$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--mradermacher--granite-4.2-8b-i1-GGUF\snapshots\4e036f43e7e72a464093de36e41388a5b1d35076\granite-4.2-8b.i1-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.090.478 I srv llama_server: initializing ... 0.00.090.484 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.090.592 I srv init_listene: The UI is disabled 0.00.090.594 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.090.669 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) 0.00.093.088 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--mradermacher--granite-4.2-8b-i1-GGUF\snapshots\4e036f43e7e72a464093de36e41388a5b1d35076\granite-4.2-8b.i1-Q4_K_M.gguf' 0.02.189.622 I cmn init: llama threadpool init, n_threads = 8 0.02.261.632 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.266.325 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.266.343 I srv llama_server: model loaded 0.02.266.345 I srv llama_server: listening on http://127.0.0.1:8089 0.02.509.746 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.509.920 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.203.769 I slot print_timing: id 0 | task 0 | prompt eval time = 102.15 ms / 368 tokens ( 0.28 ms per token, 3602.47 tokens per second) 0.03.203.775 I slot print_timing: id 0 | task 0 | eval time = 591.68 ms / 61 tokens ( 9.86 ms per token, 101.41 tokens per second) 0.03.203.776 I slot print_timing: id 0 | task 0 | total time = 693.83 ms / 429 tokens 0.03.203.781 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.03.203.782 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.203.812 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.03.224.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 3115303 0.03.239.658 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.03.740.184 I slot print_timing: id 0 | task 62 | prompt eval time = 79.12 ms / 292 tokens ( 0.27 ms per token, 3690.60 tokens per second) 0.03.740.189 I slot print_timing: id 0 | task 62 | eval time = 421.39 ms / 44 tokens ( 9.80 ms per token, 102.04 tokens per second) 0.03.740.190 I slot print_timing: id 0 | task 62 | total time = 500.51 ms / 336 tokens 0.03.740.191 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.03.740.192 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.740.217 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.03.744.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 3651707 0.03.757.823 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.04.276.716 I slot print_timing: id 0 | task 107 | prompt eval time = 87.58 ms / 338 tokens ( 0.26 ms per token, 3859.37 tokens per second) 0.04.276.721 I slot print_timing: id 0 | task 107 | eval time = 431.30 ms / 45 tokens ( 9.80 ms per token, 102.02 tokens per second) 0.04.276.723 I slot print_timing: id 0 | task 107 | total time = 518.88 ms / 383 tokens 0.04.276.723 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.04.276.724 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.276.752 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.04.280.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 4188243 0.04.295.379 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.04.824.371 I slot print_timing: id 0 | task 153 | prompt eval time = 88.06 ms / 371 tokens ( 0.24 ms per token, 4213.28 tokens per second) 0.04.824.377 I slot print_timing: id 0 | task 153 | eval time = 440.92 ms / 46 tokens ( 9.80 ms per token, 102.06 tokens per second) 0.04.824.378 I slot print_timing: id 0 | task 153 | total time = 528.98 ms / 417 tokens 0.04.824.379 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.04.824.380 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.824.410 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.04.846.744 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.104 (> 0.100 thold), f_keep = 0.091 0.04.862.057 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.05.536.939 I slot print_timing: id 0 | task 200 | prompt eval time = 88.04 ms / 345 tokens ( 0.26 ms per token, 3918.50 tokens per second) 0.05.536.945 I slot print_timing: id 0 | task 200 | eval time = 586.82 ms / 61 tokens ( 9.78 ms per token, 102.25 tokens per second) 0.05.536.946 I slot print_timing: id 0 | task 200 | total time = 674.87 ms / 406 tokens 0.05.536.947 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.05.536.948 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.536.976 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.05.563.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 5448466 0.05.579.070 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.06.282.865 I slot print_timing: id 0 | task 262 | prompt eval time = 88.26 ms / 351 tokens ( 0.25 ms per token, 3976.89 tokens per second) 0.06.282.871 I slot print_timing: id 0 | task 262 | eval time = 615.52 ms / 64 tokens ( 9.77 ms per token, 102.35 tokens per second) 0.06.282.872 I slot print_timing: id 0 | task 262 | total time = 703.78 ms / 415 tokens 0.06.282.872 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.06.282.873 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.282.900 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.06.302.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 6194391 0.06.317.655 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.06.981.743 I slot print_timing: id 0 | task 327 | prompt eval time = 106.26 ms / 395 tokens ( 0.27 ms per token, 3717.19 tokens per second) 0.06.981.750 I slot print_timing: id 0 | task 327 | eval time = 557.81 ms / 58 tokens ( 9.79 ms per token, 102.19 tokens per second) 0.06.981.752 I slot print_timing: id 0 | task 327 | total time = 664.07 ms / 453 tokens 0.06.981.753 I slot print_timing: id 0 | task 327 | graphs reused = 366 0.06.981.754 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.981.786 I slot release: id 0 | task 327 | stop processing: n_tokens = 477, truncated = 0 0.07.009.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 6893277 0.07.026.212 I slot launch_slot_: id 0 | task 386 | processing task, is_child = 0 0.07.836.610 I slot print_timing: id 0 | task 386 | prompt eval time = 109.13 ms / 446 tokens ( 0.24 ms per token, 4086.79 tokens per second) 0.07.836.616 I slot print_timing: id 0 | task 386 | eval time = 701.25 ms / 72 tokens ( 9.88 ms per token, 101.25 tokens per second) 0.07.836.616 I slot print_timing: id 0 | task 386 | total time = 810.38 ms / 518 tokens 0.07.836.617 I slot print_timing: id 0 | task 386 | graphs reused = 435 0.07.836.618 I slot print_timing: id 0 | task 386 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.836.650 I slot release: id 0 | task 386 | stop processing: n_tokens = 542, truncated = 0 0.07.856.445 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 7748140 0.07.874.746 I slot launch_slot_: id 0 | task 459 | processing task, is_child = 0 0.08.464.963 I slot print_timing: id 0 | task 459 | prompt eval time = 79.77 ms / 319 tokens ( 0.25 ms per token, 3998.90 tokens per second) 0.08.464.969 I slot print_timing: id 0 | task 459 | eval time = 510.43 ms / 52 tokens ( 10.01 ms per token, 99.92 tokens per second) 0.08.464.970 I slot print_timing: id 0 | task 459 | total time = 590.20 ms / 371 tokens 0.08.464.971 I slot print_timing: id 0 | task 459 | graphs reused = 485 0.08.464.972 I slot print_timing: id 0 | task 459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.465.001 I slot release: id 0 | task 459 | stop processing: n_tokens = 395, truncated = 0 0.08.481.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 8376491 0.08.495.963 I slot launch_slot_: id 0 | task 512 | processing task, is_child = 0 0.08.981.824 I slot print_timing: id 0 | task 512 | prompt eval time = 80.80 ms / 336 tokens ( 0.24 ms per token, 4158.21 tokens per second) 0.08.981.830 I slot print_timing: id 0 | task 512 | eval time = 405.04 ms / 42 tokens ( 9.88 ms per token, 101.22 tokens per second) 0.08.981.831 I slot print_timing: id 0 | task 512 | total time = 485.84 ms / 378 tokens 0.08.981.832 I slot print_timing: id 0 | task 512 | graphs reused = 525 0.08.981.833 I slot print_timing: id 0 | task 512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.981.862 I slot release: id 0 | task 512 | stop processing: n_tokens = 402, truncated = 0 0.09.009.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 8893353 0.09.024.008 I slot launch_slot_: id 0 | task 555 | processing task, is_child = 0 0.09.778.043 I slot print_timing: id 0 | task 555 | prompt eval time = 88.08 ms / 352 tokens ( 0.25 ms per token, 3996.50 tokens per second) 0.09.778.048 I slot print_timing: id 0 | task 555 | eval time = 665.94 ms / 68 tokens ( 9.94 ms per token, 100.61 tokens per second) 0.09.778.049 I slot print_timing: id 0 | task 555 | total time = 754.02 ms / 420 tokens 0.09.778.050 I slot print_timing: id 0 | task 555 | graphs reused = 591 0.09.778.051 I slot print_timing: id 0 | task 555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.778.078 I slot release: id 0 | task 555 | stop processing: n_tokens = 444, truncated = 0 0.09.803.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 9689569 0.09.819.196 I slot launch_slot_: id 0 | task 624 | processing task, is_child = 0 0.10.426.114 I slot print_timing: id 0 | task 624 | prompt eval time = 105.90 ms / 387 tokens ( 0.27 ms per token, 3654.46 tokens per second) 0.10.426.119 I slot print_timing: id 0 | task 624 | eval time = 501.00 ms / 52 tokens ( 9.82 ms per token, 101.80 tokens per second) 0.10.426.120 I slot print_timing: id 0 | task 624 | total time = 606.90 ms / 439 tokens 0.10.426.121 I slot print_timing: id 0 | task 624 | graphs reused = 641 0.10.426.122 I slot print_timing: id 0 | task 624 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.426.153 I slot release: id 0 | task 624 | stop processing: n_tokens = 463, truncated = 0 0.10.443.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 10337644 0.10.459.657 I slot launch_slot_: id 0 | task 677 | processing task, is_child = 0 0.11.165.043 I slot print_timing: id 0 | task 677 | prompt eval time = 88.16 ms / 349 tokens ( 0.25 ms per token, 3958.53 tokens per second) 0.11.165.049 I slot print_timing: id 0 | task 677 | eval time = 617.21 ms / 64 tokens ( 9.80 ms per token, 102.07 tokens per second) 0.11.165.050 I slot print_timing: id 0 | task 677 | total time = 705.37 ms / 413 tokens 0.11.165.051 I slot print_timing: id 0 | task 677 | graphs reused = 703 0.11.165.052 I slot print_timing: id 0 | task 677 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.165.079 I slot release: id 0 | task 677 | stop processing: n_tokens = 437, truncated = 0 0.11.190.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 11076569 0.11.205.887 I slot launch_slot_: id 0 | task 742 | processing task, is_child = 0 0.11.860.983 I slot print_timing: id 0 | task 742 | prompt eval time = 88.21 ms / 352 tokens ( 0.25 ms per token, 3990.43 tokens per second) 0.11.860.989 I slot print_timing: id 0 | task 742 | eval time = 566.87 ms / 57 tokens ( 10.12 ms per token, 98.79 tokens per second) 0.11.860.990 I slot print_timing: id 0 | task 742 | total time = 655.08 ms / 409 tokens 0.11.860.991 I slot print_timing: id 0 | task 742 | graphs reused = 758 0.11.860.992 I slot print_timing: id 0 | task 742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.861.022 I slot release: id 0 | task 742 | stop processing: n_tokens = 433, truncated = 0 0.11.875.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 11772512 0.11.890.279 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 0.12.643.858 I slot print_timing: id 0 | task 800 | prompt eval time = 87.92 ms / 347 tokens ( 0.25 ms per token, 3946.64 tokens per second) 0.12.643.864 I slot print_timing: id 0 | task 800 | eval time = 665.64 ms / 68 tokens ( 9.93 ms per token, 100.66 tokens per second) 0.12.643.865 I slot print_timing: id 0 | task 800 | total time = 753.56 ms / 415 tokens 0.12.643.867 I slot print_timing: id 0 | task 800 | graphs reused = 824 0.12.643.868 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.643.899 I slot release: id 0 | task 800 | stop processing: n_tokens = 439, truncated = 0 0.12.669.223 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 12555389 0.12.684.928 I slot launch_slot_: id 0 | task 869 | processing task, is_child = 0 0.13.303.394 I slot print_timing: id 0 | task 869 | prompt eval time = 79.64 ms / 320 tokens ( 0.25 ms per token, 4018.18 tokens per second) 0.13.303.399 I slot print_timing: id 0 | task 869 | eval time = 538.81 ms / 56 tokens ( 9.80 ms per token, 102.08 tokens per second) 0.13.303.401 I slot print_timing: id 0 | task 869 | total time = 618.45 ms / 376 tokens 0.13.303.401 I slot print_timing: id 0 | task 869 | graphs reused = 878 0.13.303.402 I slot print_timing: id 0 | task 869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.303.430 I slot release: id 0 | task 869 | stop processing: n_tokens = 400, truncated = 0 0.13.323.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 13214920 0.13.337.374 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 0.13.847.682 I slot print_timing: id 0 | task 926 | prompt eval time = 88.05 ms / 343 tokens ( 0.26 ms per token, 3895.34 tokens per second) 0.13.847.688 I slot print_timing: id 0 | task 926 | eval time = 422.24 ms / 44 tokens ( 9.82 ms per token, 101.84 tokens per second) 0.13.847.689 I slot print_timing: id 0 | task 926 | total time = 510.29 ms / 387 tokens 0.13.847.690 I slot print_timing: id 0 | task 926 | graphs reused = 920 0.13.847.691 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.847.718 I slot release: id 0 | task 926 | stop processing: n_tokens = 411, truncated = 0 0.13.867.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 13759208 0.13.881.566 I slot launch_slot_: id 0 | task 971 | processing task, is_child = 0 0.14.383.462 I slot print_timing: id 0 | task 971 | prompt eval time = 79.94 ms / 325 tokens ( 0.25 ms per token, 4065.70 tokens per second) 0.14.383.468 I slot print_timing: id 0 | task 971 | eval time = 421.94 ms / 44 tokens ( 9.81 ms per token, 101.91 tokens per second) 0.14.383.469 I slot print_timing: id 0 | task 971 | total time = 501.88 ms / 369 tokens 0.14.383.470 I slot print_timing: id 0 | task 971 | graphs reused = 962 0.14.383.471 I slot print_timing: id 0 | task 971 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.383.498 I slot release: id 0 | task 971 | stop processing: n_tokens = 393, truncated = 0 0.14.387.625 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 14294988 0.14.402.053 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.14.894.049 I slot print_timing: id 0 | task 1016 | prompt eval time = 80.05 ms / 323 tokens ( 0.25 ms per token, 4034.78 tokens per second) 0.14.894.055 I slot print_timing: id 0 | task 1016 | eval time = 411.93 ms / 43 tokens ( 9.81 ms per token, 101.96 tokens per second) 0.14.894.056 I slot print_timing: id 0 | task 1016 | total time = 491.98 ms / 366 tokens 0.14.894.057 I slot print_timing: id 0 | task 1016 | graphs reused = 1003 0.14.894.058 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.894.084 I slot release: id 0 | task 1016 | stop processing: n_tokens = 390, truncated = 0 0.14.908.