$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--mradermacher--Qwen3.5-9B-i1-GGUF\snapshots\c5044c600a7e15246d54d13e4532382bc44ef41b\Qwen3.5-9B.i1-Q4_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 0.00.096.935 I srv llama_server: initializing ... 0.00.096.942 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.097.062 I srv init_listene: The UI is disabled 0.00.097.064 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.097.151 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) 0.00.099.767 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--mradermacher--Qwen3.5-9B-i1-GGUF\snapshots\c5044c600a7e15246d54d13e4532382bc44ef41b\Qwen3.5-9B.i1-Q4_K_M.gguf' 0.02.769.439 I cmn init: llama threadpool init, n_threads = 8 0.02.848.602 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.853.254 I srv llama_server: model loaded 0.02.853.261 I srv llama_server: listening on http://127.0.0.1:8089 0.04.528.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.529.003 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.084.501 I slot print_timing: id 0 | task 0 | prompt eval time = 143.54 ms / 368 tokens ( 0.39 ms per token, 2563.76 tokens per second) 0.05.084.507 I slot print_timing: id 0 | task 0 | eval time = 411.94 ms / 41 tokens ( 10.30 ms per token, 97.10 tokens per second) 0.05.084.508 I slot print_timing: id 0 | task 0 | total time = 555.48 ms / 409 tokens 0.05.084.515 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.05.084.516 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.084.546 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.05.104.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 4989626 0.05.129.848 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.05.670.034 I slot print_timing: id 0 | task 44 | prompt eval time = 124.22 ms / 322 tokens ( 0.39 ms per token, 2592.18 tokens per second) 0.05.670.041 I slot print_timing: id 0 | task 44 | eval time = 415.94 ms / 42 tokens ( 10.14 ms per token, 98.57 tokens per second) 0.05.670.042 I slot print_timing: id 0 | task 44 | total time = 540.16 ms / 364 tokens 0.05.670.043 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.05.670.044 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.670.072 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.05.674.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5575152 0.05.707.270 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.06.249.547 I slot print_timing: id 0 | task 89 | prompt eval time = 126.12 ms / 365 tokens ( 0.35 ms per token, 2893.98 tokens per second) 0.06.249.552 I slot print_timing: id 0 | task 89 | eval time = 416.13 ms / 42 tokens ( 10.15 ms per token, 98.53 tokens per second) 0.06.249.553 I slot print_timing: id 0 | task 89 | total time = 542.26 ms / 407 tokens 0.06.249.554 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.06.249.555 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.249.583 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.06.253.494 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6154663 0.06.282.732 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.06.840.181 I slot print_timing: id 0 | task 134 | prompt eval time = 131.72 ms / 397 tokens ( 0.33 ms per token, 3013.88 tokens per second) 0.06.840.187 I slot print_timing: id 0 | task 134 | eval time = 425.70 ms / 43 tokens ( 10.14 ms per token, 98.66 tokens per second) 0.06.840.188 I slot print_timing: id 0 | task 134 | total time = 557.43 ms / 440 tokens 0.06.840.189 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.06.840.189 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.840.218 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.06.858.140 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.06.886.258 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.07.559.290 I slot print_timing: id 0 | task 180 | prompt eval time = 127.15 ms / 383 tokens ( 0.33 ms per token, 3012.19 tokens per second) 0.07.559.296 I slot print_timing: id 0 | task 180 | eval time = 545.86 ms / 55 tokens ( 10.11 ms per token, 98.93 tokens per second) 0.07.559.297 I slot print_timing: id 0 | task 180 | total time = 673.01 ms / 438 tokens 0.07.559.298 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.07.559.298 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.559.326 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.07.578.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7464406 0.07.605.612 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.08.294.386 I slot print_timing: id 0 | task 238 | prompt eval time = 137.75 ms / 372 tokens ( 0.37 ms per token, 2700.45 tokens per second) 0.08.294.393 I slot print_timing: id 0 | task 238 | eval time = 551.00 ms / 55 tokens ( 10.20 ms per token, 98.00 tokens per second) 0.08.294.394 I slot print_timing: id 0 | task 238 | total time = 688.75 ms / 427 tokens 0.08.294.395 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.08.294.396 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.294.427 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.08.298.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8199506 0.08.334.166 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 0.09.035.271 I slot print_timing: id 0 | task 296 | prompt eval time = 147.46 ms / 422 tokens ( 0.35 ms per token, 2861.81 tokens per second) 0.09.035.277 I slot print_timing: id 0 | task 296 | eval time = 553.62 ms / 55 tokens ( 10.25 ms per token, 97.54 tokens per second) 0.09.035.278 I slot print_timing: id 0 | task 296 | total time = 701.08 ms / 477 tokens 0.09.035.279 I slot print_timing: id 0 | task 296 | graphs reused = 320 0.09.035.280 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.035.312 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 0.09.049.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 8940392 0.09.086.343 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 0.09.968.617 I slot print_timing: id 0 | task 354 | prompt eval time = 151.54 ms / 470 tokens ( 0.32 ms per token, 3101.55 tokens per second) 0.09.968.623 I slot print_timing: id 0 | task 354 | eval time = 730.72 ms / 72 tokens ( 10.29 ms per token, 97.16 tokens per second) 0.09.968.624 I slot print_timing: id 0 | task 354 | total time = 882.25 ms / 542 tokens 0.09.968.625 I slot print_timing: id 0 | task 354 | graphs reused = 389 0.09.968.626 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.968.660 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 0.09.982.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 9873740 0.10.018.616 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 0.10.614.154 I slot print_timing: id 0 | task 429 | prompt eval time = 124.53 ms / 345 tokens ( 0.36 ms per token, 2770.37 tokens per second) 0.10.614.160 I slot print_timing: id 0 | task 429 | eval time = 470.99 ms / 47 tokens ( 10.24 ms per token, 97.67 tokens per second) 0.10.614.161 I slot print_timing: id 0 | task 429 | total time = 595.52 ms / 392 tokens 0.10.614.162 I slot print_timing: id 0 | task 429 | graphs reused = 434 0.10.614.163 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.614.192 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 0.10.617.868 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 10519271 0.10.652.463 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 0.11.191.673 I slot print_timing: id 0 | task 479 | prompt eval time = 126.96 ms / 364 tokens ( 0.35 ms per token, 2867.09 tokens per second) 0.11.191.679 I slot print_timing: id 0 | task 479 | eval time = 412.23 ms / 41 tokens ( 10.31 ms per token, 97.03 tokens per second) 0.11.191.680 I slot print_timing: id 0 | task 479 | total time = 539.19 ms / 405 tokens 0.11.191.681 I slot print_timing: id 0 | task 479 | graphs reused = 473 0.11.191.682 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.191.708 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 0.11.195.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 11096788 0.11.230.684 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 0.12.013.801 I slot print_timing: id 0 | task 523 | prompt eval time = 131.64 ms / 376 tokens ( 0.35 ms per token, 2856.23 tokens per second) 0.12.013.807 I slot print_timing: id 0 | task 523 | eval time = 651.46 ms / 62 tokens ( 10.68 ms per token, 93.64 tokens per second) 0.12.013.808 I slot print_timing: id 0 | task 523 | total time = 783.10 ms / 438 tokens 0.12.013.809 I slot print_timing: id 0 | task 523 | graphs reused = 533 0.12.013.810 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.013.839 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 0.12.033.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 11918918 0.12.069.289 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 0.12.668.670 I slot print_timing: id 0 | task 588 | prompt eval time = 132.86 ms / 412 tokens ( 0.32 ms per token, 3100.92 tokens per second) 0.12.668.676 I slot print_timing: id 0 | task 588 | eval time = 466.50 ms / 47 tokens ( 10.14 ms per token, 98.61 tokens per second) 0.12.668.677 I slot print_timing: id 0 | task 588 | total time = 599.36 ms / 459 tokens 0.12.668.678 I slot print_timing: id 0 | task 588 | graphs reused = 578 0.12.668.679 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.668.709 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 0.12.691.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 12573789 0.12.728.473 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 0.13.474.387 I slot print_timing: id 0 | task 638 | prompt eval time = 126.40 ms / 376 tokens ( 0.34 ms per token, 2974.71 tokens per second) 0.13.474.393 I slot print_timing: id 0 | task 638 | eval time = 619.49 ms / 62 tokens ( 10.16 ms per token, 98.47 tokens per second) 0.13.474.394 I slot print_timing: id 0 | task 638 | total time = 745.89 ms / 438 tokens 0.13.474.395 I slot print_timing: id 0 | task 638 | graphs reused = 638 0.13.474.396 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.474.424 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 0.13.499.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13379503 0.13.536.716 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 0.14.184.896 I slot print_timing: id 0 | task 703 | prompt eval time = 132.22 ms / 378 tokens ( 0.35 ms per token, 2858.89 tokens per second) 0.14.184.902 I slot print_timing: id 0 | task 703 | eval time = 515.94 ms / 52 tokens ( 10.12 ms per token, 98.85 tokens per second) 0.14.184.903 I slot print_timing: id 0 | task 703 | total time = 648.16 ms / 430 tokens 0.14.184.904 I slot print_timing: id 0 | task 703 | graphs reused = 688 0.14.184.904 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.184.933 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 0.14.203.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 14090013 0.14.240.118 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 0.14.983.246 I slot print_timing: id 0 | task 758 | prompt eval time = 135.20 ms / 367 tokens ( 0.37 ms per token, 2714.50 tokens per second) 0.14.983.252 I slot print_timing: id 0 | task 758 | eval time = 607.91 ms / 58 tokens ( 10.67 ms per token, 93.76 tokens per second) 0.14.983.253 I slot print_timing: id 0 | task 758 | total time = 743.11 ms / 425 tokens 0.14.983.254 I slot print_timing: id 0 | task 758 | graphs reused = 744 0.14.983.254 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.983.283 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 0.14.997.992 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 14888363 0.15.034.943 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.15.667.627 I slot print_timing: id 0 | task 819 | prompt eval time = 124.75 ms / 347 tokens ( 0.36 ms per token, 2781.61 tokens per second) 0.15.667.633 I slot print_timing: id 0 | task 819 | eval time = 507.92 ms / 51 tokens ( 10.16 ms per token, 98.44 tokens per second) 0.15.667.634 I slot print_timing: id 0 | task 819 | total time = 632.66 ms / 398 tokens 0.15.667.634 I slot print_timing: id 0 | task 819 | graphs reused = 793 0.15.667.635 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.667.662 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 0.15.687.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 15572742 0.15.722.955 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 0.16.255.637 I slot print_timing: id 0 | task 873 | prompt eval time = 126.61 ms / 369 tokens ( 0.34 ms per token, 2914.48 tokens per second) 0.16.255.643 I slot print_timing: id 0 | task 873 | eval time = 406.05 ms / 41 tokens ( 10.15 ms per token, 98.51 tokens per second) 0.16.255.644 I slot print_timing: id 0 | task 873 | total time = 532.66 ms / 410 tokens 0.16.255.645 I slot print_timing: id 0 | task 873 | graphs reused = 832 0.16.255.646 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.255.674 I slot release: id 0 | task 873 | stop processing: n_tokens = 409, truncated = 0 0.16.280.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 16160754 0.16.319.891 I slot launch_slot_: id 0 | task 917 | processing task, is_child = 0 0.16.850.179 I slot print_timing: id 0 | task 917 | prompt eval time = 123.88 ms / 352 tokens ( 0.35 ms per token, 2841.44 tokens per second) 0.16.850.185 I slot print_timing: id 0 | task 917 | eval time = 406.39 ms / 41 tokens ( 10.16 ms per token, 98.43 tokens per second) 0.16.850.186 I slot print_timing: id 0 | task 917 | total time = 530.27 ms / 393 tokens 0.16.850.187 I slot print_timing: id 0 | task 917 | graphs reused = 871 0.16.850.188 I slot print_timing: id 0 | task 917 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.850.215 I slot release: id 0 | task 917 | stop processing: n_tokens = 392, truncated = 0 0.16.875.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 16755295 0.16.913.344 I slot launch_slot_: id 0 | task 961 | processing task, is_child = 0 0.17.432.649 I slot print_timing: id 0 | task 961 | prompt eval time = 123.56 ms / 349 tokens ( 0.35 ms per token, 2824.65 tokens per second) 0.17.432.655 I slot print_timing: id 0 | task 961 | eval time = 395.73 ms / 40 tokens ( 10.15 ms per token, 98.55 tokens per second) 0.17.432.656 I slot print_timing: id 0 | task 961 | total time = 519.29 ms / 389 tokens 0.17.432.657 I slot print_timing: id 0 | task 961 | graphs reused = 909 0.17.432.657 I slot print_timing: id 0 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.432.684 I slot release: id 0 | task 961 | stop processing: n_tokens = 388, truncated = 0 0.17.451.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 17337764 0.17.488.202 I slot launch_slot_: id 0 | task 1004 | processing task, is_child = 0 0.18.283.384 I slot print_timing: id 0 | task 1004 | prompt eval time = 133.63 ms / 384 tokens ( 0.35 ms per token, 2873.58 tokens per second) 0.18.283.390 I slot print_timing: id 0 | task 1004 | eval time = 661.53 ms / 63 tokens ( 10.67 ms per token, 93.72 tokens per second) 0.18.283.391 I slot print_timing: id 0 | task 1004 | total time = 795.16 ms / 447 tokens 0.18.283.392 I slot print_timing: id 0 | task 1004 | graphs reused = 970 0.18.283.393 I slot print_timing: id 0 | task 1004 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.283.422 I slot release: id 0 | task 1004 | stop processing: n_tokens = 446, truncated = 0 0.18.304.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 18188502 0.18.341.250 I slot launch_slot_: id 0 | task 1070 | processing task, is_child = 0 0.18.999.579 I slot print_timing: id 0 | task 1070 | prompt eval time = 123.89 ms / 356 tokens ( 0.35 ms per token, 2873.49 tokens per second) 0.18.999.585 I slot print_timing: id 0 | task 1070 | eval time = 534.42 ms / 54 tokens ( 10.08 ms per token, 99.17 tokens per second) 0.18.999.586 I slot print_timing: id 0 | task 1070 | total time = 658.31 ms / 410 tokens 0.18.999.586 I slot print_timing: id 0 | task 1070 | graphs reused = 1022 0.18.999.587 I slot print_timing: id 0 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.999.614 I slot release: id 0 | task 1070 | stop processing: n_tokens = 409, truncated = 0 0.19.020.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 18904694 0.19.062.327 I slot launch_slot_: id 0 | task 1127 | processing task, is_child = 0 0.19.892.838 I slot print_timing: id 0 | task 1127 | prompt eval time = 134.43 ms / 410 tokens ( 0.33 ms per token, 3050.03 tokens per second) 0.19.892.844 I slot print_timing: id 0 | task 1127 | eval time = 696.07 ms / 70 tokens ( 10.09 ms per token, 99.13 tokens per second) 0.19.892.845 I slot print_timing: id 0 | task 1127 | total time = 830.49 ms / 480 tokens 0.19.892.846 I slot print_timing: id 0 | task 1127 | graphs reused = 1090 0.19.892.847 I slot print_timing: id 0 | task 1127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.892.879 I slot release: id 0 | task 1127 | stop processing: n_tokens = 479, truncated = 0 0.19.908.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 19797958 0.19.947.629 I slot launch_slot_: id 0 | task 1200 | processing task, is_child = 0 0.20.657.233 I slot print_timing: id 0 | task 1200 | prompt eval time = 131.29 ms / 385 tokens ( 0.34 ms per token, 2932.46 tokens per second) 0.20.657.238 I slot print_timing: id 0 | task 1200 | eval time = 578.29 ms / 58 tokens ( 10.15 ms per token, 98.57 tokens per second) 0.20.657.239 I slot print_timing: id 0 | task 1200 | total time = 709.58 ms / 443 tokens 0.20.657.240 I slot print_timing: id 0 | task 1200 | graphs reused = 1146 0.20.657.241 I slot print_timing: id 0 | task 1200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.657.269 I slot release: id 0 | task 1200 | stop processing: n_tokens = 442, truncated = 0 0.20.685.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 20562349 0.20.722.970 I slot launch_slot_: id 0 | task 1261 | processing task, is_child = 0 0.21.563.987 I slot print_timing: id 0 | task 1261 | prompt eval time = 134.13 ms / 395 tokens ( 0.34 ms per token, 2944.82 tokens per second) 0.21.563.993 I slot print_timing: id 0 | task 1261 | eval time = 706.86 ms / 71 tokens ( 10.10 ms per token, 99.03 tokens per second) 0.21.563.994 I slot print_timing: id 0 | task 1261 | total time = 841.00 ms / 466 tokens 0.21.563.994 I slot print_timing: id 0 | task 1261 | graphs reused = 1215 0.21.563.995 I slot print_timing: id 0 | task 1261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.564.027 I slot release: id 0 | task 1261 | stop processing: n_tokens = 465, truncated = 0 0.21.578.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 21469107 0.21.615.067 I slot launch_slot_: id 0 | task 1335 | processing task, is_child = 0 0.22.366.868 I slot print_timing: id 0 | task 1335 | prompt eval time = 134.78 ms / 430 tokens ( 0.31 ms per token, 3190.34 tokens per second) 0.22.366.874 I slot print_timing: id 0 | task 1335 | eval time = 617.00 ms / 62 tokens ( 10.11 ms per token, 98.87 tokens per second) 0.22.366.875 I slot print_timing: id 0 | task 1335 | total time = 751.78 ms / 492 tokens 0.22.366.876 I slot print_timing: id 0 | task 1335 | graphs reused = 1275 0.22.366.877 I slot print_timing: id 0 | task 1335 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.366.907 I slot release: id 0 | task 1335 | stop processing: n_tokens = 491, truncated = 0 0.22.370.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 22271987 0.22.417.530 I slot launch_slot_: id 0 | task 1400 | processing task, is_child = 0 0.23.174.963 I slot print_timing: id 0 | task 1400 | prompt eval time = 134.20 ms / 392 tokens ( 0.34 ms per token, 2921.06 tokens per second) 0.23.174.970 I slot print_timing: id 0 | task 1400 | eval time = 623.21 ms / 62 tokens ( 10.22 ms per token, 97.88 tokens per second) 0.23.174.971 I slot print_timing: id 0 | task 1400 | total time = 757.41 ms / 454 tokens 0.23.174.974 I slot print_timing: id 0 | task 1400 | graphs reused = 1335 0.23.174.975 I slot print_timing: id 0 | task 1400 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.175.007 I slot release: id 0 | task 1400 | stop processing: n_tokens = 453, truncated = 0 0.23.178.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 23080087 0.23.216.517 I slot launch_slot_: id 0 | task 1465 | processing task, is_child = 0 0.23.828.934 I slot print_timing: id 0 | task 1465 | prompt eval time = 125.68 ms / 350 tokens ( 0.36 ms per token, 2784.87 tokens per second) 0.23.828.939 I slot print_timing: id 0 | task 1465 | eval time = 486.72 ms / 49 tokens ( 10.14 ms per token, 98.62 tokens per second) 0.23.828.940 I slot print_timing: id 0 | task 1465 | total time = 612.39 ms / 399 tokens 0.23.828.941 I slot print_timing: id 0 | task 1465 | graphs reused = 1382 0.23.828.942 I slot print_timing: id 0 | task 1465 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.828.969 I slot release: id 0 | task 1465 | stop processing: n_tokens = 398, truncated = 0 0.23.846.