$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--mradermacher--Qwen3.5-4B-i1-GGUF\snapshots\8501a8b9bf0a85a86e4abce7b17870bcfad5d128\Qwen3.5-4B.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 0.00.093.668 I srv llama_server: initializing ... 0.00.093.675 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.093.802 I srv init_listene: The UI is disabled 0.00.093.805 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.093.896 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) 0.00.100.595 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--mradermacher--Qwen3.5-4B-i1-GGUF\snapshots\8501a8b9bf0a85a86e4abce7b17870bcfad5d128\Qwen3.5-4B.i1-Q4_K_M.gguf' 0.01.909.136 I cmn init: llama threadpool init, n_threads = 8 0.01.978.744 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.983.317 I srv llama_server: model loaded 0.01.983.324 I srv llama_server: listening on http://127.0.0.1:8089 0.02.538.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.539.041 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.02.986.636 I slot print_timing: id 0 | task 0 | prompt eval time = 100.65 ms / 368 tokens ( 0.27 ms per token, 3656.23 tokens per second) 0.02.986.642 I slot print_timing: id 0 | task 0 | eval time = 346.93 ms / 53 tokens ( 6.67 ms per token, 149.89 tokens per second) 0.02.986.643 I slot print_timing: id 0 | task 0 | total time = 447.58 ms / 421 tokens 0.02.986.648 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.02.986.649 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.02.986.678 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.004.435 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 2895041 0.03.029.863 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.390.018 I slot print_timing: id 0 | task 56 | prompt eval time = 88.71 ms / 322 tokens ( 0.28 ms per token, 3629.72 tokens per second) 0.03.390.024 I slot print_timing: id 0 | task 56 | eval time = 271.42 ms / 42 tokens ( 6.62 ms per token, 151.06 tokens per second) 0.03.390.025 I slot print_timing: id 0 | task 56 | total time = 360.13 ms / 364 tokens 0.03.390.026 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.390.027 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.390.055 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.412.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3298417 0.03.437.908 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.03.799.414 I slot print_timing: id 0 | task 101 | prompt eval time = 90.22 ms / 365 tokens ( 0.25 ms per token, 4045.44 tokens per second) 0.03.799.419 I slot print_timing: id 0 | task 101 | eval time = 271.26 ms / 42 tokens ( 6.62 ms per token, 151.15 tokens per second) 0.03.799.421 I slot print_timing: id 0 | task 101 | total time = 361.49 ms / 407 tokens 0.03.799.422 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.03.799.422 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.799.450 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.03.818.325 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 3707813 0.03.844.076 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.217.155 I slot print_timing: id 0 | task 146 | prompt eval time = 95.32 ms / 397 tokens ( 0.24 ms per token, 4165.05 tokens per second) 0.04.217.161 I slot print_timing: id 0 | task 146 | eval time = 277.74 ms / 43 tokens ( 6.61 ms per token, 151.22 tokens per second) 0.04.217.162 I slot print_timing: id 0 | task 146 | total time = 373.06 ms / 440 tokens 0.04.217.162 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.04.217.163 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.217.191 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.04.237.304 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 0.04.273.111 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.04.722.427 I slot print_timing: id 0 | task 192 | prompt eval time = 92.83 ms / 383 tokens ( 0.24 ms per token, 4125.87 tokens per second) 0.04.722.433 I slot print_timing: id 0 | task 192 | eval time = 356.46 ms / 55 tokens ( 6.60 ms per token, 151.49 tokens per second) 0.04.722.434 I slot print_timing: id 0 | task 192 | total time = 449.29 ms / 438 tokens 0.04.722.434 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.04.722.435 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.722.463 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.04.746.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 4630826 0.04.772.805 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.05.224.866 I slot print_timing: id 0 | task 250 | prompt eval time = 93.02 ms / 372 tokens ( 0.25 ms per token, 3999.31 tokens per second) 0.05.224.871 I slot print_timing: id 0 | task 250 | eval time = 359.02 ms / 55 tokens ( 6.65 ms per token, 150.41 tokens per second) 0.05.224.872 I slot print_timing: id 0 | task 250 | total time = 452.04 ms / 427 tokens 0.05.224.873 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.05.224.874 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.224.904 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.05.242.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5133267 0.05.269.146 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.05.729.999 I slot print_timing: id 0 | task 308 | prompt eval time = 102.29 ms / 422 tokens ( 0.24 ms per token, 4125.65 tokens per second) 0.05.730.005 I slot print_timing: id 0 | task 308 | eval time = 358.55 ms / 55 tokens ( 6.64 ms per token, 150.61 tokens per second) 0.05.730.006 I slot print_timing: id 0 | task 308 | total time = 460.83 ms / 477 tokens 0.05.730.007 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.05.730.008 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.730.042 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.05.746.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 5638404 0.05.772.766 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.06.456.078 I slot print_timing: id 0 | task 366 | prompt eval time = 103.73 ms / 470 tokens ( 0.22 ms per token, 4530.99 tokens per second) 0.06.456.084 I slot print_timing: id 0 | task 366 | eval time = 579.56 ms / 88 tokens ( 6.66 ms per token, 150.11 tokens per second) 0.06.456.085 I slot print_timing: id 0 | task 366 | total time = 683.29 ms / 558 tokens 0.06.456.087 I slot print_timing: id 0 | task 366 | graphs reused = 417 0.06.456.088 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.456.117 I slot release: id 0 | task 366 | stop processing: n_tokens = 557, truncated = 0 0.06.481.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 6364480 0.06.507.630 I slot launch_slot_: id 0 | task 457 | processing task, is_child = 0 0.06.900.020 I slot print_timing: id 0 | task 457 | prompt eval time = 88.91 ms / 345 tokens ( 0.26 ms per token, 3880.37 tokens per second) 0.06.900.025 I slot print_timing: id 0 | task 457 | eval time = 303.46 ms / 47 tokens ( 6.60 ms per token, 151.58 tokens per second) 0.06.900.026 I slot print_timing: id 0 | task 457 | total time = 392.37 ms / 392 tokens 0.06.900.027 I slot print_timing: id 0 | task 457 | graphs reused = 462 0.06.900.028 I slot print_timing: id 0 | task 457 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.900.056 I slot release: id 0 | task 457 | stop processing: n_tokens = 391, truncated = 0 0.06.920.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 6808419 0.06.945.667 I slot launch_slot_: id 0 | task 507 | processing task, is_child = 0 0.07.391.866 I slot print_timing: id 0 | task 507 | prompt eval time = 90.68 ms / 364 tokens ( 0.25 ms per token, 4013.98 tokens per second) 0.07.391.872 I slot print_timing: id 0 | task 507 | eval time = 355.50 ms / 55 tokens ( 6.58 ms per token, 151.90 tokens per second) 0.07.391.873 I slot print_timing: id 0 | task 507 | total time = 446.18 ms / 419 tokens 0.07.391.874 I slot print_timing: id 0 | task 507 | graphs reused = 515 0.07.391.875 I slot print_timing: id 0 | task 507 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.391.903 I slot release: id 0 | task 507 | stop processing: n_tokens = 418, truncated = 0 0.07.404.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 7300265 0.07.430.114 I slot launch_slot_: id 0 | task 565 | processing task, is_child = 0 0.07.959.153 I slot print_timing: id 0 | task 565 | prompt eval time = 93.23 ms / 376 tokens ( 0.25 ms per token, 4032.82 tokens per second) 0.07.959.159 I slot print_timing: id 0 | task 565 | eval time = 435.79 ms / 62 tokens ( 7.14 ms per token, 139.98 tokens per second) 0.07.959.160 I slot print_timing: id 0 | task 565 | total time = 529.02 ms / 438 tokens 0.07.959.161 I slot print_timing: id 0 | task 565 | graphs reused = 575 0.07.959.161 I slot print_timing: id 0 | task 565 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.959.188 I slot release: id 0 | task 565 | stop processing: n_tokens = 437, truncated = 0 0.07.980.948 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7867551 0.08.008.552 I slot launch_slot_: id 0 | task 630 | processing task, is_child = 0 0.08.408.237 I slot print_timing: id 0 | task 630 | prompt eval time = 95.50 ms / 412 tokens ( 0.23 ms per token, 4314.36 tokens per second) 0.08.408.243 I slot print_timing: id 0 | task 630 | eval time = 304.17 ms / 47 tokens ( 6.61 ms per token, 151.23 tokens per second) 0.08.408.244 I slot print_timing: id 0 | task 630 | total time = 399.67 ms / 459 tokens 0.08.408.245 I slot print_timing: id 0 | task 630 | graphs reused = 620 0.08.408.246 I slot print_timing: id 0 | task 630 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.408.278 I slot release: id 0 | task 630 | stop processing: n_tokens = 458, truncated = 0 0.08.436.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 8316641 0.08.461.716 I slot launch_slot_: id 0 | task 680 | processing task, is_child = 0 0.08.954.462 I slot print_timing: id 0 | task 680 | prompt eval time = 90.94 ms / 376 tokens ( 0.24 ms per token, 4134.73 tokens per second) 0.08.954.468 I slot print_timing: id 0 | task 680 | eval time = 401.79 ms / 62 tokens ( 6.59 ms per token, 151.82 tokens per second) 0.08.954.469 I slot print_timing: id 0 | task 680 | total time = 492.73 ms / 438 tokens 0.08.954.470 I slot print_timing: id 0 | task 680 | graphs reused = 680 0.08.954.470 I slot print_timing: id 0 | task 680 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.954.497 I slot release: id 0 | task 680 | stop processing: n_tokens = 437, truncated = 0 0.08.980.340 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8862860 0.09.006.061 I slot launch_slot_: id 0 | task 745 | processing task, is_child = 0 0.09.436.362 I slot print_timing: id 0 | task 745 | prompt eval time = 93.58 ms / 378 tokens ( 0.25 ms per token, 4039.54 tokens per second) 0.09.436.367 I slot print_timing: id 0 | task 745 | eval time = 336.70 ms / 52 tokens ( 6.60 ms per token, 151.47 tokens per second) 0.09.436.368 I slot print_timing: id 0 | task 745 | total time = 430.28 ms / 430 tokens 0.09.436.369 I slot print_timing: id 0 | task 745 | graphs reused = 730 0.09.436.370 I slot print_timing: id 0 | task 745 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.436.398 I slot release: id 0 | task 745 | stop processing: n_tokens = 429, truncated = 0 0.09.462.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 9344761 0.09.489.309 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 0.09.988.633 I slot print_timing: id 0 | task 800 | prompt eval time = 92.47 ms / 367 tokens ( 0.25 ms per token, 3968.98 tokens per second) 0.09.988.639 I slot print_timing: id 0 | task 800 | eval time = 406.84 ms / 58 tokens ( 7.14 ms per token, 140.10 tokens per second) 0.09.988.639 I slot print_timing: id 0 | task 800 | total time = 499.31 ms / 425 tokens 0.09.988.640 I slot print_timing: id 0 | task 800 | graphs reused = 786 0.09.988.641 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.988.669 I slot release: id 0 | task 800 | stop processing: n_tokens = 424, truncated = 0 0.10.010.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 9897031 0.10.039.058 I slot launch_slot_: id 0 | task 861 | processing task, is_child = 0 0.10.459.653 I slot print_timing: id 0 | task 861 | prompt eval time = 90.22 ms / 347 tokens ( 0.26 ms per token, 3846.11 tokens per second) 0.10.459.659 I slot print_timing: id 0 | task 861 | eval time = 330.35 ms / 51 tokens ( 6.61 ms per token, 151.35 tokens per second) 0.10.459.660 I slot print_timing: id 0 | task 861 | total time = 420.57 ms / 398 tokens 0.10.459.661 I slot print_timing: id 0 | task 861 | graphs reused = 835 0.10.459.662 I slot print_timing: id 0 | task 861 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.459.689 I slot release: id 0 | task 861 | stop processing: n_tokens = 397, truncated = 0 0.10.484.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 10368052 0.10.509.757 I slot launch_slot_: id 0 | task 915 | processing task, is_child = 0 0.10.867.167 I slot print_timing: id 0 | task 915 | prompt eval time = 90.48 ms / 369 tokens ( 0.25 ms per token, 4078.16 tokens per second) 0.10.867.174 I slot print_timing: id 0 | task 915 | eval time = 266.91 ms / 41 tokens ( 6.67 ms per token, 149.86 tokens per second) 0.10.867.175 I slot print_timing: id 0 | task 915 | total time = 357.39 ms / 410 tokens 0.10.867.176 I slot print_timing: id 0 | task 915 | graphs reused = 874 0.10.867.177 I slot print_timing: id 0 | task 915 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.867.207 I slot release: id 0 | task 915 | stop processing: n_tokens = 409, truncated = 0 0.10.890.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 10775570 0.10.916.025 I slot launch_slot_: id 0 | task 959 | processing task, is_child = 0 0.11.271.165 I slot print_timing: id 0 | task 959 | prompt eval time = 89.58 ms / 352 tokens ( 0.25 ms per token, 3929.49 tokens per second) 0.11.271.171 I slot print_timing: id 0 | task 959 | eval time = 265.54 ms / 41 tokens ( 6.64 ms per token, 150.64 tokens per second) 0.11.271.171 I slot print_timing: id 0 | task 959 | total time = 355.12 ms / 393 tokens 0.11.271.172 I slot print_timing: id 0 | task 959 | graphs reused = 913 0.11.271.174 I slot print_timing: id 0 | task 959 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.271.204 I slot release: id 0 | task 959 | stop processing: n_tokens = 392, truncated = 0 0.11.284.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 11179566 0.11.310.109 I slot launch_slot_: id 0 | task 1003 | processing task, is_child = 0 0.11.657.266 I slot print_timing: id 0 | task 1003 | prompt eval time = 88.83 ms / 349 tokens ( 0.25 ms per token, 3928.94 tokens per second) 0.11.657.272 I slot print_timing: id 0 | task 1003 | eval time = 258.31 ms / 40 tokens ( 6.62 ms per token, 150.98 tokens per second) 0.11.657.274 I slot print_timing: id 0 | task 1003 | total time = 347.13 ms / 389 tokens 0.11.657.275 I slot print_timing: id 0 | task 1003 | graphs reused = 951 0.11.657.276 I slot print_timing: id 0 | task 1003 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.657.307 I slot release: id 0 | task 1003 | stop processing: n_tokens = 388, truncated = 0 0.11.675.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 11565670 0.11.701.780 I slot launch_slot_: id 0 | task 1046 | processing task, is_child = 0 0.12.234.111 I slot print_timing: id 0 | task 1046 | prompt eval time = 94.37 ms / 384 tokens ( 0.25 ms per token, 4069.09 tokens per second) 0.12.234.117 I slot print_timing: id 0 | task 1046 | eval time = 437.94 ms / 63 tokens ( 7.06 ms per token, 141.57 tokens per second) 0.12.234.118 I slot print_timing: id 0 | task 1046 | total time = 532.31 ms / 447 tokens 0.12.234.119 I slot print_timing: id 0 | task 1046 | graphs reused = 1012 0.12.234.120 I slot print_timing: id 0 | task 1046 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.234.153 I slot release: id 0 | task 1046 | stop processing: n_tokens = 446, truncated = 0 0.12.249.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 12142515 0.12.279.589 I slot launch_slot_: id 0 | task 1112 | processing task, is_child = 0 0.12.719.549 I slot print_timing: id 0 | task 1112 | prompt eval time = 90.30 ms / 356 tokens ( 0.25 ms per token, 3942.24 tokens per second) 0.12.719.555 I slot print_timing: id 0 | task 1112 | eval time = 349.64 ms / 54 tokens ( 6.60 ms per token, 151.59 tokens per second) 0.12.719.556 I slot print_timing: id 0 | task 1112 | total time = 439.94 ms / 410 tokens 0.12.719.556 I slot print_timing: id 0 | task 1112 | graphs reused = 1064 0.12.719.557 I slot print_timing: id 0 | task 1112 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.719.584 I slot release: id 0 | task 1112 | stop processing: n_tokens = 409, truncated = 0 0.12.736.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 12627947 0.12.762.166 I slot launch_slot_: id 0 | task 1169 | processing task, is_child = 0 0.13.319.910 I slot print_timing: id 0 | task 1169 | prompt eval time = 95.09 ms / 410 tokens ( 0.23 ms per token, 4311.57 tokens per second) 0.13.319.916 I slot print_timing: id 0 | task 1169 | eval time = 462.63 ms / 70 tokens ( 6.70 ms per token, 149.15 tokens per second) 0.13.319.917 I slot print_timing: id 0 | task 1169 | total time = 557.72 ms / 480 tokens 0.13.319.918 I slot print_timing: id 0 | task 1169 | graphs reused = 1132 0.13.319.919 I slot print_timing: id 0 | task 1169 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.319.948 I slot release: id 0 | task 1169 | stop processing: n_tokens = 479, truncated = 0 0.13.344.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 13228311 0.13.370.440 I slot launch_slot_: id 0 | task 1242 | processing task, is_child = 0 0.13.840.987 I slot print_timing: id 0 | task 1242 | prompt eval time = 94.43 ms / 385 tokens ( 0.25 ms per token, 4077.18 tokens per second) 0.13.840.993 I slot print_timing: id 0 | task 1242 | eval time = 376.10 ms / 58 tokens ( 6.60 ms per token, 151.56 tokens per second) 0.13.840.995 I slot print_timing: id 0 | task 1242 | total time = 470.53 ms / 443 tokens 0.13.840.997 I slot print_timing: id 0 | task 1242 | graphs reused = 1188 0.13.840.998 I slot print_timing: id 0 | task 1242 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.841.027 I slot release: id 0 | task 1242 | stop processing: n_tokens = 442, truncated = 0 0.13.856.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 13749389 0.13.883.966 I slot launch_slot_: id 0 | task 1303 | processing task, is_child = 0 0.14.464.836 I slot print_timing: id 0 | task 1303 | prompt eval time = 99.65 ms / 395 tokens ( 0.25 ms per token, 3963.99 tokens per second) 0.14.464.841 I slot print_timing: id 0 | task 1303 | eval time = 481.20 ms / 73 tokens ( 6.68 ms per token, 149.63 tokens per second) 0.14.464.842 I slot print_timing: id 0 | task 1303 | total time = 580.85 ms / 468 tokens 0.14.464.843 I slot print_timing: id 0 | task 1303 | graphs reused = 1259 0.14.464.844 I slot print_timing: id 0 | task 1303 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.464.877 I slot release: id 0 | task 1303 | stop processing: n_tokens = 467, truncated = 0 0.14.490.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 14373239 0.14.516.740 I slot launch_slot_: id 0 | task 1379 | processing task, is_child = 0 0.14.998.978 I slot print_timing: id 0 | task 1379 | prompt eval time = 98.10 ms / 430 tokens ( 0.23 ms per token, 4383.46 tokens per second) 0.14.998.984 I slot print_timing: id 0 | task 1379 | eval time = 384.12 ms / 59 tokens ( 6.62 ms per token, 150.99 tokens per second) 0.14.998.985 I slot print_timing: id 0 | task 1379 | total time = 482.22 ms / 489 tokens 0.14.998.986 I slot print_timing: id 0 | task 1379 | graphs reused = 1316 0.14.998.987 I slot print_timing: id 0 | task 1379 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.999.018 I slot release: id 0 | task 1379 | stop processing: n_tokens = 488, truncated = 0 0.15.018.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 14907381 0.15.044.469 I slot launch_slot_: id 0 | task 1441 | processing task, is_child = 0 0.15.543.340 I slot print_timing: id 0 | task 1441 | prompt eval time = 95.36 ms / 392 tokens ( 0.24 ms per token, 4110.82 tokens per second) 0.15.543.346 I slot print_timing: id 0 | task 1441 | eval time = 403.49 ms / 62 tokens ( 6.61 ms per token, 151.18 tokens per second) 0.15.543.348 I slot print_timing: id 0 | task 1441 | total time = 498.85 ms / 454 tokens 0.15.543.348 I slot print_timing: id 0 | task 1441 | graphs reused = 1376 0.15.543.350 I slot print_timing: id 0 | task 1441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.543.379 I slot release: id 0 | task 1441 | stop processing: n_tokens = 453, truncated = 0 0.15.561.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 15451742 0.15.587.432 I slot launch_slot_: id 0 | task 1506 | processing task, is_child = 0 0.15.994.547 I slot print_timing: id 0 | task 1506 | prompt eval time = 89.41 ms / 350 tokens ( 0.26 ms per token, 3914.51 tokens per second) 0.15.994.553 I slot print_timing: id 0 | task 1506 | eval time = 317.69 ms / 49 tokens ( 6.62 ms per token, 151.09 tokens per second) 0.15.994.554 I slot print_timing: id 0 | task 1506 | total time = 407.10 ms / 399 tokens 0.15.994.554 I slot print_timing: id 0 | task 1506 | graphs reused = 1423 0.15.994.555 I slot print_timing: id 0 | task 1506 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.994.583 I slot release: id 0 | task 1506 | stop processing: n_tokens = 398, truncated = 0 0.16.018.