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 14805574 0.14.922.200 I slot launch_slot_: id 0 | task 1060 | processing task, is_child = 0 0.15.702.532 I slot print_timing: id 0 | task 1060 | prompt eval time = 88.57 ms / 359 tokens ( 0.25 ms per token, 4053.34 tokens per second) 0.15.702.540 I slot print_timing: id 0 | task 1060 | eval time = 691.75 ms / 69 tokens ( 10.17 ms per token, 98.30 tokens per second) 0.15.702.541 I slot print_timing: id 0 | task 1060 | total time = 780.32 ms / 428 tokens 0.15.702.542 I slot print_timing: id 0 | task 1060 | graphs reused = 1070 0.15.702.543 I slot print_timing: id 0 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.702.578 I slot release: id 0 | task 1060 | stop processing: n_tokens = 452, truncated = 0 0.15.706.593 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 15614069 0.15.722.357 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.16.410.060 I slot print_timing: id 0 | task 1130 | prompt eval time = 80.93 ms / 334 tokens ( 0.24 ms per token, 4127.07 tokens per second) 0.16.410.065 I slot print_timing: id 0 | task 1130 | eval time = 606.76 ms / 63 tokens ( 9.79 ms per token, 102.18 tokens per second) 0.16.410.066 I slot print_timing: id 0 | task 1130 | total time = 687.68 ms / 397 tokens 0.16.410.067 I slot print_timing: id 0 | task 1130 | graphs reused = 1131 0.16.410.068 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.410.097 I slot release: id 0 | task 1130 | stop processing: n_tokens = 421, truncated = 0 0.16.437.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 16321588 0.16.452.362 I slot launch_slot_: id 0 | task 1194 | processing task, is_child = 0 0.17.243.549 I slot print_timing: id 0 | task 1194 | prompt eval time = 88.37 ms / 382 tokens ( 0.23 ms per token, 4322.93 tokens per second) 0.17.243.554 I slot print_timing: id 0 | task 1194 | eval time = 702.80 ms / 73 tokens ( 9.76 ms per token, 102.45 tokens per second) 0.17.243.556 I slot print_timing: id 0 | task 1194 | total time = 791.17 ms / 455 tokens 0.17.243.556 I slot print_timing: id 0 | task 1194 | graphs reused = 1202 0.17.243.557 I slot print_timing: id 0 | task 1194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.243.586 I slot release: id 0 | task 1194 | stop processing: n_tokens = 479, truncated = 0 0.17.266.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 17155076 0.17.283.045 I slot launch_slot_: id 0 | task 1268 | processing task, is_child = 0 0.17.999.758 I slot print_timing: id 0 | task 1268 | prompt eval time = 89.14 ms / 368 tokens ( 0.24 ms per token, 4128.29 tokens per second) 0.17.999.764 I slot print_timing: id 0 | task 1268 | eval time = 627.56 ms / 65 tokens ( 9.81 ms per token, 101.98 tokens per second) 0.17.999.765 I slot print_timing: id 0 | task 1268 | total time = 716.70 ms / 433 tokens 0.17.999.766 I slot print_timing: id 0 | task 1268 | graphs reused = 1265 0.17.999.767 I slot print_timing: id 0 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.999.800 I slot release: id 0 | task 1268 | stop processing: n_tokens = 457, truncated = 0 0.18.025.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 17911290 0.18.041.554 I slot launch_slot_: id 0 | task 1334 | processing task, is_child = 0 0.18.969.745 I slot print_timing: id 0 | task 1334 | prompt eval time = 88.38 ms / 382 tokens ( 0.23 ms per token, 4322.39 tokens per second) 0.18.969.751 I slot print_timing: id 0 | task 1334 | eval time = 839.80 ms / 87 tokens ( 9.77 ms per token, 102.41 tokens per second) 0.18.969.752 I slot print_timing: id 0 | task 1334 | total time = 928.18 ms / 469 tokens 0.18.969.753 I slot print_timing: id 0 | task 1334 | graphs reused = 1350 0.18.969.754 I slot print_timing: id 0 | task 1334 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.969.783 I slot release: id 0 | task 1334 | stop processing: n_tokens = 493, truncated = 0 0.18.998.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 18881274 0.19.015.214 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 0.19.782.823 I slot print_timing: id 0 | task 1422 | prompt eval time = 107.24 ms / 410 tokens ( 0.26 ms per token, 3823.20 tokens per second) 0.19.782.829 I slot print_timing: id 0 | task 1422 | eval time = 660.35 ms / 67 tokens ( 10.01 ms per token, 99.95 tokens per second) 0.19.782.830 I slot print_timing: id 0 | task 1422 | total time = 767.59 ms / 477 tokens 0.19.782.831 I slot print_timing: id 0 | task 1422 | graphs reused = 1415 0.19.782.832 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.782.864 I slot release: id 0 | task 1422 | stop processing: n_tokens = 501, truncated = 0 0.19.808.900 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 19694355 0.19.826.467 I slot launch_slot_: id 0 | task 1490 | processing task, is_child = 0 0.20.543.346 I slot print_timing: id 0 | task 1490 | prompt eval time = 88.78 ms / 367 tokens ( 0.24 ms per token, 4133.77 tokens per second) 0.20.543.352 I slot print_timing: id 0 | task 1490 | eval time = 628.08 ms / 65 tokens ( 9.81 ms per token, 101.90 tokens per second) 0.20.543.353 I slot print_timing: id 0 | task 1490 | total time = 716.86 ms / 432 tokens 0.20.543.355 I slot print_timing: id 0 | task 1490 | graphs reused = 1478 0.20.543.356 I slot print_timing: id 0 | task 1490 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.543.385 I slot release: id 0 | task 1490 | stop processing: n_tokens = 458, truncated = 0 0.20.557.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 20454875 0.20.573.625 I slot launch_slot_: id 0 | task 1556 | processing task, is_child = 0 0.21.173.428 I slot print_timing: id 0 | task 1556 | prompt eval time = 80.11 ms / 326 tokens ( 0.25 ms per token, 4069.61 tokens per second) 0.21.173.434 I slot print_timing: id 0 | task 1556 | eval time = 519.68 ms / 54 tokens ( 9.81 ms per token, 101.99 tokens per second) 0.21.173.435 I slot print_timing: id 0 | task 1556 | total time = 599.78 ms / 380 tokens 0.21.173.436 I slot print_timing: id 0 | task 1556 | graphs reused = 1530 0.21.173.436 I slot print_timing: id 0 | task 1556 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.173.464 I slot release: id 0 | task 1556 | stop processing: n_tokens = 404, truncated = 0 0.21.197.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 21084955 0.21.211.818 I slot launch_slot_: id 0 | task 1611 | processing task, is_child = 0 0.21.915.465 I slot print_timing: id 0 | task 1611 | prompt eval time = 88.29 ms / 351 tokens ( 0.25 ms per token, 3975.49 tokens per second) 0.21.915.470 I slot print_timing: id 0 | task 1611 | eval time = 615.34 ms / 64 tokens ( 9.77 ms per token, 102.38 tokens per second) 0.21.915.471 I slot print_timing: id 0 | task 1611 | total time = 703.63 ms / 415 tokens 0.21.915.472 I slot print_timing: id 0 | task 1611 | graphs reused = 1592 0.21.915.473 I slot print_timing: id 0 | task 1611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.915.500 I slot release: id 0 | task 1611 | stop processing: n_tokens = 441, truncated = 0 0.21.919.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 21826991 0.21.943.454 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 0.22.793.698 I slot print_timing: id 0 | task 1676 | prompt eval time = 88.58 ms / 379 tokens ( 0.23 ms per token, 4278.42 tokens per second) 0.22.793.704 I slot print_timing: id 0 | task 1676 | eval time = 761.64 ms / 78 tokens ( 9.89 ms per token, 101.10 tokens per second) 0.22.793.705 I slot print_timing: id 0 | task 1676 | total time = 850.23 ms / 457 tokens 0.22.793.706 I slot print_timing: id 0 | task 1676 | graphs reused = 1668 0.22.793.707 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.793.740 I slot release: id 0 | task 1676 | stop processing: n_tokens = 481, truncated = 0 0.22.818.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 22705230 0.22.834.144 I slot launch_slot_: id 0 | task 1755 | processing task, is_child = 0 0.23.596.660 I slot print_timing: id 0 | task 1755 | prompt eval time = 88.08 ms / 356 tokens ( 0.25 ms per token, 4041.60 tokens per second) 0.23.596.665 I slot print_timing: id 0 | task 1755 | eval time = 674.42 ms / 70 tokens ( 9.77 ms per token, 102.31 tokens per second) 0.23.596.666 I slot print_timing: id 0 | task 1755 | total time = 762.50 ms / 426 tokens 0.23.596.667 I slot print_timing: id 0 | task 1755 | graphs reused = 1736 0.23.596.668 I slot print_timing: id 0 | task 1755 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.596.696 I slot release: id 0 | task 1755 | stop processing: n_tokens = 450, truncated = 0 0.23.600.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 23508186 0.23.616.512 I slot launch_slot_: id 0 | task 1826 | processing task, is_child = 0 0.24.303.293 I slot print_timing: id 0 | task 1826 | prompt eval time = 80.42 ms / 331 tokens ( 0.24 ms per token, 4115.79 tokens per second) 0.24.303.299 I slot print_timing: id 0 | task 1826 | eval time = 606.35 ms / 63 tokens ( 9.78 ms per token, 102.25 tokens per second) 0.24.303.300 I slot print_timing: id 0 | task 1826 | total time = 686.77 ms / 394 tokens 0.24.303.301 I slot print_timing: id 0 | task 1826 | graphs reused = 1797 0.24.303.302 I slot print_timing: id 0 | task 1826 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.303.329 I slot release: id 0 | task 1826 | stop processing: n_tokens = 418, truncated = 0 0.24.331.885 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 24214820 0.24.346.328 I slot launch_slot_: id 0 | task 1890 | processing task, is_child = 0 0.24.759.751 I slot print_timing: id 0 | task 1890 | prompt eval time = 80.40 ms / 334 tokens ( 0.24 ms per token, 4154.33 tokens per second) 0.24.759.757 I slot print_timing: id 0 | task 1890 | eval time = 333.01 ms / 34 tokens ( 10.09 ms per token, 99.10 tokens per second) 0.24.759.758 I slot print_timing: id 0 | task 1890 | total time = 413.41 ms / 368 tokens 0.24.759.759 I slot print_timing: id 0 | task 1890 | graphs reused = 1829 0.24.759.760 I slot print_timing: id 0 | task 1890 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.759.790 I slot release: id 0 | task 1890 | stop processing: n_tokens = 392, truncated = 0 0.24.764.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 24671280 0.24.777.790 I slot launch_slot_: id 0 | task 1925 | processing task, is_child = 0 0.25.521.071 I slot print_timing: id 0 | task 1925 | prompt eval time = 88.83 ms / 362 tokens ( 0.25 ms per token, 4075.11 tokens per second) 0.25.521.077 I slot print_timing: id 0 | task 1925 | eval time = 654.43 ms / 68 tokens ( 9.77 ms per token, 102.38 tokens per second) 0.25.521.078 I slot print_timing: id 0 | task 1925 | total time = 743.27 ms / 430 tokens 0.25.521.079 I slot print_timing: id 0 | task 1925 | graphs reused = 1895 0.25.521.079 I slot print_timing: id 0 | task 1925 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.521.109 I slot release: id 0 | task 1925 | stop processing: n_tokens = 454, truncated = 0 0.25.547.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 25432599 0.25.562.676 I slot launch_slot_: id 0 | task 1994 | processing task, is_child = 0 0.26.286.437 I slot print_timing: id 0 | task 1994 | prompt eval time = 88.38 ms / 384 tokens ( 0.23 ms per token, 4344.68 tokens per second) 0.26.286.443 I slot print_timing: id 0 | task 1994 | eval time = 635.36 ms / 66 tokens ( 9.77 ms per token, 102.30 tokens per second) 0.26.286.444 I slot print_timing: id 0 | task 1994 | total time = 723.75 ms / 450 tokens 0.26.286.444 I slot print_timing: id 0 | task 1994 | graphs reused = 1959 0.26.286.445 I slot print_timing: id 0 | task 1994 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.286.475 I slot release: id 0 | task 1994 | stop processing: n_tokens = 474, truncated = 0 0.26.290.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 26197966 0.26.306.524 I slot launch_slot_: id 0 | task 2061 | processing task, is_child = 0 0.26.915.304 I slot print_timing: id 0 | task 2061 | prompt eval time = 80.39 ms / 325 tokens ( 0.25 ms per token, 4042.84 tokens per second) 0.26.915.310 I slot print_timing: id 0 | task 2061 | eval time = 528.38 ms / 55 tokens ( 9.78 ms per token, 102.20 tokens per second) 0.26.915.311 I slot print_timing: id 0 | task 2061 | total time = 608.76 ms / 380 tokens 0.26.915.312 I slot print_timing: id 0 | task 2061 | graphs reused = 2012 0.26.915.313 I slot print_timing: id 0 | task 2061 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.915.341 I slot release: id 0 | task 2061 | stop processing: n_tokens = 404, truncated = 0 0.26.935.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 26826831 0.26.949.027 I slot launch_slot_: id 0 | task 2117 | processing task, is_child = 0 0.27.613.138 I slot print_timing: id 0 | task 2117 | prompt eval time = 88.72 ms / 366 tokens ( 0.24 ms per token, 4125.43 tokens per second) 0.27.613.145 I slot print_timing: id 0 | task 2117 | eval time = 575.38 ms / 59 tokens ( 9.92 ms per token, 100.80 tokens per second) 0.27.613.146 I slot print_timing: id 0 | task 2117 | total time = 664.10 ms / 425 tokens 0.27.613.146 I slot print_timing: id 0 | task 2117 | graphs reused = 2069 0.27.613.147 I slot print_timing: id 0 | task 2117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.613.177 I slot release: id 0 | task 2117 | stop processing: n_tokens = 449, truncated = 0 0.27.632.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 27524667 0.27.647.982 I slot launch_slot_: id 0 | task 2177 | processing task, is_child = 0 0.28.071.060 I slot print_timing: id 0 | task 2177 | prompt eval time = 79.11 ms / 295 tokens ( 0.27 ms per token, 3728.80 tokens per second) 0.28.071.065 I slot print_timing: id 0 | task 2177 | eval time = 343.95 ms / 36 tokens ( 9.83 ms per token, 101.76 tokens per second) 0.28.071.066 I slot print_timing: id 0 | task 2177 | total time = 423.06 ms / 331 tokens 0.28.071.067 I slot print_timing: id 0 | task 2177 | graphs reused = 2103 0.28.071.068 I slot print_timing: id 0 | task 2177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.071.094 I slot release: id 0 | task 2177 | stop processing: n_tokens = 355, truncated = 0 0.28.075.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 27982585 0.28.088.268 I slot launch_slot_: id 0 | task 2214 | processing task, is_child = 0 0.28.647.456 I slot print_timing: id 0 | task 2214 | prompt eval time = 79.55 ms / 307 tokens ( 0.26 ms per token, 3859.21 tokens per second) 0.28.647.462 I slot print_timing: id 0 | task 2214 | eval time = 479.62 ms / 50 tokens ( 9.79 ms per token, 102.16 tokens per second) 0.28.647.463 I slot print_timing: id 0 | task 2214 | total time = 559.17 ms / 357 tokens 0.28.647.464 I slot print_timing: id 0 | task 2214 | graphs reused = 2151 0.28.647.465 I slot print_timing: id 0 | task 2214 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.647.492 I slot release: id 0 | task 2214 | stop processing: n_tokens = 381, truncated = 0 0.28.663.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 28558983 0.28.677.230 I slot launch_slot_: id 0 | task 2265 | processing task, is_child = 0 0.29.120.436 I slot print_timing: id 0 | task 2265 | prompt eval time = 79.88 ms / 319 tokens ( 0.25 ms per token, 3993.64 tokens per second) 0.29.120.441 I slot print_timing: id 0 | task 2265 | eval time = 363.31 ms / 38 tokens ( 9.82 ms per token, 101.84 tokens per second) 0.29.120.443 I slot print_timing: id 0 | task 2265 | total time = 443.19 ms / 357 tokens 0.29.120.443 I slot print_timing: id 0 | task 2265 | graphs reused = 2187 0.29.120.444 I slot print_timing: id 0 | task 2265 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.120.473 I slot release: id 0 | task 2265 | stop processing: n_tokens = 381, truncated = 0 0.29.136.