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 23734049 0.23.886.401 I slot launch_slot_: id 0 | task 1517 | processing task, is_child = 0 0.24.622.972 I slot print_timing: id 0 | task 1517 | prompt eval time = 131.99 ms / 380 tokens ( 0.35 ms per token, 2879.05 tokens per second) 0.24.622.978 I slot print_timing: id 0 | task 1517 | eval time = 604.56 ms / 61 tokens ( 10.08 ms per token, 99.25 tokens per second) 0.24.622.980 I slot print_timing: id 0 | task 1517 | total time = 736.55 ms / 441 tokens 0.24.622.981 I slot print_timing: id 0 | task 1517 | graphs reused = 1441 0.24.622.982 I slot print_timing: id 0 | task 1517 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.623.011 I slot release: id 0 | task 1517 | stop processing: n_tokens = 440, truncated = 0 0.24.638.401 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 24528091 0.24.674.705 I slot launch_slot_: id 0 | task 1581 | processing task, is_child = 0 0.25.644.357 I slot print_timing: id 0 | task 1581 | prompt eval time = 140.03 ms / 410 tokens ( 0.34 ms per token, 2928.05 tokens per second) 0.25.644.363 I slot print_timing: id 0 | task 1581 | eval time = 829.60 ms / 80 tokens ( 10.50 ms per token, 95.23 tokens per second) 0.25.644.364 I slot print_timing: id 0 | task 1581 | total time = 969.63 ms / 490 tokens 0.25.644.365 I slot print_timing: id 0 | task 1581 | graphs reused = 1519 0.25.644.366 I slot print_timing: id 0 | task 1581 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.644.398 I slot release: id 0 | task 1581 | stop processing: n_tokens = 489, truncated = 0 0.25.667.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 25549478 0.25.706.057 I slot launch_slot_: id 0 | task 1664 | processing task, is_child = 0 0.26.511.934 I slot print_timing: id 0 | task 1664 | prompt eval time = 131.91 ms / 387 tokens ( 0.34 ms per token, 2933.73 tokens per second) 0.26.511.941 I slot print_timing: id 0 | task 1664 | eval time = 673.94 ms / 68 tokens ( 10.06 ms per token, 99.41 tokens per second) 0.26.511.942 I slot print_timing: id 0 | task 1664 | total time = 805.86 ms / 455 tokens 0.26.511.943 I slot print_timing: id 0 | task 1664 | graphs reused = 1585 0.26.511.944 I slot print_timing: id 0 | task 1664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.511.971 I slot release: id 0 | task 1664 | stop processing: n_tokens = 454, truncated = 0 0.26.539.528 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 26417051 0.26.575.877 I slot launch_slot_: id 0 | task 1735 | processing task, is_child = 0 0.27.283.558 I slot print_timing: id 0 | task 1735 | prompt eval time = 123.34 ms / 358 tokens ( 0.34 ms per token, 2902.59 tokens per second) 0.27.283.563 I slot print_timing: id 0 | task 1735 | eval time = 584.32 ms / 59 tokens ( 10.07 ms per token, 99.26 tokens per second) 0.27.283.564 I slot print_timing: id 0 | task 1735 | total time = 707.66 ms / 417 tokens 0.27.283.565 I slot print_timing: id 0 | task 1735 | graphs reused = 1642 0.27.283.566 I slot print_timing: id 0 | task 1735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.283.594 I slot release: id 0 | task 1735 | stop processing: n_tokens = 416, truncated = 0 0.27.302.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 27188674 0.27.354.500 I slot launch_slot_: id 0 | task 1797 | processing task, is_child = 0 0.28.083.238 I slot print_timing: id 0 | task 1797 | prompt eval time = 125.38 ms / 359 tokens ( 0.35 ms per token, 2863.34 tokens per second) 0.28.083.244 I slot print_timing: id 0 | task 1797 | eval time = 603.34 ms / 56 tokens ( 10.97 ms per token, 91.16 tokens per second) 0.28.083.246 I slot print_timing: id 0 | task 1797 | total time = 728.72 ms / 415 tokens 0.28.083.246 I slot print_timing: id 0 | task 1797 | graphs reused = 1696 0.28.083.247 I slot print_timing: id 0 | task 1797 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.083.275 I slot release: id 0 | task 1797 | stop processing: n_tokens = 414, truncated = 0 0.28.098.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 27988354 0.28.144.849 I slot launch_slot_: id 0 | task 1856 | processing task, is_child = 0 0.28.881.987 I slot print_timing: id 0 | task 1856 | prompt eval time = 131.11 ms / 387 tokens ( 0.34 ms per token, 2951.67 tokens per second) 0.28.881.993 I slot print_timing: id 0 | task 1856 | eval time = 606.01 ms / 61 tokens ( 10.10 ms per token, 99.01 tokens per second) 0.28.881.994 I slot print_timing: id 0 | task 1856 | total time = 737.12 ms / 448 tokens 0.28.881.995 I slot print_timing: id 0 | task 1856 | graphs reused = 1755 0.28.881.996 I slot print_timing: id 0 | task 1856 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.882.025 I slot release: id 0 | task 1856 | stop processing: n_tokens = 447, truncated = 0 0.28.907.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 28787105 0.28.956.939 I slot launch_slot_: id 0 | task 1920 | processing task, is_child = 0 0.29.723.691 I slot print_timing: id 0 | task 1920 | prompt eval time = 132.96 ms / 410 tokens ( 0.32 ms per token, 3083.73 tokens per second) 0.29.723.697 I slot print_timing: id 0 | task 1920 | eval time = 633.78 ms / 61 tokens ( 10.56 ms per token, 94.67 tokens per second) 0.29.723.698 I slot print_timing: id 0 | task 1920 | total time = 766.73 ms / 471 tokens 0.29.723.698 I slot print_timing: id 0 | task 1920 | graphs reused = 1814 0.29.723.699 I slot print_timing: id 0 | task 1920 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.723.730 I slot release: id 0 | task 1920 | stop processing: n_tokens = 470, truncated = 0 0.29.742.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 29628809 0.29.778.672 I slot launch_slot_: id 0 | task 1984 | processing task, is_child = 0 0.30.398.088 I slot print_timing: id 0 | task 1984 | prompt eval time = 123.55 ms / 351 tokens ( 0.35 ms per token, 2841.02 tokens per second) 0.30.398.094 I slot print_timing: id 0 | task 1984 | eval time = 495.85 ms / 50 tokens ( 10.12 ms per token, 98.82 tokens per second) 0.30.398.095 I slot print_timing: id 0 | task 1984 | total time = 619.40 ms / 401 tokens 0.30.398.096 I slot print_timing: id 0 | task 1984 | graphs reused = 1862 0.30.398.096 I slot print_timing: id 0 | task 1984 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.398.124 I slot release: id 0 | task 1984 | stop processing: n_tokens = 400, truncated = 0 0.30.426.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 30303204 0.30.462.626 I slot launch_slot_: id 0 | task 2037 | processing task, is_child = 0 0.32.841.616 I slot print_timing: id 0 | task 2037 | prompt eval time = 131.85 ms / 393 tokens ( 0.34 ms per token, 2980.66 tokens per second) 0.32.841.622 I slot print_timing: id 0 | task 2037 | eval time = 2247.12 ms / 224 tokens ( 10.08 ms per token, 99.24 tokens per second) 0.32.841.623 I slot print_timing: id 0 | task 2037 | total time = 2378.97 ms / 617 tokens 0.32.841.624 I slot print_timing: id 0 | task 2037 | graphs reused = 2083 0.32.841.625 I slot print_timing: id 0 | task 2037 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.841.654 I slot release: id 0 | task 2037 | stop processing: n_tokens = 616, truncated = 0 0.32.870.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 32746733 0.32.908.141 I slot launch_slot_: id 0 | task 2264 | processing task, is_child = 0 0.33.347.739 I slot print_timing: id 0 | task 2264 | prompt eval time = 123.90 ms / 321 tokens ( 0.39 ms per token, 2590.84 tokens per second) 0.33.347.745 I slot print_timing: id 0 | task 2264 | eval time = 315.68 ms / 32 tokens ( 10.18 ms per token, 98.20 tokens per second) 0.33.347.746 I slot print_timing: id 0 | task 2264 | total time = 439.58 ms / 353 tokens 0.33.347.747 I slot print_timing: id 0 | task 2264 | graphs reused = 2113 0.33.347.748 I slot print_timing: id 0 | task 2264 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.347.774 I slot release: id 0 | task 2264 | stop processing: n_tokens = 352, truncated = 0 0.33.366.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 33252854 0.33.407.454 I slot launch_slot_: id 0 | task 2299 | processing task, is_child = 0 0.34.086.409 I slot print_timing: id 0 | task 2299 | prompt eval time = 123.15 ms / 330 tokens ( 0.37 ms per token, 2679.57 tokens per second) 0.34.086.416 I slot print_timing: id 0 | task 2299 | eval time = 555.78 ms / 56 tokens ( 10.11 ms per token, 98.96 tokens per second) 0.34.086.417 I slot print_timing: id 0 | task 2299 | total time = 678.93 ms / 386 tokens 0.34.086.419 I slot print_timing: id 0 | task 2299 | graphs reused = 2167 0.34.086.419 I slot print_timing: id 0 | task 2299 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.086.450 I slot release: id 0 | task 2299 | stop processing: n_tokens = 385, truncated = 0 0.34.103.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 33991530 0.34.143.722 I slot launch_slot_: id 0 | task 2358 | processing task, is_child = 0 0.34.582.543 I slot print_timing: id 0 | task 2358 | prompt eval time = 123.71 ms / 341 tokens ( 0.36 ms per token, 2756.38 tokens per second) 0.34.582.550 I slot print_timing: id 0 | task 2358 | eval time = 315.09 ms / 32 tokens ( 10.16 ms per token, 98.39 tokens per second) 0.34.582.551 I slot print_timing: id 0 | task 2358 | total time = 438.80 ms / 373 tokens 0.34.582.551 I slot print_timing: id 0 | task 2358 | graphs reused = 2197 0.34.582.552 I slot print_timing: id 0 | task 2358 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.582.580 I slot release: id 0 | task 2358 | stop processing: n_tokens = 372, truncated = 0 0.34.600.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 34487660 0.34.636.759 I slot launch_slot_: id 0 | task 2393 | processing task, is_child = 0 0.35.236.437 I slot print_timing: id 0 | task 2393 | prompt eval time = 123.67 ms / 338 tokens ( 0.37 ms per token, 2732.99 tokens per second) 0.35.236.443 I slot print_timing: id 0 | task 2393 | eval time = 475.98 ms / 48 tokens ( 10.13 ms per token, 98.74 tokens per second) 0.35.236.444 I slot print_timing: id 0 | task 2393 | total time = 599.66 ms / 386 tokens 0.35.236.445 I slot print_timing: id 0 | task 2393 | graphs reused = 2243 0.35.236.446 I slot print_timing: id 0 | task 2393 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.236.473 I slot release: id 0 | task 2393 | stop processing: n_tokens = 385, truncated = 0 0.35.256.182 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 35141553 0.35.292.766 I slot launch_slot_: id 0 | task 2444 | processing task, is_child = 0 0.35.983.484 I slot print_timing: id 0 | task 2444 | prompt eval time = 134.90 ms / 395 tokens ( 0.34 ms per token, 2928.16 tokens per second) 0.35.983.490 I slot print_timing: id 0 | task 2444 | eval time = 555.80 ms / 56 tokens ( 10.11 ms per token, 98.96 tokens per second) 0.35.983.490 I slot print_timing: id 0 | task 2444 | total time = 690.70 ms / 451 tokens 0.35.983.491 I slot print_timing: id 0 | task 2444 | graphs reused = 2297 0.35.983.492 I slot print_timing: id 0 | task 2444 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.983.522 I slot release: id 0 | task 2444 | stop processing: n_tokens = 450, truncated = 0 0.36.004.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 35888601 0.36.041.099 I slot launch_slot_: id 0 | task 2503 | processing task, is_child = 0 0.37.051.968 I slot print_timing: id 0 | task 2503 | prompt eval time = 183.12 ms / 528 tokens ( 0.35 ms per token, 2883.29 tokens per second) 0.37.051.973 I slot print_timing: id 0 | task 2503 | eval time = 827.72 ms / 83 tokens ( 10.09 ms per token, 99.07 tokens per second) 0.37.051.975 I slot print_timing: id 0 | task 2503 | total time = 1010.85 ms / 611 tokens 0.37.051.976 I slot print_timing: id 0 | task 2503 | graphs reused = 2378 0.37.051.976 I slot print_timing: id 0 | task 2503 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.052.010 I slot release: id 0 | task 2503 | stop processing: n_tokens = 610, truncated = 0 0.37.080.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 36957089 0.37.148.953 I slot launch_slot_: id 0 | task 2590 | processing task, is_child = 0 0.37.746.304 I slot print_timing: id 0 | task 2590 | prompt eval time = 151.67 ms / 331 tokens ( 0.46 ms per token, 2182.31 tokens per second) 0.37.746.310 I slot print_timing: id 0 | task 2590 | eval time = 445.66 ms / 45 tokens ( 10.13 ms per token, 98.73 tokens per second) 0.37.746.311 I slot print_timing: id 0 | task 2590 | total time = 597.33 ms / 376 tokens 0.37.746.312 I slot print_timing: id 0 | task 2590 | graphs reused = 2421 0.37.746.313 I slot print_timing: id 0 | task 2590 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.746.341 I slot release: id 0 | task 2590 | stop processing: n_tokens = 387, truncated = 0 0.37.771.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 37651421 0.37.829.716 I slot launch_slot_: id 0 | task 2638 | processing task, is_child = 0 0.38.516.314 I slot print_timing: id 0 | task 2638 | prompt eval time = 160.98 ms / 362 tokens ( 0.44 ms per token, 2248.75 tokens per second) 0.38.516.320 I slot print_timing: id 0 | task 2638 | eval time = 525.60 ms / 53 tokens ( 10.11 ms per token, 98.93 tokens per second) 0.38.516.321 I slot print_timing: id 0 | task 2638 | total time = 686.58 ms / 415 tokens 0.38.516.323 I slot print_timing: id 0 | task 2638 | graphs reused = 2472 0.38.516.324 I slot print_timing: id 0 | task 2638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.516.352 I slot release: id 0 | task 2638 | stop processing: n_tokens = 426, truncated = 0 0.38.535.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 38421432 0.38.589.490 I slot launch_slot_: id 0 | task 2694 | processing task, is_child = 0 0.39.435.332 I slot print_timing: id 0 | task 2694 | prompt eval time = 159.49 ms / 419 tokens ( 0.38 ms per token, 2627.17 tokens per second) 0.39.435.338 I slot print_timing: id 0 | task 2694 | eval time = 686.34 ms / 69 tokens ( 10.09 ms per token, 99.08 tokens per second) 0.39.435.339 I slot print_timing: id 0 | task 2694 | total time = 845.82 ms / 488 tokens 0.39.435.340 I slot print_timing: id 0 | task 2694 | graphs reused = 2539 0.39.435.341 I slot print_timing: id 0 | task 2694 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.435.370 I slot release: id 0 | task 2694 | stop processing: n_tokens = 499, truncated = 0 0.39.453.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 39340450 0.39.502.178 I slot launch_slot_: id 0 | task 2766 | processing task, is_child = 0 0.40.108.138 I slot print_timing: id 0 | task 2766 | prompt eval time = 170.54 ms / 423 tokens ( 0.40 ms per token, 2480.30 tokens per second) 0.40.108.144 I slot print_timing: id 0 | task 2766 | eval time = 435.39 ms / 44 tokens ( 10.13 ms per token, 98.76 tokens per second) 0.40.108.145 I slot print_timing: id 0 | task 2766 | total time = 605.94 ms / 467 tokens 0.40.108.145 I slot print_timing: id 0 | task 2766 | graphs reused = 2581 0.40.108.146 I slot print_timing: id 0 | task 2766 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.108.179 I slot release: id 0 | task 2766 | stop processing: n_tokens = 478, truncated = 0 0.40.127.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 40013259 0.40.173.568 I slot launch_slot_: id 0 | task 2813 | processing task, is_child = 0 0.40.750.680 I slot print_timing: id 0 | task 2813 | prompt eval time = 147.87 ms / 341 tokens ( 0.43 ms per token, 2306.08 tokens per second) 0.40.750.687 I slot print_timing: id 0 | task 2813 | eval time = 429.22 ms / 43 tokens ( 10.22 ms per token, 97.85 tokens per second) 0.40.750.688 I slot print_timing: id 0 | task 2813 | total time = 577.09 ms / 384 tokens 0.40.750.688 I slot print_timing: id 0 | task 2813 | graphs reused = 2622 0.40.750.689 I slot print_timing: id 0 | task 2813 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.750.720 I slot release: id 0 | task 2813 | stop processing: n_tokens = 395, truncated = 0 0.40.767.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 40655800 0.40.812.569 I slot launch_slot_: id 0 | task 2859 | processing task, is_child = 0 0.41.444.329 I slot print_timing: id 0 | task 2859 | prompt eval time = 165.82 ms / 356 tokens ( 0.47 ms per token, 2146.95 tokens per second) 0.41.444.335 I slot print_timing: id 0 | task 2859 | eval time = 465.92 ms / 47 tokens ( 10.13 ms per token, 98.73 tokens per second) 0.41.444.336 I slot print_timing: id 0 | task 2859 | total time = 631.74 ms / 403 tokens 0.41.444.338 I slot print_timing: id 0 | task 2859 | graphs reused = 2667 0.41.444.338 I slot print_timing: id 0 | task 2859 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.444.368 I slot release: id 0 | task 2859 | stop processing: n_tokens = 414, truncated = 0 0.41.471.677 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 41349448 0.41.471.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.511 MiB) 0.41.531.100 I slot launch_slot_: id 0 | task 2909 | processing task, is_child = 0 0.42.159.781 I slot print_timing: id 0 | task 2909 | prompt eval time = 167.86 ms / 362 tokens ( 0.46 ms per token, 2156.53 tokens per second) 0.42.159.787 I slot print_timing: id 0 | task 2909 | eval time = 460.80 ms / 46 tokens ( 10.24 ms per token, 97.66 tokens per second) 0.42.159.788 I slot print_timing: id 0 | task 2909 | total time = 628.66 ms / 408 tokens 0.42.159.789 I slot print_timing: id 0 | task 2909 | graphs reused = 2711 0.42.159.789 I slot print_timing: id 0 | task 2909 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.159.819 I slot release: id 0 | task 2909 | stop processing: n_tokens = 419, truncated = 0 0.42.176.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 42064898 0.42.176.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.42.239.524 I slot launch_slot_: id 0 | task 2958 | processing task, is_child = 0 0.43.081.594 I slot print_timing: id 0 | task 2958 | prompt eval time = 158.46 ms / 391 tokens ( 0.41 ms per token, 2467.56 tokens per second) 0.43.081.600 I slot print_timing: id 0 | task 2958 | eval time = 683.59 ms / 68 tokens ( 10.20 ms per token, 98.01 tokens per second) 0.43.081.601 I slot print_timing: id 0 | task 2958 | total time = 842.05 ms / 459 tokens 0.43.081.601 I slot print_timing: id 0 | task 2958 | graphs reused = 2777 0.43.081.604 I slot print_timing: id 0 | task 2958 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.081.635 I slot release: id 0 | task 2958 | stop processing: n_tokens = 470, truncated = 0 0.43.097.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 42986715 0.43.097.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.43.157.697 I slot launch_slot_: id 0 | task 3029 | processing task, is_child = 0 0.43.851.554 I slot print_timing: id 0 | task 3029 | prompt eval time = 156.55 ms / 343 tokens ( 0.46 ms per token, 2191.01 tokens per second) 0.43.851.559 I slot print_timing: id 0 | task 3029 | eval time = 537.28 ms / 54 tokens ( 10.14 ms per token, 98.64 tokens per second) 0.43.851.560 I slot print_timing: id 0 | task 3029 | total time = 693.83 ms / 397 tokens 0.43.851.561 I slot print_timing: id 0 | task 3029 | graphs reused = 2829 0.43.851.562 I slot print_timing: id 0 | task 3029 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.851.589 I slot release: id 0 | task 3029 | stop processing: n_tokens = 408, truncated = 0 0.43.874.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 43756669 0.43.874.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.43.884.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.43.950.735 I slot launch_slot_: id 0 | task 3086 | processing task, is_child = 0 0.44.564.634 I slot print_timing: id 0 | task 3086 | prompt eval time = 157.45 ms / 401 tokens ( 0.39 ms per token, 2546.79 tokens per second) 0.44.564.640 I slot print_timing: id 0 | task 3086 | eval time = 456.43 ms / 46 tokens ( 10.14 ms per token, 98.59 tokens per second) 0.44.564.641 I slot print_timing: id 0 | task 3086 | total time = 613.88 ms / 447 tokens 0.44.564.642 I slot print_timing: id 0 | task 3086 | graphs reused = 2873 0.44.564.643 I slot print_timing: id 0 | task 3086 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.564.674 I slot release: id 0 | task 3086 | stop processing: n_tokens = 458, truncated = 0 0.44.592.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 44469754 0.44.592.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.44.642.358 I slot launch_slot_: id 0 | task 3135 | processing task, is_child = 0 0.45.470.693 I slot print_timing: id 0 | task 3135 | prompt eval time = 146.76 ms / 355 tokens ( 0.41 ms per token, 2418.83 tokens per second) 0.45.470.698 I slot print_timing: id 0 | task 3135 | eval time = 681.55 ms / 68 tokens ( 10.17 ms per token, 98.31 tokens per second) 0.45.470.700 I slot print_timing: id 0 | task 3135 | total time = 828.31 ms / 423 tokens 0.45.470.701 I slot print_timing: id 0 | task 3135 | graphs reused = 2939 0.45.470.702 I slot print_timing: id 0 | task 3135 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.470.730 I slot release: id 0 | task 3135 | stop processing: n_tokens = 434, truncated = 0 0.45.491.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 45375809 0.45.491.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.45.539.708 I slot launch_slot_: id 0 | task 3206 | processing task, is_child = 0 0.46.286.494 I slot print_timing: id 0 | task 3206 | prompt eval time = 148.27 ms / 351 tokens ( 0.42 ms per token, 2367.29 tokens per second) 0.46.286.500 I slot print_timing: id 0 | task 3206 | eval time = 598.50 ms / 57 tokens ( 10.69 ms per token, 93.57 tokens per second) 0.46.286.501 I slot print_timing: id 0 | task 3206 | total time = 746.77 ms / 408 tokens 0.46.286.501 I slot print_timing: id 0 | task 3206 | graphs reused = 2994 0.46.286.502 I slot print_timing: id 0 | task 3206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.286.532 I slot release: id 0 | task 3206 | stop processing: n_tokens = 419, truncated = 0 0.46.304.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 46191611 0.46.304.