$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-Q8_0.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.097.372 I srv llama_server: initializing ... 0.00.097.378 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.097.490 I srv init_listene: The UI is disabled 0.00.097.492 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.097.570 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) 0.00.109.574 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-9B-GGUF\snapshots\3885219b6810b007914f3a7950a8d1b469d598a5\Qwen3.5-9B-Q8_0.gguf' 0.04.028.583 I cmn init: llama threadpool init, n_threads = 8 0.04.121.867 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.04.126.574 I srv llama_server: model loaded 0.04.126.580 I srv llama_server: listening on http://127.0.0.1:8089 0.04.556.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.556.438 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.497.118 I slot print_timing: id 0 | task 0 | prompt eval time = 137.77 ms / 368 tokens ( 0.37 ms per token, 2671.10 tokens per second) 0.05.497.124 I slot print_timing: id 0 | task 0 | eval time = 802.89 ms / 53 tokens ( 15.44 ms per token, 64.77 tokens per second) 0.05.497.125 I slot print_timing: id 0 | task 0 | total time = 940.66 ms / 421 tokens 0.05.497.131 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.497.132 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.497.163 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.500.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5401737 0.05.527.528 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.06.287.102 I slot print_timing: id 0 | task 56 | prompt eval time = 127.56 ms / 322 tokens ( 0.40 ms per token, 2524.26 tokens per second) 0.06.287.107 I slot print_timing: id 0 | task 56 | eval time = 632.00 ms / 42 tokens ( 15.41 ms per token, 64.87 tokens per second) 0.06.287.108 I slot print_timing: id 0 | task 56 | total time = 759.56 ms / 364 tokens 0.06.287.109 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.06.287.110 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.287.137 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.06.305.633 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 6191712 0.06.344.224 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.07.106.554 I slot print_timing: id 0 | task 101 | prompt eval time = 131.81 ms / 365 tokens ( 0.36 ms per token, 2769.14 tokens per second) 0.07.106.560 I slot print_timing: id 0 | task 101 | eval time = 630.50 ms / 42 tokens ( 15.38 ms per token, 65.03 tokens per second) 0.07.106.561 I slot print_timing: id 0 | task 101 | total time = 762.31 ms / 407 tokens 0.07.106.562 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.07.106.563 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.106.593 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.07.129.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 7011168 0.07.155.062 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.07.934.144 I slot print_timing: id 0 | task 146 | prompt eval time = 134.42 ms / 397 tokens ( 0.34 ms per token, 2953.43 tokens per second) 0.07.934.150 I slot print_timing: id 0 | task 146 | eval time = 644.64 ms / 43 tokens ( 15.35 ms per token, 65.15 tokens per second) 0.07.934.151 I slot print_timing: id 0 | task 146 | total time = 779.06 ms / 440 tokens 0.07.934.152 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.07.934.153 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.934.181 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.07.957.236 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 0.07.983.445 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.08.942.379 I slot print_timing: id 0 | task 192 | prompt eval time = 129.95 ms / 383 tokens ( 0.34 ms per token, 2947.29 tokens per second) 0.08.942.385 I slot print_timing: id 0 | task 192 | eval time = 828.96 ms / 55 tokens ( 15.35 ms per token, 65.14 tokens per second) 0.08.942.386 I slot print_timing: id 0 | task 192 | total time = 958.91 ms / 438 tokens 0.08.942.387 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.08.942.388 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.942.417 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.08.957.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8846991 0.08.983.896 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.09.942.720 I slot print_timing: id 0 | task 250 | prompt eval time = 132.67 ms / 372 tokens ( 0.36 ms per token, 2803.91 tokens per second) 0.09.942.727 I slot print_timing: id 0 | task 250 | eval time = 826.13 ms / 55 tokens ( 15.30 ms per token, 65.36 tokens per second) 0.09.942.728 I slot print_timing: id 0 | task 250 | total time = 958.81 ms / 427 tokens 0.09.942.729 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.09.942.730 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.942.758 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.09.956.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 9847332 0.09.983.646 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.10.959.010 I slot print_timing: id 0 | task 308 | prompt eval time = 149.61 ms / 422 tokens ( 0.35 ms per token, 2820.70 tokens per second) 0.10.959.016 I slot print_timing: id 0 | task 308 | eval time = 825.74 ms / 55 tokens ( 15.29 ms per token, 65.40 tokens per second) 0.10.959.017 I slot print_timing: id 0 | task 308 | total time = 975.34 ms / 477 tokens 0.10.959.018 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.10.959.018 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.959.047 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.10.987.584 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 10863621 0.11.015.285 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.12.261.156 I slot print_timing: id 0 | task 366 | prompt eval time = 154.21 ms / 470 tokens ( 0.33 ms per token, 3047.87 tokens per second) 0.12.261.162 I slot print_timing: id 0 | task 366 | eval time = 1091.64 ms / 72 tokens ( 15.38 ms per token, 65.04 tokens per second) 0.12.261.162 I slot print_timing: id 0 | task 366 | total time = 1245.85 ms / 542 tokens 0.12.261.163 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.12.261.164 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.261.195 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.12.280.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 12165769 0.12.307.193 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.13.137.245 I slot print_timing: id 0 | task 441 | prompt eval time = 125.81 ms / 345 tokens ( 0.36 ms per token, 2742.23 tokens per second) 0.13.137.252 I slot print_timing: id 0 | task 441 | eval time = 704.22 ms / 47 tokens ( 15.31 ms per token, 65.32 tokens per second) 0.13.137.253 I slot print_timing: id 0 | task 441 | total time = 830.03 ms / 392 tokens 0.13.137.253 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.13.137.254 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.137.281 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.13.164.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 13041855 0.13.189.757 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.13.931.547 I slot print_timing: id 0 | task 491 | prompt eval time = 127.59 ms / 364 tokens ( 0.35 ms per token, 2852.96 tokens per second) 0.13.931.553 I slot print_timing: id 0 | task 491 | eval time = 614.18 ms / 41 tokens ( 15.35 ms per token, 65.13 tokens per second) 0.13.931.554 I slot print_timing: id 0 | task 491 | total time = 741.77 ms / 405 tokens 0.13.931.555 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.13.931.556 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.931.584 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.13.936.078 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 13836158 0.13.962.502 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.15.063.203 I slot print_timing: id 0 | task 535 | prompt eval time = 132.02 ms / 376 tokens ( 0.35 ms per token, 2848.07 tokens per second) 0.15.063.209 I slot print_timing: id 0 | task 535 | eval time = 968.66 ms / 62 tokens ( 15.88 ms per token, 62.97 tokens per second) 0.15.063.210 I slot print_timing: id 0 | task 535 | total time = 1100.68 ms / 438 tokens 0.15.063.211 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.15.063.212 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.063.240 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.15.091.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 14967815 0.15.116.864 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.15.955.789 I slot print_timing: id 0 | task 600 | prompt eval time = 133.74 ms / 412 tokens ( 0.32 ms per token, 3080.67 tokens per second) 0.15.955.797 I slot print_timing: id 0 | task 600 | eval time = 705.16 ms / 47 tokens ( 15.33 ms per token, 65.23 tokens per second) 0.15.955.798 I slot print_timing: id 0 | task 600 | total time = 838.90 ms / 459 tokens 0.15.955.799 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.15.955.801 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.955.840 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.15.975.468 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 15860414 0.16.001.156 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.17.063.988 I slot print_timing: id 0 | task 650 | prompt eval time = 130.29 ms / 376 tokens ( 0.35 ms per token, 2885.87 tokens per second) 0.17.063.996 I slot print_timing: id 0 | task 650 | eval time = 932.52 ms / 62 tokens ( 15.29 ms per token, 65.41 tokens per second) 0.17.063.997 I slot print_timing: id 0 | task 650 | total time = 1062.81 ms / 438 tokens 0.17.063.998 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.17.063.999 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.064.030 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.17.078.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 16968604 0.17.104.337 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.18.018.650 I slot print_timing: id 0 | task 715 | prompt eval time = 132.33 ms / 378 tokens ( 0.35 ms per token, 2856.58 tokens per second) 0.18.018.657 I slot print_timing: id 0 | task 715 | eval time = 781.97 ms / 52 tokens ( 15.33 ms per token, 65.22 tokens per second) 0.18.018.658 I slot print_timing: id 0 | task 715 | total time = 914.29 ms / 430 tokens 0.18.018.659 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.18.018.660 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.018.689 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.18.040.408 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 17923263 0.18.066.291 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.19.099.322 I slot print_timing: id 0 | task 770 | prompt eval time = 131.81 ms / 367 tokens ( 0.36 ms per token, 2784.23 tokens per second) 0.19.099.328 I slot print_timing: id 0 | task 770 | eval time = 901.20 ms / 58 tokens ( 15.81 ms per token, 63.25 tokens per second) 0.19.099.329 I slot print_timing: id 0 | task 770 | total time = 1033.01 ms / 425 tokens 0.19.099.329 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.19.099.330 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.099.359 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.19.115.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 19003933 0.19.151.992 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.20.042.939 I slot print_timing: id 0 | task 831 | prompt eval time = 126.19 ms / 347 tokens ( 0.36 ms per token, 2749.73 tokens per second) 0.20.042.945 I slot print_timing: id 0 | task 831 | eval time = 764.73 ms / 51 tokens ( 15.29 ms per token, 65.38 tokens per second) 0.20.042.946 I slot print_timing: id 0 | task 831 | total time = 890.93 ms / 398 tokens 0.20.042.947 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.20.042.948 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.042.980 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.20.062.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 19947554 0.20.087.544 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.20.825.627 I slot print_timing: id 0 | task 885 | prompt eval time = 126.29 ms / 369 tokens ( 0.34 ms per token, 2921.78 tokens per second) 0.20.825.633 I slot print_timing: id 0 | task 885 | eval time = 611.77 ms / 41 tokens ( 15.29 ms per token, 65.38 tokens per second) 0.20.825.635 I slot print_timing: id 0 | task 885 | total time = 738.06 ms / 410 tokens 0.20.825.635 I slot print_timing: id 0 | task 885 | graphs reused = 844 0.20.825.636 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.825.667 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 0.20.829.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 20730241 0.20.864.366 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 0.21.600.709 I slot print_timing: id 0 | task 929 | prompt eval time = 124.72 ms / 352 tokens ( 0.35 ms per token, 2822.34 tokens per second) 0.21.600.715 I slot print_timing: id 0 | task 929 | eval time = 611.60 ms / 41 tokens ( 15.29 ms per token, 65.40 tokens per second) 0.21.600.716 I slot print_timing: id 0 | task 929 | total time = 736.32 ms / 393 tokens 0.21.600.717 I slot print_timing: id 0 | task 929 | graphs reused = 883 0.21.600.718 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.600.747 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 0.21.620.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 21505322 0.21.647.812 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 0.22.371.734 I slot print_timing: id 0 | task 973 | prompt eval time = 125.91 ms / 349 tokens ( 0.36 ms per token, 2771.76 tokens per second) 0.22.371.740 I slot print_timing: id 0 | task 973 | eval time = 597.99 ms / 40 tokens ( 15.33 ms per token, 65.22 tokens per second) 0.22.371.741 I slot print_timing: id 0 | task 973 | total time = 723.90 ms / 389 tokens 0.22.371.741 I slot print_timing: id 0 | task 973 | graphs reused = 921 0.22.371.743 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.371.770 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 0.22.396.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 22276344 0.22.424.186 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.23.536.709 I slot print_timing: id 0 | task 1016 | prompt eval time = 132.50 ms / 384 tokens ( 0.35 ms per token, 2898.18 tokens per second) 0.23.536.715 I slot print_timing: id 0 | task 1016 | eval time = 980.01 ms / 63 tokens ( 15.81 ms per token, 63.26 tokens per second) 0.23.536.717 I slot print_timing: id 0 | task 1016 | total time = 1112.51 ms / 447 tokens 0.23.536.717 I slot print_timing: id 0 | task 1016 | graphs reused = 982 0.23.536.718 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.536.748 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 0.23.551.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 23441322 0.23.577.857 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.24.517.906 I slot print_timing: id 0 | task 1082 | prompt eval time = 126.83 ms / 356 tokens ( 0.36 ms per token, 2806.91 tokens per second) 0.24.517.912 I slot print_timing: id 0 | task 1082 | eval time = 813.20 ms / 54 tokens ( 15.34 ms per token, 65.17 tokens per second) 0.24.517.913 I slot print_timing: id 0 | task 1082 | total time = 940.03 ms / 410 tokens 0.24.517.913 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 0.24.517.914 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.517.941 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 0.24.534.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 24422516 0.24.560.143 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 0.25.757.278 I slot print_timing: id 0 | task 1139 | prompt eval time = 137.58 ms / 410 tokens ( 0.34 ms per token, 2980.17 tokens per second) 0.25.757.285 I slot print_timing: id 0 | task 1139 | eval time = 1059.54 ms / 70 tokens ( 15.36 ms per token, 65.12 tokens per second) 0.25.757.286 I slot print_timing: id 0 | task 1139 | total time = 1197.11 ms / 480 tokens 0.25.757.286 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 0.25.757.287 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.757.318 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 0.25.775.222 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 25661892 0.25.801.280 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 0.26.811.659 I slot print_timing: id 0 | task 1212 | prompt eval time = 138.10 ms / 385 tokens ( 0.36 ms per token, 2787.88 tokens per second) 0.26.811.665 I slot print_timing: id 0 | task 1212 | eval time = 872.26 ms / 58 tokens ( 15.30 ms per token, 65.35 tokens per second) 0.26.811.666 I slot print_timing: id 0 | task 1212 | total time = 1010.36 ms / 443 tokens 0.26.811.666 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 0.26.811.667 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.811.695 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 0.26.835.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 26716269 0.26.861.270 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.28.071.208 I slot print_timing: id 0 | task 1273 | prompt eval time = 135.80 ms / 395 tokens ( 0.34 ms per token, 2908.60 tokens per second) 0.28.071.214 I slot print_timing: id 0 | task 1273 | eval time = 1074.11 ms / 71 tokens ( 15.34 ms per token, 65.17 tokens per second) 0.28.071.215 I slot print_timing: id 0 | task 1273 | total time = 1209.92 ms / 466 tokens 0.28.071.215 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.28.071.216 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.071.248 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.28.099.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 27975822 0.28.125.280 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.29.200.995 I slot print_timing: id 0 | task 1347 | prompt eval time = 137.71 ms / 430 tokens ( 0.32 ms per token, 3122.53 tokens per second) 0.29.201.001 I slot print_timing: id 0 | task 1347 | eval time = 937.99 ms / 62 tokens ( 15.38 ms per token, 65.03 tokens per second) 0.29.201.002 I slot print_timing: id 0 | task 1347 | total time = 1075.69 ms / 492 tokens 0.29.201.002 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 0.29.201.003 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.201.035 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 0.29.224.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 29105609 0.29.250.507 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 0.30.316.821 I slot print_timing: id 0 | task 1412 | prompt eval time = 133.94 ms / 392 tokens ( 0.34 ms per token, 2926.64 tokens per second) 0.30.316.827 I slot print_timing: id 0 | task 1412 | eval time = 932.35 ms / 62 tokens ( 15.28 ms per token, 65.43 tokens per second) 0.30.316.828 I slot print_timing: id 0 | task 1412 | total time = 1066.29 ms / 454 tokens 0.30.316.828 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 0.30.316.829 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.316.859 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 0.30.344.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 30221433 0.30.370.231 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 0.31.374.209 I slot print_timing: id 0 | task 1477 | prompt eval time = 128.46 ms / 350 tokens ( 0.37 ms per token, 2724.54 tokens per second) 0.31.374.214 I slot print_timing: id 0 | task 1477 | eval time = 875.50 ms / 58 tokens ( 15.36 ms per token, 65.11 tokens per second) 0.31.374.215 I slot print_timing: id 0 | task 1477 | total time = 1003.96 ms / 408 tokens 0.31.374.216 I slot print_timing: id 0 | task 1477 | graphs reused = 1403 0.31.374.217 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.374.243 I slot release: id 0 | task 1477 | stop processing: n_tokens = 407, truncated = 0 0.31.402.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 31278817 0.31.427.601 I slot launch_slot_: id 0 | task 1538 | processing task, is_child = 0 0.32.490.320 I slot print_timing: id 0 | task 1538 | prompt eval time = 140.14 ms / 380 tokens ( 0.37 ms per token, 2711.63 tokens per second) 0.32.490.326 I slot print_timing: id 0 | task 1538 | eval time = 922.56 ms / 61 tokens ( 15.38 ms per token, 65.04 tokens per second) 0.32.490.328 I slot print_timing: id 0 | task 1538 | total time = 1062.70 ms / 441 tokens 0.32.490.329 I slot print_timing: id 0 | task 1538 | graphs reused = 1462 0.32.490.329 I slot print_timing: id 0 | task 1538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.490.360 I slot release: id 0 | task 1538 | stop processing: n_tokens = 440, truncated = 0 0.32.511.779 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 32394935 0.32.537.839 I slot launch_slot_: id 0 | task 1602 | processing task, is_child = 0 0.33.909.050 I slot print_timing: id 0 | task 1602 | prompt eval time = 135.89 ms / 410 tokens ( 0.33 ms per token, 3017.10 tokens per second) 0.33.909.056 I slot print_timing: id 0 | task 1602 | eval time = 1235.30 ms / 80 tokens ( 15.64 ms per token, 63.95 tokens per second) 0.33.909.057 I slot print_timing: id 0 | task 1602 | total time = 1371.19 ms / 490 tokens 0.33.909.058 I slot print_timing: id 0 | task 1602 | graphs reused = 1540 0.33.909.058 I slot print_timing: id 0 | task 1602 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.909.087 I slot release: id 0 | task 1602 | stop processing: n_tokens = 489, truncated = 0 0.33.927.