I slot launch_slot_: id 0 | task 2115 | processing task, is_child = 0 0.32.406.716 I slot print_timing: id 0 | task 2115 | prompt eval time = 91.08 ms / 366 tokens ( 0.25 ms per token, 4018.67 tokens per second) 0.32.406.723 I slot print_timing: id 0 | task 2115 | eval time = 642.84 ms / 59 tokens ( 11.08 ms per token, 90.22 tokens per second) 0.32.406.724 I slot print_timing: id 0 | task 2115 | total time = 733.92 ms / 425 tokens 0.32.406.725 I slot print_timing: id 0 | task 2115 | graphs reused = 2067 0.32.406.726 I slot print_timing: id 0 | task 2115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.406.756 I slot release: id 0 | task 2115 | stop processing: n_tokens = 449, truncated = 0 0.32.422.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 32320681 0.32.437.922 I slot launch_slot_: id 0 | task 2175 | processing task, is_child = 0 0.32.910.977 I slot print_timing: id 0 | task 2175 | prompt eval time = 82.69 ms / 295 tokens ( 0.28 ms per token, 3567.50 tokens per second) 0.32.910.982 I slot print_timing: id 0 | task 2175 | eval time = 390.35 ms / 36 tokens ( 11.15 ms per token, 89.66 tokens per second) 0.32.910.983 I slot print_timing: id 0 | task 2175 | total time = 473.04 ms / 331 tokens 0.32.910.984 I slot print_timing: id 0 | task 2175 | graphs reused = 2101 0.32.910.985 I slot print_timing: id 0 | task 2175 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.911.012 I slot release: id 0 | task 2175 | stop processing: n_tokens = 355, truncated = 0 0.32.938.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 32824937 0.32.950.997 I slot launch_slot_: id 0 | task 2212 | processing task, is_child = 0 0.33.578.165 I slot print_timing: id 0 | task 2212 | prompt eval time = 83.34 ms / 307 tokens ( 0.27 ms per token, 3683.66 tokens per second) 0.33.578.171 I slot print_timing: id 0 | task 2212 | eval time = 543.81 ms / 50 tokens ( 11.10 ms per token, 90.10 tokens per second) 0.33.578.172 I slot print_timing: id 0 | task 2212 | total time = 627.15 ms / 357 tokens 0.33.578.173 I slot print_timing: id 0 | task 2212 | graphs reused = 2149 0.33.578.173 I slot print_timing: id 0 | task 2212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.578.201 I slot release: id 0 | task 2212 | stop processing: n_tokens = 381, truncated = 0 0.33.598.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 33492125 0.33.611.274 I slot launch_slot_: id 0 | task 2263 | processing task, is_child = 0 0.34.107.371 I slot print_timing: id 0 | task 2263 | prompt eval time = 83.68 ms / 319 tokens ( 0.26 ms per token, 3812.00 tokens per second) 0.34.107.376 I slot print_timing: id 0 | task 2263 | eval time = 412.40 ms / 38 tokens ( 11.15 ms per token, 89.72 tokens per second) 0.34.107.377 I slot print_timing: id 0 | task 2263 | total time = 496.08 ms / 357 tokens 0.34.107.378 I slot print_timing: id 0 | task 2263 | graphs reused = 2185 0.34.107.379 I slot print_timing: id 0 | task 2263 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.107.407 I slot release: id 0 | task 2263 | stop processing: n_tokens = 381, truncated = 0 0.34.111.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 34021332 0.34.124.937 I slot launch_slot_: id 0 | task 2302 | processing task, is_child = 0 0.34.785.714 I slot print_timing: id 0 | task 2302 | prompt eval time = 83.61 ms / 315 tokens ( 0.27 ms per token, 3767.54 tokens per second) 0.34.785.720 I slot print_timing: id 0 | task 2302 | eval time = 577.15 ms / 53 tokens ( 11.10 ms per token, 90.10 tokens per second) 0.34.785.721 I slot print_timing: id 0 | task 2302 | total time = 660.76 ms / 368 tokens 0.34.785.722 I slot print_timing: id 0 | task 2302 | graphs reused = 2236 0.34.785.723 I slot print_timing: id 0 | task 2302 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.785.750 I slot release: id 0 | task 2302 | stop processing: n_tokens = 392, truncated = 0 0.34.804.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 34699675 0.34.817.970 I slot launch_slot_: id 0 | task 2356 | processing task, is_child = 0 0.35.541.243 I slot print_timing: id 0 | task 2356 | prompt eval time = 90.89 ms / 367 tokens ( 0.25 ms per token, 4037.67 tokens per second) 0.35.541.249 I slot print_timing: id 0 | task 2356 | eval time = 632.36 ms / 58 tokens ( 11.09 ms per token, 90.14 tokens per second) 0.35.541.250 I slot print_timing: id 0 | task 2356 | total time = 723.26 ms / 425 tokens 0.35.541.250 I slot print_timing: id 0 | task 2356 | graphs reused = 2292 0.35.541.252 I slot print_timing: id 0 | task 2356 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.541.281 I slot release: id 0 | task 2356 | stop processing: n_tokens = 449, truncated = 0 0.35.559.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 35455206 0.35.574.900 I slot launch_slot_: id 0 | task 2415 | processing task, is_child = 0 0.36.494.682 I slot print_timing: id 0 | task 2415 | prompt eval time = 124.22 ms / 499 tokens ( 0.25 ms per token, 4016.97 tokens per second) 0.36.494.687 I slot print_timing: id 0 | task 2415 | eval time = 795.54 ms / 70 tokens ( 11.53 ms per token, 86.73 tokens per second) 0.36.494.688 I slot print_timing: id 0 | task 2415 | total time = 919.77 ms / 569 tokens 0.36.494.689 I slot print_timing: id 0 | task 2415 | graphs reused = 2360 0.36.494.690 I slot print_timing: id 0 | task 2415 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.494.723 I slot release: id 0 | task 2415 | stop processing: n_tokens = 593, truncated = 0 0.36.498.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 36408647 0.36.517.454 I slot launch_slot_: id 0 | task 2486 | processing task, is_child = 0 0.37.144.937 I slot print_timing: id 0 | task 2486 | prompt eval time = 83.47 ms / 319 tokens ( 0.26 ms per token, 3821.64 tokens per second) 0.37.144.942 I slot print_timing: id 0 | task 2486 | eval time = 544.00 ms / 50 tokens ( 11.10 ms per token, 90.07 tokens per second) 0.37.144.943 I slot print_timing: id 0 | task 2486 | total time = 627.47 ms / 369 tokens 0.37.144.944 I slot print_timing: id 0 | task 2486 | graphs reused = 2408 0.37.144.945 I slot print_timing: id 0 | task 2486 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.144.972 I slot release: id 0 | task 2486 | stop processing: n_tokens = 393, truncated = 0 0.37.149.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 37058897 0.37.162.818 I slot launch_slot_: id 0 | task 2537 | processing task, is_child = 0 0.37.885.846 I slot print_timing: id 0 | task 2537 | prompt eval time = 90.46 ms / 348 tokens ( 0.26 ms per token, 3846.88 tokens per second) 0.37.885.851 I slot print_timing: id 0 | task 2537 | eval time = 632.55 ms / 58 tokens ( 11.10 ms per token, 90.11 tokens per second) 0.37.885.852 I slot print_timing: id 0 | task 2537 | total time = 723.01 ms / 406 tokens 0.37.885.853 I slot print_timing: id 0 | task 2537 | graphs reused = 2464 0.37.885.854 I slot print_timing: id 0 | task 2537 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.885.883 I slot release: id 0 | task 2537 | stop processing: n_tokens = 430, truncated = 0 0.37.914.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 37799808 0.37.929.151 I slot launch_slot_: id 0 | task 2596 | processing task, is_child = 0 0.38.861.510 I slot print_timing: id 0 | task 2596 | prompt eval time = 111.84 ms / 404 tokens ( 0.28 ms per token, 3612.21 tokens per second) 0.38.861.516 I slot print_timing: id 0 | task 2596 | eval time = 820.50 ms / 75 tokens ( 11.09 ms per token, 90.19 tokens per second) 0.38.861.517 I slot print_timing: id 0 | task 2596 | total time = 932.34 ms / 479 tokens 0.38.861.517 I slot print_timing: id 0 | task 2596 | graphs reused = 2537 0.38.861.518 I slot print_timing: id 0 | task 2596 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.861.550 I slot release: id 0 | task 2596 | stop processing: n_tokens = 503, truncated = 0 0.38.878.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 38775474 0.38.895.782 I slot launch_slot_: id 0 | task 2672 | processing task, is_child = 0 0.39.671.836 I slot print_timing: id 0 | task 2672 | prompt eval time = 112.46 ms / 408 tokens ( 0.28 ms per token, 3627.89 tokens per second) 0.39.671.842 I slot print_timing: id 0 | task 2672 | eval time = 663.55 ms / 60 tokens ( 11.25 ms per token, 88.92 tokens per second) 0.39.671.843 I slot print_timing: id 0 | task 2672 | total time = 776.01 ms / 468 tokens 0.39.671.844 I slot print_timing: id 0 | task 2672 | graphs reused = 2595 0.39.671.845 I slot print_timing: id 0 | task 2672 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.671.876 I slot release: id 0 | task 2672 | stop processing: n_tokens = 494, truncated = 0 0.39.686.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 39585801 0.39.703.113 I slot launch_slot_: id 0 | task 2733 | processing task, is_child = 0 0.40.328.925 I slot print_timing: id 0 | task 2733 | prompt eval time = 83.89 ms / 325 tokens ( 0.26 ms per token, 3874.21 tokens per second) 0.40.328.932 I slot print_timing: id 0 | task 2733 | eval time = 541.91 ms / 49 tokens ( 11.29 ms per token, 88.58 tokens per second) 0.40.328.933 I slot print_timing: id 0 | task 2733 | total time = 625.80 ms / 374 tokens 0.40.328.934 I slot print_timing: id 0 | task 2733 | graphs reused = 2642 0.40.328.934 I slot print_timing: id 0 | task 2733 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.328.961 I slot release: id 0 | task 2733 | stop processing: n_tokens = 402, truncated = 0 0.40.332.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 40242886 0.40.346.638 I slot launch_slot_: id 0 | task 2783 | processing task, is_child = 0 0.41.014.388 I slot print_timing: id 0 | task 2783 | prompt eval time = 90.24 ms / 345 tokens ( 0.26 ms per token, 3823.27 tokens per second) 0.41.014.394 I slot print_timing: id 0 | task 2783 | eval time = 577.50 ms / 53 tokens ( 11.11 ms per token, 90.04 tokens per second) 0.41.014.395 I slot print_timing: id 0 | task 2783 | total time = 667.74 ms / 398 tokens 0.41.014.396 I slot print_timing: id 0 | task 2783 | graphs reused = 2693 0.41.014.397 I slot print_timing: id 0 | task 2783 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.014.425 I slot release: id 0 | task 2783 | stop processing: n_tokens = 422, truncated = 0 0.41.042.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 40928350 0.41.056.970 I slot launch_slot_: id 0 | task 2837 | processing task, is_child = 0 0.41.691.201 I slot print_timing: id 0 | task 2837 | prompt eval time = 90.20 ms / 344 tokens ( 0.26 ms per token, 3813.66 tokens per second) 0.41.691.207 I slot print_timing: id 0 | task 2837 | eval time = 544.01 ms / 50 tokens ( 11.10 ms per token, 90.07 tokens per second) 0.41.691.208 I slot print_timing: id 0 | task 2837 | total time = 634.22 ms / 394 tokens 0.41.691.209 I slot print_timing: id 0 | task 2837 | graphs reused = 2741 0.41.691.210 I slot print_timing: id 0 | task 2837 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.691.238 I slot release: id 0 | task 2837 | stop processing: n_tokens = 418, truncated = 0 0.41.695.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 41605163 0.41.709.623 I slot launch_slot_: id 0 | task 2888 | processing task, is_child = 0 0.42.625.824 I slot print_timing: id 0 | task 2888 | prompt eval time = 90.67 ms / 378 tokens ( 0.24 ms per token, 4169.19 tokens per second) 0.42.625.829 I slot print_timing: id 0 | task 2888 | eval time = 825.52 ms / 74 tokens ( 11.31 ms per token, 88.43 tokens per second) 0.42.625.831 I slot print_timing: id 0 | task 2888 | total time = 916.18 ms / 452 tokens 0.42.625.832 I slot print_timing: id 0 | task 2888 | graphs reused = 2813 0.42.625.833 I slot print_timing: id 0 | task 2888 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.625.865 I slot release: id 0 | task 2888 | stop processing: n_tokens = 476, truncated = 0 0.42.650.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 42539790 0.42.666.817 I slot launch_slot_: id 0 | task 2963 | processing task, is_child = 0 0.43.419.407 I slot print_timing: id 0 | task 2963 | prompt eval time = 84.32 ms / 331 tokens ( 0.25 ms per token, 3925.66 tokens per second) 0.43.419.413 I slot print_timing: id 0 | task 2963 | eval time = 668.25 ms / 61 tokens ( 11.14 ms per token, 89.79 tokens per second) 0.43.419.414 I slot print_timing: id 0 | task 2963 | total time = 752.57 ms / 392 tokens 0.43.419.414 I slot print_timing: id 0 | task 2963 | graphs reused = 2872 0.43.419.415 I slot print_timing: id 0 | task 2963 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.419.442 I slot release: id 0 | task 2963 | stop processing: n_tokens = 416, truncated = 0 0.43.443.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 43333367 0.43.457.541 I slot launch_slot_: id 0 | task 3025 | processing task, is_child = 0 0.44.103.618 I slot print_timing: id 0 | task 3025 | prompt eval time = 111.72 ms / 387 tokens ( 0.29 ms per token, 3464.08 tokens per second) 0.44.103.623 I slot print_timing: id 0 | task 3025 | eval time = 534.34 ms / 49 tokens ( 11.13 ms per token, 89.83 tokens per second) 0.44.103.624 I slot print_timing: id 0 | task 3025 | total time = 646.06 ms / 436 tokens 0.44.103.625 I slot print_timing: id 0 | task 3025 | graphs reused = 2919 0.44.103.626 I slot print_timing: id 0 | task 3025 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.103.657 I slot release: id 0 | task 3025 | stop processing: n_tokens = 460, truncated = 0 0.44.129.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 44017582 0.44.145.413 I slot launch_slot_: id 0 | task 3075 | processing task, is_child = 0 0.45.056.562 I slot print_timing: id 0 | task 3075 | prompt eval time = 90.19 ms / 345 tokens ( 0.26 ms per token, 3825.34 tokens per second) 0.45.056.568 I slot print_timing: id 0 | task 3075 | eval time = 820.95 ms / 75 tokens ( 11.09 ms per token, 90.14 tokens per second) 0.45.056.569 I slot print_timing: id 0 | task 3075 | total time = 911.13 ms / 420 tokens 0.45.056.570 I slot print_timing: id 0 | task 3075 | graphs reused = 2992 0.45.056.570 I slot print_timing: id 0 | task 3075 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.056.598 I slot release: id 0 | task 3075 | stop processing: n_tokens = 444, truncated = 0 0.45.080.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 44970522 0.45.095.695 I slot launch_slot_: id 0 | task 3151 | processing task, is_child = 0 0.45.869.030 I slot print_timing: id 0 | task 3151 | prompt eval time = 90.35 ms / 337 tokens ( 0.27 ms per token, 3729.82 tokens per second) 0.45.869.036 I slot print_timing: id 0 | task 3151 | eval time = 682.97 ms / 61 tokens ( 11.38 ms per token, 87.85 tokens per second) 0.45.869.037 I slot print_timing: id 0 | task 3151 | total time = 773.32 ms / 398 tokens 0.45.869.037 I slot print_timing: id 0 | task 3151 | graphs reused = 3051 0.45.869.038 I slot print_timing: id 0 | task 3151 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.869.068 I slot release: id 0 | task 3151 | stop processing: n_tokens = 422, truncated = 0 0.45.873.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 45782993 0.45.887.719 I slot launch_slot_: id 0 | task 3213 | processing task, is_child = 0 0.47.063.308 I slot print_timing: id 0 | task 3213 | prompt eval time = 121.91 ms / 463 tokens ( 0.26 ms per token, 3797.82 tokens per second) 0.47.063.314 I slot print_timing: id 0 | task 3213 | eval time = 1053.66 ms / 95 tokens ( 11.21 ms per token, 89.21 tokens per second) 0.47.063.315 I slot print_timing: id 0 | task 3213 | total time = 1175.57 ms / 558 tokens 0.47.063.316 I slot print_timing: id 0 | task 3213 | graphs reused = 3143 0.47.063.317 I slot print_timing: id 0 | task 3213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.063.349 I slot release: id 0 | task 3213 | stop processing: n_tokens = 582, truncated = 0 0.47.092.196 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 46977273 0.47.111.344 I slot launch_slot_: id 0 | task 3309 | processing task, is_child = 0 0.48.431.618 I slot print_timing: id 0 | task 3309 | prompt eval time = 113.53 ms / 440 tokens ( 0.26 ms per token, 3875.49 tokens per second) 0.48.431.624 I slot print_timing: id 0 | task 3309 | eval time = 1206.72 ms / 109 tokens ( 11.17 ms per token, 89.50 tokens per second) 0.48.431.625 I slot print_timing: id 0 | task 3309 | total time = 1320.26 ms / 549 tokens 0.48.431.626 I slot print_timing: id 0 | task 3309 | graphs reused = 3249 0.48.431.627 I slot print_timing: id 0 | task 3309 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.431.658 I slot release: id 0 | task 3309 | stop processing: n_tokens = 573, truncated = 0 0.48.454.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 48345583 0.48.472.689 I slot launch_slot_: id 0 | task 3419 | processing task, is_child = 0 0.49.256.843 I slot print_timing: id 0 | task 3419 | prompt eval time = 84.19 ms / 336 tokens ( 0.25 ms per token, 3990.93 tokens per second) 0.49.256.848 I slot print_timing: id 0 | task 3419 | eval time = 699.95 ms / 64 tokens ( 11.11 ms per token, 90.01 tokens per second) 0.49.256.849 I slot print_timing: id 0 | task 3419 | total time = 784.14 ms / 400 tokens 0.49.256.850 I slot print_timing: id 0 | task 3419 | graphs reused = 3311 0.49.256.851 I slot print_timing: id 0 | task 3419 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.256.879 I slot release: id 0 | task 3419 | stop processing: n_tokens = 424, truncated = 0 0.49.283.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 49170804 0.49.297.900 I slot launch_slot_: id 0 | task 3484 | processing task, is_child = 0 0.50.019.391 I slot print_timing: id 0 | task 3484 | prompt eval time = 91.14 ms / 367 tokens ( 0.25 ms per token, 4026.82 tokens per second) 0.50.019.396 I slot print_timing: id 0 | task 3484 | eval time = 630.34 ms / 57 tokens ( 11.26 ms per token, 88.84 tokens per second) 0.50.019.397 I slot print_timing: id 0 | task 3484 | total time = 721.48 ms / 424 tokens 0.50.019.399 I slot print_timing: id 0 | task 3484 | graphs reused = 3366 0.50.019.399 I slot print_timing: id 0 | task 3484 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.019.430 I slot release: id 0 | task 3484 | stop processing: n_tokens = 448, truncated = 0 0.50.036.