$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-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 0.00.092.493 I srv llama_server: initializing ... 0.00.092.499 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.092.607 I srv init_listene: The UI is disabled 0.00.092.609 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.092.684 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.106.276 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-Q4_K_M.gguf' 0.02.871.343 I cmn init: llama threadpool init, n_threads = 8 0.02.945.675 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.950.317 I srv llama_server: model loaded 0.02.950.323 I srv llama_server: listening on http://127.0.0.1:8089 0.04.533.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.534.163 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.207.818 I slot print_timing: id 0 | task 0 | prompt eval time = 144.01 ms / 368 tokens ( 0.39 ms per token, 2555.45 tokens per second) 0.05.207.824 I slot print_timing: id 0 | task 0 | eval time = 529.63 ms / 53 tokens ( 10.19 ms per token, 98.18 tokens per second) 0.05.207.826 I slot print_timing: id 0 | task 0 | total time = 673.64 ms / 421 tokens 0.05.207.831 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.207.832 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.207.862 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.231.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5117305 0.05.255.487 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.05.790.090 I slot print_timing: id 0 | task 56 | prompt eval time = 118.81 ms / 322 tokens ( 0.37 ms per token, 2710.10 tokens per second) 0.05.790.096 I slot print_timing: id 0 | task 56 | eval time = 415.77 ms / 42 tokens ( 10.14 ms per token, 98.61 tokens per second) 0.05.790.097 I slot print_timing: id 0 | task 56 | total time = 534.58 ms / 364 tokens 0.05.790.098 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.05.790.099 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.790.125 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.05.809.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5699569 0.05.833.324 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.06.370.877 I slot print_timing: id 0 | task 101 | prompt eval time = 120.85 ms / 365 tokens ( 0.33 ms per token, 3020.32 tokens per second) 0.06.370.882 I slot print_timing: id 0 | task 101 | eval time = 416.69 ms / 42 tokens ( 10.16 ms per token, 98.40 tokens per second) 0.06.370.884 I slot print_timing: id 0 | task 101 | total time = 537.53 ms / 407 tokens 0.06.370.886 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.06.370.887 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.370.914 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.06.390.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6280357 0.06.414.569 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.06.968.878 I slot print_timing: id 0 | task 146 | prompt eval time = 128.01 ms / 397 tokens ( 0.32 ms per token, 3101.27 tokens per second) 0.06.968.885 I slot print_timing: id 0 | task 146 | eval time = 426.28 ms / 43 tokens ( 10.15 ms per token, 98.53 tokens per second) 0.06.968.887 I slot print_timing: id 0 | task 146 | total time = 554.29 ms / 440 tokens 0.06.968.887 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.06.968.889 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.968.920 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.06.988.148 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 0.07.012.645 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.07.683.573 I slot print_timing: id 0 | task 192 | prompt eval time = 123.69 ms / 383 tokens ( 0.32 ms per token, 3096.48 tokens per second) 0.07.683.578 I slot print_timing: id 0 | task 192 | eval time = 547.22 ms / 55 tokens ( 10.13 ms per token, 98.68 tokens per second) 0.07.683.579 I slot print_timing: id 0 | task 192 | total time = 670.91 ms / 438 tokens 0.07.683.580 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.07.683.581 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.683.609 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.07.704.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7593053 0.07.728.221 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.08.402.995 I slot print_timing: id 0 | task 250 | prompt eval time = 125.98 ms / 372 tokens ( 0.34 ms per token, 2952.90 tokens per second) 0.08.403.003 I slot print_timing: id 0 | task 250 | eval time = 548.78 ms / 55 tokens ( 10.16 ms per token, 98.40 tokens per second) 0.08.403.004 I slot print_timing: id 0 | task 250 | total time = 674.76 ms / 427 tokens 0.08.403.005 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.08.403.006 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.403.033 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.08.425.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8312477 0.08.449.868 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.09.139.213 I slot print_timing: id 0 | task 308 | prompt eval time = 142.59 ms / 422 tokens ( 0.34 ms per token, 2959.51 tokens per second) 0.09.139.219 I slot print_timing: id 0 | task 308 | eval time = 546.74 ms / 55 tokens ( 10.12 ms per token, 98.77 tokens per second) 0.09.139.220 I slot print_timing: id 0 | task 308 | total time = 689.33 ms / 477 tokens 0.09.139.221 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.09.139.222 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.139.250 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.09.166.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 9048694 0.09.191.106 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.10.059.047 I slot print_timing: id 0 | task 366 | prompt eval time = 145.53 ms / 470 tokens ( 0.31 ms per token, 3229.51 tokens per second) 0.10.059.052 I slot print_timing: id 0 | task 366 | eval time = 722.39 ms / 72 tokens ( 10.17 ms per token, 98.28 tokens per second) 0.10.059.053 I slot print_timing: id 0 | task 366 | total time = 867.92 ms / 542 tokens 0.10.059.054 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.10.059.055 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.059.085 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.10.077.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 9968529 0.10.102.358 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.10.688.504 I slot print_timing: id 0 | task 441 | prompt eval time = 120.03 ms / 345 tokens ( 0.35 ms per token, 2874.19 tokens per second) 0.10.688.509 I slot print_timing: id 0 | task 441 | eval time = 466.09 ms / 47 tokens ( 10.13 ms per token, 98.69 tokens per second) 0.10.688.511 I slot print_timing: id 0 | task 441 | total time = 586.13 ms / 392 tokens 0.10.688.512 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.10.688.513 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.688.541 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.10.713.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 10597985 0.10.738.486 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.11.266.061 I slot print_timing: id 0 | task 491 | prompt eval time = 121.53 ms / 364 tokens ( 0.33 ms per token, 2995.12 tokens per second) 0.11.266.066 I slot print_timing: id 0 | task 491 | eval time = 406.02 ms / 41 tokens ( 10.15 ms per token, 98.52 tokens per second) 0.11.266.067 I slot print_timing: id 0 | task 491 | total time = 527.56 ms / 405 tokens 0.11.266.068 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.11.266.069 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.266.098 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.11.292.629 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 11175541 0.11.317.333 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.12.093.508 I slot print_timing: id 0 | task 535 | prompt eval time = 127.06 ms / 376 tokens ( 0.34 ms per token, 2959.16 tokens per second) 0.12.093.514 I slot print_timing: id 0 | task 535 | eval time = 649.09 ms / 62 tokens ( 10.64 ms per token, 93.98 tokens per second) 0.12.093.515 I slot print_timing: id 0 | task 535 | total time = 776.15 ms / 438 tokens 0.12.093.515 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.12.093.516 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.093.544 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.12.107.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12002987 0.12.132.376 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.12.727.351 I slot print_timing: id 0 | task 600 | prompt eval time = 127.56 ms / 412 tokens ( 0.31 ms per token, 3229.75 tokens per second) 0.12.727.357 I slot print_timing: id 0 | task 600 | eval time = 467.39 ms / 47 tokens ( 10.16 ms per token, 98.42 tokens per second) 0.12.727.359 I slot print_timing: id 0 | task 600 | total time = 594.96 ms / 459 tokens 0.12.727.360 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.12.727.361 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.727.390 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.12.748.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 12636833 0.12.773.838 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.13.516.793 I slot print_timing: id 0 | task 650 | prompt eval time = 122.42 ms / 376 tokens ( 0.33 ms per token, 3071.42 tokens per second) 0.13.516.799 I slot print_timing: id 0 | task 650 | eval time = 620.52 ms / 62 tokens ( 10.17 ms per token, 98.31 tokens per second) 0.13.516.800 I slot print_timing: id 0 | task 650 | total time = 742.93 ms / 438 tokens 0.13.516.801 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.13.516.802 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.516.829 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.13.545.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13426272 0.13.570.572 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.14.213.444 I slot print_timing: id 0 | task 715 | prompt eval time = 126.70 ms / 378 tokens ( 0.34 ms per token, 2983.43 tokens per second) 0.14.213.449 I slot print_timing: id 0 | task 715 | eval time = 516.15 ms / 52 tokens ( 10.12 ms per token, 98.81 tokens per second) 0.14.213.450 I slot print_timing: id 0 | task 715 | total time = 642.85 ms / 430 tokens 0.14.213.451 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.14.213.452 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.213.479 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.14.229.464 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 14122923 0.14.256.714 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.14.993.271 I slot print_timing: id 0 | task 770 | prompt eval time = 126.65 ms / 367 tokens ( 0.35 ms per token, 2897.75 tokens per second) 0.14.993.277 I slot print_timing: id 0 | task 770 | eval time = 609.89 ms / 58 tokens ( 10.70 ms per token, 93.46 tokens per second) 0.14.993.278 I slot print_timing: id 0 | task 770 | total time = 736.54 ms / 425 tokens 0.14.993.279 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.14.993.280 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.993.308 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.15.010.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 14902752 0.15.036.628 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.15.665.197 I slot print_timing: id 0 | task 831 | prompt eval time = 120.32 ms / 347 tokens ( 0.35 ms per token, 2884.05 tokens per second) 0.15.665.203 I slot print_timing: id 0 | task 831 | eval time = 508.24 ms / 51 tokens ( 10.16 ms per token, 98.38 tokens per second) 0.15.665.204 I slot print_timing: id 0 | task 831 | total time = 628.55 ms / 398 tokens 0.15.665.205 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.15.665.207 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.665.234 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.15.683.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 15574678 0.15.708.586 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.16.239.236 I slot print_timing: id 0 | task 885 | prompt eval time = 120.68 ms / 369 tokens ( 0.33 ms per token, 3057.62 tokens per second) 0.16.239.241 I slot print_timing: id 0 | task 885 | eval time = 409.95 ms / 41 tokens ( 10.25 ms per token, 97.57 tokens per second) 0.16.239.242 I slot print_timing: id 0 | task 885 | total time = 530.63 ms / 410 tokens 0.16.239.243 I slot print_timing: id 0 | task 885 | graphs reused = 844 0.16.239.244 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.239.271 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 0.16.262.792 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 16148714 0.16.289.265 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 0.16.817.232 I slot print_timing: id 0 | task 929 | prompt eval time = 120.70 ms / 352 tokens ( 0.34 ms per token, 2916.27 tokens per second) 0.16.817.237 I slot print_timing: id 0 | task 929 | eval time = 407.25 ms / 41 tokens ( 10.18 ms per token, 98.22 tokens per second) 0.16.817.238 I slot print_timing: id 0 | task 929 | total time = 527.95 ms / 393 tokens 0.16.817.240 I slot print_timing: id 0 | task 929 | graphs reused = 883 0.16.817.240 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.817.267 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 0.16.838.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 16726711 0.16.863.498 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 0.17.380.363 I slot print_timing: id 0 | task 973 | prompt eval time = 119.18 ms / 349 tokens ( 0.34 ms per token, 2928.27 tokens per second) 0.17.380.369 I slot print_timing: id 0 | task 973 | eval time = 397.66 ms / 40 tokens ( 10.20 ms per token, 98.07 tokens per second) 0.17.380.370 I slot print_timing: id 0 | task 973 | total time = 516.85 ms / 389 tokens 0.17.380.370 I slot print_timing: id 0 | task 973 | graphs reused = 921 0.17.380.371 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.380.398 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 0.17.400.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 17289842 0.17.425.142 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.18.213.385 I slot print_timing: id 0 | task 1016 | prompt eval time = 128.02 ms / 384 tokens ( 0.33 ms per token, 2999.46 tokens per second) 0.18.213.391 I slot print_timing: id 0 | task 1016 | eval time = 660.20 ms / 63 tokens ( 10.65 ms per token, 93.91 tokens per second) 0.18.213.392 I slot print_timing: id 0 | task 1016 | total time = 788.22 ms / 447 tokens 0.18.213.392 I slot print_timing: id 0 | task 1016 | graphs reused = 982 0.18.213.393 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.213.422 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 0.18.228.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 18122866 0.18.253.578 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.18.910.728 I slot print_timing: id 0 | task 1082 | prompt eval time = 120.52 ms / 356 tokens ( 0.34 ms per token, 2953.77 tokens per second) 0.18.910.734 I slot print_timing: id 0 | task 1082 | eval time = 536.61 ms / 54 tokens ( 10.12 ms per token, 98.77 tokens per second) 0.18.910.735 I slot print_timing: id 0 | task 1082 | total time = 657.13 ms / 410 tokens 0.18.910.735 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 0.18.910.736 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.910.763 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 0.18.930.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 18820207 0.18.956.053 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 0.19.785.688 I slot print_timing: id 0 | task 1139 | prompt eval time = 129.34 ms / 410 tokens ( 0.32 ms per token, 3169.94 tokens per second) 0.19.785.694 I slot print_timing: id 0 | task 1139 | eval time = 700.28 ms / 70 tokens ( 10.15 ms per token, 98.53 tokens per second) 0.19.785.696 I slot print_timing: id 0 | task 1139 | total time = 829.62 ms / 480 tokens 0.19.785.696 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 0.19.785.698 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.785.726 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 0.19.806.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 19695169 0.19.833.914 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 0.20.540.668 I slot print_timing: id 0 | task 1212 | prompt eval time = 127.70 ms / 385 tokens ( 0.33 ms per token, 3014.95 tokens per second) 0.20.540.673 I slot print_timing: id 0 | task 1212 | eval time = 579.04 ms / 58 tokens ( 10.16 ms per token, 98.44 tokens per second) 0.20.540.674 I slot print_timing: id 0 | task 1212 | total time = 706.74 ms / 443 tokens 0.20.540.675 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 0.20.540.676 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.540.703 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 0.20.557.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 20450147 0.20.587.962 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.21.428.591 I slot print_timing: id 0 | task 1273 | prompt eval time = 129.26 ms / 395 tokens ( 0.33 ms per token, 3055.83 tokens per second) 0.21.428.597 I slot print_timing: id 0 | task 1273 | eval time = 711.35 ms / 71 tokens ( 10.16 ms per token, 98.40 tokens per second) 0.21.428.598 I slot print_timing: id 0 | task 1273 | total time = 840.61 ms / 466 tokens 0.21.428.599 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.21.428.600 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.428.631 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.21.442.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 21338074 0.21.467.796 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.22.215.152 I slot print_timing: id 0 | task 1347 | prompt eval time = 130.43 ms / 430 tokens ( 0.30 ms per token, 3296.79 tokens per second) 0.22.215.158 I slot print_timing: id 0 | task 1347 | eval time = 616.91 ms / 62 tokens ( 10.11 ms per token, 98.88 tokens per second) 0.22.215.159 I slot print_timing: id 0 | task 1347 | total time = 747.34 ms / 492 tokens 0.22.215.160 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 0.22.215.160 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.215.191 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 0.22.229.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 22124634 0.22.254.711 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 0.23.008.592 I slot print_timing: id 0 | task 1412 | prompt eval time = 129.42 ms / 392 tokens ( 0.33 ms per token, 3028.85 tokens per second) 0.23.008.598 I slot print_timing: id 0 | task 1412 | eval time = 624.44 ms / 62 tokens ( 10.24 ms per token, 97.69 tokens per second) 0.23.008.599 I slot print_timing: id 0 | task 1412 | total time = 753.86 ms / 454 tokens 0.23.008.600 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 0.23.008.601 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.008.631 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 0.23.036.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 22918074 0.23.063.158 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 0.23.672.681 I slot print_timing: id 0 | task 1477 | prompt eval time = 120.58 ms / 350 tokens ( 0.34 ms per token, 2902.61 tokens per second) 0.23.672.687 I slot print_timing: id 0 | task 1477 | eval time = 488.93 ms / 49 tokens ( 10.19 ms per token, 98.17 tokens per second) 0.23.672.688 I slot print_timing: id 0 | task 1477 | total time = 609.51 ms / 399 tokens 0.23.672.690 I slot print_timing: id 0 | task 1477 | graphs reused = 1394 0.23.672.691 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.672.722 I slot release: id 0 | task 1477 | stop processing: n_tokens = 398, truncated = 0 0.23.693.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 23582166 0.23.718.745 I slot launch_slot_: id 0 | task 1529 | processing task, is_child = 0 0.24.452.656 I slot print_timing: id 0 | task 1529 | prompt eval time = 127.17 ms / 380 tokens ( 0.33 ms per token, 2988.03 tokens per second) 0.24.452.662 I slot print_timing: id 0 | task 1529 | eval time = 606.72 ms / 61 tokens ( 10.11 ms per token, 98.89 tokens per second) 0.24.452.664 I slot print_timing: id 0 | task 1529 | total time = 733.89 ms / 441 tokens 0.24.452.664 I slot print_timing: id 0 | task 1529 | graphs reused = 1453 0.24.452.665 I slot print_timing: id 0 | task 1529 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.452.695 I slot release: id 0 | task 1529 | stop processing: n_tokens = 440, truncated = 0 0.24.472.764 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 24362139 0.24.498.353 I slot launch_slot_: id 0 | task 1593 | processing task, is_child = 0 0.25.458.070 I slot print_timing: id 0 | task 1593 | prompt eval time = 131.71 ms / 410 tokens ( 0.32 ms per token, 3112.99 tokens per second) 0.25.458.076 I slot print_timing: id 0 | task 1593 | eval time = 827.99 ms / 80 tokens ( 10.48 ms per token, 95.41 tokens per second) 0.25.458.077 I slot print_timing: id 0 | task 1593 | total time = 959.70 ms / 490 tokens 0.25.458.078 I slot print_timing: id 0 | task 1593 | graphs reused = 1531 0.25.458.078 I slot print_timing: id 0 | task 1593 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.458.109 I slot release: id 0 | task 1593 | stop processing: n_tokens = 489, truncated = 0 0.25.484.