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.46.311.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.46.354.586 I slot launch_slot_: id 0 | task 3266 | processing task, is_child = 0 0.47.451.102 I slot print_timing: id 0 | task 3266 | prompt eval time = 169.03 ms / 475 tokens ( 0.36 ms per token, 2810.22 tokens per second) 0.47.451.108 I slot print_timing: id 0 | task 3266 | eval time = 927.47 ms / 93 tokens ( 10.08 ms per token, 99.19 tokens per second) 0.47.451.109 I slot print_timing: id 0 | task 3266 | total time = 1096.50 ms / 568 tokens 0.47.451.112 I slot print_timing: id 0 | task 3266 | graphs reused = 3084 0.47.451.113 I slot print_timing: id 0 | task 3266 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.451.145 I slot release: id 0 | task 3266 | stop processing: n_tokens = 579, truncated = 0 0.47.474.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 47356225 0.47.474.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.47.515.419 I slot launch_slot_: id 0 | task 3362 | processing task, is_child = 0 0.48.735.984 I slot print_timing: id 0 | task 3362 | prompt eval time = 164.10 ms / 440 tokens ( 0.37 ms per token, 2681.34 tokens per second) 0.48.735.989 I slot print_timing: id 0 | task 3362 | eval time = 1056.45 ms / 106 tokens ( 10.06 ms per token, 99.39 tokens per second) 0.48.735.990 I slot print_timing: id 0 | task 3362 | total time = 1220.55 ms / 546 tokens 0.48.735.991 I slot print_timing: id 0 | task 3362 | graphs reused = 3187 0.48.735.992 I slot print_timing: id 0 | task 3362 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.736.023 I slot release: id 0 | task 3362 | stop processing: n_tokens = 557, truncated = 0 0.48.754.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 48641103 0.48.754.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.48.794.706 I slot launch_slot_: id 0 | task 3471 | processing task, is_child = 0 0.49.490.939 I slot print_timing: id 0 | task 3471 | prompt eval time = 146.03 ms / 345 tokens ( 0.42 ms per token, 2362.51 tokens per second) 0.49.490.947 I slot print_timing: id 0 | task 3471 | eval time = 550.18 ms / 55 tokens ( 10.19 ms per token, 98.15 tokens per second) 0.49.490.948 I slot print_timing: id 0 | task 3471 | total time = 696.21 ms / 400 tokens 0.49.490.949 I slot print_timing: id 0 | task 3471 | graphs reused = 3240 0.49.490.950 I slot print_timing: id 0 | task 3471 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.490.988 I slot release: id 0 | task 3471 | stop processing: n_tokens = 411, truncated = 0 0.49.518.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 49396067 0.49.518.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.49.526.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.49.585.274 I slot launch_slot_: id 0 | task 3529 | processing task, is_child = 0 0.50.285.641 I slot print_timing: id 0 | task 3529 | prompt eval time = 152.78 ms / 382 tokens ( 0.40 ms per token, 2500.34 tokens per second) 0.50.285.647 I slot print_timing: id 0 | task 3529 | eval time = 547.57 ms / 55 tokens ( 10.14 ms per token, 98.62 tokens per second) 0.50.285.648 I slot print_timing: id 0 | task 3529 | total time = 700.35 ms / 437 tokens 0.50.285.648 I slot print_timing: id 0 | task 3529 | graphs reused = 3293 0.50.285.650 I slot print_timing: id 0 | task 3529 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.285.680 I slot release: id 0 | task 3529 | stop processing: n_tokens = 448, truncated = 0 0.50.299.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 50190760 0.50.300.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.50.342.685 I slot launch_slot_: id 0 | task 3587 | processing task, is_child = 0 0.50.932.874 I slot print_timing: id 0 | task 3587 | prompt eval time = 143.21 ms / 337 tokens ( 0.42 ms per token, 2353.15 tokens per second) 0.50.932.879 I slot print_timing: id 0 | task 3587 | eval time = 446.95 ms / 45 tokens ( 10.16 ms per token, 98.45 tokens per second) 0.50.932.880 I slot print_timing: id 0 | task 3587 | total time = 590.16 ms / 382 tokens 0.50.932.881 I slot print_timing: id 0 | task 3587 | graphs reused = 3336 0.50.932.882 I slot print_timing: id 0 | task 3587 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.932.910 I slot release: id 0 | task 3587 | stop processing: n_tokens = 393, truncated = 0 0.50.958.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 50837990 0.50.958.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.51.014.546 I slot launch_slot_: id 0 | task 3635 | processing task, is_child = 0 0.51.910.427 I slot print_timing: id 0 | task 3635 | prompt eval time = 154.76 ms / 402 tokens ( 0.38 ms per token, 2597.64 tokens per second) 0.51.910.432 I slot print_timing: id 0 | task 3635 | eval time = 741.10 ms / 70 tokens ( 10.74 ms per token, 93.10 tokens per second) 0.51.910.433 I slot print_timing: id 0 | task 3635 | total time = 895.86 ms / 472 tokens 0.51.910.434 I slot print_timing: id 0 | task 3635 | graphs reused = 3404 0.51.910.435 I slot print_timing: id 0 | task 3635 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.910.465 I slot release: id 0 | task 3635 | stop processing: n_tokens = 483, truncated = 0 0.51.938.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 51815544 0.51.938.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.51.945.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.51.998.416 I slot launch_slot_: id 0 | task 3708 | processing task, is_child = 0 0.52.755.504 I slot print_timing: id 0 | task 3708 | prompt eval time = 191.05 ms / 549 tokens ( 0.35 ms per token, 2873.59 tokens per second) 0.52.755.511 I slot print_timing: id 0 | task 3708 | eval time = 566.01 ms / 57 tokens ( 10.11 ms per token, 98.94 tokens per second) 0.52.755.512 I slot print_timing: id 0 | task 3708 | total time = 757.06 ms / 606 tokens 0.52.755.514 I slot print_timing: id 0 | task 3708 | graphs reused = 3459 0.52.755.515 I slot print_timing: id 0 | task 3708 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.755.554 I slot release: id 0 | task 3708 | stop processing: n_tokens = 617, truncated = 0 0.52.772.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 52660633 0.52.772.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.52.823.871 I slot launch_slot_: id 0 | task 3769 | processing task, is_child = 0 0.53.607.769 I slot print_timing: id 0 | task 3769 | prompt eval time = 207.32 ms / 616 tokens ( 0.34 ms per token, 2971.18 tokens per second) 0.53.607.775 I slot print_timing: id 0 | task 3769 | eval time = 576.55 ms / 58 tokens ( 10.11 ms per token, 98.86 tokens per second) 0.53.607.776 I slot print_timing: id 0 | task 3769 | total time = 783.88 ms / 674 tokens 0.53.607.777 I slot print_timing: id 0 | task 3769 | graphs reused = 3515 0.53.607.779 I slot print_timing: id 0 | task 3769 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.607.814 I slot release: id 0 | task 3769 | stop processing: n_tokens = 685, truncated = 0 0.53.627.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 53512893 0.53.627.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.53.635.854 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.53.687.646 I slot launch_slot_: id 0 | task 3831 | processing task, is_child = 0 0.54.522.680 I slot print_timing: id 0 | task 3831 | prompt eval time = 217.09 ms / 665 tokens ( 0.33 ms per token, 3063.20 tokens per second) 0.54.522.686 I slot print_timing: id 0 | task 3831 | eval time = 617.92 ms / 62 tokens ( 10.13 ms per token, 98.72 tokens per second) 0.54.522.687 I slot print_timing: id 0 | task 3831 | total time = 835.02 ms / 727 tokens 0.54.522.688 I slot print_timing: id 0 | task 3831 | graphs reused = 3575 0.54.522.688 I slot print_timing: id 0 | task 3831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.522.726 I slot release: id 0 | task 3831 | stop processing: n_tokens = 738, truncated = 0 0.54.550.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 54427806 0.54.550.972 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.54.558.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.54.613.913 I slot launch_slot_: id 0 | task 3897 | processing task, is_child = 0 0.55.378.661 I slot print_timing: id 0 | task 3897 | prompt eval time = 215.95 ms / 645 tokens ( 0.33 ms per token, 2986.80 tokens per second) 0.55.378.668 I slot print_timing: id 0 | task 3897 | eval time = 548.78 ms / 55 tokens ( 10.16 ms per token, 98.40 tokens per second) 0.55.378.669 I slot print_timing: id 0 | task 3897 | total time = 764.73 ms / 700 tokens 0.55.378.669 I slot print_timing: id 0 | task 3897 | graphs reused = 3628 0.55.378.670 I slot print_timing: id 0 | task 3897 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.378.705 I slot release: id 0 | task 3897 | stop processing: n_tokens = 711, truncated = 0 0.55.405.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 55283785 0.55.405.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.55.461.828 I slot launch_slot_: id 0 | task 3956 | processing task, is_child = 0 0.56.157.697 I slot print_timing: id 0 | task 3956 | prompt eval time = 174.91 ms / 474 tokens ( 0.37 ms per token, 2709.92 tokens per second) 0.56.157.702 I slot print_timing: id 0 | task 3956 | eval time = 520.93 ms / 52 tokens ( 10.21 ms per token, 97.90 tokens per second) 0.56.157.703 I slot print_timing: id 0 | task 3956 | total time = 695.85 ms / 526 tokens 0.56.157.704 I slot print_timing: id 0 | task 3956 | graphs reused = 3677 0.56.157.704 I slot print_timing: id 0 | task 3956 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.157.736 I slot release: id 0 | task 3956 | stop processing: n_tokens = 537, truncated = 0 0.56.171.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 56062816 0.56.171.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.56.180.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.56.228.870 I slot launch_slot_: id 0 | task 4011 | processing task, is_child = 0 0.56.845.558 I slot print_timing: id 0 | task 4011 | prompt eval time = 200.53 ms / 617 tokens ( 0.33 ms per token, 3076.85 tokens per second) 0.56.845.563 I slot print_timing: id 0 | task 4011 | eval time = 416.14 ms / 42 tokens ( 10.15 ms per token, 98.53 tokens per second) 0.56.845.565 I slot print_timing: id 0 | task 4011 | total time = 616.67 ms / 659 tokens 0.56.845.565 I slot print_timing: id 0 | task 4011 | graphs reused = 3717 0.56.845.566 I slot print_timing: id 0 | task 4011 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.845.601 I slot release: id 0 | task 4011 | stop processing: n_tokens = 670, truncated = 0 0.56.872.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 56750681 0.56.872.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.56.925.439 I slot launch_slot_: id 0 | task 4057 | processing task, is_child = 0 0.57.602.989 I slot print_timing: id 0 | task 4057 | prompt eval time = 201.03 ms / 601 tokens ( 0.33 ms per token, 2989.60 tokens per second) 0.57.602.995 I slot print_timing: id 0 | task 4057 | eval time = 476.50 ms / 48 tokens ( 10.14 ms per token, 98.64 tokens per second) 0.57.602.996 I slot print_timing: id 0 | task 4057 | total time = 677.53 ms / 649 tokens 0.57.602.997 I slot print_timing: id 0 | task 4057 | graphs reused = 3763 0.57.602.998 I slot print_timing: id 0 | task 4057 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.603.035 I slot release: id 0 | task 4057 | stop processing: n_tokens = 660, truncated = 0 0.57.617.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 57508114 0.57.617.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.57.624.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.57.681.139 I slot launch_slot_: id 0 | task 4109 | processing task, is_child = 0 0.58.337.850 I slot print_timing: id 0 | task 4109 | prompt eval time = 190.12 ms / 533 tokens ( 0.36 ms per token, 2803.57 tokens per second) 0.58.337.856 I slot print_timing: id 0 | task 4109 | eval time = 466.57 ms / 47 tokens ( 10.14 ms per token, 98.59 tokens per second) 0.58.337.857 I slot print_timing: id 0 | task 4109 | total time = 656.69 ms / 580 tokens 0.58.337.858 I slot print_timing: id 0 | task 4109 | graphs reused = 3808 0.58.337.859 I slot print_timing: id 0 | task 4109 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.337.892 I slot release: id 0 | task 4109 | stop processing: n_tokens = 591, truncated = 0 0.58.364.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 58242972 0.58.364.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.58.426.205 I slot launch_slot_: id 0 | task 4160 | processing task, is_child = 0 0.59.125.649 I slot print_timing: id 0 | task 4160 | prompt eval time = 178.25 ms / 480 tokens ( 0.37 ms per token, 2692.92 tokens per second) 0.59.125.654 I slot print_timing: id 0 | task 4160 | eval time = 521.18 ms / 52 tokens ( 10.22 ms per token, 97.86 tokens per second) 0.59.125.656 I slot print_timing: id 0 | task 4160 | total time = 699.42 ms / 532 tokens 0.59.125.657 I slot print_timing: id 0 | task 4160 | graphs reused = 3857 0.59.125.657 I slot print_timing: id 0 | task 4160 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.125.688 I slot release: id 0 | task 4160 | stop processing: n_tokens = 560, truncated = 0 0.59.148.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 59030767 0.59.148.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.59.155.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.59.228.280 I slot launch_slot_: id 0 | task 4215 | processing task, is_child = 0 0.59.836.885 I slot print_timing: id 0 | task 4215 | prompt eval time = 191.41 ms / 567 tokens ( 0.34 ms per token, 2962.27 tokens per second) 0.59.836.891 I slot print_timing: id 0 | task 4215 | eval time = 417.18 ms / 42 tokens ( 10.18 ms per token, 98.28 tokens per second) 0.59.836.892 I slot print_timing: id 0 | task 4215 | total time = 608.58 ms / 609 tokens 0.59.836.893 I slot print_timing: id 0 | task 4215 | graphs reused = 3897 0.59.836.894 I slot print_timing: id 0 | task 4215 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.836.928 I slot release: id 0 | task 4215 | stop processing: n_tokens = 637, truncated = 0 0.59.861.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 59742007 0.59.861.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.59.869.569 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.59.928.230 I slot launch_slot_: id 0 | task 4261 | processing task, is_child = 0 1.00.749.180 I slot print_timing: id 0 | task 4261 | prompt eval time = 186.89 ms / 506 tokens ( 0.37 ms per token, 2707.46 tokens per second) 1.00.749.186 I slot print_timing: id 0 | task 4261 | eval time = 634.04 ms / 63 tokens ( 10.23 ms per token, 97.79 tokens per second) 1.00.749.187 I slot print_timing: id 0 | task 4261 | total time = 820.93 ms / 569 tokens 1.00.749.188 I slot print_timing: id 0 | task 4261 | graphs reused = 3958 1.00.749.188 I slot print_timing: id 0 | task 4261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.749.222 I slot release: id 0 | task 4261 | stop processing: n_tokens = 597, truncated = 0 1.00.774.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 60654302 1.00.774.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.00.782.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.00.834.781 I slot launch_slot_: id 0 | task 4327 | processing task, is_child = 0 1.01.397.565 I slot print_timing: id 0 | task 4327 | prompt eval time = 165.86 ms / 436 tokens ( 0.38 ms per token, 2628.68 tokens per second) 1.01.397.571 I slot print_timing: id 0 | task 4327 | eval time = 396.90 ms / 40 tokens ( 10.18 ms per token, 98.26 tokens per second) 1.01.397.572 I slot print_timing: id 0 | task 4327 | total time = 562.76 ms / 476 tokens 1.01.397.572 I slot print_timing: id 0 | task 4327 | graphs reused = 3996 1.01.397.573 I slot print_timing: id 0 | task 4327 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.397.604 I slot release: id 0 | task 4327 | stop processing: n_tokens = 504, truncated = 0 1.01.413.716 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 61302683 1.01.413.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.01.470.643 I slot launch_slot_: id 0 | task 4370 | processing task, is_child = 0 1.02.273.955 I slot print_timing: id 0 | task 4370 | prompt eval time = 184.38 ms / 519 tokens ( 0.36 ms per token, 2814.76 tokens per second) 1.02.273.961 I slot print_timing: id 0 | task 4370 | eval time = 618.91 ms / 62 tokens ( 10.15 ms per token, 98.56 tokens per second) 1.02.273.962 I slot print_timing: id 0 | task 4370 | total time = 803.29 ms / 581 tokens 1.02.273.963 I slot print_timing: id 0 | task 4370 | graphs reused = 4056 1.02.273.964 I slot print_timing: id 0 | task 4370 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.273.998 I slot release: id 0 | task 4370 | stop processing: n_tokens = 609, truncated = 0 1.02.298.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 62179078 1.02.298.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.02.308.241 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.02.417.472 I slot launch_slot_: id 0 | task 4436 | processing task, is_child = 0 1.03.052.885 I slot print_timing: id 0 | task 4436 | prompt eval time = 174.20 ms / 465 tokens ( 0.37 ms per token, 2669.39 tokens per second) 1.03.052.890 I slot print_timing: id 0 | task 4436 | eval time = 461.19 ms / 46 tokens ( 10.25 ms per token, 97.57 tokens per second) 1.03.052.891 I slot print_timing: id 0 | task 4436 | total time = 635.39 ms / 511 tokens 1.03.052.892 I slot print_timing: id 0 | task 4436 | graphs reused = 4099 1.03.052.893 I slot print_timing: id 0 | task 4436 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.052.926 I slot release: id 0 | task 4436 | stop processing: n_tokens = 542, truncated = 0 1.03.074.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 62958005 1.03.074.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.03.084.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.03.154.227 I slot launch_slot_: id 0 | task 4485 | processing task, is_child = 0 1.03.729.236 I slot print_timing: id 0 | task 4485 | prompt eval time = 168.53 ms / 431 tokens ( 0.39 ms per token, 2557.36 tokens per second) 1.03.729.241 I slot print_timing: id 0 | task 4485 | eval time = 406.45 ms / 41 tokens ( 10.16 ms per token, 98.41 tokens per second) 1.03.729.242 I slot print_timing: id 0 | task 4485 | total time = 574.99 ms / 472 tokens 1.03.729.243 I slot print_timing: id 0 | task 4485 | graphs reused = 4138 1.03.729.244 I slot print_timing: id 0 | task 4485 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.729.276 I slot release: id 0 | task 4485 | stop processing: n_tokens = 503, truncated = 0 1.03.745.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 63634356 1.03.745.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.03.754.870 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.03.829.042 I slot launch_slot_: id 0 | task 4529 | processing task, is_child = 0 1.04.436.010 I slot print_timing: id 0 | task 4529 | prompt eval time = 166.59 ms / 457 tokens ( 0.36 ms per token, 2743.18 tokens per second) 1.04.436.017 I slot print_timing: id 0 | task 4529 | eval time = 440.35 ms / 44 tokens ( 10.24 ms per token, 97.65 tokens per second) 1.04.436.018 I slot print_timing: id 0 | task 4529 | total time = 606.94 ms / 501 tokens 1.04.436.019 I slot print_timing: id 0 | task 4529 | graphs reused = 4179 1.04.436.019 I slot print_timing: id 0 | task 4529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.436.054 I slot release: id 0 | task 4529 | stop processing: n_tokens = 532, truncated = 0 1.04.462.817 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 64341133 1.04.462.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.04.532.254 I slot launch_slot_: id 0 | task 4576 | processing task, is_child = 0 1.05.593.450 I slot print_timing: id 0 | task 4576 | prompt eval time = 168.63 ms / 439 tokens ( 0.38 ms per token, 2603.35 tokens per second) 1.05.593.456 I slot print_timing: id 0 | task 4576 | eval time = 892.55 ms / 89 tokens ( 10.14 ms per token, 98.59 tokens per second) 1.05.593.457 I slot print_timing: id 0 | task 4576 | total time = 1061.17 ms / 528 tokens 1.05.593.458 I slot print_timing: id 0 | task 4576 | graphs reused = 4265 1.05.593.458 I slot print_timing: id 0 | task 4576 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.593.493 I slot release: id 0 | task 4576 | stop processing: n_tokens = 559, truncated = 0 1.05.618.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 65498572 1.05.618.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.05.631.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.05.704.719 I slot launch_slot_: id 0 | task 4668 | processing task, is_child = 0 1.06.462.468 I slot print_timing: id 0 | task 4668 | prompt eval time = 200.50 ms / 606 tokens ( 0.33 ms per token, 3022.43 tokens per second) 1.06.462.474 I slot print_timing: id 0 | task 4668 | eval time = 557.23 ms / 56 tokens ( 10.13 ms per token, 98.70 tokens per second) 1.06.462.475 I slot print_timing: id 0 | task 4668 | total time = 757.73 ms / 662 tokens 1.06.462.476 I slot print_timing: id 0 | task 4668 | graphs reused = 4319 1.06.462.476 I slot print_timing: id 0 | task 4668 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.462.514 I slot release: id 0 | task 4668 | stop processing: n_tokens = 693, truncated = 0 1.06.490.