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 29031963 0.29.150.335 I slot launch_slot_: id 0 | task 2304 | processing task, is_child = 0 0.29.739.047 I slot print_timing: id 0 | task 2304 | prompt eval time = 79.89 ms / 315 tokens ( 0.25 ms per token, 3943.07 tokens per second) 0.29.739.053 I slot print_timing: id 0 | task 2304 | eval time = 508.81 ms / 53 tokens ( 9.78 ms per token, 102.20 tokens per second) 0.29.739.054 I slot print_timing: id 0 | task 2304 | total time = 588.70 ms / 368 tokens 0.29.739.055 I slot print_timing: id 0 | task 2304 | graphs reused = 2238 0.29.739.056 I slot print_timing: id 0 | task 2304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.739.082 I slot release: id 0 | task 2304 | stop processing: n_tokens = 392, truncated = 0 0.29.763.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 29650573 0.29.776.989 I slot launch_slot_: id 0 | task 2358 | processing task, is_child = 0 0.30.423.413 I slot print_timing: id 0 | task 2358 | prompt eval time = 88.85 ms / 367 tokens ( 0.24 ms per token, 4130.56 tokens per second) 0.30.423.419 I slot print_timing: id 0 | task 2358 | eval time = 557.56 ms / 58 tokens ( 9.78 ms per token, 102.23 tokens per second) 0.30.423.420 I slot print_timing: id 0 | task 2358 | total time = 646.41 ms / 425 tokens 0.30.423.421 I slot print_timing: id 0 | task 2358 | graphs reused = 2294 0.30.423.421 I slot print_timing: id 0 | task 2358 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.423.450 I slot release: id 0 | task 2358 | stop processing: n_tokens = 449, truncated = 0 0.30.451.372 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 30334940 0.30.466.642 I slot launch_slot_: id 0 | task 2417 | processing task, is_child = 0 0.31.292.840 I slot print_timing: id 0 | task 2417 | prompt eval time = 121.86 ms / 499 tokens ( 0.24 ms per token, 4094.86 tokens per second) 0.31.292.846 I slot print_timing: id 0 | task 2417 | eval time = 704.32 ms / 70 tokens ( 10.21 ms per token, 97.97 tokens per second) 0.31.292.847 I slot print_timing: id 0 | task 2417 | total time = 826.18 ms / 569 tokens 0.31.292.848 I slot print_timing: id 0 | task 2417 | graphs reused = 2362 0.31.292.849 I slot print_timing: id 0 | task 2417 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.292.882 I slot release: id 0 | task 2417 | stop processing: n_tokens = 593, truncated = 0 0.31.319.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 31204372 0.31.339.576 I slot launch_slot_: id 0 | task 2488 | processing task, is_child = 0 0.31.900.114 I slot print_timing: id 0 | task 2488 | prompt eval time = 79.91 ms / 319 tokens ( 0.25 ms per token, 3991.79 tokens per second) 0.31.900.120 I slot print_timing: id 0 | task 2488 | eval time = 480.61 ms / 50 tokens ( 9.81 ms per token, 101.95 tokens per second) 0.31.900.121 I slot print_timing: id 0 | task 2488 | total time = 560.52 ms / 369 tokens 0.31.900.122 I slot print_timing: id 0 | task 2488 | graphs reused = 2410 0.31.900.123 I slot print_timing: id 0 | task 2488 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.900.153 I slot release: id 0 | task 2488 | stop processing: n_tokens = 393, truncated = 0 0.31.925.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 31811643 0.31.938.842 I slot launch_slot_: id 0 | task 2539 | processing task, is_child = 0 0.32.585.216 I slot print_timing: id 0 | task 2539 | prompt eval time = 88.23 ms / 348 tokens ( 0.25 ms per token, 3944.37 tokens per second) 0.32.585.222 I slot print_timing: id 0 | task 2539 | eval time = 558.13 ms / 58 tokens ( 9.79 ms per token, 102.13 tokens per second) 0.32.585.223 I slot print_timing: id 0 | task 2539 | total time = 646.36 ms / 406 tokens 0.32.585.223 I slot print_timing: id 0 | task 2539 | graphs reused = 2466 0.32.585.224 I slot print_timing: id 0 | task 2539 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.585.254 I slot release: id 0 | task 2539 | stop processing: n_tokens = 430, truncated = 0 0.32.609.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 32496745 0.32.624.533 I slot launch_slot_: id 0 | task 2598 | processing task, is_child = 0 0.33.454.242 I slot print_timing: id 0 | task 2598 | prompt eval time = 107.31 ms / 404 tokens ( 0.27 ms per token, 3764.62 tokens per second) 0.33.454.247 I slot print_timing: id 0 | task 2598 | eval time = 722.38 ms / 75 tokens ( 9.76 ms per token, 102.44 tokens per second) 0.33.454.248 I slot print_timing: id 0 | task 2598 | total time = 829.69 ms / 479 tokens 0.33.454.250 I slot print_timing: id 0 | task 2598 | graphs reused = 2539 0.33.454.250 I slot print_timing: id 0 | task 2598 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.454.280 I slot release: id 0 | task 2598 | stop processing: n_tokens = 503, truncated = 0 0.33.482.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 33365770 0.33.499.425 I slot launch_slot_: id 0 | task 2674 | processing task, is_child = 0 0.34.347.513 I slot print_timing: id 0 | task 2674 | prompt eval time = 106.93 ms / 408 tokens ( 0.26 ms per token, 3815.47 tokens per second) 0.34.347.519 I slot print_timing: id 0 | task 2674 | eval time = 741.14 ms / 75 tokens ( 10.02 ms per token, 99.85 tokens per second) 0.34.347.520 I slot print_timing: id 0 | task 2674 | total time = 848.07 ms / 483 tokens 0.34.347.521 I slot print_timing: id 0 | task 2674 | graphs reused = 2612 0.34.347.522 I slot print_timing: id 0 | task 2674 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.347.552 I slot release: id 0 | task 2674 | stop processing: n_tokens = 509, truncated = 0 0.34.370.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 509, t_last = 34259042 0.34.387.120 I slot launch_slot_: id 0 | task 2750 | processing task, is_child = 0 0.34.948.534 I slot print_timing: id 0 | task 2750 | prompt eval time = 80.10 ms / 325 tokens ( 0.25 ms per token, 4057.58 tokens per second) 0.34.948.540 I slot print_timing: id 0 | task 2750 | eval time = 481.30 ms / 49 tokens ( 10.03 ms per token, 99.73 tokens per second) 0.34.948.541 I slot print_timing: id 0 | task 2750 | total time = 561.40 ms / 374 tokens 0.34.948.542 I slot print_timing: id 0 | task 2750 | graphs reused = 2659 0.34.948.543 I slot print_timing: id 0 | task 2750 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.948.571 I slot release: id 0 | task 2750 | stop processing: n_tokens = 402, truncated = 0 0.34.961.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 34860061 0.34.976.108 I slot launch_slot_: id 0 | task 2800 | processing task, is_child = 0 0.35.583.803 I slot print_timing: id 0 | task 2800 | prompt eval time = 87.99 ms / 345 tokens ( 0.26 ms per token, 3921.03 tokens per second) 0.35.583.809 I slot print_timing: id 0 | task 2800 | eval time = 519.69 ms / 53 tokens ( 9.99 ms per token, 100.06 tokens per second) 0.35.583.810 I slot print_timing: id 0 | task 2800 | total time = 607.67 ms / 398 tokens 0.35.583.811 I slot print_timing: id 0 | task 2800 | graphs reused = 2710 0.35.583.812 I slot print_timing: id 0 | task 2800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.583.843 I slot release: id 0 | task 2800 | stop processing: n_tokens = 422, truncated = 0 0.35.612.700 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 35495334 0.35.628.117 I slot launch_slot_: id 0 | task 2854 | processing task, is_child = 0 0.36.203.736 I slot print_timing: id 0 | task 2854 | prompt eval time = 91.80 ms / 344 tokens ( 0.27 ms per token, 3747.40 tokens per second) 0.36.203.742 I slot print_timing: id 0 | task 2854 | eval time = 483.80 ms / 50 tokens ( 9.87 ms per token, 101.28 tokens per second) 0.36.203.743 I slot print_timing: id 0 | task 2854 | total time = 575.60 ms / 394 tokens 0.36.203.744 I slot print_timing: id 0 | task 2854 | graphs reused = 2758 0.36.203.744 I slot print_timing: id 0 | task 2854 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.203.772 I slot release: id 0 | task 2854 | stop processing: n_tokens = 418, truncated = 0 0.36.208.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 36115263 0.36.222.566 I slot launch_slot_: id 0 | task 2905 | processing task, is_child = 0 0.37.025.801 I slot print_timing: id 0 | task 2905 | prompt eval time = 88.49 ms / 378 tokens ( 0.23 ms per token, 4271.62 tokens per second) 0.37.025.806 I slot print_timing: id 0 | task 2905 | eval time = 714.73 ms / 74 tokens ( 9.79 ms per token, 102.14 tokens per second) 0.37.025.807 I slot print_timing: id 0 | task 2905 | total time = 803.22 ms / 452 tokens 0.37.025.808 I slot print_timing: id 0 | task 2905 | graphs reused = 2830 0.37.025.809 I slot print_timing: id 0 | task 2905 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.025.842 I slot release: id 0 | task 2905 | stop processing: n_tokens = 476, truncated = 0 0.37.042.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 36937332 0.37.059.110 I slot launch_slot_: id 0 | task 2980 | processing task, is_child = 0 0.37.727.896 I slot print_timing: id 0 | task 2980 | prompt eval time = 80.58 ms / 331 tokens ( 0.24 ms per token, 4107.87 tokens per second) 0.37.727.902 I slot print_timing: id 0 | task 2980 | eval time = 588.19 ms / 61 tokens ( 9.80 ms per token, 102.01 tokens per second) 0.37.727.903 I slot print_timing: id 0 | task 2980 | total time = 668.77 ms / 392 tokens 0.37.727.904 I slot print_timing: id 0 | task 2980 | graphs reused = 2889 0.37.727.905 I slot print_timing: id 0 | task 2980 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.727.933 I slot release: id 0 | task 2980 | stop processing: n_tokens = 416, truncated = 0 0.37.755.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 37639424 0.37.770.108 I slot launch_slot_: id 0 | task 3042 | processing task, is_child = 0 0.38.347.624 I slot print_timing: id 0 | task 3042 | prompt eval time = 106.75 ms / 387 tokens ( 0.28 ms per token, 3625.16 tokens per second) 0.38.347.630 I slot print_timing: id 0 | task 3042 | eval time = 470.75 ms / 49 tokens ( 9.81 ms per token, 101.97 tokens per second) 0.38.347.631 I slot print_timing: id 0 | task 3042 | total time = 577.50 ms / 436 tokens 0.38.347.632 I slot print_timing: id 0 | task 3042 | graphs reused = 2936 0.38.347.633 I slot print_timing: id 0 | task 3042 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.347.663 I slot release: id 0 | task 3042 | stop processing: n_tokens = 460, truncated = 0 0.38.352.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 38259154 0.38.367.658 I slot launch_slot_: id 0 | task 3092 | processing task, is_child = 0 0.39.179.662 I slot print_timing: id 0 | task 3092 | prompt eval time = 88.16 ms / 345 tokens ( 0.26 ms per token, 3913.25 tokens per second) 0.39.179.667 I slot print_timing: id 0 | task 3092 | eval time = 723.83 ms / 75 tokens ( 9.78 ms per token, 102.23 tokens per second) 0.39.179.668 I slot print_timing: id 0 | task 3092 | total time = 811.99 ms / 420 tokens 0.39.179.669 I slot print_timing: id 0 | task 3092 | graphs reused = 3009 0.39.179.670 I slot print_timing: id 0 | task 3092 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.179.698 I slot release: id 0 | task 3092 | stop processing: n_tokens = 444, truncated = 0 0.39.193.267 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 39091189 0.39.208.620 I slot launch_slot_: id 0 | task 3168 | processing task, is_child = 0 0.39.902.077 I slot print_timing: id 0 | task 3168 | prompt eval time = 88.43 ms / 337 tokens ( 0.26 ms per token, 3810.84 tokens per second) 0.39.902.082 I slot print_timing: id 0 | task 3168 | eval time = 605.01 ms / 61 tokens ( 10.08 ms per token, 99.17 tokens per second) 0.39.902.084 I slot print_timing: id 0 | task 3168 | total time = 693.44 ms / 398 tokens 0.39.902.084 I slot print_timing: id 0 | task 3168 | graphs reused = 3068 0.39.902.085 I slot print_timing: id 0 | task 3168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.902.114 I slot release: id 0 | task 3168 | stop processing: n_tokens = 422, truncated = 0 0.39.926.011 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 39813605 0.39.940.774 I slot launch_slot_: id 0 | task 3230 | processing task, is_child = 0 0.40.991.059 I slot print_timing: id 0 | task 3230 | prompt eval time = 119.49 ms / 463 tokens ( 0.26 ms per token, 3874.90 tokens per second) 0.40.991.065 I slot print_timing: id 0 | task 3230 | eval time = 930.78 ms / 95 tokens ( 9.90 ms per token, 100.99 tokens per second) 0.40.991.067 I slot print_timing: id 0 | task 3230 | total time = 1050.27 ms / 558 tokens 0.40.991.067 I slot print_timing: id 0 | task 3230 | graphs reused = 3160 0.40.991.069 I slot print_timing: id 0 | task 3230 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.991.100 I slot release: id 0 | task 3230 | stop processing: n_tokens = 582, truncated = 0 0.40.995.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 40902590 0.41.014.861 I slot launch_slot_: id 0 | task 3326 | processing task, is_child = 0 0.42.188.171 I slot print_timing: id 0 | task 3326 | prompt eval time = 108.77 ms / 440 tokens ( 0.25 ms per token, 4045.12 tokens per second) 0.42.188.177 I slot print_timing: id 0 | task 3326 | eval time = 1064.52 ms / 109 tokens ( 9.86 ms per token, 101.45 tokens per second) 0.42.188.178 I slot print_timing: id 0 | task 3326 | total time = 1173.30 ms / 549 tokens 0.42.188.179 I slot print_timing: id 0 | task 3326 | graphs reused = 3266 0.42.188.180 I slot print_timing: id 0 | task 3326 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.188.211 I slot release: id 0 | task 3326 | stop processing: n_tokens = 573, truncated = 0 0.42.214.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 42099702 0.42.233.091 I slot launch_slot_: id 0 | task 3436 | processing task, is_child = 0 0.42.920.138 I slot print_timing: id 0 | task 3436 | prompt eval time = 80.60 ms / 336 tokens ( 0.24 ms per token, 4168.89 tokens per second) 0.42.920.144 I slot print_timing: id 0 | task 3436 | eval time = 606.44 ms / 63 tokens ( 9.78 ms per token, 102.24 tokens per second) 0.42.920.145 I slot print_timing: id 0 | task 3436 | total time = 687.03 ms / 399 tokens 0.42.920.146 I slot print_timing: id 0 | task 3436 | graphs reused = 3327 0.42.920.146 I slot print_timing: id 0 | task 3436 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.920.173 I slot release: id 0 | task 3436 | stop processing: n_tokens = 423, truncated = 0 0.42.936.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 42831663 0.42.951.817 I slot launch_slot_: id 0 | task 3500 | processing task, is_child = 0 0.43.598.805 I slot print_timing: id 0 | task 3500 | prompt eval time = 89.54 ms / 367 tokens ( 0.24 ms per token, 4098.82 tokens per second) 0.43.598.811 I slot print_timing: id 0 | task 3500 | eval time = 557.43 ms / 57 tokens ( 9.95 ms per token, 100.46 tokens per second) 0.43.598.812 I slot print_timing: id 0 | task 3500 | total time = 646.97 ms / 424 tokens 0.43.598.812 I slot print_timing: id 0 | task 3500 | graphs reused = 3382 0.43.598.813 I slot print_timing: id 0 | task 3500 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.598.842 I slot release: id 0 | task 3500 | stop processing: n_tokens = 448, truncated = 0 0.43.622.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 43510333 0.43.638.547 I slot launch_slot_: id 0 | task 3558 | processing task, is_child = 0 0.44.218.630 I slot print_timing: id 0 | task 3558 | prompt eval time = 80.26 ms / 327 tokens ( 0.25 ms per token, 4074.11 tokens per second) 0.44.218.636 I slot print_timing: id 0 | task 3558 | eval time = 499.80 ms / 52 tokens ( 9.80 ms per token, 102.04 tokens per second) 0.44.218.637 I slot print_timing: id 0 | task 3558 | total time = 580.07 ms / 379 tokens 0.44.218.638 I slot print_timing: id 0 | task 3558 | graphs reused = 3432 0.44.218.639 I slot print_timing: id 0 | task 3558 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.218.668 I slot release: id 0 | task 3558 | stop processing: n_tokens = 403, truncated = 0 0.44.239.