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 49933355 0.50.051.252 I slot launch_slot_: id 0 | task 3542 | processing task, is_child = 0 0.50.703.297 I slot print_timing: id 0 | task 3542 | prompt eval time = 84.11 ms / 327 tokens ( 0.26 ms per token, 3887.90 tokens per second) 0.50.703.304 I slot print_timing: id 0 | task 3542 | eval time = 567.92 ms / 52 tokens ( 11.14 ms per token, 89.80 tokens per second) 0.50.703.306 I slot print_timing: id 0 | task 3542 | total time = 652.03 ms / 379 tokens 0.50.703.308 I slot print_timing: id 0 | task 3542 | graphs reused = 3416 0.50.703.308 I slot print_timing: id 0 | task 3542 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.703.334 I slot release: id 0 | task 3542 | stop processing: n_tokens = 403, truncated = 0 0.50.720.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 50617259 0.50.734.231 I slot launch_slot_: id 0 | task 3595 | processing task, is_child = 0 0.51.686.644 I slot print_timing: id 0 | task 3595 | prompt eval time = 111.72 ms / 393 tokens ( 0.28 ms per token, 3517.82 tokens per second) 0.51.686.650 I slot print_timing: id 0 | task 3595 | eval time = 840.68 ms / 76 tokens ( 11.21 ms per token, 89.21 tokens per second) 0.51.686.651 I slot print_timing: id 0 | task 3595 | total time = 952.40 ms / 469 tokens 0.51.686.651 I slot print_timing: id 0 | task 3595 | graphs reused = 3490 0.51.686.652 I slot print_timing: id 0 | task 3595 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.686.685 I slot release: id 0 | task 3595 | stop processing: n_tokens = 493, truncated = 0 0.51.702.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 51600610 0.51.718.983 I slot launch_slot_: id 0 | task 3672 | processing task, is_child = 0 0.52.544.802 I slot print_timing: id 0 | task 3672 | prompt eval time = 141.94 ms / 524 tokens ( 0.27 ms per token, 3691.70 tokens per second) 0.52.544.807 I slot print_timing: id 0 | task 3672 | eval time = 683.86 ms / 62 tokens ( 11.21 ms per token, 89.20 tokens per second) 0.52.544.808 I slot print_timing: id 0 | task 3672 | total time = 825.80 ms / 586 tokens 0.52.544.809 I slot print_timing: id 0 | task 3672 | graphs reused = 3550 0.52.544.810 I slot print_timing: id 0 | task 3672 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.544.842 I slot release: id 0 | task 3672 | stop processing: n_tokens = 610, truncated = 0 0.52.561.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 52458767 0.52.580.867 I slot launch_slot_: id 0 | task 3735 | processing task, is_child = 0 0.53.411.774 I slot print_timing: id 0 | task 3735 | prompt eval time = 158.21 ms / 602 tokens ( 0.26 ms per token, 3805.05 tokens per second) 0.53.411.780 I slot print_timing: id 0 | task 3735 | eval time = 672.68 ms / 61 tokens ( 11.21 ms per token, 89.20 tokens per second) 0.53.411.781 I slot print_timing: id 0 | task 3735 | total time = 830.89 ms / 663 tokens 0.53.411.782 I slot print_timing: id 0 | task 3735 | graphs reused = 3609 0.53.411.782 I slot print_timing: id 0 | task 3735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.411.820 I slot release: id 0 | task 3735 | stop processing: n_tokens = 687, truncated = 0 0.53.436.209 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 53325744 0.53.457.980 I slot launch_slot_: id 0 | task 3797 | processing task, is_child = 0 0.54.313.239 I slot print_timing: id 0 | task 3797 | prompt eval time = 160.35 ms / 640 tokens ( 0.25 ms per token, 3991.14 tokens per second) 0.54.313.245 I slot print_timing: id 0 | task 3797 | eval time = 694.89 ms / 63 tokens ( 11.21 ms per token, 89.22 tokens per second) 0.54.313.246 I slot print_timing: id 0 | task 3797 | total time = 855.24 ms / 703 tokens 0.54.313.246 I slot print_timing: id 0 | task 3797 | graphs reused = 3670 0.54.313.247 I slot print_timing: id 0 | task 3797 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.313.284 I slot release: id 0 | task 3797 | stop processing: n_tokens = 727, truncated = 0 0.54.335.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 54227209 0.54.358.607 I slot launch_slot_: id 0 | task 3861 | processing task, is_child = 0 0.55.202.355 I slot print_timing: id 0 | task 3861 | prompt eval time = 159.64 ms / 629 tokens ( 0.25 ms per token, 3940.07 tokens per second) 0.55.202.361 I slot print_timing: id 0 | task 3861 | eval time = 684.09 ms / 62 tokens ( 11.21 ms per token, 89.17 tokens per second) 0.55.202.362 I slot print_timing: id 0 | task 3861 | total time = 843.73 ms / 691 tokens 0.55.202.362 I slot print_timing: id 0 | task 3861 | graphs reused = 3730 0.55.202.363 I slot print_timing: id 0 | task 3861 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.202.400 I slot release: id 0 | task 3861 | stop processing: n_tokens = 715, truncated = 0 0.55.228.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 55116325 0.55.251.857 I slot launch_slot_: id 0 | task 3924 | processing task, is_child = 0 0.56.002.254 I slot print_timing: id 0 | task 3924 | prompt eval time = 121.51 ms / 458 tokens ( 0.27 ms per token, 3769.36 tokens per second) 0.56.002.259 I slot print_timing: id 0 | task 3924 | eval time = 628.87 ms / 57 tokens ( 11.23 ms per token, 89.05 tokens per second) 0.56.002.260 I slot print_timing: id 0 | task 3924 | total time = 750.38 ms / 515 tokens 0.56.002.261 I slot print_timing: id 0 | task 3924 | graphs reused = 3784 0.56.002.262 I slot print_timing: id 0 | task 3924 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.002.296 I slot release: id 0 | task 3924 | stop processing: n_tokens = 539, truncated = 0 0.56.023.522 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 55916221 0.56.041.362 I slot launch_slot_: id 0 | task 3982 | processing task, is_child = 0 0.56.889.206 I slot print_timing: id 0 | task 3982 | prompt eval time = 153.15 ms / 594 tokens ( 0.26 ms per token, 3878.45 tokens per second) 0.56.889.212 I slot print_timing: id 0 | task 3982 | eval time = 694.68 ms / 63 tokens ( 11.20 ms per token, 89.25 tokens per second) 0.56.889.213 I slot print_timing: id 0 | task 3982 | total time = 847.83 ms / 657 tokens 0.56.889.214 I slot print_timing: id 0 | task 3982 | graphs reused = 3845 0.56.889.215 I slot print_timing: id 0 | task 3982 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.889.251 I slot release: id 0 | task 3982 | stop processing: n_tokens = 681, truncated = 0 0.56.894.327 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 56803176 0.56.916.027 I slot launch_slot_: id 0 | task 4046 | processing task, is_child = 0 0.57.624.320 I slot print_timing: id 0 | task 4046 | prompt eval time = 147.60 ms / 572 tokens ( 0.26 ms per token, 3875.34 tokens per second) 0.57.624.326 I slot print_timing: id 0 | task 4046 | eval time = 560.68 ms / 51 tokens ( 11.21 ms per token, 89.18 tokens per second) 0.57.624.327 I slot print_timing: id 0 | task 4046 | total time = 708.28 ms / 623 tokens 0.57.624.328 I slot print_timing: id 0 | task 4046 | graphs reused = 3894 0.57.624.329 I slot print_timing: id 0 | task 4046 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.624.364 I slot release: id 0 | task 4046 | stop processing: n_tokens = 647, truncated = 0 0.57.648.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 57538289 0.57.670.211 I slot launch_slot_: id 0 | task 4098 | processing task, is_child = 0 0.58.356.697 I slot print_timing: id 0 | task 4098 | prompt eval time = 124.27 ms / 502 tokens ( 0.25 ms per token, 4039.69 tokens per second) 0.58.356.703 I slot print_timing: id 0 | task 4098 | eval time = 562.20 ms / 50 tokens ( 11.47 ms per token, 87.16 tokens per second) 0.58.356.704 I slot print_timing: id 0 | task 4098 | total time = 686.47 ms / 552 tokens 0.58.356.705 I slot print_timing: id 0 | task 4098 | graphs reused = 3942 0.58.356.705 I slot print_timing: id 0 | task 4098 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.356.739 I slot release: id 0 | task 4098 | stop processing: n_tokens = 576, truncated = 0 0.58.380.143 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 58270664 0.58.398.882 I slot launch_slot_: id 0 | task 4149 | processing task, is_child = 0 0.59.151.910 I slot print_timing: id 0 | task 4149 | prompt eval time = 121.81 ms / 479 tokens ( 0.25 ms per token, 3932.22 tokens per second) 0.59.151.916 I slot print_timing: id 0 | task 4149 | eval time = 631.20 ms / 57 tokens ( 11.27 ms per token, 88.72 tokens per second) 0.59.151.917 I slot print_timing: id 0 | task 4149 | total time = 753.01 ms / 536 tokens 0.59.151.918 I slot print_timing: id 0 | task 4149 | graphs reused = 3996 0.59.151.919 I slot print_timing: id 0 | task 4149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.151.951 I slot release: id 0 | task 4149 | stop processing: n_tokens = 560, truncated = 0 0.59.181.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 59065876 0.59.201.575 I slot launch_slot_: id 0 | task 4207 | processing task, is_child = 0 0.59.838.974 I slot print_timing: id 0 | task 4207 | prompt eval time = 143.32 ms / 552 tokens ( 0.26 ms per token, 3851.63 tokens per second) 0.59.838.980 I slot print_timing: id 0 | task 4207 | eval time = 494.06 ms / 45 tokens ( 11.23 ms per token, 89.06 tokens per second) 0.59.838.981 I slot print_timing: id 0 | task 4207 | total time = 637.38 ms / 597 tokens 0.59.838.982 I slot print_timing: id 0 | task 4207 | graphs reused = 4039 0.59.838.983 I slot print_timing: id 0 | task 4207 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.839.020 I slot release: id 0 | task 4207 | stop processing: n_tokens = 621, truncated = 0 0.59.867.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 59752945 0.59.888.053 I slot launch_slot_: id 0 | task 4253 | processing task, is_child = 0 1.01.271.961 I slot print_timing: id 0 | task 4253 | prompt eval time = 134.80 ms / 514 tokens ( 0.26 ms per token, 3813.03 tokens per second) 1.01.271.967 I slot print_timing: id 0 | task 4253 | eval time = 1249.09 ms / 113 tokens ( 11.15 ms per token, 89.67 tokens per second) 1.01.271.968 I slot print_timing: id 0 | task 4253 | total time = 1383.89 ms / 627 tokens 1.01.271.969 I slot print_timing: id 0 | task 4253 | graphs reused = 4150 1.01.271.970 I slot print_timing: id 0 | task 4253 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.272.003 I slot release: id 0 | task 4253 | stop processing: n_tokens = 651, truncated = 0 1.01.276.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 651, t_last = 61185927 1.01.298.589 I slot launch_slot_: id 0 | task 4367 | processing task, is_child = 0 1.01.867.556 I slot print_timing: id 0 | task 4367 | prompt eval time = 112.69 ms / 428 tokens ( 0.26 ms per token, 3797.90 tokens per second) 1.01.867.562 I slot print_timing: id 0 | task 4367 | eval time = 456.26 ms / 42 tokens ( 11.13 ms per token, 89.86 tokens per second) 1.01.867.563 I slot print_timing: id 0 | task 4367 | total time = 568.95 ms / 470 tokens 1.01.867.564 I slot print_timing: id 0 | task 4367 | graphs reused = 4190 1.01.867.565 I slot print_timing: id 0 | task 4367 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.867.598 I slot release: id 0 | task 4367 | stop processing: n_tokens = 494, truncated = 0 1.01.884.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 61781522 1.01.901.071 I slot launch_slot_: id 0 | task 4410 | processing task, is_child = 0 1.02.778.043 I slot print_timing: id 0 | task 4410 | prompt eval time = 138.59 ms / 521 tokens ( 0.27 ms per token, 3759.40 tokens per second) 1.02.778.049 I slot print_timing: id 0 | task 4410 | eval time = 738.37 ms / 66 tokens ( 11.36 ms per token, 88.03 tokens per second) 1.02.778.050 I slot print_timing: id 0 | task 4410 | total time = 876.96 ms / 587 tokens 1.02.778.051 I slot print_timing: id 0 | task 4410 | graphs reused = 4254 1.02.778.051 I slot print_timing: id 0 | task 4410 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.778.086 I slot release: id 0 | task 4410 | stop processing: n_tokens = 611, truncated = 0 1.02.807.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 62692011 1.02.827.525 I slot launch_slot_: id 0 | task 4477 | processing task, is_child = 0 1.03.512.319 I slot print_timing: id 0 | task 4477 | prompt eval time = 121.58 ms / 472 tokens ( 0.26 ms per token, 3882.09 tokens per second) 1.03.512.325 I slot print_timing: id 0 | task 4477 | eval time = 563.19 ms / 51 tokens ( 11.26 ms per token, 88.78 tokens per second) 1.03.512.326 I slot print_timing: id 0 | task 4477 | total time = 684.77 ms / 523 tokens 1.03.512.327 I slot print_timing: id 0 | task 4477 | graphs reused = 4302 1.03.512.327 I slot print_timing: id 0 | task 4477 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.512.360 I slot release: id 0 | task 4477 | stop processing: n_tokens = 547, truncated = 0 1.03.537.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 63426284 1.03.556.365 I slot launch_slot_: id 0 | task 4529 | processing task, is_child = 0 1.04.148.148 I slot print_timing: id 0 | task 4529 | prompt eval time = 112.77 ms / 428 tokens ( 0.26 ms per token, 3795.47 tokens per second) 1.04.148.154 I slot print_timing: id 0 | task 4529 | eval time = 479.00 ms / 44 tokens ( 11.14 ms per token, 89.77 tokens per second) 1.04.148.156 I slot print_timing: id 0 | task 4529 | total time = 591.76 ms / 472 tokens 1.04.148.157 I slot print_timing: id 0 | task 4529 | graphs reused = 4344 1.04.148.158 I slot print_timing: id 0 | task 4529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.148.195 I slot release: id 0 | task 4529 | stop processing: n_tokens = 496, truncated = 0 1.04.166.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 64062120 1.04.183.328 I slot launch_slot_: id 0 | task 4574 | processing task, is_child = 0 1.04.802.166 I slot print_timing: id 0 | task 4574 | prompt eval time = 121.51 ms / 456 tokens ( 0.27 ms per token, 3752.87 tokens per second) 1.04.802.172 I slot print_timing: id 0 | task 4574 | eval time = 497.31 ms / 45 tokens ( 11.30 ms per token, 88.48 tokens per second) 1.04.802.173 I slot print_timing: id 0 | task 4574 | total time = 618.82 ms / 501 tokens 1.04.802.174 I slot print_timing: id 0 | task 4574 | graphs reused = 4386 1.04.802.174 I slot print_timing: id 0 | task 4574 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.802.211 I slot release: id 0 | task 4574 | stop processing: n_tokens = 525, truncated = 0 1.04.807.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 64716136 1.04.825.139 I slot launch_slot_: id 0 | task 4620 | processing task, is_child = 0 1.05.420.793 I slot print_timing: id 0 | task 4620 | prompt eval time = 113.69 ms / 439 tokens ( 0.26 ms per token, 3861.24 tokens per second) 1.05.420.798 I slot print_timing: id 0 | task 4620 | eval time = 481.94 ms / 44 tokens ( 11.21 ms per token, 89.22 tokens per second) 1.05.420.799 I slot print_timing: id 0 | task 4620 | total time = 595.63 ms / 483 tokens 1.05.420.800 I slot print_timing: id 0 | task 4620 | graphs reused = 4428 1.05.420.801 I slot print_timing: id 0 | task 4620 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.420.834 I slot release: id 0 | task 4620 | stop processing: n_tokens = 507, truncated = 0 1.05.444.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 65334759 1.05.461.479 I slot launch_slot_: id 0 | task 4665 | processing task, is_child = 0 1.06.278.072 I slot print_timing: id 0 | task 4665 | prompt eval time = 153.71 ms / 600 tokens ( 0.26 ms per token, 3903.51 tokens per second) 1.06.278.078 I slot print_timing: id 0 | task 4665 | eval time = 662.87 ms / 60 tokens ( 11.24 ms per token, 89.01 tokens per second) 1.06.278.079 I slot print_timing: id 0 | task 4665 | total time = 816.57 ms / 660 tokens 1.06.278.080 I slot print_timing: id 0 | task 4665 | graphs reused = 4486 1.06.278.081 I slot print_timing: id 0 | task 4665 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.278.118 I slot release: id 0 | task 4665 | stop processing: n_tokens = 684, truncated = 0 1.06.301.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 66192043 1.06.323.839 I slot launch_slot_: id 0 | task 4726 | processing task, is_child = 0 1.06.909.064 I slot print_timing: id 0 | task 4726 | prompt eval time = 121.49 ms / 473 tokens ( 0.26 ms per token, 3893.45 tokens per second) 1.06.909.070 I slot print_timing: id 0 | task 4726 | eval time = 463.72 ms / 42 tokens ( 11.31 ms per token, 88.42 tokens per second) 1.06.909.071 I slot print_timing: id 0 | task 4726 | total time = 585.21 ms / 515 tokens 1.06.909.072 I slot print_timing: id 0 | task 4726 | graphs reused = 4525 1.06.909.073 I slot print_timing: id 0 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.909.109 I slot release: id 0 | task 4726 | stop processing: n_tokens = 539, truncated = 0 1.06.926.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 66823033 1.06.943.966 I slot launch_slot_: id 0 | task 4769 | processing task, is_child = 0 1.07.868.837 I slot print_timing: id 0 | task 4769 | prompt eval time = 206.51 ms / 835 tokens ( 0.25 ms per token, 4043.29 tokens per second) 1.07.868.843 I slot print_timing: id 0 | task 4769 | eval time = 718.34 ms / 65 tokens ( 11.22 ms per token, 89.09 tokens per second) 1.07.868.844 I slot print_timing: id 0 | task 4769 | total time = 924.86 ms / 900 tokens 1.07.868.844 I slot print_timing: id 0 | task 4769 | graphs reused = 4588 1.07.868.845 I slot print_timing: id 0 | task 4769 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.868.890 I slot release: id 0 | task 4769 | stop processing: n_tokens = 924, truncated = 0 1.07.894.