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 33813661 0.33.957.087 I slot launch_slot_: id 0 | task 1685 | processing task, is_child = 0 0.35.114.931 I slot print_timing: id 0 | task 1685 | prompt eval time = 133.34 ms / 387 tokens ( 0.34 ms per token, 2902.42 tokens per second) 0.35.114.937 I slot print_timing: id 0 | task 1685 | eval time = 1024.49 ms / 68 tokens ( 15.29 ms per token, 65.40 tokens per second) 0.35.114.938 I slot print_timing: id 0 | task 1685 | total time = 1157.83 ms / 455 tokens 0.35.114.939 I slot print_timing: id 0 | task 1685 | graphs reused = 1606 0.35.114.940 I slot print_timing: id 0 | task 1685 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.114.969 I slot release: id 0 | task 1685 | stop processing: n_tokens = 454, truncated = 0 0.35.128.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 35019544 0.35.156.630 I slot launch_slot_: id 0 | task 1756 | processing task, is_child = 0 0.36.170.698 I slot print_timing: id 0 | task 1756 | prompt eval time = 126.78 ms / 358 tokens ( 0.35 ms per token, 2823.90 tokens per second) 0.36.170.705 I slot print_timing: id 0 | task 1756 | eval time = 887.27 ms / 59 tokens ( 15.30 ms per token, 65.37 tokens per second) 0.36.170.706 I slot print_timing: id 0 | task 1756 | total time = 1014.05 ms / 417 tokens 0.36.170.706 I slot print_timing: id 0 | task 1756 | graphs reused = 1663 0.36.170.707 I slot print_timing: id 0 | task 1756 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.170.736 I slot release: id 0 | task 1756 | stop processing: n_tokens = 416, truncated = 0 0.36.189.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 36075310 0.36.215.057 I slot launch_slot_: id 0 | task 1818 | processing task, is_child = 0 0.37.217.833 I slot print_timing: id 0 | task 1818 | prompt eval time = 128.47 ms / 359 tokens ( 0.36 ms per token, 2794.32 tokens per second) 0.37.217.839 I slot print_timing: id 0 | task 1818 | eval time = 874.28 ms / 56 tokens ( 15.90 ms per token, 62.91 tokens per second) 0.37.217.840 I slot print_timing: id 0 | task 1818 | total time = 1002.76 ms / 415 tokens 0.37.217.841 I slot print_timing: id 0 | task 1818 | graphs reused = 1717 0.37.217.841 I slot print_timing: id 0 | task 1818 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.217.868 I slot release: id 0 | task 1818 | stop processing: n_tokens = 414, truncated = 0 0.37.232.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 37122442 0.37.258.558 I slot launch_slot_: id 0 | task 1877 | processing task, is_child = 0 0.38.307.999 I slot print_timing: id 0 | task 1877 | prompt eval time = 132.22 ms / 387 tokens ( 0.34 ms per token, 2926.96 tokens per second) 0.38.308.005 I slot print_timing: id 0 | task 1877 | eval time = 917.20 ms / 61 tokens ( 15.29 ms per token, 65.42 tokens per second) 0.38.308.006 I slot print_timing: id 0 | task 1877 | total time = 1049.42 ms / 448 tokens 0.38.308.006 I slot print_timing: id 0 | task 1877 | graphs reused = 1776 0.38.308.007 I slot print_timing: id 0 | task 1877 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.308.036 I slot release: id 0 | task 1877 | stop processing: n_tokens = 447, truncated = 0 0.38.325.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 38212610 0.38.352.599 I slot launch_slot_: id 0 | task 1941 | processing task, is_child = 0 0.39.433.981 I slot print_timing: id 0 | task 1941 | prompt eval time = 136.01 ms / 410 tokens ( 0.33 ms per token, 3014.55 tokens per second) 0.39.433.987 I slot print_timing: id 0 | task 1941 | eval time = 945.35 ms / 61 tokens ( 15.76 ms per token, 63.47 tokens per second) 0.39.433.988 I slot print_timing: id 0 | task 1941 | total time = 1081.36 ms / 471 tokens 0.39.433.989 I slot print_timing: id 0 | task 1941 | graphs reused = 1835 0.39.433.989 I slot print_timing: id 0 | task 1941 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.434.020 I slot release: id 0 | task 1941 | stop processing: n_tokens = 470, truncated = 0 0.39.461.728 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 39338594 0.39.493.602 I slot launch_slot_: id 0 | task 2005 | processing task, is_child = 0 0.40.370.550 I slot print_timing: id 0 | task 2005 | prompt eval time = 126.00 ms / 351 tokens ( 0.36 ms per token, 2785.60 tokens per second) 0.40.370.556 I slot print_timing: id 0 | task 2005 | eval time = 750.92 ms / 50 tokens ( 15.32 ms per token, 65.25 tokens per second) 0.40.370.557 I slot print_timing: id 0 | task 2005 | total time = 876.93 ms / 401 tokens 0.40.370.558 I slot print_timing: id 0 | task 2005 | graphs reused = 1883 0.40.370.559 I slot print_timing: id 0 | task 2005 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.370.598 I slot release: id 0 | task 2005 | stop processing: n_tokens = 400, truncated = 0 0.40.397.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 40275173 0.40.425.462 I slot launch_slot_: id 0 | task 2058 | processing task, is_child = 0 0.43.566.552 I slot print_timing: id 0 | task 2058 | n_gen = 198, tg = 65.48 t/s, tg_3s = 65.82 t/s 0.43.961.613 I slot print_timing: id 0 | task 2058 | prompt eval time = 132.75 ms / 393 tokens ( 0.34 ms per token, 2960.50 tokens per second) 0.43.961.618 I slot print_timing: id 0 | task 2058 | eval time = 3403.38 ms / 224 tokens ( 15.26 ms per token, 65.52 tokens per second) 0.43.961.620 I slot print_timing: id 0 | task 2058 | total time = 3536.13 ms / 617 tokens 0.43.961.620 I slot print_timing: id 0 | task 2058 | graphs reused = 2104 0.43.961.622 I slot print_timing: id 0 | task 2058 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.961.651 I slot release: id 0 | task 2058 | stop processing: n_tokens = 616, truncated = 0 0.43.983.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 43866226 0.44.017.066 I slot launch_slot_: id 0 | task 2285 | processing task, is_child = 0 0.44.620.309 I slot print_timing: id 0 | task 2285 | prompt eval time = 126.10 ms / 321 tokens ( 0.39 ms per token, 2545.54 tokens per second) 0.44.620.314 I slot print_timing: id 0 | task 2285 | eval time = 477.12 ms / 32 tokens ( 15.39 ms per token, 64.97 tokens per second) 0.44.620.315 I slot print_timing: id 0 | task 2285 | total time = 603.22 ms / 353 tokens 0.44.620.316 I slot print_timing: id 0 | task 2285 | graphs reused = 2134 0.44.620.317 I slot print_timing: id 0 | task 2285 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.620.342 I slot release: id 0 | task 2285 | stop processing: n_tokens = 352, truncated = 0 0.44.624.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 44524916 0.44.661.226 I slot launch_slot_: id 0 | task 2320 | processing task, is_child = 0 0.46.069.644 I slot print_timing: id 0 | task 2320 | prompt eval time = 126.72 ms / 330 tokens ( 0.38 ms per token, 2604.17 tokens per second) 0.46.069.649 I slot print_timing: id 0 | task 2320 | eval time = 1281.68 ms / 85 tokens ( 15.26 ms per token, 65.54 tokens per second) 0.46.069.650 I slot print_timing: id 0 | task 2320 | total time = 1408.40 ms / 415 tokens 0.46.069.651 I slot print_timing: id 0 | task 2320 | graphs reused = 2217 0.46.069.652 I slot print_timing: id 0 | task 2320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.069.680 I slot release: id 0 | task 2320 | stop processing: n_tokens = 414, truncated = 0 0.46.091.665 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 45974254 0.46.127.727 I slot launch_slot_: id 0 | task 2408 | processing task, is_child = 0 0.46.730.656 I slot print_timing: id 0 | task 2408 | prompt eval time = 127.16 ms / 341 tokens ( 0.37 ms per token, 2681.75 tokens per second) 0.46.730.662 I slot print_timing: id 0 | task 2408 | eval time = 475.75 ms / 32 tokens ( 15.35 ms per token, 65.16 tokens per second) 0.46.730.663 I slot print_timing: id 0 | task 2408 | total time = 602.91 ms / 373 tokens 0.46.730.664 I slot print_timing: id 0 | task 2408 | graphs reused = 2247 0.46.730.665 I slot print_timing: id 0 | task 2408 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.730.692 I slot release: id 0 | task 2408 | stop processing: n_tokens = 372, truncated = 0 0.46.745.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 46635266 0.46.780.785 I slot launch_slot_: id 0 | task 2443 | processing task, is_child = 0 0.47.625.358 I slot print_timing: id 0 | task 2443 | prompt eval time = 125.08 ms / 338 tokens ( 0.37 ms per token, 2702.25 tokens per second) 0.47.625.364 I slot print_timing: id 0 | task 2443 | eval time = 719.48 ms / 48 tokens ( 15.31 ms per token, 65.33 tokens per second) 0.47.625.365 I slot print_timing: id 0 | task 2443 | total time = 844.56 ms / 386 tokens 0.47.625.366 I slot print_timing: id 0 | task 2443 | graphs reused = 2293 0.47.625.367 I slot print_timing: id 0 | task 2443 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.625.394 I slot release: id 0 | task 2443 | stop processing: n_tokens = 385, truncated = 0 0.47.648.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 47529968 0.47.683.542 I slot launch_slot_: id 0 | task 2494 | processing task, is_child = 0 0.48.658.799 I slot print_timing: id 0 | task 2494 | prompt eval time = 134.49 ms / 395 tokens ( 0.34 ms per token, 2936.96 tokens per second) 0.48.658.804 I slot print_timing: id 0 | task 2494 | eval time = 840.74 ms / 56 tokens ( 15.29 ms per token, 65.42 tokens per second) 0.48.658.805 I slot print_timing: id 0 | task 2494 | total time = 975.23 ms / 451 tokens 0.48.658.806 I slot print_timing: id 0 | task 2494 | graphs reused = 2347 0.48.658.807 I slot print_timing: id 0 | task 2494 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.658.852 I slot release: id 0 | task 2494 | stop processing: n_tokens = 450, truncated = 0 0.48.676.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 48563426 0.48.712.523 I slot launch_slot_: id 0 | task 2553 | processing task, is_child = 0 0.50.158.225 I slot print_timing: id 0 | task 2553 | prompt eval time = 188.20 ms / 528 tokens ( 0.36 ms per token, 2805.47 tokens per second) 0.50.158.231 I slot print_timing: id 0 | task 2553 | eval time = 1257.48 ms / 83 tokens ( 15.34 ms per token, 65.21 tokens per second) 0.50.158.232 I slot print_timing: id 0 | task 2553 | total time = 1445.68 ms / 611 tokens 0.50.158.233 I slot print_timing: id 0 | task 2553 | graphs reused = 2428 0.50.158.233 I slot print_timing: id 0 | task 2553 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.158.267 I slot release: id 0 | task 2553 | stop processing: n_tokens = 610, truncated = 0 0.50.162.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 50062841 0.50.208.391 I slot launch_slot_: id 0 | task 2640 | processing task, is_child = 0 0.51.037.133 I slot print_timing: id 0 | task 2640 | prompt eval time = 152.51 ms / 331 tokens ( 0.46 ms per token, 2170.29 tokens per second) 0.51.037.139 I slot print_timing: id 0 | task 2640 | eval time = 676.21 ms / 45 tokens ( 15.37 ms per token, 65.07 tokens per second) 0.51.037.140 I slot print_timing: id 0 | task 2640 | total time = 828.72 ms / 376 tokens 0.51.037.141 I slot print_timing: id 0 | task 2640 | graphs reused = 2471 0.51.037.142 I slot print_timing: id 0 | task 2640 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.037.170 I slot release: id 0 | task 2640 | stop processing: n_tokens = 387, truncated = 0 0.51.053.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 50941745 0.51.116.127 I slot launch_slot_: id 0 | task 2688 | processing task, is_child = 0 0.52.070.726 I slot print_timing: id 0 | task 2688 | prompt eval time = 156.74 ms / 362 tokens ( 0.43 ms per token, 2309.60 tokens per second) 0.52.070.732 I slot print_timing: id 0 | task 2688 | eval time = 797.84 ms / 53 tokens ( 15.34 ms per token, 65.18 tokens per second) 0.52.070.733 I slot print_timing: id 0 | task 2688 | total time = 954.58 ms / 415 tokens 0.52.070.733 I slot print_timing: id 0 | task 2688 | graphs reused = 2522 0.52.070.734 I slot print_timing: id 0 | task 2688 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.070.763 I slot release: id 0 | task 2688 | stop processing: n_tokens = 426, truncated = 0 0.52.087.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 51975337 0.52.133.152 I slot launch_slot_: id 0 | task 2744 | processing task, is_child = 0 0.53.331.512 I slot print_timing: id 0 | task 2744 | prompt eval time = 158.79 ms / 419 tokens ( 0.38 ms per token, 2638.67 tokens per second) 0.53.331.518 I slot print_timing: id 0 | task 2744 | eval time = 1039.55 ms / 69 tokens ( 15.29 ms per token, 65.41 tokens per second) 0.53.331.519 I slot print_timing: id 0 | task 2744 | total time = 1198.34 ms / 488 tokens 0.53.331.520 I slot print_timing: id 0 | task 2744 | graphs reused = 2589 0.53.331.521 I slot print_timing: id 0 | task 2744 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.331.554 I slot release: id 0 | task 2744 | stop processing: n_tokens = 499, truncated = 0 0.53.359.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 53236128 0.53.405.048 I slot launch_slot_: id 0 | task 2816 | processing task, is_child = 0 0.54.236.324 I slot print_timing: id 0 | task 2816 | prompt eval time = 171.82 ms / 423 tokens ( 0.41 ms per token, 2461.92 tokens per second) 0.54.236.331 I slot print_timing: id 0 | task 2816 | eval time = 659.44 ms / 44 tokens ( 15.34 ms per token, 65.21 tokens per second) 0.54.236.333 I slot print_timing: id 0 | task 2816 | total time = 831.25 ms / 467 tokens 0.54.236.333 I slot print_timing: id 0 | task 2816 | graphs reused = 2631 0.54.236.334 I slot print_timing: id 0 | task 2816 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.236.369 I slot release: id 0 | task 2816 | stop processing: n_tokens = 478, truncated = 0 0.54.239.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 54140944 0.54.287.177 I slot launch_slot_: id 0 | task 2863 | processing task, is_child = 0 0.55.081.386 I slot print_timing: id 0 | task 2863 | prompt eval time = 150.97 ms / 341 tokens ( 0.44 ms per token, 2258.74 tokens per second) 0.55.081.392 I slot print_timing: id 0 | task 2863 | eval time = 643.22 ms / 43 tokens ( 15.31 ms per token, 65.30 tokens per second) 0.55.081.393 I slot print_timing: id 0 | task 2863 | total time = 794.19 ms / 384 tokens 0.55.081.394 I slot print_timing: id 0 | task 2863 | graphs reused = 2672 0.55.081.394 I slot print_timing: id 0 | task 2863 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.081.422 I slot release: id 0 | task 2863 | stop processing: n_tokens = 395, truncated = 0 0.55.108.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 54985996 0.55.156.067 I slot launch_slot_: id 0 | task 2909 | processing task, is_child = 0 0.56.013.435 I slot print_timing: id 0 | task 2909 | prompt eval time = 153.25 ms / 356 tokens ( 0.43 ms per token, 2323.05 tokens per second) 0.56.013.441 I slot print_timing: id 0 | task 2909 | eval time = 704.10 ms / 47 tokens ( 15.31 ms per token, 65.33 tokens per second) 0.56.013.442 I slot print_timing: id 0 | task 2909 | total time = 857.35 ms / 403 tokens 0.56.013.443 I slot print_timing: id 0 | task 2909 | graphs reused = 2717 0.56.013.444 I slot print_timing: id 0 | task 2909 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.013.471 I slot release: id 0 | task 2909 | stop processing: n_tokens = 414, truncated = 0 0.56.029.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 55918046 0.56.029.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.56.087.879 I slot launch_slot_: id 0 | task 2959 | processing task, is_child = 0 0.56.934.590 I slot print_timing: id 0 | task 2959 | prompt eval time = 155.48 ms / 362 tokens ( 0.43 ms per token, 2328.27 tokens per second) 0.56.934.597 I slot print_timing: id 0 | task 2959 | eval time = 691.21 ms / 46 tokens ( 15.36 ms per token, 65.10 tokens per second) 0.56.934.598 I slot print_timing: id 0 | task 2959 | total time = 846.69 ms / 408 tokens 0.56.934.599 I slot print_timing: id 0 | task 2959 | graphs reused = 2761 0.56.934.600 I slot print_timing: id 0 | task 2959 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.934.632 I slot release: id 0 | task 2959 | stop processing: n_tokens = 419, truncated = 0 0.56.962.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 56839207 0.56.962.090 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.57.020.220 I slot launch_slot_: id 0 | task 3008 | processing task, is_child = 0 0.58.209.583 I slot print_timing: id 0 | task 3008 | prompt eval time = 164.78 ms / 391 tokens ( 0.42 ms per token, 2372.79 tokens per second) 0.58.209.589 I slot print_timing: id 0 | task 3008 | eval time = 1024.56 ms / 68 tokens ( 15.29 ms per token, 65.39 tokens per second) 0.58.209.590 I slot print_timing: id 0 | task 3008 | total time = 1189.34 ms / 459 tokens 0.58.209.591 I slot print_timing: id 0 | task 3008 | graphs reused = 2827 0.58.209.592 I slot print_timing: id 0 | task 3008 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.209.623 I slot release: id 0 | task 3008 | stop processing: n_tokens = 470, truncated = 0 0.58.225.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 58114197 0.58.226.049 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.58.285.072 I slot launch_slot_: id 0 | task 3079 | processing task, is_child = 0 0.59.245.414 I slot print_timing: id 0 | task 3079 | prompt eval time = 149.64 ms / 343 tokens ( 0.44 ms per token, 2292.17 tokens per second) 0.59.245.420 I slot print_timing: id 0 | task 3079 | eval time = 810.68 ms / 54 tokens ( 15.30 ms per token, 65.38 tokens per second) 0.59.245.421 I slot print_timing: id 0 | task 3079 | total time = 960.32 ms / 397 tokens 0.59.245.422 I slot print_timing: id 0 | task 3079 | graphs reused = 2879 0.59.245.423 I slot print_timing: id 0 | task 3079 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.245.451 I slot release: id 0 | task 3079 | stop processing: n_tokens = 408, truncated = 0 0.59.271.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 59150025 0.59.271.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.59.281.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.59.345.086 I slot launch_slot_: id 0 | task 3136 | processing task, is_child = 0 1.00.192.227 I slot print_timing: id 0 | task 3136 | prompt eval time = 158.17 ms / 401 tokens ( 0.39 ms per token, 2535.29 tokens per second) 1.00.192.233 I slot print_timing: id 0 | task 3136 | eval time = 688.95 ms / 46 tokens ( 15.31 ms per token, 65.32 tokens per second) 1.00.192.234 I slot print_timing: id 0 | task 3136 | total time = 847.12 ms / 447 tokens 1.00.192.234 I slot print_timing: id 0 | task 3136 | graphs reused = 2923 1.00.192.235 I slot print_timing: id 0 | task 3136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.192.267 I slot release: id 0 | task 3136 | stop processing: n_tokens = 458, truncated = 0 1.00.206.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 60096842 1.00.207.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 1.00.260.898 I slot launch_slot_: id 0 | task 3185 | processing task, is_child = 0 1.01.436.174 I slot print_timing: id 0 | task 3185 | prompt eval time = 151.18 ms / 355 tokens ( 0.43 ms per token, 2348.18 tokens per second) 1.01.436.179 I slot print_timing: id 0 | task 3185 | eval time = 1024.08 ms / 68 tokens ( 15.28 ms per token, 65.42 tokens per second) 1.01.436.180 I slot print_timing: id 0 | task 3185 | total time = 1175.26 ms / 423 tokens 1.01.436.181 I slot print_timing: id 0 | task 3185 | graphs reused = 2989 1.01.436.182 I slot print_timing: id 0 | task 3185 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.436.210 I slot release: id 0 | task 3185 | stop processing: n_tokens = 434, truncated = 0 1.01.453.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 61340785 1.01.453.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 1.01.503.101 I slot launch_slot_: id 0 | task 3256 | processing task, is_child = 0 1.02.543.060 I slot print_timing: id 0 | task 3256 | prompt eval time = 150.91 ms / 351 tokens ( 0.43 ms per token, 2325.94 tokens per second) 1.02.543.066 I slot print_timing: id 0 | task 3256 | eval time = 889.03 ms / 57 tokens ( 15.88 ms per token, 62.99 tokens per second) 1.02.543.067 I slot print_timing: id 0 | task 3256 | total time = 1039.94 ms / 408 tokens 1.02.543.068 I slot print_timing: id 0 | task 3256 | graphs reused = 3044 1.02.543.068 I slot print_timing: id 0 | task 3256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.543.098 I slot release: id 0 | task 3256 | stop processing: n_tokens = 419, truncated = 0 1.02.564.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 62447672 1.02.564.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 1.02.575.106 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 1.02.634.708 I slot launch_slot_: id 0 | task 3316 | processing task, is_child = 0 1.04.223.957 I slot print_timing: id 0 | task 3316 | prompt eval time = 176.92 ms / 475 tokens ( 0.37 ms per token, 2684.77 tokens per second) 1.04.223.964 I slot print_timing: id 0 | task 3316 | eval time = 1412.31 ms / 93 tokens ( 15.35 ms per token, 65.14 tokens per second) 1.04.223.965 I slot print_timing: id 0 | task 3316 | total time = 1589.23 ms / 568 tokens 1.04.223.965 I slot print_timing: id 0 | task 3316 | graphs reused = 3134 1.04.223.966 I slot print_timing: id 0 | task 3316 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.223.999 I slot release: id 0 | task 3316 | stop processing: n_tokens = 579, truncated = 0 1.04.246.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 64128573 1.04.246.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 1.04.302.117 I slot launch_slot_: id 0 | task 3412 | processing task, is_child = 0 1.06.082.510 I slot print_timing: id 0 | task 3412 | prompt eval time = 173.53 ms / 440 tokens ( 0.39 ms per token, 2535.54 tokens per second) 1.06.082.515 I slot print_timing: id 0 | task 3412 | eval time = 1606.84 ms / 106 tokens ( 15.30 ms per token, 65.35 tokens per second) 1.06.082.516 I slot print_timing: id 0 | task 3412 | total time = 1780.37 ms / 546 tokens 1.06.082.517 I slot print_timing: id 0 | task 3412 | graphs reused = 3237 1.06.082.518 I slot print_timing: id 0 | task 3412 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.082.549 I slot release: id 0 | task 3412 | stop processing: n_tokens = 557, truncated = 0 1.06.097.