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 44130158 0.44.253.186 I slot launch_slot_: id 0 | task 3611 | processing task, is_child = 0 0.45.101.914 I slot print_timing: id 0 | task 3611 | prompt eval time = 106.62 ms / 393 tokens ( 0.27 ms per token, 3686.13 tokens per second) 0.45.101.920 I slot print_timing: id 0 | task 3611 | eval time = 742.10 ms / 76 tokens ( 9.89 ms per token, 101.07 tokens per second) 0.45.101.921 I slot print_timing: id 0 | task 3611 | total time = 848.71 ms / 469 tokens 0.45.101.922 I slot print_timing: id 0 | task 3611 | graphs reused = 3506 0.45.101.923 I slot print_timing: id 0 | task 3611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.101.953 I slot release: id 0 | task 3611 | stop processing: n_tokens = 493, truncated = 0 0.45.117.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 45013444 0.45.134.359 I slot launch_slot_: id 0 | task 3688 | processing task, is_child = 0 0.45.875.956 I slot print_timing: id 0 | task 3688 | prompt eval time = 138.61 ms / 524 tokens ( 0.26 ms per token, 3780.45 tokens per second) 0.45.875.961 I slot print_timing: id 0 | task 3688 | eval time = 602.97 ms / 62 tokens ( 9.88 ms per token, 101.17 tokens per second) 0.45.875.962 I slot print_timing: id 0 | task 3688 | total time = 741.58 ms / 586 tokens 0.45.875.963 I slot print_timing: id 0 | task 3688 | graphs reused = 3566 0.45.875.964 I slot print_timing: id 0 | task 3688 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.875.996 I slot release: id 0 | task 3688 | stop processing: n_tokens = 610, truncated = 0 0.45.896.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 45787486 0.45.916.556 I slot launch_slot_: id 0 | task 3751 | processing task, is_child = 0 0.46.665.714 I slot print_timing: id 0 | task 3751 | prompt eval time = 154.92 ms / 602 tokens ( 0.26 ms per token, 3885.85 tokens per second) 0.46.665.720 I slot print_timing: id 0 | task 3751 | eval time = 594.22 ms / 61 tokens ( 9.90 ms per token, 100.97 tokens per second) 0.46.665.721 I slot print_timing: id 0 | task 3751 | total time = 749.14 ms / 663 tokens 0.46.665.722 I slot print_timing: id 0 | task 3751 | graphs reused = 3625 0.46.665.723 I slot print_timing: id 0 | task 3751 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.665.758 I slot release: id 0 | task 3751 | stop processing: n_tokens = 687, truncated = 0 0.46.689.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 46577249 0.46.712.140 I slot launch_slot_: id 0 | task 3813 | processing task, is_child = 0 0.47.482.423 I slot print_timing: id 0 | task 3813 | prompt eval time = 157.07 ms / 640 tokens ( 0.25 ms per token, 4074.62 tokens per second) 0.47.482.429 I slot print_timing: id 0 | task 3813 | eval time = 613.20 ms / 63 tokens ( 9.89 ms per token, 101.11 tokens per second) 0.47.482.430 I slot print_timing: id 0 | task 3813 | total time = 770.27 ms / 703 tokens 0.47.482.431 I slot print_timing: id 0 | task 3813 | graphs reused = 3686 0.47.482.432 I slot print_timing: id 0 | task 3813 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.482.471 I slot release: id 0 | task 3813 | stop processing: n_tokens = 727, truncated = 0 0.47.503.728 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 47393962 0.47.527.021 I slot launch_slot_: id 0 | task 3877 | processing task, is_child = 0 0.48.287.419 I slot print_timing: id 0 | task 3877 | prompt eval time = 156.63 ms / 629 tokens ( 0.25 ms per token, 4015.83 tokens per second) 0.48.287.426 I slot print_timing: id 0 | task 3877 | eval time = 603.75 ms / 62 tokens ( 9.90 ms per token, 101.04 tokens per second) 0.48.287.427 I slot print_timing: id 0 | task 3877 | total time = 760.38 ms / 691 tokens 0.48.287.428 I slot print_timing: id 0 | task 3877 | graphs reused = 3746 0.48.287.428 I slot print_timing: id 0 | task 3877 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.287.465 I slot release: id 0 | task 3877 | stop processing: n_tokens = 715, truncated = 0 0.48.306.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 48198956 0.48.329.849 I slot launch_slot_: id 0 | task 3940 | processing task, is_child = 0 0.49.004.547 I slot print_timing: id 0 | task 3940 | prompt eval time = 119.15 ms / 458 tokens ( 0.26 ms per token, 3844.02 tokens per second) 0.49.004.553 I slot print_timing: id 0 | task 3940 | eval time = 555.54 ms / 57 tokens ( 9.92 ms per token, 100.80 tokens per second) 0.49.004.554 I slot print_timing: id 0 | task 3940 | total time = 674.68 ms / 515 tokens 0.49.004.555 I slot print_timing: id 0 | task 3940 | graphs reused = 3800 0.49.004.556 I slot print_timing: id 0 | task 3940 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.004.588 I slot release: id 0 | task 3940 | stop processing: n_tokens = 539, truncated = 0 0.49.027.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 48916079 0.49.045.910 I slot launch_slot_: id 0 | task 3998 | processing task, is_child = 0 0.49.808.175 I slot print_timing: id 0 | task 3998 | prompt eval time = 149.46 ms / 594 tokens ( 0.25 ms per token, 3974.33 tokens per second) 0.49.808.180 I slot print_timing: id 0 | task 3998 | eval time = 612.79 ms / 63 tokens ( 9.88 ms per token, 101.18 tokens per second) 0.49.808.182 I slot print_timing: id 0 | task 3998 | total time = 762.25 ms / 657 tokens 0.49.808.182 I slot print_timing: id 0 | task 3998 | graphs reused = 3861 0.49.808.183 I slot print_timing: id 0 | task 3998 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.808.216 I slot release: id 0 | task 3998 | stop processing: n_tokens = 681, truncated = 0 0.49.827.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 49719707 0.49.850.013 I slot launch_slot_: id 0 | task 4062 | processing task, is_child = 0 0.50.489.433 I slot print_timing: id 0 | task 4062 | prompt eval time = 143.93 ms / 572 tokens ( 0.25 ms per token, 3974.24 tokens per second) 0.50.489.438 I slot print_timing: id 0 | task 4062 | eval time = 495.48 ms / 51 tokens ( 9.91 ms per token, 100.91 tokens per second) 0.50.489.440 I slot print_timing: id 0 | task 4062 | total time = 639.40 ms / 623 tokens 0.50.489.441 I slot print_timing: id 0 | task 4062 | graphs reused = 3910 0.50.489.441 I slot print_timing: id 0 | task 4062 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.489.477 I slot release: id 0 | task 4062 | stop processing: n_tokens = 647, truncated = 0 0.50.517.535 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 50400967 0.50.538.449 I slot launch_slot_: id 0 | task 4114 | processing task, is_child = 0 0.51.145.641 I slot print_timing: id 0 | task 4114 | prompt eval time = 121.75 ms / 502 tokens ( 0.24 ms per token, 4123.10 tokens per second) 0.51.145.647 I slot print_timing: id 0 | task 4114 | eval time = 485.43 ms / 50 tokens ( 9.91 ms per token, 100.94 tokens per second) 0.51.145.648 I slot print_timing: id 0 | task 4114 | total time = 607.18 ms / 552 tokens 0.51.145.649 I slot print_timing: id 0 | task 4114 | graphs reused = 3958 0.51.145.651 I slot print_timing: id 0 | task 4114 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.145.684 I slot release: id 0 | task 4114 | stop processing: n_tokens = 576, truncated = 0 0.51.169.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 51057174 0.51.188.918 I slot launch_slot_: id 0 | task 4165 | processing task, is_child = 0 0.51.867.208 I slot print_timing: id 0 | task 4165 | prompt eval time = 119.72 ms / 479 tokens ( 0.25 ms per token, 4000.97 tokens per second) 0.51.867.214 I slot print_timing: id 0 | task 4165 | eval time = 558.55 ms / 57 tokens ( 9.97 ms per token, 100.26 tokens per second) 0.51.867.215 I slot print_timing: id 0 | task 4165 | total time = 678.27 ms / 536 tokens 0.51.867.216 I slot print_timing: id 0 | task 4165 | graphs reused = 4012 0.51.867.217 I slot print_timing: id 0 | task 4165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.867.247 I slot release: id 0 | task 4165 | stop processing: n_tokens = 560, truncated = 0 0.51.872.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 51778737 0.51.891.523 I slot launch_slot_: id 0 | task 4223 | processing task, is_child = 0 0.52.467.968 I slot print_timing: id 0 | task 4223 | prompt eval time = 140.53 ms / 552 tokens ( 0.25 ms per token, 3928.07 tokens per second) 0.52.467.974 I slot print_timing: id 0 | task 4223 | eval time = 435.90 ms / 45 tokens ( 9.91 ms per token, 100.94 tokens per second) 0.52.467.975 I slot print_timing: id 0 | task 4223 | total time = 576.43 ms / 597 tokens 0.52.467.976 I slot print_timing: id 0 | task 4223 | graphs reused = 4055 0.52.467.977 I slot print_timing: id 0 | task 4223 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.468.012 I slot release: id 0 | task 4223 | stop processing: n_tokens = 621, truncated = 0 0.52.473.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 52379503 0.52.493.793 I slot launch_slot_: id 0 | task 4269 | processing task, is_child = 0 0.54.328.750 I slot print_timing: id 0 | task 4269 | prompt eval time = 131.90 ms / 514 tokens ( 0.26 ms per token, 3896.95 tokens per second) 0.54.328.756 I slot print_timing: id 0 | task 4269 | eval time = 1703.04 ms / 174 tokens ( 9.84 ms per token, 101.58 tokens per second) 0.54.328.758 I slot print_timing: id 0 | task 4269 | total time = 1834.94 ms / 688 tokens 0.54.328.759 I slot print_timing: id 0 | task 4269 | graphs reused = 4227 0.54.328.760 I slot print_timing: id 0 | task 4269 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.328.796 I slot release: id 0 | task 4269 | stop processing: n_tokens = 712, truncated = 0 0.54.350.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 54240287 0.54.373.477 I slot launch_slot_: id 0 | task 4444 | processing task, is_child = 0 0.54.884.757 I slot print_timing: id 0 | task 4444 | prompt eval time = 108.13 ms / 428 tokens ( 0.25 ms per token, 3958.05 tokens per second) 0.54.884.763 I slot print_timing: id 0 | task 4444 | eval time = 403.13 ms / 42 tokens ( 9.83 ms per token, 101.70 tokens per second) 0.54.884.764 I slot print_timing: id 0 | task 4444 | total time = 511.26 ms / 470 tokens 0.54.884.765 I slot print_timing: id 0 | task 4444 | graphs reused = 4267 0.54.884.765 I slot print_timing: id 0 | task 4444 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.884.797 I slot release: id 0 | task 4444 | stop processing: n_tokens = 494, truncated = 0 0.54.915.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 54796288 0.54.932.134 I slot launch_slot_: id 0 | task 4487 | processing task, is_child = 0 0.55.718.896 I slot print_timing: id 0 | task 4487 | prompt eval time = 135.19 ms / 521 tokens ( 0.26 ms per token, 3853.72 tokens per second) 0.55.718.901 I slot print_timing: id 0 | task 4487 | eval time = 651.55 ms / 66 tokens ( 10.02 ms per token, 99.76 tokens per second) 0.55.718.902 I slot print_timing: id 0 | task 4487 | total time = 786.75 ms / 587 tokens 0.55.718.903 I slot print_timing: id 0 | task 4487 | graphs reused = 4331 0.55.718.904 I slot print_timing: id 0 | task 4487 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.718.939 I slot release: id 0 | task 4487 | stop processing: n_tokens = 611, truncated = 0 0.55.738.977 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 55630430 0.55.758.950 I slot launch_slot_: id 0 | task 4554 | processing task, is_child = 0 0.56.376.560 I slot print_timing: id 0 | task 4554 | prompt eval time = 119.17 ms / 472 tokens ( 0.25 ms per token, 3960.73 tokens per second) 0.56.376.570 I slot print_timing: id 0 | task 4554 | eval time = 498.42 ms / 51 tokens ( 9.97 ms per token, 100.32 tokens per second) 0.56.376.571 I slot print_timing: id 0 | task 4554 | total time = 617.59 ms / 523 tokens 0.56.376.572 I slot print_timing: id 0 | task 4554 | graphs reused = 4379 0.56.376.573 I slot print_timing: id 0 | task 4554 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.376.618 I slot release: id 0 | task 4554 | stop processing: n_tokens = 547, truncated = 0 0.56.394.787 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 56288109 0.56.412.855 I slot launch_slot_: id 0 | task 4606 | processing task, is_child = 0 0.56.943.285 I slot print_timing: id 0 | task 4606 | prompt eval time = 108.07 ms / 428 tokens ( 0.25 ms per token, 3960.51 tokens per second) 0.56.943.291 I slot print_timing: id 0 | task 4606 | eval time = 422.35 ms / 44 tokens ( 9.82 ms per token, 101.81 tokens per second) 0.56.943.292 I slot print_timing: id 0 | task 4606 | total time = 530.42 ms / 472 tokens 0.56.943.293 I slot print_timing: id 0 | task 4606 | graphs reused = 4421 0.56.943.294 I slot print_timing: id 0 | task 4606 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.943.327 I slot release: id 0 | task 4606 | stop processing: n_tokens = 496, truncated = 0 0.56.970.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 56854817 0.56.987.359 I slot launch_slot_: id 0 | task 4651 | processing task, is_child = 0 0.57.544.457 I slot print_timing: id 0 | task 4651 | prompt eval time = 118.99 ms / 456 tokens ( 0.26 ms per token, 3832.35 tokens per second) 0.57.544.462 I slot print_timing: id 0 | task 4651 | eval time = 438.10 ms / 45 tokens ( 9.96 ms per token, 100.43 tokens per second) 0.57.544.464 I slot print_timing: id 0 | task 4651 | total time = 557.08 ms / 501 tokens 0.57.544.464 I slot print_timing: id 0 | task 4651 | graphs reused = 4463 0.57.544.465 I slot print_timing: id 0 | task 4651 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.544.497 I slot release: id 0 | task 4651 | stop processing: n_tokens = 525, truncated = 0 0.57.563.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 57455988 0.57.581.694 I slot launch_slot_: id 0 | task 4697 | processing task, is_child = 0 0.58.111.999 I slot print_timing: id 0 | task 4697 | prompt eval time = 108.44 ms / 439 tokens ( 0.25 ms per token, 4048.13 tokens per second) 0.58.112.005 I slot print_timing: id 0 | task 4697 | eval time = 421.85 ms / 44 tokens ( 9.81 ms per token, 101.93 tokens per second) 0.58.112.006 I slot print_timing: id 0 | task 4697 | total time = 530.29 ms / 483 tokens 0.58.112.007 I slot print_timing: id 0 | task 4697 | graphs reused = 4505 0.58.112.008 I slot print_timing: id 0 | task 4697 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.112.041 I slot release: id 0 | task 4697 | stop processing: n_tokens = 507, truncated = 0 0.58.138.