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 66367594 1.06.490.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.06.503.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.06.580.029 I slot launch_slot_: id 0 | task 4728 | processing task, is_child = 0 1.07.166.988 I slot print_timing: id 0 | task 4728 | prompt eval time = 175.41 ms / 477 tokens ( 0.37 ms per token, 2719.33 tokens per second) 1.07.166.993 I slot print_timing: id 0 | task 4728 | eval time = 411.53 ms / 41 tokens ( 10.29 ms per token, 97.20 tokens per second) 1.07.166.995 I slot print_timing: id 0 | task 4728 | total time = 586.94 ms / 518 tokens 1.07.166.995 I slot print_timing: id 0 | task 4728 | graphs reused = 4357 1.07.166.996 I slot print_timing: id 0 | task 4728 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.167.028 I slot release: id 0 | task 4728 | stop processing: n_tokens = 549, truncated = 0 1.07.183.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 67072108 1.07.183.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.07.243.385 I slot launch_slot_: id 0 | task 4772 | processing task, is_child = 0 1.08.103.600 I slot print_timing: id 0 | task 4772 | prompt eval time = 253.92 ms / 845 tokens ( 0.30 ms per token, 3327.85 tokens per second) 1.08.103.606 I slot print_timing: id 0 | task 4772 | eval time = 606.27 ms / 60 tokens ( 10.28 ms per token, 97.32 tokens per second) 1.08.103.607 I slot print_timing: id 0 | task 4772 | total time = 860.19 ms / 905 tokens 1.08.103.608 I slot print_timing: id 0 | task 4772 | graphs reused = 4415 1.08.103.609 I slot print_timing: id 0 | task 4772 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.103.658 I slot release: id 0 | task 4772 | stop processing: n_tokens = 936, truncated = 0 1.08.118.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 68008737 1.08.118.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.08.130.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.08.215.853 I slot launch_slot_: id 0 | task 4836 | processing task, is_child = 0 1.08.820.667 I slot print_timing: id 0 | task 4836 | prompt eval time = 172.87 ms / 459 tokens ( 0.38 ms per token, 2655.19 tokens per second) 1.08.820.673 I slot print_timing: id 0 | task 4836 | eval time = 431.92 ms / 43 tokens ( 10.28 ms per token, 97.24 tokens per second) 1.08.820.674 I slot print_timing: id 0 | task 4836 | total time = 604.79 ms / 502 tokens 1.08.820.675 I slot print_timing: id 0 | task 4836 | graphs reused = 4455 1.08.820.676 I slot print_timing: id 0 | task 4836 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.820.709 I slot release: id 0 | task 4836 | stop processing: n_tokens = 533, truncated = 0 1.08.838.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 68725788 1.08.838.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.08.926.029 I slot launch_slot_: id 0 | task 4882 | processing task, is_child = 0 1.09.606.093 I slot print_timing: id 0 | task 4882 | prompt eval time = 213.56 ms / 670 tokens ( 0.32 ms per token, 3137.29 tokens per second) 1.09.606.099 I slot print_timing: id 0 | task 4882 | eval time = 466.48 ms / 47 tokens ( 10.14 ms per token, 98.61 tokens per second) 1.09.606.100 I slot print_timing: id 0 | task 4882 | total time = 680.04 ms / 717 tokens 1.09.606.101 I slot print_timing: id 0 | task 4882 | graphs reused = 4500 1.09.606.102 I slot print_timing: id 0 | task 4882 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.606.143 I slot release: id 0 | task 4882 | stop processing: n_tokens = 748, truncated = 0 1.09.633.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 69511223 1.09.633.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.09.645.853 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.09.727.041 I slot launch_slot_: id 0 | task 4933 | processing task, is_child = 0 1.10.636.159 I slot print_timing: id 0 | task 4933 | prompt eval time = 240.73 ms / 775 tokens ( 0.31 ms per token, 3219.40 tokens per second) 1.10.636.165 I slot print_timing: id 0 | task 4933 | eval time = 668.37 ms / 63 tokens ( 10.78 ms per token, 92.76 tokens per second) 1.10.636.166 I slot print_timing: id 0 | task 4933 | total time = 909.09 ms / 838 tokens 1.10.636.167 I slot print_timing: id 0 | task 4933 | graphs reused = 4561 1.10.636.168 I slot print_timing: id 0 | task 4933 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.636.213 I slot release: id 0 | task 4933 | stop processing: n_tokens = 869, truncated = 0 1.10.640.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 70541293 1.10.640.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.10.649.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.10.716.840 I slot launch_slot_: id 0 | task 5000 | processing task, is_child = 0 1.11.620.454 I slot print_timing: id 0 | task 5000 | prompt eval time = 197.67 ms / 573 tokens ( 0.34 ms per token, 2898.81 tokens per second) 1.11.620.460 I slot print_timing: id 0 | task 5000 | eval time = 705.93 ms / 71 tokens ( 10.08 ms per token, 99.16 tokens per second) 1.11.620.461 I slot print_timing: id 0 | task 5000 | total time = 903.59 ms / 644 tokens 1.11.620.462 I slot print_timing: id 0 | task 5000 | graphs reused = 4630 1.11.620.463 I slot print_timing: id 0 | task 5000 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.620.499 I slot release: id 0 | task 5000 | stop processing: n_tokens = 675, truncated = 0 1.11.648.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 71525578 1.11.648.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.11.658.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.11.725.983 I slot launch_slot_: id 0 | task 5075 | processing task, is_child = 0 1.12.540.198 I slot print_timing: id 0 | task 5075 | prompt eval time = 172.31 ms / 461 tokens ( 0.37 ms per token, 2675.43 tokens per second) 1.12.540.205 I slot print_timing: id 0 | task 5075 | eval time = 641.88 ms / 64 tokens ( 10.19 ms per token, 98.15 tokens per second) 1.12.540.206 I slot print_timing: id 0 | task 5075 | total time = 814.19 ms / 525 tokens 1.12.540.207 I slot print_timing: id 0 | task 5075 | graphs reused = 4691 1.12.540.209 I slot print_timing: id 0 | task 5075 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.540.244 I slot release: id 0 | task 5075 | stop processing: n_tokens = 556, truncated = 0 1.12.566.328 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 72445324 1.12.566.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.12.622.811 I slot launch_slot_: id 0 | task 5142 | processing task, is_child = 0 1.13.281.172 I slot print_timing: id 0 | task 5142 | prompt eval time = 198.83 ms / 609 tokens ( 0.33 ms per token, 3062.93 tokens per second) 1.13.281.178 I slot print_timing: id 0 | task 5142 | eval time = 459.51 ms / 43 tokens ( 10.94 ms per token, 91.40 tokens per second) 1.13.281.179 I slot print_timing: id 0 | task 5142 | total time = 658.34 ms / 652 tokens 1.13.281.180 I slot print_timing: id 0 | task 5142 | graphs reused = 4732 1.13.281.181 I slot print_timing: id 0 | task 5142 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.281.224 I slot release: id 0 | task 5142 | stop processing: n_tokens = 683, truncated = 0 1.13.297.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 73186304 1.13.297.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.13.307.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.13.381.020 I slot launch_slot_: id 0 | task 5189 | processing task, is_child = 0 1.14.229.235 I slot print_timing: id 0 | task 5189 | prompt eval time = 240.99 ms / 791 tokens ( 0.30 ms per token, 3282.36 tokens per second) 1.14.229.240 I slot print_timing: id 0 | task 5189 | eval time = 607.21 ms / 61 tokens ( 10.12 ms per token, 98.81 tokens per second) 1.14.229.241 I slot print_timing: id 0 | task 5189 | total time = 848.19 ms / 852 tokens 1.14.229.242 I slot print_timing: id 0 | task 5189 | graphs reused = 4791 1.14.229.243 I slot print_timing: id 0 | task 5189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.229.285 I slot release: id 0 | task 5189 | stop processing: n_tokens = 883, truncated = 0 1.14.245.013 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 74134365 1.14.245.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.14.347.436 I slot launch_slot_: id 0 | task 5254 | processing task, is_child = 0 1.15.092.359 I slot print_timing: id 0 | task 5254 | prompt eval time = 189.20 ms / 533 tokens ( 0.35 ms per token, 2817.09 tokens per second) 1.15.092.365 I slot print_timing: id 0 | task 5254 | eval time = 555.70 ms / 56 tokens ( 10.10 ms per token, 98.97 tokens per second) 1.15.092.366 I slot print_timing: id 0 | task 5254 | total time = 744.90 ms / 589 tokens 1.15.092.366 I slot print_timing: id 0 | task 5254 | graphs reused = 4845 1.15.092.367 I slot print_timing: id 0 | task 5254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.092.402 I slot release: id 0 | task 5254 | stop processing: n_tokens = 677, truncated = 0 1.15.117.997 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 74997482 1.15.118.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.15.192.269 I slot launch_slot_: id 0 | task 5314 | processing task, is_child = 0 1.15.880.331 I slot print_timing: id 0 | task 5314 | prompt eval time = 198.43 ms / 566 tokens ( 0.35 ms per token, 2852.36 tokens per second) 1.15.880.337 I slot print_timing: id 0 | task 5314 | eval time = 489.61 ms / 46 tokens ( 10.88 ms per token, 91.91 tokens per second) 1.15.880.338 I slot print_timing: id 0 | task 5314 | total time = 688.04 ms / 612 tokens 1.15.880.339 I slot print_timing: id 0 | task 5314 | graphs reused = 4889 1.15.880.340 I slot print_timing: id 0 | task 5314 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.880.375 I slot release: id 0 | task 5314 | stop processing: n_tokens = 643, truncated = 0 1.15.895.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 75785455 1.15.895.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.15.964.175 I slot launch_slot_: id 0 | task 5364 | processing task, is_child = 0 1.16.565.268 I slot print_timing: id 0 | task 5364 | prompt eval time = 169.91 ms / 443 tokens ( 0.38 ms per token, 2607.31 tokens per second) 1.16.565.275 I slot print_timing: id 0 | task 5364 | eval time = 431.16 ms / 43 tokens ( 10.27 ms per token, 97.41 tokens per second) 1.16.565.277 I slot print_timing: id 0 | task 5364 | total time = 601.07 ms / 486 tokens 1.16.565.278 I slot print_timing: id 0 | task 5364 | graphs reused = 4929 1.16.565.279 I slot print_timing: id 0 | task 5364 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.565.313 I slot release: id 0 | task 5364 | stop processing: n_tokens = 517, truncated = 0 1.16.569.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 76470393 1.16.569.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.16.632.653 I slot launch_slot_: id 0 | task 5410 | processing task, is_child = 0 1.17.451.836 I slot print_timing: id 0 | task 5410 | prompt eval time = 170.35 ms / 487 tokens ( 0.35 ms per token, 2858.74 tokens per second) 1.17.451.842 I slot print_timing: id 0 | task 5410 | eval time = 648.81 ms / 65 tokens ( 10.14 ms per token, 98.64 tokens per second) 1.17.451.843 I slot print_timing: id 0 | task 5410 | total time = 819.16 ms / 552 tokens 1.17.451.844 I slot print_timing: id 0 | task 5410 | graphs reused = 4992 1.17.451.845 I slot print_timing: id 0 | task 5410 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.451.879 I slot release: id 0 | task 5410 | stop processing: n_tokens = 583, truncated = 0 1.17.474.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 77356958 1.17.474.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.17.538.197 I slot launch_slot_: id 0 | task 5478 | processing task, is_child = 0 1.18.181.534 I slot print_timing: id 0 | task 5478 | prompt eval time = 177.06 ms / 507 tokens ( 0.35 ms per token, 2863.44 tokens per second) 1.18.181.539 I slot print_timing: id 0 | task 5478 | eval time = 466.26 ms / 47 tokens ( 10.14 ms per token, 98.66 tokens per second) 1.18.181.541 I slot print_timing: id 0 | task 5478 | total time = 643.32 ms / 554 tokens 1.18.181.542 I slot print_timing: id 0 | task 5478 | graphs reused = 5037 1.18.181.543 I slot print_timing: id 0 | task 5478 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.181.577 I slot release: id 0 | task 5478 | stop processing: n_tokens = 585, truncated = 0 1.18.208.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 78086656 1.18.208.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.18.222.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.18.287.548 I slot launch_slot_: id 0 | task 5528 | processing task, is_child = 0 1.19.146.982 I slot print_timing: id 0 | task 5528 | prompt eval time = 202.88 ms / 633 tokens ( 0.32 ms per token, 3120.04 tokens per second) 1.19.146.988 I slot print_timing: id 0 | task 5528 | eval time = 656.53 ms / 66 tokens ( 10.10 ms per token, 99.01 tokens per second) 1.19.146.989 I slot print_timing: id 0 | task 5528 | total time = 859.41 ms / 699 tokens 1.19.146.990 I slot print_timing: id 0 | task 5528 | graphs reused = 5101 1.19.146.990 I slot print_timing: id 0 | task 5528 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.147.028 I slot release: id 0 | task 5528 | stop processing: n_tokens = 730, truncated = 0 1.19.163.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 79052108 1.19.163.635 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.19.232.180 I slot launch_slot_: id 0 | task 5598 | processing task, is_child = 0 1.19.896.714 I slot print_timing: id 0 | task 5598 | prompt eval time = 196.41 ms / 571 tokens ( 0.34 ms per token, 2907.12 tokens per second) 1.19.896.720 I slot print_timing: id 0 | task 5598 | eval time = 468.10 ms / 47 tokens ( 10.18 ms per token, 98.27 tokens per second) 1.19.896.721 I slot print_timing: id 0 | task 5598 | total time = 664.51 ms / 618 tokens 1.19.896.722 I slot print_timing: id 0 | task 5598 | graphs reused = 5146 1.19.896.723 I slot print_timing: id 0 | task 5598 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.896.761 I slot release: id 0 | task 5598 | stop processing: n_tokens = 649, truncated = 0 1.19.915.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 79801840 1.19.915.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.20.007.635 I slot launch_slot_: id 0 | task 5649 | processing task, is_child = 0 1.20.684.817 I slot print_timing: id 0 | task 5649 | prompt eval time = 240.75 ms / 798 tokens ( 0.30 ms per token, 3314.63 tokens per second) 1.20.684.823 I slot print_timing: id 0 | task 5649 | eval time = 436.41 ms / 44 tokens ( 10.15 ms per token, 98.53 tokens per second) 1.20.684.824 I slot print_timing: id 0 | task 5649 | total time = 677.16 ms / 842 tokens 1.20.684.825 I slot print_timing: id 0 | task 5649 | graphs reused = 5188 1.20.684.825 I slot print_timing: id 0 | task 5649 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.684.868 I slot release: id 0 | task 5649 | stop processing: n_tokens = 873, truncated = 0 1.20.705.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 80589948 1.20.705.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.20.721.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.20.798.420 I slot launch_slot_: id 0 | task 5697 | processing task, is_child = 0 1.21.421.180 I slot print_timing: id 0 | task 5697 | prompt eval time = 197.00 ms / 572 tokens ( 0.34 ms per token, 2903.57 tokens per second) 1.21.421.186 I slot print_timing: id 0 | task 5697 | eval time = 425.74 ms / 43 tokens ( 10.14 ms per token, 98.65 tokens per second) 1.21.421.187 I slot print_timing: id 0 | task 5697 | total time = 622.74 ms / 615 tokens 1.21.421.188 I slot print_timing: id 0 | task 5697 | graphs reused = 5229 1.21.421.189 I slot print_timing: id 0 | task 5697 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.421.225 I slot release: id 0 | task 5697 | stop processing: n_tokens = 646, truncated = 0 1.21.440.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 81326304 1.21.440.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.21.519.132 I slot launch_slot_: id 0 | task 5744 | processing task, is_child = 0 1.22.210.826 I slot print_timing: id 0 | task 5744 | prompt eval time = 204.93 ms / 613 tokens ( 0.33 ms per token, 2991.28 tokens per second) 1.22.210.832 I slot print_timing: id 0 | task 5744 | eval time = 486.75 ms / 49 tokens ( 10.14 ms per token, 98.61 tokens per second) 1.22.210.833 I slot print_timing: id 0 | task 5744 | total time = 691.67 ms / 662 tokens 1.22.210.834 I slot print_timing: id 0 | task 5744 | graphs reused = 5276 1.22.210.835 I slot print_timing: id 0 | task 5744 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.210.872 I slot release: id 0 | task 5744 | stop processing: n_tokens = 693, truncated = 0 1.22.234.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 82115952 1.22.234.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.22.343.637 I slot launch_slot_: id 0 | task 5797 | processing task, is_child = 0 1.23.174.914 I slot print_timing: id 0 | task 5797 | prompt eval time = 195.20 ms / 580 tokens ( 0.34 ms per token, 2971.31 tokens per second) 1.23.174.921 I slot print_timing: id 0 | task 5797 | eval time = 636.06 ms / 64 tokens ( 10.10 ms per token, 99.05 tokens per second) 1.23.174.922 I slot print_timing: id 0 | task 5797 | total time = 831.26 ms / 644 tokens 1.23.174.923 I slot print_timing: id 0 | task 5797 | graphs reused = 5338 1.23.174.924 I slot print_timing: id 0 | task 5797 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.174.964 I slot release: id 0 | task 5797 | stop processing: n_tokens = 675, truncated = 0 1.23.191.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 83080044 1.23.191.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.23.268.263 I slot launch_slot_: id 0 | task 5865 | processing task, is_child = 0 1.23.999.540 I slot print_timing: id 0 | task 5865 | prompt eval time = 225.87 ms / 716 tokens ( 0.32 ms per token, 3169.94 tokens per second) 1.23.999.545 I slot print_timing: id 0 | task 5865 | eval time = 505.38 ms / 50 tokens ( 10.31 ms per token, 96.96 tokens per second) 1.23.999.546 I slot print_timing: id 0 | task 5865 | total time = 731.25 ms / 766 tokens 1.23.999.548 I slot print_timing: id 0 | task 5865 | graphs reused = 5385 1.23.999.549 I slot print_timing: id 0 | task 5865 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.999.594 I slot release: id 0 | task 5865 | stop processing: n_tokens = 797, truncated = 0 1.24.030.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 83904673 1.24.030.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.24.050.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.24.141.786 I slot launch_slot_: id 0 | task 5919 | processing task, is_child = 0 1.25.408.134 I slot print_timing: id 0 | task 5919 | prompt eval time = 241.11 ms / 799 tokens ( 0.30 ms per token, 3313.84 tokens per second) 1.25.408.140 I slot print_timing: id 0 | task 5919 | eval time = 1025.22 ms / 102 tokens ( 10.15 ms per token, 98.52 tokens per second) 1.25.408.141 I slot print_timing: id 0 | task 5919 | total time = 1266.33 ms / 901 tokens 1.25.408.142 I slot print_timing: id 0 | task 5919 | graphs reused = 5485 1.25.408.142 I slot print_timing: id 0 | task 5919 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.408.185 I slot release: id 0 | task 5919 | stop processing: n_tokens = 932, truncated = 0 1.25.424.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 85313265 1.25.424.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.985 MiB) 1.25.537.840 I slot launch_slot_: id 0 | task 6025 | processing task, is_child = 0 1.26.812.286 I slot print_timing: id 0 | task 6025 | prompt eval time = 152.74 ms / 361 tokens ( 0.42 ms per token, 2363.46 tokens per second) 1.26.812.291 I slot print_timing: id 0 | task 6025 | eval time = 1121.68 ms / 112 tokens ( 10.11 ms per token, 98.96 tokens per second) 1.26.812.292 I slot print_timing: id 0 | task 6025 | total time = 1274.42 ms / 473 tokens 1.26.812.293 I slot print_timing: id 0 | task 6025 | graphs reused = 5595 1.26.812.294 I slot print_timing: id 0 | task 6025 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.812.323 I slot release: id 0 | task 6025 | stop processing: n_tokens = 504, truncated = 0 1.26.839.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 86717403 1.26.839.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.26.912.364 I slot launch_slot_: id 0 | task 6140 | processing task, is_child = 0 1.28.146.553 I slot print_timing: id 0 | task 6140 | prompt eval time = 150.25 ms / 381 tokens ( 0.39 ms per token, 2535.74 tokens per second) 1.28.146.560 I slot print_timing: id 0 | task 6140 | eval time = 1083.91 ms / 108 tokens ( 10.13 ms per token, 98.72 tokens per second) 1.28.146.561 I slot print_timing: id 0 | task 6140 | total time = 1234.17 ms / 489 tokens 1.28.146.562 I slot print_timing: id 0 | task 6140 | graphs reused = 5700 1.28.146.563 I slot print_timing: id 0 | task 6140 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.146.617 I slot release: id 0 | task 6140 | stop processing: n_tokens = 520, truncated = 0 1.28.168.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 88051697 1.28.168.