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 25367553 0.25.523.015 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.26.327.502 I slot print_timing: id 0 | task 1676 | prompt eval time = 126.74 ms / 387 tokens ( 0.33 ms per token, 3053.47 tokens per second) 0.26.327.508 I slot print_timing: id 0 | task 1676 | eval time = 677.72 ms / 68 tokens ( 10.12 ms per token, 98.86 tokens per second) 0.26.327.509 I slot print_timing: id 0 | task 1676 | total time = 804.47 ms / 455 tokens 0.26.327.511 I slot print_timing: id 0 | task 1676 | graphs reused = 1597 0.26.327.511 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.327.542 I slot release: id 0 | task 1676 | stop processing: n_tokens = 454, truncated = 0 0.26.354.663 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 26236985 0.26.392.926 I slot launch_slot_: id 0 | task 1747 | processing task, is_child = 0 0.27.100.408 I slot print_timing: id 0 | task 1747 | prompt eval time = 119.51 ms / 358 tokens ( 0.33 ms per token, 2995.49 tokens per second) 0.27.100.413 I slot print_timing: id 0 | task 1747 | eval time = 587.95 ms / 59 tokens ( 10.14 ms per token, 98.65 tokens per second) 0.27.100.414 I slot print_timing: id 0 | task 1747 | total time = 707.46 ms / 417 tokens 0.27.100.415 I slot print_timing: id 0 | task 1747 | graphs reused = 1654 0.27.100.416 I slot print_timing: id 0 | task 1747 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.100.444 I slot release: id 0 | task 1747 | stop processing: n_tokens = 416, truncated = 0 0.27.122.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 27009888 0.27.158.031 I slot launch_slot_: id 0 | task 1809 | processing task, is_child = 0 0.27.863.145 I slot print_timing: id 0 | task 1809 | prompt eval time = 119.81 ms / 359 tokens ( 0.33 ms per token, 2996.54 tokens per second) 0.27.863.151 I slot print_timing: id 0 | task 1809 | eval time = 585.29 ms / 56 tokens ( 10.64 ms per token, 93.97 tokens per second) 0.27.863.152 I slot print_timing: id 0 | task 1809 | total time = 705.10 ms / 415 tokens 0.27.863.153 I slot print_timing: id 0 | task 1809 | graphs reused = 1708 0.27.863.154 I slot print_timing: id 0 | task 1809 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.863.182 I slot release: id 0 | task 1809 | stop processing: n_tokens = 414, truncated = 0 0.27.888.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 27772625 0.27.921.521 I slot launch_slot_: id 0 | task 1868 | processing task, is_child = 0 0.28.657.092 I slot print_timing: id 0 | task 1868 | prompt eval time = 127.17 ms / 387 tokens ( 0.33 ms per token, 3043.17 tokens per second) 0.28.657.098 I slot print_timing: id 0 | task 1868 | eval time = 608.38 ms / 61 tokens ( 10.14 ms per token, 98.62 tokens per second) 0.28.657.099 I slot print_timing: id 0 | task 1868 | total time = 735.55 ms / 448 tokens 0.28.657.100 I slot print_timing: id 0 | task 1868 | graphs reused = 1767 0.28.657.101 I slot print_timing: id 0 | task 1868 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.657.133 I slot release: id 0 | task 1868 | stop processing: n_tokens = 447, truncated = 0 0.28.682.042 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 28566577 0.28.717.779 I slot launch_slot_: id 0 | task 1932 | processing task, is_child = 0 0.29.478.606 I slot print_timing: id 0 | task 1932 | prompt eval time = 128.07 ms / 410 tokens ( 0.31 ms per token, 3201.45 tokens per second) 0.29.478.612 I slot print_timing: id 0 | task 1932 | eval time = 632.74 ms / 61 tokens ( 10.55 ms per token, 94.83 tokens per second) 0.29.478.613 I slot print_timing: id 0 | task 1932 | total time = 760.81 ms / 471 tokens 0.29.478.614 I slot print_timing: id 0 | task 1932 | graphs reused = 1826 0.29.478.615 I slot print_timing: id 0 | task 1932 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.478.647 I slot release: id 0 | task 1932 | stop processing: n_tokens = 470, truncated = 0 0.29.494.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 29388091 0.29.530.971 I slot launch_slot_: id 0 | task 1996 | processing task, is_child = 0 0.30.146.328 I slot print_timing: id 0 | task 1996 | prompt eval time = 119.18 ms / 351 tokens ( 0.34 ms per token, 2945.03 tokens per second) 0.30.146.334 I slot print_timing: id 0 | task 1996 | eval time = 496.15 ms / 50 tokens ( 10.13 ms per token, 98.76 tokens per second) 0.30.146.335 I slot print_timing: id 0 | task 1996 | total time = 615.34 ms / 401 tokens 0.30.146.335 I slot print_timing: id 0 | task 1996 | graphs reused = 1874 0.30.146.336 I slot print_timing: id 0 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.146.364 I slot release: id 0 | task 1996 | stop processing: n_tokens = 400, truncated = 0 0.30.169.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 30055807 0.30.203.983 I slot launch_slot_: id 0 | task 2049 | processing task, is_child = 0 0.32.599.794 I slot print_timing: id 0 | task 2049 | prompt eval time = 126.06 ms / 393 tokens ( 0.32 ms per token, 3117.51 tokens per second) 0.32.599.800 I slot print_timing: id 0 | task 2049 | eval time = 2269.73 ms / 224 tokens ( 10.18 ms per token, 98.25 tokens per second) 0.32.599.801 I slot print_timing: id 0 | task 2049 | total time = 2395.79 ms / 617 tokens 0.32.599.801 I slot print_timing: id 0 | task 2049 | graphs reused = 2095 0.32.599.802 I slot print_timing: id 0 | task 2049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.599.832 I slot release: id 0 | task 2049 | stop processing: n_tokens = 616, truncated = 0 0.32.624.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 32509276 0.32.661.089 I slot launch_slot_: id 0 | task 2276 | processing task, is_child = 0 0.33.097.391 I slot print_timing: id 0 | task 2276 | prompt eval time = 119.18 ms / 321 tokens ( 0.37 ms per token, 2693.45 tokens per second) 0.33.097.397 I slot print_timing: id 0 | task 2276 | eval time = 317.10 ms / 32 tokens ( 10.23 ms per token, 97.76 tokens per second) 0.33.097.398 I slot print_timing: id 0 | task 2276 | total time = 436.28 ms / 353 tokens 0.33.097.399 I slot print_timing: id 0 | task 2276 | graphs reused = 2125 0.33.097.400 I slot print_timing: id 0 | task 2276 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.097.427 I slot release: id 0 | task 2276 | stop processing: n_tokens = 352, truncated = 0 0.33.122.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 33006871 0.33.156.944 I slot launch_slot_: id 0 | task 2311 | processing task, is_child = 0 0.33.823.489 I slot print_timing: id 0 | task 2311 | prompt eval time = 119.22 ms / 330 tokens ( 0.36 ms per token, 2768.08 tokens per second) 0.33.823.495 I slot print_timing: id 0 | task 2311 | eval time = 547.31 ms / 55 tokens ( 10.14 ms per token, 98.66 tokens per second) 0.33.823.495 I slot print_timing: id 0 | task 2311 | total time = 666.52 ms / 385 tokens 0.33.823.496 I slot print_timing: id 0 | task 2311 | graphs reused = 2178 0.33.823.497 I slot print_timing: id 0 | task 2311 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.823.523 I slot release: id 0 | task 2311 | stop processing: n_tokens = 384, truncated = 0 0.33.840.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 384, t_last = 33732967 0.33.875.033 I slot launch_slot_: id 0 | task 2369 | processing task, is_child = 0 0.34.311.853 I slot print_timing: id 0 | task 2369 | prompt eval time = 120.52 ms / 341 tokens ( 0.35 ms per token, 2829.34 tokens per second) 0.34.311.858 I slot print_timing: id 0 | task 2369 | eval time = 316.28 ms / 32 tokens ( 10.20 ms per token, 98.02 tokens per second) 0.34.311.859 I slot print_timing: id 0 | task 2369 | total time = 436.80 ms / 373 tokens 0.34.311.860 I slot print_timing: id 0 | task 2369 | graphs reused = 2208 0.34.311.861 I slot print_timing: id 0 | task 2369 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.311.888 I slot release: id 0 | task 2369 | stop processing: n_tokens = 372, truncated = 0 0.34.338.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 34221332 0.34.372.943 I slot launch_slot_: id 0 | task 2404 | processing task, is_child = 0 0.34.967.354 I slot print_timing: id 0 | task 2404 | prompt eval time = 117.98 ms / 338 tokens ( 0.35 ms per token, 2864.77 tokens per second) 0.34.967.360 I slot print_timing: id 0 | task 2404 | eval time = 476.41 ms / 48 tokens ( 10.14 ms per token, 98.66 tokens per second) 0.34.967.361 I slot print_timing: id 0 | task 2404 | total time = 594.39 ms / 386 tokens 0.34.967.361 I slot print_timing: id 0 | task 2404 | graphs reused = 2254 0.34.967.362 I slot print_timing: id 0 | task 2404 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.967.391 I slot release: id 0 | task 2404 | stop processing: n_tokens = 385, truncated = 0 0.34.992.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 34876834 0.35.027.153 I slot launch_slot_: id 0 | task 2455 | processing task, is_child = 0 0.35.714.110 I slot print_timing: id 0 | task 2455 | prompt eval time = 129.85 ms / 395 tokens ( 0.33 ms per token, 3042.07 tokens per second) 0.35.714.116 I slot print_timing: id 0 | task 2455 | eval time = 557.09 ms / 56 tokens ( 10.13 ms per token, 98.73 tokens per second) 0.35.714.117 I slot print_timing: id 0 | task 2455 | total time = 686.94 ms / 451 tokens 0.35.714.118 I slot print_timing: id 0 | task 2455 | graphs reused = 2308 0.35.714.119 I slot print_timing: id 0 | task 2455 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.714.148 I slot release: id 0 | task 2455 | stop processing: n_tokens = 450, truncated = 0 0.35.740.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 35623591 0.35.775.760 I slot launch_slot_: id 0 | task 2514 | processing task, is_child = 0 0.36.784.134 I slot print_timing: id 0 | task 2514 | prompt eval time = 178.98 ms / 528 tokens ( 0.34 ms per token, 2950.03 tokens per second) 0.36.784.141 I slot print_timing: id 0 | task 2514 | eval time = 829.37 ms / 83 tokens ( 10.11 ms per token, 98.87 tokens per second) 0.36.784.142 I slot print_timing: id 0 | task 2514 | total time = 1008.35 ms / 611 tokens 0.36.784.143 I slot print_timing: id 0 | task 2514 | graphs reused = 2389 0.36.784.144 I slot print_timing: id 0 | task 2514 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.784.180 I slot release: id 0 | task 2514 | stop processing: n_tokens = 610, truncated = 0 0.36.800.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 36693624 0.36.845.829 I slot launch_slot_: id 0 | task 2601 | processing task, is_child = 0 0.37.430.910 I slot print_timing: id 0 | task 2601 | prompt eval time = 138.04 ms / 331 tokens ( 0.42 ms per token, 2397.84 tokens per second) 0.37.430.915 I slot print_timing: id 0 | task 2601 | eval time = 447.02 ms / 45 tokens ( 10.16 ms per token, 98.43 tokens per second) 0.37.430.916 I slot print_timing: id 0 | task 2601 | total time = 585.06 ms / 376 tokens 0.37.430.917 I slot print_timing: id 0 | task 2601 | graphs reused = 2432 0.37.430.918 I slot print_timing: id 0 | task 2601 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.430.948 I slot release: id 0 | task 2601 | stop processing: n_tokens = 387, truncated = 0 0.37.452.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 37340392 0.37.496.567 I slot launch_slot_: id 0 | task 2649 | processing task, is_child = 0 0.38.167.062 I slot print_timing: id 0 | task 2649 | prompt eval time = 143.89 ms / 362 tokens ( 0.40 ms per token, 2515.78 tokens per second) 0.38.167.068 I slot print_timing: id 0 | task 2649 | eval time = 526.58 ms / 53 tokens ( 10.13 ms per token, 98.75 tokens per second) 0.38.167.068 I slot print_timing: id 0 | task 2649 | total time = 670.48 ms / 415 tokens 0.38.167.069 I slot print_timing: id 0 | task 2649 | graphs reused = 2483 0.38.167.070 I slot print_timing: id 0 | task 2649 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.167.100 I slot release: id 0 | task 2649 | stop processing: n_tokens = 426, truncated = 0 0.38.185.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 38076543 0.38.230.119 I slot launch_slot_: id 0 | task 2705 | processing task, is_child = 0 0.39.066.851 I slot print_timing: id 0 | task 2705 | prompt eval time = 148.86 ms / 419 tokens ( 0.36 ms per token, 2814.73 tokens per second) 0.39.066.857 I slot print_timing: id 0 | task 2705 | eval time = 687.85 ms / 69 tokens ( 10.12 ms per token, 98.86 tokens per second) 0.39.066.858 I slot print_timing: id 0 | task 2705 | total time = 836.71 ms / 488 tokens 0.39.066.858 I slot print_timing: id 0 | task 2705 | graphs reused = 2550 0.39.066.859 I slot print_timing: id 0 | task 2705 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.066.892 I slot release: id 0 | task 2705 | stop processing: n_tokens = 499, truncated = 0 0.39.093.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 38976335 0.39.138.484 I slot launch_slot_: id 0 | task 2777 | processing task, is_child = 0 0.39.736.414 I slot print_timing: id 0 | task 2777 | prompt eval time = 161.02 ms / 423 tokens ( 0.38 ms per token, 2627.04 tokens per second) 0.39.736.420 I slot print_timing: id 0 | task 2777 | eval time = 436.89 ms / 44 tokens ( 10.16 ms per token, 98.42 tokens per second) 0.39.736.421 I slot print_timing: id 0 | task 2777 | total time = 597.91 ms / 467 tokens 0.39.736.422 I slot print_timing: id 0 | task 2777 | graphs reused = 2592 0.39.736.423 I slot print_timing: id 0 | task 2777 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.736.466 I slot release: id 0 | task 2777 | stop processing: n_tokens = 478, truncated = 0 0.39.762.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 39645910 0.39.807.290 I slot launch_slot_: id 0 | task 2824 | processing task, is_child = 0 0.40.377.826 I slot print_timing: id 0 | task 2824 | prompt eval time = 136.96 ms / 341 tokens ( 0.40 ms per token, 2489.80 tokens per second) 0.40.377.832 I slot print_timing: id 0 | task 2824 | eval time = 433.56 ms / 43 tokens ( 10.32 ms per token, 96.87 tokens per second) 0.40.377.833 I slot print_timing: id 0 | task 2824 | total time = 570.51 ms / 384 tokens 0.40.377.834 I slot print_timing: id 0 | task 2824 | graphs reused = 2633 0.40.377.835 I slot print_timing: id 0 | task 2824 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.377.866 I slot release: id 0 | task 2824 | stop processing: n_tokens = 395, truncated = 0 0.40.396.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 40287309 0.40.441.405 I slot launch_slot_: id 0 | task 2870 | processing task, is_child = 0 0.41.047.787 I slot print_timing: id 0 | task 2870 | prompt eval time = 140.53 ms / 356 tokens ( 0.39 ms per token, 2533.18 tokens per second) 0.41.047.792 I slot print_timing: id 0 | task 2870 | eval time = 465.83 ms / 47 tokens ( 10.13 ms per token, 98.75 tokens per second) 0.41.047.793 I slot print_timing: id 0 | task 2870 | total time = 606.36 ms / 403 tokens 0.41.047.794 I slot print_timing: id 0 | task 2870 | graphs reused = 2678 0.41.047.795 I slot print_timing: id 0 | task 2870 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.047.822 I slot release: id 0 | task 2870 | stop processing: n_tokens = 414, truncated = 0 0.41.065.437 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 40957266 0.41.065.478 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.41.105.388 I slot launch_slot_: id 0 | task 2920 | processing task, is_child = 0 0.41.707.842 I slot print_timing: id 0 | task 2920 | prompt eval time = 146.09 ms / 362 tokens ( 0.40 ms per token, 2477.91 tokens per second) 0.41.707.848 I slot print_timing: id 0 | task 2920 | eval time = 456.34 ms / 46 tokens ( 10.14 ms per token, 98.61 tokens per second) 0.41.707.850 I slot print_timing: id 0 | task 2920 | total time = 602.43 ms / 408 tokens 0.41.707.851 I slot print_timing: id 0 | task 2920 | graphs reused = 2722 0.41.707.852 I slot print_timing: id 0 | task 2920 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.707.881 I slot release: id 0 | task 2920 | stop processing: n_tokens = 419, truncated = 0 0.41.735.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 41617325 0.41.735.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.41.777.452 I slot launch_slot_: id 0 | task 2969 | processing task, is_child = 0 0.42.600.600 I slot print_timing: id 0 | task 2969 | prompt eval time = 146.03 ms / 391 tokens ( 0.37 ms per token, 2677.44 tokens per second) 0.42.600.606 I slot print_timing: id 0 | task 2969 | eval time = 677.09 ms / 68 tokens ( 10.11 ms per token, 98.95 tokens per second) 0.42.600.607 I slot print_timing: id 0 | task 2969 | total time = 823.13 ms / 459 tokens 0.42.600.607 I slot print_timing: id 0 | task 2969 | graphs reused = 2788 0.42.600.608 I slot print_timing: id 0 | task 2969 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.600.639 I slot release: id 0 | task 2969 | stop processing: n_tokens = 470, truncated = 0 0.42.623.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 42510083 0.42.623.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.42.663.513 I slot launch_slot_: id 0 | task 3040 | processing task, is_child = 0 0.43.337.707 I slot print_timing: id 0 | task 3040 | prompt eval time = 138.16 ms / 343 tokens ( 0.40 ms per token, 2482.68 tokens per second) 0.43.337.713 I slot print_timing: id 0 | task 3040 | eval time = 536.02 ms / 54 tokens ( 10.11 ms per token, 98.88 tokens per second) 0.43.337.714 I slot print_timing: id 0 | task 3040 | total time = 674.18 ms / 397 tokens 0.43.337.715 I slot print_timing: id 0 | task 3040 | graphs reused = 2840 0.43.337.716 I slot print_timing: id 0 | task 3040 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.337.743 I slot release: id 0 | task 3040 | stop processing: n_tokens = 408, truncated = 0 0.43.354.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 43247187 0.43.354.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.43.359.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.43.397.613 I slot launch_slot_: id 0 | task 3097 | processing task, is_child = 0 0.44.000.273 I slot print_timing: id 0 | task 3097 | prompt eval time = 146.90 ms / 401 tokens ( 0.37 ms per token, 2729.80 tokens per second) 0.44.000.279 I slot print_timing: id 0 | task 3097 | eval time = 455.74 ms / 46 tokens ( 10.13 ms per token, 98.74 tokens per second) 0.44.000.280 I slot print_timing: id 0 | task 3097 | total time = 602.64 ms / 447 tokens 0.44.000.282 I slot print_timing: id 0 | task 3097 | graphs reused = 2884 0.44.000.283 I slot print_timing: id 0 | task 3097 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.000.312 I slot release: id 0 | task 3097 | stop processing: n_tokens = 458, truncated = 0 0.44.023.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 43909756 0.44.023.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.44.059.505 I slot launch_slot_: id 0 | task 3146 | processing task, is_child = 0 0.44.876.042 I slot print_timing: id 0 | task 3146 | prompt eval time = 137.87 ms / 355 tokens ( 0.39 ms per token, 2574.87 tokens per second) 0.44.876.047 I slot print_timing: id 0 | task 3146 | eval time = 678.65 ms / 68 tokens ( 10.13 ms per token, 98.73 tokens per second) 0.44.876.048 I slot print_timing: id 0 | task 3146 | total time = 816.52 ms / 423 tokens 0.44.876.049 I slot print_timing: id 0 | task 3146 | graphs reused = 2950 0.44.876.050 I slot print_timing: id 0 | task 3146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.876.079 I slot release: id 0 | task 3146 | stop processing: n_tokens = 434, truncated = 0 0.44.896.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 44785522 0.44.896.445 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.44.932.772 I slot launch_slot_: id 0 | task 3217 | processing task, is_child = 0 0.45.676.893 I slot print_timing: id 0 | task 3217 | prompt eval time = 138.13 ms / 351 tokens ( 0.39 ms per token, 2541.05 tokens per second) 0.45.676.898 I slot print_timing: id 0 | task 3217 | eval time = 605.97 ms / 57 tokens ( 10.82 ms per token, 92.41 tokens per second) 0.45.676.899 I slot print_timing: id 0 | task 3217 | total time = 744.10 ms / 408 tokens 0.45.676.900 I slot print_timing: id 0 | task 3217 | graphs reused = 3005 0.45.676.901 I slot print_timing: id 0 | task 3217 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.676.930 I slot release: id 0 | task 3217 | stop processing: n_tokens = 419, truncated = 0 0.45.704.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 45586374 0.45.704.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.45.709.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.45.751.612 I slot launch_slot_: id 0 | task 3277 | processing task, is_child = 0 0.46.857.471 I slot print_timing: id 0 | task 3277 | prompt eval time = 163.31 ms / 475 tokens ( 0.34 ms per token, 2908.53 tokens per second) 0.46.857.477 I slot print_timing: id 0 | task 3277 | eval time = 942.53 ms / 93 tokens ( 10.24 ms per token, 97.61 tokens per second) 0.46.857.478 I slot print_timing: id 0 | task 3277 | total time = 1105.84 ms / 568 tokens 0.46.857.479 I slot print_timing: id 0 | task 3277 | graphs reused = 3095 0.46.857.480 I slot print_timing: id 0 | task 3277 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.857.513 I slot release: id 0 | task 3277 | stop processing: n_tokens = 579, truncated = 0 0.46.880.