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 58023531 0.58.156.110 I slot launch_slot_: id 0 | task 4742 | processing task, is_child = 0 0.58.889.614 I slot print_timing: id 0 | task 4742 | prompt eval time = 149.93 ms / 600 tokens ( 0.25 ms per token, 4001.79 tokens per second) 0.58.889.620 I slot print_timing: id 0 | task 4742 | eval time = 583.55 ms / 60 tokens ( 9.89 ms per token, 101.11 tokens per second) 0.58.889.621 I slot print_timing: id 0 | task 4742 | total time = 733.48 ms / 660 tokens 0.58.889.622 I slot print_timing: id 0 | task 4742 | graphs reused = 4563 0.58.889.622 I slot print_timing: id 0 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.889.662 I slot release: id 0 | task 4742 | stop processing: n_tokens = 684, truncated = 0 0.58.894.472 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 58801153 0.58.916.532 I slot launch_slot_: id 0 | task 4803 | processing task, is_child = 0 0.59.445.580 I slot print_timing: id 0 | task 4803 | prompt eval time = 119.25 ms / 473 tokens ( 0.25 ms per token, 3966.46 tokens per second) 0.59.445.586 I slot print_timing: id 0 | task 4803 | eval time = 409.78 ms / 42 tokens ( 9.99 ms per token, 100.05 tokens per second) 0.59.445.587 I slot print_timing: id 0 | task 4803 | total time = 529.03 ms / 515 tokens 0.59.445.587 I slot print_timing: id 0 | task 4803 | graphs reused = 4602 0.59.445.589 I slot print_timing: id 0 | task 4803 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.445.623 I slot release: id 0 | task 4803 | stop processing: n_tokens = 539, truncated = 0 0.59.474.063 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 59357113 0.59.492.017 I slot launch_slot_: id 0 | task 4846 | processing task, is_child = 0 1.00.327.382 I slot print_timing: id 0 | task 4846 | prompt eval time = 200.68 ms / 835 tokens ( 0.24 ms per token, 4160.77 tokens per second) 1.00.327.388 I slot print_timing: id 0 | task 4846 | eval time = 634.67 ms / 65 tokens ( 9.92 ms per token, 100.84 tokens per second) 1.00.327.389 I slot print_timing: id 0 | task 4846 | total time = 835.35 ms / 900 tokens 1.00.327.390 I slot print_timing: id 0 | task 4846 | graphs reused = 4665 1.00.327.391 I slot print_timing: id 0 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.327.436 I slot release: id 0 | task 4846 | stop processing: n_tokens = 924, truncated = 0 1.00.345.958 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 60238926 1.00.384.548 I slot launch_slot_: id 0 | task 4912 | processing task, is_child = 0 1.00.922.456 I slot print_timing: id 0 | task 4912 | prompt eval time = 119.50 ms / 454 tokens ( 0.26 ms per token, 3799.32 tokens per second) 1.00.922.462 I slot print_timing: id 0 | task 4912 | eval time = 418.40 ms / 43 tokens ( 9.96 ms per token, 100.38 tokens per second) 1.00.922.463 I slot print_timing: id 0 | task 4912 | total time = 537.89 ms / 497 tokens 1.00.922.464 I slot print_timing: id 0 | task 4912 | graphs reused = 4705 1.00.922.465 I slot print_timing: id 0 | task 4912 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.922.499 I slot release: id 0 | task 4912 | stop processing: n_tokens = 521, truncated = 0 1.00.940.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 60833989 1.00.957.983 I slot launch_slot_: id 0 | task 4956 | processing task, is_child = 0 1.01.590.173 I slot print_timing: id 0 | task 4956 | prompt eval time = 166.10 ms / 667 tokens ( 0.25 ms per token, 4015.60 tokens per second) 1.01.590.179 I slot print_timing: id 0 | task 4956 | eval time = 466.07 ms / 48 tokens ( 9.92 ms per token, 100.84 tokens per second) 1.01.590.180 I slot print_timing: id 0 | task 4956 | total time = 632.17 ms / 715 tokens 1.01.590.181 I slot print_timing: id 0 | task 4956 | graphs reused = 4751 1.01.590.182 I slot print_timing: id 0 | task 4956 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.590.222 I slot release: id 0 | task 4956 | stop processing: n_tokens = 741, truncated = 0 1.01.611.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 61501713 1.01.648.031 I slot launch_slot_: id 0 | task 5005 | processing task, is_child = 0 1.02.506.163 I slot print_timing: id 0 | task 5005 | prompt eval time = 156.94 ms / 628 tokens ( 0.25 ms per token, 4001.48 tokens per second) 1.02.506.168 I slot print_timing: id 0 | task 5005 | eval time = 701.17 ms / 69 tokens ( 10.31 ms per token, 96.98 tokens per second) 1.02.506.169 I slot print_timing: id 0 | task 5005 | total time = 858.11 ms / 697 tokens 1.02.506.170 I slot print_timing: id 0 | task 5005 | graphs reused = 4818 1.02.506.171 I slot print_timing: id 0 | task 5005 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.506.212 I slot release: id 0 | task 5005 | stop processing: n_tokens = 858, truncated = 0 1.02.529.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 62417702 1.02.556.245 I slot launch_slot_: id 0 | task 5075 | processing task, is_child = 0 1.03.457.832 I slot print_timing: id 0 | task 5075 | prompt eval time = 147.55 ms / 578 tokens ( 0.26 ms per token, 3917.29 tokens per second) 1.03.457.838 I slot print_timing: id 0 | task 5075 | eval time = 754.02 ms / 76 tokens ( 10.05 ms per token, 99.47 tokens per second) 1.03.457.839 I slot print_timing: id 0 | task 5075 | total time = 901.57 ms / 654 tokens 1.03.457.840 I slot print_timing: id 0 | task 5075 | graphs reused = 4892 1.03.457.841 I slot print_timing: id 0 | task 5075 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.457.879 I slot release: id 0 | task 5075 | stop processing: n_tokens = 678, truncated = 0 1.03.474.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 63369370 1.03.497.387 I slot launch_slot_: id 0 | task 5152 | processing task, is_child = 0 1.04.241.076 I slot print_timing: id 0 | task 5152 | prompt eval time = 119.28 ms / 461 tokens ( 0.26 ms per token, 3864.89 tokens per second) 1.04.241.083 I slot print_timing: id 0 | task 5152 | eval time = 624.39 ms / 64 tokens ( 9.91 ms per token, 100.90 tokens per second) 1.04.241.084 I slot print_timing: id 0 | task 5152 | total time = 743.67 ms / 525 tokens 1.04.241.084 I slot print_timing: id 0 | task 5152 | graphs reused = 4953 1.04.241.085 I slot print_timing: id 0 | task 5152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.241.118 I slot release: id 0 | task 5152 | stop processing: n_tokens = 549, truncated = 0 1.04.246.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 64152608 1.04.272.414 I slot launch_slot_: id 0 | task 5217 | processing task, is_child = 0 1.04.999.528 I slot print_timing: id 0 | task 5217 | prompt eval time = 153.49 ms / 613 tokens ( 0.25 ms per token, 3993.64 tokens per second) 1.04.999.535 I slot print_timing: id 0 | task 5217 | eval time = 573.61 ms / 59 tokens ( 9.89 ms per token, 101.11 tokens per second) 1.04.999.536 I slot print_timing: id 0 | task 5217 | total time = 727.10 ms / 672 tokens 1.04.999.538 I slot print_timing: id 0 | task 5217 | graphs reused = 5010 1.04.999.539 I slot print_timing: id 0 | task 5217 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.999.583 I slot release: id 0 | task 5217 | stop processing: n_tokens = 696, truncated = 0 1.05.029.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 64911074 1.05.052.239 I slot launch_slot_: id 0 | task 5277 | processing task, is_child = 0 1.05.877.962 I slot print_timing: id 0 | task 5277 | prompt eval time = 191.38 ms / 794 tokens ( 0.24 ms per token, 4148.92 tokens per second) 1.05.877.968 I slot print_timing: id 0 | task 5277 | eval time = 634.33 ms / 65 tokens ( 9.91 ms per token, 100.89 tokens per second) 1.05.877.969 I slot print_timing: id 0 | task 5277 | total time = 825.71 ms / 859 tokens 1.05.877.969 I slot print_timing: id 0 | task 5277 | graphs reused = 5073 1.05.877.970 I slot print_timing: id 0 | task 5277 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.878.012 I slot release: id 0 | task 5277 | stop processing: n_tokens = 883, truncated = 0 1.05.902.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 65789503 1.05.949.041 I slot launch_slot_: id 0 | task 5343 | processing task, is_child = 0 1.06.621.550 I slot print_timing: id 0 | task 5343 | prompt eval time = 108.97 ms / 431 tokens ( 0.25 ms per token, 3955.29 tokens per second) 1.06.621.556 I slot print_timing: id 0 | task 5343 | eval time = 563.52 ms / 58 tokens ( 9.89 ms per token, 101.15 tokens per second) 1.06.621.558 I slot print_timing: id 0 | task 5343 | total time = 672.49 ms / 489 tokens 1.06.621.559 I slot print_timing: id 0 | task 5343 | graphs reused = 5129 1.06.621.560 I slot print_timing: id 0 | task 5343 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.621.594 I slot release: id 0 | task 5343 | stop processing: n_tokens = 687, truncated = 0 1.06.651.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 66533085 1.06.673.894 I slot launch_slot_: id 0 | task 5402 | processing task, is_child = 0 1.07.310.212 I slot print_timing: id 0 | task 5402 | prompt eval time = 142.38 ms / 563 tokens ( 0.25 ms per token, 3954.32 tokens per second) 1.07.310.218 I slot print_timing: id 0 | task 5402 | eval time = 493.93 ms / 50 tokens ( 10.08 ms per token, 99.20 tokens per second) 1.07.310.220 I slot print_timing: id 0 | task 5402 | total time = 636.30 ms / 613 tokens 1.07.310.221 I slot print_timing: id 0 | task 5402 | graphs reused = 5177 1.07.310.222 I slot print_timing: id 0 | task 5402 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.310.257 I slot release: id 0 | task 5402 | stop processing: n_tokens = 637, truncated = 0 1.07.339.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 67221747 1.07.372.330 I slot launch_slot_: id 0 | task 5453 | processing task, is_child = 0 1.07.917.241 I slot print_timing: id 0 | task 5453 | prompt eval time = 80.58 ms / 331 tokens ( 0.24 ms per token, 4107.72 tokens per second) 1.07.917.246 I slot print_timing: id 0 | task 5453 | eval time = 464.31 ms / 48 tokens ( 9.88 ms per token, 101.23 tokens per second) 1.07.917.247 I slot print_timing: id 0 | task 5453 | total time = 544.89 ms / 379 tokens 1.07.917.248 I slot print_timing: id 0 | task 5453 | graphs reused = 5222 1.07.917.249 I slot print_timing: id 0 | task 5453 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.917.281 I slot release: id 0 | task 5453 | stop processing: n_tokens = 513, truncated = 0 1.07.933.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 67828771 1.07.950.821 I slot launch_slot_: id 0 | task 5502 | processing task, is_child = 0 1.08.724.229 I slot print_timing: id 0 | task 5502 | prompt eval time = 121.97 ms / 489 tokens ( 0.25 ms per token, 4009.05 tokens per second) 1.08.724.235 I slot print_timing: id 0 | task 5502 | eval time = 651.42 ms / 67 tokens ( 9.87 ms per token, 101.32 tokens per second) 1.08.724.236 I slot print_timing: id 0 | task 5502 | total time = 773.39 ms / 556 tokens 1.08.724.237 I slot print_timing: id 0 | task 5502 | graphs reused = 5287 1.08.724.238 I slot print_timing: id 0 | task 5502 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.724.271 I slot release: id 0 | task 5502 | stop processing: n_tokens = 580, truncated = 0 1.08.729.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 68635761 1.08.749.167 I slot launch_slot_: id 0 | task 5570 | processing task, is_child = 0 1.09.395.279 I slot print_timing: id 0 | task 5570 | prompt eval time = 122.27 ms / 510 tokens ( 0.24 ms per token, 4171.10 tokens per second) 1.09.395.285 I slot print_timing: id 0 | task 5570 | eval time = 523.83 ms / 54 tokens ( 9.88 ms per token, 101.18 tokens per second) 1.09.395.287 I slot print_timing: id 0 | task 5570 | total time = 646.10 ms / 564 tokens 1.09.395.288 I slot print_timing: id 0 | task 5570 | graphs reused = 5339 1.09.395.289 I slot print_timing: id 0 | task 5570 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.395.324 I slot release: id 0 | task 5570 | stop processing: n_tokens = 588, truncated = 0 1.09.417.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 69306815 1.09.436.672 I slot launch_slot_: id 0 | task 5625 | processing task, is_child = 0 1.10.292.128 I slot print_timing: id 0 | task 5625 | prompt eval time = 156.48 ms / 631 tokens ( 0.25 ms per token, 4032.49 tokens per second) 1.10.292.134 I slot print_timing: id 0 | task 5625 | eval time = 698.96 ms / 71 tokens ( 9.99 ms per token, 100.15 tokens per second) 1.10.292.135 I slot print_timing: id 0 | task 5625 | total time = 855.44 ms / 702 tokens 1.10.292.136 I slot print_timing: id 0 | task 5625 | graphs reused = 5408 1.10.292.137 I slot print_timing: id 0 | task 5625 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.292.176 I slot release: id 0 | task 5625 | stop processing: n_tokens = 726, truncated = 0 1.10.308.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 70203666 1.10.332.041 I slot launch_slot_: id 0 | task 5697 | processing task, is_child = 0 1.10.999.630 I slot print_timing: id 0 | task 5697 | prompt eval time = 142.66 ms / 570 tokens ( 0.25 ms per token, 3995.40 tokens per second) 1.10.999.636 I slot print_timing: id 0 | task 5697 | eval time = 524.91 ms / 54 tokens ( 9.90 ms per token, 100.97 tokens per second) 1.10.999.637 I slot print_timing: id 0 | task 5697 | total time = 667.57 ms / 624 tokens 1.10.999.638 I slot print_timing: id 0 | task 5697 | graphs reused = 5460 1.10.999.638 I slot print_timing: id 0 | task 5697 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.999.674 I slot release: id 0 | task 5697 | stop processing: n_tokens = 648, truncated = 0 1.11.006.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 70911164 1.11.028.604 I slot launch_slot_: id 0 | task 5752 | processing task, is_child = 0 1.11.696.768 I slot print_timing: id 0 | task 5752 | prompt eval time = 191.24 ms / 792 tokens ( 0.24 ms per token, 4141.44 tokens per second) 1.11.696.774 I slot print_timing: id 0 | task 5752 | eval time = 476.91 ms / 49 tokens ( 9.94 ms per token, 100.65 tokens per second) 1.11.696.775 I slot print_timing: id 0 | task 5752 | total time = 668.15 ms / 841 tokens 1.11.696.776 I slot print_timing: id 0 | task 5752 | graphs reused = 5507 1.11.696.778 I slot print_timing: id 0 | task 5752 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.696.820 I slot release: id 0 | task 5752 | stop processing: n_tokens = 867, truncated = 0 1.11.725.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 71608310 1.11.752.973 I slot launch_slot_: id 0 | task 5802 | processing task, is_child = 0 1.12.331.791 I slot print_timing: id 0 | task 5802 | prompt eval time = 142.27 ms / 564 tokens ( 0.25 ms per token, 3964.35 tokens per second) 1.12.331.797 I slot print_timing: id 0 | task 5802 | eval time = 436.53 ms / 45 tokens ( 9.92 ms per token, 100.79 tokens per second) 1.12.331.798 I slot print_timing: id 0 | task 5802 | total time = 578.80 ms / 609 tokens 1.12.331.799 I slot print_timing: id 0 | task 5802 | graphs reused = 5550 1.12.331.800 I slot print_timing: id 0 | task 5802 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.331.844 I slot release: id 0 | task 5802 | stop processing: n_tokens = 635, truncated = 0 1.12.351.749 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 72243334 1.12.372.812 I slot launch_slot_: id 0 | task 5848 | processing task, is_child = 0 1.13.059.741 I slot print_timing: id 0 | task 5848 | prompt eval time = 153.20 ms / 617 tokens ( 0.25 ms per token, 4027.49 tokens per second) 1.13.059.748 I slot print_timing: id 0 | task 5848 | eval time = 533.71 ms / 55 tokens ( 9.88 ms per token, 101.18 tokens per second) 1.13.059.749 I slot print_timing: id 0 | task 5848 | total time = 686.91 ms / 672 tokens 1.13.059.749 I slot print_timing: id 0 | task 5848 | graphs reused = 5603 1.13.059.750 I slot print_timing: id 0 | task 5848 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.059.789 I slot release: id 0 | task 5848 | stop processing: n_tokens = 696, truncated = 0 1.13.088.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 72971279 1.13.110.662 I slot launch_slot_: id 0 | task 5904 | processing task, is_child = 0 1.13.906.084 I slot print_timing: id 0 | task 5904 | prompt eval time = 143.01 ms / 572 tokens ( 0.25 ms per token, 3999.61 tokens per second) 1.13.906.089 I slot print_timing: id 0 | task 5904 | eval time = 652.39 ms / 67 tokens ( 9.88 ms per token, 101.17 tokens per second) 1.13.906.091 I slot print_timing: id 0 | task 5904 | total time = 795.41 ms / 639 tokens 1.13.906.091 I slot print_timing: id 0 | task 5904 | graphs reused = 5668 1.13.906.092 I slot print_timing: id 0 | task 5904 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.906.128 I slot release: id 0 | task 5904 | stop processing: n_tokens = 663, truncated = 0 1.13.912.