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.28.240.118 I slot launch_slot_: id 0 | task 6251 | processing task, is_child = 0 1.29.630.984 I slot print_timing: id 0 | task 6251 | prompt eval time = 148.75 ms / 365 tokens ( 0.41 ms per token, 2453.72 tokens per second) 1.29.630.990 I slot print_timing: id 0 | task 6251 | eval time = 1242.09 ms / 124 tokens ( 10.10 ms per token, 99.03 tokens per second) 1.29.630.991 I slot print_timing: id 0 | task 6251 | total time = 1390.84 ms / 489 tokens 1.29.630.992 I slot print_timing: id 0 | task 6251 | graphs reused = 5821 1.29.630.993 I slot print_timing: id 0 | task 6251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.631.031 I slot release: id 0 | task 6251 | stop processing: n_tokens = 520, truncated = 0 1.29.634.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 89536111 1.29.634.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.29.714.304 I slot launch_slot_: id 0 | task 6378 | processing task, is_child = 0 1.30.927.656 I slot print_timing: id 0 | task 6378 | prompt eval time = 146.94 ms / 333 tokens ( 0.44 ms per token, 2266.29 tokens per second) 1.30.927.662 I slot print_timing: id 0 | task 6378 | eval time = 1066.40 ms / 107 tokens ( 10.06 ms per token, 99.40 tokens per second) 1.30.927.663 I slot print_timing: id 0 | task 6378 | total time = 1213.33 ms / 440 tokens 1.30.927.663 I slot print_timing: id 0 | task 6378 | graphs reused = 5926 1.30.927.664 I slot print_timing: id 0 | task 6378 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.927.693 I slot release: id 0 | task 6378 | stop processing: n_tokens = 471, truncated = 0 1.30.954.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 90832772 1.31.021.443 I slot launch_slot_: id 0 | task 6488 | processing task, is_child = 0 1.32.558.151 I slot print_timing: id 0 | task 6488 | prompt eval time = 154.27 ms / 403 tokens ( 0.38 ms per token, 2612.29 tokens per second) 1.32.558.157 I slot print_timing: id 0 | task 6488 | eval time = 1382.42 ms / 138 tokens ( 10.09 ms per token, 99.10 tokens per second) 1.32.558.158 I slot print_timing: id 0 | task 6488 | total time = 1536.69 ms / 541 tokens 1.32.558.159 I slot print_timing: id 0 | task 6488 | graphs reused = 6061 1.32.558.160 I slot print_timing: id 0 | task 6488 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.558.193 I slot release: id 0 | task 6488 | stop processing: n_tokens = 572, truncated = 0 1.32.562.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 92463273 1.32.562.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.32.661.705 I slot launch_slot_: id 0 | task 6629 | processing task, is_child = 0 1.34.669.548 I slot print_timing: id 0 | task 6629 | prompt eval time = 152.96 ms / 411 tokens ( 0.37 ms per token, 2687.03 tokens per second) 1.34.669.554 I slot print_timing: id 0 | task 6629 | eval time = 1854.86 ms / 185 tokens ( 10.08 ms per token, 99.20 tokens per second) 1.34.669.555 I slot print_timing: id 0 | task 6629 | total time = 2007.82 ms / 596 tokens 1.34.669.556 I slot print_timing: id 0 | task 6629 | graphs reused = 6243 1.34.669.557 I slot print_timing: id 0 | task 6629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.669.588 I slot release: id 0 | task 6629 | stop processing: n_tokens = 627, truncated = 0 1.34.692.287 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 94574667 1.34.692.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.34.781.765 I slot launch_slot_: id 0 | task 6817 | processing task, is_child = 0 1.37.219.877 I slot print_timing: id 0 | task 6817 | prompt eval time = 179.82 ms / 490 tokens ( 0.37 ms per token, 2724.89 tokens per second) 1.37.219.883 I slot print_timing: id 0 | task 6817 | eval time = 2258.27 ms / 225 tokens ( 10.08 ms per token, 99.19 tokens per second) 1.37.219.884 I slot print_timing: id 0 | task 6817 | total time = 2438.09 ms / 715 tokens 1.37.219.885 I slot print_timing: id 0 | task 6817 | graphs reused = 6466 1.37.219.886 I slot print_timing: id 0 | task 6817 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.219.923 I slot release: id 0 | task 6817 | stop processing: n_tokens = 746, truncated = 0 1.37.243.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 97125002 1.37.243.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.37.307.949 I slot launch_slot_: id 0 | task 7045 | processing task, is_child = 0 1.39.183.225 I slot print_timing: id 0 | task 7045 | prompt eval time = 150.34 ms / 344 tokens ( 0.44 ms per token, 2288.18 tokens per second) 1.39.183.231 I slot print_timing: id 0 | task 7045 | eval time = 1724.92 ms / 171 tokens ( 10.15 ms per token, 98.56 tokens per second) 1.39.183.232 I slot print_timing: id 0 | task 7045 | total time = 1875.25 ms / 515 tokens 1.39.183.233 I slot print_timing: id 0 | task 7045 | graphs reused = 6634 1.39.183.234 I slot print_timing: id 0 | task 7045 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.183.262 I slot release: id 0 | task 7045 | stop processing: n_tokens = 546, truncated = 0 1.39.202.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 99088341 1.39.202.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.39.265.258 I slot launch_slot_: id 0 | task 7219 | processing task, is_child = 0 1.41.131.926 I slot print_timing: id 0 | task 7219 | prompt eval time = 147.10 ms / 347 tokens ( 0.42 ms per token, 2358.94 tokens per second) 1.41.131.932 I slot print_timing: id 0 | task 7219 | eval time = 1719.55 ms / 171 tokens ( 10.11 ms per token, 98.86 tokens per second) 1.41.131.933 I slot print_timing: id 0 | task 7219 | total time = 1866.65 ms / 518 tokens 1.41.131.933 I slot print_timing: id 0 | task 7219 | graphs reused = 6802 1.41.131.934 I slot print_timing: id 0 | task 7219 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.131.963 I slot release: id 0 | task 7219 | stop processing: n_tokens = 549, truncated = 0 1.41.153.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 101037043 1.41.153.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 1.41.221.382 I slot launch_slot_: id 0 | task 7393 | processing task, is_child = 0 1.42.640.442 I slot print_timing: id 0 | task 7393 | prompt eval time = 154.18 ms / 401 tokens ( 0.38 ms per token, 2600.89 tokens per second) 1.42.640.448 I slot print_timing: id 0 | task 7393 | eval time = 1264.86 ms / 126 tokens ( 10.12 ms per token, 98.83 tokens per second) 1.42.640.449 I slot print_timing: id 0 | task 7393 | total time = 1419.04 ms / 527 tokens 1.42.640.451 I slot print_timing: id 0 | task 7393 | graphs reused = 6925 1.42.640.452 I slot print_timing: id 0 | task 7393 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.640.480 I slot release: id 0 | task 7393 | stop processing: n_tokens = 558, truncated = 0 1.42.662.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 102545560 1.42.662.713 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.42.730.792 I slot launch_slot_: id 0 | task 7522 | processing task, is_child = 0 1.44.078.594 I slot print_timing: id 0 | task 7522 | prompt eval time = 165.03 ms / 456 tokens ( 0.36 ms per token, 2763.22 tokens per second) 1.44.078.601 I slot print_timing: id 0 | task 7522 | eval time = 1182.76 ms / 115 tokens ( 10.38 ms per token, 96.39 tokens per second) 1.44.078.602 I slot print_timing: id 0 | task 7522 | total time = 1347.78 ms / 571 tokens 1.44.078.603 I slot print_timing: id 0 | task 7522 | graphs reused = 7037 1.44.078.603 I slot print_timing: id 0 | task 7522 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.078.634 I slot release: id 0 | task 7522 | stop processing: n_tokens = 602, truncated = 0 1.44.107.315 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 1.44.107.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.44.180.540 I slot launch_slot_: id 0 | task 7640 | processing task, is_child = 0 1.45.458.108 I slot print_timing: id 0 | task 7640 | prompt eval time = 156.84 ms / 406 tokens ( 0.39 ms per token, 2588.59 tokens per second) 1.45.458.113 I slot print_timing: id 0 | task 7640 | eval time = 1120.70 ms / 112 tokens ( 10.10 ms per token, 99.04 tokens per second) 1.45.458.114 I slot print_timing: id 0 | task 7640 | total time = 1277.55 ms / 518 tokens 1.45.458.115 I slot print_timing: id 0 | task 7640 | graphs reused = 7146 1.45.458.116 I slot print_timing: id 0 | task 7640 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.458.150 I slot release: id 0 | task 7640 | stop processing: n_tokens = 549, truncated = 0 1.45.483.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 105363229 1.45.548.291 I slot launch_slot_: id 0 | task 7755 | processing task, is_child = 0 1.47.500.093 I slot print_timing: id 0 | task 7755 | prompt eval time = 155.10 ms / 406 tokens ( 0.38 ms per token, 2617.73 tokens per second) 1.47.500.099 I slot print_timing: id 0 | task 7755 | eval time = 1796.68 ms / 179 tokens ( 10.09 ms per token, 99.07 tokens per second) 1.47.500.100 I slot print_timing: id 0 | task 7755 | total time = 1951.78 ms / 585 tokens 1.47.500.101 I slot print_timing: id 0 | task 7755 | graphs reused = 7322 1.47.500.102 I slot print_timing: id 0 | task 7755 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.500.136 I slot release: id 0 | task 7755 | stop processing: n_tokens = 616, truncated = 0 1.47.504.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 107405215 1.47.504.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.47.582.347 I slot launch_slot_: id 0 | task 7937 | processing task, is_child = 0 1.49.191.797 I slot print_timing: id 0 | task 7937 | prompt eval time = 162.13 ms / 444 tokens ( 0.37 ms per token, 2738.54 tokens per second) 1.49.191.803 I slot print_timing: id 0 | task 7937 | eval time = 1447.30 ms / 144 tokens ( 10.12 ms per token, 98.80 tokens per second) 1.49.191.804 I slot print_timing: id 0 | task 7937 | total time = 1609.43 ms / 588 tokens 1.49.191.805 I slot print_timing: id 0 | task 7937 | graphs reused = 7463 1.49.191.806 I slot print_timing: id 0 | task 7937 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.191.838 I slot release: id 0 | task 7937 | stop processing: n_tokens = 619, truncated = 0 1.49.213.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 109096917 1.49.213.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.49.279.486 I slot launch_slot_: id 0 | task 8084 | processing task, is_child = 0 1.50.458.920 I slot print_timing: id 0 | task 8084 | prompt eval time = 151.66 ms / 372 tokens ( 0.41 ms per token, 2452.84 tokens per second) 1.50.458.927 I slot print_timing: id 0 | task 8084 | eval time = 1027.75 ms / 103 tokens ( 10.08 ms per token, 99.25 tokens per second) 1.50.458.928 I slot print_timing: id 0 | task 8084 | total time = 1179.41 ms / 475 tokens 1.50.458.929 I slot print_timing: id 0 | task 8084 | graphs reused = 7564 1.50.458.930 I slot print_timing: id 0 | task 8084 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.458.963 I slot release: id 0 | task 8084 | stop processing: n_tokens = 506, truncated = 0 1.50.473.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 110364043 1.50.473.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.50.537.612 I slot launch_slot_: id 0 | task 8190 | processing task, is_child = 0 1.53.005.687 I slot print_timing: id 0 | task 8190 | prompt eval time = 161.56 ms / 454 tokens ( 0.36 ms per token, 2810.14 tokens per second) 1.53.005.693 I slot print_timing: id 0 | task 8190 | eval time = 2306.50 ms / 230 tokens ( 10.07 ms per token, 99.28 tokens per second) 1.53.005.694 I slot print_timing: id 0 | task 8190 | total time = 2468.05 ms / 684 tokens 1.53.005.695 I slot print_timing: id 0 | task 8190 | graphs reused = 7791 1.53.005.695 I slot print_timing: id 0 | task 8190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.005.728 I slot release: id 0 | task 8190 | stop processing: n_tokens = 715, truncated = 0 1.53.009.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 112910808 1.53.009.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.53.081.325 I slot launch_slot_: id 0 | task 8423 | processing task, is_child = 0 1.55.511.267 I slot print_timing: id 0 | task 8423 | prompt eval time = 159.72 ms / 354 tokens ( 0.45 ms per token, 2216.36 tokens per second) 1.55.511.273 I slot print_timing: id 0 | task 8423 | eval time = 2270.20 ms / 226 tokens ( 10.09 ms per token, 99.11 tokens per second) 1.55.511.274 I slot print_timing: id 0 | task 8423 | total time = 2429.92 ms / 580 tokens 1.55.511.275 I slot print_timing: id 0 | task 8423 | graphs reused = 8014 1.55.511.276 I slot print_timing: id 0 | task 8423 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.511.306 I slot release: id 0 | task 8423 | stop processing: n_tokens = 611, truncated = 0 1.55.539.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 115416386 1.55.540.001 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.55.611.869 I slot launch_slot_: id 0 | task 8652 | processing task, is_child = 0 1.57.158.413 I slot print_timing: id 0 | task 8652 | prompt eval time = 145.59 ms / 334 tokens ( 0.44 ms per token, 2294.13 tokens per second) 1.57.158.420 I slot print_timing: id 0 | task 8652 | eval time = 1400.93 ms / 140 tokens ( 10.08 ms per token, 99.22 tokens per second) 1.57.158.421 I slot print_timing: id 0 | task 8652 | total time = 1546.52 ms / 474 tokens 1.57.158.421 I slot print_timing: id 0 | task 8652 | graphs reused = 8152 1.57.158.422 I slot print_timing: id 0 | task 8652 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.158.451 I slot release: id 0 | task 8652 | stop processing: n_tokens = 505, truncated = 0 1.57.179.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 117063531 1.57.179.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.57.258.340 I slot launch_slot_: id 0 | task 8795 | processing task, is_child = 0 1.59.172.462 I slot print_timing: id 0 | task 8795 | prompt eval time = 159.59 ms / 426 tokens ( 0.37 ms per token, 2669.37 tokens per second) 1.59.172.468 I slot print_timing: id 0 | task 8795 | eval time = 1754.51 ms / 175 tokens ( 10.08 ms per token, 99.17 tokens per second) 1.59.172.469 I slot print_timing: id 0 | task 8795 | total time = 1914.10 ms / 601 tokens 1.59.172.470 I slot print_timing: id 0 | task 8795 | graphs reused = 8324 1.59.172.471 I slot print_timing: id 0 | task 8795 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.172.503 I slot release: id 0 | task 8795 | stop processing: n_tokens = 632, truncated = 0 1.59.176.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 119077582 1.59.176.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.59.245.429 I slot launch_slot_: id 0 | task 8973 | processing task, is_child = 0 2.00.567.246 I slot print_timing: id 0 | task 8973 | prompt eval time = 149.21 ms / 366 tokens ( 0.41 ms per token, 2452.90 tokens per second) 2.00.567.252 I slot print_timing: id 0 | task 8973 | eval time = 1172.58 ms / 117 tokens ( 10.11 ms per token, 98.93 tokens per second) 2.00.567.253 I slot print_timing: id 0 | task 8973 | total time = 1321.80 ms / 483 tokens 2.00.567.255 I slot print_timing: id 0 | task 8973 | graphs reused = 8438 2.00.567.256 I slot print_timing: id 0 | task 8973 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.567.286 I slot release: id 0 | task 8973 | stop processing: n_tokens = 514, truncated = 0 2.00.589.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 120472366 2.00.589.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.00.667.847 I slot launch_slot_: id 0 | task 9093 | processing task, is_child = 0 2.03.842.955 I slot print_timing: id 0 | task 9093 | n_gen = 298, tg = 98.79 t/s, tg_3s = 99.12 t/s 2.04.074.877 I slot print_timing: id 0 | task 9093 | prompt eval time = 168.57 ms / 462 tokens ( 0.36 ms per token, 2740.75 tokens per second) 2.04.074.884 I slot print_timing: id 0 | task 9093 | eval time = 3238.44 ms / 321 tokens ( 10.12 ms per token, 98.81 tokens per second) 2.04.074.885 I slot print_timing: id 0 | task 9093 | total time = 3407.01 ms / 783 tokens 2.04.074.886 I slot print_timing: id 0 | task 9093 | graphs reused = 8755 2.04.074.888 I slot print_timing: id 0 | task 9093 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.074.938 I slot release: id 0 | task 9093 | stop processing: n_tokens = 814, truncated = 0 2.04.089.716 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 814, t_last = 123980018 2.04.089.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.04.169.399 I slot launch_slot_: id 0 | task 9417 | processing task, is_child = 0 2.05.716.108 I slot print_timing: id 0 | task 9417 | prompt eval time = 152.54 ms / 396 tokens ( 0.39 ms per token, 2596.01 tokens per second) 2.05.716.114 I slot print_timing: id 0 | task 9417 | eval time = 1394.15 ms / 139 tokens ( 10.10 ms per token, 98.99 tokens per second) 2.05.716.115 I slot print_timing: id 0 | task 9417 | total time = 1546.69 ms / 535 tokens 2.05.716.115 I slot print_timing: id 0 | task 9417 | graphs reused = 8891 2.05.716.116 I slot print_timing: id 0 | task 9417 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.716.146 I slot release: id 0 | task 9417 | stop processing: n_tokens = 566, truncated = 0 2.05.740.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 125621226 2.05.807.460 I slot launch_slot_: id 0 | task 9559 | processing task, is_child = 0 2.07.589.456 I slot print_timing: id 0 | task 9559 | prompt eval time = 164.71 ms / 458 tokens ( 0.36 ms per token, 2780.73 tokens per second) 2.07.589.461 I slot print_timing: id 0 | task 9559 | eval time = 1617.27 ms / 161 tokens ( 10.11 ms per token, 98.93 tokens per second) 2.07.589.462 I slot print_timing: id 0 | task 9559 | total time = 1781.97 ms / 619 tokens 2.07.589.463 I slot print_timing: id 0 | task 9559 | graphs reused = 9049 2.07.589.464 I slot print_timing: id 0 | task 9559 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.589.495 I slot release: id 0 | task 9559 | stop processing: n_tokens = 650, truncated = 0 2.07.608.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 127494575 2.07.608.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 2.07.680.496 I slot launch_slot_: id 0 | task 9723 | processing task, is_child = 0 2.09.641.606 I slot print_timing: id 0 | task 9723 | prompt eval time = 168.52 ms / 458 tokens ( 0.37 ms per token, 2717.75 tokens per second) 2.09.641.612 I slot print_timing: id 0 | task 9723 | eval time = 1792.57 ms / 176 tokens ( 10.24 ms per token, 97.63 tokens per second) 2.09.641.613 I slot print_timing: id 0 | task 9723 | total time = 1961.09 ms / 634 tokens 2.09.641.614 I slot print_timing: id 0 | task 9723 | graphs reused = 9222 2.09.641.615 I slot print_timing: id 0 | task 9723 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.641.647 I slot release: id 0 | task 9723 | stop processing: n_tokens = 665, truncated = 0 2.09.664.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 129546727 2.09.664.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.09.740.280 I slot launch_slot_: id 0 | task 9902 | processing task, is_child = 0 2.12.016.919 I slot print_timing: id 0 | task 9902 | prompt eval time = 166.17 ms / 452 tokens ( 0.37 ms per token, 2720.04 tokens per second) 2.12.016.924 I slot print_timing: id 0 | task 9902 | eval time = 2110.44 ms / 210 tokens ( 10.10 ms per token, 99.03 tokens per second) 2.12.016.925 I slot print_timing: id 0 | task 9902 | total time = 2276.62 ms / 662 tokens 2.12.016.926 I slot print_timing: id 0 | task 9902 | graphs reused = 9429 2.12.016.927 I slot print_timing: id 0 | task 9902 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.016.961 I slot release: id 0 | task 9902 | stop processing: n_tokens = 693, truncated = 0 2.12.043.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 131922041 2.12.043.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.12.118.276 I slot launch_slot_: id 0 | task 10115 | processing task, is_child = 0 2.13.479.514 I slot print_timing: id 0 | task 10115 | prompt eval time = 156.46 ms / 404 tokens ( 0.39 ms per token, 2582.10 tokens per second) 2.13.479.520 I slot print_timing: id 0 | task 10115 | eval time = 1204.76 ms / 120 tokens ( 10.12 ms per token, 98.78 tokens per second) 2.13.479.521 I slot print_timing: id 0 | task 10115 | total time = 1361.22 ms / 524 tokens 2.13.479.521 I slot print_timing: id 0 | task 10115 | graphs reused = 9546 2.13.479.522 I slot print_timing: id 0 | task 10115 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.479.551 I slot release: id 0 | task 10115 | stop processing: n_tokens = 555, truncated = 0 2.13.505.373 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 133384631 2.13.505.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.13.570.636 I slot launch_slot_: id 0 | task 10238 | processing task, is_child = 0 2.14.776.879 I slot print_timing: id 0 | task 10238 | prompt eval time = 146.20 ms / 345 tokens ( 0.42 ms per token, 2359.75 tokens per second) 2.14.776.885 I slot print_timing: id 0 | task 10238 | eval time = 1060.02 ms / 106 tokens ( 10.10 ms per token, 99.05 tokens per second) 2.14.776.886 I slot print_timing: id 0 | task 10238 | total time = 1206.22 ms / 451 tokens 2.14.776.887 I slot print_timing: id 0 | task 10238 | graphs reused = 9650 2.14.776.888 I slot print_timing: id 0 | task 10238 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.776.915 I slot release: id 0 | task 10238 | stop processing: n_tokens = 482, truncated = 0 2.14.796.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 134681995 2.14.796.