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 67782815 1.07.922.682 I slot launch_slot_: id 0 | task 4835 | processing task, is_child = 0 1.08.516.796 I slot print_timing: id 0 | task 4835 | prompt eval time = 121.50 ms / 454 tokens ( 0.27 ms per token, 3736.75 tokens per second) 1.08.516.802 I slot print_timing: id 0 | task 4835 | eval time = 472.60 ms / 43 tokens ( 11.25 ms per token, 88.87 tokens per second) 1.08.516.803 I slot print_timing: id 0 | task 4835 | total time = 594.10 ms / 497 tokens 1.08.516.805 I slot print_timing: id 0 | task 4835 | graphs reused = 4628 1.08.516.806 I slot print_timing: id 0 | task 4835 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.516.841 I slot release: id 0 | task 4835 | stop processing: n_tokens = 521, truncated = 0 1.08.541.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 68430766 1.08.558.343 I slot launch_slot_: id 0 | task 4879 | processing task, is_child = 0 1.09.255.804 I slot print_timing: id 0 | task 4879 | prompt eval time = 169.67 ms / 667 tokens ( 0.25 ms per token, 3931.21 tokens per second) 1.09.255.811 I slot print_timing: id 0 | task 4879 | eval time = 527.78 ms / 48 tokens ( 11.23 ms per token, 89.05 tokens per second) 1.09.255.812 I slot print_timing: id 0 | task 4879 | total time = 697.45 ms / 715 tokens 1.09.255.813 I slot print_timing: id 0 | task 4879 | graphs reused = 4674 1.09.255.813 I slot print_timing: id 0 | task 4879 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.255.857 I slot release: id 0 | task 4879 | stop processing: n_tokens = 741, truncated = 0 1.09.274.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 69169781 1.09.311.886 I slot launch_slot_: id 0 | task 4928 | processing task, is_child = 0 1.10.265.257 I slot print_timing: id 0 | task 4928 | prompt eval time = 160.08 ms / 628 tokens ( 0.25 ms per token, 3923.06 tokens per second) 1.10.265.264 I slot print_timing: id 0 | task 4928 | eval time = 793.27 ms / 69 tokens ( 11.67 ms per token, 85.72 tokens per second) 1.10.265.265 I slot print_timing: id 0 | task 4928 | total time = 953.35 ms / 697 tokens 1.10.265.265 I slot print_timing: id 0 | task 4928 | graphs reused = 4741 1.10.265.266 I slot print_timing: id 0 | task 4928 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.265.309 I slot release: id 0 | task 4928 | stop processing: n_tokens = 858, truncated = 0 1.10.290.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 70179234 1.10.317.086 I slot launch_slot_: id 0 | task 4998 | processing task, is_child = 0 1.11.306.253 I slot print_timing: id 0 | task 4998 | prompt eval time = 150.04 ms / 578 tokens ( 0.26 ms per token, 3852.36 tokens per second) 1.11.306.259 I slot print_timing: id 0 | task 4998 | eval time = 839.11 ms / 76 tokens ( 11.19 ms per token, 89.38 tokens per second) 1.11.306.260 I slot print_timing: id 0 | task 4998 | total time = 989.15 ms / 654 tokens 1.11.306.260 I slot print_timing: id 0 | task 4998 | graphs reused = 4815 1.11.306.261 I slot print_timing: id 0 | task 4998 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.306.299 I slot release: id 0 | task 4998 | stop processing: n_tokens = 678, truncated = 0 1.11.326.470 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 71220224 1.11.348.590 I slot launch_slot_: id 0 | task 5075 | processing task, is_child = 0 1.12.199.780 I slot print_timing: id 0 | task 5075 | prompt eval time = 121.92 ms / 461 tokens ( 0.26 ms per token, 3781.17 tokens per second) 1.12.199.785 I slot print_timing: id 0 | task 5075 | eval time = 729.25 ms / 66 tokens ( 11.22 ms per token, 89.13 tokens per second) 1.12.199.787 I slot print_timing: id 0 | task 5075 | total time = 851.17 ms / 527 tokens 1.12.199.787 I slot print_timing: id 0 | task 5075 | graphs reused = 4878 1.12.199.788 I slot print_timing: id 0 | task 5075 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.199.821 I slot release: id 0 | task 5075 | stop processing: n_tokens = 551, truncated = 0 1.12.218.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 72113746 1.12.236.395 I slot launch_slot_: id 0 | task 5142 | processing task, is_child = 0 1.12.928.970 I slot print_timing: id 0 | task 5142 | prompt eval time = 156.92 ms / 613 tokens ( 0.26 ms per token, 3906.52 tokens per second) 1.12.928.977 I slot print_timing: id 0 | task 5142 | eval time = 535.64 ms / 48 tokens ( 11.40 ms per token, 87.75 tokens per second) 1.12.928.979 I slot print_timing: id 0 | task 5142 | total time = 692.56 ms / 661 tokens 1.12.928.980 I slot print_timing: id 0 | task 5142 | graphs reused = 4924 1.12.928.981 I slot print_timing: id 0 | task 5142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.929.027 I slot release: id 0 | task 5142 | stop processing: n_tokens = 685, truncated = 0 1.12.956.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 72842951 1.12.978.173 I slot launch_slot_: id 0 | task 5191 | processing task, is_child = 0 1.13.895.084 I slot print_timing: id 0 | task 5191 | prompt eval time = 197.35 ms / 794 tokens ( 0.25 ms per token, 4023.29 tokens per second) 1.13.895.090 I slot print_timing: id 0 | task 5191 | eval time = 719.54 ms / 65 tokens ( 11.24 ms per token, 88.95 tokens per second) 1.13.895.091 I slot print_timing: id 0 | task 5191 | total time = 916.89 ms / 859 tokens 1.13.895.092 I slot print_timing: id 0 | task 5191 | graphs reused = 4987 1.13.895.093 I slot print_timing: id 0 | task 5191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.895.138 I slot release: id 0 | task 5191 | stop processing: n_tokens = 883, truncated = 0 1.13.920.889 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 73809062 1.13.966.596 I slot launch_slot_: id 0 | task 5257 | processing task, is_child = 0 1.14.719.527 I slot print_timing: id 0 | task 5257 | prompt eval time = 114.03 ms / 431 tokens ( 0.26 ms per token, 3779.84 tokens per second) 1.14.719.533 I slot print_timing: id 0 | task 5257 | eval time = 638.88 ms / 58 tokens ( 11.21 ms per token, 89.22 tokens per second) 1.14.719.534 I slot print_timing: id 0 | task 5257 | total time = 752.91 ms / 489 tokens 1.14.719.535 I slot print_timing: id 0 | task 5257 | graphs reused = 5043 1.14.719.536 I slot print_timing: id 0 | task 5257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.719.573 I slot release: id 0 | task 5257 | stop processing: n_tokens = 687, truncated = 0 1.14.725.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 74633498 1.14.747.426 I slot launch_slot_: id 0 | task 5316 | processing task, is_child = 0 1.15.453.168 I slot print_timing: id 0 | task 5316 | prompt eval time = 146.37 ms / 563 tokens ( 0.26 ms per token, 3846.42 tokens per second) 1.15.453.174 I slot print_timing: id 0 | task 5316 | eval time = 559.36 ms / 50 tokens ( 11.42 ms per token, 87.60 tokens per second) 1.15.453.175 I slot print_timing: id 0 | task 5316 | total time = 705.73 ms / 613 tokens 1.15.453.176 I slot print_timing: id 0 | task 5316 | graphs reused = 5091 1.15.453.177 I slot print_timing: id 0 | task 5316 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.453.213 I slot release: id 0 | task 5316 | stop processing: n_tokens = 637, truncated = 0 1.15.478.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 75367138 1.15.510.830 I slot launch_slot_: id 0 | task 5367 | processing task, is_child = 0 1.16.119.413 I slot print_timing: id 0 | task 5367 | prompt eval time = 83.99 ms / 331 tokens ( 0.25 ms per token, 3941.04 tokens per second) 1.16.119.419 I slot print_timing: id 0 | task 5367 | eval time = 524.58 ms / 48 tokens ( 11.16 ms per token, 89.60 tokens per second) 1.16.119.420 I slot print_timing: id 0 | task 5367 | total time = 608.56 ms / 379 tokens 1.16.119.421 I slot print_timing: id 0 | task 5367 | graphs reused = 5136 1.16.119.421 I slot print_timing: id 0 | task 5367 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.119.452 I slot release: id 0 | task 5367 | stop processing: n_tokens = 513, truncated = 0 1.16.124.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 76033377 1.16.141.628 I slot launch_slot_: id 0 | task 5416 | processing task, is_child = 0 1.17.003.994 I slot print_timing: id 0 | task 5416 | prompt eval time = 123.92 ms / 489 tokens ( 0.25 ms per token, 3946.06 tokens per second) 1.17.003.999 I slot print_timing: id 0 | task 5416 | eval time = 738.43 ms / 67 tokens ( 11.19 ms per token, 89.38 tokens per second) 1.17.004.001 I slot print_timing: id 0 | task 5416 | total time = 862.35 ms / 556 tokens 1.17.004.002 I slot print_timing: id 0 | task 5416 | graphs reused = 5201 1.17.004.003 I slot print_timing: id 0 | task 5416 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.004.037 I slot release: id 0 | task 5416 | stop processing: n_tokens = 580, truncated = 0 1.17.024.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 76917962 1.17.043.754 I slot launch_slot_: id 0 | task 5484 | processing task, is_child = 0 1.17.761.484 I slot print_timing: id 0 | task 5484 | prompt eval time = 124.41 ms / 510 tokens ( 0.24 ms per token, 4099.48 tokens per second) 1.17.761.490 I slot print_timing: id 0 | task 5484 | eval time = 593.31 ms / 54 tokens ( 11.19 ms per token, 89.33 tokens per second) 1.17.761.491 I slot print_timing: id 0 | task 5484 | total time = 717.71 ms / 564 tokens 1.17.761.491 I slot print_timing: id 0 | task 5484 | graphs reused = 5253 1.17.761.492 I slot print_timing: id 0 | task 5484 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.761.528 I slot release: id 0 | task 5484 | stop processing: n_tokens = 588, truncated = 0 1.17.788.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 77675453 1.17.807.508 I slot launch_slot_: id 0 | task 5539 | processing task, is_child = 0 1.18.750.343 I slot print_timing: id 0 | task 5539 | prompt eval time = 159.66 ms / 631 tokens ( 0.25 ms per token, 3952.05 tokens per second) 1.18.750.348 I slot print_timing: id 0 | task 5539 | eval time = 783.16 ms / 71 tokens ( 11.19 ms per token, 89.38 tokens per second) 1.18.750.350 I slot print_timing: id 0 | task 5539 | total time = 942.82 ms / 702 tokens 1.18.750.350 I slot print_timing: id 0 | task 5539 | graphs reused = 5322 1.18.750.351 I slot print_timing: id 0 | task 5539 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.750.389 I slot release: id 0 | task 5539 | stop processing: n_tokens = 726, truncated = 0 1.18.756.173 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 78664314 1.18.779.147 I slot launch_slot_: id 0 | task 5611 | processing task, is_child = 0 1.19.521.062 I slot print_timing: id 0 | task 5611 | prompt eval time = 146.87 ms / 570 tokens ( 0.26 ms per token, 3881.04 tokens per second) 1.19.521.067 I slot print_timing: id 0 | task 5611 | eval time = 595.03 ms / 54 tokens ( 11.23 ms per token, 89.07 tokens per second) 1.19.521.068 I slot print_timing: id 0 | task 5611 | total time = 741.90 ms / 624 tokens 1.19.521.069 I slot print_timing: id 0 | task 5611 | graphs reused = 5374 1.19.521.070 I slot print_timing: id 0 | task 5611 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.521.104 I slot release: id 0 | task 5611 | stop processing: n_tokens = 648, truncated = 0 1.19.527.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 79435029 1.19.549.207 I slot launch_slot_: id 0 | task 5666 | processing task, is_child = 0 1.20.287.131 I slot print_timing: id 0 | task 5666 | prompt eval time = 197.50 ms / 792 tokens ( 0.25 ms per token, 4010.15 tokens per second) 1.20.287.137 I slot print_timing: id 0 | task 5666 | eval time = 540.41 ms / 49 tokens ( 11.26 ms per token, 88.82 tokens per second) 1.20.287.138 I slot print_timing: id 0 | task 5666 | total time = 737.91 ms / 841 tokens 1.20.287.139 I slot print_timing: id 0 | task 5666 | graphs reused = 5421 1.20.287.140 I slot print_timing: id 0 | task 5666 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.287.184 I slot release: id 0 | task 5666 | stop processing: n_tokens = 867, truncated = 0 1.20.314.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 80201108 1.20.341.469 I slot launch_slot_: id 0 | task 5716 | processing task, is_child = 0 1.20.981.448 I slot print_timing: id 0 | task 5716 | prompt eval time = 146.30 ms / 564 tokens ( 0.26 ms per token, 3855.14 tokens per second) 1.20.981.454 I slot print_timing: id 0 | task 5716 | eval time = 493.67 ms / 45 tokens ( 11.22 ms per token, 89.13 tokens per second) 1.20.981.455 I slot print_timing: id 0 | task 5716 | total time = 639.96 ms / 609 tokens 1.20.981.456 I slot print_timing: id 0 | task 5716 | graphs reused = 5464 1.20.981.457 I slot print_timing: id 0 | task 5716 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.981.498 I slot release: id 0 | task 5716 | stop processing: n_tokens = 635, truncated = 0 1.20.999.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 80895422 1.21.019.878 I slot launch_slot_: id 0 | task 5762 | processing task, is_child = 0 1.21.781.213 I slot print_timing: id 0 | task 5762 | prompt eval time = 156.97 ms / 617 tokens ( 0.25 ms per token, 3930.69 tokens per second) 1.21.781.219 I slot print_timing: id 0 | task 5762 | eval time = 604.35 ms / 55 tokens ( 11.19 ms per token, 89.35 tokens per second) 1.21.781.220 I slot print_timing: id 0 | task 5762 | total time = 761.32 ms / 672 tokens 1.21.781.221 I slot print_timing: id 0 | task 5762 | graphs reused = 5517 1.21.781.221 I slot print_timing: id 0 | task 5762 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.781.257 I slot release: id 0 | task 5762 | stop processing: n_tokens = 696, truncated = 0 1.21.786.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 81695182 1.21.808.921 I slot launch_slot_: id 0 | task 5818 | processing task, is_child = 0 1.22.693.447 I slot print_timing: id 0 | task 5818 | prompt eval time = 146.94 ms / 572 tokens ( 0.26 ms per token, 3892.61 tokens per second) 1.22.693.454 I slot print_timing: id 0 | task 5818 | eval time = 737.57 ms / 67 tokens ( 11.18 ms per token, 89.48 tokens per second) 1.22.693.455 I slot print_timing: id 0 | task 5818 | total time = 884.51 ms / 639 tokens 1.22.693.456 I slot print_timing: id 0 | task 5818 | graphs reused = 5582 1.22.693.457 I slot print_timing: id 0 | task 5818 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.693.492 I slot release: id 0 | task 5818 | stop processing: n_tokens = 663, truncated = 0 1.22.715.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 82607416 1.22.737.293 I slot launch_slot_: id 0 | task 5886 | processing task, is_child = 0 1.23.517.549 I slot print_timing: id 0 | task 5886 | prompt eval time = 181.21 ms / 712 tokens ( 0.25 ms per token, 3929.10 tokens per second) 1.23.517.554 I slot print_timing: id 0 | task 5886 | eval time = 599.03 ms / 54 tokens ( 11.30 ms per token, 88.48 tokens per second) 1.23.517.555 I slot print_timing: id 0 | task 5886 | total time = 780.24 ms / 766 tokens 1.23.517.556 I slot print_timing: id 0 | task 5886 | graphs reused = 5633 1.23.517.557 I slot print_timing: id 0 | task 5886 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.517.598 I slot release: id 0 | task 5886 | stop processing: n_tokens = 790, truncated = 0 1.23.547.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 83431523 1.23.572.027 I slot launch_slot_: id 0 | task 5941 | processing task, is_child = 0 1.24.966.527 I slot print_timing: id 0 | task 5941 | prompt eval time = 197.17 ms / 791 tokens ( 0.25 ms per token, 4011.73 tokens per second) 1.24.966.533 I slot print_timing: id 0 | task 5941 | eval time = 1197.31 ms / 106 tokens ( 11.40 ms per token, 87.70 tokens per second) 1.24.966.534 I slot print_timing: id 0 | task 5941 | total time = 1394.49 ms / 897 tokens 1.24.966.535 I slot print_timing: id 0 | task 5941 | graphs reused = 5737 1.24.966.536 I slot print_timing: id 0 | task 5941 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.966.578 I slot release: id 0 | task 5941 | stop processing: n_tokens = 921, truncated = 0 1.24.986.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 921, t_last = 84880503 1.25.014.872 I slot launch_slot_: id 0 | task 6048 | processing task, is_child = 0 1.26.914.308 I slot print_timing: id 0 | task 6048 | prompt eval time = 90.28 ms / 369 tokens ( 0.24 ms per token, 4087.06 tokens per second) 1.26.914.316 I slot print_timing: id 0 | task 6048 | eval time = 1809.13 ms / 164 tokens ( 11.10 ms per token, 90.10 tokens per second) 1.26.914.317 I slot print_timing: id 0 | task 6048 | total time = 1899.42 ms / 533 tokens 1.26.914.318 I slot print_timing: id 0 | task 6048 | graphs reused = 5898 1.26.914.319 I slot print_timing: id 0 | task 6048 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.914.351 I slot release: id 0 | task 6048 | stop processing: n_tokens = 557, truncated = 0 1.26.931.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 86828276 1.26.949.955 I slot launch_slot_: id 0 | task 6213 | processing task, is_child = 0 1.27.737.975 I slot print_timing: id 0 | task 6213 | prompt eval time = 111.38 ms / 388 tokens ( 0.29 ms per token, 3483.66 tokens per second) 1.27.737.980 I slot print_timing: id 0 | task 6213 | eval time = 676.63 ms / 62 tokens ( 11.09 ms per token, 90.15 tokens per second) 1.27.737.981 I slot print_timing: id 0 | task 6213 | total time = 788.00 ms / 450 tokens 1.27.737.982 I slot print_timing: id 0 | task 6213 | graphs reused = 5958 1.27.737.983 I slot print_timing: id 0 | task 6213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.738.013 I slot release: id 0 | task 6213 | stop processing: n_tokens = 474, truncated = 0 1.27.758.