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 46766957 0.46.880.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.46.930.040 I slot launch_slot_: id 0 | task 3373 | processing task, is_child = 0 0.48.021.117 I slot print_timing: id 0 | task 3373 | prompt eval time = 163.14 ms / 440 tokens ( 0.37 ms per token, 2697.05 tokens per second) 0.48.021.122 I slot print_timing: id 0 | task 3373 | eval time = 927.92 ms / 92 tokens ( 10.20 ms per token, 98.07 tokens per second) 0.48.021.123 I slot print_timing: id 0 | task 3373 | total time = 1091.06 ms / 532 tokens 0.48.021.124 I slot print_timing: id 0 | task 3373 | graphs reused = 3184 0.48.021.125 I slot print_timing: id 0 | task 3373 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.021.155 I slot release: id 0 | task 3373 | stop processing: n_tokens = 543, truncated = 0 0.48.036.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 47930599 0.48.036.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.48.094.791 I slot launch_slot_: id 0 | task 3468 | processing task, is_child = 0 0.48.781.346 I slot print_timing: id 0 | task 3468 | prompt eval time = 138.44 ms / 345 tokens ( 0.40 ms per token, 2492.07 tokens per second) 0.48.781.352 I slot print_timing: id 0 | task 3468 | eval time = 548.10 ms / 55 tokens ( 10.15 ms per token, 98.52 tokens per second) 0.48.781.354 I slot print_timing: id 0 | task 3468 | total time = 686.54 ms / 400 tokens 0.48.781.354 I slot print_timing: id 0 | task 3468 | graphs reused = 3237 0.48.781.355 I slot print_timing: id 0 | task 3468 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.781.383 I slot release: id 0 | task 3468 | stop processing: n_tokens = 411, truncated = 0 0.48.785.227 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 48690826 0.48.785.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.48.795.344 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.48.850.167 I slot launch_slot_: id 0 | task 3526 | processing task, is_child = 0 0.49.543.600 I slot print_timing: id 0 | task 3526 | prompt eval time = 145.95 ms / 382 tokens ( 0.38 ms per token, 2617.39 tokens per second) 0.49.543.606 I slot print_timing: id 0 | task 3526 | eval time = 547.47 ms / 55 tokens ( 10.14 ms per token, 98.64 tokens per second) 0.49.543.607 I slot print_timing: id 0 | task 3526 | total time = 693.42 ms / 437 tokens 0.49.543.608 I slot print_timing: id 0 | task 3526 | graphs reused = 3290 0.49.543.608 I slot print_timing: id 0 | task 3526 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.543.639 I slot release: id 0 | task 3526 | stop processing: n_tokens = 448, truncated = 0 0.49.566.034 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 49453083 0.49.566.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.49.614.095 I slot launch_slot_: id 0 | task 3584 | processing task, is_child = 0 0.50.197.635 I slot print_timing: id 0 | task 3584 | prompt eval time = 137.49 ms / 337 tokens ( 0.41 ms per token, 2451.11 tokens per second) 0.50.197.641 I slot print_timing: id 0 | task 3584 | eval time = 446.04 ms / 45 tokens ( 10.14 ms per token, 98.65 tokens per second) 0.50.197.642 I slot print_timing: id 0 | task 3584 | total time = 583.52 ms / 382 tokens 0.50.197.644 I slot print_timing: id 0 | task 3584 | graphs reused = 3333 0.50.197.645 I slot print_timing: id 0 | task 3584 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.197.671 I slot release: id 0 | task 3584 | stop processing: n_tokens = 393, truncated = 0 0.50.221.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 50107114 0.50.221.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.50.270.977 I slot launch_slot_: id 0 | task 3632 | processing task, is_child = 0 0.51.143.444 I slot print_timing: id 0 | task 3632 | prompt eval time = 146.82 ms / 402 tokens ( 0.37 ms per token, 2738.07 tokens per second) 0.51.143.449 I slot print_timing: id 0 | task 3632 | eval time = 725.63 ms / 70 tokens ( 10.52 ms per token, 95.09 tokens per second) 0.51.143.450 I slot print_timing: id 0 | task 3632 | total time = 872.45 ms / 472 tokens 0.51.143.451 I slot print_timing: id 0 | task 3632 | graphs reused = 3401 0.51.143.452 I slot print_timing: id 0 | task 3632 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.143.481 I slot release: id 0 | task 3632 | stop processing: n_tokens = 483, truncated = 0 0.51.171.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 51052925 0.51.171.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.51.181.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.51.239.008 I slot launch_slot_: id 0 | task 3705 | processing task, is_child = 0 0.51.993.449 I slot print_timing: id 0 | task 3705 | prompt eval time = 185.86 ms / 549 tokens ( 0.34 ms per token, 2953.79 tokens per second) 0.51.993.455 I slot print_timing: id 0 | task 3705 | eval time = 568.56 ms / 57 tokens ( 10.15 ms per token, 98.49 tokens per second) 0.51.993.456 I slot print_timing: id 0 | task 3705 | total time = 754.42 ms / 606 tokens 0.51.993.457 I slot print_timing: id 0 | task 3705 | graphs reused = 3456 0.51.993.458 I slot print_timing: id 0 | task 3705 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.993.491 I slot release: id 0 | task 3705 | stop processing: n_tokens = 617, truncated = 0 0.52.018.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 51902935 0.52.018.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.52.083.910 I slot launch_slot_: id 0 | task 3766 | processing task, is_child = 0 0.52.864.540 I slot print_timing: id 0 | task 3766 | prompt eval time = 202.79 ms / 616 tokens ( 0.33 ms per token, 3037.55 tokens per second) 0.52.864.546 I slot print_timing: id 0 | task 3766 | eval time = 577.82 ms / 58 tokens ( 10.14 ms per token, 98.65 tokens per second) 0.52.864.547 I slot print_timing: id 0 | task 3766 | total time = 780.61 ms / 674 tokens 0.52.864.549 I slot print_timing: id 0 | task 3766 | graphs reused = 3512 0.52.864.549 I slot print_timing: id 0 | task 3766 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.864.585 I slot release: id 0 | task 3766 | stop processing: n_tokens = 685, truncated = 0 0.52.892.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 52774029 0.52.892.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.52.902.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.52.971.944 I slot launch_slot_: id 0 | task 3828 | processing task, is_child = 0 0.53.803.340 I slot print_timing: id 0 | task 3828 | prompt eval time = 213.00 ms / 665 tokens ( 0.32 ms per token, 3122.14 tokens per second) 0.53.803.346 I slot print_timing: id 0 | task 3828 | eval time = 618.38 ms / 62 tokens ( 10.14 ms per token, 98.64 tokens per second) 0.53.803.347 I slot print_timing: id 0 | task 3828 | total time = 831.38 ms / 727 tokens 0.53.803.348 I slot print_timing: id 0 | task 3828 | graphs reused = 3572 0.53.803.349 I slot print_timing: id 0 | task 3828 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.803.385 I slot release: id 0 | task 3828 | stop processing: n_tokens = 738, truncated = 0 0.53.829.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 53712828 0.53.829.754 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.53.839.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.53.911.965 I slot launch_slot_: id 0 | task 3894 | processing task, is_child = 0 0.54.669.991 I slot print_timing: id 0 | task 3894 | prompt eval time = 210.59 ms / 645 tokens ( 0.33 ms per token, 3062.85 tokens per second) 0.54.669.996 I slot print_timing: id 0 | task 3894 | eval time = 547.42 ms / 55 tokens ( 10.14 ms per token, 98.65 tokens per second) 0.54.669.997 I slot print_timing: id 0 | task 3894 | total time = 758.00 ms / 700 tokens 0.54.669.998 I slot print_timing: id 0 | task 3894 | graphs reused = 3625 0.54.669.999 I slot print_timing: id 0 | task 3894 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.670.034 I slot release: id 0 | task 3894 | stop processing: n_tokens = 711, truncated = 0 0.54.685.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 54579478 0.54.685.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.54.747.352 I slot launch_slot_: id 0 | task 3953 | processing task, is_child = 0 0.55.435.855 I slot print_timing: id 0 | task 3953 | prompt eval time = 165.06 ms / 474 tokens ( 0.35 ms per token, 2871.63 tokens per second) 0.55.435.860 I slot print_timing: id 0 | task 3953 | eval time = 523.42 ms / 52 tokens ( 10.26 ms per token, 97.44 tokens per second) 0.55.435.861 I slot print_timing: id 0 | task 3953 | total time = 688.48 ms / 526 tokens 0.55.435.862 I slot print_timing: id 0 | task 3953 | graphs reused = 3674 0.55.435.863 I slot print_timing: id 0 | task 3953 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.435.894 I slot release: id 0 | task 3953 | stop processing: n_tokens = 537, truncated = 0 0.55.455.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 55345338 0.55.456.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.55.466.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.55.521.708 I slot launch_slot_: id 0 | task 4008 | processing task, is_child = 0 0.56.134.842 I slot print_timing: id 0 | task 4008 | prompt eval time = 197.08 ms / 617 tokens ( 0.32 ms per token, 3130.77 tokens per second) 0.56.134.847 I slot print_timing: id 0 | task 4008 | eval time = 416.04 ms / 42 tokens ( 10.15 ms per token, 98.55 tokens per second) 0.56.134.848 I slot print_timing: id 0 | task 4008 | total time = 613.12 ms / 659 tokens 0.56.134.850 I slot print_timing: id 0 | task 4008 | graphs reused = 3714 0.56.134.850 I slot print_timing: id 0 | task 4008 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.134.884 I slot release: id 0 | task 4008 | stop processing: n_tokens = 670, truncated = 0 0.56.161.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 56044328 0.56.161.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.56.226.090 I slot launch_slot_: id 0 | task 4054 | processing task, is_child = 0 0.56.902.404 I slot print_timing: id 0 | task 4054 | prompt eval time = 198.00 ms / 601 tokens ( 0.33 ms per token, 3035.40 tokens per second) 0.56.902.410 I slot print_timing: id 0 | task 4054 | eval time = 478.30 ms / 48 tokens ( 10.18 ms per token, 98.26 tokens per second) 0.56.902.411 I slot print_timing: id 0 | task 4054 | total time = 676.30 ms / 649 tokens 0.56.902.413 I slot print_timing: id 0 | task 4054 | graphs reused = 3760 0.56.902.414 I slot print_timing: id 0 | task 4054 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.902.449 I slot release: id 0 | task 4054 | stop processing: n_tokens = 660, truncated = 0 0.56.926.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 56811893 0.56.926.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.56.937.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.57.010.147 I slot launch_slot_: id 0 | task 4106 | processing task, is_child = 0 0.57.663.777 I slot print_timing: id 0 | task 4106 | prompt eval time = 186.03 ms / 533 tokens ( 0.35 ms per token, 2865.05 tokens per second) 0.57.663.782 I slot print_timing: id 0 | task 4106 | eval time = 467.57 ms / 47 tokens ( 10.16 ms per token, 98.38 tokens per second) 0.57.663.783 I slot print_timing: id 0 | task 4106 | total time = 653.61 ms / 580 tokens 0.57.663.785 I slot print_timing: id 0 | task 4106 | graphs reused = 3805 0.57.663.785 I slot print_timing: id 0 | task 4106 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.663.819 I slot release: id 0 | task 4106 | stop processing: n_tokens = 591, truncated = 0 0.57.678.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 57573263 0.57.678.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.57.748.546 I slot launch_slot_: id 0 | task 4157 | processing task, is_child = 0 0.58.440.109 I slot print_timing: id 0 | task 4157 | prompt eval time = 169.66 ms / 480 tokens ( 0.35 ms per token, 2829.10 tokens per second) 0.58.440.115 I slot print_timing: id 0 | task 4157 | eval time = 521.88 ms / 52 tokens ( 10.23 ms per token, 97.72 tokens per second) 0.58.440.116 I slot print_timing: id 0 | task 4157 | total time = 691.54 ms / 532 tokens 0.58.440.116 I slot print_timing: id 0 | task 4157 | graphs reused = 3854 0.58.440.117 I slot print_timing: id 0 | task 4157 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.440.151 I slot release: id 0 | task 4157 | stop processing: n_tokens = 560, truncated = 0 0.58.459.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 58349595 0.58.459.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.58.469.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.58.541.798 I slot launch_slot_: id 0 | task 4212 | processing task, is_child = 0 0.59.148.337 I slot print_timing: id 0 | task 4212 | prompt eval time = 189.84 ms / 567 tokens ( 0.33 ms per token, 2986.74 tokens per second) 0.59.148.343 I slot print_timing: id 0 | task 4212 | eval time = 416.68 ms / 42 tokens ( 10.16 ms per token, 98.40 tokens per second) 0.59.148.344 I slot print_timing: id 0 | task 4212 | total time = 606.52 ms / 609 tokens 0.59.148.344 I slot print_timing: id 0 | task 4212 | graphs reused = 3894 0.59.148.345 I slot print_timing: id 0 | task 4212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.148.379 I slot release: id 0 | task 4212 | stop processing: n_tokens = 637, truncated = 0 0.59.176.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 59057823 0.59.176.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.59.186.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.59.265.437 I slot launch_slot_: id 0 | task 4258 | processing task, is_child = 0 1.00.071.674 I slot print_timing: id 0 | task 4258 | prompt eval time = 178.17 ms / 506 tokens ( 0.35 ms per token, 2840.00 tokens per second) 1.00.071.679 I slot print_timing: id 0 | task 4258 | eval time = 628.05 ms / 63 tokens ( 10.13 ms per token, 98.72 tokens per second) 1.00.071.681 I slot print_timing: id 0 | task 4258 | total time = 806.22 ms / 569 tokens 1.00.071.681 I slot print_timing: id 0 | task 4258 | graphs reused = 3955 1.00.071.682 I slot print_timing: id 0 | task 4258 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.071.712 I slot release: id 0 | task 4258 | stop processing: n_tokens = 597, truncated = 0 1.00.100.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 59981156 1.00.100.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.00.110.472 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.00.173.144 I slot launch_slot_: id 0 | task 4324 | processing task, is_child = 0 1.00.733.332 I slot print_timing: id 0 | task 4324 | prompt eval time = 164.11 ms / 436 tokens ( 0.38 ms per token, 2656.77 tokens per second) 1.00.733.338 I slot print_timing: id 0 | task 4324 | eval time = 396.06 ms / 40 tokens ( 10.16 ms per token, 98.47 tokens per second) 1.00.733.340 I slot print_timing: id 0 | task 4324 | total time = 560.17 ms / 476 tokens 1.00.733.340 I slot print_timing: id 0 | task 4324 | graphs reused = 3993 1.00.733.341 I slot print_timing: id 0 | task 4324 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.733.375 I slot release: id 0 | task 4324 | stop processing: n_tokens = 504, truncated = 0 1.00.757.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 60642819 1.00.757.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.00.827.048 I slot launch_slot_: id 0 | task 4367 | processing task, is_child = 0 1.01.625.453 I slot print_timing: id 0 | task 4367 | prompt eval time = 180.21 ms / 519 tokens ( 0.35 ms per token, 2879.94 tokens per second) 1.01.625.459 I slot print_timing: id 0 | task 4367 | eval time = 618.17 ms / 62 tokens ( 10.13 ms per token, 98.68 tokens per second) 1.01.625.460 I slot print_timing: id 0 | task 4367 | total time = 798.39 ms / 581 tokens 1.01.625.461 I slot print_timing: id 0 | task 4367 | graphs reused = 4053 1.01.625.461 I slot print_timing: id 0 | task 4367 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.625.496 I slot release: id 0 | task 4367 | stop processing: n_tokens = 609, truncated = 0 1.01.641.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 61534940 1.01.641.111 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.01.651.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.761 MiB) 1.01.732.118 I slot launch_slot_: id 0 | task 4433 | processing task, is_child = 0 1.02.359.856 I slot print_timing: id 0 | task 4433 | prompt eval time = 166.20 ms / 465 tokens ( 0.36 ms per token, 2797.90 tokens per second) 1.02.359.862 I slot print_timing: id 0 | task 4433 | eval time = 461.52 ms / 46 tokens ( 10.26 ms per token, 97.50 tokens per second) 1.02.359.863 I slot print_timing: id 0 | task 4433 | total time = 627.72 ms / 511 tokens 1.02.359.863 I slot print_timing: id 0 | task 4433 | graphs reused = 4096 1.02.359.864 I slot print_timing: id 0 | task 4433 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.359.896 I slot release: id 0 | task 4433 | stop processing: n_tokens = 542, truncated = 0 1.02.384.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 62269339 1.02.384.967 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.02.394.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.02.472.563 I slot launch_slot_: id 0 | task 4482 | processing task, is_child = 0 1.03.045.533 I slot print_timing: id 0 | task 4482 | prompt eval time = 166.31 ms / 431 tokens ( 0.39 ms per token, 2591.50 tokens per second) 1.03.045.539 I slot print_timing: id 0 | task 4482 | eval time = 406.64 ms / 41 tokens ( 10.17 ms per token, 98.37 tokens per second) 1.03.045.540 I slot print_timing: id 0 | task 4482 | total time = 572.95 ms / 472 tokens 1.03.045.541 I slot print_timing: id 0 | task 4482 | graphs reused = 4135 1.03.045.542 I slot print_timing: id 0 | task 4482 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.045.575 I slot release: id 0 | task 4482 | stop processing: n_tokens = 503, truncated = 0 1.03.071.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 62955019 1.03.071.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.03.082.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.03.162.101 I slot launch_slot_: id 0 | task 4526 | processing task, is_child = 0 1.03.769.455 I slot print_timing: id 0 | task 4526 | prompt eval time = 166.43 ms / 457 tokens ( 0.36 ms per token, 2745.95 tokens per second) 1.03.769.460 I slot print_timing: id 0 | task 4526 | eval time = 440.91 ms / 44 tokens ( 10.25 ms per token, 97.53 tokens per second) 1.03.769.462 I slot print_timing: id 0 | task 4526 | total time = 607.33 ms / 501 tokens 1.03.769.462 I slot print_timing: id 0 | task 4526 | graphs reused = 4176 1.03.769.463 I slot print_timing: id 0 | task 4526 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.769.495 I slot release: id 0 | task 4526 | stop processing: n_tokens = 532, truncated = 0 1.03.786.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 63678939 1.03.786.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.03.864.857 I slot launch_slot_: id 0 | task 4573 | processing task, is_child = 0 1.04.963.553 I slot print_timing: id 0 | task 4573 | prompt eval time = 165.96 ms / 439 tokens ( 0.38 ms per token, 2645.17 tokens per second) 1.04.963.559 I slot print_timing: id 0 | task 4573 | eval time = 932.71 ms / 93 tokens ( 10.14 ms per token, 98.64 tokens per second) 1.04.963.560 I slot print_timing: id 0 | task 4573 | total time = 1098.68 ms / 532 tokens 1.04.963.561 I slot print_timing: id 0 | task 4573 | graphs reused = 4266 1.04.963.562 I slot print_timing: id 0 | task 4573 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.963.597 I slot release: id 0 | task 4573 | stop processing: n_tokens = 563, truncated = 0 1.04.985.605 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 64873040 1.04.985.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.04.998.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.05.092.460 I slot launch_slot_: id 0 | task 4669 | processing task, is_child = 0 1.05.846.672 I slot print_timing: id 0 | task 4669 | prompt eval time = 197.05 ms / 606 tokens ( 0.33 ms per token, 3075.30 tokens per second) 1.05.846.677 I slot print_timing: id 0 | task 4669 | eval time = 557.14 ms / 56 tokens ( 10.13 ms per token, 98.72 tokens per second) 1.05.846.678 I slot print_timing: id 0 | task 4669 | total time = 754.19 ms / 662 tokens 1.05.846.680 I slot print_timing: id 0 | task 4669 | graphs reused = 4320 1.05.846.681 I slot print_timing: id 0 | task 4669 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.846.716 I slot release: id 0 | task 4669 | stop processing: n_tokens = 693, truncated = 0 1.05.865.529 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 65756160 1.05.865.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.05.878.804 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.05.967.682 I slot launch_slot_: id 0 | task 4729 | processing task, is_child = 0 1.06.551.165 I slot print_timing: id 0 | task 4729 | prompt eval time = 172.64 ms / 477 tokens ( 0.36 ms per token, 2763.01 tokens per second) 1.06.551.171 I slot print_timing: id 0 | task 4729 | eval time = 410.82 ms / 41 tokens ( 10.27 ms per token, 97.37 tokens per second) 1.06.551.173 I slot print_timing: id 0 | task 4729 | total time = 583.46 ms / 518 tokens 1.06.551.173 I slot print_timing: id 0 | task 4729 | graphs reused = 4358 1.06.551.174 I slot print_timing: id 0 | task 4729 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.551.206 I slot release: id 0 | task 4729 | stop processing: n_tokens = 549, truncated = 0 1.06.574.