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.14.863.227 I slot launch_slot_: id 0 | task 10347 | processing task, is_child = 0 2.16.088.662 I slot print_timing: id 0 | task 10347 | prompt eval time = 168.68 ms / 430 tokens ( 0.39 ms per token, 2549.19 tokens per second) 2.16.088.669 I slot print_timing: id 0 | task 10347 | eval time = 1056.73 ms / 105 tokens ( 10.16 ms per token, 98.42 tokens per second) 2.16.088.670 I slot print_timing: id 0 | task 10347 | total time = 1225.41 ms / 535 tokens 2.16.088.671 I slot print_timing: id 0 | task 10347 | graphs reused = 9752 2.16.088.672 I slot print_timing: id 0 | task 10347 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.088.703 I slot release: id 0 | task 10347 | stop processing: n_tokens = 566, truncated = 0 2.16.103.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 135993782 2.16.103.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.16.189.342 I slot launch_slot_: id 0 | task 10455 | processing task, is_child = 0 2.17.205.171 I slot print_timing: id 0 | task 10455 | prompt eval time = 138.95 ms / 316 tokens ( 0.44 ms per token, 2274.15 tokens per second) 2.17.205.178 I slot print_timing: id 0 | task 10455 | eval time = 876.85 ms / 85 tokens ( 10.44 ms per token, 95.80 tokens per second) 2.17.205.179 I slot print_timing: id 0 | task 10455 | total time = 1015.81 ms / 401 tokens 2.17.205.180 I slot print_timing: id 0 | task 10455 | graphs reused = 9835 2.17.205.181 I slot print_timing: id 0 | task 10455 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.205.210 I slot release: id 0 | task 10455 | stop processing: n_tokens = 432, truncated = 0 2.17.228.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 137110290 2.17.228.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.17.316.122 I slot launch_slot_: id 0 | task 10543 | processing task, is_child = 0 2.18.535.644 I slot print_timing: id 0 | task 10543 | prompt eval time = 151.84 ms / 354 tokens ( 0.43 ms per token, 2331.40 tokens per second) 2.18.535.650 I slot print_timing: id 0 | task 10543 | eval time = 1067.66 ms / 107 tokens ( 10.07 ms per token, 99.28 tokens per second) 2.18.535.651 I slot print_timing: id 0 | task 10543 | total time = 1219.50 ms / 461 tokens 2.18.535.652 I slot print_timing: id 0 | task 10543 | graphs reused = 9940 2.18.535.653 I slot print_timing: id 0 | task 10543 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.535.683 I slot release: id 0 | task 10543 | stop processing: n_tokens = 492, truncated = 0 2.18.552.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 138440762 2.18.552.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.18.648.558 I slot launch_slot_: id 0 | task 10653 | processing task, is_child = 0 2.19.807.353 I slot print_timing: id 0 | task 10653 | prompt eval time = 172.61 ms / 438 tokens ( 0.39 ms per token, 2537.48 tokens per second) 2.19.807.360 I slot print_timing: id 0 | task 10653 | eval time = 986.16 ms / 98 tokens ( 10.17 ms per token, 98.36 tokens per second) 2.19.807.361 I slot print_timing: id 0 | task 10653 | total time = 1158.77 ms / 536 tokens 2.19.807.362 I slot print_timing: id 0 | task 10653 | graphs reused = 10035 2.19.807.363 I slot print_timing: id 0 | task 10653 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.807.398 I slot release: id 0 | task 10653 | stop processing: n_tokens = 567, truncated = 0 2.19.831.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 139712478 2.19.831.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.19.910.203 I slot launch_slot_: id 0 | task 10754 | processing task, is_child = 0 2.20.781.302 I slot print_timing: id 0 | task 10754 | prompt eval time = 168.78 ms / 457 tokens ( 0.37 ms per token, 2707.60 tokens per second) 2.20.781.308 I slot print_timing: id 0 | task 10754 | eval time = 702.29 ms / 70 tokens ( 10.18 ms per token, 98.25 tokens per second) 2.20.781.309 I slot print_timing: id 0 | task 10754 | total time = 871.08 ms / 527 tokens 2.20.781.309 I slot print_timing: id 0 | task 10754 | graphs reused = 10102 2.20.781.310 I slot print_timing: id 0 | task 10754 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.781.341 I slot release: id 0 | task 10754 | stop processing: n_tokens = 558, truncated = 0 2.20.809.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 140686421 2.20.809.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.20.872.547 I slot launch_slot_: id 0 | task 10827 | processing task, is_child = 0 2.22.026.906 I slot print_timing: id 0 | task 10827 | prompt eval time = 174.39 ms / 473 tokens ( 0.37 ms per token, 2712.31 tokens per second) 2.22.026.912 I slot print_timing: id 0 | task 10827 | eval time = 979.95 ms / 98 tokens ( 10.10 ms per token, 98.98 tokens per second) 2.22.026.913 I slot print_timing: id 0 | task 10827 | total time = 1154.34 ms / 571 tokens 2.22.026.914 I slot print_timing: id 0 | task 10827 | graphs reused = 10197 2.22.026.915 I slot print_timing: id 0 | task 10827 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.026.946 I slot release: id 0 | task 10827 | stop processing: n_tokens = 602, truncated = 0 2.22.043.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 141932026 2.22.043.415 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.22.106.859 I slot launch_slot_: id 0 | task 10928 | processing task, is_child = 0 2.24.081.646 I slot print_timing: id 0 | task 10928 | prompt eval time = 170.11 ms / 476 tokens ( 0.36 ms per token, 2798.14 tokens per second) 2.24.081.653 I slot print_timing: id 0 | task 10928 | eval time = 1804.65 ms / 177 tokens ( 10.25 ms per token, 97.53 tokens per second) 2.24.081.654 I slot print_timing: id 0 | task 10928 | total time = 1974.76 ms / 653 tokens 2.24.081.654 I slot print_timing: id 0 | task 10928 | graphs reused = 10371 2.24.081.655 I slot print_timing: id 0 | task 10928 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.081.689 I slot release: id 0 | task 10928 | stop processing: n_tokens = 684, truncated = 0 2.24.104.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 143986769 2.24.104.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.24.170.113 I slot launch_slot_: id 0 | task 11108 | processing task, is_child = 0 2.25.415.348 I slot print_timing: id 0 | task 11108 | prompt eval time = 172.78 ms / 466 tokens ( 0.37 ms per token, 2697.10 tokens per second) 2.25.415.353 I slot print_timing: id 0 | task 11108 | eval time = 1072.44 ms / 107 tokens ( 10.12 ms per token, 98.84 tokens per second) 2.25.415.354 I slot print_timing: id 0 | task 11108 | total time = 1245.21 ms / 573 tokens 2.25.415.355 I slot print_timing: id 0 | task 11108 | graphs reused = 10475 2.25.415.356 I slot print_timing: id 0 | task 11108 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.415.391 I slot release: id 0 | task 11108 | stop processing: n_tokens = 604, truncated = 0 2.25.443.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 145320471 2.25.443.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.25.512.107 I slot launch_slot_: id 0 | task 11218 | processing task, is_child = 0 2.26.449.504 I slot print_timing: id 0 | task 11218 | prompt eval time = 153.19 ms / 415 tokens ( 0.37 ms per token, 2709.07 tokens per second) 2.26.449.509 I slot print_timing: id 0 | task 11218 | eval time = 784.19 ms / 78 tokens ( 10.18 ms per token, 98.19 tokens per second) 2.26.449.511 I slot print_timing: id 0 | task 11218 | total time = 937.38 ms / 493 tokens 2.26.449.511 I slot print_timing: id 0 | task 11218 | graphs reused = 10550 2.26.449.512 I slot print_timing: id 0 | task 11218 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.449.543 I slot release: id 0 | task 11218 | stop processing: n_tokens = 524, truncated = 0 2.26.475.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 146354622 2.26.475.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.26.544.941 I slot launch_slot_: id 0 | task 11299 | processing task, is_child = 0 2.27.328.373 I slot print_timing: id 0 | task 11299 | prompt eval time = 146.64 ms / 352 tokens ( 0.42 ms per token, 2400.47 tokens per second) 2.27.328.379 I slot print_timing: id 0 | task 11299 | eval time = 636.77 ms / 64 tokens ( 10.11 ms per token, 98.94 tokens per second) 2.27.328.380 I slot print_timing: id 0 | task 11299 | total time = 783.41 ms / 416 tokens 2.27.328.380 I slot print_timing: id 0 | task 11299 | graphs reused = 10612 2.27.328.381 I slot print_timing: id 0 | task 11299 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.328.410 I slot release: id 0 | task 11299 | stop processing: n_tokens = 447, truncated = 0 2.27.354.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 147233489 2.27.354.116 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.27.445.804 I slot launch_slot_: id 0 | task 11366 | processing task, is_child = 0 2.28.970.897 I slot print_timing: id 0 | task 11366 | prompt eval time = 192.60 ms / 550 tokens ( 0.35 ms per token, 2855.60 tokens per second) 2.28.970.903 I slot print_timing: id 0 | task 11366 | eval time = 1332.47 ms / 133 tokens ( 10.09 ms per token, 99.06 tokens per second) 2.28.970.904 I slot print_timing: id 0 | task 11366 | total time = 1525.07 ms / 683 tokens 2.28.970.905 I slot print_timing: id 0 | task 11366 | graphs reused = 10743 2.28.970.906 I slot print_timing: id 0 | task 11366 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.970.943 I slot release: id 0 | task 11366 | stop processing: n_tokens = 714, truncated = 0 2.28.997.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 148876023 2.28.997.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.29.073.123 I slot launch_slot_: id 0 | task 11503 | processing task, is_child = 0 2.31.572.622 I slot print_timing: id 0 | task 11503 | prompt eval time = 230.33 ms / 772 tokens ( 0.30 ms per token, 3351.65 tokens per second) 2.31.572.628 I slot print_timing: id 0 | task 11503 | eval time = 2269.14 ms / 226 tokens ( 10.09 ms per token, 99.16 tokens per second) 2.31.572.629 I slot print_timing: id 0 | task 11503 | total time = 2499.48 ms / 998 tokens 2.31.572.629 I slot print_timing: id 0 | task 11503 | graphs reused = 10966 2.31.572.630 I slot print_timing: id 0 | task 11503 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.572.670 I slot release: id 0 | task 11503 | stop processing: n_tokens = 1029, truncated = 0 2.31.590.771 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 151477750 2.31.590.846 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.31.665.202 I slot launch_slot_: id 0 | task 11733 | processing task, is_child = 0 2.33.704.486 I slot print_timing: id 0 | task 11733 | prompt eval time = 223.04 ms / 683 tokens ( 0.33 ms per token, 3062.23 tokens per second) 2.33.704.492 I slot print_timing: id 0 | task 11733 | eval time = 1816.22 ms / 181 tokens ( 10.09 ms per token, 99.11 tokens per second) 2.33.704.493 I slot print_timing: id 0 | task 11733 | total time = 2039.26 ms / 864 tokens 2.33.704.494 I slot print_timing: id 0 | task 11733 | graphs reused = 11144 2.33.704.495 I slot print_timing: id 0 | task 11733 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.704.536 I slot release: id 0 | task 11733 | stop processing: n_tokens = 895, truncated = 0 2.33.722.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 153609615 2.33.722.869 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.33.833.562 I slot launch_slot_: id 0 | task 11918 | processing task, is_child = 0 2.36.233.887 I slot print_timing: id 0 | task 11918 | prompt eval time = 209.12 ms / 579 tokens ( 0.36 ms per token, 2768.76 tokens per second) 2.36.233.893 I slot print_timing: id 0 | task 11918 | eval time = 2191.18 ms / 218 tokens ( 10.10 ms per token, 99.03 tokens per second) 2.36.233.894 I slot print_timing: id 0 | task 11918 | total time = 2400.30 ms / 797 tokens 2.36.233.894 I slot print_timing: id 0 | task 11918 | graphs reused = 11359 2.36.233.895 I slot print_timing: id 0 | task 11918 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.233.930 I slot release: id 0 | task 11918 | stop processing: n_tokens = 828, truncated = 0 2.36.258.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 156139010 2.36.258.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.36.274.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.36.348.256 I slot launch_slot_: id 0 | task 12140 | processing task, is_child = 0 2.37.597.958 I slot print_timing: id 0 | task 12140 | prompt eval time = 182.48 ms / 500 tokens ( 0.36 ms per token, 2740.06 tokens per second) 2.37.597.963 I slot print_timing: id 0 | task 12140 | eval time = 1067.20 ms / 106 tokens ( 10.16 ms per token, 98.39 tokens per second) 2.37.597.964 I slot print_timing: id 0 | task 12140 | total time = 1249.68 ms / 606 tokens 2.37.597.965 I slot print_timing: id 0 | task 12140 | graphs reused = 11463 2.37.597.966 I slot print_timing: id 0 | task 12140 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.598.003 I slot release: id 0 | task 12140 | stop processing: n_tokens = 637, truncated = 0 2.37.613.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 157503083 2.37.613.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.37.676.826 I slot launch_slot_: id 0 | task 12249 | processing task, is_child = 0 2.40.019.922 I slot print_timing: id 0 | task 12249 | prompt eval time = 235.45 ms / 776 tokens ( 0.30 ms per token, 3295.86 tokens per second) 2.40.019.928 I slot print_timing: id 0 | task 12249 | eval time = 2107.63 ms / 209 tokens ( 10.13 ms per token, 98.69 tokens per second) 2.40.019.929 I slot print_timing: id 0 | task 12249 | total time = 2343.07 ms / 985 tokens 2.40.019.930 I slot print_timing: id 0 | task 12249 | graphs reused = 11670 2.40.019.930 I slot print_timing: id 0 | task 12249 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.019.970 I slot release: id 0 | task 12249 | stop processing: n_tokens = 1016, truncated = 0 2.40.046.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 159925050 2.40.046.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.40.118.359 I slot launch_slot_: id 0 | task 12462 | processing task, is_child = 0 2.42.271.427 I slot print_timing: id 0 | task 12462 | prompt eval time = 183.53 ms / 504 tokens ( 0.36 ms per token, 2746.12 tokens per second) 2.42.271.433 I slot print_timing: id 0 | task 12462 | eval time = 1969.52 ms / 197 tokens ( 10.05 ms per token, 99.52 tokens per second) 2.42.271.434 I slot print_timing: id 0 | task 12462 | total time = 2153.05 ms / 701 tokens 2.42.271.435 I slot print_timing: id 0 | task 12462 | graphs reused = 11865 2.42.271.436 I slot print_timing: id 0 | task 12462 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.271.470 I slot release: id 0 | task 12462 | stop processing: n_tokens = 732, truncated = 0 2.42.293.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 162176550 2.42.293.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.42.357.212 I slot launch_slot_: id 0 | task 12662 | processing task, is_child = 0 2.44.638.111 I slot print_timing: id 0 | task 12662 | prompt eval time = 207.12 ms / 633 tokens ( 0.33 ms per token, 3056.18 tokens per second) 2.44.638.117 I slot print_timing: id 0 | task 12662 | eval time = 2073.76 ms / 207 tokens ( 10.07 ms per token, 99.34 tokens per second) 2.44.638.117 I slot print_timing: id 0 | task 12662 | total time = 2280.88 ms / 840 tokens 2.44.638.119 I slot print_timing: id 0 | task 12662 | graphs reused = 12069 2.44.638.119 I slot print_timing: id 0 | task 12662 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.638.156 I slot release: id 0 | task 12662 | stop processing: n_tokens = 871, truncated = 0 2.44.642.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 164543235 2.44.642.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.960 MiB) 2.44.748.391 I slot launch_slot_: id 0 | task 12873 | processing task, is_child = 0 2.46.247.130 I slot print_timing: id 0 | task 12873 | prompt eval time = 158.96 ms / 395 tokens ( 0.40 ms per token, 2484.85 tokens per second) 2.46.247.136 I slot print_timing: id 0 | task 12873 | eval time = 1339.76 ms / 134 tokens ( 10.07 ms per token, 99.27 tokens per second) 2.46.247.137 I slot print_timing: id 0 | task 12873 | total time = 1498.72 ms / 529 tokens 2.46.247.137 I slot print_timing: id 0 | task 12873 | graphs reused = 12200 2.46.247.138 I slot print_timing: id 0 | task 12873 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.247.169 I slot release: id 0 | task 12873 | stop processing: n_tokens = 560, truncated = 0 2.46.264.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 166152249 2.46.265.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.46.372.997 I slot launch_slot_: id 0 | task 13010 | processing task, is_child = 0 2.48.661.899 I slot print_timing: id 0 | task 13010 | prompt eval time = 196.00 ms / 584 tokens ( 0.34 ms per token, 2979.64 tokens per second) 2.48.661.904 I slot print_timing: id 0 | task 13010 | eval time = 2092.88 ms / 209 tokens ( 10.06 ms per token, 99.38 tokens per second) 2.48.661.906 I slot print_timing: id 0 | task 13010 | total time = 2288.88 ms / 793 tokens 2.48.661.906 I slot print_timing: id 0 | task 13010 | graphs reused = 12406 2.48.661.907 I slot print_timing: id 0 | task 13010 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.661.948 I slot release: id 0 | task 13010 | stop processing: n_tokens = 824, truncated = 0 2.48.687.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 168567027 2.48.687.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.48.773.807 I slot launch_slot_: id 0 | task 13223 | processing task, is_child = 0 2.51.302.146 I slot print_timing: id 0 | task 13223 | prompt eval time = 223.00 ms / 695 tokens ( 0.32 ms per token, 3116.63 tokens per second) 2.51.302.152 I slot print_timing: id 0 | task 13223 | eval time = 2305.32 ms / 230 tokens ( 10.07 ms per token, 99.34 tokens per second) 2.51.302.153 I slot print_timing: id 0 | task 13223 | total time = 2528.32 ms / 925 tokens 2.51.302.154 I slot print_timing: id 0 | task 13223 | graphs reused = 12633 2.51.302.155 I slot print_timing: id 0 | task 13223 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.302.193 I slot release: id 0 | task 13223 | stop processing: n_tokens = 956, truncated = 0 2.51.324.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 171207273 2.51.325.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.51.401.422 I slot launch_slot_: id 0 | task 13457 | processing task, is_child = 0 2.53.546.699 I slot print_timing: id 0 | task 13457 | prompt eval time = 236.10 ms / 769 tokens ( 0.31 ms per token, 3257.08 tokens per second) 2.53.546.705 I slot print_timing: id 0 | task 13457 | eval time = 1909.16 ms / 191 tokens ( 10.05 ms per token, 99.52 tokens per second) 2.53.546.706 I slot print_timing: id 0 | task 13457 | total time = 2145.26 ms / 960 tokens 2.53.546.707 I slot print_timing: id 0 | task 13457 | graphs reused = 12822 2.53.546.707 I slot print_timing: id 0 | task 13457 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.546.748 I slot release: id 0 | task 13457 | stop processing: n_tokens = 991, truncated = 0 2.53.562.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 173451827 2.53.562.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.53.580.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 2.53.671.415 I slot launch_slot_: id 0 | task 13652 | processing task, is_child = 0 2.55.101.469 I slot print_timing: id 0 | task 13652 | prompt eval time = 194.24 ms / 576 tokens ( 0.34 ms per token, 2965.37 tokens per second) 2.55.101.475 I slot print_timing: id 0 | task 13652 | eval time = 1235.79 ms / 124 tokens ( 10.05 ms per token, 99.53 tokens per second) 2.55.101.476 I slot print_timing: id 0 | task 13652 | total time = 1430.03 ms / 700 tokens 2.55.101.477 I slot print_timing: id 0 | task 13652 | graphs reused = 12944 2.55.101.478 I slot print_timing: id 0 | task 13652 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.101.513 I slot release: id 0 | task 13652 | stop processing: n_tokens = 731, truncated = 0 2.55.126.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 175006592 2.55.126.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.55.206.637 I slot launch_slot_: id 0 | task 13780 | processing task, is_child = 0 2.58.184.703 I slot print_timing: id 0 | task 13780 | prompt eval time = 215.55 ms / 655 tokens ( 0.33 ms per token, 3038.71 tokens per second) 2.58.184.709 I slot print_timing: id 0 | task 13780 | eval time = 2762.49 ms / 275 tokens ( 10.08 ms per token, 99.19 tokens per second) 2.58.184.710 I slot print_timing: id 0 | task 13780 | total time = 2978.05 ms / 930 tokens 2.58.184.711 I slot print_timing: id 0 | task 13780 | graphs reused = 13216 2.58.184.712 I slot print_timing: id 0 | task 13780 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.184.750 I slot release: id 0 | task 13780 | stop processing: n_tokens = 961, truncated = 0 2.58.209.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 178089830 2.58.209.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.58.291.054 I slot launch_slot_: id 0 | task 14059 | processing task, is_child = 0 2.59.710.649 I slot print_timing: id 0 | task 14059 | prompt eval time = 208.09 ms / 621 tokens ( 0.34 ms per token, 2984.21 tokens per second) 2.59.710.655 I slot print_timing: id 0 | task 14059 | eval time = 1211.48 ms / 121 tokens ( 10.10 ms per token, 99.05 tokens per second) 2.59.710.656 I slot print_timing: id 0 | task 14059 | total time = 1419.57 ms / 742 tokens 2.59.710.657 I slot print_timing: id 0 | task 14059 | graphs reused = 13334 2.59.710.658 I slot print_timing: id 0 | task 14059 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.710.701 I slot release: id 0 | task 14059 | stop processing: n_tokens = 773, truncated = 0 2.59.733.