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 65987123 1.06.097.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 1.06.157.209 I slot launch_slot_: id 0 | task 3521 | processing task, is_child = 0 1.07.136.158 I slot print_timing: id 0 | task 3521 | prompt eval time = 151.34 ms / 345 tokens ( 0.44 ms per token, 2279.64 tokens per second) 1.07.136.164 I slot print_timing: id 0 | task 3521 | eval time = 827.59 ms / 55 tokens ( 15.33 ms per token, 65.25 tokens per second) 1.07.136.165 I slot print_timing: id 0 | task 3521 | total time = 978.93 ms / 400 tokens 1.07.136.165 I slot print_timing: id 0 | task 3521 | graphs reused = 3290 1.07.136.166 I slot print_timing: id 0 | task 3521 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.136.195 I slot release: id 0 | task 3521 | stop processing: n_tokens = 411, truncated = 0 1.07.158.228 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 67040770 1.07.158.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 1.07.168.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 1.07.234.058 I slot launch_slot_: id 0 | task 3579 | processing task, is_child = 0 1.08.230.260 I slot print_timing: id 0 | task 3579 | prompt eval time = 155.84 ms / 382 tokens ( 0.41 ms per token, 2451.28 tokens per second) 1.08.230.267 I slot print_timing: id 0 | task 3579 | eval time = 840.34 ms / 55 tokens ( 15.56 ms per token, 64.26 tokens per second) 1.08.230.268 I slot print_timing: id 0 | task 3579 | total time = 996.18 ms / 437 tokens 1.08.230.269 I slot print_timing: id 0 | task 3579 | graphs reused = 3343 1.08.230.270 I slot print_timing: id 0 | task 3579 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.230.306 I slot release: id 0 | task 3579 | stop processing: n_tokens = 448, truncated = 0 1.08.247.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 68134880 1.08.247.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 1.08.303.034 I slot launch_slot_: id 0 | task 3637 | processing task, is_child = 0 1.09.132.120 I slot print_timing: id 0 | task 3637 | prompt eval time = 150.96 ms / 337 tokens ( 0.45 ms per token, 2232.38 tokens per second) 1.09.132.126 I slot print_timing: id 0 | task 3637 | eval time = 678.11 ms / 45 tokens ( 15.41 ms per token, 64.89 tokens per second) 1.09.132.127 I slot print_timing: id 0 | task 3637 | total time = 829.07 ms / 382 tokens 1.09.132.128 I slot print_timing: id 0 | task 3637 | graphs reused = 3386 1.09.132.128 I slot print_timing: id 0 | task 3637 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.132.157 I slot release: id 0 | task 3637 | stop processing: n_tokens = 393, truncated = 0 1.09.159.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 69036732 1.09.159.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 1.09.222.514 I slot launch_slot_: id 0 | task 3685 | processing task, is_child = 0 1.10.469.249 I slot print_timing: id 0 | task 3685 | prompt eval time = 159.82 ms / 402 tokens ( 0.40 ms per token, 2515.28 tokens per second) 1.10.469.255 I slot print_timing: id 0 | task 3685 | eval time = 1086.89 ms / 70 tokens ( 15.75 ms per token, 63.48 tokens per second) 1.10.469.256 I slot print_timing: id 0 | task 3685 | total time = 1246.71 ms / 472 tokens 1.10.469.257 I slot print_timing: id 0 | task 3685 | graphs reused = 3454 1.10.469.258 I slot print_timing: id 0 | task 3685 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.469.295 I slot release: id 0 | task 3685 | stop processing: n_tokens = 483, truncated = 0 1.10.486.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 70373869 1.10.487.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 1.10.496.820 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 1.10.561.123 I slot launch_slot_: id 0 | task 3758 | processing task, is_child = 0 1.11.614.350 I slot print_timing: id 0 | task 3758 | prompt eval time = 193.48 ms / 549 tokens ( 0.35 ms per token, 2837.53 tokens per second) 1.11.614.357 I slot print_timing: id 0 | task 3758 | eval time = 859.73 ms / 57 tokens ( 15.35 ms per token, 65.14 tokens per second) 1.11.614.358 I slot print_timing: id 0 | task 3758 | total time = 1053.20 ms / 606 tokens 1.11.614.359 I slot print_timing: id 0 | task 3758 | graphs reused = 3509 1.11.614.359 I slot print_timing: id 0 | task 3758 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.614.393 I slot release: id 0 | task 3758 | stop processing: n_tokens = 617, truncated = 0 1.11.638.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 71518967 1.11.638.548 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 1.11.705.900 I slot launch_slot_: id 0 | task 3819 | processing task, is_child = 0 1.12.786.210 I slot print_timing: id 0 | task 3819 | prompt eval time = 205.65 ms / 616 tokens ( 0.33 ms per token, 2995.42 tokens per second) 1.12.786.215 I slot print_timing: id 0 | task 3819 | eval time = 874.64 ms / 58 tokens ( 15.34 ms per token, 65.17 tokens per second) 1.12.786.217 I slot print_timing: id 0 | task 3819 | total time = 1080.29 ms / 674 tokens 1.12.786.218 I slot print_timing: id 0 | task 3819 | graphs reused = 3565 1.12.786.219 I slot print_timing: id 0 | task 3819 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.786.258 I slot release: id 0 | task 3819 | stop processing: n_tokens = 685, truncated = 0 1.12.810.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 72690832 1.12.810.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 1.12.820.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 1.12.897.358 I slot launch_slot_: id 0 | task 3881 | processing task, is_child = 0 1.14.050.185 I slot print_timing: id 0 | task 3881 | prompt eval time = 218.10 ms / 665 tokens ( 0.33 ms per token, 3049.00 tokens per second) 1.14.050.190 I slot print_timing: id 0 | task 3881 | eval time = 934.70 ms / 62 tokens ( 15.32 ms per token, 65.26 tokens per second) 1.14.050.191 I slot print_timing: id 0 | task 3881 | total time = 1152.81 ms / 727 tokens 1.14.050.192 I slot print_timing: id 0 | task 3881 | graphs reused = 3625 1.14.050.193 I slot print_timing: id 0 | task 3881 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.050.231 I slot release: id 0 | task 3881 | stop processing: n_tokens = 738, truncated = 0 1.14.075.631 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 73954806 1.14.075.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 1.14.085.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 1.14.172.609 I slot launch_slot_: id 0 | task 3947 | processing task, is_child = 0 1.15.215.784 I slot print_timing: id 0 | task 3947 | prompt eval time = 215.27 ms / 645 tokens ( 0.33 ms per token, 2996.24 tokens per second) 1.15.215.790 I slot print_timing: id 0 | task 3947 | eval time = 827.88 ms / 55 tokens ( 15.33 ms per token, 65.23 tokens per second) 1.15.215.791 I slot print_timing: id 0 | task 3947 | total time = 1043.15 ms / 700 tokens 1.15.215.792 I slot print_timing: id 0 | task 3947 | graphs reused = 3678 1.15.215.793 I slot print_timing: id 0 | task 3947 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.215.830 I slot release: id 0 | task 3947 | stop processing: n_tokens = 711, truncated = 0 1.15.240.189 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 75120404 1.15.240.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 1.15.307.130 I slot launch_slot_: id 0 | task 4006 | processing task, is_child = 0 1.16.273.929 I slot print_timing: id 0 | task 4006 | prompt eval time = 179.02 ms / 474 tokens ( 0.38 ms per token, 2647.73 tokens per second) 1.16.273.934 I slot print_timing: id 0 | task 4006 | eval time = 787.76 ms / 52 tokens ( 15.45 ms per token, 64.74 tokens per second) 1.16.273.935 I slot print_timing: id 0 | task 4006 | total time = 966.78 ms / 526 tokens 1.16.273.938 I slot print_timing: id 0 | task 4006 | graphs reused = 3727 1.16.273.938 I slot print_timing: id 0 | task 4006 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.273.969 I slot release: id 0 | task 4006 | stop processing: n_tokens = 537, truncated = 0 1.16.300.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 76178543 1.16.300.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 1.16.310.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 1.16.370.615 I slot launch_slot_: id 0 | task 4061 | processing task, is_child = 0 1.17.208.661 I slot print_timing: id 0 | task 4061 | prompt eval time = 201.39 ms / 617 tokens ( 0.33 ms per token, 3063.75 tokens per second) 1.17.208.667 I slot print_timing: id 0 | task 4061 | eval time = 636.64 ms / 42 tokens ( 15.53 ms per token, 64.40 tokens per second) 1.17.208.668 I slot print_timing: id 0 | task 4061 | total time = 838.03 ms / 659 tokens 1.17.208.669 I slot print_timing: id 0 | task 4061 | graphs reused = 3767 1.17.208.670 I slot print_timing: id 0 | task 4061 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.208.706 I slot release: id 0 | task 4061 | stop processing: n_tokens = 670, truncated = 0 1.17.235.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 77113280 1.17.235.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.17.304.554 I slot launch_slot_: id 0 | task 4107 | processing task, is_child = 0 1.18.233.834 I slot print_timing: id 0 | task 4107 | prompt eval time = 204.43 ms / 601 tokens ( 0.34 ms per token, 2939.84 tokens per second) 1.18.233.840 I slot print_timing: id 0 | task 4107 | eval time = 724.83 ms / 48 tokens ( 15.42 ms per token, 64.84 tokens per second) 1.18.233.841 I slot print_timing: id 0 | task 4107 | total time = 929.26 ms / 649 tokens 1.18.233.842 I slot print_timing: id 0 | task 4107 | graphs reused = 3813 1.18.233.843 I slot print_timing: id 0 | task 4107 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.233.879 I slot release: id 0 | task 4107 | stop processing: n_tokens = 660, truncated = 0 1.18.254.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 78138453 1.18.254.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.480 MiB) 1.18.264.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 1.18.337.898 I slot launch_slot_: id 0 | task 4159 | processing task, is_child = 0 1.19.238.820 I slot print_timing: id 0 | task 4159 | prompt eval time = 195.38 ms / 533 tokens ( 0.37 ms per token, 2727.99 tokens per second) 1.19.238.826 I slot print_timing: id 0 | task 4159 | eval time = 705.52 ms / 47 tokens ( 15.34 ms per token, 65.20 tokens per second) 1.19.238.829 I slot print_timing: id 0 | task 4159 | total time = 900.90 ms / 580 tokens 1.19.238.830 I slot print_timing: id 0 | task 4159 | graphs reused = 3858 1.19.238.831 I slot print_timing: id 0 | task 4159 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.238.864 I slot release: id 0 | task 4159 | stop processing: n_tokens = 591, truncated = 0 1.19.265.479 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 79143438 1.19.265.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 1.19.331.629 I slot launch_slot_: id 0 | task 4210 | processing task, is_child = 0 1.20.298.215 I slot print_timing: id 0 | task 4210 | prompt eval time = 181.62 ms / 480 tokens ( 0.38 ms per token, 2642.90 tokens per second) 1.20.298.220 I slot print_timing: id 0 | task 4210 | eval time = 784.95 ms / 52 tokens ( 15.39 ms per token, 64.97 tokens per second) 1.20.298.222 I slot print_timing: id 0 | task 4210 | total time = 966.57 ms / 532 tokens 1.20.298.223 I slot print_timing: id 0 | task 4210 | graphs reused = 3907 1.20.298.223 I slot print_timing: id 0 | task 4210 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.298.258 I slot release: id 0 | task 4210 | stop processing: n_tokens = 560, truncated = 0 1.20.325.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 80202832 1.20.325.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.20.335.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.20.405.755 I slot launch_slot_: id 0 | task 4265 | processing task, is_child = 0 1.21.231.102 I slot print_timing: id 0 | task 4265 | prompt eval time = 196.69 ms / 567 tokens ( 0.35 ms per token, 2882.78 tokens per second) 1.21.231.108 I slot print_timing: id 0 | task 4265 | eval time = 628.64 ms / 42 tokens ( 15.33 ms per token, 65.22 tokens per second) 1.21.231.109 I slot print_timing: id 0 | task 4265 | total time = 825.33 ms / 609 tokens 1.21.231.110 I slot print_timing: id 0 | task 4265 | graphs reused = 3947 1.21.231.111 I slot print_timing: id 0 | task 4265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.231.148 I slot release: id 0 | task 4265 | stop processing: n_tokens = 637, truncated = 0 1.21.259.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 81135722 1.21.259.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 1.21.269.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.21.357.898 I slot launch_slot_: id 0 | task 4311 | processing task, is_child = 0 1.22.490.908 I slot print_timing: id 0 | task 4311 | prompt eval time = 186.00 ms / 506 tokens ( 0.37 ms per token, 2720.49 tokens per second) 1.22.490.914 I slot print_timing: id 0 | task 4311 | eval time = 946.99 ms / 63 tokens ( 15.27 ms per token, 65.47 tokens per second) 1.22.490.915 I slot print_timing: id 0 | task 4311 | total time = 1132.99 ms / 569 tokens 1.22.490.916 I slot print_timing: id 0 | task 4311 | graphs reused = 4008 1.22.490.917 I slot print_timing: id 0 | task 4311 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.490.950 I slot release: id 0 | task 4311 | stop processing: n_tokens = 597, truncated = 0 1.22.506.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 82395525 1.22.506.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.22.516.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.22.595.795 I slot launch_slot_: id 0 | task 4377 | processing task, is_child = 0 1.23.368.182 I slot print_timing: id 0 | task 4377 | prompt eval time = 173.46 ms / 436 tokens ( 0.40 ms per token, 2513.61 tokens per second) 1.23.368.188 I slot print_timing: id 0 | task 4377 | eval time = 598.91 ms / 40 tokens ( 15.36 ms per token, 65.12 tokens per second) 1.23.368.190 I slot print_timing: id 0 | task 4377 | total time = 772.37 ms / 476 tokens 1.23.368.190 I slot print_timing: id 0 | task 4377 | graphs reused = 4046 1.23.368.191 I slot print_timing: id 0 | task 4377 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.368.222 I slot release: id 0 | task 4377 | stop processing: n_tokens = 504, truncated = 0 1.23.372.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 83272796 1.23.372.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.23.456.118 I slot launch_slot_: id 0 | task 4420 | processing task, is_child = 0 1.24.577.226 I slot print_timing: id 0 | task 4420 | prompt eval time = 188.99 ms / 519 tokens ( 0.36 ms per token, 2746.15 tokens per second) 1.24.577.232 I slot print_timing: id 0 | task 4420 | eval time = 932.10 ms / 62 tokens ( 15.28 ms per token, 65.44 tokens per second) 1.24.577.233 I slot print_timing: id 0 | task 4420 | total time = 1121.09 ms / 581 tokens 1.24.577.233 I slot print_timing: id 0 | task 4420 | graphs reused = 4106 1.24.577.234 I slot print_timing: id 0 | task 4420 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.577.269 I slot release: id 0 | task 4420 | stop processing: n_tokens = 609, truncated = 0 1.24.581.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 84481843 1.24.581.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.24.591.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 1.24.677.102 I slot launch_slot_: id 0 | task 4486 | processing task, is_child = 0 1.25.545.433 I slot print_timing: id 0 | task 4486 | prompt eval time = 173.07 ms / 465 tokens ( 0.37 ms per token, 2686.71 tokens per second) 1.25.545.439 I slot print_timing: id 0 | task 4486 | eval time = 695.24 ms / 46 tokens ( 15.45 ms per token, 64.73 tokens per second) 1.25.545.440 I slot print_timing: id 0 | task 4486 | total time = 868.31 ms / 511 tokens 1.25.545.441 I slot print_timing: id 0 | task 4486 | graphs reused = 4149 1.25.545.442 I slot print_timing: id 0 | task 4486 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.545.480 I slot release: id 0 | task 4486 | stop processing: n_tokens = 542, truncated = 0 1.25.563.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 85450054 1.25.563.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.25.572.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.25.669.432 I slot launch_slot_: id 0 | task 4535 | processing task, is_child = 0 1.26.456.340 I slot print_timing: id 0 | task 4535 | prompt eval time = 173.66 ms / 431 tokens ( 0.40 ms per token, 2481.86 tokens per second) 1.26.456.346 I slot print_timing: id 0 | task 4535 | eval time = 613.23 ms / 41 tokens ( 15.33 ms per token, 65.23 tokens per second) 1.26.456.347 I slot print_timing: id 0 | task 4535 | total time = 786.88 ms / 472 tokens 1.26.456.348 I slot print_timing: id 0 | task 4535 | graphs reused = 4188 1.26.456.349 I slot print_timing: id 0 | task 4535 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.456.381 I slot release: id 0 | task 4535 | stop processing: n_tokens = 503, truncated = 0 1.26.485.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 86360956 1.26.485.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.26.495.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.26.589.132 I slot launch_slot_: id 0 | task 4579 | processing task, is_child = 0 1.27.425.570 I slot print_timing: id 0 | task 4579 | prompt eval time = 173.89 ms / 457 tokens ( 0.38 ms per token, 2628.07 tokens per second) 1.27.425.576 I slot print_timing: id 0 | task 4579 | eval time = 662.53 ms / 44 tokens ( 15.41 ms per token, 64.90 tokens per second) 1.27.425.577 I slot print_timing: id 0 | task 4579 | total time = 836.42 ms / 501 tokens 1.27.425.578 I slot print_timing: id 0 | task 4579 | graphs reused = 4229 1.27.425.579 I slot print_timing: id 0 | task 4579 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.425.613 I slot release: id 0 | task 4579 | stop processing: n_tokens = 532, truncated = 0 1.27.451.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 87330187 1.27.451.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.27.523.365 I slot launch_slot_: id 0 | task 4626 | processing task, is_child = 0 1.28.323.394 I slot print_timing: id 0 | task 4626 | prompt eval time = 172.99 ms / 439 tokens ( 0.39 ms per token, 2537.66 tokens per second) 1.28.323.400 I slot print_timing: id 0 | task 4626 | eval time = 627.01 ms / 42 tokens ( 15.29 ms per token, 65.39 tokens per second) 1.28.323.401 I slot print_timing: id 0 | task 4626 | total time = 800.01 ms / 481 tokens 1.28.323.401 I slot print_timing: id 0 | task 4626 | graphs reused = 4269 1.28.323.402 I slot print_timing: id 0 | task 4626 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.323.433 I slot release: id 0 | task 4626 | stop processing: n_tokens = 512, truncated = 0 1.28.344.070 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 88228007 1.28.344.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.28.357.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.28.458.545 I slot launch_slot_: id 0 | task 4671 | processing task, is_child = 0 1.29.501.829 I slot print_timing: id 0 | task 4671 | prompt eval time = 201.35 ms / 606 tokens ( 0.33 ms per token, 3009.61 tokens per second) 1.29.501.835 I slot print_timing: id 0 | task 4671 | eval time = 841.91 ms / 56 tokens ( 15.31 ms per token, 65.33 tokens per second) 1.29.501.836 I slot print_timing: id 0 | task 4671 | total time = 1043.26 ms / 662 tokens 1.29.501.837 I slot print_timing: id 0 | task 4671 | graphs reused = 4323 1.29.501.837 I slot print_timing: id 0 | task 4671 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.501.875 I slot release: id 0 | task 4671 | stop processing: n_tokens = 693, truncated = 0 1.29.518.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 89406449 1.29.518.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.29.531.286 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.29.608.664 I slot launch_slot_: id 0 | task 4731 | processing task, is_child = 0 1.30.400.544 I slot print_timing: id 0 | task 4731 | prompt eval time = 174.84 ms / 477 tokens ( 0.37 ms per token, 2728.24 tokens per second) 1.30.400.550 I slot print_timing: id 0 | task 4731 | eval time = 617.02 ms / 41 tokens ( 15.43 ms per token, 64.83 tokens per second) 1.30.400.551 I slot print_timing: id 0 | task 4731 | total time = 791.86 ms / 518 tokens 1.30.400.552 I slot print_timing: id 0 | task 4731 | graphs reused = 4361 1.30.400.553 I slot print_timing: id 0 | task 4731 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.400.586 I slot release: id 0 | task 4731 | stop processing: n_tokens = 549, truncated = 0 1.30.429.554 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 90305160 1.30.429.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.30.507.273 I slot launch_slot_: id 0 | task 4775 | processing task, is_child = 0 1.31.652.540 I slot print_timing: id 0 | task 4775 | prompt eval time = 241.97 ms / 845 tokens ( 0.29 ms per token, 3492.17 tokens per second) 1.31.652.545 I slot print_timing: id 0 | task 4775 | eval time = 903.28 ms / 60 tokens ( 15.31 ms per token, 65.32 tokens per second) 1.31.652.546 I slot print_timing: id 0 | task 4775 | total time = 1145.25 ms / 905 tokens 1.31.652.547 I slot print_timing: id 0 | task 4775 | graphs reused = 4419 1.31.652.548 I slot print_timing: id 0 | task 4775 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.652.592 I slot release: id 0 | task 4775 | stop processing: n_tokens = 936, truncated = 0 1.31.680.