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 73817618 1.13.934.786 I slot launch_slot_: id 0 | task 5972 | processing task, is_child = 0 1.14.641.808 I slot print_timing: id 0 | task 5972 | prompt eval time = 176.67 ms / 712 tokens ( 0.25 ms per token, 4030.09 tokens per second) 1.14.641.814 I slot print_timing: id 0 | task 5972 | eval time = 530.34 ms / 54 tokens ( 10.01 ms per token, 99.94 tokens per second) 1.14.641.815 I slot print_timing: id 0 | task 5972 | total time = 707.01 ms / 766 tokens 1.14.641.816 I slot print_timing: id 0 | task 5972 | graphs reused = 5719 1.14.641.817 I slot print_timing: id 0 | task 5972 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.641.859 I slot release: id 0 | task 5972 | stop processing: n_tokens = 790, truncated = 0 1.14.665.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 74553349 1.14.691.698 I slot launch_slot_: id 0 | task 6027 | processing task, is_child = 0 1.15.930.246 I slot print_timing: id 0 | task 6027 | prompt eval time = 191.42 ms / 791 tokens ( 0.24 ms per token, 4132.32 tokens per second) 1.15.930.252 I slot print_timing: id 0 | task 6027 | eval time = 1047.12 ms / 107 tokens ( 9.88 ms per token, 101.23 tokens per second) 1.15.930.253 I slot print_timing: id 0 | task 6027 | total time = 1238.53 ms / 898 tokens 1.15.930.254 I slot print_timing: id 0 | task 6027 | graphs reused = 5824 1.15.930.255 I slot print_timing: id 0 | task 6027 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.930.296 I slot release: id 0 | task 6027 | stop processing: n_tokens = 922, truncated = 0 1.15.934.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 922, t_last = 75841786 1.15.963.305 I slot launch_slot_: id 0 | task 6135 | processing task, is_child = 0 1.19.057.344 I slot print_timing: id 0 | task 6135 | n_gen = 308, tg = 102.13 t/s, tg_3s = 102.47 t/s 1.22.059.445 I slot print_timing: id 0 | task 6135 | n_gen = 613, tg = 101.86 t/s, tg_3s = 101.60 t/s 1.23.190.037 I slot print_timing: id 0 | task 6135 | prompt eval time = 88.17 ms / 369 tokens ( 0.24 ms per token, 4185.19 tokens per second) 1.23.190.042 I slot print_timing: id 0 | task 6135 | eval time = 7138.55 ms / 726 tokens ( 9.85 ms per token, 101.56 tokens per second) 1.23.190.043 I slot print_timing: id 0 | task 6135 | total time = 7226.72 ms / 1095 tokens 1.23.190.044 I slot print_timing: id 0 | task 6135 | graphs reused = 6545 1.23.190.045 I slot print_timing: id 0 | task 6135 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.190.075 I slot release: id 0 | task 6135 | stop processing: n_tokens = 1119, truncated = 0 1.23.194.472 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1119, t_last = 83101566 1.23.230.840 I slot launch_slot_: id 0 | task 6862 | processing task, is_child = 0 1.23.934.504 I slot print_timing: id 0 | task 6862 | prompt eval time = 106.64 ms / 388 tokens ( 0.27 ms per token, 3638.58 tokens per second) 1.23.934.510 I slot print_timing: id 0 | task 6862 | eval time = 597.01 ms / 62 tokens ( 9.79 ms per token, 102.18 tokens per second) 1.23.934.511 I slot print_timing: id 0 | task 6862 | total time = 703.65 ms / 450 tokens 1.23.934.512 I slot print_timing: id 0 | task 6862 | graphs reused = 6605 1.23.934.514 I slot print_timing: id 0 | task 6862 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.934.543 I slot release: id 0 | task 6862 | stop processing: n_tokens = 474, truncated = 0 1.23.963.554 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 83846034 1.23.963.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.23.967.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.23.991.174 I slot launch_slot_: id 0 | task 6925 | processing task, is_child = 0 1.24.715.664 I slot print_timing: id 0 | task 6925 | prompt eval time = 88.23 ms / 370 tokens ( 0.24 ms per token, 4193.54 tokens per second) 1.24.715.670 I slot print_timing: id 0 | task 6925 | eval time = 636.25 ms / 66 tokens ( 9.79 ms per token, 102.16 tokens per second) 1.24.715.671 I slot print_timing: id 0 | task 6925 | total time = 724.48 ms / 436 tokens 1.24.715.671 I slot print_timing: id 0 | task 6925 | graphs reused = 6669 1.24.715.672 I slot print_timing: id 0 | task 6925 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.715.705 I slot release: id 0 | task 6925 | stop processing: n_tokens = 460, truncated = 0 1.24.741.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 84627195 1.24.741.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.24.764.033 I slot launch_slot_: id 0 | task 6992 | processing task, is_child = 0 1.25.431.160 I slot print_timing: id 0 | task 6992 | prompt eval time = 87.58 ms / 340 tokens ( 0.26 ms per token, 3882.08 tokens per second) 1.25.431.166 I slot print_timing: id 0 | task 6992 | eval time = 579.53 ms / 60 tokens ( 9.82 ms per token, 101.81 tokens per second) 1.25.431.167 I slot print_timing: id 0 | task 6992 | total time = 667.11 ms / 400 tokens 1.25.431.168 I slot print_timing: id 0 | task 6992 | graphs reused = 6727 1.25.431.169 I slot print_timing: id 0 | task 6992 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.431.199 I slot release: id 0 | task 6992 | stop processing: n_tokens = 424, truncated = 0 1.25.451.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 85342690 1.25.451.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.25.472.191 I slot launch_slot_: id 0 | task 7053 | processing task, is_child = 0 1.26.333.109 I slot print_timing: id 0 | task 7053 | prompt eval time = 107.69 ms / 409 tokens ( 0.26 ms per token, 3797.80 tokens per second) 1.26.333.115 I slot print_timing: id 0 | task 7053 | eval time = 753.21 ms / 78 tokens ( 9.78 ms per token, 102.23 tokens per second) 1.26.333.116 I slot print_timing: id 0 | task 7053 | total time = 860.90 ms / 487 tokens 1.26.333.117 I slot print_timing: id 0 | task 7053 | graphs reused = 6803 1.26.333.118 I slot print_timing: id 0 | task 7053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.333.149 I slot release: id 0 | task 7053 | stop processing: n_tokens = 511, truncated = 0 1.26.354.459 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 86244639 1.26.354.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.26.382.478 I slot launch_slot_: id 0 | task 7132 | processing task, is_child = 0 1.27.406.939 I slot print_timing: id 0 | task 7132 | prompt eval time = 107.75 ms / 422 tokens ( 0.26 ms per token, 3916.55 tokens per second) 1.27.406.945 I slot print_timing: id 0 | task 7132 | eval time = 916.70 ms / 94 tokens ( 9.86 ms per token, 101.45 tokens per second) 1.27.406.946 I slot print_timing: id 0 | task 7132 | total time = 1024.44 ms / 516 tokens 1.27.406.947 I slot print_timing: id 0 | task 7132 | graphs reused = 6894 1.27.406.947 I slot print_timing: id 0 | task 7132 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.406.976 I slot release: id 0 | task 7132 | stop processing: n_tokens = 540, truncated = 0 1.27.433.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 87318467 1.27.433.494 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.27.457.327 I slot launch_slot_: id 0 | task 7227 | processing task, is_child = 0 1.28.673.454 I slot print_timing: id 0 | task 7227 | prompt eval time = 121.99 ms / 499 tokens ( 0.24 ms per token, 4090.43 tokens per second) 1.28.673.460 I slot print_timing: id 0 | task 7227 | eval time = 1094.12 ms / 112 tokens ( 9.86 ms per token, 101.45 tokens per second) 1.28.673.461 I slot print_timing: id 0 | task 7227 | total time = 1216.11 ms / 611 tokens 1.28.673.462 I slot print_timing: id 0 | task 7227 | graphs reused = 7004 1.28.673.462 I slot print_timing: id 0 | task 7227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.673.499 I slot release: id 0 | task 7227 | stop processing: n_tokens = 639, truncated = 0 1.28.690.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 88584990 1.28.690.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.538 MiB) 1.28.694.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.28.723.436 I slot launch_slot_: id 0 | task 7340 | processing task, is_child = 0 1.29.233.820 I slot print_timing: id 0 | task 7340 | prompt eval time = 88.07 ms / 345 tokens ( 0.26 ms per token, 3917.25 tokens per second) 1.29.233.826 I slot print_timing: id 0 | task 7340 | eval time = 422.30 ms / 44 tokens ( 9.82 ms per token, 101.82 tokens per second) 1.29.233.827 I slot print_timing: id 0 | task 7340 | total time = 510.37 ms / 389 tokens 1.29.233.828 I slot print_timing: id 0 | task 7340 | graphs reused = 7046 1.29.233.829 I slot print_timing: id 0 | task 7340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.233.856 I slot release: id 0 | task 7340 | stop processing: n_tokens = 413, truncated = 0 1.29.251.266 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 89145347 1.29.265.864 I slot launch_slot_: id 0 | task 7385 | processing task, is_child = 0 1.29.776.553 I slot print_timing: id 0 | task 7385 | prompt eval time = 88.06 ms / 348 tokens ( 0.25 ms per token, 3951.85 tokens per second) 1.29.776.559 I slot print_timing: id 0 | task 7385 | eval time = 422.61 ms / 44 tokens ( 9.83 ms per token, 101.75 tokens per second) 1.29.776.560 I slot print_timing: id 0 | task 7385 | total time = 510.67 ms / 392 tokens 1.29.776.560 I slot print_timing: id 0 | task 7385 | graphs reused = 7088 1.29.776.561 I slot print_timing: id 0 | task 7385 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.776.591 I slot release: id 0 | task 7385 | stop processing: n_tokens = 416, truncated = 0 1.29.798.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 89688082 1.29.798.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.29.817.468 I slot launch_slot_: id 0 | task 7430 | processing task, is_child = 0 1.30.580.294 I slot print_timing: id 0 | task 7430 | prompt eval time = 107.56 ms / 408 tokens ( 0.26 ms per token, 3793.20 tokens per second) 1.30.580.300 I slot print_timing: id 0 | task 7430 | eval time = 655.25 ms / 68 tokens ( 9.78 ms per token, 102.25 tokens per second) 1.30.580.300 I slot print_timing: id 0 | task 7430 | total time = 762.81 ms / 476 tokens 1.30.580.301 I slot print_timing: id 0 | task 7430 | graphs reused = 7154 1.30.580.302 I slot print_timing: id 0 | task 7430 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.580.331 I slot release: id 0 | task 7430 | stop processing: n_tokens = 500, truncated = 0 1.30.584.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 90491821 1.30.584.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.30.588.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 1.30.611.713 I slot launch_slot_: id 0 | task 7499 | processing task, is_child = 0 1.31.326.924 I slot print_timing: id 0 | task 7499 | prompt eval time = 119.52 ms / 465 tokens ( 0.26 ms per token, 3890.73 tokens per second) 1.31.326.930 I slot print_timing: id 0 | task 7499 | eval time = 595.68 ms / 61 tokens ( 9.93 ms per token, 100.73 tokens per second) 1.31.326.931 I slot print_timing: id 0 | task 7499 | total time = 715.20 ms / 526 tokens 1.31.326.932 I slot print_timing: id 0 | task 7499 | graphs reused = 7212 1.31.326.933 I slot print_timing: id 0 | task 7499 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.326.966 I slot release: id 0 | task 7499 | stop processing: n_tokens = 550, truncated = 0 1.31.341.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 91238457 1.31.341.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 1.31.365.030 I slot launch_slot_: id 0 | task 7561 | processing task, is_child = 0 1.32.049.783 I slot print_timing: id 0 | task 7561 | prompt eval time = 106.84 ms / 399 tokens ( 0.27 ms per token, 3734.49 tokens per second) 1.32.049.789 I slot print_timing: id 0 | task 7561 | eval time = 577.89 ms / 60 tokens ( 9.79 ms per token, 102.09 tokens per second) 1.32.049.790 I slot print_timing: id 0 | task 7561 | total time = 684.74 ms / 459 tokens 1.32.049.791 I slot print_timing: id 0 | task 7561 | graphs reused = 7270 1.32.049.791 I slot print_timing: id 0 | task 7561 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.049.822 I slot release: id 0 | task 7561 | stop processing: n_tokens = 500, truncated = 0 1.32.074.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 91961313 1.32.074.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 1.32.096.095 I slot launch_slot_: id 0 | task 7622 | processing task, is_child = 0 1.32.903.803 I slot print_timing: id 0 | task 7622 | prompt eval time = 107.88 ms / 419 tokens ( 0.26 ms per token, 3883.98 tokens per second) 1.32.903.809 I slot print_timing: id 0 | task 7622 | eval time = 699.81 ms / 72 tokens ( 9.86 ms per token, 101.46 tokens per second) 1.32.903.810 I slot print_timing: id 0 | task 7622 | total time = 807.69 ms / 491 tokens 1.32.903.810 I slot print_timing: id 0 | task 7622 | graphs reused = 7339 1.32.903.811 I slot print_timing: id 0 | task 7622 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.903.842 I slot release: id 0 | task 7622 | stop processing: n_tokens = 515, truncated = 0 1.32.930.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 92815332 1.32.930.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 1.32.953.340 I slot launch_slot_: id 0 | task 7695 | processing task, is_child = 0 1.33.765.283 I slot print_timing: id 0 | task 7695 | prompt eval time = 108.68 ms / 440 tokens ( 0.25 ms per token, 4048.73 tokens per second) 1.33.765.289 I slot print_timing: id 0 | task 7695 | eval time = 703.25 ms / 71 tokens ( 10.05 ms per token, 99.54 tokens per second) 1.33.765.290 I slot print_timing: id 0 | task 7695 | total time = 811.93 ms / 511 tokens 1.33.765.291 I slot print_timing: id 0 | task 7695 | graphs reused = 7407 1.33.765.292 I slot print_timing: id 0 | task 7695 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.765.325 I slot release: id 0 | task 7695 | stop processing: n_tokens = 535, truncated = 0 1.33.784.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 93676815 1.33.784.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.33.812.235 I slot launch_slot_: id 0 | task 7767 | processing task, is_child = 0 1.34.408.411 I slot print_timing: id 0 | task 7767 | prompt eval time = 91.63 ms / 372 tokens ( 0.25 ms per token, 4059.89 tokens per second) 1.34.408.417 I slot print_timing: id 0 | task 7767 | eval time = 504.53 ms / 52 tokens ( 9.89 ms per token, 101.08 tokens per second) 1.34.408.418 I slot print_timing: id 0 | task 7767 | total time = 596.16 ms / 424 tokens 1.34.408.418 I slot print_timing: id 0 | task 7767 | graphs reused = 7457 1.34.408.419 I slot print_timing: id 0 | task 7767 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.408.451 I slot release: id 0 | task 7767 | stop processing: n_tokens = 448, truncated = 0 1.34.436.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 94319942 1.34.436.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 1.34.458.808 I slot launch_slot_: id 0 | task 7820 | processing task, is_child = 0 1.35.143.386 I slot print_timing: id 0 | task 7820 | prompt eval time = 118.91 ms / 449 tokens ( 0.26 ms per token, 3775.90 tokens per second) 1.35.143.392 I slot print_timing: id 0 | task 7820 | eval time = 565.65 ms / 58 tokens ( 9.92 ms per token, 100.77 tokens per second) 1.35.143.393 I slot print_timing: id 0 | task 7820 | total time = 684.56 ms / 507 tokens 1.35.143.394 I slot print_timing: id 0 | task 7820 | graphs reused = 7512 1.35.143.395 I slot print_timing: id 0 | task 7820 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.143.429 I slot release: id 0 | task 7820 | stop processing: n_tokens = 531, truncated = 0 1.35.167.