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 179615781 2.59.733.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.59.840.137 I slot launch_slot_: id 0 | task 14184 | processing task, is_child = 0 3.01.881.652 I slot print_timing: id 0 | task 14184 | prompt eval time = 231.52 ms / 767 tokens ( 0.30 ms per token, 3312.87 tokens per second) 3.01.881.658 I slot print_timing: id 0 | task 14184 | eval time = 1809.97 ms / 178 tokens ( 10.23 ms per token, 97.79 tokens per second) 3.01.881.659 I slot print_timing: id 0 | task 14184 | total time = 2041.49 ms / 945 tokens 3.01.881.660 I slot print_timing: id 0 | task 14184 | graphs reused = 13510 3.01.881.661 I slot print_timing: id 0 | task 14184 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.881.705 I slot release: id 0 | task 14184 | stop processing: n_tokens = 976, truncated = 0 3.01.910.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 181786784 3.01.910.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 3.02.023.266 I slot launch_slot_: id 0 | task 14366 | processing task, is_child = 0 3.04.352.245 I slot print_timing: id 0 | task 14366 | prompt eval time = 256.35 ms / 864 tokens ( 0.30 ms per token, 3370.43 tokens per second) 3.04.352.251 I slot print_timing: id 0 | task 14366 | eval time = 2072.61 ms / 203 tokens ( 10.26 ms per token, 97.46 tokens per second) 3.04.352.252 I slot print_timing: id 0 | task 14366 | total time = 2328.96 ms / 1067 tokens 3.04.352.252 I slot print_timing: id 0 | task 14366 | graphs reused = 13710 3.04.352.253 I slot print_timing: id 0 | task 14366 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.352.298 I slot release: id 0 | task 14366 | stop processing: n_tokens = 1098, truncated = 0 3.04.381.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 184257378 3.04.381.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.04.401.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.04.477.491 I slot launch_slot_: id 0 | task 14573 | processing task, is_child = 0 3.05.991.964 I slot print_timing: id 0 | task 14573 | prompt eval time = 221.44 ms / 646 tokens ( 0.34 ms per token, 2917.20 tokens per second) 3.05.991.970 I slot print_timing: id 0 | task 14573 | eval time = 1293.01 ms / 129 tokens ( 10.10 ms per token, 98.99 tokens per second) 3.05.991.971 I slot print_timing: id 0 | task 14573 | total time = 1514.45 ms / 775 tokens 3.05.991.972 I slot print_timing: id 0 | task 14573 | graphs reused = 13836 3.05.991.973 I slot print_timing: id 0 | task 14573 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.992.012 I slot release: id 0 | task 14573 | stop processing: n_tokens = 806, truncated = 0 3.06.010.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 185897091 3.06.010.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.06.079.229 I slot launch_slot_: id 0 | task 14706 | processing task, is_child = 0 3.08.560.473 I slot print_timing: id 0 | task 14706 | prompt eval time = 225.50 ms / 720 tokens ( 0.31 ms per token, 3192.85 tokens per second) 3.08.560.479 I slot print_timing: id 0 | task 14706 | eval time = 2255.72 ms / 219 tokens ( 10.35 ms per token, 96.64 tokens per second) 3.08.560.480 I slot print_timing: id 0 | task 14706 | total time = 2481.22 ms / 939 tokens 3.08.560.481 I slot print_timing: id 0 | task 14706 | graphs reused = 14052 3.08.560.481 I slot print_timing: id 0 | task 14706 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.560.522 I slot release: id 0 | task 14706 | stop processing: n_tokens = 970, truncated = 0 3.08.587.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 188465601 3.08.587.070 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.894 MiB) 3.08.660.381 I slot launch_slot_: id 0 | task 14929 | processing task, is_child = 0 3.10.984.423 I slot print_timing: id 0 | task 14929 | prompt eval time = 186.73 ms / 509 tokens ( 0.37 ms per token, 2725.86 tokens per second) 3.10.984.429 I slot print_timing: id 0 | task 14929 | eval time = 2137.29 ms / 214 tokens ( 10.03 ms per token, 99.66 tokens per second) 3.10.984.430 I slot print_timing: id 0 | task 14929 | total time = 2324.02 ms / 723 tokens 3.10.984.432 I slot print_timing: id 0 | task 14929 | graphs reused = 14264 3.10.984.433 I slot print_timing: id 0 | task 14929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.984.467 I slot release: id 0 | task 14929 | stop processing: n_tokens = 754, truncated = 0 3.11.001.096 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 190889547 3.11.001.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 3.11.068.965 I slot launch_slot_: id 0 | task 15146 | processing task, is_child = 0 3.13.696.616 I slot print_timing: id 0 | task 15146 | prompt eval time = 198.47 ms / 581 tokens ( 0.34 ms per token, 2927.44 tokens per second) 3.13.696.622 I slot print_timing: id 0 | task 15146 | eval time = 2429.16 ms / 242 tokens ( 10.08 ms per token, 99.21 tokens per second) 3.13.696.623 I slot print_timing: id 0 | task 15146 | total time = 2627.63 ms / 823 tokens 3.13.696.623 I slot print_timing: id 0 | task 15146 | graphs reused = 14503 3.13.696.624 I slot print_timing: id 0 | task 15146 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.696.662 I slot release: id 0 | task 15146 | stop processing: n_tokens = 854, truncated = 0 3.13.702.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 193601741 3.13.702.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.13.784.542 I slot launch_slot_: id 0 | task 15392 | processing task, is_child = 0 3.16.264.186 I slot print_timing: id 0 | task 15392 | prompt eval time = 267.18 ms / 925 tokens ( 0.29 ms per token, 3462.12 tokens per second) 3.16.264.191 I slot print_timing: id 0 | task 15392 | eval time = 2212.45 ms / 220 tokens ( 10.10 ms per token, 98.99 tokens per second) 3.16.264.192 I slot print_timing: id 0 | task 15392 | total time = 2479.62 ms / 1145 tokens 3.16.264.193 I slot print_timing: id 0 | task 15392 | graphs reused = 14720 3.16.264.194 I slot print_timing: id 0 | task 15392 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.264.240 I slot release: id 0 | task 15392 | stop processing: n_tokens = 1176, truncated = 0 3.16.289.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 196169319 3.16.289.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.16.393.045 I slot launch_slot_: id 0 | task 15616 | processing task, is_child = 0 3.19.141.826 I slot print_timing: id 0 | task 15616 | prompt eval time = 253.87 ms / 885 tokens ( 0.29 ms per token, 3486.06 tokens per second) 3.19.141.832 I slot print_timing: id 0 | task 15616 | eval time = 2494.89 ms / 245 tokens ( 10.22 ms per token, 97.80 tokens per second) 3.19.141.833 I slot print_timing: id 0 | task 15616 | total time = 2748.76 ms / 1130 tokens 3.19.141.835 I slot print_timing: id 0 | task 15616 | graphs reused = 14962 3.19.141.836 I slot print_timing: id 0 | task 15616 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.141.883 I slot release: id 0 | task 15616 | stop processing: n_tokens = 1161, truncated = 0 3.19.161.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 199046962 3.19.161.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.19.238.555 I slot launch_slot_: id 0 | task 15865 | processing task, is_child = 0 3.20.677.443 I slot print_timing: id 0 | task 15865 | prompt eval time = 155.77 ms / 392 tokens ( 0.40 ms per token, 2516.55 tokens per second) 3.20.677.449 I slot print_timing: id 0 | task 15865 | eval time = 1283.10 ms / 128 tokens ( 10.10 ms per token, 98.98 tokens per second) 3.20.677.450 I slot print_timing: id 0 | task 15865 | total time = 1438.87 ms / 520 tokens 3.20.677.451 I slot print_timing: id 0 | task 15865 | graphs reused = 15087 3.20.677.452 I slot print_timing: id 0 | task 15865 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.677.482 I slot release: id 0 | task 15865 | stop processing: n_tokens = 551, truncated = 0 3.20.700.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 200582561 3.20.700.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.20.769.623 I slot launch_slot_: id 0 | task 15996 | processing task, is_child = 0 3.21.338.231 I slot print_timing: id 0 | task 15996 | prompt eval time = 141.82 ms / 331 tokens ( 0.43 ms per token, 2333.98 tokens per second) 3.21.338.237 I slot print_timing: id 0 | task 15996 | eval time = 426.77 ms / 43 tokens ( 10.16 ms per token, 98.41 tokens per second) 3.21.338.238 I slot print_timing: id 0 | task 15996 | total time = 568.59 ms / 374 tokens 3.21.338.238 I slot print_timing: id 0 | task 15996 | graphs reused = 15128 3.21.338.239 I slot print_timing: id 0 | task 15996 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.338.268 I slot release: id 0 | task 15996 | stop processing: n_tokens = 405, truncated = 0 3.21.352.212 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 201243347 3.21.352.256 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.21.418.977 I slot launch_slot_: id 0 | task 16042 | processing task, is_child = 0 3.23.301.102 I slot print_timing: id 0 | task 16042 | prompt eval time = 145.72 ms / 357 tokens ( 0.41 ms per token, 2449.89 tokens per second) 3.23.301.108 I slot print_timing: id 0 | task 16042 | eval time = 1736.38 ms / 172 tokens ( 10.15 ms per token, 98.48 tokens per second) 3.23.301.109 I slot print_timing: id 0 | task 16042 | total time = 1882.11 ms / 529 tokens 3.23.301.110 I slot print_timing: id 0 | task 16042 | graphs reused = 15297 3.23.301.111 I slot print_timing: id 0 | task 16042 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.301.138 I slot release: id 0 | task 16042 | stop processing: n_tokens = 560, truncated = 0 3.23.317.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 203206218 3.23.317.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.23.384.654 I slot launch_slot_: id 0 | task 16217 | processing task, is_child = 0 3.24.044.712 I slot print_timing: id 0 | task 16217 | prompt eval time = 141.76 ms / 315 tokens ( 0.45 ms per token, 2222.13 tokens per second) 3.24.044.719 I slot print_timing: id 0 | task 16217 | eval time = 518.28 ms / 52 tokens ( 10.16 ms per token, 98.40 tokens per second) 3.24.044.720 I slot print_timing: id 0 | task 16217 | total time = 660.04 ms / 367 tokens 3.24.044.721 I slot print_timing: id 0 | task 16217 | graphs reused = 15347 3.24.044.722 I slot print_timing: id 0 | task 16217 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.044.755 I slot release: id 0 | task 16217 | stop processing: n_tokens = 398, truncated = 0 3.24.066.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 203949835 3.24.066.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.24.131.059 I slot launch_slot_: id 0 | task 16272 | processing task, is_child = 0 3.25.095.511 I slot print_timing: id 0 | task 16272 | prompt eval time = 150.81 ms / 378 tokens ( 0.40 ms per token, 2506.43 tokens per second) 3.25.095.517 I slot print_timing: id 0 | task 16272 | eval time = 813.62 ms / 82 tokens ( 10.04 ms per token, 99.55 tokens per second) 3.25.095.518 I slot print_timing: id 0 | task 16272 | total time = 964.43 ms / 460 tokens 3.25.095.519 I slot print_timing: id 0 | task 16272 | graphs reused = 15427 3.25.095.520 I slot print_timing: id 0 | task 16272 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.095.550 I slot release: id 0 | task 16272 | stop processing: n_tokens = 491, truncated = 0 3.25.110.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 205000629 3.25.110.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.25.177.569 I slot launch_slot_: id 0 | task 16357 | processing task, is_child = 0 3.25.592.037 I slot print_timing: id 0 | task 16357 | prompt eval time = 139.94 ms / 295 tokens ( 0.47 ms per token, 2108.09 tokens per second) 3.25.592.043 I slot print_timing: id 0 | task 16357 | eval time = 274.51 ms / 28 tokens ( 10.17 ms per token, 98.36 tokens per second) 3.25.592.044 I slot print_timing: id 0 | task 16357 | total time = 414.45 ms / 323 tokens 3.25.592.045 I slot print_timing: id 0 | task 16357 | graphs reused = 15453 3.25.592.046 I slot print_timing: id 0 | task 16357 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.592.073 I slot release: id 0 | task 16357 | stop processing: n_tokens = 354, truncated = 0 3.25.607.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 205497153 3.25.607.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.25.671.727 I slot launch_slot_: id 0 | task 16388 | processing task, is_child = 0 3.28.506.523 I slot print_timing: id 0 | task 16388 | prompt eval time = 143.91 ms / 337 tokens ( 0.43 ms per token, 2341.76 tokens per second) 3.28.506.530 I slot print_timing: id 0 | task 16388 | eval time = 2690.87 ms / 268 tokens ( 10.08 ms per token, 99.22 tokens per second) 3.28.506.531 I slot print_timing: id 0 | task 16388 | total time = 2834.78 ms / 605 tokens 3.28.506.532 I slot print_timing: id 0 | task 16388 | graphs reused = 15718 3.28.506.533 I slot print_timing: id 0 | task 16388 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.506.561 I slot release: id 0 | task 16388 | stop processing: n_tokens = 636, truncated = 0 3.28.520.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 636, t_last = 208411641 3.28.520.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.28.593.809 I slot launch_slot_: id 0 | task 16659 | processing task, is_child = 0 3.29.939.347 I slot print_timing: id 0 | task 16659 | prompt eval time = 144.55 ms / 325 tokens ( 0.44 ms per token, 2248.33 tokens per second) 3.29.939.352 I slot print_timing: id 0 | task 16659 | eval time = 1200.97 ms / 120 tokens ( 10.09 ms per token, 99.09 tokens per second) 3.29.939.353 I slot print_timing: id 0 | task 16659 | total time = 1345.52 ms / 445 tokens 3.29.939.354 I slot print_timing: id 0 | task 16659 | graphs reused = 15836 3.29.939.355 I slot print_timing: id 0 | task 16659 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.939.386 I slot release: id 0 | task 16659 | stop processing: n_tokens = 476, truncated = 0 3.29.959.744 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.067 3.30.041.515 I slot launch_slot_: id 0 | task 16782 | processing task, is_child = 0 3.30.766.093 I slot print_timing: id 0 | task 16782 | prompt eval time = 130.39 ms / 264 tokens ( 0.49 ms per token, 2024.68 tokens per second) 3.30.766.099 I slot print_timing: id 0 | task 16782 | eval time = 594.17 ms / 60 tokens ( 10.07 ms per token, 99.30 tokens per second) 3.30.766.100 I slot print_timing: id 0 | task 16782 | total time = 724.56 ms / 324 tokens 3.30.766.101 I slot print_timing: id 0 | task 16782 | graphs reused = 15894 3.30.766.102 I slot print_timing: id 0 | task 16782 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.766.127 I slot release: id 0 | task 16782 | stop processing: n_tokens = 355, truncated = 0 3.30.788.760 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 210671207 3.30.788.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.30.876.281 I slot launch_slot_: id 0 | task 16845 | processing task, is_child = 0 3.31.228.888 I slot print_timing: id 0 | task 16845 | prompt eval time = 147.52 ms / 331 tokens ( 0.45 ms per token, 2243.81 tokens per second) 3.31.228.893 I slot print_timing: id 0 | task 16845 | eval time = 205.07 ms / 21 tokens ( 10.25 ms per token, 97.53 tokens per second) 3.31.228.894 I slot print_timing: id 0 | task 16845 | total time = 352.59 ms / 352 tokens 3.31.228.895 I slot print_timing: id 0 | task 16845 | graphs reused = 15913 3.31.228.896 I slot print_timing: id 0 | task 16845 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.228.925 I slot release: id 0 | task 16845 | stop processing: n_tokens = 383, truncated = 0 3.31.254.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 211134004 3.31.254.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.31.325.485 I slot launch_slot_: id 0 | task 16869 | processing task, is_child = 0 3.32.604.591 I slot print_timing: id 0 | task 16869 | prompt eval time = 143.38 ms / 333 tokens ( 0.43 ms per token, 2322.45 tokens per second) 3.32.604.597 I slot print_timing: id 0 | task 16869 | eval time = 1135.70 ms / 114 tokens ( 10.05 ms per token, 99.50 tokens per second) 3.32.604.598 I slot print_timing: id 0 | task 16869 | total time = 1279.09 ms / 447 tokens 3.32.604.600 I slot print_timing: id 0 | task 16869 | graphs reused = 16025 3.32.604.600 I slot print_timing: id 0 | task 16869 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.604.632 I slot release: id 0 | task 16869 | stop processing: n_tokens = 478, truncated = 0 3.32.633.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 212509711 3.32.633.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.32.703.320 I slot launch_slot_: id 0 | task 16986 | processing task, is_child = 0 3.33.375.020 I slot print_timing: id 0 | task 16986 | prompt eval time = 147.02 ms / 346 tokens ( 0.42 ms per token, 2353.42 tokens per second) 3.33.375.026 I slot print_timing: id 0 | task 16986 | eval time = 524.66 ms / 53 tokens ( 10.09 ms per token, 99.11 tokens per second) 3.33.375.027 I slot print_timing: id 0 | task 16986 | total time = 671.68 ms / 399 tokens 3.33.375.028 I slot print_timing: id 0 | task 16986 | graphs reused = 16076 3.33.375.029 I slot print_timing: id 0 | task 16986 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.375.060 I slot release: id 0 | task 16986 | stop processing: n_tokens = 430, truncated = 0 3.33.397.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 213280140 3.33.397.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.33.475.846 I slot launch_slot_: id 0 | task 17042 | processing task, is_child = 0 3.34.291.128 I slot print_timing: id 0 | task 17042 | prompt eval time = 141.54 ms / 325 tokens ( 0.44 ms per token, 2296.09 tokens per second) 3.34.291.134 I slot print_timing: id 0 | task 17042 | eval time = 673.72 ms / 68 tokens ( 10.06 ms per token, 99.45 tokens per second) 3.34.291.136 I slot print_timing: id 0 | task 17042 | total time = 815.26 ms / 393 tokens 3.34.291.137 I slot print_timing: id 0 | task 17042 | graphs reused = 16142 3.34.291.138 I slot print_timing: id 0 | task 17042 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.291.178 I slot release: id 0 | task 17042 | stop processing: n_tokens = 424, truncated = 0 3.34.295.026 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 214196258 3.34.295.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.34.368.026 I slot launch_slot_: id 0 | task 17113 | processing task, is_child = 0 3.37.169.815 I slot print_timing: id 0 | task 17113 | prompt eval time = 142.02 ms / 322 tokens ( 0.44 ms per token, 2267.32 tokens per second) 3.37.169.821 I slot print_timing: id 0 | task 17113 | eval time = 2659.75 ms / 266 tokens ( 10.04 ms per token, 99.63 tokens per second) 3.37.169.822 I slot print_timing: id 0 | task 17113 | total time = 2801.77 ms / 588 tokens 3.37.169.823 I slot print_timing: id 0 | task 17113 | graphs reused = 16405 3.37.169.824 I slot print_timing: id 0 | task 17113 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.169.852 I slot release: id 0 | task 17113 | stop processing: n_tokens = 619, truncated = 0 3.37.196.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 217074931 3.37.258.178 I slot launch_slot_: id 0 | task 17382 | processing task, is_child = 0 3.40.344.117 I slot print_timing: id 0 | task 17382 | prompt eval time = 145.68 ms / 338 tokens ( 0.43 ms per token, 2320.19 tokens per second) 3.40.344.123 I slot print_timing: id 0 | task 17382 | eval time = 2940.24 ms / 294 tokens ( 10.03 ms per token, 99.65 tokens per second) 3.40.344.124 I slot print_timing: id 0 | task 17382 | total time = 3085.92 ms / 632 tokens 3.40.344.124 I slot print_timing: id 0 | task 17382 | graphs reused = 16696 3.40.344.126 I slot print_timing: id 0 | task 17382 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.344.156 I slot release: id 0 | task 17382 | stop processing: n_tokens = 663, truncated = 0 3.40.357.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 220249235 3.40.357.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.40.457.740 I slot launch_slot_: id 0 | task 17679 | processing task, is_child = 0 3.43.429.427 I slot print_timing: id 0 | task 17679 | prompt eval time = 144.30 ms / 347 tokens ( 0.42 ms per token, 2404.65 tokens per second) 3.43.429.432 I slot print_timing: id 0 | task 17679 | eval time = 2827.36 ms / 282 tokens ( 10.06 ms per token, 99.39 tokens per second) 3.43.429.433 I slot print_timing: id 0 | task 17679 | total time = 2971.67 ms / 629 tokens 3.43.429.434 I slot print_timing: id 0 | task 17679 | graphs reused = 16975 3.43.429.434 I slot print_timing: id 0 | task 17679 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.429.462 I slot release: id 0 | task 17679 | stop processing: n_tokens = 660, truncated = 0 3.43.442.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 223334541 3.43.442.