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 15902945 0.16.043.623 I slot launch_slot_: id 0 | task 1558 | processing task, is_child = 0 0.16.533.607 I slot print_timing: id 0 | task 1558 | prompt eval time = 93.99 ms / 380 tokens ( 0.25 ms per token, 4042.90 tokens per second) 0.16.533.612 I slot print_timing: id 0 | task 1558 | eval time = 395.97 ms / 61 tokens ( 6.60 ms per token, 151.53 tokens per second) 0.16.533.613 I slot print_timing: id 0 | task 1558 | total time = 489.96 ms / 441 tokens 0.16.533.614 I slot print_timing: id 0 | task 1558 | graphs reused = 1482 0.16.533.615 I slot print_timing: id 0 | task 1558 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.533.642 I slot release: id 0 | task 1558 | stop processing: n_tokens = 440, truncated = 0 0.16.559.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 16442005 0.16.585.064 I slot launch_slot_: id 0 | task 1622 | processing task, is_child = 0 0.17.237.576 I slot print_timing: id 0 | task 1622 | prompt eval time = 97.53 ms / 410 tokens ( 0.24 ms per token, 4204.01 tokens per second) 0.17.237.582 I slot print_timing: id 0 | task 1622 | eval time = 554.96 ms / 80 tokens ( 7.02 ms per token, 142.35 tokens per second) 0.17.237.583 I slot print_timing: id 0 | task 1622 | total time = 652.49 ms / 490 tokens 0.17.237.584 I slot print_timing: id 0 | task 1622 | graphs reused = 1560 0.17.237.585 I slot print_timing: id 0 | task 1622 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.237.622 I slot release: id 0 | task 1622 | stop processing: n_tokens = 489, truncated = 0 0.17.262.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 17145984 0.17.287.929 I slot launch_slot_: id 0 | task 1705 | processing task, is_child = 0 0.17.824.701 I slot print_timing: id 0 | task 1705 | prompt eval time = 94.05 ms / 387 tokens ( 0.24 ms per token, 4115.05 tokens per second) 0.17.824.707 I slot print_timing: id 0 | task 1705 | eval time = 442.71 ms / 68 tokens ( 6.61 ms per token, 151.34 tokens per second) 0.17.824.708 I slot print_timing: id 0 | task 1705 | total time = 536.75 ms / 455 tokens 0.17.824.709 I slot print_timing: id 0 | task 1705 | graphs reused = 1626 0.17.824.710 I slot print_timing: id 0 | task 1705 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.824.738 I slot release: id 0 | task 1705 | stop processing: n_tokens = 454, truncated = 0 0.17.851.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 17733100 0.17.877.691 I slot launch_slot_: id 0 | task 1776 | processing task, is_child = 0 0.18.351.380 I slot print_timing: id 0 | task 1776 | prompt eval time = 89.67 ms / 358 tokens ( 0.25 ms per token, 3992.37 tokens per second) 0.18.351.386 I slot print_timing: id 0 | task 1776 | eval time = 384.00 ms / 59 tokens ( 6.62 ms per token, 151.04 tokens per second) 0.18.351.387 I slot print_timing: id 0 | task 1776 | total time = 473.67 ms / 417 tokens 0.18.351.387 I slot print_timing: id 0 | task 1776 | graphs reused = 1683 0.18.351.388 I slot print_timing: id 0 | task 1776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.351.417 I slot release: id 0 | task 1776 | stop processing: n_tokens = 416, truncated = 0 0.18.373.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 18259780 0.18.399.348 I slot launch_slot_: id 0 | task 1838 | processing task, is_child = 0 0.18.884.238 I slot print_timing: id 0 | task 1838 | prompt eval time = 89.37 ms / 359 tokens ( 0.25 ms per token, 4017.01 tokens per second) 0.18.884.243 I slot print_timing: id 0 | task 1838 | eval time = 395.50 ms / 56 tokens ( 7.19 ms per token, 139.06 tokens per second) 0.18.884.245 I slot print_timing: id 0 | task 1838 | total time = 484.87 ms / 415 tokens 0.18.884.246 I slot print_timing: id 0 | task 1838 | graphs reused = 1737 0.18.884.247 I slot print_timing: id 0 | task 1838 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.884.274 I slot release: id 0 | task 1838 | stop processing: n_tokens = 414, truncated = 0 0.18.908.408 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 18792636 0.18.933.843 I slot launch_slot_: id 0 | task 1897 | processing task, is_child = 0 0.19.423.951 I slot print_timing: id 0 | task 1897 | prompt eval time = 93.73 ms / 387 tokens ( 0.24 ms per token, 4128.97 tokens per second) 0.19.423.957 I slot print_timing: id 0 | task 1897 | eval time = 396.36 ms / 61 tokens ( 6.61 ms per token, 151.38 tokens per second) 0.19.423.958 I slot print_timing: id 0 | task 1897 | total time = 490.09 ms / 448 tokens 0.19.423.959 I slot print_timing: id 0 | task 1897 | graphs reused = 1796 0.19.423.960 I slot print_timing: id 0 | task 1897 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.423.989 I slot release: id 0 | task 1897 | stop processing: n_tokens = 447, truncated = 0 0.19.440.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 19332351 0.19.466.416 I slot launch_slot_: id 0 | task 1961 | processing task, is_child = 0 0.19.983.604 I slot print_timing: id 0 | task 1961 | prompt eval time = 95.25 ms / 410 tokens ( 0.23 ms per token, 4304.55 tokens per second) 0.19.983.609 I slot print_timing: id 0 | task 1961 | eval time = 421.92 ms / 61 tokens ( 7.03 ms per token, 142.21 tokens per second) 0.19.983.611 I slot print_timing: id 0 | task 1961 | total time = 517.17 ms / 471 tokens 0.19.983.611 I slot print_timing: id 0 | task 1961 | graphs reused = 1855 0.19.983.612 I slot print_timing: id 0 | task 1961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.983.643 I slot release: id 0 | task 1961 | stop processing: n_tokens = 470, truncated = 0 0.20.000.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 19892005 0.20.026.616 I slot launch_slot_: id 0 | task 2025 | processing task, is_child = 0 0.20.439.773 I slot print_timing: id 0 | task 2025 | prompt eval time = 88.93 ms / 351 tokens ( 0.25 ms per token, 3946.84 tokens per second) 0.20.439.779 I slot print_timing: id 0 | task 2025 | eval time = 324.21 ms / 50 tokens ( 6.62 ms per token, 151.14 tokens per second) 0.20.439.780 I slot print_timing: id 0 | task 2025 | total time = 413.14 ms / 401 tokens 0.20.439.781 I slot print_timing: id 0 | task 2025 | graphs reused = 1903 0.20.439.782 I slot print_timing: id 0 | task 2025 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.439.811 I slot release: id 0 | task 2025 | stop processing: n_tokens = 400, truncated = 0 0.20.467.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 20348174 0.20.492.159 I slot launch_slot_: id 0 | task 2078 | processing task, is_child = 0 0.22.051.139 I slot print_timing: id 0 | task 2078 | prompt eval time = 93.07 ms / 393 tokens ( 0.24 ms per token, 4222.81 tokens per second) 0.22.051.144 I slot print_timing: id 0 | task 2078 | eval time = 1465.89 ms / 224 tokens ( 6.57 ms per token, 152.13 tokens per second) 0.22.051.145 I slot print_timing: id 0 | task 2078 | total time = 1558.96 ms / 617 tokens 0.22.051.146 I slot print_timing: id 0 | task 2078 | graphs reused = 2124 0.22.051.147 I slot print_timing: id 0 | task 2078 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.051.178 I slot release: id 0 | task 2078 | stop processing: n_tokens = 616, truncated = 0 0.22.065.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 21959540 0.22.099.054 I slot launch_slot_: id 0 | task 2305 | processing task, is_child = 0 0.22.379.640 I slot print_timing: id 0 | task 2305 | prompt eval time = 87.28 ms / 321 tokens ( 0.27 ms per token, 3677.73 tokens per second) 0.22.379.646 I slot print_timing: id 0 | task 2305 | eval time = 193.28 ms / 30 tokens ( 6.66 ms per token, 150.04 tokens per second) 0.22.379.646 I slot print_timing: id 0 | task 2305 | total time = 280.57 ms / 351 tokens 0.22.379.647 I slot print_timing: id 0 | task 2305 | graphs reused = 2152 0.22.379.648 I slot print_timing: id 0 | task 2305 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.379.685 I slot release: id 0 | task 2305 | stop processing: n_tokens = 350, truncated = 0 0.22.406.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 22288048 0.22.432.065 I slot launch_slot_: id 0 | task 2338 | processing task, is_child = 0 0.22.818.655 I slot print_timing: id 0 | task 2338 | prompt eval time = 87.61 ms / 330 tokens ( 0.27 ms per token, 3766.69 tokens per second) 0.22.818.661 I slot print_timing: id 0 | task 2338 | eval time = 298.96 ms / 46 tokens ( 6.64 ms per token, 150.52 tokens per second) 0.22.818.662 I slot print_timing: id 0 | task 2338 | total time = 386.57 ms / 376 tokens 0.22.818.663 I slot print_timing: id 0 | task 2338 | graphs reused = 2196 0.22.818.663 I slot print_timing: id 0 | task 2338 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.818.691 I slot release: id 0 | task 2338 | stop processing: n_tokens = 375, truncated = 0 0.22.844.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 22727053 0.22.869.003 I slot launch_slot_: id 0 | task 2387 | processing task, is_child = 0 0.23.163.803 I slot print_timing: id 0 | task 2387 | prompt eval time = 88.25 ms / 341 tokens ( 0.26 ms per token, 3864.20 tokens per second) 0.23.163.809 I slot print_timing: id 0 | task 2387 | eval time = 206.53 ms / 32 tokens ( 6.66 ms per token, 150.10 tokens per second) 0.23.163.809 I slot print_timing: id 0 | task 2387 | total time = 294.78 ms / 373 tokens 0.23.163.810 I slot print_timing: id 0 | task 2387 | graphs reused = 2226 0.23.163.811 I slot print_timing: id 0 | task 2387 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.163.842 I slot release: id 0 | task 2387 | stop processing: n_tokens = 372, truncated = 0 0.23.186.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 23072205 0.23.211.689 I slot launch_slot_: id 0 | task 2422 | processing task, is_child = 0 0.23.613.891 I slot print_timing: id 0 | task 2422 | prompt eval time = 89.33 ms / 338 tokens ( 0.26 ms per token, 3783.51 tokens per second) 0.23.613.897 I slot print_timing: id 0 | task 2422 | eval time = 312.85 ms / 48 tokens ( 6.66 ms per token, 150.23 tokens per second) 0.23.613.898 I slot print_timing: id 0 | task 2422 | total time = 402.18 ms / 386 tokens 0.23.613.899 I slot print_timing: id 0 | task 2422 | graphs reused = 2272 0.23.613.899 I slot print_timing: id 0 | task 2422 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.613.928 I slot release: id 0 | task 2422 | stop processing: n_tokens = 385, truncated = 0 0.23.641.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 23522291 0.23.667.110 I slot launch_slot_: id 0 | task 2473 | processing task, is_child = 0 0.24.125.085 I slot print_timing: id 0 | task 2473 | prompt eval time = 94.79 ms / 395 tokens ( 0.24 ms per token, 4167.15 tokens per second) 0.24.125.091 I slot print_timing: id 0 | task 2473 | eval time = 363.17 ms / 56 tokens ( 6.60 ms per token, 151.45 tokens per second) 0.24.125.092 I slot print_timing: id 0 | task 2473 | total time = 457.95 ms / 451 tokens 0.24.125.093 I slot print_timing: id 0 | task 2473 | graphs reused = 2326 0.24.125.094 I slot print_timing: id 0 | task 2473 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.125.123 I slot release: id 0 | task 2473 | stop processing: n_tokens = 450, truncated = 0 0.24.142.144 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 24033486 0.24.167.853 I slot launch_slot_: id 0 | task 2532 | processing task, is_child = 0 0.24.836.351 I slot print_timing: id 0 | task 2532 | prompt eval time = 128.34 ms / 528 tokens ( 0.24 ms per token, 4114.01 tokens per second) 0.24.836.357 I slot print_timing: id 0 | task 2532 | eval time = 540.14 ms / 83 tokens ( 6.59 ms per token, 151.81 tokens per second) 0.24.836.359 I slot print_timing: id 0 | task 2532 | total time = 668.48 ms / 611 tokens 0.24.836.359 I slot print_timing: id 0 | task 2532 | graphs reused = 2407 0.24.836.360 I slot print_timing: id 0 | task 2532 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.836.396 I slot release: id 0 | task 2532 | stop processing: n_tokens = 610, truncated = 0 0.24.861.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 24744759 0.24.894.008 I slot launch_slot_: id 0 | task 2619 | processing task, is_child = 0 0.25.292.810 I slot print_timing: id 0 | task 2619 | prompt eval time = 107.12 ms / 331 tokens ( 0.32 ms per token, 3090.02 tokens per second) 0.25.292.816 I slot print_timing: id 0 | task 2619 | eval time = 291.66 ms / 45 tokens ( 6.63 ms per token, 150.86 tokens per second) 0.25.292.817 I slot print_timing: id 0 | task 2619 | total time = 398.78 ms / 376 tokens 0.25.292.818 I slot print_timing: id 0 | task 2619 | graphs reused = 2450 0.25.292.818 I slot print_timing: id 0 | task 2619 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.292.847 I slot release: id 0 | task 2619 | stop processing: n_tokens = 387, truncated = 0 0.25.314.787 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 25201210 0.25.345.448 I slot launch_slot_: id 0 | task 2667 | processing task, is_child = 0 0.25.801.004 I slot print_timing: id 0 | task 2667 | prompt eval time = 111.16 ms / 362 tokens ( 0.31 ms per token, 3256.60 tokens per second) 0.25.801.010 I slot print_timing: id 0 | task 2667 | eval time = 344.38 ms / 53 tokens ( 6.62 ms per token, 151.00 tokens per second) 0.25.801.011 I slot print_timing: id 0 | task 2667 | total time = 455.54 ms / 415 tokens 0.25.801.011 I slot print_timing: id 0 | task 2667 | graphs reused = 2501 0.25.801.012 I slot print_timing: id 0 | task 2667 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.801.040 I slot release: id 0 | task 2667 | stop processing: n_tokens = 426, truncated = 0 0.25.826.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 25709403 0.25.862.153 I slot launch_slot_: id 0 | task 2723 | processing task, is_child = 0 0.26.424.677 I slot print_timing: id 0 | task 2723 | prompt eval time = 114.78 ms / 419 tokens ( 0.27 ms per token, 3650.49 tokens per second) 0.26.424.682 I slot print_timing: id 0 | task 2723 | eval time = 447.72 ms / 69 tokens ( 6.58 ms per token, 151.88 tokens per second) 0.26.424.683 I slot print_timing: id 0 | task 2723 | total time = 562.50 ms / 488 tokens 0.26.424.684 I slot print_timing: id 0 | task 2723 | graphs reused = 2568 0.26.424.685 I slot print_timing: id 0 | task 2723 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.424.721 I slot release: id 0 | task 2723 | stop processing: n_tokens = 499, truncated = 0 0.26.451.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 26333083 0.26.482.889 I slot launch_slot_: id 0 | task 2795 | processing task, is_child = 0 0.27.130.483 I slot print_timing: id 0 | task 2795 | prompt eval time = 119.87 ms / 423 tokens ( 0.28 ms per token, 3528.73 tokens per second) 0.27.130.489 I slot print_timing: id 0 | task 2795 | eval time = 527.70 ms / 72 tokens ( 7.43 ms per token, 134.55 tokens per second) 0.27.130.491 I slot print_timing: id 0 | task 2795 | total time = 647.57 ms / 495 tokens 0.27.130.492 I slot print_timing: id 0 | task 2795 | graphs reused = 2638 0.27.130.493 I slot print_timing: id 0 | task 2795 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.130.528 I slot release: id 0 | task 2795 | stop processing: n_tokens = 506, truncated = 0 0.27.148.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 27038890 0.27.180.916 I slot launch_slot_: id 0 | task 2870 | processing task, is_child = 0 0.27.569.022 I slot print_timing: id 0 | task 2870 | prompt eval time = 109.14 ms / 341 tokens ( 0.32 ms per token, 3124.31 tokens per second) 0.27.569.028 I slot print_timing: id 0 | task 2870 | eval time = 278.94 ms / 43 tokens ( 6.64 ms per token, 150.57 tokens per second) 0.27.569.029 I slot print_timing: id 0 | task 2870 | total time = 388.08 ms / 384 tokens 0.27.569.030 I slot print_timing: id 0 | task 2870 | graphs reused = 2679 0.27.569.032 I slot print_timing: id 0 | task 2870 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.569.063 I slot release: id 0 | task 2870 | stop processing: n_tokens = 395, truncated = 0 0.27.584.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 27477425 0.27.615.358 I slot launch_slot_: id 0 | task 2916 | processing task, is_child = 0 0.28.028.612 I slot print_timing: id 0 | task 2916 | prompt eval time = 108.78 ms / 356 tokens ( 0.31 ms per token, 3272.57 tokens per second) 0.28.028.618 I slot print_timing: id 0 | task 2916 | eval time = 304.45 ms / 47 tokens ( 6.62 ms per token, 151.09 tokens per second) 0.28.028.619 I slot print_timing: id 0 | task 2916 | total time = 413.23 ms / 403 tokens 0.28.028.620 I slot print_timing: id 0 | task 2916 | graphs reused = 2724 0.28.028.620 I slot print_timing: id 0 | task 2916 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.028.650 I slot release: id 0 | task 2916 | stop processing: n_tokens = 414, truncated = 0 0.28.056.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 27937013 0.28.056.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.28.097.529 I slot launch_slot_: id 0 | task 2966 | processing task, is_child = 0 0.28.507.856 I slot print_timing: id 0 | task 2966 | prompt eval time = 111.62 ms / 362 tokens ( 0.31 ms per token, 3243.18 tokens per second) 0.28.507.861 I slot print_timing: id 0 | task 2966 | eval time = 298.69 ms / 46 tokens ( 6.64 ms per token, 150.66 tokens per second) 0.28.507.863 I slot print_timing: id 0 | task 2966 | total time = 410.31 ms / 408 tokens 0.28.507.864 I slot print_timing: id 0 | task 2966 | graphs reused = 2768 0.28.507.865 I slot print_timing: id 0 | task 2966 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.507.894 I slot release: id 0 | task 2966 | stop processing: n_tokens = 419, truncated = 0 0.28.529.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 28416256 0.28.529.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.28.573.507 I slot launch_slot_: id 0 | task 3015 | processing task, is_child = 0 0.29.150.596 I slot print_timing: id 0 | task 3015 | prompt eval time = 115.89 ms / 391 tokens ( 0.30 ms per token, 3373.89 tokens per second) 0.29.150.602 I slot print_timing: id 0 | task 3015 | eval time = 461.18 ms / 68 tokens ( 6.88 ms per token, 145.28 tokens per second) 0.29.150.603 I slot print_timing: id 0 | task 3015 | total time = 577.07 ms / 459 tokens 0.29.150.604 I slot print_timing: id 0 | task 3015 | graphs reused = 2834 0.29.150.605 I slot print_timing: id 0 | task 3015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.150.638 I slot release: id 0 | task 3015 | stop processing: n_tokens = 470, truncated = 0 0.29.178.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 29059001 0.29.179.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.29.222.594 I slot launch_slot_: id 0 | task 3086 | processing task, is_child = 0 0.29.684.497 I slot print_timing: id 0 | task 3086 | prompt eval time = 111.35 ms / 343 tokens ( 0.32 ms per token, 3080.43 tokens per second) 0.29.684.503 I slot print_timing: id 0 | task 3086 | eval time = 350.53 ms / 54 tokens ( 6.61 ms per token, 151.20 tokens per second) 0.29.684.504 I slot print_timing: id 0 | task 3086 | total time = 461.88 ms / 397 tokens 0.29.684.505 I slot print_timing: id 0 | task 3086 | graphs reused = 2886 0.29.684.506 I slot print_timing: id 0 | task 3086 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.684.538 I slot release: id 0 | task 3086 | stop processing: n_tokens = 408, truncated = 0 0.29.711.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 29592901 0.29.711.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.29.721.661 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.29.765.004 I slot launch_slot_: id 0 | task 3143 | processing task, is_child = 0 0.30.255.899 I slot print_timing: id 0 | task 3143 | prompt eval time = 113.79 ms / 401 tokens ( 0.28 ms per token, 3523.97 tokens per second) 0.30.255.905 I slot print_timing: id 0 | task 3143 | eval time = 377.08 ms / 58 tokens ( 6.62 ms per token, 151.16 tokens per second) 0.30.255.906 I slot print_timing: id 0 | task 3143 | total time = 490.88 ms / 459 tokens 0.30.255.907 I slot print_timing: id 0 | task 3143 | graphs reused = 2942 0.30.255.908 I slot print_timing: id 0 | task 3143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.255.942 I slot release: id 0 | task 3143 | stop processing: n_tokens = 470, truncated = 0 0.30.275.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 30164305 0.30.275.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.30.327.291 I slot launch_slot_: id 0 | task 3204 | processing task, is_child = 0 0.30.879.037 I slot print_timing: id 0 | task 3204 | prompt eval time = 110.45 ms / 355 tokens ( 0.31 ms per token, 3214.15 tokens per second) 0.30.879.043 I slot print_timing: id 0 | task 3204 | eval time = 441.28 ms / 68 tokens ( 6.59 ms per token, 151.83 tokens per second) 0.30.879.045 I slot print_timing: id 0 | task 3204 | total time = 551.73 ms / 423 tokens 0.30.879.045 I slot print_timing: id 0 | task 3204 | graphs reused = 3008 0.30.879.046 I slot print_timing: id 0 | task 3204 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.879.073 I slot release: id 0 | task 3204 | stop processing: n_tokens = 434, truncated = 0 0.30.897.528 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 30787436 0.30.897.