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 91557166 1.31.680.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.31.693.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.31.792.994 I slot launch_slot_: id 0 | task 4839 | processing task, is_child = 0 1.32.620.287 I slot print_timing: id 0 | task 4839 | prompt eval time = 178.63 ms / 459 tokens ( 0.39 ms per token, 2569.54 tokens per second) 1.32.620.293 I slot print_timing: id 0 | task 4839 | eval time = 648.64 ms / 43 tokens ( 15.44 ms per token, 64.75 tokens per second) 1.32.620.294 I slot print_timing: id 0 | task 4839 | total time = 827.27 ms / 502 tokens 1.32.620.295 I slot print_timing: id 0 | task 4839 | graphs reused = 4459 1.32.620.295 I slot print_timing: id 0 | task 4839 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.620.329 I slot release: id 0 | task 4839 | stop processing: n_tokens = 533, truncated = 0 1.32.637.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 92524903 1.32.637.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.32.717.790 I slot launch_slot_: id 0 | task 4885 | processing task, is_child = 0 1.33.656.564 I slot print_timing: id 0 | task 4885 | prompt eval time = 216.27 ms / 670 tokens ( 0.32 ms per token, 3097.97 tokens per second) 1.33.656.570 I slot print_timing: id 0 | task 4885 | eval time = 722.48 ms / 47 tokens ( 15.71 ms per token, 63.67 tokens per second) 1.33.656.571 I slot print_timing: id 0 | task 4885 | total time = 938.75 ms / 717 tokens 1.33.656.572 I slot print_timing: id 0 | task 4885 | graphs reused = 4504 1.33.656.573 I slot print_timing: id 0 | task 4885 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.656.612 I slot release: id 0 | task 4885 | stop processing: n_tokens = 748, truncated = 0 1.33.661.779 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 93561186 1.33.661.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.33.675.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.33.772.399 I slot launch_slot_: id 0 | task 4936 | processing task, is_child = 0 1.35.000.468 I slot print_timing: id 0 | task 4936 | prompt eval time = 237.50 ms / 775 tokens ( 0.31 ms per token, 3263.09 tokens per second) 1.35.000.474 I slot print_timing: id 0 | task 4936 | eval time = 990.54 ms / 63 tokens ( 15.98 ms per token, 62.59 tokens per second) 1.35.000.475 I slot print_timing: id 0 | task 4936 | total time = 1228.05 ms / 838 tokens 1.35.000.476 I slot print_timing: id 0 | task 4936 | graphs reused = 4565 1.35.000.476 I slot print_timing: id 0 | task 4936 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.000.523 I slot release: id 0 | task 4936 | stop processing: n_tokens = 869, truncated = 0 1.35.026.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 94905097 1.35.026.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.35.039.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.35.141.533 I slot launch_slot_: id 0 | task 5003 | processing task, is_child = 0 1.36.416.369 I slot print_timing: id 0 | task 5003 | prompt eval time = 201.25 ms / 573 tokens ( 0.35 ms per token, 2847.20 tokens per second) 1.36.416.374 I slot print_timing: id 0 | task 5003 | eval time = 1073.57 ms / 71 tokens ( 15.34 ms per token, 65.20 tokens per second) 1.36.416.376 I slot print_timing: id 0 | task 5003 | total time = 1274.82 ms / 644 tokens 1.36.416.377 I slot print_timing: id 0 | task 5003 | graphs reused = 4634 1.36.416.378 I slot print_timing: id 0 | task 5003 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.416.414 I slot release: id 0 | task 5003 | stop processing: n_tokens = 675, truncated = 0 1.36.433.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 96320988 1.36.433.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.36.446.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.36.528.925 I slot launch_slot_: id 0 | task 5078 | processing task, is_child = 0 1.37.672.088 I slot print_timing: id 0 | task 5078 | prompt eval time = 174.42 ms / 461 tokens ( 0.38 ms per token, 2642.98 tokens per second) 1.37.672.095 I slot print_timing: id 0 | task 5078 | eval time = 968.72 ms / 64 tokens ( 15.38 ms per token, 65.03 tokens per second) 1.37.672.096 I slot print_timing: id 0 | task 5078 | total time = 1143.14 ms / 525 tokens 1.37.672.097 I slot print_timing: id 0 | task 5078 | graphs reused = 4695 1.37.672.098 I slot print_timing: id 0 | task 5078 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.672.134 I slot release: id 0 | task 5078 | stop processing: n_tokens = 556, truncated = 0 1.37.699.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 97576708 1.37.699.075 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.37.773.085 I slot launch_slot_: id 0 | task 5145 | processing task, is_child = 0 1.38.655.029 I slot print_timing: id 0 | task 5145 | prompt eval time = 199.66 ms / 609 tokens ( 0.33 ms per token, 3050.26 tokens per second) 1.38.655.034 I slot print_timing: id 0 | task 5145 | eval time = 682.27 ms / 43 tokens ( 16.24 ms per token, 61.56 tokens per second) 1.38.655.035 I slot print_timing: id 0 | task 5145 | total time = 881.92 ms / 652 tokens 1.38.655.036 I slot print_timing: id 0 | task 5145 | graphs reused = 4736 1.38.655.037 I slot print_timing: id 0 | task 5145 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.655.079 I slot release: id 0 | task 5145 | stop processing: n_tokens = 683, truncated = 0 1.38.678.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 98559653 1.38.678.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.38.694.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.38.784.618 I slot launch_slot_: id 0 | task 5192 | processing task, is_child = 0 1.39.960.919 I slot print_timing: id 0 | task 5192 | prompt eval time = 244.03 ms / 791 tokens ( 0.31 ms per token, 3241.35 tokens per second) 1.39.960.925 I slot print_timing: id 0 | task 5192 | eval time = 932.25 ms / 61 tokens ( 15.54 ms per token, 64.36 tokens per second) 1.39.960.927 I slot print_timing: id 0 | task 5192 | total time = 1176.28 ms / 852 tokens 1.39.960.929 I slot print_timing: id 0 | task 5192 | graphs reused = 4795 1.39.960.930 I slot print_timing: id 0 | task 5192 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.960.977 I slot release: id 0 | task 5192 | stop processing: n_tokens = 883, truncated = 0 1.39.979.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 99865552 1.39.979.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.40.126.379 I slot launch_slot_: id 0 | task 5257 | processing task, is_child = 0 1.41.163.273 I slot print_timing: id 0 | task 5257 | prompt eval time = 193.46 ms / 533 tokens ( 0.36 ms per token, 2755.09 tokens per second) 1.41.163.279 I slot print_timing: id 0 | task 5257 | eval time = 843.41 ms / 56 tokens ( 15.33 ms per token, 65.21 tokens per second) 1.41.163.280 I slot print_timing: id 0 | task 5257 | total time = 1036.87 ms / 589 tokens 1.41.163.281 I slot print_timing: id 0 | task 5257 | graphs reused = 4849 1.41.163.281 I slot print_timing: id 0 | task 5257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.163.317 I slot release: id 0 | task 5257 | stop processing: n_tokens = 677, truncated = 0 1.41.182.617 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 101067892 1.41.182.674 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.41.279.503 I slot launch_slot_: id 0 | task 5317 | processing task, is_child = 0 1.42.207.258 I slot print_timing: id 0 | task 5317 | prompt eval time = 203.17 ms / 566 tokens ( 0.36 ms per token, 2785.83 tokens per second) 1.42.207.264 I slot print_timing: id 0 | task 5317 | eval time = 724.56 ms / 46 tokens ( 16.10 ms per token, 62.11 tokens per second) 1.42.207.265 I slot print_timing: id 0 | task 5317 | total time = 927.73 ms / 612 tokens 1.42.207.265 I slot print_timing: id 0 | task 5317 | graphs reused = 4893 1.42.207.266 I slot print_timing: id 0 | task 5317 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.207.301 I slot release: id 0 | task 5317 | stop processing: n_tokens = 643, truncated = 0 1.42.228.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 102111875 1.42.228.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.42.320.668 I slot launch_slot_: id 0 | task 5367 | processing task, is_child = 0 1.43.146.834 I slot print_timing: id 0 | task 5367 | prompt eval time = 176.60 ms / 443 tokens ( 0.40 ms per token, 2508.42 tokens per second) 1.43.146.840 I slot print_timing: id 0 | task 5367 | eval time = 649.54 ms / 43 tokens ( 15.47 ms per token, 64.66 tokens per second) 1.43.146.842 I slot print_timing: id 0 | task 5367 | total time = 826.14 ms / 486 tokens 1.43.146.842 I slot print_timing: id 0 | task 5367 | graphs reused = 4933 1.43.146.843 I slot print_timing: id 0 | task 5367 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.146.883 I slot release: id 0 | task 5367 | stop processing: n_tokens = 517, truncated = 0 1.43.168.542 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 103051457 1.43.168.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.43.249.586 I slot launch_slot_: id 0 | task 5413 | processing task, is_child = 0 1.44.404.712 I slot print_timing: id 0 | task 5413 | prompt eval time = 175.09 ms / 487 tokens ( 0.36 ms per token, 2781.41 tokens per second) 1.44.404.717 I slot print_timing: id 0 | task 5413 | eval time = 980.01 ms / 65 tokens ( 15.31 ms per token, 65.31 tokens per second) 1.44.404.718 I slot print_timing: id 0 | task 5413 | total time = 1155.11 ms / 552 tokens 1.44.404.719 I slot print_timing: id 0 | task 5413 | graphs reused = 4996 1.44.404.720 I slot print_timing: id 0 | task 5413 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.404.754 I slot release: id 0 | task 5413 | stop processing: n_tokens = 583, truncated = 0 1.44.430.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 104309328 1.44.430.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.44.502.914 I slot launch_slot_: id 0 | task 5481 | processing task, is_child = 0 1.45.387.668 I slot print_timing: id 0 | task 5481 | prompt eval time = 179.97 ms / 507 tokens ( 0.35 ms per token, 2817.15 tokens per second) 1.45.387.673 I slot print_timing: id 0 | task 5481 | eval time = 704.76 ms / 47 tokens ( 15.32 ms per token, 65.27 tokens per second) 1.45.387.674 I slot print_timing: id 0 | task 5481 | total time = 884.73 ms / 554 tokens 1.45.387.675 I slot print_timing: id 0 | task 5481 | graphs reused = 5041 1.45.387.676 I slot print_timing: id 0 | task 5481 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.387.711 I slot release: id 0 | task 5481 | stop processing: n_tokens = 585, truncated = 0 1.45.414.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 105292286 1.45.414.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.45.431.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.45.517.267 I slot launch_slot_: id 0 | task 5531 | processing task, is_child = 0 1.46.715.735 I slot print_timing: id 0 | task 5531 | prompt eval time = 203.92 ms / 633 tokens ( 0.32 ms per token, 3104.13 tokens per second) 1.46.715.741 I slot print_timing: id 0 | task 5531 | eval time = 994.52 ms / 66 tokens ( 15.30 ms per token, 65.36 tokens per second) 1.46.715.742 I slot print_timing: id 0 | task 5531 | total time = 1198.45 ms / 699 tokens 1.46.715.743 I slot print_timing: id 0 | task 5531 | graphs reused = 5105 1.46.715.743 I slot print_timing: id 0 | task 5531 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.715.781 I slot release: id 0 | task 5531 | stop processing: n_tokens = 730, truncated = 0 1.46.735.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 106620355 1.46.735.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.46.837.307 I slot launch_slot_: id 0 | task 5601 | processing task, is_child = 0 1.47.741.619 I slot print_timing: id 0 | task 5601 | prompt eval time = 198.77 ms / 571 tokens ( 0.35 ms per token, 2872.61 tokens per second) 1.47.741.626 I slot print_timing: id 0 | task 5601 | eval time = 705.52 ms / 47 tokens ( 15.34 ms per token, 65.20 tokens per second) 1.47.741.628 I slot print_timing: id 0 | task 5601 | total time = 904.29 ms / 618 tokens 1.47.741.628 I slot print_timing: id 0 | task 5601 | graphs reused = 5150 1.47.741.630 I slot print_timing: id 0 | task 5601 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.741.669 I slot release: id 0 | task 5601 | stop processing: n_tokens = 649, truncated = 0 1.47.769.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 107646243 1.47.769.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.47.875.837 I slot launch_slot_: id 0 | task 5652 | processing task, is_child = 0 1.48.773.621 I slot print_timing: id 0 | task 5652 | prompt eval time = 236.26 ms / 798 tokens ( 0.30 ms per token, 3377.68 tokens per second) 1.48.773.627 I slot print_timing: id 0 | task 5652 | eval time = 661.50 ms / 44 tokens ( 15.38 ms per token, 65.00 tokens per second) 1.48.773.628 I slot print_timing: id 0 | task 5652 | total time = 897.76 ms / 842 tokens 1.48.773.629 I slot print_timing: id 0 | task 5652 | graphs reused = 5192 1.48.773.630 I slot print_timing: id 0 | task 5652 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.773.679 I slot release: id 0 | task 5652 | stop processing: n_tokens = 873, truncated = 0 1.48.795.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 108678253 1.48.795.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.48.815.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.48.923.635 I slot launch_slot_: id 0 | task 5700 | processing task, is_child = 0 1.49.766.580 I slot print_timing: id 0 | task 5700 | prompt eval time = 198.35 ms / 572 tokens ( 0.35 ms per token, 2883.85 tokens per second) 1.49.766.586 I slot print_timing: id 0 | task 5700 | eval time = 644.58 ms / 43 tokens ( 15.35 ms per token, 65.16 tokens per second) 1.49.766.587 I slot print_timing: id 0 | task 5700 | total time = 842.92 ms / 615 tokens 1.49.766.588 I slot print_timing: id 0 | task 5700 | graphs reused = 5233 1.49.766.588 I slot print_timing: id 0 | task 5700 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.766.625 I slot release: id 0 | task 5700 | stop processing: n_tokens = 646, truncated = 0 1.49.794.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 109671199 1.49.794.845 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.49.889.487 I slot launch_slot_: id 0 | task 5747 | processing task, is_child = 0 1.50.830.564 I slot print_timing: id 0 | task 5747 | prompt eval time = 204.18 ms / 613 tokens ( 0.33 ms per token, 3002.19 tokens per second) 1.50.830.570 I slot print_timing: id 0 | task 5747 | eval time = 736.87 ms / 49 tokens ( 15.35 ms per token, 65.14 tokens per second) 1.50.830.571 I slot print_timing: id 0 | task 5747 | total time = 941.06 ms / 662 tokens 1.50.830.572 I slot print_timing: id 0 | task 5747 | graphs reused = 5280 1.50.830.572 I slot print_timing: id 0 | task 5747 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.830.611 I slot release: id 0 | task 5747 | stop processing: n_tokens = 693, truncated = 0 1.50.847.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 110735185 1.50.848.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.50.953.659 I slot launch_slot_: id 0 | task 5800 | processing task, is_child = 0 1.52.305.690 I slot print_timing: id 0 | task 5800 | prompt eval time = 198.82 ms / 580 tokens ( 0.34 ms per token, 2917.18 tokens per second) 1.52.305.697 I slot print_timing: id 0 | task 5800 | eval time = 1153.19 ms / 76 tokens ( 15.38 ms per token, 65.04 tokens per second) 1.52.305.698 I slot print_timing: id 0 | task 5800 | total time = 1352.01 ms / 656 tokens 1.52.305.699 I slot print_timing: id 0 | task 5800 | graphs reused = 5354 1.52.305.699 I slot print_timing: id 0 | task 5800 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.305.737 I slot release: id 0 | task 5800 | stop processing: n_tokens = 687, truncated = 0 1.52.323.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 112210311 1.52.323.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.52.426.959 I slot launch_slot_: id 0 | task 5880 | processing task, is_child = 0 1.53.407.801 I slot print_timing: id 0 | task 5880 | prompt eval time = 223.56 ms / 716 tokens ( 0.31 ms per token, 3202.65 tokens per second) 1.53.407.806 I slot print_timing: id 0 | task 5880 | eval time = 757.26 ms / 50 tokens ( 15.45 ms per token, 64.71 tokens per second) 1.53.407.807 I slot print_timing: id 0 | task 5880 | total time = 980.82 ms / 766 tokens 1.53.407.808 I slot print_timing: id 0 | task 5880 | graphs reused = 5401 1.53.407.809 I slot print_timing: id 0 | task 5880 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.407.848 I slot release: id 0 | task 5880 | stop processing: n_tokens = 797, truncated = 0 1.53.413.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 113312422 1.53.413.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.53.432.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.53.524.292 I slot launch_slot_: id 0 | task 5934 | processing task, is_child = 0 1.55.303.699 I slot print_timing: id 0 | task 5934 | prompt eval time = 236.88 ms / 799 tokens ( 0.30 ms per token, 3372.96 tokens per second) 1.55.303.705 I slot print_timing: id 0 | task 5934 | eval time = 1542.50 ms / 102 tokens ( 15.27 ms per token, 65.48 tokens per second) 1.55.303.706 I slot print_timing: id 0 | task 5934 | total time = 1779.39 ms / 901 tokens 1.55.303.707 I slot print_timing: id 0 | task 5934 | graphs reused = 5501 1.55.303.708 I slot print_timing: id 0 | task 5934 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.303.751 I slot release: id 0 | task 5934 | stop processing: n_tokens = 932, truncated = 0 1.55.307.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 115208325 1.55.307.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.55.398.711 I slot launch_slot_: id 0 | task 6040 | processing task, is_child = 0 1.57.243.915 I slot print_timing: id 0 | task 6040 | prompt eval time = 152.64 ms / 361 tokens ( 0.42 ms per token, 2364.98 tokens per second) 1.57.243.921 I slot print_timing: id 0 | task 6040 | eval time = 1692.54 ms / 112 tokens ( 15.25 ms per token, 65.58 tokens per second) 1.57.243.922 I slot print_timing: id 0 | task 6040 | total time = 1845.18 ms / 473 tokens 1.57.243.923 I slot print_timing: id 0 | task 6040 | graphs reused = 5611 1.57.243.924 I slot print_timing: id 0 | task 6040 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.243.955 I slot release: id 0 | task 6040 | stop processing: n_tokens = 504, truncated = 0 1.57.271.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 117148529 1.57.271.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.57.345.927 I slot launch_slot_: id 0 | task 6155 | processing task, is_child = 0 1.59.132.527 I slot print_timing: id 0 | task 6155 | prompt eval time = 149.68 ms / 381 tokens ( 0.39 ms per token, 2545.40 tokens per second) 1.59.132.533 I slot print_timing: id 0 | task 6155 | eval time = 1636.90 ms / 108 tokens ( 15.30 ms per token, 65.37 tokens per second) 1.59.132.534 I slot print_timing: id 0 | task 6155 | total time = 1786.58 ms / 489 tokens 1.59.132.535 I slot print_timing: id 0 | task 6155 | graphs reused = 5716 1.59.132.535 I slot print_timing: id 0 | task 6155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.132.565 I slot release: id 0 | task 6155 | stop processing: n_tokens = 520, truncated = 0 1.59.157.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 119037139 1.59.157.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.59.241.378 I slot launch_slot_: id 0 | task 6266 | processing task, is_child = 0 2.01.271.685 I slot print_timing: id 0 | task 6266 | prompt eval time = 150.16 ms / 365 tokens ( 0.41 ms per token, 2430.71 tokens per second) 2.01.271.691 I slot print_timing: id 0 | task 6266 | eval time = 1880.12 ms / 124 tokens ( 15.29 ms per token, 65.42 tokens per second) 2.01.271.693 I slot print_timing: id 0 | task 6266 | total time = 2030.29 ms / 489 tokens 2.01.271.693 I slot print_timing: id 0 | task 6266 | graphs reused = 5837 2.01.271.694 I slot print_timing: id 0 | task 6266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.271.727 I slot release: id 0 | task 6266 | stop processing: n_tokens = 520, truncated = 0 2.01.289.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 121176302 2.01.289.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 2.01.375.332 I slot launch_slot_: id 0 | task 6393 | processing task, is_child = 0 2.03.148.022 I slot print_timing: id 0 | task 6393 | prompt eval time = 152.06 ms / 333 tokens ( 0.46 ms per token, 2189.93 tokens per second) 2.03.148.028 I slot print_timing: id 0 | task 6393 | eval time = 1620.61 ms / 107 tokens ( 15.29 ms per token, 65.41 tokens per second) 2.03.148.029 I slot print_timing: id 0 | task 6393 | total time = 1772.67 ms / 440 tokens 2.03.148.030 I slot print_timing: id 0 | task 6393 | graphs reused = 5942 2.03.148.031 I slot print_timing: id 0 | task 6393 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.148.064 I slot release: id 0 | task 6393 | stop processing: n_tokens = 471, truncated = 0 2.03.175.