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 95054919 1.35.167.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 1.35.171.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.35.199.628 I slot launch_slot_: id 0 | task 7879 | processing task, is_child = 0 1.35.886.813 I slot print_timing: id 0 | task 7879 | prompt eval time = 88.71 ms / 360 tokens ( 0.25 ms per token, 4058.17 tokens per second) 1.35.886.819 I slot print_timing: id 0 | task 7879 | eval time = 598.46 ms / 62 tokens ( 9.81 ms per token, 101.93 tokens per second) 1.35.886.821 I slot print_timing: id 0 | task 7879 | total time = 687.17 ms / 422 tokens 1.35.886.821 I slot print_timing: id 0 | task 7879 | graphs reused = 7572 1.35.886.822 I slot print_timing: id 0 | task 7879 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.886.851 I slot release: id 0 | task 7879 | stop processing: n_tokens = 446, truncated = 0 1.35.915.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 95798342 1.35.915.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 1.35.935.903 I slot launch_slot_: id 0 | task 7942 | processing task, is_child = 0 1.36.554.802 I slot print_timing: id 0 | task 7942 | prompt eval time = 88.15 ms / 346 tokens ( 0.25 ms per token, 3924.99 tokens per second) 1.36.554.808 I slot print_timing: id 0 | task 7942 | eval time = 530.73 ms / 55 tokens ( 9.83 ms per token, 101.75 tokens per second) 1.36.554.809 I slot print_timing: id 0 | task 7942 | total time = 618.88 ms / 401 tokens 1.36.554.810 I slot print_timing: id 0 | task 7942 | graphs reused = 7625 1.36.554.811 I slot print_timing: id 0 | task 7942 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.554.843 I slot release: id 0 | task 7942 | stop processing: n_tokens = 425, truncated = 0 1.36.569.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 96466333 1.36.569.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 1.36.590.777 I slot launch_slot_: id 0 | task 7998 | processing task, is_child = 0 1.37.199.974 I slot print_timing: id 0 | task 7998 | prompt eval time = 108.59 ms / 434 tokens ( 0.25 ms per token, 3996.57 tokens per second) 1.37.199.980 I slot print_timing: id 0 | task 7998 | eval time = 500.59 ms / 52 tokens ( 9.82 ms per token, 101.88 tokens per second) 1.37.199.981 I slot print_timing: id 0 | task 7998 | total time = 609.18 ms / 486 tokens 1.37.199.982 I slot print_timing: id 0 | task 7998 | graphs reused = 7675 1.37.199.983 I slot print_timing: id 0 | task 7998 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.200.015 I slot release: id 0 | task 7998 | stop processing: n_tokens = 510, truncated = 0 1.37.219.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 97111506 1.37.220.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 1.37.243.326 I slot launch_slot_: id 0 | task 8051 | processing task, is_child = 0 1.37.909.511 I slot print_timing: id 0 | task 8051 | prompt eval time = 88.00 ms / 369 tokens ( 0.24 ms per token, 4193.09 tokens per second) 1.37.909.517 I slot print_timing: id 0 | task 8051 | eval time = 578.17 ms / 59 tokens ( 9.97 ms per token, 100.32 tokens per second) 1.37.909.518 I slot print_timing: id 0 | task 8051 | total time = 666.17 ms / 428 tokens 1.37.909.519 I slot print_timing: id 0 | task 8051 | graphs reused = 7732 1.37.909.520 I slot print_timing: id 0 | task 8051 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.909.554 I slot release: id 0 | task 8051 | stop processing: n_tokens = 452, truncated = 0 1.37.926.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 97821045 1.37.926.294 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 1.37.946.790 I slot launch_slot_: id 0 | task 8111 | processing task, is_child = 0 1.38.818.407 I slot print_timing: id 0 | task 8111 | prompt eval time = 109.40 ms / 446 tokens ( 0.25 ms per token, 4076.71 tokens per second) 1.38.818.412 I slot print_timing: id 0 | task 8111 | eval time = 762.20 ms / 78 tokens ( 9.90 ms per token, 101.02 tokens per second) 1.38.818.413 I slot print_timing: id 0 | task 8111 | total time = 871.60 ms / 524 tokens 1.38.818.414 I slot print_timing: id 0 | task 8111 | graphs reused = 7807 1.38.818.415 I slot print_timing: id 0 | task 8111 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.818.447 I slot release: id 0 | task 8111 | stop processing: n_tokens = 548, truncated = 0 1.38.822.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 98729938 1.38.822.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 1.38.845.503 I slot launch_slot_: id 0 | task 8190 | processing task, is_child = 0 1.39.414.824 I slot print_timing: id 0 | task 8190 | prompt eval time = 106.84 ms / 396 tokens ( 0.27 ms per token, 3706.44 tokens per second) 1.39.414.831 I slot print_timing: id 0 | task 8190 | eval time = 462.47 ms / 48 tokens ( 9.84 ms per token, 101.63 tokens per second) 1.39.414.832 I slot print_timing: id 0 | task 8190 | total time = 569.31 ms / 444 tokens 1.39.414.833 I slot print_timing: id 0 | task 8190 | graphs reused = 7853 1.39.414.833 I slot print_timing: id 0 | task 8190 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.414.865 I slot release: id 0 | task 8190 | stop processing: n_tokens = 470, truncated = 0 1.39.440.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 99326355 1.39.440.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.39.464.124 I slot launch_slot_: id 0 | task 8239 | processing task, is_child = 0 1.40.446.265 I slot print_timing: id 0 | task 8239 | prompt eval time = 120.06 ms / 466 tokens ( 0.26 ms per token, 3881.30 tokens per second) 1.40.446.271 I slot print_timing: id 0 | task 8239 | eval time = 862.06 ms / 88 tokens ( 9.91 ms per token, 100.92 tokens per second) 1.40.446.272 I slot print_timing: id 0 | task 8239 | total time = 982.12 ms / 554 tokens 1.40.446.273 I slot print_timing: id 0 | task 8239 | graphs reused = 7938 1.40.446.274 I slot print_timing: id 0 | task 8239 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.446.304 I slot release: id 0 | task 8239 | stop processing: n_tokens = 578, truncated = 0 1.40.469.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 100357795 1.40.469.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 1.40.495.062 I slot launch_slot_: id 0 | task 8328 | processing task, is_child = 0 1.41.289.295 I slot print_timing: id 0 | task 8328 | prompt eval time = 119.75 ms / 467 tokens ( 0.26 ms per token, 3899.63 tokens per second) 1.41.289.301 I slot print_timing: id 0 | task 8328 | eval time = 674.46 ms / 66 tokens ( 10.38 ms per token, 96.37 tokens per second) 1.41.289.302 I slot print_timing: id 0 | task 8328 | total time = 794.21 ms / 533 tokens 1.41.289.303 I slot print_timing: id 0 | task 8328 | graphs reused = 8001 1.41.289.305 I slot print_timing: id 0 | task 8328 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.289.341 I slot release: id 0 | task 8328 | stop processing: n_tokens = 557, truncated = 0 1.41.312.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 101200832 1.41.312.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 1.41.317.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.41.342.673 I slot launch_slot_: id 0 | task 8395 | processing task, is_child = 0 1.42.156.515 I slot print_timing: id 0 | task 8395 | prompt eval time = 119.32 ms / 454 tokens ( 0.26 ms per token, 3804.86 tokens per second) 1.42.156.521 I slot print_timing: id 0 | task 8395 | eval time = 694.50 ms / 71 tokens ( 9.92 ms per token, 100.79 tokens per second) 1.42.156.522 I slot print_timing: id 0 | task 8395 | total time = 813.83 ms / 525 tokens 1.42.156.523 I slot print_timing: id 0 | task 8395 | graphs reused = 8069 1.42.156.524 I slot print_timing: id 0 | task 8395 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.156.559 I slot release: id 0 | task 8395 | stop processing: n_tokens = 549, truncated = 0 1.42.170.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 102068050 1.42.170.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.42.193.324 I slot launch_slot_: id 0 | task 8467 | processing task, is_child = 0 1.42.898.697 I slot print_timing: id 0 | task 8467 | prompt eval time = 107.84 ms / 409 tokens ( 0.26 ms per token, 3792.66 tokens per second) 1.42.898.703 I slot print_timing: id 0 | task 8467 | eval time = 597.52 ms / 62 tokens ( 9.80 ms per token, 102.09 tokens per second) 1.42.898.704 I slot print_timing: id 0 | task 8467 | total time = 705.36 ms / 471 tokens 1.42.898.705 I slot print_timing: id 0 | task 8467 | graphs reused = 8129 1.42.898.706 I slot print_timing: id 0 | task 8467 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.898.735 I slot release: id 0 | task 8467 | stop processing: n_tokens = 495, truncated = 0 1.42.924.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 102810226 1.42.924.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 1.42.946.507 I slot launch_slot_: id 0 | task 8530 | processing task, is_child = 0 1.44.120.106 I slot print_timing: id 0 | task 8530 | prompt eval time = 88.20 ms / 349 tokens ( 0.25 ms per token, 3956.78 tokens per second) 1.44.120.112 I slot print_timing: id 0 | task 8530 | eval time = 1085.38 ms / 112 tokens ( 9.78 ms per token, 102.27 tokens per second) 1.44.120.113 I slot print_timing: id 0 | task 8530 | total time = 1173.59 ms / 461 tokens 1.44.120.114 I slot print_timing: id 0 | task 8530 | graphs reused = 8239 1.44.120.115 I slot print_timing: id 0 | task 8530 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.120.142 I slot release: id 0 | task 8530 | stop processing: n_tokens = 485, truncated = 0 1.44.124.638 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 104031633 1.44.124.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 1.44.145.574 I slot launch_slot_: id 0 | task 8643 | processing task, is_child = 0 1.44.818.687 I slot print_timing: id 0 | task 8643 | prompt eval time = 108.64 ms / 435 tokens ( 0.25 ms per token, 4003.94 tokens per second) 1.44.818.693 I slot print_timing: id 0 | task 8643 | eval time = 564.46 ms / 58 tokens ( 9.90 ms per token, 100.98 tokens per second) 1.44.818.694 I slot print_timing: id 0 | task 8643 | total time = 673.10 ms / 493 tokens 1.44.818.696 I slot print_timing: id 0 | task 8643 | graphs reused = 8294 1.44.818.697 I slot print_timing: id 0 | task 8643 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.818.727 I slot release: id 0 | task 8643 | stop processing: n_tokens = 517, truncated = 0 1.44.839.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 104730217 1.44.839.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.318 MiB) 1.44.861.031 I slot launch_slot_: id 0 | task 8702 | processing task, is_child = 0 1.45.411.457 I slot print_timing: id 0 | task 8702 | prompt eval time = 80.47 ms / 322 tokens ( 0.25 ms per token, 4001.69 tokens per second) 1.45.411.462 I slot print_timing: id 0 | task 8702 | eval time = 469.94 ms / 47 tokens ( 10.22 ms per token, 97.88 tokens per second) 1.45.411.464 I slot print_timing: id 0 | task 8702 | total time = 550.41 ms / 369 tokens 1.45.411.464 I slot print_timing: id 0 | task 8702 | graphs reused = 8339 1.45.411.465 I slot print_timing: id 0 | task 8702 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.411.495 I slot release: id 0 | task 8702 | stop processing: n_tokens = 393, truncated = 0 1.45.415.671 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 105322985 1.45.415.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.45.435.428 I slot launch_slot_: id 0 | task 8750 | processing task, is_child = 0 1.46.064.082 I slot print_timing: id 0 | task 8750 | prompt eval time = 88.81 ms / 360 tokens ( 0.25 ms per token, 4053.37 tokens per second) 1.46.064.088 I slot print_timing: id 0 | task 8750 | eval time = 539.82 ms / 56 tokens ( 9.81 ms per token, 101.89 tokens per second) 1.46.064.089 I slot print_timing: id 0 | task 8750 | total time = 628.64 ms / 416 tokens 1.46.064.090 I slot print_timing: id 0 | task 8750 | graphs reused = 8393 1.46.064.091 I slot print_timing: id 0 | task 8750 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.064.121 I slot release: id 0 | task 8750 | stop processing: n_tokens = 440, truncated = 0 1.46.085.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 105975611 1.46.085.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 1.46.104.946 I slot launch_slot_: id 0 | task 8807 | processing task, is_child = 0 1.46.925.620 I slot print_timing: id 0 | task 8807 | prompt eval time = 108.69 ms / 443 tokens ( 0.25 ms per token, 4075.77 tokens per second) 1.46.925.626 I slot print_timing: id 0 | task 8807 | eval time = 711.97 ms / 73 tokens ( 9.89 ms per token, 101.13 tokens per second) 1.46.925.627 I slot print_timing: id 0 | task 8807 | total time = 820.66 ms / 516 tokens 1.46.925.628 I slot print_timing: id 0 | task 8807 | graphs reused = 8463 1.46.925.629 I slot print_timing: id 0 | task 8807 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.925.660 I slot release: id 0 | task 8807 | stop processing: n_tokens = 540, truncated = 0 1.46.954.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 106837151 1.46.954.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 1.46.985.101 I slot launch_slot_: id 0 | task 8881 | processing task, is_child = 0 1.47.517.515 I slot print_timing: id 0 | task 8881 | prompt eval time = 108.87 ms / 442 tokens ( 0.25 ms per token, 4059.85 tokens per second) 1.47.517.521 I slot print_timing: id 0 | task 8881 | eval time = 423.52 ms / 44 tokens ( 9.85 ms per token, 101.53 tokens per second) 1.47.517.522 I slot print_timing: id 0 | task 8881 | total time = 532.40 ms / 486 tokens 1.47.517.523 I slot print_timing: id 0 | task 8881 | graphs reused = 8505 1.47.517.524 I slot print_timing: id 0 | task 8881 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.517.553 I slot release: id 0 | task 8881 | stop processing: n_tokens = 510, truncated = 0 1.47.546.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 107429044 1.47.546.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.47.550.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.47.574.360 I slot launch_slot_: id 0 | task 8926 | processing task, is_child = 0 1.48.124.109 I slot print_timing: id 0 | task 8926 | prompt eval time = 119.12 ms / 470 tokens ( 0.25 ms per token, 3945.60 tokens per second) 1.48.124.114 I slot print_timing: id 0 | task 8926 | eval time = 430.61 ms / 44 tokens ( 10.01 ms per token, 99.86 tokens per second) 1.48.124.115 I slot print_timing: id 0 | task 8926 | total time = 549.73 ms / 514 tokens 1.48.124.116 I slot print_timing: id 0 | task 8926 | graphs reused = 8546 1.48.124.117 I slot print_timing: id 0 | task 8926 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.124.151 I slot release: id 0 | task 8926 | stop processing: n_tokens = 538, truncated = 0 1.48.153.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 108035641 1.48.153.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 1.48.175.203 I slot launch_slot_: id 0 | task 8971 | processing task, is_child = 0 1.48.632.537 I slot print_timing: id 0 | task 8971 | prompt eval time = 120.54 ms / 483 tokens ( 0.25 ms per token, 4007.07 tokens per second) 1.48.632.543 I slot print_timing: id 0 | task 8971 | eval time = 336.78 ms / 34 tokens ( 10.21 ms per token, 97.99 tokens per second) 1.48.632.545 I slot print_timing: id 0 | task 8971 | total time = 457.31 ms / 517 tokens 1.48.632.546 I slot print_timing: id 0 | task 8971 | graphs reused = 8577 1.48.632.547 I slot print_timing: id 0 | task 8971 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.632.607 I slot release: id 0 | task 8971 | stop processing: n_tokens = 541, truncated = 0 1.48.638.