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 87651938 1.27.774.642 I slot launch_slot_: id 0 | task 6276 | processing task, is_child = 0 1.28.586.046 I slot print_timing: id 0 | task 6276 | prompt eval time = 90.34 ms / 370 tokens ( 0.24 ms per token, 4095.41 tokens per second) 1.28.586.051 I slot print_timing: id 0 | task 6276 | eval time = 721.04 ms / 66 tokens ( 11.09 ms per token, 90.15 tokens per second) 1.28.586.052 I slot print_timing: id 0 | task 6276 | total time = 811.39 ms / 436 tokens 1.28.586.053 I slot print_timing: id 0 | task 6276 | graphs reused = 6022 1.28.586.054 I slot print_timing: id 0 | task 6276 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.586.084 I slot release: id 0 | task 6276 | stop processing: n_tokens = 460, truncated = 0 1.28.590.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 88500009 1.28.590.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.28.609.196 I slot launch_slot_: id 0 | task 6343 | processing task, is_child = 0 1.29.354.075 I slot print_timing: id 0 | task 6343 | prompt eval time = 90.06 ms / 340 tokens ( 0.26 ms per token, 3775.34 tokens per second) 1.29.354.082 I slot print_timing: id 0 | task 6343 | eval time = 654.80 ms / 60 tokens ( 11.10 ms per token, 90.10 tokens per second) 1.29.354.083 I slot print_timing: id 0 | task 6343 | total time = 744.86 ms / 400 tokens 1.29.354.084 I slot print_timing: id 0 | task 6343 | graphs reused = 6080 1.29.354.085 I slot print_timing: id 0 | task 6343 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.354.116 I slot release: id 0 | task 6343 | stop processing: n_tokens = 424, truncated = 0 1.29.381.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 89268041 1.29.381.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.29.399.651 I slot launch_slot_: id 0 | task 6404 | processing task, is_child = 0 1.30.364.473 I slot print_timing: id 0 | task 6404 | prompt eval time = 111.98 ms / 409 tokens ( 0.27 ms per token, 3652.50 tokens per second) 1.30.364.478 I slot print_timing: id 0 | task 6404 | eval time = 852.83 ms / 78 tokens ( 11.08 ms per token, 90.29 tokens per second) 1.30.364.479 I slot print_timing: id 0 | task 6404 | total time = 964.81 ms / 487 tokens 1.30.364.481 I slot print_timing: id 0 | task 6404 | graphs reused = 6156 1.30.364.481 I slot print_timing: id 0 | task 6404 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.364.514 I slot release: id 0 | task 6404 | stop processing: n_tokens = 511, truncated = 0 1.30.380.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 90278439 1.30.380.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.30.384.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.30.405.589 I slot launch_slot_: id 0 | task 6483 | processing task, is_child = 0 1.31.554.695 I slot print_timing: id 0 | task 6483 | prompt eval time = 112.23 ms / 422 tokens ( 0.27 ms per token, 3760.10 tokens per second) 1.31.554.702 I slot print_timing: id 0 | task 6483 | eval time = 1036.86 ms / 94 tokens ( 11.15 ms per token, 89.69 tokens per second) 1.31.554.703 I slot print_timing: id 0 | task 6483 | total time = 1149.09 ms / 516 tokens 1.31.554.703 I slot print_timing: id 0 | task 6483 | graphs reused = 6247 1.31.554.706 I slot print_timing: id 0 | task 6483 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.554.737 I slot release: id 0 | task 6483 | stop processing: n_tokens = 540, truncated = 0 1.31.571.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 91468662 1.31.571.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.31.592.875 I slot launch_slot_: id 0 | task 6578 | processing task, is_child = 0 1.32.955.171 I slot print_timing: id 0 | task 6578 | prompt eval time = 124.24 ms / 499 tokens ( 0.25 ms per token, 4016.52 tokens per second) 1.32.955.176 I slot print_timing: id 0 | task 6578 | eval time = 1238.04 ms / 112 tokens ( 11.15 ms per token, 89.66 tokens per second) 1.32.955.177 I slot print_timing: id 0 | task 6578 | total time = 1362.28 ms / 611 tokens 1.32.955.178 I slot print_timing: id 0 | task 6578 | graphs reused = 6357 1.32.955.179 I slot print_timing: id 0 | task 6578 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.955.213 I slot release: id 0 | task 6578 | stop processing: n_tokens = 639, truncated = 0 1.32.975.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 92869137 1.32.975.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.33.000.947 I slot launch_slot_: id 0 | task 6691 | processing task, is_child = 0 1.33.568.959 I slot print_timing: id 0 | task 6691 | prompt eval time = 90.18 ms / 345 tokens ( 0.26 ms per token, 3825.51 tokens per second) 1.33.568.964 I slot print_timing: id 0 | task 6691 | eval time = 477.81 ms / 44 tokens ( 11.11 ms per token, 89.99 tokens per second) 1.33.568.965 I slot print_timing: id 0 | task 6691 | total time = 568.00 ms / 389 tokens 1.33.568.966 I slot print_timing: id 0 | task 6691 | graphs reused = 6399 1.33.568.967 I slot print_timing: id 0 | task 6691 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.568.997 I slot release: id 0 | task 6691 | stop processing: n_tokens = 413, truncated = 0 1.33.589.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 93482922 1.33.589.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.538 MiB) 1.33.607.965 I slot launch_slot_: id 0 | task 6736 | processing task, is_child = 0 1.34.177.031 I slot print_timing: id 0 | task 6736 | prompt eval time = 90.46 ms / 348 tokens ( 0.26 ms per token, 3847.17 tokens per second) 1.34.177.037 I slot print_timing: id 0 | task 6736 | eval time = 478.60 ms / 44 tokens ( 11.13 ms per token, 89.85 tokens per second) 1.34.177.038 I slot print_timing: id 0 | task 6736 | total time = 569.05 ms / 392 tokens 1.34.177.039 I slot print_timing: id 0 | task 6736 | graphs reused = 6441 1.34.177.040 I slot print_timing: id 0 | task 6736 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.177.070 I slot release: id 0 | task 6736 | stop processing: n_tokens = 416, truncated = 0 1.34.204.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 94090995 1.34.204.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.34.224.455 I slot launch_slot_: id 0 | task 6781 | processing task, is_child = 0 1.35.079.798 I slot print_timing: id 0 | task 6781 | prompt eval time = 112.22 ms / 408 tokens ( 0.28 ms per token, 3635.78 tokens per second) 1.35.079.804 I slot print_timing: id 0 | task 6781 | eval time = 743.11 ms / 68 tokens ( 11.09 ms per token, 90.16 tokens per second) 1.35.079.805 I slot print_timing: id 0 | task 6781 | total time = 855.33 ms / 476 tokens 1.35.079.806 I slot print_timing: id 0 | task 6781 | graphs reused = 6507 1.35.079.807 I slot print_timing: id 0 | task 6781 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.079.839 I slot release: id 0 | task 6781 | stop processing: n_tokens = 500, truncated = 0 1.35.097.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 94993764 1.35.098.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.35.118.453 I slot launch_slot_: id 0 | task 6850 | processing task, is_child = 0 1.35.936.591 I slot print_timing: id 0 | task 6850 | prompt eval time = 121.42 ms / 465 tokens ( 0.26 ms per token, 3829.68 tokens per second) 1.35.936.596 I slot print_timing: id 0 | task 6850 | eval time = 696.70 ms / 61 tokens ( 11.61 ms per token, 86.12 tokens per second) 1.35.936.597 I slot print_timing: id 0 | task 6850 | total time = 818.12 ms / 526 tokens 1.35.936.598 I slot print_timing: id 0 | task 6850 | graphs reused = 6565 1.35.936.599 I slot print_timing: id 0 | task 6850 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.936.631 I slot release: id 0 | task 6850 | stop processing: n_tokens = 550, truncated = 0 1.35.965.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 95850556 1.35.965.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.35.988.278 I slot launch_slot_: id 0 | task 6912 | processing task, is_child = 0 1.36.757.599 I slot print_timing: id 0 | task 6912 | prompt eval time = 111.66 ms / 399 tokens ( 0.28 ms per token, 3573.48 tokens per second) 1.36.757.605 I slot print_timing: id 0 | task 6912 | eval time = 657.65 ms / 60 tokens ( 11.15 ms per token, 89.71 tokens per second) 1.36.757.606 I slot print_timing: id 0 | task 6912 | total time = 769.30 ms / 459 tokens 1.36.757.607 I slot print_timing: id 0 | task 6912 | graphs reused = 6623 1.36.757.608 I slot print_timing: id 0 | task 6912 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.757.639 I slot release: id 0 | task 6912 | stop processing: n_tokens = 500, truncated = 0 1.36.777.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 96671564 1.36.777.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 1.36.798.889 I slot launch_slot_: id 0 | task 6973 | processing task, is_child = 0 1.37.714.542 I slot print_timing: id 0 | task 6973 | prompt eval time = 112.53 ms / 419 tokens ( 0.27 ms per token, 3723.52 tokens per second) 1.37.714.547 I slot print_timing: id 0 | task 6973 | eval time = 803.11 ms / 72 tokens ( 11.31 ms per token, 88.41 tokens per second) 1.37.714.548 I slot print_timing: id 0 | task 6973 | total time = 915.63 ms / 491 tokens 1.37.714.549 I slot print_timing: id 0 | task 6973 | graphs reused = 6692 1.37.714.550 I slot print_timing: id 0 | task 6973 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.714.582 I slot release: id 0 | task 6973 | stop processing: n_tokens = 515, truncated = 0 1.37.729.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 97628507 1.37.729.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 1.37.734.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 1.37.755.665 I slot launch_slot_: id 0 | task 7046 | processing task, is_child = 0 1.38.652.689 I slot print_timing: id 0 | task 7046 | prompt eval time = 113.92 ms / 440 tokens ( 0.26 ms per token, 3862.46 tokens per second) 1.38.652.694 I slot print_timing: id 0 | task 7046 | eval time = 783.09 ms / 71 tokens ( 11.19 ms per token, 89.39 tokens per second) 1.38.652.695 I slot print_timing: id 0 | task 7046 | total time = 897.01 ms / 511 tokens 1.38.652.697 I slot print_timing: id 0 | task 7046 | graphs reused = 6760 1.38.652.698 I slot print_timing: id 0 | task 7046 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.652.730 I slot release: id 0 | task 7046 | stop processing: n_tokens = 535, truncated = 0 1.38.680.995 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 98566655 1.38.681.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 1.38.702.760 I slot launch_slot_: id 0 | task 7118 | processing task, is_child = 0 1.39.359.876 I slot print_timing: id 0 | task 7118 | prompt eval time = 90.44 ms / 372 tokens ( 0.24 ms per token, 4113.36 tokens per second) 1.39.359.881 I slot print_timing: id 0 | task 7118 | eval time = 566.66 ms / 52 tokens ( 11.11 ms per token, 90.00 tokens per second) 1.39.359.882 I slot print_timing: id 0 | task 7118 | total time = 657.10 ms / 424 tokens 1.39.359.883 I slot print_timing: id 0 | task 7118 | graphs reused = 6810 1.39.359.884 I slot print_timing: id 0 | task 7118 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.359.915 I slot release: id 0 | task 7118 | stop processing: n_tokens = 448, truncated = 0 1.39.364.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 99273840 1.39.364.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.39.384.981 I slot launch_slot_: id 0 | task 7171 | processing task, is_child = 0 1.40.147.063 I slot print_timing: id 0 | task 7171 | prompt eval time = 122.00 ms / 449 tokens ( 0.27 ms per token, 3680.27 tokens per second) 1.40.147.068 I slot print_timing: id 0 | task 7171 | eval time = 640.06 ms / 58 tokens ( 11.23 ms per token, 89.05 tokens per second) 1.40.147.069 I slot print_timing: id 0 | task 7171 | total time = 762.06 ms / 507 tokens 1.40.147.070 I slot print_timing: id 0 | task 7171 | graphs reused = 6865 1.40.147.071 I slot print_timing: id 0 | task 7171 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.147.104 I slot release: id 0 | task 7171 | stop processing: n_tokens = 531, truncated = 0 1.40.161.968 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 100061029 1.40.162.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 1.40.183.640 I slot launch_slot_: id 0 | task 7230 | processing task, is_child = 0 1.40.952.017 I slot print_timing: id 0 | task 7230 | prompt eval time = 91.00 ms / 360 tokens ( 0.25 ms per token, 3956.26 tokens per second) 1.40.952.023 I slot print_timing: id 0 | task 7230 | eval time = 677.37 ms / 62 tokens ( 11.10 ms per token, 90.05 tokens per second) 1.40.952.024 I slot print_timing: id 0 | task 7230 | total time = 768.36 ms / 422 tokens 1.40.952.025 I slot print_timing: id 0 | task 7230 | graphs reused = 6925 1.40.952.026 I slot print_timing: id 0 | task 7230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.952.055 I slot release: id 0 | task 7230 | stop processing: n_tokens = 446, truncated = 0 1.40.972.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 100865980 1.40.972.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 1.40.991.783 I slot launch_slot_: id 0 | task 7293 | processing task, is_child = 0 1.41.682.474 I slot print_timing: id 0 | task 7293 | prompt eval time = 90.42 ms / 346 tokens ( 0.26 ms per token, 3826.50 tokens per second) 1.41.682.479 I slot print_timing: id 0 | task 7293 | eval time = 600.25 ms / 55 tokens ( 11.12 ms per token, 89.96 tokens per second) 1.41.682.481 I slot print_timing: id 0 | task 7293 | total time = 690.68 ms / 401 tokens 1.41.682.482 I slot print_timing: id 0 | task 7293 | graphs reused = 6978 1.41.682.482 I slot print_timing: id 0 | task 7293 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.682.511 I slot release: id 0 | task 7293 | stop processing: n_tokens = 425, truncated = 0 1.41.703.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 101596436 1.41.704.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.41.722.265 I slot launch_slot_: id 0 | task 7349 | processing task, is_child = 0 1.42.414.016 I slot print_timing: id 0 | task 7349 | prompt eval time = 118.97 ms / 434 tokens ( 0.27 ms per token, 3648.01 tokens per second) 1.42.414.022 I slot print_timing: id 0 | task 7349 | eval time = 572.76 ms / 52 tokens ( 11.23 ms per token, 89.04 tokens per second) 1.42.414.023 I slot print_timing: id 0 | task 7349 | total time = 691.73 ms / 486 tokens 1.42.414.025 I slot print_timing: id 0 | task 7349 | graphs reused = 7028 1.42.414.026 I slot print_timing: id 0 | task 7349 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.414.064 I slot release: id 0 | task 7349 | stop processing: n_tokens = 510, truncated = 0 1.42.441.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 102327988 1.42.441.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 1.42.445.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 1.42.466.393 I slot launch_slot_: id 0 | task 7402 | processing task, is_child = 0 1.43.218.221 I slot print_timing: id 0 | task 7402 | prompt eval time = 90.20 ms / 369 tokens ( 0.24 ms per token, 4090.77 tokens per second) 1.43.218.227 I slot print_timing: id 0 | task 7402 | eval time = 661.61 ms / 59 tokens ( 11.41 ms per token, 87.67 tokens per second) 1.43.218.228 I slot print_timing: id 0 | task 7402 | total time = 751.81 ms / 428 tokens 1.43.218.229 I slot print_timing: id 0 | task 7402 | graphs reused = 7085 1.43.218.230 I slot print_timing: id 0 | task 7402 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.218.258 I slot release: id 0 | task 7402 | stop processing: n_tokens = 452, truncated = 0 1.43.236.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 103132183 1.43.236.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 1.43.255.958 I slot launch_slot_: id 0 | task 7462 | processing task, is_child = 0 1.44.230.833 I slot print_timing: id 0 | task 7462 | prompt eval time = 113.88 ms / 446 tokens ( 0.26 ms per token, 3916.54 tokens per second) 1.44.230.839 I slot print_timing: id 0 | task 7462 | eval time = 860.98 ms / 78 tokens ( 11.18 ms per token, 89.43 tokens per second) 1.44.230.841 I slot print_timing: id 0 | task 7462 | total time = 974.86 ms / 524 tokens 1.44.230.841 I slot print_timing: id 0 | task 7462 | graphs reused = 7160 1.44.230.843 I slot print_timing: id 0 | task 7462 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.230.874 I slot release: id 0 | task 7462 | stop processing: n_tokens = 548, truncated = 0 1.44.252.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 104144799 1.44.252.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 1.44.276.074 I slot launch_slot_: id 0 | task 7541 | processing task, is_child = 0 1.44.910.002 I slot print_timing: id 0 | task 7541 | prompt eval time = 111.55 ms / 396 tokens ( 0.28 ms per token, 3549.98 tokens per second) 1.44.910.008 I slot print_timing: id 0 | task 7541 | eval time = 522.36 ms / 48 tokens ( 11.11 ms per token, 89.98 tokens per second) 1.44.910.009 I slot print_timing: id 0 | task 7541 | total time = 633.91 ms / 444 tokens 1.44.910.010 I slot print_timing: id 0 | task 7541 | graphs reused = 7206 1.44.910.011 I slot print_timing: id 0 | task 7541 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.910.041 I slot release: id 0 | task 7541 | stop processing: n_tokens = 470, truncated = 0 1.44.924.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 104823966 1.44.924.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 1.44.944.599 I slot launch_slot_: id 0 | task 7590 | processing task, is_child = 0 1.46.039.456 I slot print_timing: id 0 | task 7590 | prompt eval time = 121.64 ms / 466 tokens ( 0.26 ms per token, 3830.82 tokens per second) 1.46.039.462 I slot print_timing: id 0 | task 7590 | eval time = 973.20 ms / 88 tokens ( 11.19 ms per token, 89.40 tokens per second) 1.46.039.463 I slot print_timing: id 0 | task 7590 | total time = 1094.84 ms / 554 tokens 1.46.039.464 I slot print_timing: id 0 | task 7590 | graphs reused = 7291 1.46.039.465 I slot print_timing: id 0 | task 7590 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.039.495 I slot release: id 0 | task 7590 | stop processing: n_tokens = 578, truncated = 0 1.46.067.