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.30.941.381 I slot launch_slot_: id 0 | task 3275 | processing task, is_child = 0 0.31.446.452 I slot print_timing: id 0 | task 3275 | prompt eval time = 108.32 ms / 351 tokens ( 0.31 ms per token, 3240.31 tokens per second) 0.31.446.459 I slot print_timing: id 0 | task 3275 | eval time = 396.73 ms / 57 tokens ( 7.08 ms per token, 141.15 tokens per second) 0.31.446.460 I slot print_timing: id 0 | task 3275 | total time = 505.05 ms / 408 tokens 0.31.446.461 I slot print_timing: id 0 | task 3275 | graphs reused = 3063 0.31.446.461 I slot print_timing: id 0 | task 3275 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.446.490 I slot release: id 0 | task 3275 | stop processing: n_tokens = 419, truncated = 0 0.31.462.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 31354853 0.31.462.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.171 MiB) 0.31.472.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.31.515.926 I slot launch_slot_: id 0 | task 3335 | processing task, is_child = 0 0.32.250.072 I slot print_timing: id 0 | task 3335 | prompt eval time = 121.69 ms / 475 tokens ( 0.26 ms per token, 3903.43 tokens per second) 0.32.250.078 I slot print_timing: id 0 | task 3335 | eval time = 612.44 ms / 93 tokens ( 6.66 ms per token, 150.22 tokens per second) 0.32.250.079 I slot print_timing: id 0 | task 3335 | total time = 734.13 ms / 568 tokens 0.32.250.080 I slot print_timing: id 0 | task 3335 | graphs reused = 3153 0.32.250.081 I slot print_timing: id 0 | task 3335 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.250.116 I slot release: id 0 | task 3335 | stop processing: n_tokens = 579, truncated = 0 0.32.272.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 32158479 0.32.272.930 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.824 MiB) 0.32.322.725 I slot launch_slot_: id 0 | task 3431 | processing task, is_child = 0 0.33.048.527 I slot print_timing: id 0 | task 3431 | prompt eval time = 122.89 ms / 440 tokens ( 0.28 ms per token, 3580.47 tokens per second) 0.33.048.533 I slot print_timing: id 0 | task 3431 | eval time = 602.89 ms / 92 tokens ( 6.63 ms per token, 150.94 tokens per second) 0.33.048.534 I slot print_timing: id 0 | task 3431 | total time = 725.78 ms / 532 tokens 0.33.048.535 I slot print_timing: id 0 | task 3431 | graphs reused = 3242 0.33.048.536 I slot print_timing: id 0 | task 3431 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.048.568 I slot release: id 0 | task 3431 | stop processing: n_tokens = 543, truncated = 0 0.33.067.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 32956931 0.33.067.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.33.109.325 I slot launch_slot_: id 0 | task 3526 | processing task, is_child = 0 0.33.574.631 I slot print_timing: id 0 | task 3526 | prompt eval time = 107.29 ms / 345 tokens ( 0.31 ms per token, 3215.46 tokens per second) 0.33.574.637 I slot print_timing: id 0 | task 3526 | eval time = 357.99 ms / 55 tokens ( 6.63 ms per token, 150.84 tokens per second) 0.33.574.638 I slot print_timing: id 0 | task 3526 | total time = 465.28 ms / 400 tokens 0.33.574.639 I slot print_timing: id 0 | task 3526 | graphs reused = 3295 0.33.574.640 I slot print_timing: id 0 | task 3526 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.574.670 I slot release: id 0 | task 3526 | stop processing: n_tokens = 411, truncated = 0 0.33.598.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 33483033 0.33.598.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.33.609.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.33.652.667 I slot launch_slot_: id 0 | task 3584 | processing task, is_child = 0 0.34.122.445 I slot print_timing: id 0 | task 3584 | prompt eval time = 113.01 ms / 382 tokens ( 0.30 ms per token, 3380.23 tokens per second) 0.34.122.451 I slot print_timing: id 0 | task 3584 | eval time = 356.75 ms / 55 tokens ( 6.61 ms per token, 151.37 tokens per second) 0.34.122.452 I slot print_timing: id 0 | task 3584 | total time = 469.76 ms / 437 tokens 0.34.122.453 I slot print_timing: id 0 | task 3584 | graphs reused = 3348 0.34.122.454 I slot print_timing: id 0 | task 3584 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.122.484 I slot release: id 0 | task 3584 | stop processing: n_tokens = 448, truncated = 0 0.34.139.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 34030847 0.34.139.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.34.182.378 I slot launch_slot_: id 0 | task 3642 | processing task, is_child = 0 0.34.584.259 I slot print_timing: id 0 | task 3642 | prompt eval time = 110.06 ms / 337 tokens ( 0.33 ms per token, 3061.99 tokens per second) 0.34.584.265 I slot print_timing: id 0 | task 3642 | eval time = 291.80 ms / 45 tokens ( 6.63 ms per token, 150.79 tokens per second) 0.34.584.266 I slot print_timing: id 0 | task 3642 | total time = 401.86 ms / 382 tokens 0.34.584.267 I slot print_timing: id 0 | task 3642 | graphs reused = 3391 0.34.584.268 I slot print_timing: id 0 | task 3642 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.584.296 I slot release: id 0 | task 3642 | stop processing: n_tokens = 393, truncated = 0 0.34.607.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 34492659 0.34.607.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.34.650.325 I slot launch_slot_: id 0 | task 3690 | processing task, is_child = 0 0.35.246.128 I slot print_timing: id 0 | task 3690 | prompt eval time = 113.89 ms / 402 tokens ( 0.28 ms per token, 3529.63 tokens per second) 0.35.246.134 I slot print_timing: id 0 | task 3690 | eval time = 481.89 ms / 70 tokens ( 6.98 ms per token, 143.19 tokens per second) 0.35.246.135 I slot print_timing: id 0 | task 3690 | total time = 595.78 ms / 472 tokens 0.35.246.136 I slot print_timing: id 0 | task 3690 | graphs reused = 3459 0.35.246.136 I slot print_timing: id 0 | task 3690 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.246.169 I slot release: id 0 | task 3690 | stop processing: n_tokens = 483, truncated = 0 0.35.265.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 35154532 0.35.265.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.35.276.823 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.35.323.672 I slot launch_slot_: id 0 | task 3763 | processing task, is_child = 0 0.35.830.431 I slot print_timing: id 0 | task 3763 | prompt eval time = 135.47 ms / 549 tokens ( 0.25 ms per token, 4052.56 tokens per second) 0.35.830.436 I slot print_timing: id 0 | task 3763 | eval time = 371.27 ms / 57 tokens ( 6.63 ms per token, 150.83 tokens per second) 0.35.830.437 I slot print_timing: id 0 | task 3763 | total time = 506.74 ms / 606 tokens 0.35.830.439 I slot print_timing: id 0 | task 3763 | graphs reused = 3514 0.35.830.439 I slot print_timing: id 0 | task 3763 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.830.471 I slot release: id 0 | task 3763 | stop processing: n_tokens = 617, truncated = 0 0.35.855.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 35738833 0.35.855.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.35.906.370 I slot launch_slot_: id 0 | task 3824 | processing task, is_child = 0 0.36.431.462 I slot print_timing: id 0 | task 3824 | prompt eval time = 145.47 ms / 616 tokens ( 0.24 ms per token, 4234.43 tokens per second) 0.36.431.469 I slot print_timing: id 0 | task 3824 | eval time = 379.60 ms / 58 tokens ( 6.66 ms per token, 150.16 tokens per second) 0.36.431.470 I slot print_timing: id 0 | task 3824 | total time = 525.07 ms / 674 tokens 0.36.431.471 I slot print_timing: id 0 | task 3824 | graphs reused = 3570 0.36.431.472 I slot print_timing: id 0 | task 3824 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.431.513 I slot release: id 0 | task 3824 | stop processing: n_tokens = 685, truncated = 0 0.36.459.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 36339876 0.36.459.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.36.469.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.36.521.049 I slot launch_slot_: id 0 | task 3886 | processing task, is_child = 0 0.37.067.335 I slot print_timing: id 0 | task 3886 | prompt eval time = 150.22 ms / 665 tokens ( 0.23 ms per token, 4426.72 tokens per second) 0.37.067.341 I slot print_timing: id 0 | task 3886 | eval time = 396.04 ms / 61 tokens ( 6.60 ms per token, 151.50 tokens per second) 0.37.067.342 I slot print_timing: id 0 | task 3886 | total time = 546.27 ms / 726 tokens 0.37.067.343 I slot print_timing: id 0 | task 3886 | graphs reused = 3629 0.37.067.344 I slot print_timing: id 0 | task 3886 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.067.381 I slot release: id 0 | task 3886 | stop processing: n_tokens = 737, truncated = 0 0.37.083.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 36975744 0.37.083.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.37.093.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.37.149.039 I slot launch_slot_: id 0 | task 3951 | processing task, is_child = 0 0.37.657.722 I slot print_timing: id 0 | task 3951 | prompt eval time = 150.74 ms / 645 tokens ( 0.23 ms per token, 4278.92 tokens per second) 0.37.657.728 I slot print_timing: id 0 | task 3951 | eval time = 357.92 ms / 55 tokens ( 6.63 ms per token, 150.87 tokens per second) 0.37.657.729 I slot print_timing: id 0 | task 3951 | total time = 508.66 ms / 700 tokens 0.37.657.730 I slot print_timing: id 0 | task 3951 | graphs reused = 3682 0.37.657.730 I slot print_timing: id 0 | task 3951 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.657.767 I slot release: id 0 | task 3951 | stop processing: n_tokens = 711, truncated = 0 0.37.674.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 37566129 0.37.674.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.37.724.601 I slot launch_slot_: id 0 | task 4010 | processing task, is_child = 0 0.38.190.941 I slot print_timing: id 0 | task 4010 | prompt eval time = 124.51 ms / 474 tokens ( 0.26 ms per token, 3807.05 tokens per second) 0.38.190.947 I slot print_timing: id 0 | task 4010 | eval time = 341.81 ms / 52 tokens ( 6.70 ms per token, 149.20 tokens per second) 0.38.190.948 I slot print_timing: id 0 | task 4010 | total time = 466.32 ms / 526 tokens 0.38.190.949 I slot print_timing: id 0 | task 4010 | graphs reused = 3731 0.38.190.950 I slot print_timing: id 0 | task 4010 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.190.982 I slot release: id 0 | task 4010 | stop processing: n_tokens = 537, truncated = 0 0.38.219.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 38099345 0.38.219.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.356 MiB) 0.38.229.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.38.278.122 I slot launch_slot_: id 0 | task 4065 | processing task, is_child = 0 0.38.693.443 I slot print_timing: id 0 | task 4065 | prompt eval time = 143.41 ms / 617 tokens ( 0.23 ms per token, 4302.32 tokens per second) 0.38.693.449 I slot print_timing: id 0 | task 4065 | eval time = 271.89 ms / 42 tokens ( 6.63 ms per token, 150.80 tokens per second) 0.38.693.450 I slot print_timing: id 0 | task 4065 | total time = 415.30 ms / 659 tokens 0.38.693.451 I slot print_timing: id 0 | task 4065 | graphs reused = 3771 0.38.693.451 I slot print_timing: id 0 | task 4065 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.693.487 I slot release: id 0 | task 4065 | stop processing: n_tokens = 670, truncated = 0 0.38.716.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 38601850 0.38.716.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.38.764.583 I slot launch_slot_: id 0 | task 4111 | processing task, is_child = 0 0.39.218.415 I slot print_timing: id 0 | task 4111 | prompt eval time = 142.91 ms / 601 tokens ( 0.24 ms per token, 4205.30 tokens per second) 0.39.218.421 I slot print_timing: id 0 | task 4111 | eval time = 310.90 ms / 48 tokens ( 6.61 ms per token, 151.18 tokens per second) 0.39.218.422 I slot print_timing: id 0 | task 4111 | total time = 453.81 ms / 649 tokens 0.39.218.423 I slot print_timing: id 0 | task 4111 | graphs reused = 3817 0.39.218.423 I slot print_timing: id 0 | task 4111 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.218.459 I slot release: id 0 | task 4111 | stop processing: n_tokens = 660, truncated = 0 0.39.245.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 39126821 0.39.245.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.39.257.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.39.312.206 I slot launch_slot_: id 0 | task 4163 | processing task, is_child = 0 0.39.755.124 I slot print_timing: id 0 | task 4163 | prompt eval time = 137.90 ms / 533 tokens ( 0.26 ms per token, 3865.01 tokens per second) 0.39.755.129 I slot print_timing: id 0 | task 4163 | eval time = 304.99 ms / 47 tokens ( 6.63 ms per token, 150.82 tokens per second) 0.39.755.130 I slot print_timing: id 0 | task 4163 | total time = 442.90 ms / 580 tokens 0.39.755.131 I slot print_timing: id 0 | task 4163 | graphs reused = 3862 0.39.755.132 I slot print_timing: id 0 | task 4163 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.755.165 I slot release: id 0 | task 4163 | stop processing: n_tokens = 591, truncated = 0 0.39.775.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 39663528 0.39.776.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.39.826.687 I slot launch_slot_: id 0 | task 4214 | processing task, is_child = 0 0.40.295.216 I slot print_timing: id 0 | task 4214 | prompt eval time = 126.32 ms / 480 tokens ( 0.26 ms per token, 3799.78 tokens per second) 0.40.295.221 I slot print_timing: id 0 | task 4214 | eval time = 342.19 ms / 52 tokens ( 6.71 ms per token, 149.04 tokens per second) 0.40.295.223 I slot print_timing: id 0 | task 4214 | total time = 468.51 ms / 532 tokens 0.40.295.223 I slot print_timing: id 0 | task 4214 | graphs reused = 3911 0.40.295.224 I slot print_timing: id 0 | task 4214 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.295.257 I slot release: id 0 | task 4214 | stop processing: n_tokens = 560, truncated = 0 0.40.321.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 40203619 0.40.321.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.40.331.688 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.40.385.895 I slot launch_slot_: id 0 | task 4269 | processing task, is_child = 0 0.40.791.698 I slot print_timing: id 0 | task 4269 | prompt eval time = 134.13 ms / 567 tokens ( 0.24 ms per token, 4227.18 tokens per second) 0.40.791.704 I slot print_timing: id 0 | task 4269 | eval time = 271.65 ms / 42 tokens ( 6.63 ms per token, 150.93 tokens per second) 0.40.791.705 I slot print_timing: id 0 | task 4269 | total time = 405.79 ms / 609 tokens 0.40.791.705 I slot print_timing: id 0 | task 4269 | graphs reused = 3951 0.40.791.706 I slot print_timing: id 0 | task 4269 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.791.739 I slot release: id 0 | task 4269 | stop processing: n_tokens = 637, truncated = 0 0.40.819.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 40700102 0.40.819.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.40.829.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.40.897.166 I slot launch_slot_: id 0 | task 4315 | processing task, is_child = 0 0.41.441.119 I slot print_timing: id 0 | task 4315 | prompt eval time = 134.54 ms / 506 tokens ( 0.27 ms per token, 3760.82 tokens per second) 0.41.441.125 I slot print_timing: id 0 | task 4315 | eval time = 409.39 ms / 63 tokens ( 6.60 ms per token, 151.45 tokens per second) 0.41.441.126 I slot print_timing: id 0 | task 4315 | total time = 543.93 ms / 569 tokens 0.41.441.127 I slot print_timing: id 0 | task 4315 | graphs reused = 4012 0.41.441.127 I slot print_timing: id 0 | task 4315 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.441.160 I slot release: id 0 | task 4315 | stop processing: n_tokens = 597, truncated = 0 0.41.458.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 41349523 0.41.458.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.41.469.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.41.519.949 I slot launch_slot_: id 0 | task 4381 | processing task, is_child = 0 0.41.900.666 I slot print_timing: id 0 | task 4381 | prompt eval time = 120.52 ms / 436 tokens ( 0.28 ms per token, 3617.66 tokens per second) 0.41.900.672 I slot print_timing: id 0 | task 4381 | eval time = 260.18 ms / 40 tokens ( 6.67 ms per token, 149.90 tokens per second) 0.41.900.673 I slot print_timing: id 0 | task 4381 | total time = 380.70 ms / 476 tokens 0.41.900.674 I slot print_timing: id 0 | task 4381 | graphs reused = 4050 0.41.900.675 I slot print_timing: id 0 | task 4381 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.900.705 I slot release: id 0 | task 4381 | stop processing: n_tokens = 504, truncated = 0 0.41.927.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 41809067 0.41.927.829 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.41.980.801 I slot launch_slot_: id 0 | task 4424 | processing task, is_child = 0 0.42.515.690 I slot print_timing: id 0 | task 4424 | prompt eval time = 132.15 ms / 519 tokens ( 0.25 ms per token, 3927.30 tokens per second) 0.42.515.696 I slot print_timing: id 0 | task 4424 | eval time = 402.72 ms / 62 tokens ( 6.60 ms per token, 151.47 tokens per second) 0.42.515.696 I slot print_timing: id 0 | task 4424 | total time = 534.87 ms / 581 tokens 0.42.515.698 I slot print_timing: id 0 | task 4424 | graphs reused = 4110 0.42.515.699 I slot print_timing: id 0 | task 4424 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.515.734 I slot release: id 0 | task 4424 | stop processing: n_tokens = 609, truncated = 0 0.42.536.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 42424097 0.42.536.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.42.546.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.479 MiB) 0.42.603.027 I slot launch_slot_: id 0 | task 4490 | processing task, is_child = 0 0.43.025.909 I slot print_timing: id 0 | task 4490 | prompt eval time = 120.19 ms / 465 tokens ( 0.26 ms per token, 3868.91 tokens per second) 0.43.025.914 I slot print_timing: id 0 | task 4490 | eval time = 302.67 ms / 46 tokens ( 6.73 ms per token, 148.68 tokens per second) 0.43.025.915 I slot print_timing: id 0 | task 4490 | total time = 422.86 ms / 511 tokens 0.43.025.916 I slot print_timing: id 0 | task 4490 | graphs reused = 4153 0.43.025.917 I slot print_timing: id 0 | task 4490 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.025.949 I slot release: id 0 | task 4490 | stop processing: n_tokens = 542, truncated = 0 0.43.050.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 42934312 0.43.050.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.43.060.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.43.132.156 I slot launch_slot_: id 0 | task 4539 | processing task, is_child = 0 0.43.522.920 I slot print_timing: id 0 | task 4539 | prompt eval time = 125.64 ms / 431 tokens ( 0.29 ms per token, 3430.33 tokens per second) 0.43.522.925 I slot print_timing: id 0 | task 4539 | eval time = 265.10 ms / 41 tokens ( 6.63 ms per token, 150.89 tokens per second) 0.43.522.926 I slot print_timing: id 0 | task 4539 | total time = 390.74 ms / 472 tokens 0.43.522.927 I slot print_timing: id 0 | task 4539 | graphs reused = 4192 0.43.522.928 I slot print_timing: id 0 | task 4539 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.522.959 I slot release: id 0 | task 4539 | stop processing: n_tokens = 503, truncated = 0 0.43.547.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 43431321 0.43.547.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.43.557.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.43.617.572 I slot launch_slot_: id 0 | task 4583 | processing task, is_child = 0 0.44.028.330 I slot print_timing: id 0 | task 4583 | prompt eval time = 120.90 ms / 457 tokens ( 0.26 ms per token, 3780.08 tokens per second) 0.44.028.336 I slot print_timing: id 0 | task 4583 | eval time = 289.84 ms / 44 tokens ( 6.74 ms per token, 148.36 tokens per second) 0.44.028.337 I slot print_timing: id 0 | task 4583 | total time = 410.74 ms / 501 tokens 0.44.028.338 I slot print_timing: id 0 | task 4583 | graphs reused = 4233 0.44.028.339 I slot print_timing: id 0 | task 4583 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.028.372 I slot release: id 0 | task 4583 | stop processing: n_tokens = 532, truncated = 0 0.44.048.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 43936735 0.44.048.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.44.123.785 I slot launch_slot_: id 0 | task 4630 | processing task, is_child = 0 0.44.521.935 I slot print_timing: id 0 | task 4630 | prompt eval time = 126.10 ms / 439 tokens ( 0.29 ms per token, 3481.25 tokens per second) 0.44.521.940 I slot print_timing: id 0 | task 4630 | eval time = 272.03 ms / 42 tokens ( 6.63 ms per token, 150.72 tokens per second) 0.44.521.941 I slot print_timing: id 0 | task 4630 | total time = 398.13 ms / 481 tokens 0.44.521.942 I slot print_timing: id 0 | task 4630 | graphs reused = 4273 0.44.521.943 I slot print_timing: id 0 | task 4630 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.521.974 I slot release: id 0 | task 4630 | stop processing: n_tokens = 512, truncated = 0 0.44.548.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 44430337 0.44.548.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.44.561.