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 123052638 2.03.232.912 I slot launch_slot_: id 0 | task 6503 | processing task, is_child = 0 2.05.483.405 I slot print_timing: id 0 | task 6503 | prompt eval time = 154.48 ms / 403 tokens ( 0.38 ms per token, 2608.82 tokens per second) 2.05.483.411 I slot print_timing: id 0 | task 6503 | eval time = 2096.00 ms / 138 tokens ( 15.30 ms per token, 65.36 tokens per second) 2.05.483.412 I slot print_timing: id 0 | task 6503 | total time = 2250.47 ms / 541 tokens 2.05.483.412 I slot print_timing: id 0 | task 6503 | graphs reused = 6077 2.05.483.413 I slot print_timing: id 0 | task 6503 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.483.444 I slot release: id 0 | task 6503 | stop processing: n_tokens = 572, truncated = 0 2.05.487.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 125388018 2.05.487.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 2.05.584.007 I slot launch_slot_: id 0 | task 6644 | processing task, is_child = 0 2.08.548.523 I slot print_timing: id 0 | task 6644 | prompt eval time = 155.91 ms / 411 tokens ( 0.38 ms per token, 2636.19 tokens per second) 2.08.548.528 I slot print_timing: id 0 | task 6644 | eval time = 2808.59 ms / 185 tokens ( 15.26 ms per token, 65.51 tokens per second) 2.08.548.530 I slot print_timing: id 0 | task 6644 | total time = 2964.49 ms / 596 tokens 2.08.548.530 I slot print_timing: id 0 | task 6644 | graphs reused = 6259 2.08.548.531 I slot print_timing: id 0 | task 6644 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.548.564 I slot release: id 0 | task 6644 | stop processing: n_tokens = 627, truncated = 0 2.08.566.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 128453139 2.08.566.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 2.08.662.230 I slot launch_slot_: id 0 | task 6832 | processing task, is_child = 0 2.11.846.186 I slot print_timing: id 0 | task 6832 | n_gen = 197, tg = 65.32 t/s, tg_3s = 65.65 t/s 2.12.272.704 I slot print_timing: id 0 | task 6832 | prompt eval time = 183.17 ms / 490 tokens ( 0.37 ms per token, 2675.17 tokens per second) 2.12.272.710 I slot print_timing: id 0 | task 6832 | eval time = 3427.29 ms / 225 tokens ( 15.30 ms per token, 65.36 tokens per second) 2.12.272.711 I slot print_timing: id 0 | task 6832 | total time = 3610.45 ms / 715 tokens 2.12.272.712 I slot print_timing: id 0 | task 6832 | graphs reused = 6482 2.12.272.712 I slot print_timing: id 0 | task 6832 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.272.748 I slot release: id 0 | task 6832 | stop processing: n_tokens = 746, truncated = 0 2.12.292.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 132177322 2.12.292.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 2.12.391.254 I slot launch_slot_: id 0 | task 7060 | processing task, is_child = 0 2.15.145.210 I slot print_timing: id 0 | task 7060 | prompt eval time = 156.61 ms / 344 tokens ( 0.46 ms per token, 2196.55 tokens per second) 2.15.145.216 I slot print_timing: id 0 | task 7060 | eval time = 2597.33 ms / 171 tokens ( 15.28 ms per token, 65.45 tokens per second) 2.15.145.217 I slot print_timing: id 0 | task 7060 | total time = 2753.94 ms / 515 tokens 2.15.145.218 I slot print_timing: id 0 | task 7060 | graphs reused = 6650 2.15.145.218 I slot print_timing: id 0 | task 7060 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.145.249 I slot release: id 0 | task 7060 | stop processing: n_tokens = 546, truncated = 0 2.15.169.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 135049823 2.15.169.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 2.15.271.172 I slot launch_slot_: id 0 | task 7234 | processing task, is_child = 0 2.18.024.188 I slot print_timing: id 0 | task 7234 | prompt eval time = 148.41 ms / 347 tokens ( 0.43 ms per token, 2338.16 tokens per second) 2.18.024.195 I slot print_timing: id 0 | task 7234 | eval time = 2604.59 ms / 171 tokens ( 15.32 ms per token, 65.27 tokens per second) 2.18.024.196 I slot print_timing: id 0 | task 7234 | total time = 2752.99 ms / 518 tokens 2.18.024.196 I slot print_timing: id 0 | task 7234 | graphs reused = 6818 2.18.024.197 I slot print_timing: id 0 | task 7234 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.024.226 I slot release: id 0 | task 7234 | stop processing: n_tokens = 549, truncated = 0 2.18.045.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 137928801 2.18.045.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 2.18.121.913 I slot launch_slot_: id 0 | task 7408 | processing task, is_child = 0 2.20.194.282 I slot print_timing: id 0 | task 7408 | prompt eval time = 153.84 ms / 401 tokens ( 0.38 ms per token, 2606.60 tokens per second) 2.20.194.288 I slot print_timing: id 0 | task 7408 | eval time = 1918.51 ms / 126 tokens ( 15.35 ms per token, 65.15 tokens per second) 2.20.194.289 I slot print_timing: id 0 | task 7408 | total time = 2072.35 ms / 527 tokens 2.20.194.290 I slot print_timing: id 0 | task 7408 | graphs reused = 6941 2.20.194.291 I slot print_timing: id 0 | task 7408 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.194.323 I slot release: id 0 | task 7408 | stop processing: n_tokens = 558, truncated = 0 2.20.222.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 140098897 2.20.222.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 2.20.318.584 I slot launch_slot_: id 0 | task 7537 | processing task, is_child = 0 2.22.262.136 I slot print_timing: id 0 | task 7537 | prompt eval time = 168.88 ms / 456 tokens ( 0.37 ms per token, 2700.16 tokens per second) 2.22.262.142 I slot print_timing: id 0 | task 7537 | eval time = 1774.65 ms / 115 tokens ( 15.57 ms per token, 64.24 tokens per second) 2.22.262.143 I slot print_timing: id 0 | task 7537 | total time = 1943.53 ms / 571 tokens 2.22.262.143 I slot print_timing: id 0 | task 7537 | graphs reused = 7053 2.22.262.144 I slot print_timing: id 0 | task 7537 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.262.176 I slot release: id 0 | task 7537 | stop processing: n_tokens = 602, truncated = 0 2.22.283.895 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 2.22.283.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 2.22.387.151 I slot launch_slot_: id 0 | task 7655 | processing task, is_child = 0 2.24.244.912 I slot print_timing: id 0 | task 7655 | prompt eval time = 158.86 ms / 406 tokens ( 0.39 ms per token, 2555.71 tokens per second) 2.24.244.918 I slot print_timing: id 0 | task 7655 | eval time = 1698.88 ms / 112 tokens ( 15.31 ms per token, 65.34 tokens per second) 2.24.244.919 I slot print_timing: id 0 | task 7655 | total time = 1857.74 ms / 518 tokens 2.24.244.919 I slot print_timing: id 0 | task 7655 | graphs reused = 7162 2.24.244.920 I slot print_timing: id 0 | task 7655 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.244.952 I slot release: id 0 | task 7655 | stop processing: n_tokens = 549, truncated = 0 2.24.266.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 144149526 2.24.326.657 I slot launch_slot_: id 0 | task 7770 | processing task, is_child = 0 2.27.200.726 I slot print_timing: id 0 | task 7770 | prompt eval time = 154.73 ms / 406 tokens ( 0.38 ms per token, 2623.96 tokens per second) 2.27.200.732 I slot print_timing: id 0 | task 7770 | eval time = 2719.32 ms / 179 tokens ( 15.28 ms per token, 65.46 tokens per second) 2.27.200.733 I slot print_timing: id 0 | task 7770 | total time = 2874.05 ms / 585 tokens 2.27.200.733 I slot print_timing: id 0 | task 7770 | graphs reused = 7338 2.27.200.734 I slot print_timing: id 0 | task 7770 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.200.765 I slot release: id 0 | task 7770 | stop processing: n_tokens = 616, truncated = 0 2.27.218.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 147105339 2.27.218.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 2.27.315.088 I slot launch_slot_: id 0 | task 7952 | processing task, is_child = 0 2.29.663.467 I slot print_timing: id 0 | task 7952 | prompt eval time = 162.75 ms / 444 tokens ( 0.37 ms per token, 2728.03 tokens per second) 2.29.663.473 I slot print_timing: id 0 | task 7952 | eval time = 2185.60 ms / 144 tokens ( 15.28 ms per token, 65.43 tokens per second) 2.29.663.474 I slot print_timing: id 0 | task 7952 | total time = 2348.36 ms / 588 tokens 2.29.663.475 I slot print_timing: id 0 | task 7952 | graphs reused = 7479 2.29.663.475 I slot print_timing: id 0 | task 7952 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.663.507 I slot release: id 0 | task 7952 | stop processing: n_tokens = 619, truncated = 0 2.29.691.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 149568081 2.29.691.812 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 2.29.784.646 I slot launch_slot_: id 0 | task 8099 | processing task, is_child = 0 2.31.508.493 I slot print_timing: id 0 | task 8099 | prompt eval time = 152.98 ms / 372 tokens ( 0.41 ms per token, 2431.74 tokens per second) 2.31.508.499 I slot print_timing: id 0 | task 8099 | eval time = 1570.85 ms / 103 tokens ( 15.40 ms per token, 64.93 tokens per second) 2.31.508.500 I slot print_timing: id 0 | task 8099 | total time = 1723.83 ms / 475 tokens 2.31.508.501 I slot print_timing: id 0 | task 8099 | graphs reused = 7580 2.31.508.503 I slot print_timing: id 0 | task 8099 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.508.534 I slot release: id 0 | task 8099 | stop processing: n_tokens = 506, truncated = 0 2.31.527.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 151413109 2.31.527.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 2.31.617.386 I slot launch_slot_: id 0 | task 8205 | processing task, is_child = 0 2.34.784.537 I slot print_timing: id 0 | task 8205 | n_gen = 197, tg = 65.22 t/s, tg_3s = 65.55 t/s 2.35.286.615 I slot print_timing: id 0 | task 8205 | prompt eval time = 161.73 ms / 454 tokens ( 0.36 ms per token, 2807.11 tokens per second) 2.35.286.621 I slot print_timing: id 0 | task 8205 | eval time = 3507.47 ms / 230 tokens ( 15.32 ms per token, 65.29 tokens per second) 2.35.286.623 I slot print_timing: id 0 | task 8205 | total time = 3669.21 ms / 684 tokens 2.35.286.623 I slot print_timing: id 0 | task 8205 | graphs reused = 7807 2.35.286.624 I slot print_timing: id 0 | task 8205 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.286.657 I slot release: id 0 | task 8205 | stop processing: n_tokens = 715, truncated = 0 2.35.308.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 155191232 2.35.308.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 2.35.407.636 I slot launch_slot_: id 0 | task 8438 | processing task, is_child = 0 2.38.570.777 I slot print_timing: id 0 | task 8438 | n_gen = 198, tg = 65.39 t/s, tg_3s = 65.72 t/s 2.38.997.377 I slot print_timing: id 0 | task 8438 | prompt eval time = 150.51 ms / 354 tokens ( 0.43 ms per token, 2351.93 tokens per second) 2.38.997.382 I slot print_timing: id 0 | task 8438 | eval time = 3439.20 ms / 226 tokens ( 15.29 ms per token, 65.42 tokens per second) 2.38.997.383 I slot print_timing: id 0 | task 8438 | total time = 3589.72 ms / 580 tokens 2.38.997.384 I slot print_timing: id 0 | task 8438 | graphs reused = 8030 2.38.997.385 I slot print_timing: id 0 | task 8438 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.997.414 I slot release: id 0 | task 8438 | stop processing: n_tokens = 611, truncated = 0 2.39.015.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 158901988 2.39.015.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.39.122.066 I slot launch_slot_: id 0 | task 8667 | processing task, is_child = 0 2.41.398.966 I slot print_timing: id 0 | task 8667 | prompt eval time = 155.29 ms / 334 tokens ( 0.46 ms per token, 2150.81 tokens per second) 2.41.398.972 I slot print_timing: id 0 | task 8667 | eval time = 2121.59 ms / 140 tokens ( 15.26 ms per token, 65.52 tokens per second) 2.41.398.973 I slot print_timing: id 0 | task 8667 | total time = 2276.88 ms / 474 tokens 2.41.398.974 I slot print_timing: id 0 | task 8667 | graphs reused = 8168 2.41.398.975 I slot print_timing: id 0 | task 8667 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.399.002 I slot release: id 0 | task 8667 | stop processing: n_tokens = 505, truncated = 0 2.41.418.976 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 161303577 2.41.419.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 2.41.506.982 I slot launch_slot_: id 0 | task 8810 | processing task, is_child = 0 2.44.337.802 I slot print_timing: id 0 | task 8810 | prompt eval time = 169.91 ms / 426 tokens ( 0.40 ms per token, 2507.25 tokens per second) 2.44.337.809 I slot print_timing: id 0 | task 8810 | eval time = 2660.89 ms / 175 tokens ( 15.29 ms per token, 65.39 tokens per second) 2.44.337.810 I slot print_timing: id 0 | task 8810 | total time = 2830.80 ms / 601 tokens 2.44.337.811 I slot print_timing: id 0 | task 8810 | graphs reused = 8340 2.44.337.811 I slot print_timing: id 0 | task 8810 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.337.844 I slot release: id 0 | task 8810 | stop processing: n_tokens = 632, truncated = 0 2.44.351.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 164242418 2.44.351.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.44.451.325 I slot launch_slot_: id 0 | task 8988 | processing task, is_child = 0 2.46.388.458 I slot print_timing: id 0 | task 8988 | prompt eval time = 153.05 ms / 366 tokens ( 0.42 ms per token, 2391.41 tokens per second) 2.46.388.465 I slot print_timing: id 0 | task 8988 | eval time = 1784.06 ms / 117 tokens ( 15.38 ms per token, 65.02 tokens per second) 2.46.388.466 I slot print_timing: id 0 | task 8988 | total time = 1937.11 ms / 483 tokens 2.46.388.467 I slot print_timing: id 0 | task 8988 | graphs reused = 8454 2.46.388.468 I slot print_timing: id 0 | task 8988 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.388.505 I slot release: id 0 | task 8988 | stop processing: n_tokens = 514, truncated = 0 2.46.393.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 166293080 2.46.393.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.46.497.447 I slot launch_slot_: id 0 | task 9108 | processing task, is_child = 0 2.49.681.131 I slot print_timing: id 0 | task 9108 | n_gen = 198, tg = 65.43 t/s, tg_3s = 65.76 t/s 2.51.529.190 I slot print_timing: id 0 | task 9108 | prompt eval time = 172.85 ms / 462 tokens ( 0.37 ms per token, 2672.81 tokens per second) 2.51.529.195 I slot print_timing: id 0 | task 9108 | eval time = 4858.86 ms / 319 tokens ( 15.28 ms per token, 65.45 tokens per second) 2.51.529.196 I slot print_timing: id 0 | task 9108 | total time = 5031.71 ms / 781 tokens 2.51.529.197 I slot print_timing: id 0 | task 9108 | graphs reused = 8769 2.51.529.197 I slot print_timing: id 0 | task 9108 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.529.229 I slot release: id 0 | task 9108 | stop processing: n_tokens = 812, truncated = 0 2.51.557.129 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 812, t_last = 171433803 2.51.557.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.51.666.647 I slot launch_slot_: id 0 | task 9430 | processing task, is_child = 0 2.53.943.318 I slot print_timing: id 0 | task 9430 | prompt eval time = 157.02 ms / 396 tokens ( 0.40 ms per token, 2522.02 tokens per second) 2.53.943.324 I slot print_timing: id 0 | task 9430 | eval time = 2119.63 ms / 139 tokens ( 15.36 ms per token, 65.11 tokens per second) 2.53.943.325 I slot print_timing: id 0 | task 9430 | total time = 2276.65 ms / 535 tokens 2.53.943.327 I slot print_timing: id 0 | task 9430 | graphs reused = 8905 2.53.943.328 I slot print_timing: id 0 | task 9430 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.943.362 I slot release: id 0 | task 9430 | stop processing: n_tokens = 566, truncated = 0 2.53.968.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 173847936 2.54.036.793 I slot launch_slot_: id 0 | task 9572 | processing task, is_child = 0 2.56.660.712 I slot print_timing: id 0 | task 9572 | prompt eval time = 166.91 ms / 458 tokens ( 0.36 ms per token, 2744.03 tokens per second) 2.56.660.718 I slot print_timing: id 0 | task 9572 | eval time = 2456.99 ms / 161 tokens ( 15.36 ms per token, 65.12 tokens per second) 2.56.660.719 I slot print_timing: id 0 | task 9572 | total time = 2623.90 ms / 619 tokens 2.56.660.719 I slot print_timing: id 0 | task 9572 | graphs reused = 9063 2.56.660.720 I slot print_timing: id 0 | task 9572 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.660.752 I slot release: id 0 | task 9572 | stop processing: n_tokens = 650, truncated = 0 2.56.687.823 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 176565326 2.56.687.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.56.787.765 I slot launch_slot_: id 0 | task 9736 | processing task, is_child = 0 2.59.671.930 I slot print_timing: id 0 | task 9736 | prompt eval time = 176.03 ms / 458 tokens ( 0.38 ms per token, 2601.84 tokens per second) 2.59.671.936 I slot print_timing: id 0 | task 9736 | eval time = 2708.12 ms / 176 tokens ( 15.47 ms per token, 64.62 tokens per second) 2.59.671.937 I slot print_timing: id 0 | task 9736 | total time = 2884.15 ms / 634 tokens 2.59.671.938 I slot print_timing: id 0 | task 9736 | graphs reused = 9236 2.59.671.938 I slot print_timing: id 0 | task 9736 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.671.971 I slot release: id 0 | task 9736 | stop processing: n_tokens = 665, truncated = 0 2.59.697.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 179576545 2.59.698.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.59.773.657 I slot launch_slot_: id 0 | task 9915 | processing task, is_child = 0 3.02.945.308 I slot print_timing: id 0 | task 9915 | n_gen = 198, tg = 65.45 t/s, tg_3s = 65.78 t/s 3.03.127.516 I slot print_timing: id 0 | task 9915 | prompt eval time = 161.56 ms / 452 tokens ( 0.36 ms per token, 2797.81 tokens per second) 3.03.127.521 I slot print_timing: id 0 | task 9915 | eval time = 3192.28 ms / 210 tokens ( 15.27 ms per token, 65.47 tokens per second) 3.03.127.523 I slot print_timing: id 0 | task 9915 | total time = 3353.84 ms / 662 tokens 3.03.127.524 I slot print_timing: id 0 | task 9915 | graphs reused = 9443 3.03.127.524 I slot print_timing: id 0 | task 9915 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.127.557 I slot release: id 0 | task 9915 | stop processing: n_tokens = 693, truncated = 0 3.03.155.897 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 183032131 3.03.155.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 3.03.253.798 I slot launch_slot_: id 0 | task 10128 | processing task, is_child = 0 3.05.235.454 I slot print_timing: id 0 | task 10128 | prompt eval time = 157.82 ms / 404 tokens ( 0.39 ms per token, 2559.86 tokens per second) 3.05.235.459 I slot print_timing: id 0 | task 10128 | eval time = 1823.81 ms / 120 tokens ( 15.33 ms per token, 65.25 tokens per second) 3.05.235.460 I slot print_timing: id 0 | task 10128 | total time = 1981.63 ms / 524 tokens 3.05.235.461 I slot print_timing: id 0 | task 10128 | graphs reused = 9560 3.05.235.462 I slot print_timing: id 0 | task 10128 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.235.491 I slot release: id 0 | task 10128 | stop processing: n_tokens = 555, truncated = 0 3.05.262.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 185140065 3.05.262.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 3.05.333.100 I slot launch_slot_: id 0 | task 10251 | processing task, is_child = 0 3.07.089.425 I slot print_timing: id 0 | task 10251 | prompt eval time = 151.24 ms / 345 tokens ( 0.44 ms per token, 2281.22 tokens per second) 3.07.089.430 I slot print_timing: id 0 | task 10251 | eval time = 1605.07 ms / 106 tokens ( 15.29 ms per token, 65.42 tokens per second) 3.07.089.431 I slot print_timing: id 0 | task 10251 | total time = 1756.30 ms / 451 tokens 3.07.089.432 I slot print_timing: id 0 | task 10251 | graphs reused = 9664 3.07.089.433 I slot print_timing: id 0 | task 10251 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.089.463 I slot release: id 0 | task 10251 | stop processing: n_tokens = 482, truncated = 0 3.07.112.187 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 186994037 3.07.112.227 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 3.07.204.492 I slot launch_slot_: id 0 | task 10360 | processing task, is_child = 0 3.08.964.822 I slot print_timing: id 0 | task 10360 | prompt eval time = 167.60 ms / 430 tokens ( 0.39 ms per token, 2565.60 tokens per second) 3.08.964.828 I slot print_timing: id 0 | task 10360 | eval time = 1592.71 ms / 105 tokens ( 15.31 ms per token, 65.30 tokens per second) 3.08.964.829 I slot print_timing: id 0 | task 10360 | total time = 1760.31 ms / 535 tokens 3.08.964.830 I slot print_timing: id 0 | task 10360 | graphs reused = 9766 3.08.964.831 I slot print_timing: id 0 | task 10360 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.964.862 I slot release: id 0 | task 10360 | stop processing: n_tokens = 566, truncated = 0 3.08.981.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 188869437 3.08.981.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 3.09.079.461 I slot launch_slot_: id 0 | task 10468 | processing task, is_child = 0 3.10.536.493 I slot print_timing: id 0 | task 10468 | prompt eval time = 141.95 ms / 316 tokens ( 0.45 ms per token, 2226.15 tokens per second) 3.10.536.499 I slot print_timing: id 0 | task 10468 | eval time = 1315.06 ms / 85 tokens ( 15.66 ms per token, 63.88 tokens per second) 3.10.536.500 I slot print_timing: id 0 | task 10468 | total time = 1457.01 ms / 401 tokens 3.10.536.501 I slot print_timing: id 0 | task 10468 | graphs reused = 9849 3.10.536.501 I slot print_timing: id 0 | task 10468 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.536.529 I slot release: id 0 | task 10468 | stop processing: n_tokens = 432, truncated = 0 3.10.562.