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 105953419 1.46.067.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.46.091.631 I slot launch_slot_: id 0 | task 7679 | processing task, is_child = 0 1.46.960.903 I slot print_timing: id 0 | task 7679 | prompt eval time = 121.53 ms / 467 tokens ( 0.26 ms per token, 3842.83 tokens per second) 1.46.960.908 I slot print_timing: id 0 | task 7679 | eval time = 747.73 ms / 66 tokens ( 11.50 ms per token, 86.93 tokens per second) 1.46.960.910 I slot print_timing: id 0 | task 7679 | total time = 869.26 ms / 533 tokens 1.46.960.911 I slot print_timing: id 0 | task 7679 | graphs reused = 7354 1.46.960.911 I slot print_timing: id 0 | task 7679 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.960.944 I slot release: id 0 | task 7679 | stop processing: n_tokens = 557, truncated = 0 1.46.965.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 106874869 1.46.965.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 1.46.992.693 I slot launch_slot_: id 0 | task 7746 | processing task, is_child = 0 1.47.905.916 I slot print_timing: id 0 | task 7746 | prompt eval time = 121.43 ms / 454 tokens ( 0.27 ms per token, 3738.69 tokens per second) 1.47.905.922 I slot print_timing: id 0 | task 7746 | eval time = 791.78 ms / 71 tokens ( 11.31 ms per token, 88.41 tokens per second) 1.47.905.923 I slot print_timing: id 0 | task 7746 | total time = 913.21 ms / 525 tokens 1.47.905.923 I slot print_timing: id 0 | task 7746 | graphs reused = 7422 1.47.905.925 I slot print_timing: id 0 | task 7746 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.905.958 I slot release: id 0 | task 7746 | stop processing: n_tokens = 549, truncated = 0 1.47.932.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 107819883 1.47.932.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 1.47.954.677 I slot launch_slot_: id 0 | task 7818 | processing task, is_child = 0 1.48.742.941 I slot print_timing: id 0 | task 7818 | prompt eval time = 111.87 ms / 409 tokens ( 0.27 ms per token, 3656.09 tokens per second) 1.48.742.947 I slot print_timing: id 0 | task 7818 | eval time = 676.38 ms / 62 tokens ( 11.09 ms per token, 90.19 tokens per second) 1.48.742.948 I slot print_timing: id 0 | task 7818 | total time = 788.25 ms / 471 tokens 1.48.742.949 I slot print_timing: id 0 | task 7818 | graphs reused = 7482 1.48.742.950 I slot print_timing: id 0 | task 7818 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.742.980 I slot release: id 0 | task 7818 | stop processing: n_tokens = 495, truncated = 0 1.48.770.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 108656904 1.48.770.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.48.774.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.48.795.263 I slot launch_slot_: id 0 | task 7881 | processing task, is_child = 0 1.50.113.277 I slot print_timing: id 0 | task 7881 | prompt eval time = 90.32 ms / 349 tokens ( 0.26 ms per token, 3864.04 tokens per second) 1.50.113.283 I slot print_timing: id 0 | task 7881 | eval time = 1227.68 ms / 112 tokens ( 11.06 ms per token, 90.41 tokens per second) 1.50.113.284 I slot print_timing: id 0 | task 7881 | total time = 1318.00 ms / 461 tokens 1.50.113.285 I slot print_timing: id 0 | task 7881 | graphs reused = 7592 1.50.113.286 I slot print_timing: id 0 | task 7881 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.113.314 I slot release: id 0 | task 7881 | stop processing: n_tokens = 485, truncated = 0 1.50.128.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 110027239 1.50.128.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 1.50.149.949 I slot launch_slot_: id 0 | task 7994 | processing task, is_child = 0 1.50.901.407 I slot print_timing: id 0 | task 7994 | prompt eval time = 113.46 ms / 435 tokens ( 0.26 ms per token, 3833.92 tokens per second) 1.50.901.413 I slot print_timing: id 0 | task 7994 | eval time = 637.98 ms / 58 tokens ( 11.19 ms per token, 89.34 tokens per second) 1.50.901.414 I slot print_timing: id 0 | task 7994 | total time = 751.44 ms / 493 tokens 1.50.901.415 I slot print_timing: id 0 | task 7994 | graphs reused = 7647 1.50.901.416 I slot print_timing: id 0 | task 7994 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.901.447 I slot release: id 0 | task 7994 | stop processing: n_tokens = 517, truncated = 0 1.50.922.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 110815372 1.50.922.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 1.50.943.964 I slot launch_slot_: id 0 | task 8053 | processing task, is_child = 0 1.51.556.320 I slot print_timing: id 0 | task 8053 | prompt eval time = 83.66 ms / 322 tokens ( 0.26 ms per token, 3849.14 tokens per second) 1.51.556.326 I slot print_timing: id 0 | task 8053 | eval time = 528.69 ms / 47 tokens ( 11.49 ms per token, 87.01 tokens per second) 1.51.556.327 I slot print_timing: id 0 | task 8053 | total time = 612.34 ms / 369 tokens 1.51.556.328 I slot print_timing: id 0 | task 8053 | graphs reused = 7692 1.51.556.329 I slot print_timing: id 0 | task 8053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.556.361 I slot release: id 0 | task 8053 | stop processing: n_tokens = 393, truncated = 0 1.51.575.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 111470285 1.51.576.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.51.594.052 I slot launch_slot_: id 0 | task 8101 | processing task, is_child = 0 1.52.295.417 I slot print_timing: id 0 | task 8101 | prompt eval time = 90.75 ms / 360 tokens ( 0.25 ms per token, 3966.81 tokens per second) 1.52.295.423 I slot print_timing: id 0 | task 8101 | eval time = 610.60 ms / 56 tokens ( 11.10 ms per token, 90.08 tokens per second) 1.52.295.424 I slot print_timing: id 0 | task 8101 | total time = 701.35 ms / 416 tokens 1.52.295.425 I slot print_timing: id 0 | task 8101 | graphs reused = 7746 1.52.295.426 I slot print_timing: id 0 | task 8101 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.295.455 I slot release: id 0 | task 8101 | stop processing: n_tokens = 440, truncated = 0 1.52.310.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 112209380 1.52.310.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.52.329.384 I slot launch_slot_: id 0 | task 8158 | processing task, is_child = 0 1.53.247.980 I slot print_timing: id 0 | task 8158 | prompt eval time = 113.49 ms / 443 tokens ( 0.26 ms per token, 3903.46 tokens per second) 1.53.247.985 I slot print_timing: id 0 | task 8158 | eval time = 805.09 ms / 73 tokens ( 11.18 ms per token, 89.43 tokens per second) 1.53.247.986 I slot print_timing: id 0 | task 8158 | total time = 918.58 ms / 516 tokens 1.53.247.987 I slot print_timing: id 0 | task 8158 | graphs reused = 7816 1.53.247.988 I slot print_timing: id 0 | task 8158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.248.018 I slot release: id 0 | task 8158 | stop processing: n_tokens = 540, truncated = 0 1.53.274.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 113161943 1.53.274.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 1.53.296.835 I slot launch_slot_: id 0 | task 8232 | processing task, is_child = 0 1.53.889.298 I slot print_timing: id 0 | task 8232 | prompt eval time = 113.52 ms / 442 tokens ( 0.26 ms per token, 3893.76 tokens per second) 1.53.889.304 I slot print_timing: id 0 | task 8232 | eval time = 478.93 ms / 44 tokens ( 11.14 ms per token, 89.78 tokens per second) 1.53.889.305 I slot print_timing: id 0 | task 8232 | total time = 592.45 ms / 486 tokens 1.53.889.306 I slot print_timing: id 0 | task 8232 | graphs reused = 7858 1.53.889.307 I slot print_timing: id 0 | task 8232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.889.337 I slot release: id 0 | task 8232 | stop processing: n_tokens = 510, truncated = 0 1.53.915.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 113803262 1.53.915.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 1.53.937.137 I slot launch_slot_: id 0 | task 8277 | processing task, is_child = 0 1.54.543.204 I slot print_timing: id 0 | task 8277 | prompt eval time = 121.37 ms / 470 tokens ( 0.26 ms per token, 3872.42 tokens per second) 1.54.543.209 I slot print_timing: id 0 | task 8277 | eval time = 484.68 ms / 44 tokens ( 11.27 ms per token, 88.72 tokens per second) 1.54.543.210 I slot print_timing: id 0 | task 8277 | total time = 606.05 ms / 514 tokens 1.54.543.211 I slot print_timing: id 0 | task 8277 | graphs reused = 7899 1.54.543.212 I slot print_timing: id 0 | task 8277 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.543.246 I slot release: id 0 | task 8277 | stop processing: n_tokens = 538, truncated = 0 1.54.568.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 114457170 1.54.568.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.54.595.891 I slot launch_slot_: id 0 | task 8322 | processing task, is_child = 0 1.55.093.660 I slot print_timing: id 0 | task 8322 | prompt eval time = 122.57 ms / 483 tokens ( 0.25 ms per token, 3940.70 tokens per second) 1.55.093.666 I slot print_timing: id 0 | task 8322 | eval time = 375.19 ms / 34 tokens ( 11.37 ms per token, 87.96 tokens per second) 1.55.093.667 I slot print_timing: id 0 | task 8322 | total time = 497.75 ms / 517 tokens 1.55.093.668 I slot print_timing: id 0 | task 8322 | graphs reused = 7930 1.55.093.668 I slot print_timing: id 0 | task 8322 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.093.701 I slot release: id 0 | task 8322 | stop processing: n_tokens = 541, truncated = 0 1.55.098.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 115007626 1.55.098.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.55.102.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 1.55.124.208 I slot launch_slot_: id 0 | task 8357 | processing task, is_child = 0 1.56.429.642 I slot print_timing: id 0 | task 8357 | prompt eval time = 121.52 ms / 463 tokens ( 0.26 ms per token, 3810.23 tokens per second) 1.56.429.648 I slot print_timing: id 0 | task 8357 | eval time = 1183.90 ms / 107 tokens ( 11.17 ms per token, 89.53 tokens per second) 1.56.429.649 I slot print_timing: id 0 | task 8357 | total time = 1305.42 ms / 570 tokens 1.56.429.649 I slot print_timing: id 0 | task 8357 | graphs reused = 8034 1.56.429.650 I slot print_timing: id 0 | task 8357 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.429.680 I slot release: id 0 | task 8357 | stop processing: n_tokens = 594, truncated = 0 1.56.454.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 594, t_last = 116343604 1.56.454.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.56.478.067 I slot launch_slot_: id 0 | task 8465 | processing task, is_child = 0 1.57.134.884 I slot print_timing: id 0 | task 8465 | prompt eval time = 112.58 ms / 421 tokens ( 0.27 ms per token, 3739.66 tokens per second) 1.57.134.890 I slot print_timing: id 0 | task 8465 | eval time = 544.22 ms / 50 tokens ( 11.11 ms per token, 90.04 tokens per second) 1.57.134.891 I slot print_timing: id 0 | task 8465 | total time = 656.80 ms / 471 tokens 1.57.134.892 I slot print_timing: id 0 | task 8465 | graphs reused = 8082 1.57.134.893 I slot print_timing: id 0 | task 8465 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.134.922 I slot release: id 0 | task 8465 | stop processing: n_tokens = 495, truncated = 0 1.57.161.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 117048847 1.57.161.189 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.57.181.855 I slot launch_slot_: id 0 | task 8516 | processing task, is_child = 0 1.57.739.393 I slot print_timing: id 0 | task 8516 | prompt eval time = 90.81 ms / 360 tokens ( 0.25 ms per token, 3964.54 tokens per second) 1.57.739.399 I slot print_timing: id 0 | task 8516 | eval time = 466.72 ms / 43 tokens ( 11.11 ms per token, 89.99 tokens per second) 1.57.739.400 I slot print_timing: id 0 | task 8516 | total time = 557.52 ms / 403 tokens 1.57.739.401 I slot print_timing: id 0 | task 8516 | graphs reused = 8123 1.57.739.402 I slot print_timing: id 0 | task 8516 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.739.433 I slot release: id 0 | task 8516 | stop processing: n_tokens = 427, truncated = 0 1.57.759.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 117653358 1.57.759.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.57.762.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.57.781.886 I slot launch_slot_: id 0 | task 8560 | processing task, is_child = 0 1.58.687.608 I slot print_timing: id 0 | task 8560 | prompt eval time = 145.71 ms / 547 tokens ( 0.27 ms per token, 3754.01 tokens per second) 1.58.687.614 I slot print_timing: id 0 | task 8560 | eval time = 760.00 ms / 69 tokens ( 11.18 ms per token, 89.47 tokens per second) 1.58.687.615 I slot print_timing: id 0 | task 8560 | total time = 905.71 ms / 616 tokens 1.58.687.616 I slot print_timing: id 0 | task 8560 | graphs reused = 8190 1.58.687.617 I slot print_timing: id 0 | task 8560 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.687.653 I slot release: id 0 | task 8560 | stop processing: n_tokens = 640, truncated = 0 1.58.693.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 118601577 1.58.693.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.664 MiB) 1.58.724.486 I slot launch_slot_: id 0 | task 8630 | processing task, is_child = 0 2.00.104.603 I slot print_timing: id 0 | task 8630 | prompt eval time = 191.68 ms / 749 tokens ( 0.26 ms per token, 3907.51 tokens per second) 2.00.104.608 I slot print_timing: id 0 | task 8630 | eval time = 1188.42 ms / 107 tokens ( 11.21 ms per token, 89.19 tokens per second) 2.00.104.610 I slot print_timing: id 0 | task 8630 | total time = 1380.10 ms / 856 tokens 2.00.104.610 I slot print_timing: id 0 | task 8630 | graphs reused = 8295 2.00.104.611 I slot print_timing: id 0 | task 8630 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.104.652 I slot release: id 0 | task 8630 | stop processing: n_tokens = 880, truncated = 0 2.00.110.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 120018576 2.00.110.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 2.00.114.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 2.00.145.861 I slot launch_slot_: id 0 | task 8738 | processing task, is_child = 0 2.00.847.886 I slot print_timing: id 0 | task 8738 | prompt eval time = 174.66 ms / 678 tokens ( 0.26 ms per token, 3881.92 tokens per second) 2.00.847.892 I slot print_timing: id 0 | task 8738 | eval time = 527.35 ms / 48 tokens ( 11.22 ms per token, 89.12 tokens per second) 2.00.847.893 I slot print_timing: id 0 | task 8738 | total time = 702.01 ms / 726 tokens 2.00.847.894 I slot print_timing: id 0 | task 8738 | graphs reused = 8341 2.00.847.895 I slot print_timing: id 0 | task 8738 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.847.933 I slot release: id 0 | task 8738 | stop processing: n_tokens = 750, truncated = 0 2.00.875.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 120761858 2.00.875.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 2.00.904.621 I slot launch_slot_: id 0 | task 8787 | processing task, is_child = 0 2.01.686.219 I slot print_timing: id 0 | task 8787 | prompt eval time = 146.38 ms / 567 tokens ( 0.26 ms per token, 3873.37 tokens per second) 2.01.686.225 I slot print_timing: id 0 | task 8787 | eval time = 635.20 ms / 57 tokens ( 11.34 ms per token, 88.16 tokens per second) 2.01.686.226 I slot print_timing: id 0 | task 8787 | total time = 781.58 ms / 624 tokens 2.01.686.226 I slot print_timing: id 0 | task 8787 | graphs reused = 8396 2.01.686.227 I slot print_timing: id 0 | task 8787 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.686.262 I slot release: id 0 | task 8787 | stop processing: n_tokens = 648, truncated = 0 2.01.715.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 121600187 2.01.715.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.01.720.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 2.01.744.947 I slot launch_slot_: id 0 | task 8845 | processing task, is_child = 0 2.02.507.567 I slot print_timing: id 0 | task 8845 | prompt eval time = 124.33 ms / 501 tokens ( 0.25 ms per token, 4029.57 tokens per second) 2.02.507.573 I slot print_timing: id 0 | task 8845 | eval time = 638.27 ms / 58 tokens ( 11.20 ms per token, 89.30 tokens per second) 2.02.507.574 I slot print_timing: id 0 | task 8845 | total time = 762.60 ms / 559 tokens 2.02.507.575 I slot print_timing: id 0 | task 8845 | graphs reused = 8452 2.02.507.576 I slot print_timing: id 0 | task 8845 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.507.610 I slot release: id 0 | task 8845 | stop processing: n_tokens = 583, truncated = 0 2.02.513.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 122421534 2.02.513.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.02.537.181 I slot launch_slot_: id 0 | task 8904 | processing task, is_child = 0 2.03.419.573 I slot print_timing: id 0 | task 8904 | prompt eval time = 197.42 ms / 769 tokens ( 0.26 ms per token, 3895.31 tokens per second) 2.03.419.579 I slot print_timing: id 0 | task 8904 | eval time = 684.96 ms / 62 tokens ( 11.23 ms per token, 89.06 tokens per second) 2.03.419.580 I slot print_timing: id 0 | task 8904 | total time = 882.38 ms / 831 tokens 2.03.419.581 I slot print_timing: id 0 | task 8904 | graphs reused = 8512 2.03.419.582 I slot print_timing: id 0 | task 8904 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.419.626 I slot release: id 0 | task 8904 | stop processing: n_tokens = 855, truncated = 0 2.03.444.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 123333551 2.03.444.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 2.03.449.