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.44.621.698 I slot launch_slot_: id 0 | task 4675 | processing task, is_child = 0 0.45.124.369 I slot print_timing: id 0 | task 4675 | prompt eval time = 138.76 ms / 606 tokens ( 0.23 ms per token, 4367.10 tokens per second) 0.45.124.375 I slot print_timing: id 0 | task 4675 | eval time = 363.89 ms / 56 tokens ( 6.62 ms per token, 151.15 tokens per second) 0.45.124.376 I slot print_timing: id 0 | task 4675 | total time = 502.65 ms / 662 tokens 0.45.124.377 I slot print_timing: id 0 | task 4675 | graphs reused = 4327 0.45.124.377 I slot print_timing: id 0 | task 4675 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.124.414 I slot release: id 0 | task 4675 | stop processing: n_tokens = 693, truncated = 0 0.45.139.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 45032776 0.45.139.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.45.152.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.45.240.582 I slot launch_slot_: id 0 | task 4735 | processing task, is_child = 0 0.45.644.504 I slot print_timing: id 0 | task 4735 | prompt eval time = 133.46 ms / 477 tokens ( 0.28 ms per token, 3574.13 tokens per second) 0.45.644.511 I slot print_timing: id 0 | task 4735 | eval time = 270.44 ms / 41 tokens ( 6.76 ms per token, 147.91 tokens per second) 0.45.644.512 I slot print_timing: id 0 | task 4735 | total time = 403.90 ms / 518 tokens 0.45.644.513 I slot print_timing: id 0 | task 4735 | graphs reused = 4365 0.45.644.513 I slot print_timing: id 0 | task 4735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.644.548 I slot release: id 0 | task 4735 | stop processing: n_tokens = 549, truncated = 0 0.45.673.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 45552911 0.45.674.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.45.735.053 I slot launch_slot_: id 0 | task 4779 | processing task, is_child = 0 0.46.296.660 I slot print_timing: id 0 | task 4779 | prompt eval time = 170.66 ms / 845 tokens ( 0.20 ms per token, 4951.25 tokens per second) 0.46.296.666 I slot print_timing: id 0 | task 4779 | eval time = 390.93 ms / 60 tokens ( 6.63 ms per token, 150.92 tokens per second) 0.46.296.667 I slot print_timing: id 0 | task 4779 | total time = 561.59 ms / 905 tokens 0.46.296.668 I slot print_timing: id 0 | task 4779 | graphs reused = 4423 0.46.296.668 I slot print_timing: id 0 | task 4779 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.296.714 I slot release: id 0 | task 4779 | stop processing: n_tokens = 936, truncated = 0 0.46.310.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 46205077 0.46.310.920 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.46.323.886 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.46.392.281 I slot launch_slot_: id 0 | task 4843 | processing task, is_child = 0 0.46.800.083 I slot print_timing: id 0 | task 4843 | prompt eval time = 124.44 ms / 459 tokens ( 0.27 ms per token, 3688.61 tokens per second) 0.46.800.089 I slot print_timing: id 0 | task 4843 | eval time = 283.35 ms / 43 tokens ( 6.75 ms per token, 148.23 tokens per second) 0.46.800.090 I slot print_timing: id 0 | task 4843 | total time = 407.78 ms / 502 tokens 0.46.800.091 I slot print_timing: id 0 | task 4843 | graphs reused = 4463 0.46.800.091 I slot print_timing: id 0 | task 4843 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.800.123 I slot release: id 0 | task 4843 | stop processing: n_tokens = 533, truncated = 0 0.46.817.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 46708485 0.46.817.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.46.913.551 I slot launch_slot_: id 0 | task 4889 | processing task, is_child = 0 0.47.367.037 I slot print_timing: id 0 | task 4889 | prompt eval time = 148.15 ms / 670 tokens ( 0.22 ms per token, 4522.57 tokens per second) 0.47.367.043 I slot print_timing: id 0 | task 4889 | eval time = 305.32 ms / 47 tokens ( 6.64 ms per token, 150.66 tokens per second) 0.47.367.044 I slot print_timing: id 0 | task 4889 | total time = 453.47 ms / 717 tokens 0.47.367.045 I slot print_timing: id 0 | task 4889 | graphs reused = 4508 0.47.367.046 I slot print_timing: id 0 | task 4889 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.367.084 I slot release: id 0 | task 4889 | stop processing: n_tokens = 748, truncated = 0 0.47.392.307 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 47275447 0.47.392.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.47.405.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.47.474.088 I slot launch_slot_: id 0 | task 4940 | processing task, is_child = 0 0.48.084.861 I slot print_timing: id 0 | task 4940 | prompt eval time = 165.31 ms / 775 tokens ( 0.21 ms per token, 4688.13 tokens per second) 0.48.084.866 I slot print_timing: id 0 | task 4940 | eval time = 445.44 ms / 63 tokens ( 7.18 ms per token, 139.19 tokens per second) 0.48.084.867 I slot print_timing: id 0 | task 4940 | total time = 610.75 ms / 838 tokens 0.48.084.868 I slot print_timing: id 0 | task 4940 | graphs reused = 4569 0.48.084.869 I slot print_timing: id 0 | task 4940 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.084.916 I slot release: id 0 | task 4940 | stop processing: n_tokens = 869, truncated = 0 0.48.104.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 47993279 0.48.104.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.48.118.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 0.48.232.400 I slot launch_slot_: id 0 | task 5007 | processing task, is_child = 0 0.48.836.018 I slot print_timing: id 0 | task 5007 | prompt eval time = 142.39 ms / 573 tokens ( 0.25 ms per token, 4024.19 tokens per second) 0.48.836.024 I slot print_timing: id 0 | task 5007 | eval time = 461.21 ms / 71 tokens ( 6.59 ms per token, 151.77 tokens per second) 0.48.836.025 I slot print_timing: id 0 | task 5007 | total time = 603.60 ms / 644 tokens 0.48.836.026 I slot print_timing: id 0 | task 5007 | graphs reused = 4638 0.48.836.026 I slot print_timing: id 0 | task 5007 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.836.062 I slot release: id 0 | task 5007 | stop processing: n_tokens = 675, truncated = 0 0.48.850.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 48744425 0.48.850.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 0.48.863.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 0.48.932.636 I slot launch_slot_: id 0 | task 5082 | processing task, is_child = 0 0.49.477.392 I slot print_timing: id 0 | task 5082 | prompt eval time = 124.29 ms / 461 tokens ( 0.27 ms per token, 3709.10 tokens per second) 0.49.477.398 I slot print_timing: id 0 | task 5082 | eval time = 420.44 ms / 64 tokens ( 6.67 ms per token, 149.84 tokens per second) 0.49.477.399 I slot print_timing: id 0 | task 5082 | total time = 544.73 ms / 525 tokens 0.49.477.400 I slot print_timing: id 0 | task 5082 | graphs reused = 4699 0.49.477.401 I slot print_timing: id 0 | task 5082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.477.433 I slot release: id 0 | task 5082 | stop processing: n_tokens = 556, truncated = 0 0.49.506.728 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 49385796 0.49.506.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 0.49.568.217 I slot launch_slot_: id 0 | task 5149 | processing task, is_child = 0 0.49.961.521 I slot print_timing: id 0 | task 5149 | prompt eval time = 140.93 ms / 609 tokens ( 0.23 ms per token, 4321.20 tokens per second) 0.49.961.526 I slot print_timing: id 0 | task 5149 | eval time = 252.35 ms / 39 tokens ( 6.64 ms per token, 150.58 tokens per second) 0.49.961.529 I slot print_timing: id 0 | task 5149 | total time = 393.28 ms / 648 tokens 0.49.961.530 I slot print_timing: id 0 | task 5149 | graphs reused = 4736 0.49.961.531 I slot print_timing: id 0 | task 5149 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.961.569 I slot release: id 0 | task 5149 | stop processing: n_tokens = 679, truncated = 0 0.49.988.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 49869932 0.49.988.948 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 0.50.002.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 0.50.080.288 I slot launch_slot_: id 0 | task 5192 | processing task, is_child = 0 0.50.656.933 I slot print_timing: id 0 | task 5192 | prompt eval time = 179.59 ms / 791 tokens ( 0.23 ms per token, 4404.53 tokens per second) 0.50.656.939 I slot print_timing: id 0 | task 5192 | eval time = 397.04 ms / 61 tokens ( 6.62 ms per token, 151.12 tokens per second) 0.50.656.940 I slot print_timing: id 0 | task 5192 | total time = 576.62 ms / 852 tokens 0.50.656.940 I slot print_timing: id 0 | task 5192 | graphs reused = 4795 0.50.656.941 I slot print_timing: id 0 | task 5192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.656.985 I slot release: id 0 | task 5192 | stop processing: n_tokens = 883, truncated = 0 0.50.678.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 50565347 0.50.678.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 0.50.783.221 I slot launch_slot_: id 0 | task 5257 | processing task, is_child = 0 0.51.281.364 I slot print_timing: id 0 | task 5257 | prompt eval time = 131.57 ms / 533 tokens ( 0.25 ms per token, 4051.08 tokens per second) 0.51.281.371 I slot print_timing: id 0 | task 5257 | eval time = 366.55 ms / 56 tokens ( 6.66 ms per token, 150.05 tokens per second) 0.51.281.373 I slot print_timing: id 0 | task 5257 | total time = 498.12 ms / 589 tokens 0.51.281.374 I slot print_timing: id 0 | task 5257 | graphs reused = 4849 0.51.281.374 I slot print_timing: id 0 | task 5257 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.281.415 I slot release: id 0 | task 5257 | stop processing: n_tokens = 677, truncated = 0 0.51.309.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 51189778 0.51.309.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 0.51.396.999 I slot launch_slot_: id 0 | task 5317 | processing task, is_child = 0 0.51.868.265 I slot print_timing: id 0 | task 5317 | prompt eval time = 145.24 ms / 566 tokens ( 0.26 ms per token, 3897.05 tokens per second) 0.51.868.271 I slot print_timing: id 0 | task 5317 | eval time = 326.01 ms / 46 tokens ( 7.24 ms per token, 138.03 tokens per second) 0.51.868.272 I slot print_timing: id 0 | task 5317 | total time = 471.24 ms / 612 tokens 0.51.868.273 I slot print_timing: id 0 | task 5317 | graphs reused = 4893 0.51.868.273 I slot print_timing: id 0 | task 5317 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.868.310 I slot release: id 0 | task 5317 | stop processing: n_tokens = 643, truncated = 0 0.51.889.028 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 51776673 0.51.889.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 0.51.959.451 I slot launch_slot_: id 0 | task 5367 | processing task, is_child = 0 0.52.366.044 I slot print_timing: id 0 | task 5367 | prompt eval time = 122.84 ms / 443 tokens ( 0.28 ms per token, 3606.23 tokens per second) 0.52.366.050 I slot print_timing: id 0 | task 5367 | eval time = 283.73 ms / 43 tokens ( 6.76 ms per token, 148.03 tokens per second) 0.52.366.051 I slot print_timing: id 0 | task 5367 | total time = 406.57 ms / 486 tokens 0.52.366.053 I slot print_timing: id 0 | task 5367 | graphs reused = 4933 0.52.366.054 I slot print_timing: id 0 | task 5367 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.366.083 I slot release: id 0 | task 5367 | stop processing: n_tokens = 517, truncated = 0 0.52.387.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 52274446 0.52.387.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 0.52.452.879 I slot launch_slot_: id 0 | task 5413 | processing task, is_child = 0 0.52.997.913 I slot print_timing: id 0 | task 5413 | prompt eval time = 122.37 ms / 487 tokens ( 0.25 ms per token, 3979.70 tokens per second) 0.52.997.920 I slot print_timing: id 0 | task 5413 | eval time = 422.64 ms / 65 tokens ( 6.60 ms per token, 151.43 tokens per second) 0.52.997.921 I slot print_timing: id 0 | task 5413 | total time = 545.01 ms / 552 tokens 0.52.997.922 I slot print_timing: id 0 | task 5413 | graphs reused = 4996 0.52.997.923 I slot print_timing: id 0 | task 5413 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.997.959 I slot release: id 0 | task 5413 | stop processing: n_tokens = 583, truncated = 0 0.53.002.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 52906322 0.53.002.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 0.53.069.333 I slot launch_slot_: id 0 | task 5481 | processing task, is_child = 0 0.53.507.820 I slot print_timing: id 0 | task 5481 | prompt eval time = 133.12 ms / 507 tokens ( 0.26 ms per token, 3808.68 tokens per second) 0.53.507.825 I slot print_timing: id 0 | task 5481 | eval time = 305.35 ms / 47 tokens ( 6.64 ms per token, 150.65 tokens per second) 0.53.507.826 I slot print_timing: id 0 | task 5481 | total time = 438.47 ms / 554 tokens 0.53.507.827 I slot print_timing: id 0 | task 5481 | graphs reused = 5041 0.53.507.828 I slot print_timing: id 0 | task 5481 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.507.864 I slot release: id 0 | task 5481 | stop processing: n_tokens = 585, truncated = 0 0.53.523.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 53416227 0.53.523.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 0.53.540.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 0.53.603.647 I slot launch_slot_: id 0 | task 5531 | processing task, is_child = 0 0.54.176.070 I slot print_timing: id 0 | task 5531 | prompt eval time = 143.13 ms / 633 tokens ( 0.23 ms per token, 4422.68 tokens per second) 0.54.176.077 I slot print_timing: id 0 | task 5531 | eval time = 429.28 ms / 66 tokens ( 6.60 ms per token, 151.42 tokens per second) 0.54.176.078 I slot print_timing: id 0 | task 5531 | total time = 572.40 ms / 699 tokens 0.54.176.079 I slot print_timing: id 0 | task 5531 | graphs reused = 5105 0.54.176.080 I slot print_timing: id 0 | task 5531 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.176.121 I slot release: id 0 | task 5531 | stop processing: n_tokens = 730, truncated = 0 0.54.201.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 54084484 0.54.201.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 0.54.296.456 I slot launch_slot_: id 0 | task 5601 | processing task, is_child = 0 0.54.820.175 I slot print_timing: id 0 | task 5601 | prompt eval time = 140.53 ms / 571 tokens ( 0.25 ms per token, 4063.33 tokens per second) 0.54.820.181 I slot print_timing: id 0 | task 5601 | eval time = 383.17 ms / 59 tokens ( 6.61 ms per token, 151.37 tokens per second) 0.54.820.182 I slot print_timing: id 0 | task 5601 | total time = 523.70 ms / 630 tokens 0.54.820.183 I slot print_timing: id 0 | task 5601 | graphs reused = 5162 0.54.820.184 I slot print_timing: id 0 | task 5601 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.820.218 I slot release: id 0 | task 5601 | stop processing: n_tokens = 661, truncated = 0 0.54.845.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 54728581 0.54.845.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 0.54.915.760 I slot launch_slot_: id 0 | task 5664 | processing task, is_child = 0 0.55.366.362 I slot print_timing: id 0 | task 5664 | prompt eval time = 164.39 ms / 798 tokens ( 0.21 ms per token, 4854.19 tokens per second) 0.55.366.368 I slot print_timing: id 0 | task 5664 | eval time = 286.19 ms / 44 tokens ( 6.66 ms per token, 150.25 tokens per second) 0.55.366.369 I slot print_timing: id 0 | task 5664 | total time = 450.58 ms / 842 tokens 0.55.366.369 I slot print_timing: id 0 | task 5664 | graphs reused = 5204 0.55.366.370 I slot print_timing: id 0 | task 5664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.366.412 I slot release: id 0 | task 5664 | stop processing: n_tokens = 873, truncated = 0 0.55.370.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 55274774 0.55.370.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 0.55.390.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 0.55.457.660 I slot launch_slot_: id 0 | task 5712 | processing task, is_child = 0 0.55.877.052 I slot print_timing: id 0 | task 5712 | prompt eval time = 139.82 ms / 572 tokens ( 0.24 ms per token, 4090.92 tokens per second) 0.55.877.059 I slot print_timing: id 0 | task 5712 | eval time = 279.55 ms / 43 tokens ( 6.66 ms per token, 150.24 tokens per second) 0.55.877.060 I slot print_timing: id 0 | task 5712 | total time = 419.37 ms / 615 tokens 0.55.877.061 I slot print_timing: id 0 | task 5712 | graphs reused = 5245 0.55.877.062 I slot print_timing: id 0 | task 5712 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.877.101 I slot release: id 0 | task 5712 | stop processing: n_tokens = 646, truncated = 0 0.55.896.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 55785464 0.55.896.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 0.55.996.426 I slot launch_slot_: id 0 | task 5759 | processing task, is_child = 0 0.56.557.118 I slot print_timing: id 0 | task 5759 | prompt eval time = 144.27 ms / 613 tokens ( 0.24 ms per token, 4249.10 tokens per second) 0.56.557.123 I slot print_timing: id 0 | task 5759 | eval time = 416.41 ms / 64 tokens ( 6.61 ms per token, 151.29 tokens per second) 0.56.557.124 I slot print_timing: id 0 | task 5759 | total time = 560.67 ms / 677 tokens 0.56.557.125 I slot print_timing: id 0 | task 5759 | graphs reused = 5307 0.56.557.126 I slot print_timing: id 0 | task 5759 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.557.162 I slot release: id 0 | task 5759 | stop processing: n_tokens = 708, truncated = 0 0.56.579.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 56465525 0.56.579.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 0.56.653.028 I slot launch_slot_: id 0 | task 5827 | processing task, is_child = 0 0.57.208.471 I slot print_timing: id 0 | task 5827 | prompt eval time = 137.86 ms / 580 tokens ( 0.24 ms per token, 4207.26 tokens per second) 0.57.208.478 I slot print_timing: id 0 | task 5827 | eval time = 417.57 ms / 64 tokens ( 6.63 ms per token, 150.87 tokens per second) 0.57.208.479 I slot print_timing: id 0 | task 5827 | total time = 555.42 ms / 644 tokens 0.57.208.480 I slot print_timing: id 0 | task 5827 | graphs reused = 5369 0.57.208.482 I slot print_timing: id 0 | task 5827 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.208.521 I slot release: id 0 | task 5827 | stop processing: n_tokens = 675, truncated = 0 0.57.229.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 57116884 0.57.229.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 0.57.321.162 I slot launch_slot_: id 0 | task 5895 | processing task, is_child = 0 0.57.812.908 I slot print_timing: id 0 | task 5895 | prompt eval time = 157.50 ms / 716 tokens ( 0.22 ms per token, 4546.15 tokens per second) 0.57.812.914 I slot print_timing: id 0 | task 5895 | eval time = 334.23 ms / 50 tokens ( 6.82 ms per token, 146.61 tokens per second) 0.57.812.915 I slot print_timing: id 0 | task 5895 | total time = 491.73 ms / 766 tokens 0.57.812.916 I slot print_timing: id 0 | task 5895 | graphs reused = 5416 0.57.812.917 I slot print_timing: id 0 | task 5895 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.812.957 I slot release: id 0 | task 5895 | stop processing: n_tokens = 797, truncated = 0 0.57.841.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 57721320 0.57.841.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 0.57.860.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 0.57.930.377 I slot launch_slot_: id 0 | task 5949 | processing task, is_child = 0 0.58.762.534 I slot print_timing: id 0 | task 5949 | prompt eval time = 165.92 ms / 799 tokens ( 0.21 ms per token, 4815.69 tokens per second) 0.58.762.540 I slot print_timing: id 0 | task 5949 | eval time = 666.22 ms / 102 tokens ( 6.60 ms per token, 151.60 tokens per second) 0.58.762.541 I slot print_timing: id 0 | task 5949 | total time = 832.14 ms / 901 tokens 0.58.762.542 I slot print_timing: id 0 | task 5949 | graphs reused = 5516 0.58.762.542 I slot print_timing: id 0 | task 5949 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.762.585 I slot release: id 0 | task 5949 | stop processing: n_tokens = 932, truncated = 0 0.58.778.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 58670947 0.58.778.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 0.58.853.617 I slot launch_slot_: id 0 | task 6055 | processing task, is_child = 0 0.59.694.074 I slot print_timing: id 0 | task 6055 | prompt eval time = 112.52 ms / 361 tokens ( 0.31 ms per token, 3208.43 tokens per second) 0.59.694.080 I slot print_timing: id 0 | task 6055 | eval time = 727.92 ms / 112 tokens ( 6.56 ms per token, 152.49 tokens per second) 0.59.694.081 I slot print_timing: id 0 | task 6055 | total time = 840.44 ms / 473 tokens 0.59.694.081 I slot print_timing: id 0 | task 6055 | graphs reused = 5626 0.59.694.082 I slot print_timing: id 0 | task 6055 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.694.111 I slot release: id 0 | task 6055 | stop processing: n_tokens = 504, truncated = 0 0.59.716.992 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 59602474 0.59.717.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 0.59.785.688 I slot launch_slot_: id 0 | task 6170 | processing task, is_child = 0 1.00.603.476 I slot print_timing: id 0 | task 6170 | prompt eval time = 111.29 ms / 381 tokens ( 0.29 ms per token, 3423.61 tokens per second) 1.00.603.481 I slot print_timing: id 0 | task 6170 | eval time = 706.48 ms / 108 tokens ( 6.60 ms per token, 151.46 tokens per second) 1.00.603.482 I slot print_timing: id 0 | task 6170 | total time = 817.77 ms / 489 tokens 1.00.603.483 I slot print_timing: id 0 | task 6170 | graphs reused = 5731 1.00.603.484 I slot print_timing: id 0 | task 6170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.603.514 I slot release: id 0 | task 6170 | stop processing: n_tokens = 520, truncated = 0 1.00.618.