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 66460650 1.06.574.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.06.627.100 I slot launch_slot_: id 0 | task 4773 | processing task, is_child = 0 1.07.473.317 I slot print_timing: id 0 | task 4773 | prompt eval time = 246.52 ms / 845 tokens ( 0.29 ms per token, 3427.73 tokens per second) 1.07.473.322 I slot print_timing: id 0 | task 4773 | eval time = 599.68 ms / 60 tokens ( 10.16 ms per token, 98.39 tokens per second) 1.07.473.324 I slot print_timing: id 0 | task 4773 | total time = 846.20 ms / 905 tokens 1.07.473.325 I slot print_timing: id 0 | task 4773 | graphs reused = 4416 1.07.473.326 I slot print_timing: id 0 | task 4773 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.473.369 I slot release: id 0 | task 4773 | stop processing: n_tokens = 936, truncated = 0 1.07.493.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 67382813 1.07.494.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.07.504.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.07.566.641 I slot launch_slot_: id 0 | task 4837 | processing task, is_child = 0 1.08.168.155 I slot print_timing: id 0 | task 4837 | prompt eval time = 170.05 ms / 459 tokens ( 0.37 ms per token, 2699.17 tokens per second) 1.08.168.161 I slot print_timing: id 0 | task 4837 | eval time = 431.44 ms / 43 tokens ( 10.27 ms per token, 97.35 tokens per second) 1.08.168.162 I slot print_timing: id 0 | task 4837 | total time = 601.50 ms / 502 tokens 1.08.168.163 I slot print_timing: id 0 | task 4837 | graphs reused = 4456 1.08.168.164 I slot print_timing: id 0 | task 4837 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.168.197 I slot release: id 0 | task 4837 | stop processing: n_tokens = 533, truncated = 0 1.08.195.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 68077640 1.08.195.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.08.248.108 I slot launch_slot_: id 0 | task 4883 | processing task, is_child = 0 1.08.926.329 I slot print_timing: id 0 | task 4883 | prompt eval time = 210.92 ms / 670 tokens ( 0.31 ms per token, 3176.59 tokens per second) 1.08.926.336 I slot print_timing: id 0 | task 4883 | eval time = 467.28 ms / 47 tokens ( 10.16 ms per token, 98.44 tokens per second) 1.08.926.337 I slot print_timing: id 0 | task 4883 | total time = 678.20 ms / 717 tokens 1.08.926.338 I slot print_timing: id 0 | task 4883 | graphs reused = 4501 1.08.926.339 I slot print_timing: id 0 | task 4883 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.926.380 I slot release: id 0 | task 4883 | stop processing: n_tokens = 748, truncated = 0 1.08.943.638 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 68835823 1.08.943.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.08.949.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.09.009.217 I slot launch_slot_: id 0 | task 4934 | processing task, is_child = 0 1.09.912.062 I slot print_timing: id 0 | task 4934 | prompt eval time = 237.47 ms / 775 tokens ( 0.31 ms per token, 3263.57 tokens per second) 1.09.912.068 I slot print_timing: id 0 | task 4934 | eval time = 665.36 ms / 63 tokens ( 10.73 ms per token, 93.18 tokens per second) 1.09.912.070 I slot print_timing: id 0 | task 4934 | total time = 902.83 ms / 838 tokens 1.09.912.070 I slot print_timing: id 0 | task 4934 | graphs reused = 4562 1.09.912.071 I slot print_timing: id 0 | task 4934 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.912.112 I slot release: id 0 | task 4934 | stop processing: n_tokens = 869, truncated = 0 1.09.928.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 69821556 1.09.928.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.09.936.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.10.006.013 I slot launch_slot_: id 0 | task 5001 | processing task, is_child = 0 1.10.925.224 I slot print_timing: id 0 | task 5001 | prompt eval time = 194.92 ms / 573 tokens ( 0.34 ms per token, 2939.64 tokens per second) 1.10.925.230 I slot print_timing: id 0 | task 5001 | eval time = 724.27 ms / 71 tokens ( 10.35 ms per token, 96.65 tokens per second) 1.10.925.231 I slot print_timing: id 0 | task 5001 | total time = 919.19 ms / 644 tokens 1.10.925.232 I slot print_timing: id 0 | task 5001 | graphs reused = 4631 1.10.925.233 I slot print_timing: id 0 | task 5001 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.925.274 I slot release: id 0 | task 5001 | stop processing: n_tokens = 675, truncated = 0 1.10.939.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 70834718 1.10.939.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 1.10.953.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.11.082.221 I slot launch_slot_: id 0 | task 5076 | processing task, is_child = 0 1.11.905.300 I slot print_timing: id 0 | task 5076 | prompt eval time = 176.41 ms / 461 tokens ( 0.38 ms per token, 2613.17 tokens per second) 1.11.905.306 I slot print_timing: id 0 | task 5076 | eval time = 646.65 ms / 64 tokens ( 10.26 ms per token, 97.43 tokens per second) 1.11.905.307 I slot print_timing: id 0 | task 5076 | total time = 823.06 ms / 525 tokens 1.11.905.308 I slot print_timing: id 0 | task 5076 | graphs reused = 4692 1.11.905.309 I slot print_timing: id 0 | task 5076 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.905.341 I slot release: id 0 | task 5076 | stop processing: n_tokens = 556, truncated = 0 1.11.934.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 71814784 1.11.934.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.12.005.001 I slot launch_slot_: id 0 | task 5143 | processing task, is_child = 0 1.12.659.807 I slot print_timing: id 0 | task 5143 | prompt eval time = 196.65 ms / 609 tokens ( 0.32 ms per token, 3096.87 tokens per second) 1.12.659.812 I slot print_timing: id 0 | task 5143 | eval time = 458.13 ms / 43 tokens ( 10.91 ms per token, 91.68 tokens per second) 1.12.659.813 I slot print_timing: id 0 | task 5143 | total time = 654.78 ms / 652 tokens 1.12.659.814 I slot print_timing: id 0 | task 5143 | graphs reused = 4733 1.12.659.815 I slot print_timing: id 0 | task 5143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.659.858 I slot release: id 0 | task 5143 | stop processing: n_tokens = 683, truncated = 0 1.12.680.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 72569302 1.12.680.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.12.693.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.12.790.994 I slot launch_slot_: id 0 | task 5190 | processing task, is_child = 0 1.13.641.060 I slot print_timing: id 0 | task 5190 | prompt eval time = 239.09 ms / 791 tokens ( 0.30 ms per token, 3308.38 tokens per second) 1.13.641.066 I slot print_timing: id 0 | task 5190 | eval time = 610.96 ms / 61 tokens ( 10.18 ms per token, 98.21 tokens per second) 1.13.641.067 I slot print_timing: id 0 | task 5190 | total time = 850.05 ms / 852 tokens 1.13.641.068 I slot print_timing: id 0 | task 5190 | graphs reused = 4792 1.13.641.069 I slot print_timing: id 0 | task 5190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.641.108 I slot release: id 0 | task 5190 | stop processing: n_tokens = 883, truncated = 0 1.13.663.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 73550552 1.13.663.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.13.786.991 I slot launch_slot_: id 0 | task 5255 | processing task, is_child = 0 1.14.531.796 I slot print_timing: id 0 | task 5255 | prompt eval time = 186.01 ms / 533 tokens ( 0.35 ms per token, 2865.38 tokens per second) 1.14.531.802 I slot print_timing: id 0 | task 5255 | eval time = 558.77 ms / 56 tokens ( 10.16 ms per token, 98.43 tokens per second) 1.14.531.803 I slot print_timing: id 0 | task 5255 | total time = 744.78 ms / 589 tokens 1.14.531.804 I slot print_timing: id 0 | task 5255 | graphs reused = 4846 1.14.531.805 I slot print_timing: id 0 | task 5255 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.531.839 I slot release: id 0 | task 5255 | stop processing: n_tokens = 677, truncated = 0 1.14.549.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 74441283 1.14.549.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.14.633.587 I slot launch_slot_: id 0 | task 5315 | processing task, is_child = 0 1.15.316.890 I slot print_timing: id 0 | task 5315 | prompt eval time = 193.71 ms / 566 tokens ( 0.34 ms per token, 2921.97 tokens per second) 1.15.316.896 I slot print_timing: id 0 | task 5315 | eval time = 489.57 ms / 46 tokens ( 10.88 ms per token, 91.92 tokens per second) 1.15.316.897 I slot print_timing: id 0 | task 5315 | total time = 683.28 ms / 612 tokens 1.15.316.898 I slot print_timing: id 0 | task 5315 | graphs reused = 4890 1.15.316.899 I slot print_timing: id 0 | task 5315 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.316.936 I slot release: id 0 | task 5315 | stop processing: n_tokens = 643, truncated = 0 1.15.343.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 75226380 1.15.343.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.15.428.273 I slot launch_slot_: id 0 | task 5365 | processing task, is_child = 0 1.16.024.789 I slot print_timing: id 0 | task 5365 | prompt eval time = 164.31 ms / 443 tokens ( 0.37 ms per token, 2696.14 tokens per second) 1.16.024.795 I slot print_timing: id 0 | task 5365 | eval time = 432.19 ms / 43 tokens ( 10.29 ms per token, 97.18 tokens per second) 1.16.024.796 I slot print_timing: id 0 | task 5365 | total time = 596.50 ms / 486 tokens 1.16.024.797 I slot print_timing: id 0 | task 5365 | graphs reused = 4930 1.16.024.798 I slot print_timing: id 0 | task 5365 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.024.831 I slot release: id 0 | task 5365 | stop processing: n_tokens = 517, truncated = 0 1.16.043.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 75934275 1.16.043.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.16.114.689 I slot launch_slot_: id 0 | task 5411 | processing task, is_child = 0 1.16.930.056 I slot print_timing: id 0 | task 5411 | prompt eval time = 166.72 ms / 487 tokens ( 0.34 ms per token, 2921.10 tokens per second) 1.16.930.062 I slot print_timing: id 0 | task 5411 | eval time = 648.63 ms / 65 tokens ( 10.13 ms per token, 98.67 tokens per second) 1.16.930.063 I slot print_timing: id 0 | task 5411 | total time = 815.35 ms / 552 tokens 1.16.930.064 I slot print_timing: id 0 | task 5411 | graphs reused = 4993 1.16.930.065 I slot print_timing: id 0 | task 5411 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.930.097 I slot release: id 0 | task 5411 | stop processing: n_tokens = 583, truncated = 0 1.16.950.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 76839541 1.16.950.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.17.020.923 I slot launch_slot_: id 0 | task 5479 | processing task, is_child = 0 1.17.661.585 I slot print_timing: id 0 | task 5479 | prompt eval time = 173.20 ms / 507 tokens ( 0.34 ms per token, 2927.20 tokens per second) 1.17.661.591 I slot print_timing: id 0 | task 5479 | eval time = 467.44 ms / 47 tokens ( 10.16 ms per token, 98.41 tokens per second) 1.17.661.592 I slot print_timing: id 0 | task 5479 | total time = 640.64 ms / 554 tokens 1.17.661.593 I slot print_timing: id 0 | task 5479 | graphs reused = 5038 1.17.661.594 I slot print_timing: id 0 | task 5479 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.661.629 I slot release: id 0 | task 5479 | stop processing: n_tokens = 585, truncated = 0 1.17.689.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 77571073 1.17.689.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.17.705.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.17.797.726 I slot launch_slot_: id 0 | task 5529 | processing task, is_child = 0 1.18.655.653 I slot print_timing: id 0 | task 5529 | prompt eval time = 198.43 ms / 633 tokens ( 0.31 ms per token, 3190.06 tokens per second) 1.18.655.659 I slot print_timing: id 0 | task 5529 | eval time = 659.48 ms / 66 tokens ( 10.15 ms per token, 98.56 tokens per second) 1.18.655.660 I slot print_timing: id 0 | task 5529 | total time = 857.91 ms / 699 tokens 1.18.655.661 I slot print_timing: id 0 | task 5529 | graphs reused = 5102 1.18.655.662 I slot print_timing: id 0 | task 5529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.655.701 I slot release: id 0 | task 5529 | stop processing: n_tokens = 730, truncated = 0 1.18.684.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 78565145 1.18.684.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.18.764.305 I slot launch_slot_: id 0 | task 5599 | processing task, is_child = 0 1.19.424.145 I slot print_timing: id 0 | task 5599 | prompt eval time = 191.75 ms / 571 tokens ( 0.34 ms per token, 2977.76 tokens per second) 1.19.424.151 I slot print_timing: id 0 | task 5599 | eval time = 468.06 ms / 47 tokens ( 10.18 ms per token, 98.28 tokens per second) 1.19.424.152 I slot print_timing: id 0 | task 5599 | total time = 659.82 ms / 618 tokens 1.19.424.152 I slot print_timing: id 0 | task 5599 | graphs reused = 5147 1.19.424.153 I slot print_timing: id 0 | task 5599 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.424.188 I slot release: id 0 | task 5599 | stop processing: n_tokens = 649, truncated = 0 1.19.444.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 79333631 1.19.444.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.19.533.042 I slot launch_slot_: id 0 | task 5650 | processing task, is_child = 0 1.20.206.705 I slot print_timing: id 0 | task 5650 | prompt eval time = 235.27 ms / 798 tokens ( 0.29 ms per token, 3391.80 tokens per second) 1.20.206.711 I slot print_timing: id 0 | task 5650 | eval time = 438.37 ms / 44 tokens ( 10.19 ms per token, 98.09 tokens per second) 1.20.206.712 I slot print_timing: id 0 | task 5650 | total time = 673.64 ms / 842 tokens 1.20.206.713 I slot print_timing: id 0 | task 5650 | graphs reused = 5189 1.20.206.714 I slot print_timing: id 0 | task 5650 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.206.756 I slot release: id 0 | task 5650 | stop processing: n_tokens = 873, truncated = 0 1.20.235.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 80116200 1.20.235.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.20.254.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.20.343.945 I slot launch_slot_: id 0 | task 5698 | processing task, is_child = 0 1.20.963.584 I slot print_timing: id 0 | task 5698 | prompt eval time = 192.24 ms / 572 tokens ( 0.34 ms per token, 2975.43 tokens per second) 1.20.963.590 I slot print_timing: id 0 | task 5698 | eval time = 427.38 ms / 43 tokens ( 10.18 ms per token, 98.27 tokens per second) 1.20.963.591 I slot print_timing: id 0 | task 5698 | total time = 619.62 ms / 615 tokens 1.20.963.592 I slot print_timing: id 0 | task 5698 | graphs reused = 5230 1.20.963.593 I slot print_timing: id 0 | task 5698 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.963.629 I slot release: id 0 | task 5698 | stop processing: n_tokens = 646, truncated = 0 1.20.983.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 80873073 1.20.983.233 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.21.057.738 I slot launch_slot_: id 0 | task 5745 | processing task, is_child = 0 1.21.746.098 I slot print_timing: id 0 | task 5745 | prompt eval time = 200.75 ms / 613 tokens ( 0.33 ms per token, 3053.61 tokens per second) 1.21.746.104 I slot print_timing: id 0 | task 5745 | eval time = 487.60 ms / 49 tokens ( 10.16 ms per token, 98.44 tokens per second) 1.21.746.105 I slot print_timing: id 0 | task 5745 | total time = 688.34 ms / 662 tokens 1.21.746.106 I slot print_timing: id 0 | task 5745 | graphs reused = 5277 1.21.746.107 I slot print_timing: id 0 | task 5745 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.746.141 I slot release: id 0 | task 5745 | stop processing: n_tokens = 693, truncated = 0 1.21.760.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 81655585 1.21.761.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.21.849.070 I slot launch_slot_: id 0 | task 5798 | processing task, is_child = 0 1.22.799.997 I slot print_timing: id 0 | task 5798 | prompt eval time = 191.24 ms / 580 tokens ( 0.33 ms per token, 3032.84 tokens per second) 1.22.800.003 I slot print_timing: id 0 | task 5798 | eval time = 759.67 ms / 76 tokens ( 10.13 ms per token, 98.73 tokens per second) 1.22.800.004 I slot print_timing: id 0 | task 5798 | total time = 950.91 ms / 656 tokens 1.22.800.005 I slot print_timing: id 0 | task 5798 | graphs reused = 5351 1.22.800.006 I slot print_timing: id 0 | task 5798 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.800.041 I slot release: id 0 | task 5798 | stop processing: n_tokens = 687, truncated = 0 1.22.820.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 82709485 1.22.820.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.22.919.123 I slot launch_slot_: id 0 | task 5878 | processing task, is_child = 0 1.23.644.062 I slot print_timing: id 0 | task 5878 | prompt eval time = 221.04 ms / 716 tokens ( 0.31 ms per token, 3239.23 tokens per second) 1.23.644.067 I slot print_timing: id 0 | task 5878 | eval time = 503.88 ms / 50 tokens ( 10.28 ms per token, 97.25 tokens per second) 1.23.644.068 I slot print_timing: id 0 | task 5878 | total time = 724.92 ms / 766 tokens 1.23.644.069 I slot print_timing: id 0 | task 5878 | graphs reused = 5398 1.23.644.070 I slot print_timing: id 0 | task 5878 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.644.109 I slot release: id 0 | task 5878 | stop processing: n_tokens = 797, truncated = 0 1.23.666.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 83553553 1.23.666.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.23.685.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.23.789.433 I slot launch_slot_: id 0 | task 5932 | processing task, is_child = 0 1.25.048.793 I slot print_timing: id 0 | task 5932 | prompt eval time = 235.30 ms / 799 tokens ( 0.29 ms per token, 3395.62 tokens per second) 1.25.048.798 I slot print_timing: id 0 | task 5932 | eval time = 1024.04 ms / 102 tokens ( 10.14 ms per token, 98.63 tokens per second) 1.25.048.799 I slot print_timing: id 0 | task 5932 | total time = 1259.34 ms / 901 tokens 1.25.048.800 I slot print_timing: id 0 | task 5932 | graphs reused = 5498 1.25.048.801 I slot print_timing: id 0 | task 5932 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.048.842 I slot release: id 0 | task 5932 | stop processing: n_tokens = 932, truncated = 0 1.25.074.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 84958286 1.25.075.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.110 MiB) 1.25.153.538 I slot launch_slot_: id 0 | task 6038 | processing task, is_child = 0 1.26.435.656 I slot print_timing: id 0 | task 6038 | prompt eval time = 145.14 ms / 361 tokens ( 0.40 ms per token, 2487.27 tokens per second) 1.26.435.662 I slot print_timing: id 0 | task 6038 | eval time = 1136.96 ms / 112 tokens ( 10.24 ms per token, 97.63 tokens per second) 1.26.435.663 I slot print_timing: id 0 | task 6038 | total time = 1282.10 ms / 473 tokens 1.26.435.663 I slot print_timing: id 0 | task 6038 | graphs reused = 5608 1.26.435.664 I slot print_timing: id 0 | task 6038 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.435.698 I slot release: id 0 | task 6038 | stop processing: n_tokens = 504, truncated = 0 1.26.458.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 86345142 1.26.459.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.26.543.185 I slot launch_slot_: id 0 | task 6153 | processing task, is_child = 0 1.27.793.034 I slot print_timing: id 0 | task 6153 | prompt eval time = 150.67 ms / 381 tokens ( 0.40 ms per token, 2528.65 tokens per second) 1.27.793.039 I slot print_timing: id 0 | task 6153 | eval time = 1099.16 ms / 108 tokens ( 10.27 ms per token, 97.35 tokens per second) 1.27.793.040 I slot print_timing: id 0 | task 6153 | total time = 1249.83 ms / 489 tokens 1.27.793.041 I slot print_timing: id 0 | task 6153 | graphs reused = 5713 1.27.793.042 I slot print_timing: id 0 | task 6153 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.793.073 I slot release: id 0 | task 6153 | stop processing: n_tokens = 520, truncated = 0 1.27.814.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 87702517 1.27.814.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.27.877.058 I slot launch_slot_: id 0 | task 6264 | processing task, is_child = 0 1.29.271.802 I slot print_timing: id 0 | task 6264 | prompt eval time = 143.35 ms / 365 tokens ( 0.39 ms per token, 2546.29 tokens per second) 1.29.271.808 I slot print_timing: id 0 | task 6264 | eval time = 1251.38 ms / 124 tokens ( 10.17 ms per token, 98.29 tokens per second) 1.29.271.809 I slot print_timing: id 0 | task 6264 | total time = 1394.72 ms / 489 tokens 1.29.271.809 I slot print_timing: id 0 | task 6264 | graphs reused = 5834 1.29.271.810 I slot print_timing: id 0 | task 6264 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.271.839 I slot release: id 0 | task 6264 | stop processing: n_tokens = 520, truncated = 0 1.29.296.