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.43.532.172 I slot launch_slot_: id 0 | task 17964 | processing task, is_child = 0 3.44.653.620 I slot print_timing: id 0 | task 17964 | prompt eval time = 146.72 ms / 331 tokens ( 0.44 ms per token, 2256.04 tokens per second) 3.44.653.626 I slot print_timing: id 0 | task 17964 | eval time = 974.71 ms / 98 tokens ( 10.05 ms per token, 99.52 tokens per second) 3.44.653.627 I slot print_timing: id 0 | task 17964 | total time = 1121.43 ms / 429 tokens 3.44.653.628 I slot print_timing: id 0 | task 17964 | graphs reused = 17071 3.44.653.628 I slot print_timing: id 0 | task 17964 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.653.656 I slot release: id 0 | task 17964 | stop processing: n_tokens = 460, truncated = 0 3.44.674.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 224558736 3.44.674.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 3.44.751.095 I slot launch_slot_: id 0 | task 18065 | processing task, is_child = 0 3.45.341.693 I slot print_timing: id 0 | task 18065 | prompt eval time = 145.14 ms / 345 tokens ( 0.42 ms per token, 2377.00 tokens per second) 3.45.341.699 I slot print_timing: id 0 | task 18065 | eval time = 445.44 ms / 45 tokens ( 10.12 ms per token, 98.78 tokens per second) 3.45.341.700 I slot print_timing: id 0 | task 18065 | total time = 590.58 ms / 390 tokens 3.45.341.702 I slot print_timing: id 0 | task 18065 | graphs reused = 17114 3.45.341.703 I slot print_timing: id 0 | task 18065 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.341.730 I slot release: id 0 | task 18065 | stop processing: n_tokens = 421, truncated = 0 3.45.345.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 225246809 3.45.345.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.45.405.884 I slot launch_slot_: id 0 | task 18113 | processing task, is_child = 0 3.46.075.879 I slot print_timing: id 0 | task 18113 | prompt eval time = 143.47 ms / 320 tokens ( 0.45 ms per token, 2230.43 tokens per second) 3.46.075.885 I slot print_timing: id 0 | task 18113 | eval time = 526.51 ms / 53 tokens ( 10.13 ms per token, 98.76 tokens per second) 3.46.075.886 I slot print_timing: id 0 | task 18113 | total time = 669.98 ms / 373 tokens 3.46.075.887 I slot print_timing: id 0 | task 18113 | graphs reused = 17165 3.46.075.888 I slot print_timing: id 0 | task 18113 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.075.916 I slot release: id 0 | task 18113 | stop processing: n_tokens = 404, truncated = 0 3.46.092.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 225980996 3.46.092.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.46.174.499 I slot launch_slot_: id 0 | task 18169 | processing task, is_child = 0 3.46.817.063 I slot print_timing: id 0 | task 18169 | prompt eval time = 141.37 ms / 297 tokens ( 0.48 ms per token, 2100.88 tokens per second) 3.46.817.070 I slot print_timing: id 0 | task 18169 | eval time = 501.17 ms / 47 tokens ( 10.90 ms per token, 91.78 tokens per second) 3.46.817.071 I slot print_timing: id 0 | task 18169 | total time = 642.54 ms / 344 tokens 3.46.817.072 I slot print_timing: id 0 | task 18169 | graphs reused = 17210 3.46.817.073 I slot print_timing: id 0 | task 18169 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.817.100 I slot release: id 0 | task 18169 | stop processing: n_tokens = 375, truncated = 0 3.46.842.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 226722179 3.46.901.140 I slot launch_slot_: id 0 | task 18219 | processing task, is_child = 0 3.49.754.815 I slot print_timing: id 0 | task 18219 | prompt eval time = 142.54 ms / 343 tokens ( 0.42 ms per token, 2406.38 tokens per second) 3.49.754.821 I slot print_timing: id 0 | task 18219 | eval time = 2711.12 ms / 271 tokens ( 10.04 ms per token, 99.59 tokens per second) 3.49.754.822 I slot print_timing: id 0 | task 18219 | total time = 2853.66 ms / 614 tokens 3.49.754.823 I slot print_timing: id 0 | task 18219 | graphs reused = 17478 3.49.754.823 I slot print_timing: id 0 | task 18219 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.754.851 I slot release: id 0 | task 18219 | stop processing: n_tokens = 645, truncated = 0 3.49.776.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 645, t_last = 229659931 3.49.776.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.49.849.563 I slot launch_slot_: id 0 | task 18493 | processing task, is_child = 0 3.51.033.163 I slot print_timing: id 0 | task 18493 | prompt eval time = 149.73 ms / 371 tokens ( 0.40 ms per token, 2477.81 tokens per second) 3.51.033.168 I slot print_timing: id 0 | task 18493 | eval time = 1033.85 ms / 104 tokens ( 10.04 ms per token, 99.63 tokens per second) 3.51.033.169 I slot print_timing: id 0 | task 18493 | total time = 1183.58 ms / 475 tokens 3.51.033.170 I slot print_timing: id 0 | task 18493 | graphs reused = 17580 3.51.033.171 I slot print_timing: id 0 | task 18493 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.033.201 I slot release: id 0 | task 18493 | stop processing: n_tokens = 506, truncated = 0 3.51.051.447 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 230938280 3.51.051.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.51.118.252 I slot launch_slot_: id 0 | task 18600 | processing task, is_child = 0 3.54.254.243 I slot print_timing: id 0 | task 18600 | n_gen = 300, tg = 99.63 t/s, tg_3s = 99.96 t/s 3.54.454.262 I slot print_timing: id 0 | task 18600 | prompt eval time = 134.82 ms / 292 tokens ( 0.46 ms per token, 2165.85 tokens per second) 3.54.454.269 I slot print_timing: id 0 | task 18600 | eval time = 3201.17 ms / 320 tokens ( 10.04 ms per token, 99.65 tokens per second) 3.54.454.270 I slot print_timing: id 0 | task 18600 | total time = 3335.99 ms / 612 tokens 3.54.454.271 I slot print_timing: id 0 | task 18600 | graphs reused = 17897 3.54.454.273 I slot print_timing: id 0 | task 18600 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.454.303 I slot release: id 0 | task 18600 | stop processing: n_tokens = 643, truncated = 0 3.54.482.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 234359383 3.54.482.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.54.554.788 I slot launch_slot_: id 0 | task 18923 | processing task, is_child = 0 3.55.413.251 I slot print_timing: id 0 | task 18923 | prompt eval time = 134.18 ms / 301 tokens ( 0.45 ms per token, 2243.34 tokens per second) 3.55.413.256 I slot print_timing: id 0 | task 18923 | eval time = 724.27 ms / 73 tokens ( 10.06 ms per token, 99.41 tokens per second) 3.55.413.257 I slot print_timing: id 0 | task 18923 | total time = 858.44 ms / 374 tokens 3.55.413.259 I slot print_timing: id 0 | task 18923 | graphs reused = 17968 3.55.413.260 I slot print_timing: id 0 | task 18923 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.413.287 I slot release: id 0 | task 18923 | stop processing: n_tokens = 405, truncated = 0 3.55.434.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 235318367 3.55.435.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 3.55.529.528 I slot launch_slot_: id 0 | task 18999 | processing task, is_child = 0 3.56.677.150 I slot print_timing: id 0 | task 18999 | prompt eval time = 143.39 ms / 303 tokens ( 0.47 ms per token, 2113.12 tokens per second) 3.56.677.156 I slot print_timing: id 0 | task 18999 | eval time = 1004.21 ms / 101 tokens ( 10.04 ms per token, 99.58 tokens per second) 3.56.677.157 I slot print_timing: id 0 | task 18999 | total time = 1147.60 ms / 404 tokens 3.56.677.157 I slot print_timing: id 0 | task 18999 | graphs reused = 18067 3.56.677.158 I slot print_timing: id 0 | task 18999 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.677.185 I slot release: id 0 | task 18999 | stop processing: n_tokens = 435, truncated = 0 3.56.697.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 236582265 3.56.697.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 3.56.766.666 I slot launch_slot_: id 0 | task 19103 | processing task, is_child = 0 3.57.212.834 I slot print_timing: id 0 | task 19103 | prompt eval time = 142.59 ms / 321 tokens ( 0.44 ms per token, 2251.19 tokens per second) 3.57.212.840 I slot print_timing: id 0 | task 19103 | eval time = 303.56 ms / 31 tokens ( 10.12 ms per token, 98.83 tokens per second) 3.57.212.841 I slot print_timing: id 0 | task 19103 | total time = 446.15 ms / 352 tokens 3.57.212.842 I slot print_timing: id 0 | task 19103 | graphs reused = 18096 3.57.212.843 I slot print_timing: id 0 | task 19103 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.212.869 I slot release: id 0 | task 19103 | stop processing: n_tokens = 383, truncated = 0 3.57.239.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 237117949 3.57.239.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.735 MiB) 3.57.309.101 I slot launch_slot_: id 0 | task 19137 | processing task, is_child = 0 3.57.894.851 I slot print_timing: id 0 | task 19137 | prompt eval time = 141.42 ms / 322 tokens ( 0.44 ms per token, 2276.95 tokens per second) 3.57.894.857 I slot print_timing: id 0 | task 19137 | eval time = 444.31 ms / 45 tokens ( 10.10 ms per token, 99.03 tokens per second) 3.57.894.858 I slot print_timing: id 0 | task 19137 | total time = 585.73 ms / 367 tokens 3.57.894.859 I slot print_timing: id 0 | task 19137 | graphs reused = 18139 3.57.894.859 I slot print_timing: id 0 | task 19137 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.894.889 I slot release: id 0 | task 19137 | stop processing: n_tokens = 398, truncated = 0 3.57.908.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 237799968 3.57.908.246 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.169 MiB) 3.57.970.443 I slot launch_slot_: id 0 | task 19185 | processing task, is_child = 0 3.58.788.704 I slot print_timing: id 0 | task 19185 | prompt eval time = 142.99 ms / 323 tokens ( 0.44 ms per token, 2258.84 tokens per second) 3.58.788.710 I slot print_timing: id 0 | task 19185 | eval time = 675.25 ms / 68 tokens ( 10.08 ms per token, 99.22 tokens per second) 3.58.788.711 I slot print_timing: id 0 | task 19185 | total time = 818.24 ms / 391 tokens 3.58.788.712 I slot print_timing: id 0 | task 19185 | graphs reused = 18205 3.58.788.713 I slot print_timing: id 0 | task 19185 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.788.742 I slot release: id 0 | task 19185 | stop processing: n_tokens = 422, truncated = 0 3.58.814.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 238693821 3.58.814.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.58.887.861 I slot launch_slot_: id 0 | task 19256 | processing task, is_child = 0 4.02.034.252 I slot print_timing: id 0 | task 19256 | n_gen = 299, tg = 99.23 t/s, tg_3s = 99.56 t/s 4.04.354.211 I slot print_timing: id 0 | task 19256 | prompt eval time = 143.25 ms / 321 tokens ( 0.45 ms per token, 2240.78 tokens per second) 4.04.354.216 I slot print_timing: id 0 | task 19256 | eval time = 5323.07 ms / 529 tokens ( 10.08 ms per token, 99.19 tokens per second) 4.04.354.217 I slot print_timing: id 0 | task 19256 | total time = 5466.33 ms / 850 tokens 4.04.354.218 I slot print_timing: id 0 | task 19256 | graphs reused = 18730 4.04.354.218 I slot print_timing: id 0 | task 19256 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.354.247 I slot release: id 0 | task 19256 | stop processing: n_tokens = 881, truncated = 0 4.04.377.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 881, t_last = 244259327 4.04.377.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.950 MiB) 4.04.491.840 I slot launch_slot_: id 0 | task 19788 | processing task, is_child = 0 4.06.792.364 I slot print_timing: id 0 | task 19788 | prompt eval time = 143.07 ms / 322 tokens ( 0.44 ms per token, 2250.65 tokens per second) 4.06.792.370 I slot print_timing: id 0 | task 19788 | eval time = 2157.43 ms / 216 tokens ( 10.03 ms per token, 99.66 tokens per second) 4.06.792.371 I slot print_timing: id 0 | task 19788 | total time = 2300.51 ms / 538 tokens 4.06.792.371 I slot print_timing: id 0 | task 19788 | graphs reused = 18943 4.06.792.372 I slot print_timing: id 0 | task 19788 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.792.399 I slot release: id 0 | task 19788 | stop processing: n_tokens = 569, truncated = 0 4.06.820.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 246697479 4.06.820.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 4.06.887.032 I slot launch_slot_: id 0 | task 20007 | processing task, is_child = 0 4.07.490.394 I slot print_timing: id 0 | task 20007 | prompt eval time = 143.43 ms / 337 tokens ( 0.43 ms per token, 2349.56 tokens per second) 4.07.490.400 I slot print_timing: id 0 | task 20007 | eval time = 459.90 ms / 46 tokens ( 10.22 ms per token, 97.85 tokens per second) 4.07.490.401 I slot print_timing: id 0 | task 20007 | total time = 603.34 ms / 383 tokens 4.07.490.402 I slot print_timing: id 0 | task 20007 | graphs reused = 18987 4.07.490.403 I slot print_timing: id 0 | task 20007 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.490.437 I slot release: id 0 | task 20007 | stop processing: n_tokens = 414, truncated = 0 4.07.518.013 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 247395516 4.07.518.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.07.609.448 I slot launch_slot_: id 0 | task 20056 | processing task, is_child = 0 4.08.222.467 I slot print_timing: id 0 | task 20056 | prompt eval time = 145.08 ms / 325 tokens ( 0.45 ms per token, 2240.19 tokens per second) 4.08.222.472 I slot print_timing: id 0 | task 20056 | eval time = 467.92 ms / 47 tokens ( 10.17 ms per token, 98.31 tokens per second) 4.08.222.473 I slot print_timing: id 0 | task 20056 | total time = 613.00 ms / 372 tokens 4.08.222.474 I slot print_timing: id 0 | task 20056 | graphs reused = 19032 4.08.222.475 I slot print_timing: id 0 | task 20056 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.222.505 I slot release: id 0 | task 20056 | stop processing: n_tokens = 403, truncated = 0 4.08.226.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 248127585 4.08.226.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.393 MiB) 4.08.323.236 I slot launch_slot_: id 0 | task 20106 | processing task, is_child = 0 4.08.980.746 I slot print_timing: id 0 | task 20106 | prompt eval time = 143.30 ms / 331 tokens ( 0.43 ms per token, 2309.79 tokens per second) 4.08.980.752 I slot print_timing: id 0 | task 20106 | eval time = 514.19 ms / 52 tokens ( 10.08 ms per token, 99.19 tokens per second) 4.08.980.752 I slot print_timing: id 0 | task 20106 | total time = 657.49 ms / 383 tokens 4.08.980.753 I slot print_timing: id 0 | task 20106 | graphs reused = 19082 4.08.980.754 I slot print_timing: id 0 | task 20106 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.980.782 I slot release: id 0 | task 20106 | stop processing: n_tokens = 414, truncated = 0 4.08.984.522 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 248885862 4.08.984.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.390 MiB) 4.09.055.467 I slot launch_slot_: id 0 | task 20161 | processing task, is_child = 0 4.10.065.911 I slot print_timing: id 0 | task 20161 | prompt eval time = 145.85 ms / 336 tokens ( 0.43 ms per token, 2303.69 tokens per second) 4.10.065.916 I slot print_timing: id 0 | task 20161 | eval time = 864.57 ms / 87 tokens ( 10.05 ms per token, 99.47 tokens per second) 4.10.065.917 I slot print_timing: id 0 | task 20161 | total time = 1010.42 ms / 423 tokens 4.10.065.918 I slot print_timing: id 0 | task 20161 | graphs reused = 19167 4.10.065.919 I slot print_timing: id 0 | task 20161 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.065.947 I slot release: id 0 | task 20161 | stop processing: n_tokens = 454, truncated = 0 4.10.080.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 249971027 4.10.080.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.606 MiB) 4.10.169.893 I slot launch_slot_: id 0 | task 20251 | processing task, is_child = 0 4.10.620.207 I slot print_timing: id 0 | task 20251 | prompt eval time = 146.00 ms / 349 tokens ( 0.42 ms per token, 2390.35 tokens per second) 4.10.620.212 I slot print_timing: id 0 | task 20251 | eval time = 304.29 ms / 31 tokens ( 10.14 ms per token, 98.59 tokens per second) 4.10.620.213 I slot print_timing: id 0 | task 20251 | total time = 450.29 ms / 380 tokens 4.10.620.214 I slot print_timing: id 0 | task 20251 | graphs reused = 19196 4.10.620.214 I slot print_timing: id 0 | task 20251 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.620.242 I slot release: id 0 | task 20251 | stop processing: n_tokens = 411, truncated = 0 4.10.639.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 250525322 4.10.639.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.10.708.954 I slot launch_slot_: id 0 | task 20285 | processing task, is_child = 0 4.13.851.903 I slot print_timing: id 0 | task 20285 | n_gen = 300, tg = 99.60 t/s, tg_3s = 99.93 t/s 4.16.852.678 I slot print_timing: id 0 | task 20285 | n_gen = 599, tg = 99.62 t/s, tg_3s = 99.64 t/s 4.19.862.549 I slot print_timing: id 0 | task 20285 | n_gen = 898, tg = 99.53 t/s, tg_3s = 99.34 t/s 4.20.811.856 I slot print_timing: id 0 | task 20285 | prompt eval time = 140.96 ms / 336 tokens ( 0.42 ms per token, 2383.69 tokens per second) 4.20.811.861 I slot print_timing: id 0 | task 20285 | eval time = 9961.92 ms / 992 tokens ( 10.05 ms per token, 99.48 tokens per second) 4.20.811.862 I slot print_timing: id 0 | task 20285 | total time = 10102.88 ms / 1328 tokens 4.20.811.863 I slot print_timing: id 0 | task 20285 | graphs reused = 20182 4.20.811.864 I slot print_timing: id 0 | task 20285 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.811.894 I slot release: id 0 | task 20285 | stop processing: n_tokens = 1359, truncated = 0 4.20.829.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1359, t_last = 260716973 4.20.829.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.452 MiB) 4.20.905.964 I slot launch_slot_: id 0 | task 21280 | processing task, is_child = 0 4.24.060.941 I slot print_timing: id 0 | task 21280 | n_gen = 301, tg = 99.68 t/s, tg_3s = 100.02 t/s 4.27.066.439 I slot print_timing: id 0 | task 21280 | n_gen = 600, tg = 99.58 t/s, tg_3s = 99.48 t/s 4.27.076.398 I slot print_timing: id 0 | task 21280 | prompt eval time = 145.45 ms / 349 tokens ( 0.42 ms per token, 2399.47 tokens per second) 4.27.076.403 I slot print_timing: id 0 | task 21280 | eval time = 6024.97 ms / 601 tokens ( 10.04 ms per token, 99.59 tokens per second) 4.27.076.404 I slot print_timing: id 0 | task 21280 | total time = 6170.42 ms / 950 tokens 4.27.076.405 I slot print_timing: id 0 | task 21280 | graphs reused = 20779 4.27.076.406 I slot print_timing: id 0 | task 21280 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.076.437 I slot release: id 0 | task 21280 | stop processing: n_tokens = 981, truncated = 0 4.27.100.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 981, t_last = 266981516 4.27.100.320 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.27.172.599 I slot launch_slot_: id 0 | task 21884 | processing task, is_child = 0 4.27.787.674 I slot print_timing: id 0 | task 21884 | prompt eval time = 148.12 ms / 349 tokens ( 0.42 ms per token, 2356.26 tokens per second) 4.27.787.680 I slot print_timing: id 0 | task 21884 | eval time = 466.94 ms / 47 tokens ( 10.15 ms per token, 98.51 tokens per second) 4.27.787.682 I slot print_timing: id 0 | task 21884 | total time = 615.06 ms / 396 tokens 4.27.787.682 I slot print_timing: id 0 | task 21884 | graphs reused = 20824 4.27.787.683 I slot print_timing: id 0 | task 21884 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.787.712 I slot release: id 0 | task 21884 | stop processing: n_tokens = 427, truncated = 0 4.27.801.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 267692792 4.27.802.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.763 MiB) 4.27.868.975 I slot launch_slot_: id 0 | task 21934 | processing task, is_child = 0 4.28.516.004 I slot print_timing: id 0 | task 21934 | prompt eval time = 151.57 ms / 385 tokens ( 0.39 ms per token, 2540.06 tokens per second) 4.28.516.010 I slot print_timing: id 0 | task 21934 | eval time = 495.44 ms / 50 tokens ( 10.11 ms per token, 98.90 tokens per second) 4.28.516.011 I slot print_timing: id 0 | task 21934 | total time = 647.01 ms / 435 tokens 4.28.516.012 I slot print_timing: id 0 | task 21934 | graphs reused = 20872 4.28.516.013 I slot print_timing: id 0 | task 21934 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.516.043 I slot release: id 0 | task 21934 | stop processing: n_tokens = 466, truncated = 0 4.28.519.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 268421123 4.28.519.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 4.28.586.292 I slot launch_slot_: id 0 | task 21987 | processing task, is_child = 0 4.29.296.199 I slot print_timing: id 0 | task 21987 | prompt eval time = 142.37 ms / 328 tokens ( 0.43 ms per token, 2303.89 tokens per second) 4.29.296.204 I slot print_timing: id 0 | task 21987 | eval time = 567.52 ms / 57 tokens ( 10.13 ms per token, 98.68 tokens per second) 4.29.296.205 I slot print_timing: id 0 | task 21987 | total time = 709.89 ms / 385 tokens 4.29.296.206 I slot print_timing: id 0 | task 21987 | graphs reused = 20927 4.29.296.206 I slot print_timing: id 0 | task 21987 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.296.235 I slot release: id 0 | task 21987 | stop processing: n_tokens = 416, truncated = 0