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 60511877 1.00.618.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.00.685.146 I slot launch_slot_: id 0 | task 6281 | processing task, is_child = 0 1.01.608.391 I slot print_timing: id 0 | task 6281 | prompt eval time = 110.00 ms / 365 tokens ( 0.30 ms per token, 3318.24 tokens per second) 1.01.608.396 I slot print_timing: id 0 | task 6281 | eval time = 813.23 ms / 124 tokens ( 6.61 ms per token, 151.25 tokens per second) 1.01.608.397 I slot print_timing: id 0 | task 6281 | total time = 923.22 ms / 489 tokens 1.01.608.398 I slot print_timing: id 0 | task 6281 | graphs reused = 5852 1.01.608.399 I slot print_timing: id 0 | task 6281 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.608.430 I slot release: id 0 | task 6281 | stop processing: n_tokens = 520, truncated = 0 1.01.635.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 61516793 1.01.635.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.01.706.306 I slot launch_slot_: id 0 | task 6408 | processing task, is_child = 0 1.02.511.445 I slot print_timing: id 0 | task 6408 | prompt eval time = 108.68 ms / 333 tokens ( 0.33 ms per token, 3063.98 tokens per second) 1.02.511.451 I slot print_timing: id 0 | task 6408 | eval time = 696.44 ms / 107 tokens ( 6.57 ms per token, 152.20 tokens per second) 1.02.511.452 I slot print_timing: id 0 | task 6408 | total time = 805.12 ms / 440 tokens 1.02.511.453 I slot print_timing: id 0 | task 6408 | graphs reused = 5957 1.02.511.453 I slot print_timing: id 0 | task 6408 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.511.482 I slot release: id 0 | task 6408 | stop processing: n_tokens = 471, truncated = 0 1.02.537.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 62419845 1.02.581.035 I slot launch_slot_: id 0 | task 6518 | processing task, is_child = 0 1.03.597.426 I slot print_timing: id 0 | task 6518 | prompt eval time = 114.13 ms / 403 tokens ( 0.28 ms per token, 3531.12 tokens per second) 1.03.597.431 I slot print_timing: id 0 | task 6518 | eval time = 902.24 ms / 138 tokens ( 6.59 ms per token, 151.84 tokens per second) 1.03.597.432 I slot print_timing: id 0 | task 6518 | total time = 1016.37 ms / 541 tokens 1.03.597.433 I slot print_timing: id 0 | task 6518 | graphs reused = 6092 1.03.597.434 I slot print_timing: id 0 | task 6518 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.597.463 I slot release: id 0 | task 6518 | stop processing: n_tokens = 572, truncated = 0 1.03.622.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 63505826 1.03.622.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.03.688.862 I slot launch_slot_: id 0 | task 6659 | processing task, is_child = 0 1.05.028.376 I slot print_timing: id 0 | task 6659 | prompt eval time = 114.02 ms / 411 tokens ( 0.28 ms per token, 3604.54 tokens per second) 1.05.028.382 I slot print_timing: id 0 | task 6659 | eval time = 1225.47 ms / 185 tokens ( 6.66 ms per token, 150.15 tokens per second) 1.05.028.383 I slot print_timing: id 0 | task 6659 | total time = 1339.49 ms / 596 tokens 1.05.028.384 I slot print_timing: id 0 | task 6659 | graphs reused = 6274 1.05.028.386 I slot print_timing: id 0 | task 6659 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.028.418 I slot release: id 0 | task 6659 | stop processing: n_tokens = 627, truncated = 0 1.05.044.739 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 64936781 1.05.044.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.05.120.326 I slot launch_slot_: id 0 | task 6847 | processing task, is_child = 0 1.06.730.073 I slot print_timing: id 0 | task 6847 | prompt eval time = 134.80 ms / 490 tokens ( 0.28 ms per token, 3635.12 tokens per second) 1.06.730.079 I slot print_timing: id 0 | task 6847 | eval time = 1474.93 ms / 225 tokens ( 6.58 ms per token, 151.87 tokens per second) 1.06.730.080 I slot print_timing: id 0 | task 6847 | total time = 1609.73 ms / 715 tokens 1.06.730.081 I slot print_timing: id 0 | task 6847 | graphs reused = 6497 1.06.730.081 I slot print_timing: id 0 | task 6847 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.730.114 I slot release: id 0 | task 6847 | stop processing: n_tokens = 746, truncated = 0 1.06.750.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 66638476 1.06.750.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.06.819.325 I slot launch_slot_: id 0 | task 7075 | processing task, is_child = 0 1.08.043.985 I slot print_timing: id 0 | task 7075 | prompt eval time = 107.73 ms / 344 tokens ( 0.31 ms per token, 3193.17 tokens per second) 1.08.043.991 I slot print_timing: id 0 | task 7075 | eval time = 1116.91 ms / 171 tokens ( 6.57 ms per token, 152.21 tokens per second) 1.08.043.991 I slot print_timing: id 0 | task 7075 | total time = 1224.64 ms / 515 tokens 1.08.043.992 I slot print_timing: id 0 | task 7075 | graphs reused = 6665 1.08.043.993 I slot print_timing: id 0 | task 7075 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.044.020 I slot release: id 0 | task 7075 | stop processing: n_tokens = 546, truncated = 0 1.08.068.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 67952383 1.08.068.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.08.137.412 I slot launch_slot_: id 0 | task 7249 | processing task, is_child = 0 1.09.365.029 I slot print_timing: id 0 | task 7249 | prompt eval time = 109.75 ms / 347 tokens ( 0.32 ms per token, 3161.79 tokens per second) 1.09.365.034 I slot print_timing: id 0 | task 7249 | eval time = 1117.85 ms / 171 tokens ( 6.58 ms per token, 152.08 tokens per second) 1.09.365.036 I slot print_timing: id 0 | task 7249 | total time = 1227.60 ms / 518 tokens 1.09.365.036 I slot print_timing: id 0 | task 7249 | graphs reused = 6833 1.09.365.037 I slot print_timing: id 0 | task 7249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.365.067 I slot release: id 0 | task 7249 | stop processing: n_tokens = 549, truncated = 0 1.09.387.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 69273429 1.09.387.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.989 MiB) 1.09.457.133 I slot launch_slot_: id 0 | task 7423 | processing task, is_child = 0 1.10.397.617 I slot print_timing: id 0 | task 7423 | prompt eval time = 114.56 ms / 401 tokens ( 0.29 ms per token, 3500.35 tokens per second) 1.10.397.623 I slot print_timing: id 0 | task 7423 | eval time = 825.90 ms / 126 tokens ( 6.61 ms per token, 151.35 tokens per second) 1.10.397.624 I slot print_timing: id 0 | task 7423 | total time = 940.46 ms / 527 tokens 1.10.397.625 I slot print_timing: id 0 | task 7423 | graphs reused = 6956 1.10.397.625 I slot print_timing: id 0 | task 7423 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.397.654 I slot release: id 0 | task 7423 | stop processing: n_tokens = 558, truncated = 0 1.10.418.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 70306017 1.10.418.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.10.492.920 I slot launch_slot_: id 0 | task 7552 | processing task, is_child = 0 1.11.387.528 I slot print_timing: id 0 | task 7552 | prompt eval time = 121.86 ms / 456 tokens ( 0.27 ms per token, 3741.94 tokens per second) 1.11.387.534 I slot print_timing: id 0 | task 7552 | eval time = 772.72 ms / 114 tokens ( 6.84 ms per token, 146.24 tokens per second) 1.11.387.535 I slot print_timing: id 0 | task 7552 | total time = 894.59 ms / 570 tokens 1.11.387.536 I slot print_timing: id 0 | task 7552 | graphs reused = 7067 1.11.387.537 I slot print_timing: id 0 | task 7552 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.387.569 I slot release: id 0 | task 7552 | stop processing: n_tokens = 601, truncated = 0 1.11.415.008 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 1.11.415.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.11.487.770 I slot launch_slot_: id 0 | task 7669 | processing task, is_child = 0 1.12.337.913 I slot print_timing: id 0 | task 7669 | prompt eval time = 116.60 ms / 406 tokens ( 0.29 ms per token, 3481.87 tokens per second) 1.12.337.918 I slot print_timing: id 0 | task 7669 | eval time = 733.52 ms / 112 tokens ( 6.61 ms per token, 151.33 tokens per second) 1.12.337.919 I slot print_timing: id 0 | task 7669 | total time = 850.12 ms / 518 tokens 1.12.337.920 I slot print_timing: id 0 | task 7669 | graphs reused = 7176 1.12.337.921 I slot print_timing: id 0 | task 7669 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.337.954 I slot release: id 0 | task 7669 | stop processing: n_tokens = 549, truncated = 0 1.12.362.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 72246316 1.12.405.475 I slot launch_slot_: id 0 | task 7784 | processing task, is_child = 0 1.13.707.374 I slot print_timing: id 0 | task 7784 | prompt eval time = 115.66 ms / 406 tokens ( 0.28 ms per token, 3510.41 tokens per second) 1.13.707.379 I slot print_timing: id 0 | task 7784 | eval time = 1186.22 ms / 179 tokens ( 6.66 ms per token, 150.06 tokens per second) 1.13.707.380 I slot print_timing: id 0 | task 7784 | total time = 1301.88 ms / 585 tokens 1.13.707.381 I slot print_timing: id 0 | task 7784 | graphs reused = 7352 1.13.707.382 I slot print_timing: id 0 | task 7784 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.707.412 I slot release: id 0 | task 7784 | stop processing: n_tokens = 616, truncated = 0 1.13.730.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 73615775 1.13.730.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.13.800.588 I slot launch_slot_: id 0 | task 7966 | processing task, is_child = 0 1.14.822.880 I slot print_timing: id 0 | task 7966 | prompt eval time = 119.20 ms / 444 tokens ( 0.27 ms per token, 3724.93 tokens per second) 1.14.822.886 I slot print_timing: id 0 | task 7966 | eval time = 903.07 ms / 134 tokens ( 6.79 ms per token, 147.27 tokens per second) 1.14.822.887 I slot print_timing: id 0 | task 7966 | total time = 1022.27 ms / 578 tokens 1.14.822.888 I slot print_timing: id 0 | task 7966 | graphs reused = 7483 1.14.822.889 I slot print_timing: id 0 | task 7966 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.822.920 I slot release: id 0 | task 7966 | stop processing: n_tokens = 609, truncated = 0 1.14.837.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 74731282 1.14.837.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.14.904.127 I slot launch_slot_: id 0 | task 8103 | processing task, is_child = 0 1.15.686.015 I slot print_timing: id 0 | task 8103 | prompt eval time = 112.28 ms / 372 tokens ( 0.30 ms per token, 3313.00 tokens per second) 1.15.686.022 I slot print_timing: id 0 | task 8103 | eval time = 669.59 ms / 103 tokens ( 6.56 ms per token, 152.33 tokens per second) 1.15.686.023 I slot print_timing: id 0 | task 8103 | total time = 781.87 ms / 475 tokens 1.15.686.024 I slot print_timing: id 0 | task 8103 | graphs reused = 7584 1.15.686.025 I slot print_timing: id 0 | task 8103 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.686.057 I slot release: id 0 | task 8103 | stop processing: n_tokens = 506, truncated = 0 1.15.711.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 75594420 1.15.711.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.15.777.638 I slot launch_slot_: id 0 | task 8209 | processing task, is_child = 0 1.17.400.162 I slot print_timing: id 0 | task 8209 | prompt eval time = 119.82 ms / 454 tokens ( 0.26 ms per token, 3789.05 tokens per second) 1.17.400.169 I slot print_timing: id 0 | task 8209 | eval time = 1502.68 ms / 230 tokens ( 6.56 ms per token, 152.39 tokens per second) 1.17.400.170 I slot print_timing: id 0 | task 8209 | total time = 1622.50 ms / 684 tokens 1.17.400.171 I slot print_timing: id 0 | task 8209 | graphs reused = 7811 1.17.400.172 I slot print_timing: id 0 | task 8209 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.400.207 I slot release: id 0 | task 8209 | stop processing: n_tokens = 715, truncated = 0 1.17.420.455 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 77308570 1.17.420.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.17.487.467 I slot launch_slot_: id 0 | task 8442 | processing task, is_child = 0 1.19.088.125 I slot print_timing: id 0 | task 8442 | prompt eval time = 111.16 ms / 354 tokens ( 0.31 ms per token, 3184.48 tokens per second) 1.19.088.131 I slot print_timing: id 0 | task 8442 | eval time = 1489.48 ms / 228 tokens ( 6.56 ms per token, 152.40 tokens per second) 1.19.088.132 I slot print_timing: id 0 | task 8442 | total time = 1600.64 ms / 582 tokens 1.19.088.133 I slot print_timing: id 0 | task 8442 | graphs reused = 8036 1.19.088.134 I slot print_timing: id 0 | task 8442 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.088.166 I slot release: id 0 | task 8442 | stop processing: n_tokens = 613, truncated = 0 1.19.104.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 613, t_last = 78996529 1.19.104.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.19.177.953 I slot launch_slot_: id 0 | task 8673 | processing task, is_child = 0 1.20.197.413 I slot print_timing: id 0 | task 8673 | prompt eval time = 109.39 ms / 334 tokens ( 0.33 ms per token, 3053.18 tokens per second) 1.20.197.420 I slot print_timing: id 0 | task 8673 | eval time = 910.05 ms / 140 tokens ( 6.55 ms per token, 152.74 tokens per second) 1.20.197.421 I slot print_timing: id 0 | task 8673 | total time = 1019.44 ms / 474 tokens 1.20.197.422 I slot print_timing: id 0 | task 8673 | graphs reused = 8174 1.20.197.422 I slot print_timing: id 0 | task 8673 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.197.451 I slot release: id 0 | task 8673 | stop processing: n_tokens = 505, truncated = 0 1.20.214.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 80105814 1.20.214.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 1.20.292.764 I slot launch_slot_: id 0 | task 8816 | processing task, is_child = 0 1.21.556.836 I slot print_timing: id 0 | task 8816 | prompt eval time = 120.22 ms / 426 tokens ( 0.28 ms per token, 3543.47 tokens per second) 1.21.556.842 I slot print_timing: id 0 | task 8816 | eval time = 1143.83 ms / 175 tokens ( 6.57 ms per token, 152.12 tokens per second) 1.21.556.843 I slot print_timing: id 0 | task 8816 | total time = 1264.05 ms / 601 tokens 1.21.556.844 I slot print_timing: id 0 | task 8816 | graphs reused = 8346 1.21.556.844 I slot print_timing: id 0 | task 8816 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.556.876 I slot release: id 0 | task 8816 | stop processing: n_tokens = 632, truncated = 0 1.21.586.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 81465239 1.21.586.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.21.659.856 I slot launch_slot_: id 0 | task 8994 | processing task, is_child = 0 1.22.537.275 I slot print_timing: id 0 | task 8994 | prompt eval time = 111.53 ms / 366 tokens ( 0.30 ms per token, 3281.54 tokens per second) 1.22.537.282 I slot print_timing: id 0 | task 8994 | eval time = 765.87 ms / 117 tokens ( 6.60 ms per token, 151.46 tokens per second) 1.22.537.283 I slot print_timing: id 0 | task 8994 | total time = 877.40 ms / 483 tokens 1.22.537.284 I slot print_timing: id 0 | task 8994 | graphs reused = 8460 1.22.537.285 I slot print_timing: id 0 | task 8994 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.537.316 I slot release: id 0 | task 8994 | stop processing: n_tokens = 514, truncated = 0 1.22.557.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 82445679 1.22.557.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.22.627.188 I slot launch_slot_: id 0 | task 9114 | processing task, is_child = 0 1.24.451.050 I slot print_timing: id 0 | task 9114 | prompt eval time = 122.35 ms / 462 tokens ( 0.26 ms per token, 3775.96 tokens per second) 1.24.451.055 I slot print_timing: id 0 | task 9114 | eval time = 1701.49 ms / 260 tokens ( 6.57 ms per token, 152.22 tokens per second) 1.24.451.056 I slot print_timing: id 0 | task 9114 | total time = 1823.84 ms / 722 tokens 1.24.451.057 I slot print_timing: id 0 | task 9114 | graphs reused = 8717 1.24.451.058 I slot print_timing: id 0 | task 9114 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.451.089 I slot release: id 0 | task 9114 | stop processing: n_tokens = 753, truncated = 0 1.24.473.215 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 84359452 1.24.473.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.24.543.469 I slot launch_slot_: id 0 | task 9377 | processing task, is_child = 0 1.25.566.367 I slot print_timing: id 0 | task 9377 | prompt eval time = 113.91 ms / 396 tokens ( 0.29 ms per token, 3476.31 tokens per second) 1.25.566.373 I slot print_timing: id 0 | task 9377 | eval time = 908.97 ms / 139 tokens ( 6.59 ms per token, 151.82 tokens per second) 1.25.566.374 I slot print_timing: id 0 | task 9377 | total time = 1022.88 ms / 535 tokens 1.25.566.375 I slot print_timing: id 0 | task 9377 | graphs reused = 8853 1.25.566.376 I slot print_timing: id 0 | task 9377 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.566.404 I slot release: id 0 | task 9377 | stop processing: n_tokens = 566, truncated = 0 1.25.594.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 85474767 1.25.638.296 I slot launch_slot_: id 0 | task 9519 | processing task, is_child = 0 1.26.817.479 I slot print_timing: id 0 | task 9519 | prompt eval time = 123.06 ms / 458 tokens ( 0.27 ms per token, 3721.67 tokens per second) 1.26.817.484 I slot print_timing: id 0 | task 9519 | eval time = 1056.10 ms / 161 tokens ( 6.60 ms per token, 151.50 tokens per second) 1.26.817.486 I slot print_timing: id 0 | task 9519 | total time = 1179.16 ms / 619 tokens 1.26.817.487 I slot print_timing: id 0 | task 9519 | graphs reused = 9011 1.26.817.488 I slot print_timing: id 0 | task 9519 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.817.517 I slot release: id 0 | task 9519 | stop processing: n_tokens = 650, truncated = 0 1.26.840.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 86725880 1.26.840.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.26.908.614 I slot launch_slot_: id 0 | task 9683 | processing task, is_child = 0 1.28.215.164 I slot print_timing: id 0 | task 9683 | prompt eval time = 122.45 ms / 458 tokens ( 0.27 ms per token, 3740.36 tokens per second) 1.28.215.170 I slot print_timing: id 0 | task 9683 | eval time = 1184.08 ms / 176 tokens ( 6.77 ms per token, 147.79 tokens per second) 1.28.215.171 I slot print_timing: id 0 | task 9683 | total time = 1306.53 ms / 634 tokens 1.28.215.172 I slot print_timing: id 0 | task 9683 | graphs reused = 9184 1.28.215.173 I slot print_timing: id 0 | task 9683 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.215.206 I slot release: id 0 | task 9683 | stop processing: n_tokens = 665, truncated = 0 1.28.240.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 88123568 1.28.240.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.28.317.563 I slot launch_slot_: id 0 | task 9862 | processing task, is_child = 0 1.29.812.717 I slot print_timing: id 0 | task 9862 | prompt eval time = 121.18 ms / 452 tokens ( 0.27 ms per token, 3729.87 tokens per second) 1.29.812.722 I slot print_timing: id 0 | task 9862 | eval time = 1373.95 ms / 210 tokens ( 6.57 ms per token, 152.12 tokens per second) 1.29.812.723 I slot print_timing: id 0 | task 9862 | total time = 1495.13 ms / 662 tokens 1.29.812.725 I slot print_timing: id 0 | task 9862 | graphs reused = 9391 1.29.812.726 I slot print_timing: id 0 | task 9862 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.812.758 I slot release: id 0 | task 9862 | stop processing: n_tokens = 693, truncated = 0 1.29.833.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 89721120 1.29.833.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.29.903.333 I slot launch_slot_: id 0 | task 10075 | processing task, is_child = 0 1.30.768.774 I slot print_timing: id 0 | task 10075 | prompt eval time = 118.77 ms / 404 tokens ( 0.29 ms per token, 3401.42 tokens per second) 1.30.768.780 I slot print_timing: id 0 | task 10075 | eval time = 746.65 ms / 114 tokens ( 6.61 ms per token, 151.34 tokens per second) 1.30.768.781 I slot print_timing: id 0 | task 10075 | total time = 865.42 ms / 518 tokens 1.30.768.782 I slot print_timing: id 0 | task 10075 | graphs reused = 9502 1.30.768.783 I slot print_timing: id 0 | task 10075 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.768.813 I slot release: id 0 | task 10075 | stop processing: n_tokens = 549, truncated = 0 1.30.786.710 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 90677175 1.30.786.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.30.853.117 I slot launch_slot_: id 0 | task 10192 | processing task, is_child = 0 1.31.655.036 I slot print_timing: id 0 | task 10192 | prompt eval time = 109.03 ms / 345 tokens ( 0.32 ms per token, 3164.21 tokens per second) 1.31.655.043 I slot print_timing: id 0 | task 10192 | eval time = 692.87 ms / 106 tokens ( 6.60 ms per token, 151.54 tokens per second) 1.31.655.043 I slot print_timing: id 0 | task 10192 | total time = 801.90 ms / 451 tokens 1.31.655.044 I slot print_timing: id 0 | task 10192 | graphs reused = 9606 1.31.655.045 I slot print_timing: id 0 | task 10192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.655.073 I slot release: id 0 | task 10192 | stop processing: n_tokens = 482, truncated = 0 1.31.673.