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 89181283 1.29.296.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.29.354.289 I slot launch_slot_: id 0 | task 6391 | processing task, is_child = 0 1.30.563.012 I slot print_timing: id 0 | task 6391 | prompt eval time = 138.87 ms / 333 tokens ( 0.42 ms per token, 2398.00 tokens per second) 1.30.563.017 I slot print_timing: id 0 | task 6391 | eval time = 1069.84 ms / 107 tokens ( 10.09 ms per token, 99.08 tokens per second) 1.30.563.019 I slot print_timing: id 0 | task 6391 | total time = 1208.70 ms / 440 tokens 1.30.563.020 I slot print_timing: id 0 | task 6391 | graphs reused = 5939 1.30.563.021 I slot print_timing: id 0 | task 6391 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.563.049 I slot release: id 0 | task 6391 | stop processing: n_tokens = 471, truncated = 0 1.30.588.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 90472492 1.30.634.669 I slot launch_slot_: id 0 | task 6501 | processing task, is_child = 0 1.32.171.433 I slot print_timing: id 0 | task 6501 | prompt eval time = 147.17 ms / 403 tokens ( 0.37 ms per token, 2738.37 tokens per second) 1.32.171.439 I slot print_timing: id 0 | task 6501 | eval time = 1389.58 ms / 138 tokens ( 10.14 ms per token, 98.59 tokens per second) 1.32.171.439 I slot print_timing: id 0 | task 6501 | total time = 1536.74 ms / 541 tokens 1.32.171.442 I slot print_timing: id 0 | task 6501 | graphs reused = 6074 1.32.171.443 I slot print_timing: id 0 | task 6501 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.171.475 I slot release: id 0 | task 6501 | stop processing: n_tokens = 572, truncated = 0 1.32.175.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 92080918 1.32.175.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.32.233.482 I slot launch_slot_: id 0 | task 6642 | processing task, is_child = 0 1.34.241.037 I slot print_timing: id 0 | task 6642 | prompt eval time = 146.87 ms / 411 tokens ( 0.36 ms per token, 2798.47 tokens per second) 1.34.241.042 I slot print_timing: id 0 | task 6642 | eval time = 1860.67 ms / 185 tokens ( 10.11 ms per token, 98.89 tokens per second) 1.34.241.043 I slot print_timing: id 0 | task 6642 | total time = 2007.54 ms / 596 tokens 1.34.241.044 I slot print_timing: id 0 | task 6642 | graphs reused = 6256 1.34.241.045 I slot print_timing: id 0 | task 6642 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.241.075 I slot release: id 0 | task 6642 | stop processing: n_tokens = 627, truncated = 0 1.34.256.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 94150518 1.34.256.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.34.313.359 I slot launch_slot_: id 0 | task 6830 | processing task, is_child = 0 1.36.749.758 I slot print_timing: id 0 | task 6830 | prompt eval time = 173.16 ms / 490 tokens ( 0.35 ms per token, 2829.77 tokens per second) 1.36.749.764 I slot print_timing: id 0 | task 6830 | eval time = 2263.22 ms / 225 tokens ( 10.10 ms per token, 98.97 tokens per second) 1.36.749.765 I slot print_timing: id 0 | task 6830 | total time = 2436.38 ms / 715 tokens 1.36.749.765 I slot print_timing: id 0 | task 6830 | graphs reused = 6479 1.36.749.766 I slot print_timing: id 0 | task 6830 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.749.799 I slot release: id 0 | task 6830 | stop processing: n_tokens = 746, truncated = 0 1.36.772.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 96659243 1.36.772.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.36.839.549 I slot launch_slot_: id 0 | task 7058 | processing task, is_child = 0 1.38.706.112 I slot print_timing: id 0 | task 7058 | prompt eval time = 138.96 ms / 344 tokens ( 0.40 ms per token, 2475.59 tokens per second) 1.38.706.117 I slot print_timing: id 0 | task 7058 | eval time = 1727.59 ms / 171 tokens ( 10.16 ms per token, 98.40 tokens per second) 1.38.706.118 I slot print_timing: id 0 | task 7058 | total time = 1866.54 ms / 515 tokens 1.38.706.120 I slot print_timing: id 0 | task 7058 | graphs reused = 6647 1.38.706.121 I slot print_timing: id 0 | task 7058 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.706.151 I slot release: id 0 | task 7058 | stop processing: n_tokens = 546, truncated = 0 1.38.725.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 98615595 1.38.725.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.38.795.440 I slot launch_slot_: id 0 | task 7232 | processing task, is_child = 0 1.40.658.022 I slot print_timing: id 0 | task 7232 | prompt eval time = 139.81 ms / 347 tokens ( 0.40 ms per token, 2481.94 tokens per second) 1.40.658.027 I slot print_timing: id 0 | task 7232 | eval time = 1722.75 ms / 171 tokens ( 10.13 ms per token, 98.68 tokens per second) 1.40.658.028 I slot print_timing: id 0 | task 7232 | total time = 1862.56 ms / 518 tokens 1.40.658.029 I slot print_timing: id 0 | task 7232 | graphs reused = 6815 1.40.658.030 I slot print_timing: id 0 | task 7232 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.658.058 I slot release: id 0 | task 7232 | stop processing: n_tokens = 549, truncated = 0 1.40.676.542 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 100567502 1.40.676.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 1.40.758.170 I slot launch_slot_: id 0 | task 7406 | processing task, is_child = 0 1.42.182.586 I slot print_timing: id 0 | task 7406 | prompt eval time = 149.74 ms / 401 tokens ( 0.37 ms per token, 2678.03 tokens per second) 1.42.182.592 I slot print_timing: id 0 | task 7406 | eval time = 1274.66 ms / 126 tokens ( 10.20 ms per token, 98.07 tokens per second) 1.42.182.593 I slot print_timing: id 0 | task 7406 | total time = 1424.40 ms / 527 tokens 1.42.182.594 I slot print_timing: id 0 | task 7406 | graphs reused = 6938 1.42.182.595 I slot print_timing: id 0 | task 7406 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.182.627 I slot release: id 0 | task 7406 | stop processing: n_tokens = 558, truncated = 0 1.42.204.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 102092070 1.42.204.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.42.282.088 I slot launch_slot_: id 0 | task 7535 | processing task, is_child = 0 1.43.627.594 I slot print_timing: id 0 | task 7535 | prompt eval time = 159.54 ms / 456 tokens ( 0.35 ms per token, 2858.27 tokens per second) 1.43.627.600 I slot print_timing: id 0 | task 7535 | eval time = 1185.95 ms / 115 tokens ( 10.40 ms per token, 96.13 tokens per second) 1.43.627.601 I slot print_timing: id 0 | task 7535 | total time = 1345.49 ms / 571 tokens 1.43.627.603 I slot print_timing: id 0 | task 7535 | graphs reused = 7050 1.43.627.604 I slot print_timing: id 0 | task 7535 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.627.634 I slot release: id 0 | task 7535 | stop processing: n_tokens = 602, truncated = 0 1.43.650.606 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 1.43.650.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.43.726.386 I slot launch_slot_: id 0 | task 7653 | processing task, is_child = 0 1.45.009.402 I slot print_timing: id 0 | task 7653 | prompt eval time = 151.25 ms / 406 tokens ( 0.37 ms per token, 2684.32 tokens per second) 1.45.009.407 I slot print_timing: id 0 | task 7653 | eval time = 1131.75 ms / 112 tokens ( 10.20 ms per token, 98.08 tokens per second) 1.45.009.408 I slot print_timing: id 0 | task 7653 | total time = 1283.00 ms / 518 tokens 1.45.009.409 I slot print_timing: id 0 | task 7653 | graphs reused = 7159 1.45.009.410 I slot print_timing: id 0 | task 7653 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.009.441 I slot release: id 0 | task 7653 | stop processing: n_tokens = 549, truncated = 0 1.45.026.630 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 104918884 1.45.075.195 I slot launch_slot_: id 0 | task 7768 | processing task, is_child = 0 1.47.036.580 I slot print_timing: id 0 | task 7768 | prompt eval time = 149.42 ms / 406 tokens ( 0.37 ms per token, 2717.14 tokens per second) 1.47.036.585 I slot print_timing: id 0 | task 7768 | eval time = 1811.94 ms / 179 tokens ( 10.18 ms per token, 98.24 tokens per second) 1.47.036.586 I slot print_timing: id 0 | task 7768 | total time = 1961.36 ms / 585 tokens 1.47.036.587 I slot print_timing: id 0 | task 7768 | graphs reused = 7335 1.47.036.588 I slot print_timing: id 0 | task 7768 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.036.619 I slot release: id 0 | task 7768 | stop processing: n_tokens = 616, truncated = 0 1.47.052.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 106946063 1.47.052.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.47.142.112 I slot launch_slot_: id 0 | task 7950 | processing task, is_child = 0 1.48.749.314 I slot print_timing: id 0 | task 7950 | prompt eval time = 155.23 ms / 444 tokens ( 0.35 ms per token, 2860.24 tokens per second) 1.48.749.319 I slot print_timing: id 0 | task 7950 | eval time = 1451.95 ms / 144 tokens ( 10.15 ms per token, 98.49 tokens per second) 1.48.749.320 I slot print_timing: id 0 | task 7950 | total time = 1607.18 ms / 588 tokens 1.48.749.321 I slot print_timing: id 0 | task 7950 | graphs reused = 7476 1.48.749.322 I slot print_timing: id 0 | task 7950 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.749.355 I slot release: id 0 | task 7950 | stop processing: n_tokens = 619, truncated = 0 1.48.774.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 108658798 1.48.774.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.48.856.917 I slot launch_slot_: id 0 | task 8097 | processing task, is_child = 0 1.50.034.598 I slot print_timing: id 0 | task 8097 | prompt eval time = 148.15 ms / 372 tokens ( 0.40 ms per token, 2510.99 tokens per second) 1.50.034.603 I slot print_timing: id 0 | task 8097 | eval time = 1029.51 ms / 103 tokens ( 10.09 ms per token, 99.08 tokens per second) 1.50.034.604 I slot print_timing: id 0 | task 8097 | total time = 1177.66 ms / 475 tokens 1.50.034.605 I slot print_timing: id 0 | task 8097 | graphs reused = 7577 1.50.034.606 I slot print_timing: id 0 | task 8097 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.034.637 I slot release: id 0 | task 8097 | stop processing: n_tokens = 506, truncated = 0 1.50.053.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 109944080 1.50.053.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.50.133.962 I slot launch_slot_: id 0 | task 8203 | processing task, is_child = 0 1.52.606.052 I slot print_timing: id 0 | task 8203 | prompt eval time = 155.07 ms / 454 tokens ( 0.34 ms per token, 2927.69 tokens per second) 1.52.606.058 I slot print_timing: id 0 | task 8203 | eval time = 2317.00 ms / 230 tokens ( 10.12 ms per token, 98.83 tokens per second) 1.52.606.059 I slot print_timing: id 0 | task 8203 | total time = 2472.07 ms / 684 tokens 1.52.606.060 I slot print_timing: id 0 | task 8203 | graphs reused = 7804 1.52.606.061 I slot print_timing: id 0 | task 8203 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.606.091 I slot release: id 0 | task 8203 | stop processing: n_tokens = 715, truncated = 0 1.52.620.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 112515535 1.52.620.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.52.704.629 I slot launch_slot_: id 0 | task 8436 | processing task, is_child = 0 1.55.120.004 I slot print_timing: id 0 | task 8436 | prompt eval time = 142.74 ms / 354 tokens ( 0.40 ms per token, 2479.98 tokens per second) 1.55.120.010 I slot print_timing: id 0 | task 8436 | eval time = 2272.61 ms / 226 tokens ( 10.10 ms per token, 99.00 tokens per second) 1.55.120.011 I slot print_timing: id 0 | task 8436 | total time = 2415.36 ms / 580 tokens 1.55.120.012 I slot print_timing: id 0 | task 8436 | graphs reused = 8027 1.55.120.013 I slot print_timing: id 0 | task 8436 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.120.042 I slot release: id 0 | task 8436 | stop processing: n_tokens = 611, truncated = 0 1.55.146.701 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 115029486 1.55.146.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.55.233.438 I slot launch_slot_: id 0 | task 8665 | processing task, is_child = 0 1.56.775.586 I slot print_timing: id 0 | task 8665 | prompt eval time = 140.61 ms / 334 tokens ( 0.42 ms per token, 2375.35 tokens per second) 1.56.775.591 I slot print_timing: id 0 | task 8665 | eval time = 1401.52 ms / 140 tokens ( 10.08 ms per token, 99.18 tokens per second) 1.56.775.592 I slot print_timing: id 0 | task 8665 | total time = 1542.13 ms / 474 tokens 1.56.775.593 I slot print_timing: id 0 | task 8665 | graphs reused = 8165 1.56.775.594 I slot print_timing: id 0 | task 8665 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.775.622 I slot release: id 0 | task 8665 | stop processing: n_tokens = 505, truncated = 0 1.56.793.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 116685066 1.56.793.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.56.875.093 I slot launch_slot_: id 0 | task 8808 | processing task, is_child = 0 1.58.789.131 I slot print_timing: id 0 | task 8808 | prompt eval time = 155.31 ms / 426 tokens ( 0.36 ms per token, 2742.85 tokens per second) 1.58.789.137 I slot print_timing: id 0 | task 8808 | eval time = 1758.70 ms / 175 tokens ( 10.11 ms per token, 98.94 tokens per second) 1.58.789.138 I slot print_timing: id 0 | task 8808 | total time = 1914.02 ms / 601 tokens 1.58.789.139 I slot print_timing: id 0 | task 8808 | graphs reused = 8337 1.58.789.140 I slot print_timing: id 0 | task 8808 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.789.171 I slot release: id 0 | task 8808 | stop processing: n_tokens = 632, truncated = 0 1.58.804.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 118698615 1.58.804.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.58.875.415 I slot launch_slot_: id 0 | task 8986 | processing task, is_child = 0 2.00.194.937 I slot print_timing: id 0 | task 8986 | prompt eval time = 144.40 ms / 366 tokens ( 0.39 ms per token, 2534.71 tokens per second) 2.00.194.944 I slot print_timing: id 0 | task 8986 | eval time = 1175.11 ms / 117 tokens ( 10.13 ms per token, 98.71 tokens per second) 2.00.194.945 I slot print_timing: id 0 | task 8986 | total time = 1319.50 ms / 483 tokens 2.00.194.946 I slot print_timing: id 0 | task 8986 | graphs reused = 8451 2.00.194.948 I slot print_timing: id 0 | task 8986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.194.981 I slot release: id 0 | task 8986 | stop processing: n_tokens = 514, truncated = 0 2.00.211.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 120104425 2.00.211.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.00.282.298 I slot launch_slot_: id 0 | task 9106 | processing task, is_child = 0 2.03.093.240 I slot print_timing: id 0 | task 9106 | prompt eval time = 163.63 ms / 462 tokens ( 0.35 ms per token, 2823.41 tokens per second) 2.03.093.246 I slot print_timing: id 0 | task 9106 | eval time = 2647.29 ms / 263 tokens ( 10.10 ms per token, 98.97 tokens per second) 2.03.093.247 I slot print_timing: id 0 | task 9106 | total time = 2810.92 ms / 725 tokens 2.03.093.248 I slot print_timing: id 0 | task 9106 | graphs reused = 8711 2.03.093.248 I slot print_timing: id 0 | task 9106 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.093.278 I slot release: id 0 | task 9106 | stop processing: n_tokens = 756, truncated = 0 2.03.112.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 123002722 2.03.112.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.03.182.432 I slot launch_slot_: id 0 | task 9372 | processing task, is_child = 0 2.04.726.382 I slot print_timing: id 0 | task 9372 | prompt eval time = 148.32 ms / 396 tokens ( 0.37 ms per token, 2669.81 tokens per second) 2.04.726.387 I slot print_timing: id 0 | task 9372 | eval time = 1395.61 ms / 139 tokens ( 10.11 ms per token, 98.88 tokens per second) 2.04.726.388 I slot print_timing: id 0 | task 9372 | total time = 1543.93 ms / 535 tokens 2.04.726.389 I slot print_timing: id 0 | task 9372 | graphs reused = 8847 2.04.726.390 I slot print_timing: id 0 | task 9372 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.726.419 I slot release: id 0 | task 9372 | stop processing: n_tokens = 566, truncated = 0 2.04.747.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 124635862 2.04.794.026 I slot launch_slot_: id 0 | task 9514 | processing task, is_child = 0 2.06.572.770 I slot print_timing: id 0 | task 9514 | prompt eval time = 159.81 ms / 458 tokens ( 0.35 ms per token, 2865.83 tokens per second) 2.06.572.776 I slot print_timing: id 0 | task 9514 | eval time = 1618.91 ms / 161 tokens ( 10.12 ms per token, 98.83 tokens per second) 2.06.572.777 I slot print_timing: id 0 | task 9514 | total time = 1778.73 ms / 619 tokens 2.06.572.778 I slot print_timing: id 0 | task 9514 | graphs reused = 9005 2.06.572.779 I slot print_timing: id 0 | task 9514 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.572.810 I slot release: id 0 | task 9514 | stop processing: n_tokens = 650, truncated = 0 2.06.586.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 126482254 2.06.586.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.06.672.567 I slot launch_slot_: id 0 | task 9678 | processing task, is_child = 0 2.08.634.639 I slot print_timing: id 0 | task 9678 | prompt eval time = 163.84 ms / 458 tokens ( 0.36 ms per token, 2795.50 tokens per second) 2.08.634.645 I slot print_timing: id 0 | task 9678 | eval time = 1798.22 ms / 176 tokens ( 10.28 ms per token, 97.32 tokens per second) 2.08.634.646 I slot print_timing: id 0 | task 9678 | total time = 1962.05 ms / 634 tokens 2.08.634.647 I slot print_timing: id 0 | task 9678 | graphs reused = 9178 2.08.634.647 I slot print_timing: id 0 | task 9678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.634.681 I slot release: id 0 | task 9678 | stop processing: n_tokens = 665, truncated = 0 2.08.658.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 128544124 2.08.658.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.08.740.563 I slot launch_slot_: id 0 | task 9857 | processing task, is_child = 0 2.11.026.800 I slot print_timing: id 0 | task 9857 | prompt eval time = 159.11 ms / 452 tokens ( 0.35 ms per token, 2840.84 tokens per second) 2.11.026.806 I slot print_timing: id 0 | task 9857 | eval time = 2127.11 ms / 210 tokens ( 10.18 ms per token, 98.26 tokens per second) 2.11.026.807 I slot print_timing: id 0 | task 9857 | total time = 2286.22 ms / 662 tokens 2.11.026.807 I slot print_timing: id 0 | task 9857 | graphs reused = 9385 2.11.026.808 I slot print_timing: id 0 | task 9857 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.026.841 I slot release: id 0 | task 9857 | stop processing: n_tokens = 693, truncated = 0 2.11.054.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 130936284 2.11.054.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.11.135.624 I slot launch_slot_: id 0 | task 10070 | processing task, is_child = 0 2.12.495.048 I slot print_timing: id 0 | task 10070 | prompt eval time = 152.48 ms / 404 tokens ( 0.38 ms per token, 2649.58 tokens per second) 2.12.495.053 I slot print_timing: id 0 | task 10070 | eval time = 1206.93 ms / 120 tokens ( 10.14 ms per token, 98.60 tokens per second) 2.12.495.055 I slot print_timing: id 0 | task 10070 | total time = 1359.41 ms / 524 tokens 2.12.495.055 I slot print_timing: id 0 | task 10070 | graphs reused = 9502 2.12.495.056 I slot print_timing: id 0 | task 10070 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.495.086 I slot release: id 0 | task 10070 | stop processing: n_tokens = 555, truncated = 0 2.12.520.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 132404530 2.12.520.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.12.603.118 I slot launch_slot_: id 0 | task 10193 | processing task, is_child = 0 2.13.802.095 I slot print_timing: id 0 | task 10193 | prompt eval time = 140.12 ms / 345 tokens ( 0.41 ms per token, 2462.14 tokens per second) 2.13.802.102 I slot print_timing: id 0 | task 10193 | eval time = 1058.84 ms / 106 tokens ( 10.08 ms per token, 99.17 tokens per second) 2.13.802.103 I slot print_timing: id 0 | task 10193 | total time = 1198.96 ms / 451 tokens 2.13.802.103 I slot print_timing: id 0 | task 10193 | graphs reused = 9606 2.13.802.104 I slot print_timing: id 0 | task 10193 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.802.132 I slot release: id 0 | task 10193 | stop processing: n_tokens = 482, truncated = 0 2.13.816.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 133711576 2.13.816.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.13.874.188 I slot launch_slot_: id 0 | task 10302 | processing task, is_child = 0 2.15.090.736 I slot print_timing: id 0 | task 10302 | prompt eval time = 161.71 ms / 430 tokens ( 0.38 ms per token, 2659.03 tokens per second) 2.15.090.743 I slot print_timing: id 0 | task 10302 | eval time = 1054.81 ms / 105 tokens ( 10.14 ms per token, 98.60 tokens per second) 2.15.090.744 I slot print_timing: id 0 | task 10302 | total time = 1216.53 ms / 535 tokens 2.15.090.745 I slot print_timing: id 0 | task 10302 | graphs reused = 9708 2.15.090.746 I slot print_timing: id 0 | task 10302 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.090.780 I slot release: id 0 | task 10302 | stop processing: n_tokens = 566, truncated = 0 2.15.105.