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.03.479.802 I slot launch_slot_: id 0 | task 8967 | processing task, is_child = 0 2.04.275.596 I slot print_timing: id 0 | task 8967 | prompt eval time = 124.33 ms / 500 tokens ( 0.25 ms per token, 4021.43 tokens per second) 2.04.275.602 I slot print_timing: id 0 | task 8967 | eval time = 671.45 ms / 61 tokens ( 11.19 ms per token, 89.36 tokens per second) 2.04.275.604 I slot print_timing: id 0 | task 8967 | total time = 795.78 ms / 561 tokens 2.04.275.606 I slot print_timing: id 0 | task 8967 | graphs reused = 8571 2.04.275.607 I slot print_timing: id 0 | task 8967 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.275.645 I slot release: id 0 | task 8967 | stop processing: n_tokens = 585, truncated = 0 2.04.300.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 124189569 2.04.300.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 2.04.323.764 I slot launch_slot_: id 0 | task 9029 | processing task, is_child = 0 2.05.131.532 I slot print_timing: id 0 | task 9029 | prompt eval time = 159.57 ms / 632 tokens ( 0.25 ms per token, 3960.72 tokens per second) 2.05.131.538 I slot print_timing: id 0 | task 9029 | eval time = 648.19 ms / 58 tokens ( 11.37 ms per token, 87.94 tokens per second) 2.05.131.539 I slot print_timing: id 0 | task 9029 | total time = 807.75 ms / 690 tokens 2.05.131.540 I slot print_timing: id 0 | task 9029 | graphs reused = 8627 2.05.131.541 I slot print_timing: id 0 | task 9029 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.131.578 I slot release: id 0 | task 9029 | stop processing: n_tokens = 714, truncated = 0 2.05.158.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 125045503 2.05.158.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.05.162.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 2.05.198.694 I slot launch_slot_: id 0 | task 9088 | processing task, is_child = 0 2.05.711.225 I slot print_timing: id 0 | task 9088 | prompt eval time = 111.67 ms / 395 tokens ( 0.28 ms per token, 3537.05 tokens per second) 2.05.711.230 I slot print_timing: id 0 | task 9088 | eval time = 400.84 ms / 37 tokens ( 11.13 ms per token, 89.81 tokens per second) 2.05.711.231 I slot print_timing: id 0 | task 9088 | total time = 512.51 ms / 432 tokens 2.05.711.232 I slot print_timing: id 0 | task 9088 | graphs reused = 8662 2.05.711.233 I slot print_timing: id 0 | task 9088 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.711.260 I slot release: id 0 | task 9088 | stop processing: n_tokens = 456, truncated = 0 2.05.736.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 125625185 2.05.736.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 2.05.757.886 I slot launch_slot_: id 0 | task 9126 | processing task, is_child = 0 2.06.575.117 I slot print_timing: id 0 | task 9126 | prompt eval time = 150.35 ms / 579 tokens ( 0.26 ms per token, 3851.12 tokens per second) 2.06.575.124 I slot print_timing: id 0 | task 9126 | eval time = 666.87 ms / 59 tokens ( 11.50 ms per token, 86.97 tokens per second) 2.06.575.125 I slot print_timing: id 0 | task 9126 | total time = 817.22 ms / 638 tokens 2.06.575.126 I slot print_timing: id 0 | task 9126 | graphs reused = 8719 2.06.575.127 I slot print_timing: id 0 | task 9126 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.575.164 I slot release: id 0 | task 9126 | stop processing: n_tokens = 662, truncated = 0 2.06.604.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 126489089 2.06.604.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 2.06.629.728 I slot launch_slot_: id 0 | task 9186 | processing task, is_child = 0 2.07.466.643 I slot print_timing: id 0 | task 9186 | prompt eval time = 174.23 ms / 689 tokens ( 0.25 ms per token, 3954.59 tokens per second) 2.07.466.649 I slot print_timing: id 0 | task 9186 | eval time = 662.67 ms / 59 tokens ( 11.43 ms per token, 87.52 tokens per second) 2.07.466.650 I slot print_timing: id 0 | task 9186 | total time = 836.90 ms / 748 tokens 2.07.466.651 I slot print_timing: id 0 | task 9186 | graphs reused = 8775 2.07.466.652 I slot print_timing: id 0 | task 9186 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.466.691 I slot release: id 0 | task 9186 | stop processing: n_tokens = 772, truncated = 0 2.07.489.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 127380616 2.07.489.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 2.07.494.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 2.07.522.170 I slot launch_slot_: id 0 | task 9246 | processing task, is_child = 0 2.08.456.921 I slot print_timing: id 0 | task 9246 | prompt eval time = 187.34 ms / 752 tokens ( 0.25 ms per token, 4014.01 tokens per second) 2.08.456.927 I slot print_timing: id 0 | task 9246 | eval time = 747.39 ms / 66 tokens ( 11.50 ms per token, 86.97 tokens per second) 2.08.456.928 I slot print_timing: id 0 | task 9246 | total time = 934.74 ms / 818 tokens 2.08.456.928 I slot print_timing: id 0 | task 9246 | graphs reused = 8839 2.08.456.930 I slot print_timing: id 0 | task 9246 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.456.973 I slot release: id 0 | task 9246 | stop processing: n_tokens = 842, truncated = 0 2.08.475.159 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 128370897 2.08.475.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 2.08.480.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 2.08.512.306 I slot launch_slot_: id 0 | task 9313 | processing task, is_child = 0 2.09.401.255 I slot print_timing: id 0 | task 9313 | prompt eval time = 150.99 ms / 582 tokens ( 0.26 ms per token, 3854.61 tokens per second) 2.09.401.261 I slot print_timing: id 0 | task 9313 | eval time = 737.94 ms / 67 tokens ( 11.18 ms per token, 89.44 tokens per second) 2.09.401.262 I slot print_timing: id 0 | task 9313 | total time = 888.93 ms / 649 tokens 2.09.401.263 I slot print_timing: id 0 | task 9313 | graphs reused = 8904 2.09.401.264 I slot print_timing: id 0 | task 9313 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.401.300 I slot release: id 0 | task 9313 | stop processing: n_tokens = 673, truncated = 0 2.09.424.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 129315224 2.09.424.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.09.455.176 I slot launch_slot_: id 0 | task 9381 | processing task, is_child = 0 2.10.473.852 I slot print_timing: id 0 | task 9381 | prompt eval time = 168.61 ms / 656 tokens ( 0.26 ms per token, 3890.68 tokens per second) 2.10.473.858 I slot print_timing: id 0 | task 9381 | eval time = 850.05 ms / 77 tokens ( 11.18 ms per token, 89.41 tokens per second) 2.10.473.859 I slot print_timing: id 0 | task 9381 | total time = 1018.66 ms / 733 tokens 2.10.473.859 I slot print_timing: id 0 | task 9381 | graphs reused = 8979 2.10.473.860 I slot print_timing: id 0 | task 9381 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.473.899 I slot release: id 0 | task 9381 | stop processing: n_tokens = 757, truncated = 0 2.10.499.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 130387824 2.10.499.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 2.10.530.444 I slot launch_slot_: id 0 | task 9459 | processing task, is_child = 0 2.11.025.325 I slot print_timing: id 0 | task 9459 | prompt eval time = 156.97 ms / 613 tokens ( 0.26 ms per token, 3905.28 tokens per second) 2.11.025.331 I slot print_timing: id 0 | task 9459 | eval time = 337.90 ms / 31 tokens ( 11.26 ms per token, 88.78 tokens per second) 2.11.025.332 I slot print_timing: id 0 | task 9459 | total time = 494.87 ms / 644 tokens 2.11.025.333 I slot print_timing: id 0 | task 9459 | graphs reused = 9008 2.11.025.334 I slot print_timing: id 0 | task 9459 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.025.372 I slot release: id 0 | task 9459 | stop processing: n_tokens = 668, truncated = 0 2.11.031.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 130939297 2.11.031.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.728 MiB) 2.11.061.206 I slot launch_slot_: id 0 | task 9491 | processing task, is_child = 0 2.12.478.332 I slot print_timing: id 0 | task 9491 | prompt eval time = 188.49 ms / 766 tokens ( 0.25 ms per token, 4063.83 tokens per second) 2.12.478.337 I slot print_timing: id 0 | task 9491 | eval time = 1228.62 ms / 109 tokens ( 11.38 ms per token, 87.90 tokens per second) 2.12.478.338 I slot print_timing: id 0 | task 9491 | total time = 1417.11 ms / 875 tokens 2.12.478.339 I slot print_timing: id 0 | task 9491 | graphs reused = 9115 2.12.478.340 I slot print_timing: id 0 | task 9491 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.478.383 I slot release: id 0 | task 9491 | stop processing: n_tokens = 899, truncated = 0 2.12.509.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 132392308 2.12.509.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.12.542.678 I slot launch_slot_: id 0 | task 9601 | processing task, is_child = 0 2.13.423.425 I slot print_timing: id 0 | task 9601 | prompt eval time = 206.77 ms / 846 tokens ( 0.24 ms per token, 4091.48 tokens per second) 2.13.423.431 I slot print_timing: id 0 | task 9601 | eval time = 673.96 ms / 61 tokens ( 11.23 ms per token, 89.03 tokens per second) 2.13.423.432 I slot print_timing: id 0 | task 9601 | total time = 880.73 ms / 907 tokens 2.13.423.433 I slot print_timing: id 0 | task 9601 | graphs reused = 9174 2.13.423.434 I slot print_timing: id 0 | task 9601 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.423.482 I slot release: id 0 | task 9601 | stop processing: n_tokens = 931, truncated = 0 2.13.446.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 133337407 2.13.446.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 2.13.481.997 I slot launch_slot_: id 0 | task 9663 | processing task, is_child = 0 2.14.499.149 I slot print_timing: id 0 | task 9663 | prompt eval time = 168.43 ms / 650 tokens ( 0.26 ms per token, 3859.10 tokens per second) 2.14.499.155 I slot print_timing: id 0 | task 9663 | eval time = 848.70 ms / 77 tokens ( 11.17 ms per token, 89.55 tokens per second) 2.14.499.156 I slot print_timing: id 0 | task 9663 | total time = 1017.13 ms / 727 tokens 2.14.499.157 I slot print_timing: id 0 | task 9663 | graphs reused = 9249 2.14.499.157 I slot print_timing: id 0 | task 9663 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.499.195 I slot release: id 0 | task 9663 | stop processing: n_tokens = 751, truncated = 0 2.14.525.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 134413120 2.14.525.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.14.531.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.14.561.328 I slot launch_slot_: id 0 | task 9741 | processing task, is_child = 0 2.15.330.730 I slot print_timing: id 0 | task 9741 | prompt eval time = 181.43 ms / 717 tokens ( 0.25 ms per token, 3952.02 tokens per second) 2.15.330.736 I slot print_timing: id 0 | task 9741 | eval time = 587.95 ms / 53 tokens ( 11.31 ms per token, 88.44 tokens per second) 2.15.330.737 I slot print_timing: id 0 | task 9741 | total time = 769.38 ms / 770 tokens 2.15.330.738 I slot print_timing: id 0 | task 9741 | graphs reused = 9299 2.15.330.738 I slot print_timing: id 0 | task 9741 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.330.780 I slot release: id 0 | task 9741 | stop processing: n_tokens = 794, truncated = 0 2.15.335.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 135244705 2.15.335.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 2.15.365.897 I slot launch_slot_: id 0 | task 9795 | processing task, is_child = 0 2.16.148.268 I slot print_timing: id 0 | task 9795 | prompt eval time = 124.11 ms / 494 tokens ( 0.25 ms per token, 3980.18 tokens per second) 2.16.148.274 I slot print_timing: id 0 | task 9795 | eval time = 658.24 ms / 59 tokens ( 11.35 ms per token, 88.11 tokens per second) 2.16.148.275 I slot print_timing: id 0 | task 9795 | total time = 782.36 ms / 553 tokens 2.16.148.276 I slot print_timing: id 0 | task 9795 | graphs reused = 9356 2.16.148.277 I slot print_timing: id 0 | task 9795 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.148.310 I slot release: id 0 | task 9795 | stop processing: n_tokens = 577, truncated = 0 2.16.173.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 136062235 2.16.173.757 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.16.199.455 I slot launch_slot_: id 0 | task 9855 | processing task, is_child = 0 2.16.956.707 I slot print_timing: id 0 | task 9855 | prompt eval time = 150.36 ms / 579 tokens ( 0.26 ms per token, 3850.71 tokens per second) 2.16.956.713 I slot print_timing: id 0 | task 9855 | eval time = 606.87 ms / 54 tokens ( 11.45 ms per token, 87.33 tokens per second) 2.16.956.714 I slot print_timing: id 0 | task 9855 | total time = 757.23 ms / 633 tokens 2.16.956.714 I slot print_timing: id 0 | task 9855 | graphs reused = 9408 2.16.956.716 I slot print_timing: id 0 | task 9855 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.956.754 I slot release: id 0 | task 9855 | stop processing: n_tokens = 657, truncated = 0 2.16.982.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 136870679 2.16.982.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.727 MiB) 2.17.010.927 I slot launch_slot_: id 0 | task 9910 | processing task, is_child = 0 2.18.073.937 I slot print_timing: id 0 | task 9910 | prompt eval time = 235.38 ms / 919 tokens ( 0.26 ms per token, 3904.26 tokens per second) 2.18.073.944 I slot print_timing: id 0 | task 9910 | eval time = 827.61 ms / 73 tokens ( 11.49 ms per token, 87.00 tokens per second) 2.18.073.945 I slot print_timing: id 0 | task 9910 | total time = 1062.99 ms / 992 tokens 2.18.073.947 I slot print_timing: id 0 | task 9910 | graphs reused = 9479 2.18.073.948 I slot print_timing: id 0 | task 9910 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.073.996 I slot release: id 0 | task 9910 | stop processing: n_tokens = 1016, truncated = 0 2.18.103.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 137987921 2.18.103.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.18.108.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.18.148.040 I slot launch_slot_: id 0 | task 9984 | processing task, is_child = 0 2.18.790.681 I slot print_timing: id 0 | task 9984 | prompt eval time = 213.84 ms / 865 tokens ( 0.25 ms per token, 4045.14 tokens per second) 2.18.790.687 I slot print_timing: id 0 | task 9984 | eval time = 428.78 ms / 39 tokens ( 11.28 ms per token, 88.62 tokens per second) 2.18.790.688 I slot print_timing: id 0 | task 9984 | total time = 642.62 ms / 904 tokens 2.18.790.688 I slot print_timing: id 0 | task 9984 | graphs reused = 9516 2.18.790.689 I slot print_timing: id 0 | task 9984 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.790.737 I slot release: id 0 | task 9984 | stop processing: n_tokens = 928, truncated = 0 2.18.815.447 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 138704662 2.18.815.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 2.18.820.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 2.18.854.162 I slot launch_slot_: id 0 | task 10024 | processing task, is_child = 0 2.21.970.478 I slot print_timing: id 0 | task 10024 | n_gen = 271, tg = 89.87 t/s, tg_3s = 90.20 t/s 2.24.974.145 I slot print_timing: id 0 | task 10024 | n_gen = 540, tg = 89.71 t/s, tg_3s = 89.56 t/s 2.27.980.022 I slot print_timing: id 0 | task 10024 | n_gen = 805, tg = 89.20 t/s, tg_3s = 88.16 t/s 2.30.477.480 I slot print_timing: id 0 | task 10024 | prompt eval time = 111.98 ms / 408 tokens ( 0.27 ms per token, 3643.41 tokens per second) 2.30.477.487 I slot print_timing: id 0 | task 10024 | eval time = 11511.32 ms / 1024 tokens ( 11.25 ms per token, 88.87 tokens per second) 2.30.477.488 I slot print_timing: id 0 | task 10024 | total time = 11623.30 ms / 1432 tokens 2.30.477.489 I slot print_timing: id 0 | task 10024 | graphs reused = 10534 2.30.477.490 I slot print_timing: id 0 | task 10024 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.477.527 I slot release: id 0 | task 10024 | stop processing: n_tokens = 1456, truncated = 0 2.30.481.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1456, t_last = 150391451 2.30.481.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 2.30.486.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 2.30.537.893 I slot launch_slot_: id 0 | task 11049 | processing task, is_child = 0 2.32.067.118 I slot print_timing: id 0 | task 11049 | prompt eval time = 91.62 ms / 338 tokens ( 0.27 ms per token, 3689.15 tokens per second) 2.32.067.124 I slot print_timing: id 0 | task 11049 | eval time = 1437.59 ms / 131 tokens ( 11.06 ms per token, 90.43 tokens per second) 2.32.067.125 I slot print_timing: id 0 | task 11049 | total time = 1529.21 ms / 469 tokens 2.32.067.126 I slot print_timing: id 0 | task 11049 | graphs reused = 10663 2.32.067.126 I slot print_timing: id 0 | task 11049 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.067.154 I slot release: id 0 | task 11049 | stop processing: n_tokens = 495, truncated = 0 2.32.090.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 151981079 2.32.090.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 2.32.113.982 I slot launch_slot_: id 0 | task 11181 | processing task, is_child = 0 2.35.206.101 I slot print_timing: id 0 | task 11181 | n_gen = 271, tg = 89.98 t/s, tg_3s = 90.31 t/s 2.38.208.887 I slot print_timing: id 0 | task 11181 | n_gen = 540, tg = 89.78 t/s, tg_3s = 89.58 t/s 2.41.219.330 I slot print_timing: id 0 | task 11181 | n_gen = 807, tg = 89.42 t/s, tg_3s = 88.69 t/s 2.43.686.265 I slot print_timing: id 0 | task 11181 | prompt eval time = 91.34 ms / 363 tokens ( 0.25 ms per token, 3974.29 tokens per second) 2.43.686.270 I slot print_timing: id 0 | task 11181 | eval time = 11480.93 ms / 1024 tokens ( 11.22 ms per token, 89.10 tokens per second) 2.43.686.271 I slot print_timing: id 0 | task 11181 | total time = 11572.27 ms / 1387 tokens 2.43.686.272 I slot print_timing: id 0 | task 11181 | graphs reused = 11681 2.43.686.273 I slot print_timing: id 0 | task 11181 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.686.302 I slot release: id 0 | task 11181 | stop processing: n_tokens = 1413, truncated = 0 2.43.706.