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 91563435 1.31.673.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.31.739.221 I slot launch_slot_: id 0 | task 10301 | processing task, is_child = 0 1.32.549.911 I slot print_timing: id 0 | task 10301 | prompt eval time = 122.45 ms / 430 tokens ( 0.28 ms per token, 3511.75 tokens per second) 1.32.549.917 I slot print_timing: id 0 | task 10301 | eval time = 688.23 ms / 105 tokens ( 6.62 ms per token, 151.11 tokens per second) 1.32.549.918 I slot print_timing: id 0 | task 10301 | total time = 810.67 ms / 535 tokens 1.32.549.918 I slot print_timing: id 0 | task 10301 | graphs reused = 9708 1.32.549.919 I slot print_timing: id 0 | task 10301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.549.949 I slot release: id 0 | task 10301 | stop processing: n_tokens = 566, truncated = 0 1.32.575.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 92458311 1.32.575.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.32.641.669 I slot launch_slot_: id 0 | task 10409 | processing task, is_child = 0 1.33.328.199 I slot print_timing: id 0 | task 10409 | prompt eval time = 104.47 ms / 316 tokens ( 0.33 ms per token, 3024.70 tokens per second) 1.33.328.205 I slot print_timing: id 0 | task 10409 | eval time = 582.04 ms / 85 tokens ( 6.93 ms per token, 144.32 tokens per second) 1.33.328.206 I slot print_timing: id 0 | task 10409 | total time = 686.51 ms / 401 tokens 1.33.328.207 I slot print_timing: id 0 | task 10409 | graphs reused = 9791 1.33.328.208 I slot print_timing: id 0 | task 10409 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.328.235 I slot release: id 0 | task 10409 | stop processing: n_tokens = 432, truncated = 0 1.33.343.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 93236598 1.33.343.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 1.33.408.372 I slot launch_slot_: id 0 | task 10497 | processing task, is_child = 0 1.34.216.329 I slot print_timing: id 0 | task 10497 | prompt eval time = 110.71 ms / 354 tokens ( 0.31 ms per token, 3197.46 tokens per second) 1.34.216.334 I slot print_timing: id 0 | task 10497 | eval time = 697.23 ms / 107 tokens ( 6.58 ms per token, 152.03 tokens per second) 1.34.216.336 I slot print_timing: id 0 | task 10497 | total time = 807.94 ms / 461 tokens 1.34.216.337 I slot print_timing: id 0 | task 10497 | graphs reused = 9896 1.34.216.338 I slot print_timing: id 0 | task 10497 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.216.369 I slot release: id 0 | task 10497 | stop processing: n_tokens = 492, truncated = 0 1.34.237.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 94124732 1.34.237.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 1.34.315.436 I slot launch_slot_: id 0 | task 10607 | processing task, is_child = 0 1.35.081.763 I slot print_timing: id 0 | task 10607 | prompt eval time = 124.74 ms / 438 tokens ( 0.28 ms per token, 3511.33 tokens per second) 1.35.081.769 I slot print_timing: id 0 | task 10607 | eval time = 641.57 ms / 98 tokens ( 6.61 ms per token, 151.19 tokens per second) 1.35.081.770 I slot print_timing: id 0 | task 10607 | total time = 766.31 ms / 536 tokens 1.35.081.771 I slot print_timing: id 0 | task 10607 | graphs reused = 9991 1.35.081.771 I slot print_timing: id 0 | task 10607 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.081.803 I slot release: id 0 | task 10607 | stop processing: n_tokens = 567, truncated = 0 1.35.108.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 94990165 1.35.108.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.35.178.880 I slot launch_slot_: id 0 | task 10708 | processing task, is_child = 0 1.35.761.093 I slot print_timing: id 0 | task 10708 | prompt eval time = 122.56 ms / 457 tokens ( 0.27 ms per token, 3728.82 tokens per second) 1.35.761.099 I slot print_timing: id 0 | task 10708 | eval time = 459.63 ms / 70 tokens ( 6.66 ms per token, 150.12 tokens per second) 1.35.761.101 I slot print_timing: id 0 | task 10708 | total time = 582.19 ms / 527 tokens 1.35.761.101 I slot print_timing: id 0 | task 10708 | graphs reused = 10058 1.35.761.102 I slot print_timing: id 0 | task 10708 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.761.132 I slot release: id 0 | task 10708 | stop processing: n_tokens = 558, truncated = 0 1.35.778.362 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 95669494 1.35.778.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 1.35.845.132 I slot launch_slot_: id 0 | task 10781 | processing task, is_child = 0 1.36.614.099 I slot print_timing: id 0 | task 10781 | prompt eval time = 125.84 ms / 473 tokens ( 0.27 ms per token, 3758.83 tokens per second) 1.36.614.106 I slot print_timing: id 0 | task 10781 | eval time = 643.11 ms / 98 tokens ( 6.63 ms per token, 150.83 tokens per second) 1.36.614.108 I slot print_timing: id 0 | task 10781 | total time = 768.95 ms / 571 tokens 1.36.614.108 I slot print_timing: id 0 | task 10781 | graphs reused = 10153 1.36.614.109 I slot print_timing: id 0 | task 10781 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.614.144 I slot release: id 0 | task 10781 | stop processing: n_tokens = 602, truncated = 0 1.36.632.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 96522507 1.36.632.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 1.36.710.667 I slot launch_slot_: id 0 | task 10882 | processing task, is_child = 0 1.37.014.448 I slot print_timing: id 0 | task 10882 | prompt eval time = 122.62 ms / 476 tokens ( 0.26 ms per token, 3882.04 tokens per second) 1.37.014.453 I slot print_timing: id 0 | task 10882 | eval time = 181.15 ms / 27 tokens ( 6.97 ms per token, 143.53 tokens per second) 1.37.014.455 I slot print_timing: id 0 | task 10882 | total time = 303.76 ms / 503 tokens 1.37.014.455 I slot print_timing: id 0 | task 10882 | graphs reused = 10177 1.37.014.456 I slot print_timing: id 0 | task 10882 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.014.487 I slot release: id 0 | task 10882 | stop processing: n_tokens = 534, truncated = 0 1.37.034.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 96922850 1.37.035.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.37.108.199 I slot launch_slot_: id 0 | task 10912 | processing task, is_child = 0 1.37.939.682 I slot print_timing: id 0 | task 10912 | prompt eval time = 128.84 ms / 466 tokens ( 0.28 ms per token, 3616.97 tokens per second) 1.37.939.688 I slot print_timing: id 0 | task 10912 | eval time = 702.63 ms / 107 tokens ( 6.63 ms per token, 150.86 tokens per second) 1.37.939.689 I slot print_timing: id 0 | task 10912 | total time = 831.46 ms / 573 tokens 1.37.939.690 I slot print_timing: id 0 | task 10912 | graphs reused = 10281 1.37.939.691 I slot print_timing: id 0 | task 10912 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.939.723 I slot release: id 0 | task 10912 | stop processing: n_tokens = 604, truncated = 0 1.37.958.536 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 97848085 1.37.958.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.38.025.576 I slot launch_slot_: id 0 | task 11022 | processing task, is_child = 0 1.38.652.461 I slot print_timing: id 0 | task 11022 | prompt eval time = 114.35 ms / 415 tokens ( 0.28 ms per token, 3629.34 tokens per second) 1.38.652.467 I slot print_timing: id 0 | task 11022 | eval time = 512.52 ms / 78 tokens ( 6.66 ms per token, 150.24 tokens per second) 1.38.652.469 I slot print_timing: id 0 | task 11022 | total time = 626.87 ms / 493 tokens 1.38.652.470 I slot print_timing: id 0 | task 11022 | graphs reused = 10356 1.38.652.471 I slot print_timing: id 0 | task 11022 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.652.502 I slot release: id 0 | task 11022 | stop processing: n_tokens = 524, truncated = 0 1.38.666.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 98560865 1.38.666.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.299 MiB) 1.38.732.436 I slot launch_slot_: id 0 | task 11103 | processing task, is_child = 0 1.39.257.571 I slot print_timing: id 0 | task 11103 | prompt eval time = 108.97 ms / 352 tokens ( 0.31 ms per token, 3230.25 tokens per second) 1.39.257.577 I slot print_timing: id 0 | task 11103 | eval time = 416.14 ms / 64 tokens ( 6.61 ms per token, 151.39 tokens per second) 1.39.257.578 I slot print_timing: id 0 | task 11103 | total time = 525.12 ms / 416 tokens 1.39.257.578 I slot print_timing: id 0 | task 11103 | graphs reused = 10418 1.39.257.579 I slot print_timing: id 0 | task 11103 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.257.610 I slot release: id 0 | task 11103 | stop processing: n_tokens = 447, truncated = 0 1.39.273.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 99165973 1.39.273.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.39.346.078 I slot launch_slot_: id 0 | task 11170 | processing task, is_child = 0 1.40.351.378 I slot print_timing: id 0 | task 11170 | prompt eval time = 137.39 ms / 550 tokens ( 0.25 ms per token, 4003.14 tokens per second) 1.40.351.385 I slot print_timing: id 0 | task 11170 | eval time = 867.89 ms / 133 tokens ( 6.57 ms per token, 152.09 tokens per second) 1.40.351.386 I slot print_timing: id 0 | task 11170 | total time = 1005.28 ms / 683 tokens 1.40.351.387 I slot print_timing: id 0 | task 11170 | graphs reused = 10549 1.40.351.388 I slot print_timing: id 0 | task 11170 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.351.427 I slot release: id 0 | task 11170 | stop processing: n_tokens = 714, truncated = 0 1.40.381.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 100259790 1.40.381.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 1.40.455.362 I slot launch_slot_: id 0 | task 11307 | processing task, is_child = 0 1.42.098.174 I slot print_timing: id 0 | task 11307 | prompt eval time = 159.06 ms / 772 tokens ( 0.21 ms per token, 4853.61 tokens per second) 1.42.098.180 I slot print_timing: id 0 | task 11307 | eval time = 1483.73 ms / 226 tokens ( 6.59 ms per token, 151.64 tokens per second) 1.42.098.181 I slot print_timing: id 0 | task 11307 | total time = 1642.79 ms / 998 tokens 1.42.098.182 I slot print_timing: id 0 | task 11307 | graphs reused = 10772 1.42.098.183 I slot print_timing: id 0 | task 11307 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.098.221 I slot release: id 0 | task 11307 | stop processing: n_tokens = 1029, truncated = 0 1.42.102.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 102006584 1.42.102.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.42.180.851 I slot launch_slot_: id 0 | task 11537 | processing task, is_child = 0 1.43.523.724 I slot print_timing: id 0 | task 11537 | prompt eval time = 154.45 ms / 683 tokens ( 0.23 ms per token, 4422.23 tokens per second) 1.43.523.729 I slot print_timing: id 0 | task 11537 | eval time = 1188.41 ms / 181 tokens ( 6.60 ms per token, 151.46 tokens per second) 1.43.523.730 I slot print_timing: id 0 | task 11537 | total time = 1342.85 ms / 864 tokens 1.43.523.731 I slot print_timing: id 0 | task 11537 | graphs reused = 10950 1.43.523.732 I slot print_timing: id 0 | task 11537 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.523.769 I slot release: id 0 | task 11537 | stop processing: n_tokens = 895, truncated = 0 1.43.540.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 103432132 1.43.540.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 1.43.615.413 I slot launch_slot_: id 0 | task 11722 | processing task, is_child = 0 1.45.183.078 I slot print_timing: id 0 | task 11722 | prompt eval time = 141.99 ms / 579 tokens ( 0.25 ms per token, 4077.69 tokens per second) 1.45.183.084 I slot print_timing: id 0 | task 11722 | eval time = 1425.65 ms / 218 tokens ( 6.57 ms per token, 152.21 tokens per second) 1.45.183.085 I slot print_timing: id 0 | task 11722 | total time = 1567.65 ms / 797 tokens 1.45.183.086 I slot print_timing: id 0 | task 11722 | graphs reused = 11165 1.45.183.086 I slot print_timing: id 0 | task 11722 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.183.119 I slot release: id 0 | task 11722 | stop processing: n_tokens = 828, truncated = 0 1.45.208.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 105091482 1.45.208.537 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 1.45.228.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.674 MiB) 1.45.309.431 I slot launch_slot_: id 0 | task 11944 | processing task, is_child = 0 1.46.134.363 I slot print_timing: id 0 | task 11944 | prompt eval time = 133.39 ms / 500 tokens ( 0.27 ms per token, 3748.41 tokens per second) 1.46.134.369 I slot print_timing: id 0 | task 11944 | eval time = 691.52 ms / 106 tokens ( 6.59 ms per token, 151.84 tokens per second) 1.46.134.370 I slot print_timing: id 0 | task 11944 | total time = 824.91 ms / 606 tokens 1.46.134.371 I slot print_timing: id 0 | task 11944 | graphs reused = 11269 1.46.134.372 I slot print_timing: id 0 | task 11944 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.134.404 I slot release: id 0 | task 11944 | stop processing: n_tokens = 637, truncated = 0 1.46.162.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 106042767 1.46.162.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 1.46.226.389 I slot launch_slot_: id 0 | task 12053 | processing task, is_child = 0 1.47.754.865 I slot print_timing: id 0 | task 12053 | prompt eval time = 163.47 ms / 776 tokens ( 0.21 ms per token, 4746.93 tokens per second) 1.47.754.871 I slot print_timing: id 0 | task 12053 | eval time = 1364.98 ms / 209 tokens ( 6.56 ms per token, 152.38 tokens per second) 1.47.754.873 I slot print_timing: id 0 | task 12053 | total time = 1528.45 ms / 985 tokens 1.47.754.874 I slot print_timing: id 0 | task 12053 | graphs reused = 11476 1.47.754.875 I slot print_timing: id 0 | task 12053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.754.918 I slot release: id 0 | task 12053 | stop processing: n_tokens = 1016, truncated = 0 1.47.779.159 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 107663281 1.47.779.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 1.47.853.580 I slot launch_slot_: id 0 | task 12266 | processing task, is_child = 0 1.49.266.935 I slot print_timing: id 0 | task 12266 | prompt eval time = 129.01 ms / 504 tokens ( 0.26 ms per token, 3906.55 tokens per second) 1.49.266.941 I slot print_timing: id 0 | task 12266 | eval time = 1284.32 ms / 197 tokens ( 6.55 ms per token, 152.61 tokens per second) 1.49.266.942 I slot print_timing: id 0 | task 12266 | total time = 1413.34 ms / 701 tokens 1.49.266.943 I slot print_timing: id 0 | task 12266 | graphs reused = 11671 1.49.266.943 I slot print_timing: id 0 | task 12266 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.266.976 I slot release: id 0 | task 12266 | stop processing: n_tokens = 732, truncated = 0 1.49.283.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 109175339 1.49.283.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 1.49.350.638 I slot launch_slot_: id 0 | task 12466 | processing task, is_child = 0 1.50.852.169 I slot print_timing: id 0 | task 12466 | prompt eval time = 144.98 ms / 633 tokens ( 0.23 ms per token, 4366.09 tokens per second) 1.50.852.175 I slot print_timing: id 0 | task 12466 | eval time = 1356.53 ms / 207 tokens ( 6.59 ms per token, 151.86 tokens per second) 1.50.852.176 I slot print_timing: id 0 | task 12466 | total time = 1501.51 ms / 840 tokens 1.50.852.177 I slot print_timing: id 0 | task 12466 | graphs reused = 11875 1.50.852.178 I slot print_timing: id 0 | task 12466 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.852.215 I slot release: id 0 | task 12466 | stop processing: n_tokens = 871, truncated = 0 1.50.875.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 110760578 1.50.875.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.052 MiB) 1.50.949.858 I slot launch_slot_: id 0 | task 12677 | processing task, is_child = 0 1.51.945.180 I slot print_timing: id 0 | task 12677 | prompt eval time = 119.07 ms / 395 tokens ( 0.30 ms per token, 3317.32 tokens per second) 1.51.945.186 I slot print_timing: id 0 | task 12677 | eval time = 876.23 ms / 134 tokens ( 6.59 ms per token, 151.79 tokens per second) 1.51.945.187 I slot print_timing: id 0 | task 12677 | total time = 995.30 ms / 529 tokens 1.51.945.188 I slot print_timing: id 0 | task 12677 | graphs reused = 12006 1.51.945.189 I slot print_timing: id 0 | task 12677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.945.219 I slot release: id 0 | task 12677 | stop processing: n_tokens = 560, truncated = 0 1.51.971.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 111853582 1.51.971.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 1.52.038.568 I slot launch_slot_: id 0 | task 12814 | processing task, is_child = 0 1.53.544.602 I slot print_timing: id 0 | task 12814 | prompt eval time = 138.67 ms / 584 tokens ( 0.24 ms per token, 4211.50 tokens per second) 1.53.544.608 I slot print_timing: id 0 | task 12814 | eval time = 1367.35 ms / 209 tokens ( 6.57 ms per token, 152.12 tokens per second) 1.53.544.609 I slot print_timing: id 0 | task 12814 | total time = 1506.01 ms / 793 tokens 1.53.544.610 I slot print_timing: id 0 | task 12814 | graphs reused = 12212 1.53.544.610 I slot print_timing: id 0 | task 12814 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.544.647 I slot release: id 0 | task 12814 | stop processing: n_tokens = 824, truncated = 0 1.53.561.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 113453009 1.53.561.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 1.53.636.561 I slot launch_slot_: id 0 | task 13027 | processing task, is_child = 0 1.55.311.153 I slot print_timing: id 0 | task 13027 | prompt eval time = 155.77 ms / 695 tokens ( 0.22 ms per token, 4461.76 tokens per second) 1.55.311.159 I slot print_timing: id 0 | task 13027 | eval time = 1518.80 ms / 230 tokens ( 6.63 ms per token, 150.78 tokens per second) 1.55.311.160 I slot print_timing: id 0 | task 13027 | total time = 1674.57 ms / 925 tokens 1.55.311.160 I slot print_timing: id 0 | task 13027 | graphs reused = 12439 1.55.311.161 I slot print_timing: id 0 | task 13027 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.311.200 I slot release: id 0 | task 13027 | stop processing: n_tokens = 956, truncated = 0 1.55.333.264 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 115219563 1.55.333.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 1.55.408.069 I slot launch_slot_: id 0 | task 13261 | processing task, is_child = 0 1.56.826.809 I slot print_timing: id 0 | task 13261 | prompt eval time = 164.67 ms / 769 tokens ( 0.21 ms per token, 4669.86 tokens per second) 1.56.826.817 I slot print_timing: id 0 | task 13261 | eval time = 1254.05 ms / 191 tokens ( 6.60 ms per token, 151.51 tokens per second) 1.56.826.818 I slot print_timing: id 0 | task 13261 | total time = 1418.72 ms / 960 tokens 1.56.826.819 I slot print_timing: id 0 | task 13261 | graphs reused = 12628 1.56.826.820 I slot print_timing: id 0 | task 13261 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.826.862 I slot release: id 0 | task 13261 | stop processing: n_tokens = 991, truncated = 0 1.56.845.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 116735225 1.56.846.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 1.56.865.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.56.941.234 I slot launch_slot_: id 0 | task 13456 | processing task, is_child = 0 1.57.942.966 I slot print_timing: id 0 | task 13456 | prompt eval time = 139.12 ms / 576 tokens ( 0.24 ms per token, 4140.28 tokens per second) 1.57.942.972 I slot print_timing: id 0 | task 13456 | eval time = 862.59 ms / 124 tokens ( 7.01 ms per token, 142.59 tokens per second) 1.57.942.973 I slot print_timing: id 0 | task 13456 | total time = 1001.71 ms / 700 tokens 1.57.942.974 I slot print_timing: id 0 | task 13456 | graphs reused = 12750 1.57.942.978 I slot print_timing: id 0 | task 13456 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.943.014 I slot release: id 0 | task 13456 | stop processing: n_tokens = 731, truncated = 0 1.57.969.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 117851377 1.57.969.748 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 1.58.043.346 I slot launch_slot_: id 0 | task 13584 | processing task, is_child = 0 2.00.014.857 I slot print_timing: id 0 | task 13584 | prompt eval time = 151.41 ms / 655 tokens ( 0.23 ms per token, 4326.06 tokens per second) 2.00.014.862 I slot print_timing: id 0 | task 13584 | eval time = 1820.08 ms / 275 tokens ( 6.64 ms per token, 150.54 tokens per second) 2.00.014.863 I slot print_timing: id 0 | task 13584 | total time = 1971.49 ms / 930 tokens 2.00.014.866 I slot print_timing: id 0 | task 13584 | graphs reused = 13022 2.00.014.867 I slot print_timing: id 0 | task 13584 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.014.904 I slot release: id 0 | task 13584 | stop processing: n_tokens = 961, truncated = 0 2.00.044.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 119923267 2.00.044.