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 190441103 3.10.562.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 3.10.674.580 I slot launch_slot_: id 0 | task 10556 | processing task, is_child = 0 3.12.447.669 I slot print_timing: id 0 | task 10556 | prompt eval time = 151.59 ms / 354 tokens ( 0.43 ms per token, 2335.25 tokens per second) 3.12.447.673 I slot print_timing: id 0 | task 10556 | eval time = 1621.48 ms / 107 tokens ( 15.30 ms per token, 65.37 tokens per second) 3.12.447.674 I slot print_timing: id 0 | task 10556 | total time = 1773.07 ms / 461 tokens 3.12.447.675 I slot print_timing: id 0 | task 10556 | graphs reused = 9954 3.12.447.676 I slot print_timing: id 0 | task 10556 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.447.710 I slot release: id 0 | task 10556 | stop processing: n_tokens = 492, truncated = 0 3.12.467.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 192352284 3.12.467.475 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 3.12.555.701 I slot launch_slot_: id 0 | task 10666 | processing task, is_child = 0 3.14.218.123 I slot print_timing: id 0 | task 10666 | prompt eval time = 172.60 ms / 438 tokens ( 0.39 ms per token, 2537.62 tokens per second) 3.14.218.128 I slot print_timing: id 0 | task 10666 | eval time = 1489.80 ms / 98 tokens ( 15.36 ms per token, 65.11 tokens per second) 3.14.218.130 I slot print_timing: id 0 | task 10666 | total time = 1662.40 ms / 536 tokens 3.14.218.131 I slot print_timing: id 0 | task 10666 | graphs reused = 10049 3.14.218.131 I slot print_timing: id 0 | task 10666 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.218.162 I slot release: id 0 | task 10666 | stop processing: n_tokens = 567, truncated = 0 3.14.234.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 194122736 3.14.235.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 3.14.327.360 I slot launch_slot_: id 0 | task 10767 | processing task, is_child = 0 3.15.561.269 I slot print_timing: id 0 | task 10767 | prompt eval time = 174.26 ms / 457 tokens ( 0.38 ms per token, 2622.49 tokens per second) 3.15.561.275 I slot print_timing: id 0 | task 10767 | eval time = 1059.63 ms / 70 tokens ( 15.36 ms per token, 65.12 tokens per second) 3.15.561.277 I slot print_timing: id 0 | task 10767 | total time = 1233.89 ms / 527 tokens 3.15.561.277 I slot print_timing: id 0 | task 10767 | graphs reused = 10116 3.15.561.278 I slot print_timing: id 0 | task 10767 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.561.311 I slot release: id 0 | task 10767 | stop processing: n_tokens = 558, truncated = 0 3.15.589.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 195465886 3.15.589.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 3.15.689.575 I slot launch_slot_: id 0 | task 10840 | processing task, is_child = 0 3.17.352.109 I slot print_timing: id 0 | task 10840 | prompt eval time = 175.69 ms / 473 tokens ( 0.37 ms per token, 2692.20 tokens per second) 3.17.352.116 I slot print_timing: id 0 | task 10840 | eval time = 1486.82 ms / 98 tokens ( 15.33 ms per token, 65.24 tokens per second) 3.17.352.118 I slot print_timing: id 0 | task 10840 | total time = 1662.51 ms / 571 tokens 3.17.352.118 I slot print_timing: id 0 | task 10840 | graphs reused = 10211 3.17.352.119 I slot print_timing: id 0 | task 10840 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.352.155 I slot release: id 0 | task 10840 | stop processing: n_tokens = 602, truncated = 0 3.17.379.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 197256729 3.17.379.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 3.17.473.861 I slot launch_slot_: id 0 | task 10941 | processing task, is_child = 0 3.18.739.461 I slot print_timing: id 0 | task 10941 | prompt eval time = 174.28 ms / 476 tokens ( 0.37 ms per token, 2731.27 tokens per second) 3.18.739.467 I slot print_timing: id 0 | task 10941 | eval time = 1091.30 ms / 72 tokens ( 15.37 ms per token, 65.06 tokens per second) 3.18.739.468 I slot print_timing: id 0 | task 10941 | total time = 1265.58 ms / 548 tokens 3.18.739.468 I slot print_timing: id 0 | task 10941 | graphs reused = 10280 3.18.739.469 I slot print_timing: id 0 | task 10941 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.739.502 I slot release: id 0 | task 10941 | stop processing: n_tokens = 579, truncated = 0 3.18.764.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 198644077 3.18.764.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 3.18.833.470 I slot launch_slot_: id 0 | task 11016 | processing task, is_child = 0 3.20.635.479 I slot print_timing: id 0 | task 11016 | prompt eval time = 178.67 ms / 466 tokens ( 0.38 ms per token, 2608.20 tokens per second) 3.20.635.485 I slot print_timing: id 0 | task 11016 | eval time = 1623.32 ms / 107 tokens ( 15.31 ms per token, 65.30 tokens per second) 3.20.635.486 I slot print_timing: id 0 | task 11016 | total time = 1801.99 ms / 573 tokens 3.20.635.487 I slot print_timing: id 0 | task 11016 | graphs reused = 10384 3.20.635.488 I slot print_timing: id 0 | task 11016 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.635.520 I slot release: id 0 | task 11016 | stop processing: n_tokens = 604, truncated = 0 3.20.656.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 200540094 3.20.656.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.20.747.828 I slot launch_slot_: id 0 | task 11126 | processing task, is_child = 0 3.22.085.560 I slot print_timing: id 0 | task 11126 | prompt eval time = 156.53 ms / 415 tokens ( 0.38 ms per token, 2651.18 tokens per second) 3.22.085.566 I slot print_timing: id 0 | task 11126 | eval time = 1181.18 ms / 78 tokens ( 15.34 ms per token, 65.19 tokens per second) 3.22.085.567 I slot print_timing: id 0 | task 11126 | total time = 1337.71 ms / 493 tokens 3.22.085.568 I slot print_timing: id 0 | task 11126 | graphs reused = 10459 3.22.085.569 I slot print_timing: id 0 | task 11126 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.085.599 I slot release: id 0 | task 11126 | stop processing: n_tokens = 524, truncated = 0 3.22.112.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 201990174 3.22.112.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.22.213.068 I slot launch_slot_: id 0 | task 11207 | processing task, is_child = 0 3.23.333.207 I slot print_timing: id 0 | task 11207 | prompt eval time = 155.29 ms / 352 tokens ( 0.44 ms per token, 2266.67 tokens per second) 3.23.333.213 I slot print_timing: id 0 | task 11207 | eval time = 964.83 ms / 64 tokens ( 15.31 ms per token, 65.30 tokens per second) 3.23.333.214 I slot print_timing: id 0 | task 11207 | total time = 1120.12 ms / 416 tokens 3.23.333.215 I slot print_timing: id 0 | task 11207 | graphs reused = 10521 3.23.333.215 I slot print_timing: id 0 | task 11207 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.333.244 I slot release: id 0 | task 11207 | stop processing: n_tokens = 447, truncated = 0 3.23.357.543 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 203237818 3.23.357.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 3.23.455.239 I slot launch_slot_: id 0 | task 11274 | processing task, is_child = 0 3.25.684.884 I slot print_timing: id 0 | task 11274 | prompt eval time = 199.41 ms / 550 tokens ( 0.36 ms per token, 2758.12 tokens per second) 3.25.684.890 I slot print_timing: id 0 | task 11274 | eval time = 2030.21 ms / 133 tokens ( 15.38 ms per token, 65.02 tokens per second) 3.25.684.891 I slot print_timing: id 0 | task 11274 | total time = 2229.62 ms / 683 tokens 3.25.684.892 I slot print_timing: id 0 | task 11274 | graphs reused = 10652 3.25.684.893 I slot print_timing: id 0 | task 11274 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.684.935 I slot release: id 0 | task 11274 | stop processing: n_tokens = 714, truncated = 0 3.25.690.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 205589509 3.25.690.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 3.25.795.470 I slot launch_slot_: id 0 | task 11411 | processing task, is_child = 0 3.29.036.024 I slot print_timing: id 0 | task 11411 | n_gen = 198, tg = 65.41 t/s, tg_3s = 65.74 t/s 3.29.468.332 I slot print_timing: id 0 | task 11411 | prompt eval time = 228.84 ms / 772 tokens ( 0.30 ms per token, 3373.54 tokens per second) 3.29.468.338 I slot print_timing: id 0 | task 11411 | eval time = 3444.00 ms / 226 tokens ( 15.31 ms per token, 65.33 tokens per second) 3.29.468.339 I slot print_timing: id 0 | task 11411 | total time = 3672.84 ms / 998 tokens 3.29.468.340 I slot print_timing: id 0 | task 11411 | graphs reused = 10875 3.29.468.340 I slot print_timing: id 0 | task 11411 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.468.381 I slot release: id 0 | task 11411 | stop processing: n_tokens = 1029, truncated = 0 3.29.492.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 209372955 3.29.492.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 3.29.597.861 I slot launch_slot_: id 0 | task 11641 | processing task, is_child = 0 3.32.583.151 I slot print_timing: id 0 | task 11641 | prompt eval time = 220.11 ms / 683 tokens ( 0.32 ms per token, 3102.98 tokens per second) 3.32.583.158 I slot print_timing: id 0 | task 11641 | eval time = 2765.16 ms / 181 tokens ( 15.36 ms per token, 65.10 tokens per second) 3.32.583.159 I slot print_timing: id 0 | task 11641 | total time = 2985.27 ms / 864 tokens 3.32.583.159 I slot print_timing: id 0 | task 11641 | graphs reused = 11053 3.32.583.160 I slot print_timing: id 0 | task 11641 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.583.199 I slot release: id 0 | task 11641 | stop processing: n_tokens = 895, truncated = 0 3.32.611.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 212487773 3.32.611.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 3.32.717.099 I slot launch_slot_: id 0 | task 11826 | processing task, is_child = 0 3.35.927.880 I slot print_timing: id 0 | task 11826 | n_gen = 198, tg = 65.43 t/s, tg_3s = 65.76 t/s 3.36.232.228 I slot print_timing: id 0 | task 11826 | prompt eval time = 200.03 ms / 579 tokens ( 0.35 ms per token, 2894.61 tokens per second) 3.36.232.233 I slot print_timing: id 0 | task 11826 | eval time = 3315.08 ms / 218 tokens ( 15.28 ms per token, 65.46 tokens per second) 3.36.232.234 I slot print_timing: id 0 | task 11826 | total time = 3515.11 ms / 797 tokens 3.36.232.235 I slot print_timing: id 0 | task 11826 | graphs reused = 11268 3.36.232.236 I slot print_timing: id 0 | task 11826 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.232.273 I slot release: id 0 | task 11826 | stop processing: n_tokens = 828, truncated = 0 3.36.256.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 216136847 3.36.256.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 3.36.276.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 3.36.380.263 I slot launch_slot_: id 0 | task 12048 | processing task, is_child = 0 3.38.170.566 I slot print_timing: id 0 | task 12048 | prompt eval time = 187.66 ms / 500 tokens ( 0.38 ms per token, 2664.35 tokens per second) 3.38.170.571 I slot print_timing: id 0 | task 12048 | eval time = 1602.62 ms / 106 tokens ( 15.26 ms per token, 65.52 tokens per second) 3.38.170.572 I slot print_timing: id 0 | task 12048 | total time = 1790.28 ms / 606 tokens 3.38.170.573 I slot print_timing: id 0 | task 12048 | graphs reused = 11372 3.38.170.574 I slot print_timing: id 0 | task 12048 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.170.607 I slot release: id 0 | task 12048 | stop processing: n_tokens = 637, truncated = 0 3.38.187.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 218075181 3.38.187.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 3.38.262.514 I slot launch_slot_: id 0 | task 12157 | processing task, is_child = 0 3.41.493.843 I slot print_timing: id 0 | task 12157 | n_gen = 198, tg = 65.58 t/s, tg_3s = 65.91 t/s 3.41.661.507 I slot print_timing: id 0 | task 12157 | prompt eval time = 227.21 ms / 776 tokens ( 0.29 ms per token, 3415.30 tokens per second) 3.41.661.513 I slot print_timing: id 0 | task 12157 | eval time = 3171.76 ms / 209 tokens ( 15.25 ms per token, 65.58 tokens per second) 3.41.661.514 I slot print_timing: id 0 | task 12157 | total time = 3398.97 ms / 985 tokens 3.41.661.515 I slot print_timing: id 0 | task 12157 | graphs reused = 11579 3.41.661.516 I slot print_timing: id 0 | task 12157 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.661.555 I slot release: id 0 | task 12157 | stop processing: n_tokens = 1016, truncated = 0 3.41.690.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 221566130 3.41.690.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 3.41.803.535 I slot launch_slot_: id 0 | task 12370 | processing task, is_child = 0 3.44.979.953 I slot print_timing: id 0 | task 12370 | prompt eval time = 189.14 ms / 504 tokens ( 0.38 ms per token, 2664.72 tokens per second) 3.44.979.959 I slot print_timing: id 0 | task 12370 | eval time = 2987.26 ms / 197 tokens ( 15.24 ms per token, 65.61 tokens per second) 3.44.979.960 I slot print_timing: id 0 | task 12370 | total time = 3176.40 ms / 701 tokens 3.44.979.961 I slot print_timing: id 0 | task 12370 | graphs reused = 11774 3.44.979.961 I slot print_timing: id 0 | task 12370 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.979.995 I slot release: id 0 | task 12370 | stop processing: n_tokens = 732, truncated = 0 3.45.002.685 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 224884570 3.45.002.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 3.45.102.157 I slot launch_slot_: id 0 | task 12570 | processing task, is_child = 0 3.48.310.087 I slot print_timing: id 0 | task 12570 | n_gen = 196, tg = 64.92 t/s, tg_3s = 65.25 t/s 3.48.477.730 I slot print_timing: id 0 | task 12570 | prompt eval time = 204.30 ms / 633 tokens ( 0.32 ms per token, 3098.37 tokens per second) 3.48.477.735 I slot print_timing: id 0 | task 12570 | eval time = 3171.25 ms / 207 tokens ( 15.39 ms per token, 64.96 tokens per second) 3.48.477.736 I slot print_timing: id 0 | task 12570 | total time = 3375.55 ms / 840 tokens 3.48.477.738 I slot print_timing: id 0 | task 12570 | graphs reused = 11978 3.48.477.739 I slot print_timing: id 0 | task 12570 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.477.776 I slot release: id 0 | task 12570 | stop processing: n_tokens = 871, truncated = 0 3.48.494.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 228382351 3.48.494.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.897 MiB) 3.48.603.388 I slot launch_slot_: id 0 | task 12781 | processing task, is_child = 0 3.50.808.876 I slot print_timing: id 0 | task 12781 | prompt eval time = 161.74 ms / 395 tokens ( 0.41 ms per token, 2442.19 tokens per second) 3.50.808.881 I slot print_timing: id 0 | task 12781 | eval time = 2043.73 ms / 134 tokens ( 15.37 ms per token, 65.08 tokens per second) 3.50.808.883 I slot print_timing: id 0 | task 12781 | total time = 2205.47 ms / 529 tokens 3.50.808.883 I slot print_timing: id 0 | task 12781 | graphs reused = 12109 3.50.808.884 I slot print_timing: id 0 | task 12781 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.808.915 I slot release: id 0 | task 12781 | stop processing: n_tokens = 560, truncated = 0 3.50.813.128 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 230713490 3.50.813.180 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.50.916.890 I slot launch_slot_: id 0 | task 12918 | processing task, is_child = 0 3.54.116.111 I slot print_timing: id 0 | task 12918 | n_gen = 197, tg = 65.30 t/s, tg_3s = 65.63 t/s 3.54.299.107 I slot print_timing: id 0 | task 12918 | prompt eval time = 197.69 ms / 584 tokens ( 0.34 ms per token, 2954.19 tokens per second) 3.54.299.112 I slot print_timing: id 0 | task 12918 | eval time = 3184.51 ms / 209 tokens ( 15.31 ms per token, 65.32 tokens per second) 3.54.299.113 I slot print_timing: id 0 | task 12918 | total time = 3382.20 ms / 793 tokens 3.54.299.114 I slot print_timing: id 0 | task 12918 | graphs reused = 12315 3.54.299.115 I slot print_timing: id 0 | task 12918 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.299.151 I slot release: id 0 | task 12918 | stop processing: n_tokens = 824, truncated = 0 3.54.316.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 234203725 3.54.316.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 3.54.419.186 I slot launch_slot_: id 0 | task 13131 | processing task, is_child = 0 3.57.642.783 I slot print_timing: id 0 | task 13131 | n_gen = 198, tg = 65.48 t/s, tg_3s = 65.81 t/s 3.58.130.702 I slot print_timing: id 0 | task 13131 | prompt eval time = 214.82 ms / 695 tokens ( 0.31 ms per token, 3235.22 tokens per second) 3.58.130.708 I slot print_timing: id 0 | task 13131 | eval time = 3496.67 ms / 230 tokens ( 15.27 ms per token, 65.49 tokens per second) 3.58.130.709 I slot print_timing: id 0 | task 13131 | total time = 3711.49 ms / 925 tokens 3.58.130.709 I slot print_timing: id 0 | task 13131 | graphs reused = 12542 3.58.130.710 I slot print_timing: id 0 | task 13131 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.130.748 I slot release: id 0 | task 13131 | stop processing: n_tokens = 956, truncated = 0 3.58.156.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 238035323 3.58.156.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 3.58.240.367 I slot launch_slot_: id 0 | task 13365 | processing task, is_child = 0 4.01.370.607 I slot print_timing: id 0 | task 13365 | prompt eval time = 229.63 ms / 769 tokens ( 0.30 ms per token, 3348.87 tokens per second) 4.01.370.613 I slot print_timing: id 0 | task 13365 | eval time = 2900.59 ms / 191 tokens ( 15.27 ms per token, 65.50 tokens per second) 4.01.370.614 I slot print_timing: id 0 | task 13365 | total time = 3130.22 ms / 960 tokens 4.01.370.615 I slot print_timing: id 0 | task 13365 | graphs reused = 12731 4.01.370.616 I slot print_timing: id 0 | task 13365 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.370.659 I slot release: id 0 | task 13365 | stop processing: n_tokens = 991, truncated = 0 4.01.385.853 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 241275233 4.01.385.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 4.01.405.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 4.01.518.930 I slot launch_slot_: id 0 | task 13560 | processing task, is_child = 0 4.03.595.924 I slot print_timing: id 0 | task 13560 | prompt eval time = 197.46 ms / 576 tokens ( 0.34 ms per token, 2917.03 tokens per second) 4.03.595.930 I slot print_timing: id 0 | task 13560 | eval time = 1879.51 ms / 124 tokens ( 15.28 ms per token, 65.44 tokens per second) 4.03.595.931 I slot print_timing: id 0 | task 13560 | total time = 2076.97 ms / 700 tokens 4.03.595.932 I slot print_timing: id 0 | task 13560 | graphs reused = 12853 4.03.595.932 I slot print_timing: id 0 | task 13560 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.595.969 I slot release: id 0 | task 13560 | stop processing: n_tokens = 731, truncated = 0 4.03.625.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 243500543 4.03.625.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 4.03.717.099 I slot launch_slot_: id 0 | task 13688 | processing task, is_child = 0 4.06.935.065 I slot print_timing: id 0 | task 13688 | n_gen = 198, tg = 65.45 t/s, tg_3s = 65.78 t/s 4.08.111.546 I slot print_timing: id 0 | task 13688 | prompt eval time = 208.09 ms / 655 tokens ( 0.32 ms per token, 3147.63 tokens per second) 4.08.111.552 I slot print_timing: id 0 | task 13688 | eval time = 4186.34 ms / 275 tokens ( 15.28 ms per token, 65.45 tokens per second) 4.08.111.553 I slot print_timing: id 0 | task 13688 | total time = 4394.43 ms / 930 tokens 4.08.111.553 I slot print_timing: id 0 | task 13688 | graphs reused = 13125 4.08.111.554 I slot print_timing: id 0 | task 13688 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.111.593 I slot release: id 0 | task 13688 | stop processing: n_tokens = 961, truncated = 0 4.08.129.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 248016167 4.08.129.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 4.08.242.184 I slot launch_slot_: id 0 | task 13967 | processing task, is_child = 0 4.10.286.440 I slot print_timing: id 0 | task 13967 | prompt eval time = 205.06 ms / 621 tokens ( 0.33 ms per token, 3028.35 tokens per second) 4.10.286.446 I slot print_timing: id 0 | task 13967 | eval time = 1839.17 ms / 121 tokens ( 15.33 ms per token, 65.25 tokens per second) 4.10.286.447 I slot print_timing: id 0 | task 13967 | total time = 2044.24 ms / 742 tokens 4.10.286.448 I slot print_timing: id 0 | task 13967 | graphs reused = 13243 4.10.286.448 I slot print_timing: id 0 | task 13967 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.286.486 I slot release: id 0 | task 13967 | stop processing: n_tokens = 773, truncated = 0 4.10.311.452 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 250191060 4.10.311.516 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 4.10.425.038 I slot launch_slot_: id 0 | task 14092 | processing task, is_child = 0 4.13.487.587 I slot print_timing: id 0 | task 14092 | prompt eval time = 224.63 ms / 767 tokens ( 0.29 ms per token, 3414.46 tokens per second) 4.13.487.592 I slot print_timing: id 0 | task 14092 | eval time = 2837.89 ms / 184 tokens ( 15.51 ms per token, 64.48 tokens per second) 4.13.487.593 I slot print_timing: id 0 | task 14092 | total time = 3062.53 ms / 951 tokens 4.13.487.594 I slot print_timing: id 0 | task 14092 | graphs reused = 13425 4.13.487.595 I slot print_timing: id 0 | task 14092 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.487.640 I slot release: id 0 | task 14092 | stop processing: n_tokens = 982, truncated = 0 4.13.506.