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 163600227 2.43.706.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.43.711.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 2.43.764.494 I slot launch_slot_: id 0 | task 12206 | processing task, is_child = 0 2.46.858.022 I slot print_timing: id 0 | task 12206 | n_gen = 270, tg = 89.36 t/s, tg_3s = 89.69 t/s 2.49.864.002 I slot print_timing: id 0 | task 12206 | n_gen = 539, tg = 89.43 t/s, tg_3s = 89.49 t/s 2.52.871.074 I slot print_timing: id 0 | task 12206 | n_gen = 806, tg = 89.21 t/s, tg_3s = 88.79 t/s 2.55.349.486 I slot print_timing: id 0 | task 12206 | prompt eval time = 83.29 ms / 317 tokens ( 0.26 ms per token, 3806.02 tokens per second) 2.55.349.491 I slot print_timing: id 0 | task 12206 | eval time = 11501.69 ms / 1024 tokens ( 11.24 ms per token, 88.94 tokens per second) 2.55.349.492 I slot print_timing: id 0 | task 12206 | total time = 11584.98 ms / 1341 tokens 2.55.349.493 I slot print_timing: id 0 | task 12206 | graphs reused = 12699 2.55.349.494 I slot print_timing: id 0 | task 12206 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.349.523 I slot release: id 0 | task 12206 | stop processing: n_tokens = 1367, truncated = 0 2.55.377.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1367, t_last = 175263448 2.55.377.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 2.55.382.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 2.55.433.899 I slot launch_slot_: id 0 | task 13231 | processing task, is_child = 0 2.58.555.195 I slot print_timing: id 0 | task 13231 | n_gen = 271, tg = 89.70 t/s, tg_3s = 90.03 t/s 3.01.561.546 I slot print_timing: id 0 | task 13231 | n_gen = 540, tg = 89.59 t/s, tg_3s = 89.48 t/s 3.04.465.200 I slot print_timing: id 0 | task 13231 | prompt eval time = 111.27 ms / 389 tokens ( 0.29 ms per token, 3496.09 tokens per second) 3.04.465.206 I slot print_timing: id 0 | task 13231 | eval time = 8920.02 ms / 797 tokens ( 11.21 ms per token, 89.24 tokens per second) 3.04.465.207 I slot print_timing: id 0 | task 13231 | total time = 9031.28 ms / 1186 tokens 3.04.465.209 I slot print_timing: id 0 | task 13231 | graphs reused = 13491 3.04.465.209 I slot print_timing: id 0 | task 13231 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.465.239 I slot release: id 0 | task 13231 | stop processing: n_tokens = 1210, truncated = 0 3.04.469.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1210, t_last = 184379164 3.04.469.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 3.04.477.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.101 MiB) 3.04.525.537 I slot launch_slot_: id 0 | task 14029 | processing task, is_child = 0 3.04.945.135 I slot print_timing: id 0 | task 14029 | prompt eval time = 83.05 ms / 300 tokens ( 0.28 ms per token, 3612.41 tokens per second) 3.04.945.141 I slot print_timing: id 0 | task 14029 | eval time = 336.54 ms / 31 tokens ( 11.22 ms per token, 89.14 tokens per second) 3.04.945.142 I slot print_timing: id 0 | task 14029 | total time = 419.58 ms / 331 tokens 3.04.945.143 I slot print_timing: id 0 | task 14029 | graphs reused = 13520 3.04.945.144 I slot print_timing: id 0 | task 14029 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.945.171 I slot release: id 0 | task 14029 | stop processing: n_tokens = 355, truncated = 0 3.04.949.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 184859095 3.04.961.515 I slot launch_slot_: id 0 | task 14061 | processing task, is_child = 0 3.05.553.272 I slot print_timing: id 0 | task 14061 | prompt eval time = 90.24 ms / 341 tokens ( 0.26 ms per token, 3778.81 tokens per second) 3.05.553.277 I slot print_timing: id 0 | task 14061 | eval time = 501.50 ms / 46 tokens ( 11.14 ms per token, 89.73 tokens per second) 3.05.553.278 I slot print_timing: id 0 | task 14061 | total time = 591.74 ms / 387 tokens 3.05.553.279 I slot print_timing: id 0 | task 14061 | graphs reused = 13564 3.05.553.280 I slot print_timing: id 0 | task 14061 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.553.308 I slot release: id 0 | task 14061 | stop processing: n_tokens = 411, truncated = 0 3.05.557.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 185467233 3.05.557.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.040 MiB) 3.05.578.145 I slot launch_slot_: id 0 | task 14108 | processing task, is_child = 0 3.07.201.527 I slot print_timing: id 0 | task 14108 | prompt eval time = 84.31 ms / 332 tokens ( 0.25 ms per token, 3938.08 tokens per second) 3.07.201.532 I slot print_timing: id 0 | task 14108 | eval time = 1539.06 ms / 140 tokens ( 11.07 ms per token, 90.31 tokens per second) 3.07.201.534 I slot print_timing: id 0 | task 14108 | total time = 1623.37 ms / 472 tokens 3.07.201.534 I slot print_timing: id 0 | task 14108 | graphs reused = 13702 3.07.201.535 I slot print_timing: id 0 | task 14108 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.201.562 I slot release: id 0 | task 14108 | stop processing: n_tokens = 496, truncated = 0 3.07.221.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 187115487 3.07.221.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 3.07.246.751 I slot launch_slot_: id 0 | task 14249 | processing task, is_child = 0 3.08.022.260 I slot print_timing: id 0 | task 14249 | prompt eval time = 75.31 ms / 269 tokens ( 0.28 ms per token, 3571.86 tokens per second) 3.08.022.267 I slot print_timing: id 0 | task 14249 | eval time = 700.18 ms / 64 tokens ( 11.11 ms per token, 89.98 tokens per second) 3.08.022.268 I slot print_timing: id 0 | task 14249 | total time = 775.49 ms / 333 tokens 3.08.022.269 I slot print_timing: id 0 | task 14249 | graphs reused = 13764 3.08.022.270 I slot print_timing: id 0 | task 14249 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.022.298 I slot release: id 0 | task 14249 | stop processing: n_tokens = 357, truncated = 0 3.08.051.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 357, t_last = 187936223 3.08.064.202 I slot launch_slot_: id 0 | task 14314 | processing task, is_child = 0 3.11.154.993 I slot print_timing: id 0 | task 14314 | n_gen = 271, tg = 89.98 t/s, tg_3s = 90.32 t/s 3.14.160.473 I slot print_timing: id 0 | task 14314 | n_gen = 539, tg = 89.58 t/s, tg_3s = 89.17 t/s 3.17.167.866 I slot print_timing: id 0 | task 14314 | n_gen = 806, tg = 89.31 t/s, tg_3s = 88.78 t/s 3.19.644.636 I slot print_timing: id 0 | task 14314 | prompt eval time = 90.17 ms / 341 tokens ( 0.26 ms per token, 3781.54 tokens per second) 3.19.644.641 I slot print_timing: id 0 | task 14314 | eval time = 11490.24 ms / 1024 tokens ( 11.23 ms per token, 89.03 tokens per second) 3.19.644.642 I slot print_timing: id 0 | task 14314 | total time = 11580.42 ms / 1365 tokens 3.19.644.643 I slot print_timing: id 0 | task 14314 | graphs reused = 14782 3.19.644.644 I slot print_timing: id 0 | task 14314 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.644.675 I slot release: id 0 | task 14314 | stop processing: n_tokens = 1389, truncated = 0 3.19.663.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1389, t_last = 199558600 3.19.663.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 3.19.669.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 3.19.719.526 I slot launch_slot_: id 0 | task 15339 | processing task, is_child = 0 3.21.541.556 I slot print_timing: id 0 | task 15339 | prompt eval time = 90.47 ms / 343 tokens ( 0.26 ms per token, 3791.48 tokens per second) 3.21.541.561 I slot print_timing: id 0 | task 15339 | eval time = 1731.55 ms / 157 tokens ( 11.10 ms per token, 90.09 tokens per second) 3.21.541.562 I slot print_timing: id 0 | task 15339 | total time = 1822.01 ms / 500 tokens 3.21.541.563 I slot print_timing: id 0 | task 15339 | graphs reused = 14936 3.21.541.564 I slot print_timing: id 0 | task 15339 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.541.592 I slot release: id 0 | task 15339 | stop processing: n_tokens = 524, truncated = 0 3.21.563.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 201455517 3.21.563.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 3.21.585.546 I slot launch_slot_: id 0 | task 15497 | processing task, is_child = 0 3.24.686.080 I slot print_timing: id 0 | task 15497 | n_gen = 272, tg = 90.03 t/s, tg_3s = 90.36 t/s 3.27.690.825 I slot print_timing: id 0 | task 15497 | n_gen = 541, tg = 89.78 t/s, tg_3s = 89.53 t/s 3.29.161.804 I slot print_timing: id 0 | task 15497 | prompt eval time = 90.39 ms / 347 tokens ( 0.26 ms per token, 3839.05 tokens per second) 3.29.161.810 I slot print_timing: id 0 | task 15497 | eval time = 7485.86 ms / 672 tokens ( 11.16 ms per token, 89.64 tokens per second) 3.29.161.811 I slot print_timing: id 0 | task 15497 | total time = 7576.24 ms / 1019 tokens 3.29.161.812 I slot print_timing: id 0 | task 15497 | graphs reused = 15603 3.29.161.812 I slot print_timing: id 0 | task 15497 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.161.843 I slot release: id 0 | task 15497 | stop processing: n_tokens = 1043, truncated = 0 3.29.183.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1043, t_last = 209075768 3.29.183.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 3.29.188.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 3.29.227.973 I slot launch_slot_: id 0 | task 16170 | processing task, is_child = 0 3.30.982.745 I slot print_timing: id 0 | task 16170 | prompt eval time = 84.15 ms / 332 tokens ( 0.25 ms per token, 3945.52 tokens per second) 3.30.982.750 I slot print_timing: id 0 | task 16170 | eval time = 1670.61 ms / 152 tokens ( 11.06 ms per token, 90.39 tokens per second) 3.30.982.751 I slot print_timing: id 0 | task 16170 | total time = 1754.76 ms / 484 tokens 3.30.982.752 I slot print_timing: id 0 | task 16170 | graphs reused = 15753 3.30.982.753 I slot print_timing: id 0 | task 16170 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.982.781 I slot release: id 0 | task 16170 | stop processing: n_tokens = 508, truncated = 0 3.31.005.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 210896706 3.31.005.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 3.31.029.517 I slot launch_slot_: id 0 | task 16323 | processing task, is_child = 0 3.32.684.831 I slot print_timing: id 0 | task 16323 | prompt eval time = 84.15 ms / 332 tokens ( 0.25 ms per token, 3945.24 tokens per second) 3.32.684.837 I slot print_timing: id 0 | task 16323 | eval time = 1571.15 ms / 143 tokens ( 11.06 ms per token, 90.38 tokens per second) 3.32.684.838 I slot print_timing: id 0 | task 16323 | total time = 1655.30 ms / 475 tokens 3.32.684.838 I slot print_timing: id 0 | task 16323 | graphs reused = 15894 3.32.684.839 I slot print_timing: id 0 | task 16323 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.684.866 I slot release: id 0 | task 16323 | stop processing: n_tokens = 499, truncated = 0 3.32.713.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 212598791 3.32.729.875 I slot launch_slot_: id 0 | task 16467 | processing task, is_child = 0 3.34.193.005 I slot print_timing: id 0 | task 16467 | prompt eval time = 90.47 ms / 354 tokens ( 0.26 ms per token, 3912.73 tokens per second) 3.34.193.010 I slot print_timing: id 0 | task 16467 | eval time = 1372.64 ms / 125 tokens ( 11.07 ms per token, 90.34 tokens per second) 3.34.193.011 I slot print_timing: id 0 | task 16467 | total time = 1463.12 ms / 479 tokens 3.34.193.012 I slot print_timing: id 0 | task 16467 | graphs reused = 16017 3.34.193.013 I slot print_timing: id 0 | task 16467 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.193.041 I slot release: id 0 | task 16467 | stop processing: n_tokens = 503, truncated = 0 3.34.220.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 214106966 3.34.220.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 3.34.243.963 I slot launch_slot_: id 0 | task 16593 | processing task, is_child = 0 3.37.335.462 I slot print_timing: id 0 | task 16593 | n_gen = 271, tg = 89.98 t/s, tg_3s = 90.31 t/s 3.40.341.277 I slot print_timing: id 0 | task 16593 | n_gen = 540, tg = 89.74 t/s, tg_3s = 89.49 t/s 3.43.349.231 I slot print_timing: id 0 | task 16593 | n_gen = 805, tg = 89.19 t/s, tg_3s = 88.10 t/s 3.45.841.763 I slot print_timing: id 0 | task 16593 | prompt eval time = 90.75 ms / 354 tokens ( 0.26 ms per token, 3900.78 tokens per second) 3.45.841.769 I slot print_timing: id 0 | task 16593 | eval time = 11507.04 ms / 1024 tokens ( 11.25 ms per token, 88.90 tokens per second) 3.45.841.770 I slot print_timing: id 0 | task 16593 | total time = 11597.79 ms / 1378 tokens 3.45.841.771 I slot print_timing: id 0 | task 16593 | graphs reused = 17035 3.45.841.771 I slot print_timing: id 0 | task 16593 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.841.803 I slot release: id 0 | task 16593 | stop processing: n_tokens = 1402, truncated = 0 3.45.846.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 225755728 3.45.846.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 3.45.854.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 3.45.904.834 I slot launch_slot_: id 0 | task 17618 | processing task, is_child = 0 3.46.507.286 I slot print_timing: id 0 | task 17618 | prompt eval time = 89.79 ms / 339 tokens ( 0.26 ms per token, 3775.52 tokens per second) 3.46.507.292 I slot print_timing: id 0 | task 17618 | eval time = 512.65 ms / 47 tokens ( 11.14 ms per token, 89.73 tokens per second) 3.46.507.293 I slot print_timing: id 0 | task 17618 | total time = 602.44 ms / 386 tokens 3.46.507.294 I slot print_timing: id 0 | task 17618 | graphs reused = 17080 3.46.507.295 I slot print_timing: id 0 | task 17618 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.507.322 I slot release: id 0 | task 17618 | stop processing: n_tokens = 410, truncated = 0 3.46.527.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 226421247 3.46.527.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.759 MiB) 3.46.547.897 I slot launch_slot_: id 0 | task 17666 | processing task, is_child = 0 3.49.641.346 I slot print_timing: id 0 | task 17666 | n_gen = 271, tg = 89.90 t/s, tg_3s = 90.24 t/s 3.49.997.722 I slot print_timing: id 0 | task 17666 | prompt eval time = 90.19 ms / 351 tokens ( 0.26 ms per token, 3891.61 tokens per second) 3.49.997.727 I slot print_timing: id 0 | task 17666 | eval time = 3359.61 ms / 303 tokens ( 11.12 ms per token, 89.89 tokens per second) 3.49.997.728 I slot print_timing: id 0 | task 17666 | total time = 3449.81 ms / 654 tokens 3.49.997.729 I slot print_timing: id 0 | task 17666 | graphs reused = 17380 3.49.997.730 I slot print_timing: id 0 | task 17666 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.997.761 I slot release: id 0 | task 17666 | stop processing: n_tokens = 678, truncated = 0 3.50.019.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 229911685 3.50.019.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 3.50.047.503 I slot launch_slot_: id 0 | task 17970 | processing task, is_child = 0 3.51.725.840 I slot print_timing: id 0 | task 17970 | prompt eval time = 83.80 ms / 325 tokens ( 0.26 ms per token, 3878.10 tokens per second) 3.51.725.848 I slot print_timing: id 0 | task 17970 | eval time = 1594.52 ms / 145 tokens ( 11.07 ms per token, 90.31 tokens per second) 3.51.725.849 I slot print_timing: id 0 | task 17970 | total time = 1678.32 ms / 470 tokens 3.51.725.850 I slot print_timing: id 0 | task 17970 | graphs reused = 17523 3.51.725.851 I slot print_timing: id 0 | task 17970 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.725.883 I slot release: id 0 | task 17970 | stop processing: n_tokens = 494, truncated = 0 3.51.748.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 231639808 3.51.764.932 I slot launch_slot_: id 0 | task 18116 | processing task, is_child = 0 3.52.468.803 I slot print_timing: id 0 | task 18116 | prompt eval time = 83.09 ms / 308 tokens ( 0.27 ms per token, 3706.91 tokens per second) 3.52.468.809 I slot print_timing: id 0 | task 18116 | eval time = 620.77 ms / 56 tokens ( 11.29 ms per token, 88.60 tokens per second) 3.52.468.810 I slot print_timing: id 0 | task 18116 | total time = 703.85 ms / 364 tokens 3.52.468.810 I slot print_timing: id 0 | task 18116 | graphs reused = 17577 3.52.468.811 I slot print_timing: id 0 | task 18116 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.468.839 I slot release: id 0 | task 18116 | stop processing: n_tokens = 388, truncated = 0 3.52.485.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 232382764 3.52.486.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 3.52.507.032 I slot launch_slot_: id 0 | task 18173 | processing task, is_child = 0 3.55.499.849 I slot print_timing: id 0 | task 18173 | prompt eval time = 90.82 ms / 349 tokens ( 0.26 ms per token, 3842.89 tokens per second) 3.55.499.854 I slot print_timing: id 0 | task 18173 | eval time = 2901.98 ms / 262 tokens ( 11.12 ms per token, 89.94 tokens per second) 3.55.499.855 I slot print_timing: id 0 | task 18173 | total time = 2992.80 ms / 611 tokens 3.55.499.856 I slot print_timing: id 0 | task 18173 | graphs reused = 17836 3.55.499.857 I slot print_timing: id 0 | task 18173 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.499.886 I slot release: id 0 | task 18173 | stop processing: n_tokens = 635, truncated = 0 3.55.525.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 235413811 3.55.526.