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 135000224 2.15.105.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.15.160.317 I slot launch_slot_: id 0 | task 10410 | processing task, is_child = 0 2.16.168.464 I slot print_timing: id 0 | task 10410 | prompt eval time = 133.45 ms / 316 tokens ( 0.42 ms per token, 2367.86 tokens per second) 2.16.168.470 I slot print_timing: id 0 | task 10410 | eval time = 874.67 ms / 85 tokens ( 10.41 ms per token, 96.04 tokens per second) 2.16.168.471 I slot print_timing: id 0 | task 10410 | total time = 1008.12 ms / 401 tokens 2.16.168.471 I slot print_timing: id 0 | task 10410 | graphs reused = 9791 2.16.168.472 I slot print_timing: id 0 | task 10410 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.168.498 I slot release: id 0 | task 10410 | stop processing: n_tokens = 432, truncated = 0 2.16.197.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 136077941 2.16.197.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.16.267.615 I slot launch_slot_: id 0 | task 10498 | processing task, is_child = 0 2.17.478.326 I slot print_timing: id 0 | task 10498 | prompt eval time = 142.53 ms / 354 tokens ( 0.40 ms per token, 2483.65 tokens per second) 2.17.478.332 I slot print_timing: id 0 | task 10498 | eval time = 1068.16 ms / 107 tokens ( 10.08 ms per token, 99.24 tokens per second) 2.17.478.333 I slot print_timing: id 0 | task 10498 | total time = 1210.69 ms / 461 tokens 2.17.478.333 I slot print_timing: id 0 | task 10498 | graphs reused = 9896 2.17.478.334 I slot print_timing: id 0 | task 10498 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.478.364 I slot release: id 0 | task 10498 | stop processing: n_tokens = 492, truncated = 0 2.17.494.083 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 137387807 2.17.494.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.17.552.940 I slot launch_slot_: id 0 | task 10608 | processing task, is_child = 0 2.18.700.721 I slot print_timing: id 0 | task 10608 | prompt eval time = 162.92 ms / 438 tokens ( 0.37 ms per token, 2688.49 tokens per second) 2.18.700.728 I slot print_timing: id 0 | task 10608 | eval time = 984.84 ms / 98 tokens ( 10.15 ms per token, 98.49 tokens per second) 2.18.700.729 I slot print_timing: id 0 | task 10608 | total time = 1147.76 ms / 536 tokens 2.18.700.729 I slot print_timing: id 0 | task 10608 | graphs reused = 9991 2.18.700.730 I slot print_timing: id 0 | task 10608 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.700.761 I slot release: id 0 | task 10608 | stop processing: n_tokens = 567, truncated = 0 2.18.726.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 138610204 2.18.726.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.18.781.150 I slot launch_slot_: id 0 | task 10709 | processing task, is_child = 0 2.19.647.084 I slot print_timing: id 0 | task 10709 | prompt eval time = 162.49 ms / 457 tokens ( 0.36 ms per token, 2812.50 tokens per second) 2.19.647.089 I slot print_timing: id 0 | task 10709 | eval time = 703.43 ms / 70 tokens ( 10.19 ms per token, 98.09 tokens per second) 2.19.647.091 I slot print_timing: id 0 | task 10709 | total time = 865.92 ms / 527 tokens 2.19.647.092 I slot print_timing: id 0 | task 10709 | graphs reused = 10058 2.19.647.092 I slot print_timing: id 0 | task 10709 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.647.122 I slot release: id 0 | task 10709 | stop processing: n_tokens = 558, truncated = 0 2.19.666.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 139556566 2.19.666.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.19.723.688 I slot launch_slot_: id 0 | task 10782 | processing task, is_child = 0 2.20.874.387 I slot print_timing: id 0 | task 10782 | prompt eval time = 167.07 ms / 473 tokens ( 0.35 ms per token, 2831.13 tokens per second) 2.20.874.392 I slot print_timing: id 0 | task 10782 | eval time = 983.61 ms / 98 tokens ( 10.14 ms per token, 98.62 tokens per second) 2.20.874.393 I slot print_timing: id 0 | task 10782 | total time = 1150.68 ms / 571 tokens 2.20.874.394 I slot print_timing: id 0 | task 10782 | graphs reused = 10153 2.20.874.395 I slot print_timing: id 0 | task 10782 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.874.425 I slot release: id 0 | task 10782 | stop processing: n_tokens = 602, truncated = 0 2.20.889.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 140783869 2.20.889.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.20.960.339 I slot launch_slot_: id 0 | task 10883 | processing task, is_child = 0 2.21.396.436 I slot print_timing: id 0 | task 10883 | prompt eval time = 165.02 ms / 476 tokens ( 0.35 ms per token, 2884.48 tokens per second) 2.21.396.443 I slot print_timing: id 0 | task 10883 | eval time = 271.06 ms / 27 tokens ( 10.43 ms per token, 95.92 tokens per second) 2.21.396.444 I slot print_timing: id 0 | task 10883 | total time = 436.08 ms / 503 tokens 2.21.396.444 I slot print_timing: id 0 | task 10883 | graphs reused = 10177 2.21.396.445 I slot print_timing: id 0 | task 10883 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.396.479 I slot release: id 0 | task 10883 | stop processing: n_tokens = 534, truncated = 0 2.21.423.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 141305922 2.21.423.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.21.507.821 I slot launch_slot_: id 0 | task 10913 | processing task, is_child = 0 2.22.751.948 I slot print_timing: id 0 | task 10913 | prompt eval time = 169.12 ms / 466 tokens ( 0.36 ms per token, 2755.46 tokens per second) 2.22.751.954 I slot print_timing: id 0 | task 10913 | eval time = 1074.99 ms / 107 tokens ( 10.14 ms per token, 98.61 tokens per second) 2.22.751.955 I slot print_timing: id 0 | task 10913 | total time = 1244.11 ms / 573 tokens 2.22.751.955 I slot print_timing: id 0 | task 10913 | graphs reused = 10281 2.22.751.957 I slot print_timing: id 0 | task 10913 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.751.988 I slot release: id 0 | task 10913 | stop processing: n_tokens = 604, truncated = 0 2.22.768.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 142661431 2.22.769.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.22.839.377 I slot launch_slot_: id 0 | task 11023 | processing task, is_child = 0 2.23.770.185 I slot print_timing: id 0 | task 11023 | prompt eval time = 147.95 ms / 415 tokens ( 0.36 ms per token, 2804.98 tokens per second) 2.23.770.192 I slot print_timing: id 0 | task 11023 | eval time = 782.84 ms / 78 tokens ( 10.17 ms per token, 98.36 tokens per second) 2.23.770.193 I slot print_timing: id 0 | task 11023 | total time = 930.79 ms / 493 tokens 2.23.770.194 I slot print_timing: id 0 | task 11023 | graphs reused = 10356 2.23.770.195 I slot print_timing: id 0 | task 11023 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.770.225 I slot release: id 0 | task 11023 | stop processing: n_tokens = 524, truncated = 0 2.23.773.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 143679669 2.23.774.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.23.846.621 I slot launch_slot_: id 0 | task 11104 | processing task, is_child = 0 2.24.623.808 I slot print_timing: id 0 | task 11104 | prompt eval time = 140.35 ms / 352 tokens ( 0.40 ms per token, 2508.09 tokens per second) 2.24.623.814 I slot print_timing: id 0 | task 11104 | eval time = 636.82 ms / 64 tokens ( 10.11 ms per token, 98.93 tokens per second) 2.24.623.815 I slot print_timing: id 0 | task 11104 | total time = 777.17 ms / 416 tokens 2.24.623.816 I slot print_timing: id 0 | task 11104 | graphs reused = 10418 2.24.623.817 I slot print_timing: id 0 | task 11104 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.623.845 I slot release: id 0 | task 11104 | stop processing: n_tokens = 447, truncated = 0 2.24.649.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 144533289 2.24.649.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.24.719.443 I slot launch_slot_: id 0 | task 11171 | processing task, is_child = 0 2.26.239.368 I slot print_timing: id 0 | task 11171 | prompt eval time = 188.03 ms / 550 tokens ( 0.34 ms per token, 2925.11 tokens per second) 2.26.239.374 I slot print_timing: id 0 | task 11171 | eval time = 1331.88 ms / 133 tokens ( 10.09 ms per token, 99.11 tokens per second) 2.26.239.375 I slot print_timing: id 0 | task 11171 | total time = 1519.90 ms / 683 tokens 2.26.239.376 I slot print_timing: id 0 | task 11171 | graphs reused = 10549 2.26.239.376 I slot print_timing: id 0 | task 11171 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.239.410 I slot release: id 0 | task 11171 | stop processing: n_tokens = 714, truncated = 0 2.26.261.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 146148853 2.26.261.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.26.347.866 I slot launch_slot_: id 0 | task 11308 | processing task, is_child = 0 2.28.851.803 I slot print_timing: id 0 | task 11308 | prompt eval time = 224.26 ms / 772 tokens ( 0.29 ms per token, 3442.36 tokens per second) 2.28.851.809 I slot print_timing: id 0 | task 11308 | eval time = 2279.65 ms / 226 tokens ( 10.13 ms per token, 98.70 tokens per second) 2.28.851.810 I slot print_timing: id 0 | task 11308 | total time = 2503.91 ms / 998 tokens 2.28.851.811 I slot print_timing: id 0 | task 11308 | graphs reused = 10772 2.28.851.812 I slot print_timing: id 0 | task 11308 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.851.857 I slot release: id 0 | task 11308 | stop processing: n_tokens = 1029, truncated = 0 2.28.856.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 148761300 2.28.856.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.28.951.125 I slot launch_slot_: id 0 | task 11538 | processing task, is_child = 0 2.30.992.202 I slot print_timing: id 0 | task 11538 | prompt eval time = 219.82 ms / 683 tokens ( 0.32 ms per token, 3107.10 tokens per second) 2.30.992.208 I slot print_timing: id 0 | task 11538 | eval time = 1821.24 ms / 181 tokens ( 10.12 ms per token, 98.83 tokens per second) 2.30.992.209 I slot print_timing: id 0 | task 11538 | total time = 2041.06 ms / 864 tokens 2.30.992.210 I slot print_timing: id 0 | task 11538 | graphs reused = 10950 2.30.992.211 I slot print_timing: id 0 | task 11538 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.992.249 I slot release: id 0 | task 11538 | stop processing: n_tokens = 895, truncated = 0 2.31.008.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 150901693 2.31.008.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.31.110.996 I slot launch_slot_: id 0 | task 11723 | processing task, is_child = 0 2.33.499.690 I slot print_timing: id 0 | task 11723 | prompt eval time = 197.00 ms / 579 tokens ( 0.34 ms per token, 2939.07 tokens per second) 2.33.499.695 I slot print_timing: id 0 | task 11723 | eval time = 2191.67 ms / 218 tokens ( 10.10 ms per token, 99.01 tokens per second) 2.33.499.697 I slot print_timing: id 0 | task 11723 | total time = 2388.67 ms / 797 tokens 2.33.499.698 I slot print_timing: id 0 | task 11723 | graphs reused = 11165 2.33.499.699 I slot print_timing: id 0 | task 11723 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.499.734 I slot release: id 0 | task 11723 | stop processing: n_tokens = 828, truncated = 0 2.33.518.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 153409178 2.33.518.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.33.538.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.33.637.443 I slot launch_slot_: id 0 | task 11945 | processing task, is_child = 0 2.34.874.425 I slot print_timing: id 0 | task 11945 | prompt eval time = 176.63 ms / 500 tokens ( 0.35 ms per token, 2830.81 tokens per second) 2.34.874.431 I slot print_timing: id 0 | task 11945 | eval time = 1060.33 ms / 106 tokens ( 10.10 ms per token, 99.03 tokens per second) 2.34.874.432 I slot print_timing: id 0 | task 11945 | total time = 1236.96 ms / 606 tokens 2.34.874.433 I slot print_timing: id 0 | task 11945 | graphs reused = 11269 2.34.874.433 I slot print_timing: id 0 | task 11945 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.874.466 I slot release: id 0 | task 11945 | stop processing: n_tokens = 637, truncated = 0 2.34.895.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 154783910 2.34.895.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.34.962.660 I slot launch_slot_: id 0 | task 12054 | processing task, is_child = 0 2.37.293.799 I slot print_timing: id 0 | task 12054 | prompt eval time = 232.25 ms / 776 tokens ( 0.30 ms per token, 3341.24 tokens per second) 2.37.293.805 I slot print_timing: id 0 | task 12054 | eval time = 2098.87 ms / 209 tokens ( 10.09 ms per token, 99.10 tokens per second) 2.37.293.806 I slot print_timing: id 0 | task 12054 | total time = 2331.12 ms / 985 tokens 2.37.293.807 I slot print_timing: id 0 | task 12054 | graphs reused = 11476 2.37.293.808 I slot print_timing: id 0 | task 12054 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.293.853 I slot release: id 0 | task 12054 | stop processing: n_tokens = 1016, truncated = 0 2.37.317.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 157203297 2.37.317.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.37.394.117 I slot launch_slot_: id 0 | task 12267 | processing task, is_child = 0 2.39.545.784 I slot print_timing: id 0 | task 12267 | prompt eval time = 173.51 ms / 504 tokens ( 0.34 ms per token, 2904.80 tokens per second) 2.39.545.791 I slot print_timing: id 0 | task 12267 | eval time = 1978.14 ms / 197 tokens ( 10.09 ms per token, 99.08 tokens per second) 2.39.545.792 I slot print_timing: id 0 | task 12267 | total time = 2151.65 ms / 701 tokens 2.39.545.793 I slot print_timing: id 0 | task 12267 | graphs reused = 11671 2.39.545.794 I slot print_timing: id 0 | task 12267 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.545.831 I slot release: id 0 | task 12267 | stop processing: n_tokens = 732, truncated = 0 2.39.560.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 159455275 2.39.561.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.39.628.867 I slot launch_slot_: id 0 | task 12467 | processing task, is_child = 0 2.41.917.212 I slot print_timing: id 0 | task 12467 | prompt eval time = 204.26 ms / 633 tokens ( 0.32 ms per token, 3098.98 tokens per second) 2.41.917.218 I slot print_timing: id 0 | task 12467 | eval time = 2084.06 ms / 207 tokens ( 10.12 ms per token, 98.85 tokens per second) 2.41.917.219 I slot print_timing: id 0 | task 12467 | total time = 2288.32 ms / 840 tokens 2.41.917.220 I slot print_timing: id 0 | task 12467 | graphs reused = 11875 2.41.917.220 I slot print_timing: id 0 | task 12467 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.917.259 I slot release: id 0 | task 12467 | stop processing: n_tokens = 871, truncated = 0 2.41.945.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 161826702 2.41.945.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 2.42.031.422 I slot launch_slot_: id 0 | task 12678 | processing task, is_child = 0 2.43.531.808 I slot print_timing: id 0 | task 12678 | prompt eval time = 154.92 ms / 395 tokens ( 0.39 ms per token, 2549.67 tokens per second) 2.43.531.813 I slot print_timing: id 0 | task 12678 | eval time = 1345.44 ms / 134 tokens ( 10.12 ms per token, 98.85 tokens per second) 2.43.531.814 I slot print_timing: id 0 | task 12678 | total time = 1500.37 ms / 529 tokens 2.43.531.815 I slot print_timing: id 0 | task 12678 | graphs reused = 12006 2.43.531.816 I slot print_timing: id 0 | task 12678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.531.845 I slot release: id 0 | task 12678 | stop processing: n_tokens = 560, truncated = 0 2.43.556.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 163441289 2.43.556.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.43.628.402 I slot launch_slot_: id 0 | task 12815 | processing task, is_child = 0 2.45.925.422 I slot print_timing: id 0 | task 12815 | prompt eval time = 194.70 ms / 584 tokens ( 0.33 ms per token, 2999.46 tokens per second) 2.45.925.427 I slot print_timing: id 0 | task 12815 | eval time = 2102.30 ms / 209 tokens ( 10.11 ms per token, 98.94 tokens per second) 2.45.925.428 I slot print_timing: id 0 | task 12815 | total time = 2297.00 ms / 793 tokens 2.45.925.429 I slot print_timing: id 0 | task 12815 | graphs reused = 12212 2.45.925.429 I slot print_timing: id 0 | task 12815 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.925.466 I slot release: id 0 | task 12815 | stop processing: n_tokens = 824, truncated = 0 2.45.945.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 165834910 2.45.945.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.46.034.188 I slot launch_slot_: id 0 | task 13028 | processing task, is_child = 0 2.48.567.932 I slot print_timing: id 0 | task 13028 | prompt eval time = 219.46 ms / 695 tokens ( 0.32 ms per token, 3166.86 tokens per second) 2.48.567.938 I slot print_timing: id 0 | task 13028 | eval time = 2314.26 ms / 230 tokens ( 10.11 ms per token, 98.95 tokens per second) 2.48.567.939 I slot print_timing: id 0 | task 13028 | total time = 2533.72 ms / 925 tokens 2.48.567.940 I slot print_timing: id 0 | task 13028 | graphs reused = 12439 2.48.567.940 I slot print_timing: id 0 | task 13028 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.567.979 I slot release: id 0 | task 13028 | stop processing: n_tokens = 956, truncated = 0 2.48.573.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 168477423 2.48.573.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.48.667.098 I slot launch_slot_: id 0 | task 13262 | processing task, is_child = 0 2.50.816.759 I slot print_timing: id 0 | task 13262 | prompt eval time = 231.83 ms / 769 tokens ( 0.30 ms per token, 3317.03 tokens per second) 2.50.816.764 I slot print_timing: id 0 | task 13262 | eval time = 1917.81 ms / 191 tokens ( 10.09 ms per token, 99.07 tokens per second) 2.50.816.765 I slot print_timing: id 0 | task 13262 | total time = 2149.64 ms / 960 tokens 2.50.816.766 I slot print_timing: id 0 | task 13262 | graphs reused = 12628 2.50.816.767 I slot print_timing: id 0 | task 13262 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.816.807 I slot release: id 0 | task 13262 | stop processing: n_tokens = 991, truncated = 0 2.50.838.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 170726251 2.50.838.710 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.50.858.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 2.50.955.429 I slot launch_slot_: id 0 | task 13457 | processing task, is_child = 0 2.52.397.797 I slot print_timing: id 0 | task 13457 | prompt eval time = 191.47 ms / 576 tokens ( 0.33 ms per token, 3008.32 tokens per second) 2.52.397.803 I slot print_timing: id 0 | task 13457 | eval time = 1250.88 ms / 124 tokens ( 10.17 ms per token, 98.33 tokens per second) 2.52.397.804 I slot print_timing: id 0 | task 13457 | total time = 1442.35 ms / 700 tokens 2.52.397.805 I slot print_timing: id 0 | task 13457 | graphs reused = 12750 2.52.397.806 I slot print_timing: id 0 | task 13457 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.397.844 I slot release: id 0 | task 13457 | stop processing: n_tokens = 731, truncated = 0 2.52.419.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 172307288 2.52.419.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.52.494.459 I slot launch_slot_: id 0 | task 13585 | processing task, is_child = 0 2.55.481.552 I slot print_timing: id 0 | task 13585 | prompt eval time = 213.81 ms / 655 tokens ( 0.33 ms per token, 3063.50 tokens per second) 2.55.481.558 I slot print_timing: id 0 | task 13585 | eval time = 2773.26 ms / 275 tokens ( 10.12 ms per token, 98.80 tokens per second) 2.55.481.559 I slot print_timing: id 0 | task 13585 | total time = 2987.07 ms / 930 tokens 2.55.481.561 I slot print_timing: id 0 | task 13585 | graphs reused = 13022 2.55.481.562 I slot print_timing: id 0 | task 13585 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.481.603 I slot release: id 0 | task 13585 | stop processing: n_tokens = 961, truncated = 0 2.55.497.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 175391046 2.55.497.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.55.561.209 I slot launch_slot_: id 0 | task 13864 | processing task, is_child = 0 2.56.999.714 I slot print_timing: id 0 | task 13864 | prompt eval time = 203.50 ms / 621 tokens ( 0.33 ms per token, 3051.64 tokens per second) 2.56.999.719 I slot print_timing: id 0 | task 13864 | eval time = 1234.99 ms / 121 tokens ( 10.29 ms per token, 97.17 tokens per second) 2.56.999.721 I slot print_timing: id 0 | task 13864 | total time = 1438.49 ms / 742 tokens 2.56.999.722 I slot print_timing: id 0 | task 13864 | graphs reused = 13140 2.56.999.723 I slot print_timing: id 0 | task 13864 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.999.761 I slot release: id 0 | task 13864 | stop processing: n_tokens = 773, truncated = 0 2.57.022.