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 253392214 4.13.506.162 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 4.13.586.644 I slot launch_slot_: id 0 | task 14280 | processing task, is_child = 0 4.16.849.862 I slot print_timing: id 0 | task 14280 | n_gen = 195, tg = 64.37 t/s, tg_3s = 64.71 t/s 4.16.974.162 I slot print_timing: id 0 | task 14280 | prompt eval time = 249.60 ms / 864 tokens ( 0.29 ms per token, 3461.55 tokens per second) 4.16.974.168 I slot print_timing: id 0 | task 14280 | eval time = 3137.89 ms / 203 tokens ( 15.53 ms per token, 64.37 tokens per second) 4.16.974.170 I slot print_timing: id 0 | task 14280 | total time = 3387.49 ms / 1067 tokens 4.16.974.171 I slot print_timing: id 0 | task 14280 | graphs reused = 13625 4.16.974.171 I slot print_timing: id 0 | task 14280 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.974.222 I slot release: id 0 | task 14280 | stop processing: n_tokens = 1098, truncated = 0 4.17.003.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 256878796 4.17.003.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 4.17.025.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 4.17.153.952 I slot launch_slot_: id 0 | task 14487 | processing task, is_child = 0 4.19.332.559 I slot print_timing: id 0 | task 14487 | prompt eval time = 217.94 ms / 646 tokens ( 0.34 ms per token, 2964.10 tokens per second) 4.19.332.565 I slot print_timing: id 0 | task 14487 | eval time = 1960.65 ms / 129 tokens ( 15.32 ms per token, 65.28 tokens per second) 4.19.332.566 I slot print_timing: id 0 | task 14487 | total time = 2178.59 ms / 775 tokens 4.19.332.566 I slot print_timing: id 0 | task 14487 | graphs reused = 13751 4.19.332.567 I slot print_timing: id 0 | task 14487 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.332.606 I slot release: id 0 | task 14487 | stop processing: n_tokens = 806, truncated = 0 4.19.356.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 259237180 4.19.356.876 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 4.19.450.661 I slot launch_slot_: id 0 | task 14620 | processing task, is_child = 0 4.22.673.080 I slot print_timing: id 0 | task 14620 | n_gen = 192, tg = 63.60 t/s, tg_3s = 63.93 t/s 4.23.133.915 I slot print_timing: id 0 | task 14620 | prompt eval time = 219.26 ms / 720 tokens ( 0.30 ms per token, 3283.83 tokens per second) 4.23.133.921 I slot print_timing: id 0 | task 14620 | eval time = 3463.98 ms / 222 tokens ( 15.67 ms per token, 63.80 tokens per second) 4.23.133.922 I slot print_timing: id 0 | task 14620 | total time = 3683.23 ms / 942 tokens 4.23.133.923 I slot print_timing: id 0 | task 14620 | graphs reused = 13970 4.23.133.924 I slot print_timing: id 0 | task 14620 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.133.967 I slot release: id 0 | task 14620 | stop processing: n_tokens = 973, truncated = 0 4.23.160.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 263038541 4.23.160.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 4.23.239.140 I slot launch_slot_: id 0 | task 14846 | processing task, is_child = 0 4.26.427.609 I slot print_timing: id 0 | task 14846 | n_gen = 198, tg = 65.59 t/s, tg_3s = 65.92 t/s 4.26.671.058 I slot print_timing: id 0 | task 14846 | prompt eval time = 184.81 ms / 509 tokens ( 0.36 ms per token, 2754.15 tokens per second) 4.26.671.065 I slot print_timing: id 0 | task 14846 | eval time = 3247.09 ms / 214 tokens ( 15.24 ms per token, 65.60 tokens per second) 4.26.671.067 I slot print_timing: id 0 | task 14846 | total time = 3431.90 ms / 723 tokens 4.26.671.068 I slot print_timing: id 0 | task 14846 | graphs reused = 14182 4.26.671.069 I slot print_timing: id 0 | task 14846 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.671.106 I slot release: id 0 | task 14846 | stop processing: n_tokens = 754, truncated = 0 4.26.687.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 266575680 4.26.687.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 4.26.784.661 I slot launch_slot_: id 0 | task 15063 | processing task, is_child = 0 4.29.989.524 I slot print_timing: id 0 | task 15063 | n_gen = 198, tg = 65.49 t/s, tg_3s = 65.83 t/s 4.30.659.935 I slot print_timing: id 0 | task 15063 | prompt eval time = 196.90 ms / 581 tokens ( 0.34 ms per token, 2950.69 tokens per second) 4.30.659.941 I slot print_timing: id 0 | task 15063 | eval time = 3678.35 ms / 242 tokens ( 15.26 ms per token, 65.52 tokens per second) 4.30.659.942 I slot print_timing: id 0 | task 15063 | total time = 3875.25 ms / 823 tokens 4.30.659.943 I slot print_timing: id 0 | task 15063 | graphs reused = 14421 4.30.659.944 I slot print_timing: id 0 | task 15063 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.659.983 I slot release: id 0 | task 15063 | stop processing: n_tokens = 854, truncated = 0 4.30.679.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 270564557 4.30.679.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 4.30.783.795 I slot launch_slot_: id 0 | task 15309 | processing task, is_child = 0 4.34.055.057 I slot print_timing: id 0 | task 15309 | n_gen = 198, tg = 65.37 t/s, tg_3s = 65.70 t/s 4.34.390.381 I slot print_timing: id 0 | task 15309 | prompt eval time = 257.55 ms / 925 tokens ( 0.28 ms per token, 3591.58 tokens per second) 4.34.390.386 I slot print_timing: id 0 | task 15309 | eval time = 3349.02 ms / 220 tokens ( 15.29 ms per token, 65.39 tokens per second) 4.34.390.387 I slot print_timing: id 0 | task 15309 | total time = 3606.56 ms / 1145 tokens 4.34.390.388 I slot print_timing: id 0 | task 15309 | graphs reused = 14638 4.34.390.389 I slot print_timing: id 0 | task 15309 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.390.435 I slot release: id 0 | task 15309 | stop processing: n_tokens = 1176, truncated = 0 4.34.414.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 274295009 4.34.414.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 4.34.511.817 I slot launch_slot_: id 0 | task 15533 | processing task, is_child = 0 4.37.762.724 I slot print_timing: id 0 | task 15533 | n_gen = 195, tg = 64.53 t/s, tg_3s = 64.86 t/s 4.38.525.708 I slot print_timing: id 0 | task 15533 | prompt eval time = 244.55 ms / 885 tokens ( 0.28 ms per token, 3618.94 tokens per second) 4.38.525.714 I slot print_timing: id 0 | task 15533 | eval time = 3769.32 ms / 245 tokens ( 15.45 ms per token, 64.73 tokens per second) 4.38.525.715 I slot print_timing: id 0 | task 15533 | total time = 4013.87 ms / 1130 tokens 4.38.525.716 I slot print_timing: id 0 | task 15533 | graphs reused = 14880 4.38.525.716 I slot print_timing: id 0 | task 15533 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.525.762 I slot release: id 0 | task 15533 | stop processing: n_tokens = 1161, truncated = 0 4.38.543.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 278430336 4.38.543.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 4.38.659.236 I slot launch_slot_: id 0 | task 15782 | processing task, is_child = 0 4.40.405.992 I slot print_timing: id 0 | task 15782 | prompt eval time = 157.79 ms / 392 tokens ( 0.40 ms per token, 2484.25 tokens per second) 4.40.405.997 I slot print_timing: id 0 | task 15782 | eval time = 1588.94 ms / 105 tokens ( 15.28 ms per token, 65.45 tokens per second) 4.40.405.998 I slot print_timing: id 0 | task 15782 | total time = 1746.74 ms / 497 tokens 4.40.406.001 I slot print_timing: id 0 | task 15782 | graphs reused = 14982 4.40.406.001 I slot print_timing: id 0 | task 15782 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.406.034 I slot release: id 0 | task 15782 | stop processing: n_tokens = 528, truncated = 0 4.40.409.602 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 528, t_last = 280310608 4.40.409.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 4.40.499.204 I slot launch_slot_: id 0 | task 15890 | processing task, is_child = 0 4.42.565.374 I slot print_timing: id 0 | task 15890 | prompt eval time = 145.97 ms / 331 tokens ( 0.44 ms per token, 2267.53 tokens per second) 4.42.565.379 I slot print_timing: id 0 | task 15890 | eval time = 1920.18 ms / 127 tokens ( 15.24 ms per token, 65.62 tokens per second) 4.42.565.380 I slot print_timing: id 0 | task 15890 | total time = 2066.15 ms / 458 tokens 4.42.565.381 I slot print_timing: id 0 | task 15890 | graphs reused = 15107 4.42.565.382 I slot print_timing: id 0 | task 15890 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.565.412 I slot release: id 0 | task 15890 | stop processing: n_tokens = 489, truncated = 0 4.42.588.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 282469986 4.42.588.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 4.42.684.549 I slot launch_slot_: id 0 | task 16020 | processing task, is_child = 0 4.45.099.226 I slot print_timing: id 0 | task 16020 | prompt eval time = 153.87 ms / 357 tokens ( 0.43 ms per token, 2320.11 tokens per second) 4.45.099.232 I slot print_timing: id 0 | task 16020 | eval time = 2260.78 ms / 149 tokens ( 15.28 ms per token, 65.46 tokens per second) 4.45.099.233 I slot print_timing: id 0 | task 16020 | total time = 2414.65 ms / 506 tokens 4.45.099.236 I slot print_timing: id 0 | task 16020 | graphs reused = 15253 4.45.099.237 I slot print_timing: id 0 | task 16020 | graph reallocs = 0 / 0 (same size) / (changed size) 4.45.099.273 I slot release: id 0 | task 16020 | stop processing: n_tokens = 537, truncated = 0 4.45.102.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 285003847 4.45.102.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 4.45.199.073 I slot launch_slot_: id 0 | task 16172 | processing task, is_child = 0 4.46.129.701 I slot print_timing: id 0 | task 16172 | prompt eval time = 151.24 ms / 315 tokens ( 0.48 ms per token, 2082.73 tokens per second) 4.46.129.706 I slot print_timing: id 0 | task 16172 | eval time = 779.36 ms / 52 tokens ( 15.28 ms per token, 65.44 tokens per second) 4.46.129.707 I slot print_timing: id 0 | task 16172 | total time = 930.61 ms / 367 tokens 4.46.129.708 I slot print_timing: id 0 | task 16172 | graphs reused = 15303 4.46.129.709 I slot print_timing: id 0 | task 16172 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.129.738 I slot release: id 0 | task 16172 | stop processing: n_tokens = 398, truncated = 0 4.46.144.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 286034313 4.46.144.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 4.46.230.342 I slot launch_slot_: id 0 | task 16227 | processing task, is_child = 0 4.47.616.946 I slot print_timing: id 0 | task 16227 | prompt eval time = 150.93 ms / 378 tokens ( 0.40 ms per token, 2504.56 tokens per second) 4.47.616.952 I slot print_timing: id 0 | task 16227 | eval time = 1235.66 ms / 82 tokens ( 15.26 ms per token, 65.55 tokens per second) 4.47.616.953 I slot print_timing: id 0 | task 16227 | total time = 1386.58 ms / 460 tokens 4.47.616.954 I slot print_timing: id 0 | task 16227 | graphs reused = 15383 4.47.616.955 I slot print_timing: id 0 | task 16227 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.616.984 I slot release: id 0 | task 16227 | stop processing: n_tokens = 491, truncated = 0 4.47.636.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 287521559 4.47.636.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 4.47.733.615 I slot launch_slot_: id 0 | task 16312 | processing task, is_child = 0 4.48.291.431 I slot print_timing: id 0 | task 16312 | prompt eval time = 141.25 ms / 295 tokens ( 0.48 ms per token, 2088.55 tokens per second) 4.48.291.437 I slot print_timing: id 0 | task 16312 | eval time = 416.55 ms / 28 tokens ( 15.43 ms per token, 64.82 tokens per second) 4.48.291.438 I slot print_timing: id 0 | task 16312 | total time = 557.79 ms / 323 tokens 4.48.291.440 I slot print_timing: id 0 | task 16312 | graphs reused = 15409 4.48.291.441 I slot print_timing: id 0 | task 16312 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.291.473 I slot release: id 0 | task 16312 | stop processing: n_tokens = 354, truncated = 0 4.48.309.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 288196048 4.48.309.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 4.48.398.317 I slot launch_slot_: id 0 | task 16343 | processing task, is_child = 0 4.51.553.185 I slot print_timing: id 0 | task 16343 | n_gen = 198, tg = 65.57 t/s, tg_3s = 65.90 t/s 4.51.614.039 I slot print_timing: id 0 | task 16343 | prompt eval time = 150.20 ms / 337 tokens ( 0.45 ms per token, 2243.69 tokens per second) 4.51.614.044 I slot print_timing: id 0 | task 16343 | eval time = 3065.51 ms / 202 tokens ( 15.25 ms per token, 65.57 tokens per second) 4.51.614.045 I slot print_timing: id 0 | task 16343 | total time = 3215.70 ms / 539 tokens 4.51.614.047 I slot print_timing: id 0 | task 16343 | graphs reused = 15608 4.51.614.048 I slot print_timing: id 0 | task 16343 | graph reallocs = 0 / 0 (same size) / (changed size) 4.51.614.076 I slot release: id 0 | task 16343 | stop processing: n_tokens = 570, truncated = 0 4.51.617.821 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 570, t_last = 291518650 4.51.617.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 4.51.712.502 I slot launch_slot_: id 0 | task 16548 | processing task, is_child = 0 4.53.235.725 I slot print_timing: id 0 | task 16548 | prompt eval time = 147.91 ms / 325 tokens ( 0.46 ms per token, 2197.30 tokens per second) 4.53.235.731 I slot print_timing: id 0 | task 16548 | eval time = 1375.30 ms / 91 tokens ( 15.28 ms per token, 65.44 tokens per second) 4.53.235.732 I slot print_timing: id 0 | task 16548 | total time = 1523.20 ms / 416 tokens 4.53.235.733 I slot print_timing: id 0 | task 16548 | graphs reused = 15697 4.53.235.734 I slot print_timing: id 0 | task 16548 | graph reallocs = 0 / 0 (same size) / (changed size) 4.53.235.762 I slot release: id 0 | task 16548 | stop processing: n_tokens = 447, truncated = 0 4.53.252.368 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.072 4.53.316.465 I slot launch_slot_: id 0 | task 16642 | processing task, is_child = 0 4.54.907.213 I slot print_timing: id 0 | task 16642 | prompt eval time = 136.69 ms / 264 tokens ( 0.52 ms per token, 1931.42 tokens per second) 4.54.907.218 I slot print_timing: id 0 | task 16642 | eval time = 1454.04 ms / 95 tokens ( 15.47 ms per token, 64.65 tokens per second) 4.54.907.219 I slot print_timing: id 0 | task 16642 | total time = 1590.73 ms / 359 tokens 4.54.907.220 I slot print_timing: id 0 | task 16642 | graphs reused = 15790 4.54.907.221 I slot print_timing: id 0 | task 16642 | graph reallocs = 0 / 0 (same size) / (changed size) 4.54.907.246 I slot release: id 0 | task 16642 | stop processing: n_tokens = 390, truncated = 0 4.54.933.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 294811820 4.54.933.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 4.55.024.172 I slot launch_slot_: id 0 | task 16740 | processing task, is_child = 0 4.55.484.266 I slot print_timing: id 0 | task 16740 | prompt eval time = 150.16 ms / 331 tokens ( 0.45 ms per token, 2204.33 tokens per second) 4.55.484.271 I slot print_timing: id 0 | task 16740 | eval time = 309.92 ms / 21 tokens ( 15.50 ms per token, 64.53 tokens per second) 4.55.484.273 I slot print_timing: id 0 | task 16740 | total time = 460.07 ms / 352 tokens 4.55.484.273 I slot print_timing: id 0 | task 16740 | graphs reused = 15809 4.55.484.275 I slot print_timing: id 0 | task 16740 | graph reallocs = 0 / 0 (same size) / (changed size) 4.55.484.303 I slot release: id 0 | task 16740 | stop processing: n_tokens = 383, truncated = 0 4.55.509.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 295388877 4.55.509.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 4.55.613.741 I slot launch_slot_: id 0 | task 16764 | processing task, is_child = 0 4.57.582.993 I slot print_timing: id 0 | task 16764 | prompt eval time = 150.72 ms / 333 tokens ( 0.45 ms per token, 2209.39 tokens per second) 4.57.582.998 I slot print_timing: id 0 | task 16764 | eval time = 1818.51 ms / 120 tokens ( 15.28 ms per token, 65.44 tokens per second) 4.57.582.999 I slot print_timing: id 0 | task 16764 | total time = 1969.23 ms / 453 tokens 4.57.583.000 I slot print_timing: id 0 | task 16764 | graphs reused = 15927 4.57.583.000 I slot print_timing: id 0 | task 16764 | graph reallocs = 0 / 0 (same size) / (changed size) 4.57.583.028 I slot release: id 0 | task 16764 | stop processing: n_tokens = 484, truncated = 0 4.57.610.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 297487602 4.57.610.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 4.57.686.320 I slot launch_slot_: id 0 | task 16887 | processing task, is_child = 0 4.58.631.133 I slot print_timing: id 0 | task 16887 | prompt eval time = 147.63 ms / 346 tokens ( 0.43 ms per token, 2343.74 tokens per second) 4.58.631.139 I slot print_timing: id 0 | task 16887 | eval time = 797.16 ms / 53 tokens ( 15.33 ms per token, 65.23 tokens per second) 4.58.631.140 I slot print_timing: id 0 | task 16887 | total time = 944.79 ms / 399 tokens 4.58.631.141 I slot print_timing: id 0 | task 16887 | graphs reused = 15978 4.58.631.142 I slot print_timing: id 0 | task 16887 | graph reallocs = 0 / 0 (same size) / (changed size) 4.58.631.172 I slot release: id 0 | task 16887 | stop processing: n_tokens = 430, truncated = 0 4.58.657.933 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 298535746 4.58.657.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 4.58.754.940 I slot launch_slot_: id 0 | task 16943 | processing task, is_child = 0 4.59.717.315 I slot print_timing: id 0 | task 16943 | prompt eval time = 150.98 ms / 325 tokens ( 0.46 ms per token, 2152.60 tokens per second) 4.59.717.321 I slot print_timing: id 0 | task 16943 | eval time = 811.38 ms / 54 tokens ( 15.31 ms per token, 65.32 tokens per second) 4.59.717.322 I slot print_timing: id 0 | task 16943 | total time = 962.36 ms / 379 tokens 4.59.717.323 I slot print_timing: id 0 | task 16943 | graphs reused = 16030 4.59.717.324 I slot print_timing: id 0 | task 16943 | graph reallocs = 0 / 0 (same size) / (changed size) 4.59.717.353 I slot release: id 0 | task 16943 | stop processing: n_tokens = 410, truncated = 0 4.59.734.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 299621927 4.59.734.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 4.59.823.917 I slot launch_slot_: id 0 | task 17000 | processing task, is_child = 0 5.02.986.988 I slot print_timing: id 0 | task 17000 | n_gen = 197, tg = 65.04 t/s, tg_3s = 65.37 t/s 5.03.109.374 I slot print_timing: id 0 | task 17000 | prompt eval time = 149.54 ms / 322 tokens ( 0.46 ms per token, 2153.24 tokens per second) 5.03.109.380 I slot print_timing: id 0 | task 17000 | eval time = 3135.89 ms / 205 tokens ( 15.37 ms per token, 65.05 tokens per second) 5.03.109.381 I slot print_timing: id 0 | task 17000 | total time = 3285.43 ms / 527 tokens 5.03.109.382 I slot print_timing: id 0 | task 17000 | graphs reused = 16232 5.03.109.383 I slot print_timing: id 0 | task 17000 | graph reallocs = 0 / 0 (same size) / (changed size) 5.03.109.414 I slot release: id 0 | task 17000 | stop processing: n_tokens = 558, truncated = 0 5.03.113.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 303013988 5.03.186.262 I slot launch_slot_: id 0 | task 17208 | processing task, is_child = 0 5.06.336.852 I slot print_timing: id 0 | task 17208 | n_gen = 197, tg = 65.26 t/s, tg_3s = 65.60 t/s 5.09.003.394 I slot print_timing: id 0 | task 17208 | prompt eval time = 147.42 ms / 338 tokens ( 0.44 ms per token, 2292.82 tokens per second) 5.09.003.400 I slot print_timing: id 0 | task 17208 | eval time = 5669.69 ms / 372 tokens ( 15.28 ms per token, 65.44 tokens per second) 5.09.003.401 I slot print_timing: id 0 | task 17208 | total time = 5817.11 ms / 710 tokens 5.09.003.401 I slot print_timing: id 0 | task 17208 | graphs reused = 16601 5.09.003.402 I slot print_timing: id 0 | task 17208 | graph reallocs = 0 / 0 (same size) / (changed size) 5.09.003.431 I slot release: id 0 | task 17208 | stop processing: n_tokens = 741, truncated = 0 5.09.018.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 308908005 5.09.018.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 5.09.113.067 I slot launch_slot_: id 0 | task 17583 | processing task, is_child = 0 5.12.264.107 I slot print_timing: id 0 | task 17583 | n_gen = 198, tg = 65.60 t/s, tg_3s = 65.93 t/s 5.14.014.142 I slot print_timing: id 0 | task 17583 | prompt eval time = 147.80 ms / 347 tokens ( 0.43 ms per token, 2347.81 tokens per second) 5.14.014.148 I slot print_timing: id 0 | task 17583 | eval time = 4753.26 ms / 313 tokens ( 15.23 ms per token, 65.64 tokens per second) 5.14.014.150 I slot print_timing: id 0 | task 17583 | total time = 4901.05 ms / 660 tokens 5.14.014.151 I slot print_timing: id 0 | task 17583 | graphs reused = 16911 5.14.014.152 I slot print_timing: id 0 | task 17583 | graph reallocs = 0 / 0 (same size) / (changed size) 5.14.014.183 I slot release: id 0 | task 17583 | stop processing: n_tokens = 691, truncated = 0 5.14.031.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 313918757 5.14.031.