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.00.120.010 I slot launch_slot_: id 0 | task 13863 | processing task, is_child = 0 2.01.061.974 I slot print_timing: id 0 | task 13863 | prompt eval time = 147.06 ms / 621 tokens ( 0.24 ms per token, 4222.65 tokens per second) 2.01.061.980 I slot print_timing: id 0 | task 13863 | eval time = 794.88 ms / 121 tokens ( 6.62 ms per token, 150.97 tokens per second) 2.01.061.981 I slot print_timing: id 0 | task 13863 | total time = 941.94 ms / 742 tokens 2.01.061.982 I slot print_timing: id 0 | task 13863 | graphs reused = 13140 2.01.061.983 I slot print_timing: id 0 | task 13863 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.062.019 I slot release: id 0 | task 13863 | stop processing: n_tokens = 773, truncated = 0 2.01.081.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 120970382 2.01.081.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.01.152.963 I slot launch_slot_: id 0 | task 13988 | processing task, is_child = 0 2.02.514.414 I slot print_timing: id 0 | task 13988 | prompt eval time = 162.45 ms / 767 tokens ( 0.21 ms per token, 4721.34 tokens per second) 2.02.514.421 I slot print_timing: id 0 | task 13988 | eval time = 1198.98 ms / 178 tokens ( 6.77 ms per token, 147.63 tokens per second) 2.02.514.422 I slot print_timing: id 0 | task 13988 | total time = 1361.43 ms / 945 tokens 2.02.514.423 I slot print_timing: id 0 | task 13988 | graphs reused = 13316 2.02.514.424 I slot print_timing: id 0 | task 13988 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.514.471 I slot release: id 0 | task 13988 | stop processing: n_tokens = 976, truncated = 0 2.02.544.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 122422834 2.02.544.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.02.619.196 I slot launch_slot_: id 0 | task 14170 | processing task, is_child = 0 2.04.160.298 I slot print_timing: id 0 | task 14170 | prompt eval time = 177.67 ms / 864 tokens ( 0.21 ms per token, 4862.98 tokens per second) 2.04.160.303 I slot print_timing: id 0 | task 14170 | eval time = 1363.41 ms / 203 tokens ( 6.75 ms per token, 148.16 tokens per second) 2.04.160.305 I slot print_timing: id 0 | task 14170 | total time = 1541.08 ms / 1067 tokens 2.04.160.306 I slot print_timing: id 0 | task 14170 | graphs reused = 13516 2.04.160.306 I slot print_timing: id 0 | task 14170 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.160.351 I slot release: id 0 | task 14170 | stop processing: n_tokens = 1098, truncated = 0 2.04.188.209 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 124068714 2.04.188.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.04.207.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.04.287.318 I slot launch_slot_: id 0 | task 14377 | processing task, is_child = 0 2.05.288.278 I slot print_timing: id 0 | task 14377 | prompt eval time = 154.76 ms / 646 tokens ( 0.24 ms per token, 4174.26 tokens per second) 2.05.288.284 I slot print_timing: id 0 | task 14377 | eval time = 846.18 ms / 129 tokens ( 6.61 ms per token, 151.27 tokens per second) 2.05.288.285 I slot print_timing: id 0 | task 14377 | total time = 1000.94 ms / 775 tokens 2.05.288.286 I slot print_timing: id 0 | task 14377 | graphs reused = 13642 2.05.288.287 I slot print_timing: id 0 | task 14377 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.288.326 I slot release: id 0 | task 14377 | stop processing: n_tokens = 806, truncated = 0 2.05.310.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 125196689 2.05.310.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.05.385.239 I slot launch_slot_: id 0 | task 14510 | processing task, is_child = 0 2.07.036.486 I slot print_timing: id 0 | task 14510 | prompt eval time = 156.33 ms / 720 tokens ( 0.22 ms per token, 4605.64 tokens per second) 2.07.036.492 I slot print_timing: id 0 | task 14510 | eval time = 1494.90 ms / 219 tokens ( 6.86 ms per token, 145.83 tokens per second) 2.07.036.493 I slot print_timing: id 0 | task 14510 | total time = 1651.23 ms / 939 tokens 2.07.036.494 I slot print_timing: id 0 | task 14510 | graphs reused = 13858 2.07.036.495 I slot print_timing: id 0 | task 14510 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.036.534 I slot release: id 0 | task 14510 | stop processing: n_tokens = 970, truncated = 0 2.07.057.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 126944896 2.07.057.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.07.133.438 I slot launch_slot_: id 0 | task 14733 | processing task, is_child = 0 2.08.664.196 I slot print_timing: id 0 | task 14733 | prompt eval time = 133.74 ms / 509 tokens ( 0.26 ms per token, 3806.01 tokens per second) 2.08.664.202 I slot print_timing: id 0 | task 14733 | eval time = 1397.00 ms / 214 tokens ( 6.56 ms per token, 152.47 tokens per second) 2.08.664.203 I slot print_timing: id 0 | task 14733 | total time = 1530.74 ms / 723 tokens 2.08.664.204 I slot print_timing: id 0 | task 14733 | graphs reused = 14070 2.08.664.205 I slot print_timing: id 0 | task 14733 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.664.241 I slot release: id 0 | task 14733 | stop processing: n_tokens = 754, truncated = 0 2.08.684.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 128572604 2.08.684.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.08.752.123 I slot launch_slot_: id 0 | task 14950 | processing task, is_child = 0 2.10.474.729 I slot print_timing: id 0 | task 14950 | prompt eval time = 139.75 ms / 581 tokens ( 0.24 ms per token, 4157.45 tokens per second) 2.10.474.735 I slot print_timing: id 0 | task 14950 | eval time = 1582.84 ms / 242 tokens ( 6.57 ms per token, 152.26 tokens per second) 2.10.474.736 I slot print_timing: id 0 | task 14950 | total time = 1722.59 ms / 823 tokens 2.10.474.737 I slot print_timing: id 0 | task 14950 | graphs reused = 14309 2.10.474.737 I slot print_timing: id 0 | task 14950 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.474.775 I slot release: id 0 | task 14950 | stop processing: n_tokens = 854, truncated = 0 2.10.480.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 130383137 2.10.480.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.10.555.795 I slot launch_slot_: id 0 | task 15196 | processing task, is_child = 0 2.12.181.903 I slot print_timing: id 0 | task 15196 | prompt eval time = 179.78 ms / 925 tokens ( 0.19 ms per token, 5145.09 tokens per second) 2.12.181.909 I slot print_timing: id 0 | task 15196 | eval time = 1446.31 ms / 220 tokens ( 6.60 ms per token, 151.42 tokens per second) 2.12.181.910 I slot print_timing: id 0 | task 15196 | total time = 1626.09 ms / 1145 tokens 2.12.181.911 I slot print_timing: id 0 | task 15196 | graphs reused = 14526 2.12.181.911 I slot print_timing: id 0 | task 15196 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.181.961 I slot release: id 0 | task 15196 | stop processing: n_tokens = 1176, truncated = 0 2.12.210.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 132090323 2.12.210.670 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.12.304.344 I slot launch_slot_: id 0 | task 15420 | processing task, is_child = 0 2.14.124.671 I slot print_timing: id 0 | task 15420 | prompt eval time = 175.12 ms / 885 tokens ( 0.20 ms per token, 5053.62 tokens per second) 2.14.124.677 I slot print_timing: id 0 | task 15420 | eval time = 1645.18 ms / 245 tokens ( 6.74 ms per token, 148.31 tokens per second) 2.14.124.678 I slot print_timing: id 0 | task 15420 | total time = 1820.31 ms / 1130 tokens 2.14.124.679 I slot print_timing: id 0 | task 15420 | graphs reused = 14768 2.14.124.679 I slot print_timing: id 0 | task 15420 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.124.724 I slot release: id 0 | task 15420 | stop processing: n_tokens = 1161, truncated = 0 2.14.139.472 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 134033087 2.14.139.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.14.221.008 I slot launch_slot_: id 0 | task 15669 | processing task, is_child = 0 2.16.199.588 I slot print_timing: id 0 | task 15669 | prompt eval time = 119.14 ms / 392 tokens ( 0.30 ms per token, 3290.36 tokens per second) 2.16.199.593 I slot print_timing: id 0 | task 15669 | eval time = 1859.42 ms / 285 tokens ( 6.55 ms per token, 152.74 tokens per second) 2.16.199.595 I slot print_timing: id 0 | task 15669 | total time = 1978.56 ms / 677 tokens 2.16.199.596 I slot print_timing: id 0 | task 15669 | graphs reused = 15050 2.16.199.596 I slot print_timing: id 0 | task 15669 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.199.627 I slot release: id 0 | task 15669 | stop processing: n_tokens = 708, truncated = 0 2.16.203.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 136107990 2.16.203.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 2.16.287.448 I slot launch_slot_: id 0 | task 15957 | processing task, is_child = 0 2.16.890.229 I slot print_timing: id 0 | task 15957 | prompt eval time = 109.37 ms / 331 tokens ( 0.33 ms per token, 3026.40 tokens per second) 2.16.890.235 I slot print_timing: id 0 | task 15957 | eval time = 493.39 ms / 76 tokens ( 6.58 ms per token, 152.01 tokens per second) 2.16.890.236 I slot print_timing: id 0 | task 15957 | total time = 602.76 ms / 407 tokens 2.16.890.237 I slot print_timing: id 0 | task 15957 | graphs reused = 15124 2.16.890.238 I slot print_timing: id 0 | task 15957 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.890.267 I slot release: id 0 | task 15957 | stop processing: n_tokens = 438, truncated = 0 2.16.909.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 136798629 2.16.909.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.16.988.094 I slot launch_slot_: id 0 | task 16036 | processing task, is_child = 0 2.19.287.371 I slot print_timing: id 0 | task 16036 | prompt eval time = 108.66 ms / 357 tokens ( 0.30 ms per token, 3285.54 tokens per second) 2.19.287.377 I slot print_timing: id 0 | task 16036 | eval time = 2190.60 ms / 335 tokens ( 6.56 ms per token, 152.47 tokens per second) 2.19.287.378 I slot print_timing: id 0 | task 16036 | total time = 2299.26 ms / 692 tokens 2.19.287.379 I slot print_timing: id 0 | task 16036 | graphs reused = 15456 2.19.287.380 I slot print_timing: id 0 | task 16036 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.287.407 I slot release: id 0 | task 16036 | stop processing: n_tokens = 723, truncated = 0 2.19.302.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 723, t_last = 139195770 2.19.302.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 2.19.373.305 I slot launch_slot_: id 0 | task 16374 | processing task, is_child = 0 2.19.810.693 I slot print_timing: id 0 | task 16374 | prompt eval time = 114.23 ms / 315 tokens ( 0.36 ms per token, 2757.64 tokens per second) 2.19.810.698 I slot print_timing: id 0 | task 16374 | eval time = 323.14 ms / 50 tokens ( 6.59 ms per token, 151.64 tokens per second) 2.19.810.699 I slot print_timing: id 0 | task 16374 | total time = 437.37 ms / 365 tokens 2.19.810.700 I slot print_timing: id 0 | task 16374 | graphs reused = 15504 2.19.810.701 I slot print_timing: id 0 | task 16374 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.810.727 I slot release: id 0 | task 16374 | stop processing: n_tokens = 396, truncated = 0 2.19.834.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 139719090 2.19.834.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.19.911.759 I slot launch_slot_: id 0 | task 16427 | processing task, is_child = 0 2.20.414.388 I slot print_timing: id 0 | task 16427 | prompt eval time = 113.88 ms / 378 tokens ( 0.30 ms per token, 3319.23 tokens per second) 2.20.414.393 I slot print_timing: id 0 | task 16427 | eval time = 388.73 ms / 60 tokens ( 6.59 ms per token, 151.78 tokens per second) 2.20.414.394 I slot print_timing: id 0 | task 16427 | total time = 502.61 ms / 438 tokens 2.20.414.395 I slot print_timing: id 0 | task 16427 | graphs reused = 15562 2.20.414.396 I slot print_timing: id 0 | task 16427 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.414.425 I slot release: id 0 | task 16427 | stop processing: n_tokens = 469, truncated = 0 2.20.429.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 140322787 2.20.429.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 2.20.499.189 I slot launch_slot_: id 0 | task 16490 | processing task, is_child = 0 2.20.782.420 I slot print_timing: id 0 | task 16490 | prompt eval time = 102.76 ms / 295 tokens ( 0.35 ms per token, 2870.71 tokens per second) 2.20.782.426 I slot print_timing: id 0 | task 16490 | eval time = 180.45 ms / 28 tokens ( 6.68 ms per token, 149.63 tokens per second) 2.20.782.427 I slot print_timing: id 0 | task 16490 | total time = 283.21 ms / 323 tokens 2.20.782.428 I slot print_timing: id 0 | task 16490 | graphs reused = 15588 2.20.782.429 I slot print_timing: id 0 | task 16490 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.782.454 I slot release: id 0 | task 16490 | stop processing: n_tokens = 354, truncated = 0 2.20.803.000 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 140690816 2.20.803.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 2.20.881.825 I slot launch_slot_: id 0 | task 16521 | processing task, is_child = 0 2.23.995.013 I slot print_timing: id 0 | task 16521 | n_gen = 459, tg = 152.61 t/s, tg_3s = 152.95 t/s 2.26.999.955 I slot print_timing: id 0 | task 16521 | n_gen = 910, tg = 151.35 t/s, tg_3s = 150.09 t/s 2.27.780.131 I slot print_timing: id 0 | task 16521 | prompt eval time = 112.11 ms / 337 tokens ( 0.33 ms per token, 3005.87 tokens per second) 2.27.780.136 I slot print_timing: id 0 | task 16521 | eval time = 6786.17 ms / 1024 tokens ( 6.63 ms per token, 150.75 tokens per second) 2.27.780.137 I slot print_timing: id 0 | task 16521 | total time = 6898.28 ms / 1361 tokens 2.27.780.138 I slot print_timing: id 0 | task 16521 | graphs reused = 16606 2.27.780.139 I slot print_timing: id 0 | task 16521 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.780.166 I slot release: id 0 | task 16521 | stop processing: n_tokens = 1392, truncated = 0 2.27.800.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1392, t_last = 147688529 2.27.800.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 2.27.877.877 I slot launch_slot_: id 0 | task 17548 | processing task, is_child = 0 2.28.679.255 I slot print_timing: id 0 | task 17548 | prompt eval time = 110.53 ms / 325 tokens ( 0.34 ms per token, 2940.35 tokens per second) 2.28.679.262 I slot print_timing: id 0 | task 17548 | eval time = 690.83 ms / 102 tokens ( 6.84 ms per token, 146.20 tokens per second) 2.28.679.263 I slot print_timing: id 0 | task 17548 | total time = 801.36 ms / 427 tokens 2.28.679.264 I slot print_timing: id 0 | task 17548 | graphs reused = 16706 2.28.679.265 I slot print_timing: id 0 | task 17548 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.679.297 I slot release: id 0 | task 17548 | stop processing: n_tokens = 458, truncated = 0 2.28.695.313 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.070 2.28.738.892 I slot launch_slot_: id 0 | task 17653 | processing task, is_child = 0 2.30.095.946 I slot print_timing: id 0 | task 17653 | prompt eval time = 108.65 ms / 264 tokens ( 0.41 ms per token, 2429.87 tokens per second) 2.30.095.952 I slot print_timing: id 0 | task 17653 | eval time = 1248.39 ms / 187 tokens ( 6.71 ms per token, 148.99 tokens per second) 2.30.095.953 I slot print_timing: id 0 | task 17653 | total time = 1357.03 ms / 451 tokens 2.30.095.954 I slot print_timing: id 0 | task 17653 | graphs reused = 16891 2.30.095.955 I slot print_timing: id 0 | task 17653 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.095.981 I slot release: id 0 | task 17653 | stop processing: n_tokens = 482, truncated = 0 2.30.122.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 150004343 2.30.122.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 2.30.189.266 I slot launch_slot_: id 0 | task 17843 | processing task, is_child = 0 2.30.360.242 I slot print_timing: id 0 | task 17843 | prompt eval time = 110.28 ms / 331 tokens ( 0.33 ms per token, 3001.42 tokens per second) 2.30.360.247 I slot print_timing: id 0 | task 17843 | eval time = 60.67 ms / 9 tokens ( 7.58 ms per token, 131.85 tokens per second) 2.30.360.248 I slot print_timing: id 0 | task 17843 | total time = 170.96 ms / 340 tokens 2.30.360.249 I slot print_timing: id 0 | task 17843 | graphs reused = 16898 2.30.360.249 I slot print_timing: id 0 | task 17843 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.360.280 I slot release: id 0 | task 17843 | stop processing: n_tokens = 371, truncated = 0 2.30.386.219 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 371, t_last = 150268643 2.30.386.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 2.30.455.294 I slot launch_slot_: id 0 | task 17855 | processing task, is_child = 0 2.31.139.290 I slot print_timing: id 0 | task 17855 | prompt eval time = 110.23 ms / 333 tokens ( 0.33 ms per token, 3020.96 tokens per second) 2.31.139.296 I slot print_timing: id 0 | task 17855 | eval time = 573.75 ms / 85 tokens ( 6.83 ms per token, 146.41 tokens per second) 2.31.139.297 I slot print_timing: id 0 | task 17855 | total time = 683.98 ms / 418 tokens 2.31.139.298 I slot print_timing: id 0 | task 17855 | graphs reused = 16981 2.31.139.298 I slot print_timing: id 0 | task 17855 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.139.330 I slot release: id 0 | task 17855 | stop processing: n_tokens = 449, truncated = 0 2.31.162.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 151047692 2.31.162.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 2.31.251.609 I slot launch_slot_: id 0 | task 17943 | processing task, is_child = 0 2.31.728.390 I slot print_timing: id 0 | task 17943 | prompt eval time = 120.34 ms / 346 tokens ( 0.35 ms per token, 2875.21 tokens per second) 2.31.728.395 I slot print_timing: id 0 | task 17943 | eval time = 356.42 ms / 53 tokens ( 6.85 ms per token, 145.89 tokens per second) 2.31.728.396 I slot print_timing: id 0 | task 17943 | total time = 476.76 ms / 399 tokens 2.31.728.397 I slot print_timing: id 0 | task 17943 | graphs reused = 17032 2.31.728.398 I slot print_timing: id 0 | task 17943 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.728.427 I slot release: id 0 | task 17943 | stop processing: n_tokens = 430, truncated = 0 2.31.741.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 151636790 2.31.741.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 2.31.812.902 I slot launch_slot_: id 0 | task 17999 | processing task, is_child = 0 2.32.170.478 I slot print_timing: id 0 | task 17999 | prompt eval time = 109.85 ms / 325 tokens ( 0.34 ms per token, 2958.55 tokens per second) 2.32.170.484 I slot print_timing: id 0 | task 17999 | eval time = 247.71 ms / 37 tokens ( 6.88 ms per token, 145.33 tokens per second) 2.32.170.485 I slot print_timing: id 0 | task 17999 | total time = 357.56 ms / 362 tokens 2.32.170.486 I slot print_timing: id 0 | task 17999 | graphs reused = 17067 2.32.170.487 I slot print_timing: id 0 | task 17999 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.170.516 I slot release: id 0 | task 17999 | stop processing: n_tokens = 393, truncated = 0 2.32.194.488 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 152078879 2.32.194.534 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 2.32.276.686 I slot launch_slot_: id 0 | task 18039 | processing task, is_child = 0 2.33.963.886 I slot print_timing: id 0 | task 18039 | prompt eval time = 117.48 ms / 322 tokens ( 0.36 ms per token, 2740.92 tokens per second) 2.33.963.892 I slot print_timing: id 0 | task 18039 | eval time = 1569.70 ms / 232 tokens ( 6.80 ms per token, 147.16 tokens per second) 2.33.963.893 I slot print_timing: id 0 | task 18039 | total time = 1687.18 ms / 554 tokens 2.33.963.894 I slot print_timing: id 0 | task 18039 | graphs reused = 17296 2.33.963.895 I slot print_timing: id 0 | task 18039 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.963.923 I slot release: id 0 | task 18039 | stop processing: n_tokens = 585, truncated = 0 2.33.982.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 153872286 2.33.982.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 2.34.058.417 I slot launch_slot_: id 0 | task 18274 | processing task, is_child = 0 2.35.833.816 I slot print_timing: id 0 | task 18274 | prompt eval time = 113.31 ms / 338 tokens ( 0.34 ms per token, 2982.89 tokens per second) 2.35.833.822 I slot print_timing: id 0 | task 18274 | eval time = 1662.06 ms / 244 tokens ( 6.84 ms per token, 146.20 tokens per second) 2.35.833.823 I slot print_timing: id 0 | task 18274 | total time = 1775.38 ms / 582 tokens 2.35.833.823 I slot print_timing: id 0 | task 18274 | graphs reused = 17537 2.35.833.824 I slot print_timing: id 0 | task 18274 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.833.854 I slot release: id 0 | task 18274 | stop processing: n_tokens = 613, truncated = 0 2.35.861.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 613, t_last = 155742217 2.35.906.153 I slot launch_slot_: id 0 | task 18521 | processing task, is_child = 0 2.39.020.859 I slot print_timing: id 0 | task 18521 | n_gen = 442, tg = 146.81 t/s, tg_3s = 147.14 t/s 2.42.022.413 I slot print_timing: id 0 | task 18521 | n_gen = 882, tg = 146.70 t/s, tg_3s = 146.59 t/s 2.42.992.965 I slot print_timing: id 0 | task 18521 | prompt eval time = 110.72 ms / 347 tokens ( 0.32 ms per token, 3134.12 tokens per second) 2.42.992.971 I slot print_timing: id 0 | task 18521 | eval time = 6976.08 ms / 1024 tokens ( 6.82 ms per token, 146.64 tokens per second) 2.42.992.972 I slot print_timing: id 0 | task 18521 | total time = 7086.79 ms / 1371 tokens 2.42.992.973 I slot print_timing: id 0 | task 18521 | graphs reused = 18555 2.42.992.973 I slot print_timing: id 0 | task 18521 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.993.003 I slot release: id 0 | task 18521 | stop processing: n_tokens = 1402, truncated = 0 2.43.016.