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 176909204 2.57.022.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.57.119.802 I slot launch_slot_: id 0 | task 13989 | processing task, is_child = 0 2.59.172.401 I slot print_timing: id 0 | task 13989 | prompt eval time = 226.36 ms / 767 tokens ( 0.30 ms per token, 3388.36 tokens per second) 2.59.172.406 I slot print_timing: id 0 | task 13989 | eval time = 1826.22 ms / 178 tokens ( 10.32 ms per token, 96.92 tokens per second) 2.59.172.407 I slot print_timing: id 0 | task 13989 | total time = 2052.58 ms / 945 tokens 2.59.172.408 I slot print_timing: id 0 | task 13989 | graphs reused = 13316 2.59.172.409 I slot print_timing: id 0 | task 13989 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.172.450 I slot release: id 0 | task 13989 | stop processing: n_tokens = 976, truncated = 0 2.59.192.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 179081894 2.59.192.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.59.259.503 I slot launch_slot_: id 0 | task 14171 | processing task, is_child = 0 3.01.588.390 I slot print_timing: id 0 | task 14171 | prompt eval time = 253.08 ms / 864 tokens ( 0.29 ms per token, 3413.91 tokens per second) 3.01.588.396 I slot print_timing: id 0 | task 14171 | eval time = 2075.79 ms / 203 tokens ( 10.28 ms per token, 97.31 tokens per second) 3.01.588.397 I slot print_timing: id 0 | task 14171 | total time = 2328.87 ms / 1067 tokens 3.01.588.398 I slot print_timing: id 0 | task 14171 | graphs reused = 13516 3.01.588.399 I slot print_timing: id 0 | task 14171 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.588.443 I slot release: id 0 | task 14171 | stop processing: n_tokens = 1098, truncated = 0 3.01.603.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 181497886 3.01.603.474 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.01.612.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.01.681.760 I slot launch_slot_: id 0 | task 14378 | processing task, is_child = 0 3.03.195.321 I slot print_timing: id 0 | task 14378 | prompt eval time = 215.26 ms / 646 tokens ( 0.33 ms per token, 3000.99 tokens per second) 3.03.195.326 I slot print_timing: id 0 | task 14378 | eval time = 1298.28 ms / 129 tokens ( 10.14 ms per token, 98.59 tokens per second) 3.03.195.327 I slot print_timing: id 0 | task 14378 | total time = 1513.54 ms / 775 tokens 3.03.195.328 I slot print_timing: id 0 | task 14378 | graphs reused = 13642 3.03.195.329 I slot print_timing: id 0 | task 14378 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.195.367 I slot release: id 0 | task 14378 | stop processing: n_tokens = 806, truncated = 0 3.03.209.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 183104811 3.03.209.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.03.289.897 I slot launch_slot_: id 0 | task 14511 | processing task, is_child = 0 3.05.769.428 I slot print_timing: id 0 | task 14511 | prompt eval time = 217.82 ms / 720 tokens ( 0.30 ms per token, 3305.41 tokens per second) 3.05.769.434 I slot print_timing: id 0 | task 14511 | eval time = 2261.69 ms / 219 tokens ( 10.37 ms per token, 96.39 tokens per second) 3.05.769.434 I slot print_timing: id 0 | task 14511 | total time = 2479.51 ms / 939 tokens 3.05.769.436 I slot print_timing: id 0 | task 14511 | graphs reused = 13858 3.05.769.436 I slot print_timing: id 0 | task 14511 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.769.477 I slot release: id 0 | task 14511 | stop processing: n_tokens = 970, truncated = 0 3.05.789.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 185678920 3.05.789.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 3.05.872.518 I slot launch_slot_: id 0 | task 14734 | processing task, is_child = 0 3.08.194.828 I slot print_timing: id 0 | task 14734 | prompt eval time = 174.97 ms / 509 tokens ( 0.34 ms per token, 2909.02 tokens per second) 3.08.194.836 I slot print_timing: id 0 | task 14734 | eval time = 2147.32 ms / 214 tokens ( 10.08 ms per token, 99.19 tokens per second) 3.08.194.837 I slot print_timing: id 0 | task 14734 | total time = 2322.29 ms / 723 tokens 3.08.194.838 I slot print_timing: id 0 | task 14734 | graphs reused = 14070 3.08.194.839 I slot print_timing: id 0 | task 14734 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.194.876 I slot release: id 0 | task 14734 | stop processing: n_tokens = 754, truncated = 0 3.08.212.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 188104320 3.08.212.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 3.08.291.179 I slot launch_slot_: id 0 | task 14951 | processing task, is_child = 0 3.10.917.064 I slot print_timing: id 0 | task 14951 | prompt eval time = 192.40 ms / 581 tokens ( 0.33 ms per token, 3019.70 tokens per second) 3.10.917.070 I slot print_timing: id 0 | task 14951 | eval time = 2433.46 ms / 242 tokens ( 10.10 ms per token, 99.04 tokens per second) 3.10.917.071 I slot print_timing: id 0 | task 14951 | total time = 2625.86 ms / 823 tokens 3.10.917.072 I slot print_timing: id 0 | task 14951 | graphs reused = 14309 3.10.917.073 I slot print_timing: id 0 | task 14951 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.917.110 I slot release: id 0 | task 14951 | stop processing: n_tokens = 854, truncated = 0 3.10.945.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 190826554 3.10.945.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.11.037.472 I slot launch_slot_: id 0 | task 15197 | processing task, is_child = 0 3.13.520.626 I slot print_timing: id 0 | task 15197 | prompt eval time = 261.73 ms / 925 tokens ( 0.28 ms per token, 3534.12 tokens per second) 3.13.520.631 I slot print_timing: id 0 | task 15197 | eval time = 2221.40 ms / 220 tokens ( 10.14 ms per token, 98.59 tokens per second) 3.13.520.632 I slot print_timing: id 0 | task 15197 | total time = 2483.13 ms / 1145 tokens 3.13.520.634 I slot print_timing: id 0 | task 15197 | graphs reused = 14526 3.13.520.634 I slot print_timing: id 0 | task 15197 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.520.683 I slot release: id 0 | task 15197 | stop processing: n_tokens = 1176, truncated = 0 3.13.548.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 193430127 3.13.548.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.13.648.015 I slot launch_slot_: id 0 | task 15421 | processing task, is_child = 0 3.16.402.543 I slot print_timing: id 0 | task 15421 | prompt eval time = 250.44 ms / 885 tokens ( 0.28 ms per token, 3533.79 tokens per second) 3.16.402.549 I slot print_timing: id 0 | task 15421 | eval time = 2504.07 ms / 245 tokens ( 10.26 ms per token, 97.44 tokens per second) 3.16.402.550 I slot print_timing: id 0 | task 15421 | total time = 2754.51 ms / 1130 tokens 3.16.402.551 I slot print_timing: id 0 | task 15421 | graphs reused = 14768 3.16.402.552 I slot print_timing: id 0 | task 15421 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.402.599 I slot release: id 0 | task 15421 | stop processing: n_tokens = 1161, truncated = 0 3.16.429.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 196312043 3.16.429.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.16.541.403 I slot launch_slot_: id 0 | task 15670 | processing task, is_child = 0 3.17.889.431 I slot print_timing: id 0 | task 15670 | prompt eval time = 148.33 ms / 392 tokens ( 0.38 ms per token, 2642.77 tokens per second) 3.17.889.436 I slot print_timing: id 0 | task 15670 | eval time = 1199.68 ms / 119 tokens ( 10.17 ms per token, 98.36 tokens per second) 3.17.889.437 I slot print_timing: id 0 | task 15670 | total time = 1348.01 ms / 511 tokens 3.17.889.438 I slot print_timing: id 0 | task 15670 | graphs reused = 14884 3.17.889.439 I slot print_timing: id 0 | task 15670 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.889.470 I slot release: id 0 | task 15670 | stop processing: n_tokens = 542, truncated = 0 3.17.908.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 197798914 3.17.908.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.18.000.255 I slot launch_slot_: id 0 | task 15792 | processing task, is_child = 0 3.18.633.782 I slot print_timing: id 0 | task 15792 | prompt eval time = 137.10 ms / 331 tokens ( 0.41 ms per token, 2414.30 tokens per second) 3.18.633.787 I slot print_timing: id 0 | task 15792 | eval time = 496.41 ms / 50 tokens ( 10.13 ms per token, 98.71 tokens per second) 3.18.633.788 I slot print_timing: id 0 | task 15792 | total time = 633.51 ms / 381 tokens 3.18.633.789 I slot print_timing: id 0 | task 15792 | graphs reused = 14932 3.18.633.790 I slot print_timing: id 0 | task 15792 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.633.818 I slot release: id 0 | task 15792 | stop processing: n_tokens = 412, truncated = 0 3.18.661.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 198543262 3.18.661.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.18.741.907 I slot launch_slot_: id 0 | task 15845 | processing task, is_child = 0 3.20.586.269 I slot print_timing: id 0 | task 15845 | prompt eval time = 139.58 ms / 357 tokens ( 0.39 ms per token, 2557.67 tokens per second) 3.20.586.275 I slot print_timing: id 0 | task 15845 | eval time = 1704.76 ms / 169 tokens ( 10.15 ms per token, 98.55 tokens per second) 3.20.586.276 I slot print_timing: id 0 | task 15845 | total time = 1844.34 ms / 526 tokens 3.20.586.277 I slot print_timing: id 0 | task 15845 | graphs reused = 15098 3.20.586.278 I slot print_timing: id 0 | task 15845 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.586.307 I slot release: id 0 | task 15845 | stop processing: n_tokens = 557, truncated = 0 3.20.599.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 200495750 3.20.599.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.20.677.106 I slot launch_slot_: id 0 | task 16017 | processing task, is_child = 0 3.21.350.298 I slot print_timing: id 0 | task 16017 | prompt eval time = 136.85 ms / 315 tokens ( 0.43 ms per token, 2301.76 tokens per second) 3.21.350.304 I slot print_timing: id 0 | task 16017 | eval time = 536.32 ms / 54 tokens ( 10.12 ms per token, 98.82 tokens per second) 3.21.350.305 I slot print_timing: id 0 | task 16017 | total time = 673.17 ms / 369 tokens 3.21.350.305 I slot print_timing: id 0 | task 16017 | graphs reused = 15150 3.21.350.306 I slot print_timing: id 0 | task 16017 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.350.333 I slot release: id 0 | task 16017 | stop processing: n_tokens = 400, truncated = 0 3.21.363.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 201259777 3.21.363.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.21.431.415 I slot launch_slot_: id 0 | task 16074 | processing task, is_child = 0 3.22.390.339 I slot print_timing: id 0 | task 16074 | prompt eval time = 140.89 ms / 378 tokens ( 0.37 ms per token, 2682.98 tokens per second) 3.22.390.345 I slot print_timing: id 0 | task 16074 | eval time = 818.02 ms / 82 tokens ( 10.10 ms per token, 99.02 tokens per second) 3.22.390.346 I slot print_timing: id 0 | task 16074 | total time = 958.91 ms / 460 tokens 3.22.390.347 I slot print_timing: id 0 | task 16074 | graphs reused = 15230 3.22.390.348 I slot print_timing: id 0 | task 16074 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.390.379 I slot release: id 0 | task 16074 | stop processing: n_tokens = 491, truncated = 0 3.22.408.015 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 202299822 3.22.408.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.22.481.822 I slot launch_slot_: id 0 | task 16159 | processing task, is_child = 0 3.22.886.876 I slot print_timing: id 0 | task 16159 | prompt eval time = 129.27 ms / 295 tokens ( 0.44 ms per token, 2281.97 tokens per second) 3.22.886.882 I slot print_timing: id 0 | task 16159 | eval time = 275.76 ms / 28 tokens ( 10.21 ms per token, 97.91 tokens per second) 3.22.886.884 I slot print_timing: id 0 | task 16159 | total time = 405.04 ms / 323 tokens 3.22.886.884 I slot print_timing: id 0 | task 16159 | graphs reused = 15256 3.22.886.886 I slot print_timing: id 0 | task 16159 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.886.913 I slot release: id 0 | task 16159 | stop processing: n_tokens = 354, truncated = 0 3.22.908.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 202796357 3.22.908.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.22.972.014 I slot launch_slot_: id 0 | task 16190 | processing task, is_child = 0 3.24.492.442 I slot print_timing: id 0 | task 16190 | prompt eval time = 137.55 ms / 337 tokens ( 0.41 ms per token, 2450.02 tokens per second) 3.24.492.448 I slot print_timing: id 0 | task 16190 | eval time = 1382.86 ms / 138 tokens ( 10.09 ms per token, 99.07 tokens per second) 3.24.492.449 I slot print_timing: id 0 | task 16190 | total time = 1520.41 ms / 475 tokens 3.24.492.449 I slot print_timing: id 0 | task 16190 | graphs reused = 15392 3.24.492.450 I slot print_timing: id 0 | task 16190 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.492.478 I slot release: id 0 | task 16190 | stop processing: n_tokens = 506, truncated = 0 3.24.520.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 204401922 3.24.520.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.24.594.901 I slot launch_slot_: id 0 | task 16331 | processing task, is_child = 0 3.25.178.508 I slot print_timing: id 0 | task 16331 | prompt eval time = 137.73 ms / 325 tokens ( 0.42 ms per token, 2359.62 tokens per second) 3.25.178.513 I slot print_timing: id 0 | task 16331 | eval time = 445.85 ms / 45 tokens ( 10.13 ms per token, 98.69 tokens per second) 3.25.178.514 I slot print_timing: id 0 | task 16331 | total time = 583.59 ms / 370 tokens 3.25.178.515 I slot print_timing: id 0 | task 16331 | graphs reused = 15435 3.25.178.516 I slot print_timing: id 0 | task 16331 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.178.544 I slot release: id 0 | task 16331 | stop processing: n_tokens = 401, truncated = 0 3.25.196.044 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.080 3.25.237.809 I slot launch_slot_: id 0 | task 16379 | processing task, is_child = 0 3.26.267.029 I slot print_timing: id 0 | task 16379 | prompt eval time = 122.15 ms / 264 tokens ( 0.46 ms per token, 2161.26 tokens per second) 3.26.267.035 I slot print_timing: id 0 | task 16379 | eval time = 907.05 ms / 91 tokens ( 10.08 ms per token, 99.22 tokens per second) 3.26.267.036 I slot print_timing: id 0 | task 16379 | total time = 1029.20 ms / 355 tokens 3.26.267.037 I slot print_timing: id 0 | task 16379 | graphs reused = 15524 3.26.267.038 I slot print_timing: id 0 | task 16379 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.267.063 I slot release: id 0 | task 16379 | stop processing: n_tokens = 386, truncated = 0 3.26.294.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 386, t_last = 206176507 3.26.294.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.26.373.096 I slot launch_slot_: id 0 | task 16473 | processing task, is_child = 0 3.26.714.345 I slot print_timing: id 0 | task 16473 | prompt eval time = 136.26 ms / 331 tokens ( 0.41 ms per token, 2429.25 tokens per second) 3.26.714.350 I slot print_timing: id 0 | task 16473 | eval time = 204.97 ms / 21 tokens ( 10.25 ms per token, 97.57 tokens per second) 3.26.714.352 I slot print_timing: id 0 | task 16473 | total time = 341.23 ms / 352 tokens 3.26.714.352 I slot print_timing: id 0 | task 16473 | graphs reused = 15543 3.26.714.353 I slot print_timing: id 0 | task 16473 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.714.382 I slot release: id 0 | task 16473 | stop processing: n_tokens = 383, truncated = 0 3.26.730.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 206623825 3.26.730.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.26.802.787 I slot launch_slot_: id 0 | task 16497 | processing task, is_child = 0 3.28.059.081 I slot print_timing: id 0 | task 16497 | prompt eval time = 137.70 ms / 333 tokens ( 0.41 ms per token, 2418.30 tokens per second) 3.28.059.087 I slot print_timing: id 0 | task 16497 | eval time = 1118.57 ms / 112 tokens ( 10.08 ms per token, 99.23 tokens per second) 3.28.059.088 I slot print_timing: id 0 | task 16497 | total time = 1256.27 ms / 445 tokens 3.28.059.089 I slot print_timing: id 0 | task 16497 | graphs reused = 15653 3.28.059.089 I slot print_timing: id 0 | task 16497 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.059.115 I slot release: id 0 | task 16497 | stop processing: n_tokens = 476, truncated = 0 3.28.074.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 207968559 3.28.074.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.28.156.430 I slot launch_slot_: id 0 | task 16612 | processing task, is_child = 0 3.28.825.150 I slot print_timing: id 0 | task 16612 | prompt eval time = 141.19 ms / 346 tokens ( 0.41 ms per token, 2450.63 tokens per second) 3.28.825.155 I slot print_timing: id 0 | task 16612 | eval time = 527.51 ms / 53 tokens ( 10.14 ms per token, 98.58 tokens per second) 3.28.825.157 I slot print_timing: id 0 | task 16612 | total time = 668.70 ms / 399 tokens 3.28.825.157 I slot print_timing: id 0 | task 16612 | graphs reused = 15704 3.28.825.158 I slot print_timing: id 0 | task 16612 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.825.187 I slot release: id 0 | task 16612 | stop processing: n_tokens = 430, truncated = 0 3.28.851.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 208734631 3.28.851.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.28.925.667 I slot launch_slot_: id 0 | task 16668 | processing task, is_child = 0 3.29.436.414 I slot print_timing: id 0 | task 16668 | prompt eval time = 135.29 ms / 325 tokens ( 0.42 ms per token, 2402.25 tokens per second) 3.29.436.419 I slot print_timing: id 0 | task 16668 | eval time = 375.44 ms / 38 tokens ( 10.15 ms per token, 98.55 tokens per second) 3.29.436.420 I slot print_timing: id 0 | task 16668 | total time = 510.73 ms / 363 tokens 3.29.436.421 I slot print_timing: id 0 | task 16668 | graphs reused = 15740 3.29.436.422 I slot print_timing: id 0 | task 16668 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.436.450 I slot release: id 0 | task 16668 | stop processing: n_tokens = 394, truncated = 0 3.29.462.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 209345894 3.29.462.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.29.526.388 I slot launch_slot_: id 0 | task 16709 | processing task, is_child = 0 3.31.772.002 I slot print_timing: id 0 | task 16709 | prompt eval time = 135.62 ms / 322 tokens ( 0.42 ms per token, 2374.28 tokens per second) 3.31.772.008 I slot print_timing: id 0 | task 16709 | eval time = 2109.97 ms / 210 tokens ( 10.10 ms per token, 99.05 tokens per second) 3.31.772.009 I slot print_timing: id 0 | task 16709 | total time = 2245.59 ms / 532 tokens 3.31.772.009 I slot print_timing: id 0 | task 16709 | graphs reused = 15947 3.31.772.010 I slot print_timing: id 0 | task 16709 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.772.039 I slot release: id 0 | task 16709 | stop processing: n_tokens = 563, truncated = 0 3.31.800.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 211681483 3.31.844.166 I slot launch_slot_: id 0 | task 16922 | processing task, is_child = 0 3.34.984.420 I slot print_timing: id 0 | task 16922 | n_gen = 297, tg = 98.54 t/s, tg_3s = 98.87 t/s 3.35.798.837 I slot print_timing: id 0 | task 16922 | prompt eval time = 136.42 ms / 338 tokens ( 0.40 ms per token, 2477.62 tokens per second) 3.35.798.843 I slot print_timing: id 0 | task 16922 | eval time = 3818.23 ms / 378 tokens ( 10.13 ms per token, 98.74 tokens per second) 3.35.798.844 I slot print_timing: id 0 | task 16922 | total time = 3954.65 ms / 716 tokens 3.35.798.845 I slot print_timing: id 0 | task 16922 | graphs reused = 16322 3.35.798.846 I slot print_timing: id 0 | task 16922 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.798.877 I slot release: id 0 | task 16922 | stop processing: n_tokens = 747, truncated = 0 3.35.816.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 747, t_last = 215708320 3.35.816.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.35.876.802 I slot launch_slot_: id 0 | task 17303 | processing task, is_child = 0 3.39.024.180 I slot print_timing: id 0 | task 17303 | n_gen = 299, tg = 99.02 t/s, tg_3s = 99.36 t/s 3.40.355.654 I slot print_timing: id 0 | task 17303 | prompt eval time = 137.96 ms / 347 tokens ( 0.40 ms per token, 2515.26 tokens per second) 3.40.355.660 I slot print_timing: id 0 | task 17303 | eval time = 4340.87 ms / 430 tokens ( 10.12 ms per token, 98.83 tokens per second) 3.40.355.661 I slot print_timing: id 0 | task 17303 | total time = 4478.83 ms / 777 tokens 3.40.355.661 I slot print_timing: id 0 | task 17303 | graphs reused = 16748 3.40.355.662 I slot print_timing: id 0 | task 17303 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.355.694 I slot release: id 0 | task 17303 | stop processing: n_tokens = 808, truncated = 0 3.40.374.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 808, t_last = 220265137 3.40.374.