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 5.14.129.503 I slot launch_slot_: id 0 | task 17899 | processing task, is_child = 0 5.16.168.298 I slot print_timing: id 0 | task 17899 | prompt eval time = 146.95 ms / 331 tokens ( 0.44 ms per token, 2252.41 tokens per second) 5.16.168.303 I slot print_timing: id 0 | task 17899 | eval time = 1891.82 ms / 125 tokens ( 15.26 ms per token, 65.55 tokens per second) 5.16.168.304 I slot print_timing: id 0 | task 17899 | total time = 2038.77 ms / 456 tokens 5.16.168.305 I slot print_timing: id 0 | task 17899 | graphs reused = 17034 5.16.168.306 I slot print_timing: id 0 | task 17899 | graph reallocs = 0 / 0 (same size) / (changed size) 5.16.168.334 I slot release: id 0 | task 17899 | stop processing: n_tokens = 487, truncated = 0 5.16.184.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 487, t_last = 316072908 5.16.184.912 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.464 MiB) 5.16.261.465 I slot launch_slot_: id 0 | task 18027 | processing task, is_child = 0 5.18.023.006 I slot print_timing: id 0 | task 18027 | prompt eval time = 146.27 ms / 345 tokens ( 0.42 ms per token, 2358.62 tokens per second) 5.18.023.011 I slot print_timing: id 0 | task 18027 | eval time = 1615.25 ms / 107 tokens ( 15.24 ms per token, 65.62 tokens per second) 5.18.023.012 I slot print_timing: id 0 | task 18027 | total time = 1761.52 ms / 452 tokens 5.18.023.013 I slot print_timing: id 0 | task 18027 | graphs reused = 17139 5.18.023.014 I slot print_timing: id 0 | task 18027 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.023.043 I slot release: id 0 | task 18027 | stop processing: n_tokens = 483, truncated = 0 5.18.044.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 317927617 5.18.044.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 5.18.138.133 I slot launch_slot_: id 0 | task 18137 | processing task, is_child = 0 5.19.082.856 I slot print_timing: id 0 | task 18137 | prompt eval time = 147.16 ms / 320 tokens ( 0.46 ms per token, 2174.50 tokens per second) 5.19.082.862 I slot print_timing: id 0 | task 18137 | eval time = 797.54 ms / 53 tokens ( 15.34 ms per token, 65.20 tokens per second) 5.19.082.863 I slot print_timing: id 0 | task 18137 | total time = 944.70 ms / 373 tokens 5.19.082.864 I slot print_timing: id 0 | task 18137 | graphs reused = 17190 5.19.082.865 I slot print_timing: id 0 | task 18137 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.082.897 I slot release: id 0 | task 18137 | stop processing: n_tokens = 404, truncated = 0 5.19.096.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 318987472 5.19.096.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 5.19.185.284 I slot launch_slot_: id 0 | task 18193 | processing task, is_child = 0 5.19.832.544 I slot print_timing: id 0 | task 18193 | prompt eval time = 141.73 ms / 297 tokens ( 0.48 ms per token, 2095.52 tokens per second) 5.19.832.550 I slot print_timing: id 0 | task 18193 | eval time = 505.51 ms / 34 tokens ( 15.32 ms per token, 65.28 tokens per second) 5.19.832.551 I slot print_timing: id 0 | task 18193 | total time = 647.24 ms / 331 tokens 5.19.832.552 I slot print_timing: id 0 | task 18193 | graphs reused = 17222 5.19.832.553 I slot print_timing: id 0 | task 18193 | graph reallocs = 0 / 0 (same size) / (changed size) 5.19.832.580 I slot release: id 0 | task 18193 | stop processing: n_tokens = 362, truncated = 0 5.19.848.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 319737154 5.19.848.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.183 MiB) 5.19.919.542 I slot launch_slot_: id 0 | task 18230 | processing task, is_child = 0 5.23.077.050 I slot print_timing: id 0 | task 18230 | n_gen = 198, tg = 65.43 t/s, tg_3s = 65.76 t/s 5.23.290.653 I slot print_timing: id 0 | task 18230 | prompt eval time = 146.69 ms / 343 tokens ( 0.43 ms per token, 2338.33 tokens per second) 5.23.290.661 I slot print_timing: id 0 | task 18230 | eval time = 3224.40 ms / 212 tokens ( 15.28 ms per token, 65.44 tokens per second) 5.23.290.662 I slot print_timing: id 0 | task 18230 | total time = 3371.09 ms / 555 tokens 5.23.290.663 I slot print_timing: id 0 | task 18230 | graphs reused = 17431 5.23.290.664 I slot print_timing: id 0 | task 18230 | graph reallocs = 0 / 0 (same size) / (changed size) 5.23.290.703 I slot release: id 0 | task 18230 | stop processing: n_tokens = 586, truncated = 0 5.23.314.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 323195277 5.23.377.324 I slot launch_slot_: id 0 | task 18445 | processing task, is_child = 0 5.24.371.287 I slot print_timing: id 0 | task 18445 | prompt eval time = 153.44 ms / 371 tokens ( 0.41 ms per token, 2417.84 tokens per second) 5.24.371.293 I slot print_timing: id 0 | task 18445 | eval time = 840.50 ms / 56 tokens ( 15.28 ms per token, 65.44 tokens per second) 5.24.371.294 I slot print_timing: id 0 | task 18445 | total time = 993.94 ms / 427 tokens 5.24.371.294 I slot print_timing: id 0 | task 18445 | graphs reused = 17485 5.24.371.295 I slot print_timing: id 0 | task 18445 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.371.328 I slot release: id 0 | task 18445 | stop processing: n_tokens = 458, truncated = 0 5.24.387.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 324275902 5.24.387.762 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 5.24.477.217 I slot launch_slot_: id 0 | task 18504 | processing task, is_child = 0 5.26.474.213 I slot print_timing: id 0 | task 18504 | prompt eval time = 139.98 ms / 292 tokens ( 0.48 ms per token, 2086.03 tokens per second) 5.26.474.221 I slot print_timing: id 0 | task 18504 | eval time = 1857.00 ms / 123 tokens ( 15.22 ms per token, 65.70 tokens per second) 5.26.474.222 I slot print_timing: id 0 | task 18504 | total time = 1996.98 ms / 415 tokens 5.26.474.223 I slot print_timing: id 0 | task 18504 | graphs reused = 17606 5.26.474.224 I slot print_timing: id 0 | task 18504 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.474.253 I slot release: id 0 | task 18504 | stop processing: n_tokens = 446, truncated = 0 5.26.488.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 326378827 5.26.488.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 5.26.582.402 I slot launch_slot_: id 0 | task 18630 | processing task, is_child = 0 5.26.986.676 I slot print_timing: id 0 | task 18630 | prompt eval time = 141.41 ms / 301 tokens ( 0.47 ms per token, 2128.55 tokens per second) 5.26.986.683 I slot print_timing: id 0 | task 18630 | eval time = 262.84 ms / 18 tokens ( 15.46 ms per token, 64.68 tokens per second) 5.26.986.684 I slot print_timing: id 0 | task 18630 | total time = 404.25 ms / 319 tokens 5.26.986.685 I slot print_timing: id 0 | task 18630 | graphs reused = 17622 5.26.986.686 I slot print_timing: id 0 | task 18630 | graph reallocs = 0 / 0 (same size) / (changed size) 5.26.986.716 I slot release: id 0 | task 18630 | stop processing: n_tokens = 350, truncated = 0 5.27.015.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 326891290 5.27.015.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 5.27.110.507 I slot launch_slot_: id 0 | task 18651 | processing task, is_child = 0 5.28.307.717 I slot print_timing: id 0 | task 18651 | prompt eval time = 143.46 ms / 303 tokens ( 0.47 ms per token, 2112.10 tokens per second) 5.28.307.722 I slot print_timing: id 0 | task 18651 | eval time = 1053.73 ms / 70 tokens ( 15.27 ms per token, 65.48 tokens per second) 5.28.307.724 I slot print_timing: id 0 | task 18651 | total time = 1197.19 ms / 373 tokens 5.28.307.724 I slot print_timing: id 0 | task 18651 | graphs reused = 17690 5.28.307.725 I slot print_timing: id 0 | task 18651 | graph reallocs = 0 / 0 (same size) / (changed size) 5.28.307.752 I slot release: id 0 | task 18651 | stop processing: n_tokens = 404, truncated = 0 5.28.324.346 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 328212326 5.28.324.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 5.28.412.559 I slot launch_slot_: id 0 | task 18724 | processing task, is_child = 0 5.29.020.824 I slot print_timing: id 0 | task 18724 | prompt eval time = 147.38 ms / 321 tokens ( 0.46 ms per token, 2178.09 tokens per second) 5.29.020.830 I slot print_timing: id 0 | task 18724 | eval time = 460.87 ms / 31 tokens ( 15.36 ms per token, 65.09 tokens per second) 5.29.020.831 I slot print_timing: id 0 | task 18724 | total time = 608.25 ms / 352 tokens 5.29.020.832 I slot print_timing: id 0 | task 18724 | graphs reused = 17719 5.29.020.832 I slot print_timing: id 0 | task 18724 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.020.862 I slot release: id 0 | task 18724 | stop processing: n_tokens = 383, truncated = 0 5.29.046.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 328925436 5.29.046.460 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.016 MiB) 5.29.124.112 I slot launch_slot_: id 0 | task 18758 | processing task, is_child = 0 5.29.554.436 I slot print_timing: id 0 | task 18758 | prompt eval time = 152.25 ms / 322 tokens ( 0.47 ms per token, 2114.97 tokens per second) 5.29.554.441 I slot print_timing: id 0 | task 18758 | eval time = 278.06 ms / 19 tokens ( 15.45 ms per token, 64.74 tokens per second) 5.29.554.442 I slot print_timing: id 0 | task 18758 | total time = 430.30 ms / 341 tokens 5.29.554.443 I slot print_timing: id 0 | task 18758 | graphs reused = 17736 5.29.554.444 I slot print_timing: id 0 | task 18758 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.554.472 I slot release: id 0 | task 18758 | stop processing: n_tokens = 372, truncated = 0 5.29.577.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 329459046 5.29.577.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.796 MiB) 5.29.656.234 I slot launch_slot_: id 0 | task 18780 | processing task, is_child = 0 5.32.214.558 I slot print_timing: id 0 | task 18780 | prompt eval time = 147.61 ms / 323 tokens ( 0.46 ms per token, 2188.15 tokens per second) 5.32.214.563 I slot print_timing: id 0 | task 18780 | eval time = 2410.69 ms / 158 tokens ( 15.35 ms per token, 65.13 tokens per second) 5.32.214.564 I slot print_timing: id 0 | task 18780 | total time = 2558.30 ms / 481 tokens 5.32.214.565 I slot print_timing: id 0 | task 18780 | graphs reused = 17892 5.32.214.566 I slot print_timing: id 0 | task 18780 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.214.593 I slot release: id 0 | task 18780 | stop processing: n_tokens = 512, truncated = 0 5.32.238.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 332119167 5.32.238.147 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.297 MiB) 5.32.322.061 I slot launch_slot_: id 0 | task 18941 | processing task, is_child = 0 5.35.478.896 I slot print_timing: id 0 | task 18941 | n_gen = 198, tg = 65.47 t/s, tg_3s = 65.80 t/s 5.38.479.883 I slot print_timing: id 0 | task 18941 | n_gen = 395, tg = 65.56 t/s, tg_3s = 65.65 t/s 5.40.769.656 I slot print_timing: id 0 | task 18941 | prompt eval time = 147.82 ms / 321 tokens ( 0.46 ms per token, 2171.50 tokens per second) 5.40.769.661 I slot print_timing: id 0 | task 18941 | eval time = 8299.75 ms / 545 tokens ( 15.26 ms per token, 65.54 tokens per second) 5.40.769.662 I slot print_timing: id 0 | task 18941 | total time = 8447.58 ms / 866 tokens 5.40.769.663 I slot print_timing: id 0 | task 18941 | graphs reused = 18433 5.40.769.664 I slot print_timing: id 0 | task 18941 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.769.691 I slot release: id 0 | task 18941 | stop processing: n_tokens = 897, truncated = 0 5.40.792.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 340674265 5.40.792.732 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.950 MiB) 5.40.887.622 I slot launch_slot_: id 0 | task 19489 | processing task, is_child = 0 5.43.708.717 I slot print_timing: id 0 | task 19489 | prompt eval time = 147.68 ms / 322 tokens ( 0.46 ms per token, 2180.36 tokens per second) 5.43.708.722 I slot print_timing: id 0 | task 19489 | eval time = 2673.39 ms / 176 tokens ( 15.28 ms per token, 65.46 tokens per second) 5.43.708.723 I slot print_timing: id 0 | task 19489 | total time = 2821.07 ms / 498 tokens 5.43.708.725 I slot print_timing: id 0 | task 19489 | graphs reused = 18606 5.43.708.725 I slot print_timing: id 0 | task 19489 | graph reallocs = 0 / 0 (same size) / (changed size) 5.43.708.752 I slot release: id 0 | task 19489 | stop processing: n_tokens = 529, truncated = 0 5.43.733.000 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 343613327 5.43.733.041 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 5.43.835.913 I slot launch_slot_: id 0 | task 19668 | processing task, is_child = 0 5.44.675.444 I slot print_timing: id 0 | task 19668 | prompt eval time = 148.68 ms / 337 tokens ( 0.44 ms per token, 2266.66 tokens per second) 5.44.675.450 I slot print_timing: id 0 | task 19668 | eval time = 690.83 ms / 46 tokens ( 15.35 ms per token, 65.14 tokens per second) 5.44.675.451 I slot print_timing: id 0 | task 19668 | total time = 839.51 ms / 383 tokens 5.44.675.451 I slot print_timing: id 0 | task 19668 | graphs reused = 18650 5.44.675.452 I slot print_timing: id 0 | task 19668 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.675.484 I slot release: id 0 | task 19668 | stop processing: n_tokens = 414, truncated = 0 5.44.692.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 344580058 5.44.692.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 5.44.787.754 I slot launch_slot_: id 0 | task 19717 | processing task, is_child = 0 5.45.643.082 I slot print_timing: id 0 | task 19717 | prompt eval time = 149.53 ms / 325 tokens ( 0.46 ms per token, 2173.46 tokens per second) 5.45.643.088 I slot print_timing: id 0 | task 19717 | eval time = 705.77 ms / 47 tokens ( 15.34 ms per token, 65.18 tokens per second) 5.45.643.089 I slot print_timing: id 0 | task 19717 | total time = 855.31 ms / 372 tokens 5.45.643.091 I slot print_timing: id 0 | task 19717 | graphs reused = 18695 5.45.643.092 I slot print_timing: id 0 | task 19717 | graph reallocs = 0 / 0 (same size) / (changed size) 5.45.643.122 I slot release: id 0 | task 19717 | stop processing: n_tokens = 403, truncated = 0 5.45.659.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 345547697 5.45.659.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.329 MiB) 5.45.748.037 I slot launch_slot_: id 0 | task 19767 | processing task, is_child = 0 5.46.909.116 I slot print_timing: id 0 | task 19767 | prompt eval time = 149.11 ms / 331 tokens ( 0.45 ms per token, 2219.90 tokens per second) 5.46.909.122 I slot print_timing: id 0 | task 19767 | eval time = 1011.95 ms / 67 tokens ( 15.33 ms per token, 65.22 tokens per second) 5.46.909.123 I slot print_timing: id 0 | task 19767 | total time = 1161.06 ms / 398 tokens 5.46.909.124 I slot print_timing: id 0 | task 19767 | graphs reused = 18760 5.46.909.125 I slot print_timing: id 0 | task 19767 | graph reallocs = 0 / 0 (same size) / (changed size) 5.46.909.154 I slot release: id 0 | task 19767 | stop processing: n_tokens = 429, truncated = 0 5.46.937.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 346813728 5.46.937.541 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 5.47.045.504 I slot launch_slot_: id 0 | task 19837 | processing task, is_child = 0 5.48.093.255 I slot print_timing: id 0 | task 19837 | prompt eval time = 157.10 ms / 336 tokens ( 0.47 ms per token, 2138.81 tokens per second) 5.48.093.260 I slot print_timing: id 0 | task 19837 | eval time = 890.63 ms / 59 tokens ( 15.36 ms per token, 65.12 tokens per second) 5.48.093.261 I slot print_timing: id 0 | task 19837 | total time = 1047.73 ms / 395 tokens 5.48.093.262 I slot print_timing: id 0 | task 19837 | graphs reused = 18817 5.48.093.263 I slot print_timing: id 0 | task 19837 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.093.290 I slot release: id 0 | task 19837 | stop processing: n_tokens = 426, truncated = 0 5.48.119.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 347997864 5.48.119.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.700 MiB) 5.48.210.147 I slot launch_slot_: id 0 | task 19899 | processing task, is_child = 0 5.48.820.204 I slot print_timing: id 0 | task 19899 | prompt eval time = 148.10 ms / 349 tokens ( 0.42 ms per token, 2356.47 tokens per second) 5.48.820.210 I slot print_timing: id 0 | task 19899 | eval time = 461.93 ms / 31 tokens ( 15.40 ms per token, 64.94 tokens per second) 5.48.820.210 I slot print_timing: id 0 | task 19899 | total time = 610.04 ms / 380 tokens 5.48.820.212 I slot print_timing: id 0 | task 19899 | graphs reused = 18846 5.48.820.212 I slot print_timing: id 0 | task 19899 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.820.241 I slot release: id 0 | task 19899 | stop processing: n_tokens = 411, truncated = 0 5.48.834.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 348724816 5.48.834.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 5.48.921.300 I slot launch_slot_: id 0 | task 19933 | processing task, is_child = 0 5.52.073.072 I slot print_timing: id 0 | task 19933 | n_gen = 198, tg = 65.60 t/s, tg_3s = 65.93 t/s 5.55.086.561 I slot print_timing: id 0 | task 19933 | n_gen = 396, tg = 65.65 t/s, tg_3s = 65.70 t/s 5.58.088.739 I slot print_timing: id 0 | task 19933 | n_gen = 593, tg = 65.64 t/s, tg_3s = 65.62 t/s 6.01.093.245 I slot print_timing: id 0 | task 19933 | n_gen = 790, tg = 65.62 t/s, tg_3s = 65.57 t/s 6.04.010.456 I slot print_timing: id 0 | task 19933 | prompt eval time = 148.52 ms / 336 tokens ( 0.44 ms per token, 2262.31 tokens per second) 6.04.010.462 I slot print_timing: id 0 | task 19933 | eval time = 14940.61 ms / 981 tokens ( 15.25 ms per token, 65.59 tokens per second) 6.04.010.463 I slot print_timing: id 0 | task 19933 | total time = 15089.14 ms / 1317 tokens 6.04.010.464 I slot print_timing: id 0 | task 19933 | graphs reused = 19821 6.04.010.464 I slot print_timing: id 0 | task 19933 | graph reallocs = 0 / 0 (same size) / (changed size) 6.04.010.517 I slot release: id 0 | task 19933 | stop processing: n_tokens = 1348, truncated = 0 6.04.026.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1348, t_last = 363915093 6.04.026.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.640 MiB) 6.04.125.705 I slot launch_slot_: id 0 | task 20917 | processing task, is_child = 0 6.07.288.504 I slot print_timing: id 0 | task 20917 | n_gen = 198, tg = 65.35 t/s, tg_3s = 65.69 t/s 6.10.290.376 I slot print_timing: id 0 | task 20917 | n_gen = 395, tg = 65.49 t/s, tg_3s = 65.63 t/s 6.10.853.958 I slot print_timing: id 0 | task 20917 | prompt eval time = 148.47 ms / 349 tokens ( 0.43 ms per token, 2350.67 tokens per second) 6.10.853.964 I slot print_timing: id 0 | task 20917 | eval time = 6579.77 ms / 432 tokens ( 15.27 ms per token, 65.50 tokens per second) 6.10.853.965 I slot print_timing: id 0 | task 20917 | total time = 6728.23 ms / 781 tokens 6.10.853.966 I slot print_timing: id 0 | task 20917 | graphs reused = 20249 6.10.853.966 I slot print_timing: id 0 | task 20917 | graph reallocs = 0 / 0 (same size) / (changed size) 6.10.853.999 I slot release: id 0 | task 20917 | stop processing: n_tokens = 812, truncated = 0 6.10.871.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 812, t_last = 370758574 6.10.871.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 6.10.965.666 I slot launch_slot_: id 0 | task 21352 | processing task, is_child = 0 6.11.819.963 I slot print_timing: id 0 | task 21352 | prompt eval time = 149.08 ms / 349 tokens ( 0.43 ms per token, 2341.04 tokens per second) 6.11.819.968 I slot print_timing: id 0 | task 21352 | eval time = 705.20 ms / 47 tokens ( 15.33 ms per token, 65.23 tokens per second) 6.11.819.969 I slot print_timing: id 0 | task 21352 | total time = 854.28 ms / 396 tokens 6.11.819.970 I slot print_timing: id 0 | task 21352 | graphs reused = 20294 6.11.819.971 I slot print_timing: id 0 | task 21352 | graph reallocs = 0 / 0 (same size) / (changed size) 6.11.819.999 I slot release: id 0 | task 21352 | stop processing: n_tokens = 427, truncated = 0 6.11.845.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 371724573 6.11.845.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.326 MiB) 6.11.935.733 I slot launch_slot_: id 0 | task 21402 | processing task, is_child = 0 6.12.323.290 I slot print_timing: id 0 | task 21402 | prompt eval time = 153.84 ms / 385 tokens ( 0.40 ms per token, 2502.57 tokens per second) 6.12.323.296 I slot print_timing: id 0 | task 21402 | eval time = 233.70 ms / 16 tokens ( 15.58 ms per token, 64.19 tokens per second) 6.12.323.297 I slot print_timing: id 0 | task 21402 | total time = 387.54 ms / 401 tokens 6.12.323.298 I slot print_timing: id 0 | task 21402 | graphs reused = 20308 6.12.323.299 I slot print_timing: id 0 | task 21402 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.323.328 I slot release: id 0 | task 21402 | stop processing: n_tokens = 432, truncated = 0 6.12.350.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 372227902 6.12.350.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 6.12.420.460 I slot launch_slot_: id 0 | task 21421 | processing task, is_child = 0 6.13.426.362 I slot print_timing: id 0 | task 21421 | prompt eval time = 148.66 ms / 328 tokens ( 0.45 ms per token, 2206.45 tokens per second) 6.13.426.368 I slot print_timing: id 0 | task 21421 | eval time = 857.23 ms / 57 tokens ( 15.31 ms per token, 65.33 tokens per second) 6.13.426.369 I slot print_timing: id 0 | task 21421 | total time = 1005.88 ms / 385 tokens 6.13.426.370 I slot print_timing: id 0 | task 21421 | graphs reused = 20363 6.13.426.371 I slot print_timing: id 0 | task 21421 | graph reallocs = 0 / 0 (same size) / (changed size) 6.13.426.400 I slot release: id 0 | task 21421 | stop processing: n_tokens = 416, truncated = 0