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 143.918 MiB) 3.55.556.199 I slot launch_slot_: id 0 | task 18436 | processing task, is_child = 0 3.58.650.128 I slot print_timing: id 0 | task 18436 | n_gen = 270, tg = 89.55 t/s, tg_3s = 89.88 t/s 3.58.983.691 I slot print_timing: id 0 | task 18436 | prompt eval time = 90.06 ms / 371 tokens ( 0.24 ms per token, 4119.25 tokens per second) 3.58.983.697 I slot print_timing: id 0 | task 18436 | eval time = 3337.41 ms / 300 tokens ( 11.16 ms per token, 89.59 tokens per second) 3.58.983.698 I slot print_timing: id 0 | task 18436 | total time = 3427.47 ms / 671 tokens 3.58.983.699 I slot print_timing: id 0 | task 18436 | graphs reused = 18133 3.58.983.699 I slot print_timing: id 0 | task 18436 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.983.728 I slot release: id 0 | task 18436 | stop processing: n_tokens = 700, truncated = 0 3.59.003.339 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 700, t_last = 238897653 3.59.025.451 I slot launch_slot_: id 0 | task 18737 | processing task, is_child = 0 4.00.414.837 I slot print_timing: id 0 | task 18737 | prompt eval time = 82.99 ms / 303 tokens ( 0.27 ms per token, 3650.87 tokens per second) 4.00.414.843 I slot print_timing: id 0 | task 18737 | eval time = 1306.38 ms / 119 tokens ( 11.07 ms per token, 90.33 tokens per second) 4.00.414.844 I slot print_timing: id 0 | task 18737 | total time = 1389.37 ms / 422 tokens 4.00.414.845 I slot print_timing: id 0 | task 18737 | graphs reused = 18250 4.00.414.846 I slot print_timing: id 0 | task 18737 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.414.872 I slot release: id 0 | task 18737 | stop processing: n_tokens = 446, truncated = 0 4.00.438.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 240328797 4.00.438.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.039 MiB) 4.00.458.584 I slot launch_slot_: id 0 | task 18857 | processing task, is_child = 0 4.02.713.619 I slot print_timing: id 0 | task 18857 | prompt eval time = 83.45 ms / 312 tokens ( 0.27 ms per token, 3738.90 tokens per second) 4.02.713.624 I slot print_timing: id 0 | task 18857 | eval time = 2171.57 ms / 197 tokens ( 11.08 ms per token, 90.26 tokens per second) 4.02.713.626 I slot print_timing: id 0 | task 18857 | total time = 2255.02 ms / 509 tokens 4.02.713.626 I slot print_timing: id 0 | task 18857 | graphs reused = 18444 4.02.713.628 I slot print_timing: id 0 | task 18857 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.713.655 I slot release: id 0 | task 18857 | stop processing: n_tokens = 533, truncated = 0 4.02.738.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 242627580 4.02.738.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 4.02.760.693 I slot launch_slot_: id 0 | task 19055 | processing task, is_child = 0 4.04.982.072 I slot print_timing: id 0 | task 19055 | prompt eval time = 83.01 ms / 311 tokens ( 0.27 ms per token, 3746.36 tokens per second) 4.04.982.079 I slot print_timing: id 0 | task 19055 | eval time = 2138.35 ms / 194 tokens ( 11.08 ms per token, 90.26 tokens per second) 4.04.982.080 I slot print_timing: id 0 | task 19055 | total time = 2221.37 ms / 505 tokens 4.04.982.081 I slot print_timing: id 0 | task 19055 | graphs reused = 18635 4.04.982.083 I slot print_timing: id 0 | task 19055 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.982.109 I slot release: id 0 | task 19055 | stop processing: n_tokens = 529, truncated = 0 4.05.010.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 244896034 4.05.010.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 4.05.031.263 I slot launch_slot_: id 0 | task 19250 | processing task, is_child = 0 4.08.124.272 I slot print_timing: id 0 | task 19250 | n_gen = 272, tg = 90.07 t/s, tg_3s = 90.40 t/s 4.09.437.405 I slot print_timing: id 0 | task 19250 | prompt eval time = 84.16 ms / 331 tokens ( 0.25 ms per token, 3933.03 tokens per second) 4.09.437.410 I slot print_timing: id 0 | task 19250 | eval time = 4321.97 ms / 390 tokens ( 11.11 ms per token, 90.01 tokens per second) 4.09.437.411 I slot print_timing: id 0 | task 19250 | total time = 4406.13 ms / 721 tokens 4.09.437.412 I slot print_timing: id 0 | task 19250 | graphs reused = 19022 4.09.437.413 I slot print_timing: id 0 | task 19250 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.437.439 I slot release: id 0 | task 19250 | stop processing: n_tokens = 745, truncated = 0 4.09.462.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 745, t_last = 249351364 4.09.462.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 4.09.466.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 4.09.494.718 I slot launch_slot_: id 0 | task 19641 | processing task, is_child = 0 4.12.588.102 I slot print_timing: id 0 | task 19641 | n_gen = 272, tg = 90.05 t/s, tg_3s = 90.38 t/s 4.15.591.916 I slot print_timing: id 0 | task 19641 | n_gen = 541, tg = 89.80 t/s, tg_3s = 89.55 t/s 4.18.598.793 I slot print_timing: id 0 | task 19641 | n_gen = 808, tg = 89.47 t/s, tg_3s = 88.80 t/s 4.21.053.563 I slot print_timing: id 0 | task 19641 | prompt eval time = 83.91 ms / 335 tokens ( 0.25 ms per token, 3992.61 tokens per second) 4.21.053.568 I slot print_timing: id 0 | task 19641 | eval time = 11474.92 ms / 1024 tokens ( 11.22 ms per token, 89.15 tokens per second) 4.21.053.570 I slot print_timing: id 0 | task 19641 | total time = 11558.83 ms / 1359 tokens 4.21.053.571 I slot print_timing: id 0 | task 19641 | graphs reused = 20040 4.21.053.572 I slot print_timing: id 0 | task 19641 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.053.600 I slot release: id 0 | task 19641 | stop processing: n_tokens = 1383, truncated = 0 4.21.078.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 260967525 4.21.078.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 4.21.084.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 4.21.133.014 I slot launch_slot_: id 0 | task 20666 | processing task, is_child = 0 4.24.226.740 I slot print_timing: id 0 | task 20666 | n_gen = 272, tg = 90.04 t/s, tg_3s = 90.37 t/s 4.27.230.246 I slot print_timing: id 0 | task 20666 | n_gen = 541, tg = 89.80 t/s, tg_3s = 89.56 t/s 4.27.241.413 I slot print_timing: id 0 | task 20666 | prompt eval time = 83.88 ms / 331 tokens ( 0.25 ms per token, 3946.35 tokens per second) 4.27.241.417 I slot print_timing: id 0 | task 20666 | eval time = 6024.51 ms / 542 tokens ( 11.14 ms per token, 89.80 tokens per second) 4.27.241.418 I slot print_timing: id 0 | task 20666 | total time = 6108.39 ms / 873 tokens 4.27.241.419 I slot print_timing: id 0 | task 20666 | graphs reused = 20578 4.27.241.420 I slot print_timing: id 0 | task 20666 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.241.447 I slot release: id 0 | task 20666 | stop processing: n_tokens = 897, truncated = 0 4.27.268.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 267155372 4.27.268.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 4.27.272.230 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 4.27.311.297 I slot launch_slot_: id 0 | task 21209 | processing task, is_child = 0 4.28.920.971 I slot print_timing: id 0 | task 21209 | prompt eval time = 83.97 ms / 328 tokens ( 0.26 ms per token, 3905.92 tokens per second) 4.28.920.977 I slot print_timing: id 0 | task 21209 | eval time = 1525.68 ms / 139 tokens ( 11.06 ms per token, 90.45 tokens per second) 4.28.920.978 I slot print_timing: id 0 | task 21209 | total time = 1609.66 ms / 467 tokens 4.28.920.979 I slot print_timing: id 0 | task 21209 | graphs reused = 20715 4.28.920.980 I slot print_timing: id 0 | task 21209 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.921.005 I slot release: id 0 | task 21209 | stop processing: n_tokens = 491, truncated = 0 4.28.944.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 268834930 4.28.944.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 4.28.966.192 I slot launch_slot_: id 0 | task 21349 | processing task, is_child = 0 4.32.059.488 I slot print_timing: id 0 | task 21349 | n_gen = 272, tg = 90.05 t/s, tg_3s = 90.38 t/s 4.35.060.410 I slot print_timing: id 0 | task 21349 | n_gen = 541, tg = 89.84 t/s, tg_3s = 89.64 t/s 4.35.172.350 I slot print_timing: id 0 | task 21349 | prompt eval time = 83.84 ms / 331 tokens ( 0.25 ms per token, 3948.04 tokens per second) 4.35.172.355 I slot print_timing: id 0 | task 21349 | eval time = 6122.31 ms / 551 tokens ( 11.13 ms per token, 89.84 tokens per second) 4.35.172.356 I slot print_timing: id 0 | task 21349 | total time = 6206.14 ms / 882 tokens 4.35.172.357 I slot print_timing: id 0 | task 21349 | graphs reused = 21262 4.35.172.358 I slot print_timing: id 0 | task 21349 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.172.385 I slot release: id 0 | task 21349 | stop processing: n_tokens = 906, truncated = 0 4.35.190.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 906, t_last = 275086309 4.35.190.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 4.35.195.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 4.35.228.428 I slot launch_slot_: id 0 | task 21901 | processing task, is_child = 0 4.35.908.027 I slot print_timing: id 0 | task 21901 | prompt eval time = 90.24 ms / 348 tokens ( 0.26 ms per token, 3856.43 tokens per second) 4.35.908.033 I slot print_timing: id 0 | task 21901 | eval time = 589.34 ms / 54 tokens ( 11.12 ms per token, 89.93 tokens per second) 4.35.908.034 I slot print_timing: id 0 | task 21901 | total time = 679.58 ms / 402 tokens 4.35.908.035 I slot print_timing: id 0 | task 21901 | graphs reused = 21314 4.35.908.036 I slot print_timing: id 0 | task 21901 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.908.065 I slot release: id 0 | task 21901 | stop processing: n_tokens = 426, truncated = 0 4.35.931.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 275821990 4.35.931.405 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 4.35.951.102 I slot launch_slot_: id 0 | task 21956 | processing task, is_child = 0 4.36.613.586 I slot print_timing: id 0 | task 21956 | prompt eval time = 84.09 ms / 332 tokens ( 0.25 ms per token, 3948.20 tokens per second) 4.36.613.596 I slot print_timing: id 0 | task 21956 | eval time = 578.38 ms / 53 tokens ( 11.12 ms per token, 89.91 tokens per second) 4.36.613.597 I slot print_timing: id 0 | task 21956 | total time = 662.47 ms / 385 tokens 4.36.613.598 I slot print_timing: id 0 | task 21956 | graphs reused = 21365 4.36.613.599 I slot print_timing: id 0 | task 21956 | graph reallocs = 0 / 0 (same size) / (changed size) 4.36.613.627 I slot release: id 0 | task 21956 | stop processing: n_tokens = 411, truncated = 0 4.36.633.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 276527551 4.36.633.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 4.36.652.618 I slot launch_slot_: id 0 | task 22010 | processing task, is_child = 0 4.38.081.652 I slot print_timing: id 0 | task 22010 | prompt eval time = 89.91 ms / 339 tokens ( 0.27 ms per token, 3770.40 tokens per second) 4.38.081.658 I slot print_timing: id 0 | task 22010 | eval time = 1339.11 ms / 122 tokens ( 11.07 ms per token, 90.36 tokens per second) 4.38.081.659 I slot print_timing: id 0 | task 22010 | total time = 1429.02 ms / 461 tokens 4.38.081.659 I slot print_timing: id 0 | task 22010 | graphs reused = 21485 4.38.081.660 I slot print_timing: id 0 | task 22010 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.081.688 I slot release: id 0 | task 22010 | stop processing: n_tokens = 485, truncated = 0 4.38.105.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 277995613 4.38.105.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 4.38.126.797 I slot launch_slot_: id 0 | task 22133 | processing task, is_child = 0 4.38.548.433 I slot print_timing: id 0 | task 22133 | prompt eval time = 89.97 ms / 343 tokens ( 0.26 ms per token, 3812.51 tokens per second) 4.38.548.440 I slot print_timing: id 0 | task 22133 | eval time = 331.65 ms / 30 tokens ( 11.44 ms per token, 87.44 tokens per second) 4.38.548.441 I slot print_timing: id 0 | task 22133 | total time = 421.62 ms / 373 tokens 4.38.548.442 I slot print_timing: id 0 | task 22133 | graphs reused = 21513 4.38.548.443 I slot print_timing: id 0 | task 22133 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.548.478 I slot release: id 0 | task 22133 | stop processing: n_tokens = 397, truncated = 0 4.38.568.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 278462403 4.38.568.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 4.38.587.795 I slot launch_slot_: id 0 | task 22164 | processing task, is_child = 0 4.39.580.566 I slot print_timing: id 0 | task 22164 | prompt eval time = 92.27 ms / 360 tokens ( 0.26 ms per token, 3901.80 tokens per second) 4.39.580.572 I slot print_timing: id 0 | task 22164 | eval time = 900.49 ms / 82 tokens ( 11.12 ms per token, 89.95 tokens per second) 4.39.580.573 I slot print_timing: id 0 | task 22164 | total time = 992.75 ms / 442 tokens 4.39.580.574 I slot print_timing: id 0 | task 22164 | graphs reused = 21593 4.39.580.575 I slot print_timing: id 0 | task 22164 | graph reallocs = 0 / 0 (same size) / (changed size) 4.39.580.605 I slot release: id 0 | task 22164 | stop processing: n_tokens = 466, truncated = 0 4.39.608.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 279494530 4.39.624.510 I slot launch_slot_: id 0 | task 22247 | processing task, is_child = 0 4.40.239.758 I slot print_timing: id 0 | task 22247 | prompt eval time = 89.95 ms / 341 tokens ( 0.26 ms per token, 3791.16 tokens per second) 4.40.239.764 I slot print_timing: id 0 | task 22247 | eval time = 525.29 ms / 48 tokens ( 11.18 ms per token, 89.47 tokens per second) 4.40.239.765 I slot print_timing: id 0 | task 22247 | total time = 615.23 ms / 389 tokens 4.40.239.766 I slot print_timing: id 0 | task 22247 | graphs reused = 21639 4.40.239.767 I slot print_timing: id 0 | task 22247 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.239.798 I slot release: id 0 | task 22247 | stop processing: n_tokens = 413, truncated = 0 4.40.265.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 280153723 4.40.265.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.694 MiB) 4.40.284.773 I slot launch_slot_: id 0 | task 22296 | processing task, is_child = 0 4.43.381.535 I slot print_timing: id 0 | task 22296 | n_gen = 270, tg = 89.48 t/s, tg_3s = 89.82 t/s 4.46.386.269 I slot print_timing: id 0 | task 22296 | n_gen = 539, tg = 89.50 t/s, tg_3s = 89.53 t/s 4.46.799.374 I slot print_timing: id 0 | task 22296 | prompt eval time = 90.63 ms / 358 tokens ( 0.25 ms per token, 3950.13 tokens per second) 4.46.799.379 I slot print_timing: id 0 | task 22296 | eval time = 6423.95 ms / 576 tokens ( 11.17 ms per token, 89.51 tokens per second) 4.46.799.380 I slot print_timing: id 0 | task 22296 | total time = 6514.59 ms / 934 tokens 4.46.799.381 I slot print_timing: id 0 | task 22296 | graphs reused = 22211 4.46.799.381 I slot print_timing: id 0 | task 22296 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.799.412 I slot release: id 0 | task 22296 | stop processing: n_tokens = 958, truncated = 0 4.46.826.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 958, t_last = 286713336 4.46.826.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.412 MiB) 4.46.831.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.694 MiB) 4.46.865.514 I slot launch_slot_: id 0 | task 22873 | processing task, is_child = 0 4.47.706.931 I slot print_timing: id 0 | task 22873 | prompt eval time = 90.53 ms / 358 tokens ( 0.25 ms per token, 3954.45 tokens per second) 4.47.706.939 I slot print_timing: id 0 | task 22873 | eval time = 750.87 ms / 67 tokens ( 11.38 ms per token, 87.90 tokens per second) 4.47.706.940 I slot print_timing: id 0 | task 22873 | total time = 841.40 ms / 425 tokens 4.47.706.942 I slot print_timing: id 0 | task 22873 | graphs reused = 22276 4.47.706.943 I slot print_timing: id 0 | task 22873 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.706.975 I slot release: id 0 | task 22873 | stop processing: n_tokens = 452, truncated = 0 4.47.711.190 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 287620900 4.47.711.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 4.47.730.679 I slot launch_slot_: id 0 | task 22941 | processing task, is_child = 0 4.49.167.197 I slot print_timing: id 0 | task 22941 | prompt eval time = 111.25 ms / 387 tokens ( 0.29 ms per token, 3478.50 tokens per second) 4.49.167.203 I slot print_timing: id 0 | task 22941 | eval time = 1325.25 ms / 120 tokens ( 11.14 ms per token, 89.79 tokens per second) 4.49.167.204 I slot print_timing: id 0 | task 22941 | total time = 1436.50 ms / 507 tokens 4.49.167.204 I slot print_timing: id 0 | task 22941 | graphs reused = 22393 4.49.167.205 I slot print_timing: id 0 | task 22941 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.167.234 I slot release: id 0 | task 22941 | stop processing: n_tokens = 531, truncated = 0 4.49.190.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 289081159 4.49.191.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.632 MiB) 4.49.213.960 I slot launch_slot_: id 0 | task 23062 | processing task, is_child = 0 4.49.982.287 I slot print_timing: id 0 | task 23062 | prompt eval time = 83.96 ms / 333 tokens ( 0.25 ms per token, 3966.17 tokens per second) 4.49.982.293 I slot print_timing: id 0 | task 23062 | eval time = 684.35 ms / 61 tokens ( 11.41 ms per token, 87.67 tokens per second) 4.49.982.294 I slot print_timing: id 0 | task 23062 | total time = 768.31 ms / 394 tokens 4.49.982.295 I slot print_timing: id 0 | task 23062 | graphs reused = 22452 4.49.982.296 I slot print_timing: id 0 | task 23062 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.982.323 I slot release: id 0 | task 23062 | stop processing: n_tokens = 418, truncated = 0