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.40.467.087 I slot launch_slot_: id 0 | task 17736 | processing task, is_child = 0 3.41.314.128 I slot print_timing: id 0 | task 17736 | prompt eval time = 138.71 ms / 331 tokens ( 0.42 ms per token, 2386.24 tokens per second) 3.41.314.133 I slot print_timing: id 0 | task 17736 | eval time = 708.31 ms / 71 tokens ( 10.12 ms per token, 98.83 tokens per second) 3.41.314.135 I slot print_timing: id 0 | task 17736 | total time = 847.02 ms / 402 tokens 3.41.314.136 I slot print_timing: id 0 | task 17736 | graphs reused = 16817 3.41.314.136 I slot print_timing: id 0 | task 17736 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.314.163 I slot release: id 0 | task 17736 | stop processing: n_tokens = 433, truncated = 0 3.41.336.637 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 221223607 3.41.336.683 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 3.41.399.622 I slot launch_slot_: id 0 | task 17810 | processing task, is_child = 0 3.41.984.577 I slot print_timing: id 0 | task 17810 | prompt eval time = 137.88 ms / 345 tokens ( 0.40 ms per token, 2502.10 tokens per second) 3.41.984.583 I slot print_timing: id 0 | task 17810 | eval time = 447.05 ms / 45 tokens ( 10.16 ms per token, 98.42 tokens per second) 3.41.984.584 I slot print_timing: id 0 | task 17810 | total time = 584.94 ms / 390 tokens 3.41.984.585 I slot print_timing: id 0 | task 17810 | graphs reused = 16860 3.41.984.586 I slot print_timing: id 0 | task 17810 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.984.614 I slot release: id 0 | task 17810 | stop processing: n_tokens = 421, truncated = 0 3.42.006.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 221894058 3.42.006.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.42.063.314 I slot launch_slot_: id 0 | task 17858 | processing task, is_child = 0 3.42.726.671 I slot print_timing: id 0 | task 17858 | prompt eval time = 135.76 ms / 320 tokens ( 0.42 ms per token, 2357.07 tokens per second) 3.42.726.676 I slot print_timing: id 0 | task 17858 | eval time = 527.58 ms / 53 tokens ( 10.15 ms per token, 98.56 tokens per second) 3.42.726.678 I slot print_timing: id 0 | task 17858 | total time = 663.34 ms / 373 tokens 3.42.726.678 I slot print_timing: id 0 | task 17858 | graphs reused = 16911 3.42.726.679 I slot print_timing: id 0 | task 17858 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.726.708 I slot release: id 0 | task 17858 | stop processing: n_tokens = 404, truncated = 0 3.42.745.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 222636152 3.42.745.521 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.42.812.751 I slot launch_slot_: id 0 | task 17914 | processing task, is_child = 0 3.43.436.529 I slot print_timing: id 0 | task 17914 | prompt eval time = 129.31 ms / 297 tokens ( 0.44 ms per token, 2296.72 tokens per second) 3.43.436.536 I slot print_timing: id 0 | task 17914 | eval time = 494.44 ms / 47 tokens ( 10.75 ms per token, 93.03 tokens per second) 3.43.436.537 I slot print_timing: id 0 | task 17914 | total time = 623.76 ms / 344 tokens 3.43.436.538 I slot print_timing: id 0 | task 17914 | graphs reused = 16956 3.43.436.538 I slot print_timing: id 0 | task 17914 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.436.564 I slot release: id 0 | task 17914 | stop processing: n_tokens = 375, truncated = 0 3.43.464.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 223346008 3.43.507.965 I slot launch_slot_: id 0 | task 17964 | processing task, is_child = 0 3.46.502.921 I slot print_timing: id 0 | task 17964 | prompt eval time = 137.78 ms / 343 tokens ( 0.40 ms per token, 2489.46 tokens per second) 3.46.502.927 I slot print_timing: id 0 | task 17964 | eval time = 2857.16 ms / 284 tokens ( 10.10 ms per token, 99.05 tokens per second) 3.46.502.928 I slot print_timing: id 0 | task 17964 | total time = 2994.94 ms / 627 tokens 3.46.502.929 I slot print_timing: id 0 | task 17964 | graphs reused = 17237 3.46.502.930 I slot print_timing: id 0 | task 17964 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.502.958 I slot release: id 0 | task 17964 | stop processing: n_tokens = 658, truncated = 0 3.46.530.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 658, t_last = 226412402 3.46.530.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.46.625.098 I slot launch_slot_: id 0 | task 18251 | processing task, is_child = 0 3.48.253.473 I slot print_timing: id 0 | task 18251 | prompt eval time = 145.11 ms / 371 tokens ( 0.39 ms per token, 2556.66 tokens per second) 3.48.253.478 I slot print_timing: id 0 | task 18251 | eval time = 1483.24 ms / 147 tokens ( 10.16 ms per token, 98.43 tokens per second) 3.48.253.480 I slot print_timing: id 0 | task 18251 | total time = 1628.36 ms / 518 tokens 3.48.253.480 I slot print_timing: id 0 | task 18251 | graphs reused = 17381 3.48.253.481 I slot print_timing: id 0 | task 18251 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.253.512 I slot release: id 0 | task 18251 | stop processing: n_tokens = 549, truncated = 0 3.48.274.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 228162956 3.48.274.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.48.340.464 I slot launch_slot_: id 0 | task 18401 | processing task, is_child = 0 3.49.786.738 I slot print_timing: id 0 | task 18401 | prompt eval time = 129.92 ms / 292 tokens ( 0.44 ms per token, 2247.50 tokens per second) 3.49.786.743 I slot print_timing: id 0 | task 18401 | eval time = 1316.33 ms / 131 tokens ( 10.13 ms per token, 98.76 tokens per second) 3.49.786.744 I slot print_timing: id 0 | task 18401 | total time = 1446.26 ms / 423 tokens 3.49.786.745 I slot print_timing: id 0 | task 18401 | graphs reused = 17510 3.49.786.746 I slot print_timing: id 0 | task 18401 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.786.773 I slot release: id 0 | task 18401 | stop processing: n_tokens = 454, truncated = 0 3.49.804.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 229696216 3.49.804.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.49.901.060 I slot launch_slot_: id 0 | task 18535 | processing task, is_child = 0 3.50.799.819 I slot print_timing: id 0 | task 18535 | prompt eval time = 129.52 ms / 301 tokens ( 0.43 ms per token, 2324.02 tokens per second) 3.50.799.824 I slot print_timing: id 0 | task 18535 | eval time = 769.22 ms / 77 tokens ( 10.12 ms per token, 98.80 tokens per second) 3.50.799.825 I slot print_timing: id 0 | task 18535 | total time = 898.74 ms / 378 tokens 3.50.799.826 I slot print_timing: id 0 | task 18535 | graphs reused = 17585 3.50.799.827 I slot print_timing: id 0 | task 18535 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.799.854 I slot release: id 0 | task 18535 | stop processing: n_tokens = 409, truncated = 0 3.50.815.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 230709298 3.50.815.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 3.50.897.512 I slot launch_slot_: id 0 | task 18615 | processing task, is_child = 0 3.52.129.477 I slot print_timing: id 0 | task 18615 | prompt eval time = 131.03 ms / 303 tokens ( 0.43 ms per token, 2312.48 tokens per second) 3.52.129.482 I slot print_timing: id 0 | task 18615 | eval time = 1100.92 ms / 110 tokens ( 10.10 ms per token, 99.01 tokens per second) 3.52.129.483 I slot print_timing: id 0 | task 18615 | total time = 1231.95 ms / 413 tokens 3.52.129.484 I slot print_timing: id 0 | task 18615 | graphs reused = 17693 3.52.129.485 I slot print_timing: id 0 | task 18615 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.129.511 I slot release: id 0 | task 18615 | stop processing: n_tokens = 444, truncated = 0 3.52.158.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 232038955 3.52.158.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 3.52.237.392 I slot launch_slot_: id 0 | task 18728 | processing task, is_child = 0 3.52.628.725 I slot print_timing: id 0 | task 18728 | prompt eval time = 144.60 ms / 321 tokens ( 0.45 ms per token, 2219.98 tokens per second) 3.52.628.730 I slot print_timing: id 0 | task 18728 | eval time = 246.72 ms / 25 tokens ( 10.28 ms per token, 97.28 tokens per second) 3.52.628.731 I slot print_timing: id 0 | task 18728 | total time = 391.31 ms / 346 tokens 3.52.628.732 I slot print_timing: id 0 | task 18728 | graphs reused = 17716 3.52.628.733 I slot print_timing: id 0 | task 18728 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.628.761 I slot release: id 0 | task 18728 | stop processing: n_tokens = 377, truncated = 0 3.52.644.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 377, t_last = 232538204 3.52.644.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 3.52.720.770 I slot launch_slot_: id 0 | task 18756 | processing task, is_child = 0 3.53.285.654 I slot print_timing: id 0 | task 18756 | prompt eval time = 138.35 ms / 322 tokens ( 0.43 ms per token, 2327.40 tokens per second) 3.53.285.659 I slot print_timing: id 0 | task 18756 | eval time = 426.51 ms / 43 tokens ( 10.16 ms per token, 98.47 tokens per second) 3.53.285.660 I slot print_timing: id 0 | task 18756 | total time = 564.87 ms / 365 tokens 3.53.285.661 I slot print_timing: id 0 | task 18756 | graphs reused = 17757 3.53.285.661 I slot print_timing: id 0 | task 18756 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.285.690 I slot release: id 0 | task 18756 | stop processing: n_tokens = 396, truncated = 0 3.53.299.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 233195134 3.53.299.364 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.388 MiB) 3.53.365.454 I slot launch_slot_: id 0 | task 18802 | processing task, is_child = 0 3.53.839.525 I slot print_timing: id 0 | task 18802 | prompt eval time = 137.93 ms / 323 tokens ( 0.43 ms per token, 2341.72 tokens per second) 3.53.839.531 I slot print_timing: id 0 | task 18802 | eval time = 336.12 ms / 34 tokens ( 10.19 ms per token, 98.18 tokens per second) 3.53.839.532 I slot print_timing: id 0 | task 18802 | total time = 474.05 ms / 357 tokens 3.53.839.533 I slot print_timing: id 0 | task 18802 | graphs reused = 17789 3.53.839.533 I slot print_timing: id 0 | task 18802 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.839.565 I slot release: id 0 | task 18802 | stop processing: n_tokens = 388, truncated = 0 3.53.860.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 233749009 3.53.860.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.923 MiB) 3.53.928.339 I slot launch_slot_: id 0 | task 18839 | processing task, is_child = 0 3.57.073.842 I slot print_timing: id 0 | task 18839 | n_gen = 297, tg = 98.38 t/s, tg_3s = 98.72 t/s 3.58.981.395 I slot print_timing: id 0 | task 18839 | prompt eval time = 136.88 ms / 321 tokens ( 0.43 ms per token, 2345.19 tokens per second) 3.58.981.400 I slot print_timing: id 0 | task 18839 | eval time = 4916.16 ms / 484 tokens ( 10.18 ms per token, 98.25 tokens per second) 3.58.981.401 I slot print_timing: id 0 | task 18839 | total time = 5053.04 ms / 805 tokens 3.58.981.402 I slot print_timing: id 0 | task 18839 | graphs reused = 18269 3.58.981.403 I slot print_timing: id 0 | task 18839 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.981.432 I slot release: id 0 | task 18839 | stop processing: n_tokens = 836, truncated = 0 3.59.004.157 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 836, t_last = 238890876 3.59.004.222 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.013 MiB) 3.59.073.042 I slot launch_slot_: id 0 | task 19326 | processing task, is_child = 0 3.59.819.849 I slot print_timing: id 0 | task 19326 | prompt eval time = 139.50 ms / 322 tokens ( 0.43 ms per token, 2308.24 tokens per second) 3.59.819.855 I slot print_timing: id 0 | task 19326 | eval time = 607.29 ms / 61 tokens ( 10.12 ms per token, 98.80 tokens per second) 3.59.819.856 I slot print_timing: id 0 | task 19326 | total time = 746.79 ms / 383 tokens 3.59.819.857 I slot print_timing: id 0 | task 19326 | graphs reused = 18328 3.59.819.858 I slot print_timing: id 0 | task 19326 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.819.889 I slot release: id 0 | task 19326 | stop processing: n_tokens = 414, truncated = 0 3.59.844.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 239729333 3.59.844.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 3.59.912.259 I slot launch_slot_: id 0 | task 19390 | processing task, is_child = 0 4.00.507.759 I slot print_timing: id 0 | task 19390 | prompt eval time = 137.70 ms / 337 tokens ( 0.41 ms per token, 2447.28 tokens per second) 4.00.507.765 I slot print_timing: id 0 | task 19390 | eval time = 457.78 ms / 46 tokens ( 10.17 ms per token, 98.30 tokens per second) 4.00.507.766 I slot print_timing: id 0 | task 19390 | total time = 595.48 ms / 383 tokens 4.00.507.767 I slot print_timing: id 0 | task 19390 | graphs reused = 18372 4.00.507.767 I slot print_timing: id 0 | task 19390 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.507.796 I slot release: id 0 | task 19390 | stop processing: n_tokens = 414, truncated = 0 4.00.534.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 240417240 4.00.534.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.00.609.380 I slot launch_slot_: id 0 | task 19439 | processing task, is_child = 0 4.01.220.168 I slot print_timing: id 0 | task 19439 | prompt eval time = 137.52 ms / 325 tokens ( 0.42 ms per token, 2363.34 tokens per second) 4.01.220.174 I slot print_timing: id 0 | task 19439 | eval time = 473.25 ms / 47 tokens ( 10.29 ms per token, 97.20 tokens per second) 4.01.220.175 I slot print_timing: id 0 | task 19439 | total time = 610.77 ms / 372 tokens 4.01.220.176 I slot print_timing: id 0 | task 19439 | graphs reused = 18417 4.01.220.177 I slot print_timing: id 0 | task 19439 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.220.208 I slot release: id 0 | task 19439 | stop processing: n_tokens = 403, truncated = 0 4.01.237.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 241129652 4.01.237.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 4.01.310.210 I slot launch_slot_: id 0 | task 19489 | processing task, is_child = 0 4.01.860.450 I slot print_timing: id 0 | task 19489 | prompt eval time = 139.57 ms / 331 tokens ( 0.42 ms per token, 2371.50 tokens per second) 4.01.860.455 I slot print_timing: id 0 | task 19489 | eval time = 410.64 ms / 41 tokens ( 10.27 ms per token, 97.41 tokens per second) 4.01.860.457 I slot print_timing: id 0 | task 19489 | total time = 550.22 ms / 372 tokens 4.01.860.457 I slot print_timing: id 0 | task 19489 | graphs reused = 18456 4.01.860.458 I slot print_timing: id 0 | task 19489 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.860.491 I slot release: id 0 | task 19489 | stop processing: n_tokens = 403, truncated = 0 4.01.864.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 241769935 4.01.864.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.044 MiB) 4.01.937.864 I slot launch_slot_: id 0 | task 19533 | processing task, is_child = 0 4.02.436.490 I slot print_timing: id 0 | task 19533 | prompt eval time = 139.43 ms / 336 tokens ( 0.41 ms per token, 2409.86 tokens per second) 4.02.436.497 I slot print_timing: id 0 | task 19533 | eval time = 359.18 ms / 36 tokens ( 10.26 ms per token, 97.44 tokens per second) 4.02.436.498 I slot print_timing: id 0 | task 19533 | total time = 498.61 ms / 372 tokens 4.02.436.499 I slot print_timing: id 0 | task 19533 | graphs reused = 18490 4.02.436.500 I slot print_timing: id 0 | task 19533 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.436.533 I slot release: id 0 | task 19533 | stop processing: n_tokens = 403, truncated = 0 4.02.451.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 242345976 4.02.451.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.575 MiB) 4.02.521.720 I slot launch_slot_: id 0 | task 19572 | processing task, is_child = 0 4.02.846.747 I slot print_timing: id 0 | task 19572 | prompt eval time = 138.78 ms / 349 tokens ( 0.40 ms per token, 2514.84 tokens per second) 4.02.846.753 I slot print_timing: id 0 | task 19572 | eval time = 186.23 ms / 19 tokens ( 10.35 ms per token, 96.65 tokens per second) 4.02.846.754 I slot print_timing: id 0 | task 19572 | total time = 325.01 ms / 368 tokens 4.02.846.755 I slot print_timing: id 0 | task 19572 | graphs reused = 18507 4.02.846.755 I slot print_timing: id 0 | task 19572 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.846.786 I slot release: id 0 | task 19572 | stop processing: n_tokens = 399, truncated = 0 4.02.874.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 242756229 4.02.874.668 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.02.941.305 I slot launch_slot_: id 0 | task 19594 | processing task, is_child = 0 4.06.085.296 I slot print_timing: id 0 | task 19594 | n_gen = 297, tg = 98.45 t/s, tg_3s = 98.79 t/s 4.09.093.819 I slot print_timing: id 0 | task 19594 | n_gen = 593, tg = 98.42 t/s, tg_3s = 98.39 t/s 4.12.102.866 I slot print_timing: id 0 | task 19594 | n_gen = 886, tg = 98.07 t/s, tg_3s = 97.37 t/s 4.13.064.401 I slot print_timing: id 0 | task 19594 | prompt eval time = 137.48 ms / 336 tokens ( 0.41 ms per token, 2443.92 tokens per second) 4.13.064.406 I slot print_timing: id 0 | task 19594 | eval time = 9985.59 ms / 977 tokens ( 10.23 ms per token, 97.74 tokens per second) 4.13.064.407 I slot print_timing: id 0 | task 19594 | total time = 10123.08 ms / 1313 tokens 4.13.064.408 I slot print_timing: id 0 | task 19594 | graphs reused = 19478 4.13.064.409 I slot print_timing: id 0 | task 19594 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.064.439 I slot release: id 0 | task 19594 | stop processing: n_tokens = 1344, truncated = 0 4.13.084.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1344, t_last = 252973883 4.13.084.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.390 MiB) 4.13.165.112 I slot launch_slot_: id 0 | task 20574 | processing task, is_child = 0 4.16.312.178 I slot print_timing: id 0 | task 20574 | n_gen = 299, tg = 99.06 t/s, tg_3s = 99.40 t/s 4.18.886.319 I slot print_timing: id 0 | task 20574 | prompt eval time = 138.85 ms / 349 tokens ( 0.40 ms per token, 2513.43 tokens per second) 4.18.886.325 I slot print_timing: id 0 | task 20574 | eval time = 5582.34 ms / 554 tokens ( 10.09 ms per token, 99.06 tokens per second) 4.18.886.326 I slot print_timing: id 0 | task 20574 | total time = 5721.19 ms / 903 tokens 4.18.886.327 I slot print_timing: id 0 | task 20574 | graphs reused = 20028 4.18.886.327 I slot print_timing: id 0 | task 20574 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.886.356 I slot release: id 0 | task 20574 | stop processing: n_tokens = 934, truncated = 0 4.18.905.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 934, t_last = 258795800 4.18.905.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.18.977.643 I slot launch_slot_: id 0 | task 21131 | processing task, is_child = 0 4.19.583.701 I slot print_timing: id 0 | task 21131 | prompt eval time = 137.78 ms / 349 tokens ( 0.39 ms per token, 2532.97 tokens per second) 4.19.583.707 I slot print_timing: id 0 | task 21131 | eval time = 468.25 ms / 47 tokens ( 10.18 ms per token, 98.24 tokens per second) 4.19.583.708 I slot print_timing: id 0 | task 21131 | total time = 606.04 ms / 396 tokens 4.19.583.709 I slot print_timing: id 0 | task 21131 | graphs reused = 20073 4.19.583.710 I slot print_timing: id 0 | task 21131 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.583.745 I slot release: id 0 | task 21131 | stop processing: n_tokens = 427, truncated = 0 4.19.606.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 259493188 4.19.606.852 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.825 MiB) 4.19.665.581 I slot launch_slot_: id 0 | task 21181 | processing task, is_child = 0 4.20.479.598 I slot print_timing: id 0 | task 21181 | prompt eval time = 144.53 ms / 385 tokens ( 0.38 ms per token, 2663.75 tokens per second) 4.20.479.604 I slot print_timing: id 0 | task 21181 | eval time = 669.47 ms / 67 tokens ( 10.14 ms per token, 98.59 tokens per second) 4.20.479.606 I slot print_timing: id 0 | task 21181 | total time = 814.00 ms / 452 tokens 4.20.479.607 I slot print_timing: id 0 | task 21181 | graphs reused = 20138 4.20.479.608 I slot print_timing: id 0 | task 21181 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.479.641 I slot release: id 0 | task 21181 | stop processing: n_tokens = 483, truncated = 0 4.20.494.859 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 260389084 4.20.494.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.110 MiB) 4.20.564.530 I slot launch_slot_: id 0 | task 21251 | processing task, is_child = 0 4.21.270.181 I slot print_timing: id 0 | task 21251 | prompt eval time = 138.28 ms / 328 tokens ( 0.42 ms per token, 2372.03 tokens per second) 4.21.270.187 I slot print_timing: id 0 | task 21251 | eval time = 567.35 ms / 57 tokens ( 10.13 ms per token, 98.70 tokens per second) 4.21.270.188 I slot print_timing: id 0 | task 21251 | total time = 705.63 ms / 385 tokens 4.21.270.188 I slot print_timing: id 0 | task 21251 | graphs reused = 20193 4.21.270.189 I slot print_timing: id 0 | task 21251 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.270.216 I slot release: id 0 | task 21251 | stop processing: n_tokens = 416, truncated = 0