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 162901365 2.43.016.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 2.43.093.701 I slot launch_slot_: id 0 | task 19548 | processing task, is_child = 0 2.44.632.067 I slot print_timing: id 0 | task 19548 | prompt eval time = 109.42 ms / 331 tokens ( 0.33 ms per token, 3024.96 tokens per second) 2.44.632.073 I slot print_timing: id 0 | task 19548 | eval time = 1428.92 ms / 219 tokens ( 6.55 ms per token, 152.56 tokens per second) 2.44.632.074 I slot print_timing: id 0 | task 19548 | total time = 1538.35 ms / 550 tokens 2.44.632.075 I slot print_timing: id 0 | task 19548 | graphs reused = 18771 2.44.632.075 I slot print_timing: id 0 | task 19548 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.632.104 I slot release: id 0 | task 19548 | stop processing: n_tokens = 581, truncated = 0 2.44.654.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 164540466 2.44.654.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 2.44.724.364 I slot launch_slot_: id 0 | task 19770 | processing task, is_child = 0 2.45.669.993 I slot print_timing: id 0 | task 19770 | prompt eval time = 107.95 ms / 345 tokens ( 0.31 ms per token, 3196.04 tokens per second) 2.45.669.998 I slot print_timing: id 0 | task 19770 | eval time = 837.66 ms / 129 tokens ( 6.54 ms per token, 152.81 tokens per second) 2.45.669.999 I slot print_timing: id 0 | task 19770 | total time = 945.61 ms / 474 tokens 2.45.670.000 I slot print_timing: id 0 | task 19770 | graphs reused = 18898 2.45.670.001 I slot print_timing: id 0 | task 19770 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.670.028 I slot release: id 0 | task 19770 | stop processing: n_tokens = 505, truncated = 0 2.45.689.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 165578391 2.45.689.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 2.45.762.476 I slot launch_slot_: id 0 | task 19902 | processing task, is_child = 0 2.46.316.496 I slot print_timing: id 0 | task 19902 | prompt eval time = 107.64 ms / 320 tokens ( 0.34 ms per token, 2972.96 tokens per second) 2.46.316.501 I slot print_timing: id 0 | task 19902 | eval time = 446.36 ms / 69 tokens ( 6.56 ms per token, 152.34 tokens per second) 2.46.316.502 I slot print_timing: id 0 | task 19902 | total time = 554.00 ms / 389 tokens 2.46.316.504 I slot print_timing: id 0 | task 19902 | graphs reused = 18965 2.46.316.504 I slot print_timing: id 0 | task 19902 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.316.535 I slot release: id 0 | task 19902 | stop processing: n_tokens = 420, truncated = 0 2.46.334.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 166224898 2.46.334.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 2.46.403.264 I slot launch_slot_: id 0 | task 19974 | processing task, is_child = 0 2.46.838.589 I slot print_timing: id 0 | task 19974 | prompt eval time = 103.28 ms / 297 tokens ( 0.35 ms per token, 2875.71 tokens per second) 2.46.838.595 I slot print_timing: id 0 | task 19974 | eval time = 332.03 ms / 47 tokens ( 7.22 ms per token, 138.54 tokens per second) 2.46.838.596 I slot print_timing: id 0 | task 19974 | total time = 435.31 ms / 344 tokens 2.46.838.597 I slot print_timing: id 0 | task 19974 | graphs reused = 19010 2.46.838.598 I slot print_timing: id 0 | task 19974 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.838.624 I slot release: id 0 | task 19974 | stop processing: n_tokens = 375, truncated = 0 2.46.842.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 166746987 2.46.842.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 2.46.925.148 I slot launch_slot_: id 0 | task 20024 | processing task, is_child = 0 2.47.706.933 I slot print_timing: id 0 | task 20024 | prompt eval time = 113.17 ms / 343 tokens ( 0.33 ms per token, 3030.87 tokens per second) 2.47.706.939 I slot print_timing: id 0 | task 20024 | eval time = 668.60 ms / 103 tokens ( 6.55 ms per token, 152.56 tokens per second) 2.47.706.940 I slot print_timing: id 0 | task 20024 | total time = 781.76 ms / 446 tokens 2.47.706.941 I slot print_timing: id 0 | task 20024 | graphs reused = 19111 2.47.706.942 I slot print_timing: id 0 | task 20024 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.706.970 I slot release: id 0 | task 20024 | stop processing: n_tokens = 477, truncated = 0 2.47.722.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 167615332 2.47.771.618 I slot launch_slot_: id 0 | task 20130 | processing task, is_child = 0 2.48.510.904 I slot print_timing: id 0 | task 20130 | prompt eval time = 112.14 ms / 371 tokens ( 0.30 ms per token, 3308.36 tokens per second) 2.48.510.910 I slot print_timing: id 0 | task 20130 | eval time = 627.13 ms / 96 tokens ( 6.60 ms per token, 151.48 tokens per second) 2.48.510.911 I slot print_timing: id 0 | task 20130 | total time = 739.27 ms / 467 tokens 2.48.510.912 I slot print_timing: id 0 | task 20130 | graphs reused = 19205 2.48.510.913 I slot print_timing: id 0 | task 20130 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.510.946 I slot release: id 0 | task 20130 | stop processing: n_tokens = 498, truncated = 0 2.48.528.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 168419309 2.48.528.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 2.48.595.067 I slot launch_slot_: id 0 | task 20229 | processing task, is_child = 0 2.49.713.705 I slot print_timing: id 0 | task 20229 | prompt eval time = 104.62 ms / 292 tokens ( 0.36 ms per token, 2791.08 tokens per second) 2.49.713.711 I slot print_timing: id 0 | task 20229 | eval time = 1014.00 ms / 156 tokens ( 6.54 ms per token, 152.86 tokens per second) 2.49.713.712 I slot print_timing: id 0 | task 20229 | total time = 1118.62 ms / 448 tokens 2.49.713.713 I slot print_timing: id 0 | task 20229 | graphs reused = 19359 2.49.713.714 I slot print_timing: id 0 | task 20229 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.713.741 I slot release: id 0 | task 20229 | stop processing: n_tokens = 479, truncated = 0 2.49.728.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 169622104 2.49.728.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 2.49.808.013 I slot launch_slot_: id 0 | task 20388 | processing task, is_child = 0 2.50.780.952 I slot print_timing: id 0 | task 20388 | prompt eval time = 102.51 ms / 301 tokens ( 0.34 ms per token, 2936.41 tokens per second) 2.50.780.957 I slot print_timing: id 0 | task 20388 | eval time = 870.41 ms / 134 tokens ( 6.54 ms per token, 152.80 tokens per second) 2.50.780.958 I slot print_timing: id 0 | task 20388 | total time = 972.92 ms / 435 tokens 2.50.780.959 I slot print_timing: id 0 | task 20388 | graphs reused = 19491 2.50.780.960 I slot print_timing: id 0 | task 20388 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.780.987 I slot release: id 0 | task 20388 | stop processing: n_tokens = 466, truncated = 0 2.50.784.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 170689349 2.50.784.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 2.50.852.410 I slot launch_slot_: id 0 | task 20525 | processing task, is_child = 0 2.51.416.585 I slot print_timing: id 0 | task 20525 | prompt eval time = 103.62 ms / 303 tokens ( 0.34 ms per token, 2924.09 tokens per second) 2.51.416.590 I slot print_timing: id 0 | task 20525 | eval time = 460.53 ms / 71 tokens ( 6.58 ms per token, 152.00 tokens per second) 2.51.416.591 I slot print_timing: id 0 | task 20525 | total time = 564.15 ms / 374 tokens 2.51.416.592 I slot print_timing: id 0 | task 20525 | graphs reused = 19560 2.51.416.593 I slot print_timing: id 0 | task 20525 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.416.617 I slot release: id 0 | task 20525 | stop processing: n_tokens = 405, truncated = 0 2.51.441.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 171324980 2.51.441.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 2.51.511.458 I slot launch_slot_: id 0 | task 20599 | processing task, is_child = 0 2.51.970.012 I slot print_timing: id 0 | task 20599 | prompt eval time = 108.23 ms / 321 tokens ( 0.34 ms per token, 2965.88 tokens per second) 2.51.970.017 I slot print_timing: id 0 | task 20599 | eval time = 350.30 ms / 54 tokens ( 6.61 ms per token, 151.30 tokens per second) 2.51.970.019 I slot print_timing: id 0 | task 20599 | total time = 458.53 ms / 375 tokens 2.51.970.021 I slot print_timing: id 0 | task 20599 | graphs reused = 19612 2.51.970.021 I slot print_timing: id 0 | task 20599 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.970.050 I slot release: id 0 | task 20599 | stop processing: n_tokens = 406, truncated = 0 2.51.984.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 171878413 2.51.984.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.645 MiB) 2.52.061.167 I slot launch_slot_: id 0 | task 20656 | processing task, is_child = 0 2.52.527.522 I slot print_timing: id 0 | task 20656 | prompt eval time = 114.92 ms / 322 tokens ( 0.36 ms per token, 2802.00 tokens per second) 2.52.527.527 I slot print_timing: id 0 | task 20656 | eval time = 351.42 ms / 54 tokens ( 6.63 ms per token, 150.82 tokens per second) 2.52.527.528 I slot print_timing: id 0 | task 20656 | total time = 466.33 ms / 376 tokens 2.52.527.529 I slot print_timing: id 0 | task 20656 | graphs reused = 19664 2.52.527.530 I slot print_timing: id 0 | task 20656 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.527.557 I slot release: id 0 | task 20656 | stop processing: n_tokens = 407, truncated = 0 2.52.548.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 172435920 2.52.548.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.201 MiB) 2.52.619.641 I slot launch_slot_: id 0 | task 20713 | processing task, is_child = 0 2.53.681.366 I slot print_timing: id 0 | task 20713 | prompt eval time = 107.22 ms / 323 tokens ( 0.33 ms per token, 3012.61 tokens per second) 2.53.681.372 I slot print_timing: id 0 | task 20713 | eval time = 954.49 ms / 147 tokens ( 6.54 ms per token, 152.96 tokens per second) 2.53.681.373 I slot print_timing: id 0 | task 20713 | total time = 1061.70 ms / 470 tokens 2.53.681.375 I slot print_timing: id 0 | task 20713 | graphs reused = 19809 2.53.681.375 I slot print_timing: id 0 | task 20713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.681.404 I slot release: id 0 | task 20713 | stop processing: n_tokens = 501, truncated = 0 2.53.704.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 173589766 2.53.704.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.114 MiB) 2.53.770.411 I slot launch_slot_: id 0 | task 20863 | processing task, is_child = 0 2.56.879.008 I slot print_timing: id 0 | task 20863 | n_gen = 459, tg = 152.57 t/s, tg_3s = 152.90 t/s 2.58.620.013 I slot print_timing: id 0 | task 20863 | prompt eval time = 106.63 ms / 321 tokens ( 0.33 ms per token, 3010.49 tokens per second) 2.58.620.020 I slot print_timing: id 0 | task 20863 | eval time = 4742.96 ms / 724 tokens ( 6.56 ms per token, 152.44 tokens per second) 2.58.620.020 I slot print_timing: id 0 | task 20863 | total time = 4849.59 ms / 1045 tokens 2.58.620.021 I slot print_timing: id 0 | task 20863 | graphs reused = 20528 2.58.620.022 I slot print_timing: id 0 | task 20863 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.620.050 I slot release: id 0 | task 20863 | stop processing: n_tokens = 1076, truncated = 0 2.58.638.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1076, t_last = 178528413 2.58.638.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 2.58.708.248 I slot launch_slot_: id 0 | task 21590 | processing task, is_child = 0 3.00.695.351 I slot print_timing: id 0 | task 21590 | prompt eval time = 106.09 ms / 322 tokens ( 0.33 ms per token, 3035.19 tokens per second) 3.00.695.356 I slot print_timing: id 0 | task 21590 | eval time = 1880.99 ms / 288 tokens ( 6.55 ms per token, 152.58 tokens per second) 3.00.695.357 I slot print_timing: id 0 | task 21590 | total time = 1987.08 ms / 610 tokens 3.00.695.358 I slot print_timing: id 0 | task 21590 | graphs reused = 20813 3.00.695.359 I slot print_timing: id 0 | task 21590 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.695.387 I slot release: id 0 | task 21590 | stop processing: n_tokens = 641, truncated = 0 3.00.712.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 641, t_last = 180603749 3.00.712.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 3.00.781.707 I slot launch_slot_: id 0 | task 21881 | processing task, is_child = 0 3.01.189.266 I slot print_timing: id 0 | task 21881 | prompt eval time = 108.58 ms / 337 tokens ( 0.32 ms per token, 3103.59 tokens per second) 3.01.189.273 I slot print_timing: id 0 | task 21881 | eval time = 298.95 ms / 46 tokens ( 6.64 ms per token, 150.52 tokens per second) 3.01.189.275 I slot print_timing: id 0 | task 21881 | total time = 407.54 ms / 383 tokens 3.01.189.275 I slot print_timing: id 0 | task 21881 | graphs reused = 20857 3.01.189.276 I slot print_timing: id 0 | task 21881 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.189.305 I slot release: id 0 | task 21881 | stop processing: n_tokens = 414, truncated = 0 3.01.210.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 181097668 3.01.210.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.01.289.799 I slot launch_slot_: id 0 | task 21930 | processing task, is_child = 0 3.01.707.870 I slot print_timing: id 0 | task 21930 | prompt eval time = 113.51 ms / 325 tokens ( 0.35 ms per token, 2863.13 tokens per second) 3.01.707.875 I slot print_timing: id 0 | task 21930 | eval time = 304.54 ms / 47 tokens ( 6.62 ms per token, 151.05 tokens per second) 3.01.707.876 I slot print_timing: id 0 | task 21930 | total time = 418.05 ms / 372 tokens 3.01.707.877 I slot print_timing: id 0 | task 21930 | graphs reused = 20902 3.01.707.878 I slot print_timing: id 0 | task 21930 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.707.907 I slot release: id 0 | task 21930 | stop processing: n_tokens = 403, truncated = 0 3.01.727.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 181616270 3.01.727.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 345.036 MiB) 3.01.802.843 I slot launch_slot_: id 0 | task 21980 | processing task, is_child = 0 3.02.246.893 I slot print_timing: id 0 | task 21980 | prompt eval time = 107.76 ms / 331 tokens ( 0.33 ms per token, 3071.61 tokens per second) 3.02.246.898 I slot print_timing: id 0 | task 21980 | eval time = 336.27 ms / 52 tokens ( 6.59 ms per token, 151.66 tokens per second) 3.02.246.900 I slot print_timing: id 0 | task 21980 | total time = 444.03 ms / 383 tokens 3.02.246.901 I slot print_timing: id 0 | task 21980 | graphs reused = 20952 3.02.246.902 I slot print_timing: id 0 | task 21980 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.246.933 I slot release: id 0 | task 21980 | stop processing: n_tokens = 414, truncated = 0 3.02.260.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 182155295 3.02.260.231 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.827 MiB) 3.02.334.487 I slot launch_slot_: id 0 | task 22035 | processing task, is_child = 0 3.03.277.266 I slot print_timing: id 0 | task 22035 | prompt eval time = 111.64 ms / 336 tokens ( 0.33 ms per token, 3009.73 tokens per second) 3.03.277.272 I slot print_timing: id 0 | task 22035 | eval time = 831.12 ms / 128 tokens ( 6.54 ms per token, 152.81 tokens per second) 3.03.277.273 I slot print_timing: id 0 | task 22035 | total time = 942.76 ms / 464 tokens 3.03.277.274 I slot print_timing: id 0 | task 22035 | graphs reused = 21078 3.03.277.275 I slot print_timing: id 0 | task 22035 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.277.303 I slot release: id 0 | task 22035 | stop processing: n_tokens = 495, truncated = 0 3.03.291.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 183185666 3.03.291.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 3.03.357.770 I slot launch_slot_: id 0 | task 22166 | processing task, is_child = 0 3.03.659.514 I slot print_timing: id 0 | task 22166 | prompt eval time = 108.25 ms / 349 tokens ( 0.31 ms per token, 3224.14 tokens per second) 3.03.659.520 I slot print_timing: id 0 | task 22166 | eval time = 193.48 ms / 30 tokens ( 6.67 ms per token, 149.89 tokens per second) 3.03.659.521 I slot print_timing: id 0 | task 22166 | total time = 301.72 ms / 379 tokens 3.03.659.522 I slot print_timing: id 0 | task 22166 | graphs reused = 21106 3.03.659.522 I slot print_timing: id 0 | task 22166 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.659.550 I slot release: id 0 | task 22166 | stop processing: n_tokens = 410, truncated = 0 3.03.681.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 183567912 3.03.681.455 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.106 MiB) 3.03.748.109 I slot launch_slot_: id 0 | task 22199 | processing task, is_child = 0 3.06.861.066 I slot print_timing: id 0 | task 22199 | n_gen = 459, tg = 152.58 t/s, tg_3s = 152.91 t/s 3.07.980.551 I slot print_timing: id 0 | task 22199 | prompt eval time = 111.15 ms / 336 tokens ( 0.33 ms per token, 3022.89 tokens per second) 3.07.980.557 I slot print_timing: id 0 | task 22199 | eval time = 4121.27 ms / 630 tokens ( 6.55 ms per token, 152.62 tokens per second) 3.07.980.558 I slot print_timing: id 0 | task 22199 | total time = 4232.42 ms / 966 tokens 3.07.980.559 I slot print_timing: id 0 | task 22199 | graphs reused = 21732 3.07.980.559 I slot print_timing: id 0 | task 22199 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.980.591 I slot release: id 0 | task 22199 | stop processing: n_tokens = 997, truncated = 0 3.07.999.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 997, t_last = 187888954 3.07.999.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.545 MiB) 3.08.067.762 I slot launch_slot_: id 0 | task 22832 | processing task, is_child = 0 3.11.146.011 I slot print_timing: id 0 | task 22832 | prompt eval time = 107.81 ms / 349 tokens ( 0.31 ms per token, 3237.12 tokens per second) 3.11.146.016 I slot print_timing: id 0 | task 22832 | eval time = 2970.42 ms / 454 tokens ( 6.56 ms per token, 152.50 tokens per second) 3.11.146.017 I slot print_timing: id 0 | task 22832 | total time = 3078.23 ms / 803 tokens 3.11.146.018 I slot print_timing: id 0 | task 22832 | graphs reused = 22182 3.11.146.019 I slot print_timing: id 0 | task 22832 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.146.047 I slot release: id 0 | task 22832 | stop processing: n_tokens = 834, truncated = 0 3.11.171.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 834, t_last = 191054410 3.11.171.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 3.11.239.003 I slot launch_slot_: id 0 | task 23289 | processing task, is_child = 0 3.11.700.392 I slot print_timing: id 0 | task 23289 | prompt eval time = 111.57 ms / 349 tokens ( 0.32 ms per token, 3128.05 tokens per second) 3.11.700.398 I slot print_timing: id 0 | task 23289 | eval time = 349.80 ms / 54 tokens ( 6.60 ms per token, 151.52 tokens per second) 3.11.700.399 I slot print_timing: id 0 | task 23289 | total time = 461.37 ms / 403 tokens 3.11.700.399 I slot print_timing: id 0 | task 23289 | graphs reused = 22234 3.11.700.400 I slot print_timing: id 0 | task 23289 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.700.428 I slot release: id 0 | task 23289 | stop processing: n_tokens = 434, truncated = 0 3.11.720.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 191608791 3.11.720.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.794 MiB) 3.11.787.683 I slot launch_slot_: id 0 | task 23346 | processing task, is_child = 0 3.12.353.615 I slot print_timing: id 0 | task 23346 | prompt eval time = 112.58 ms / 385 tokens ( 0.29 ms per token, 3419.67 tokens per second) 3.12.353.620 I slot print_timing: id 0 | task 23346 | eval time = 453.33 ms / 70 tokens ( 6.57 ms per token, 152.21 tokens per second) 3.12.353.621 I slot print_timing: id 0 | task 23346 | total time = 565.91 ms / 455 tokens 3.12.353.622 I slot print_timing: id 0 | task 23346 | graphs reused = 22302 3.12.353.623 I slot print_timing: id 0 | task 23346 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.353.651 I slot release: id 0 | task 23346 | stop processing: n_tokens = 486, truncated = 0 3.12.376.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 192262013 3.12.376.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 3.12.442.902 I slot launch_slot_: id 0 | task 23419 | processing task, is_child = 0 3.12.920.724 I slot print_timing: id 0 | task 23419 | prompt eval time = 107.97 ms / 328 tokens ( 0.33 ms per token, 3037.77 tokens per second) 3.12.920.729 I slot print_timing: id 0 | task 23419 | eval time = 369.83 ms / 57 tokens ( 6.60 ms per token, 151.42 tokens per second) 3.12.920.731 I slot print_timing: id 0 | task 23419 | total time = 477.80 ms / 385 tokens 3.12.920.731 I slot print_timing: id 0 | task 23419 | graphs reused = 22357 3.12.920.732 I slot print_timing: id 0 | task 23419 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.920.760 I slot release: id 0 | task 23419 | stop processing: n_tokens = 416, truncated = 0