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 108544099 1.48.638.459 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.48.666.830 I slot launch_slot_: id 0 | task 9006 | processing task, is_child = 0 1.49.327.113 I slot print_timing: id 0 | task 9006 | prompt eval time = 120.70 ms / 463 tokens ( 0.26 ms per token, 3835.89 tokens per second) 1.49.327.119 I slot print_timing: id 0 | task 9006 | eval time = 539.56 ms / 55 tokens ( 9.99 ms per token, 100.08 tokens per second) 1.49.327.120 I slot print_timing: id 0 | task 9006 | total time = 660.26 ms / 518 tokens 1.49.327.121 I slot print_timing: id 0 | task 9006 | graphs reused = 8629 1.49.327.122 I slot print_timing: id 0 | task 9006 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.327.154 I slot release: id 0 | task 9006 | stop processing: n_tokens = 542, truncated = 0 1.49.348.207 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 109238644 1.49.348.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.49.351.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.49.376.652 I slot launch_slot_: id 0 | task 9062 | processing task, is_child = 0 1.49.965.589 I slot print_timing: id 0 | task 9062 | prompt eval time = 107.78 ms / 421 tokens ( 0.26 ms per token, 3906.25 tokens per second) 1.49.965.594 I slot print_timing: id 0 | task 9062 | eval time = 481.14 ms / 50 tokens ( 9.82 ms per token, 101.84 tokens per second) 1.49.965.595 I slot print_timing: id 0 | task 9062 | total time = 588.92 ms / 471 tokens 1.49.965.596 I slot print_timing: id 0 | task 9062 | graphs reused = 8677 1.49.965.598 I slot print_timing: id 0 | task 9062 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.965.627 I slot release: id 0 | task 9062 | stop processing: n_tokens = 495, truncated = 0 1.49.984.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 109877118 1.49.984.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.50.005.905 I slot launch_slot_: id 0 | task 9113 | processing task, is_child = 0 1.50.507.435 I slot print_timing: id 0 | task 9113 | prompt eval time = 89.10 ms / 360 tokens ( 0.25 ms per token, 4040.27 tokens per second) 1.50.507.441 I slot print_timing: id 0 | task 9113 | eval time = 412.41 ms / 43 tokens ( 9.82 ms per token, 101.84 tokens per second) 1.50.507.442 I slot print_timing: id 0 | task 9113 | total time = 501.51 ms / 403 tokens 1.50.507.443 I slot print_timing: id 0 | task 9113 | graphs reused = 8718 1.50.507.444 I slot print_timing: id 0 | task 9113 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.507.473 I slot release: id 0 | task 9113 | stop processing: n_tokens = 427, truncated = 0 1.50.528.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 110418964 1.50.528.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.664 MiB) 1.50.551.700 I slot launch_slot_: id 0 | task 9157 | processing task, is_child = 0 1.51.366.402 I slot print_timing: id 0 | task 9157 | prompt eval time = 142.26 ms / 547 tokens ( 0.26 ms per token, 3844.99 tokens per second) 1.51.366.408 I slot print_timing: id 0 | task 9157 | eval time = 672.42 ms / 69 tokens ( 9.89 ms per token, 101.13 tokens per second) 1.51.366.409 I slot print_timing: id 0 | task 9157 | total time = 814.69 ms / 616 tokens 1.51.366.410 I slot print_timing: id 0 | task 9157 | graphs reused = 8785 1.51.366.411 I slot print_timing: id 0 | task 9157 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.366.446 I slot release: id 0 | task 9157 | stop processing: n_tokens = 640, truncated = 0 1.51.372.490 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 111277936 1.51.372.554 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.51.398.020 I slot launch_slot_: id 0 | task 9227 | processing task, is_child = 0 1.52.634.881 I slot print_timing: id 0 | task 9227 | prompt eval time = 187.25 ms / 749 tokens ( 0.25 ms per token, 3999.94 tokens per second) 1.52.634.887 I slot print_timing: id 0 | task 9227 | eval time = 1049.59 ms / 107 tokens ( 9.90 ms per token, 100.99 tokens per second) 1.52.634.888 I slot print_timing: id 0 | task 9227 | total time = 1236.85 ms / 856 tokens 1.52.634.889 I slot print_timing: id 0 | task 9227 | graphs reused = 8890 1.52.634.890 I slot print_timing: id 0 | task 9227 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.634.930 I slot release: id 0 | task 9227 | stop processing: n_tokens = 880, truncated = 0 1.52.663.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 112546420 1.52.663.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 1.52.667.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 1.52.712.812 I slot launch_slot_: id 0 | task 9335 | processing task, is_child = 0 1.53.349.335 I slot print_timing: id 0 | task 9335 | prompt eval time = 170.35 ms / 678 tokens ( 0.25 ms per token, 3980.09 tokens per second) 1.53.349.341 I slot print_timing: id 0 | task 9335 | eval time = 466.16 ms / 48 tokens ( 9.92 ms per token, 100.82 tokens per second) 1.53.349.342 I slot print_timing: id 0 | task 9335 | total time = 636.50 ms / 726 tokens 1.53.349.342 I slot print_timing: id 0 | task 9335 | graphs reused = 8936 1.53.349.343 I slot print_timing: id 0 | task 9335 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.349.381 I slot release: id 0 | task 9335 | stop processing: n_tokens = 750, truncated = 0 1.53.354.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 113260871 1.53.354.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.538 MiB) 1.53.359.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.53.389.727 I slot launch_slot_: id 0 | task 9384 | processing task, is_child = 0 1.54.095.942 I slot print_timing: id 0 | task 9384 | prompt eval time = 142.62 ms / 567 tokens ( 0.25 ms per token, 3975.49 tokens per second) 1.54.095.948 I slot print_timing: id 0 | task 9384 | eval time = 563.58 ms / 57 tokens ( 10.06 ms per token, 99.37 tokens per second) 1.54.095.949 I slot print_timing: id 0 | task 9384 | total time = 706.20 ms / 624 tokens 1.54.095.950 I slot print_timing: id 0 | task 9384 | graphs reused = 8991 1.54.095.951 I slot print_timing: id 0 | task 9384 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.095.986 I slot release: id 0 | task 9384 | stop processing: n_tokens = 648, truncated = 0 1.54.122.561 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 114007477 1.54.122.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.54.149.154 I slot launch_slot_: id 0 | task 9442 | processing task, is_child = 0 1.54.835.645 I slot print_timing: id 0 | task 9442 | prompt eval time = 122.02 ms / 501 tokens ( 0.24 ms per token, 4105.95 tokens per second) 1.54.835.650 I slot print_timing: id 0 | task 9442 | eval time = 564.46 ms / 58 tokens ( 9.90 ms per token, 100.98 tokens per second) 1.54.835.651 I slot print_timing: id 0 | task 9442 | total time = 686.48 ms / 559 tokens 1.54.835.652 I slot print_timing: id 0 | task 9442 | graphs reused = 9047 1.54.835.653 I slot print_timing: id 0 | task 9442 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.835.684 I slot release: id 0 | task 9442 | stop processing: n_tokens = 583, truncated = 0 1.54.857.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 114747175 1.54.857.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 1.54.885.662 I slot launch_slot_: id 0 | task 9501 | processing task, is_child = 0 1.55.681.496 I slot print_timing: id 0 | task 9501 | prompt eval time = 190.94 ms / 769 tokens ( 0.25 ms per token, 4027.36 tokens per second) 1.55.681.501 I slot print_timing: id 0 | task 9501 | eval time = 604.87 ms / 62 tokens ( 9.92 ms per token, 100.85 tokens per second) 1.55.681.502 I slot print_timing: id 0 | task 9501 | total time = 795.81 ms / 831 tokens 1.55.681.503 I slot print_timing: id 0 | task 9501 | graphs reused = 9107 1.55.681.504 I slot print_timing: id 0 | task 9501 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.681.544 I slot release: id 0 | task 9501 | stop processing: n_tokens = 855, truncated = 0 1.55.686.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 115593035 1.55.686.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.55.690.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 1.55.727.787 I slot launch_slot_: id 0 | task 9564 | processing task, is_child = 0 1.56.452.305 I slot print_timing: id 0 | task 9564 | prompt eval time = 122.04 ms / 500 tokens ( 0.24 ms per token, 4097.02 tokens per second) 1.56.452.311 I slot print_timing: id 0 | task 9564 | eval time = 602.46 ms / 61 tokens ( 10.04 ms per token, 99.59 tokens per second) 1.56.452.312 I slot print_timing: id 0 | task 9564 | total time = 724.50 ms / 561 tokens 1.56.452.313 I slot print_timing: id 0 | task 9564 | graphs reused = 9166 1.56.452.314 I slot print_timing: id 0 | task 9564 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.452.348 I slot release: id 0 | task 9564 | stop processing: n_tokens = 585, truncated = 0 1.56.478.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 116363839 1.56.479.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.56.483.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 1.56.510.509 I slot launch_slot_: id 0 | task 9626 | processing task, is_child = 0 1.57.240.630 I slot print_timing: id 0 | task 9626 | prompt eval time = 156.46 ms / 632 tokens ( 0.25 ms per token, 4039.42 tokens per second) 1.57.240.636 I slot print_timing: id 0 | task 9626 | eval time = 573.65 ms / 58 tokens ( 10.06 ms per token, 99.36 tokens per second) 1.57.240.637 I slot print_timing: id 0 | task 9626 | total time = 730.11 ms / 690 tokens 1.57.240.638 I slot print_timing: id 0 | task 9626 | graphs reused = 9222 1.57.240.639 I slot print_timing: id 0 | task 9626 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.240.675 I slot release: id 0 | task 9626 | stop processing: n_tokens = 714, truncated = 0 1.57.257.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 117152166 1.57.257.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 1.57.295.242 I slot launch_slot_: id 0 | task 9685 | processing task, is_child = 0 1.57.756.423 I slot print_timing: id 0 | task 9685 | prompt eval time = 107.00 ms / 395 tokens ( 0.27 ms per token, 3691.55 tokens per second) 1.57.756.428 I slot print_timing: id 0 | task 9685 | eval time = 354.16 ms / 37 tokens ( 9.84 ms per token, 101.65 tokens per second) 1.57.756.429 I slot print_timing: id 0 | task 9685 | total time = 461.16 ms / 432 tokens 1.57.756.430 I slot print_timing: id 0 | task 9685 | graphs reused = 9257 1.57.756.431 I slot print_timing: id 0 | task 9685 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.756.460 I slot release: id 0 | task 9685 | stop processing: n_tokens = 456, truncated = 0 1.57.770.680 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 117667950 1.57.770.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.100 MiB) 1.57.793.192 I slot launch_slot_: id 0 | task 9723 | processing task, is_child = 0 1.58.532.342 I slot print_timing: id 0 | task 9723 | prompt eval time = 147.06 ms / 579 tokens ( 0.25 ms per token, 3937.30 tokens per second) 1.58.532.349 I slot print_timing: id 0 | task 9723 | eval time = 592.08 ms / 59 tokens ( 10.21 ms per token, 97.96 tokens per second) 1.58.532.350 I slot print_timing: id 0 | task 9723 | total time = 739.13 ms / 638 tokens 1.58.532.351 I slot print_timing: id 0 | task 9723 | graphs reused = 9314 1.58.532.352 I slot print_timing: id 0 | task 9723 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.532.388 I slot release: id 0 | task 9723 | stop processing: n_tokens = 662, truncated = 0 1.58.551.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 118443879 1.58.551.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 1.58.585.625 I slot launch_slot_: id 0 | task 9783 | processing task, is_child = 0 1.59.333.724 I slot print_timing: id 0 | task 9783 | prompt eval time = 169.50 ms / 689 tokens ( 0.25 ms per token, 4064.85 tokens per second) 1.59.333.730 I slot print_timing: id 0 | task 9783 | eval time = 578.58 ms / 59 tokens ( 9.98 ms per token, 100.25 tokens per second) 1.59.333.731 I slot print_timing: id 0 | task 9783 | total time = 748.08 ms / 748 tokens 1.59.333.732 I slot print_timing: id 0 | task 9783 | graphs reused = 9370 1.59.333.732 I slot print_timing: id 0 | task 9783 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.333.770 I slot release: id 0 | task 9783 | stop processing: n_tokens = 772, truncated = 0 1.59.364.645 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 119245261 1.59.364.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 1.59.368.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.59.405.445 I slot launch_slot_: id 0 | task 9843 | processing task, is_child = 0 2.00.241.770 I slot print_timing: id 0 | task 9843 | prompt eval time = 183.32 ms / 752 tokens ( 0.24 ms per token, 4102.07 tokens per second) 2.00.241.775 I slot print_timing: id 0 | task 9843 | eval time = 652.99 ms / 66 tokens ( 10.05 ms per token, 99.54 tokens per second) 2.00.241.777 I slot print_timing: id 0 | task 9843 | total time = 836.31 ms / 818 tokens 2.00.241.777 I slot print_timing: id 0 | task 9843 | graphs reused = 9434 2.00.241.778 I slot print_timing: id 0 | task 9843 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.241.818 I slot release: id 0 | task 9843 | stop processing: n_tokens = 842, truncated = 0 2.00.268.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 120153309 2.00.268.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 2.00.303.931 I slot launch_slot_: id 0 | task 9910 | processing task, is_child = 0 2.01.103.659 I slot print_timing: id 0 | task 9910 | prompt eval time = 147.12 ms / 582 tokens ( 0.25 ms per token, 3956.09 tokens per second) 2.01.103.665 I slot print_timing: id 0 | task 9910 | eval time = 652.60 ms / 67 tokens ( 9.89 ms per token, 101.13 tokens per second) 2.01.103.666 I slot print_timing: id 0 | task 9910 | total time = 799.71 ms / 649 tokens 2.01.103.666 I slot print_timing: id 0 | task 9910 | graphs reused = 9499 2.01.103.667 I slot print_timing: id 0 | task 9910 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.103.703 I slot release: id 0 | task 9910 | stop processing: n_tokens = 673, truncated = 0 2.01.108.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 121015193 2.01.109.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.01.140.829 I slot launch_slot_: id 0 | task 9978 | processing task, is_child = 0 2.04.306.026 I slot print_timing: id 0 | task 9978 | n_gen = 305, tg = 101.32 t/s, tg_3s = 101.65 t/s 2.07.308.762 I slot print_timing: id 0 | task 9978 | n_gen = 605, tg = 100.61 t/s, tg_3s = 99.91 t/s 2.10.312.619 I slot print_timing: id 0 | task 9978 | n_gen = 903, tg = 100.14 t/s, tg_3s = 99.21 t/s 2.11.537.274 I slot print_timing: id 0 | task 9978 | prompt eval time = 164.80 ms / 656 tokens ( 0.25 ms per token, 3980.53 tokens per second) 2.11.537.279 I slot print_timing: id 0 | task 9978 | eval time = 10231.63 ms / 1024 tokens ( 10.00 ms per token, 99.98 tokens per second) 2.11.537.280 I slot print_timing: id 0 | task 9978 | total time = 10396.43 ms / 1680 tokens 2.11.537.281 I slot print_timing: id 0 | task 9978 | graphs reused = 10517 2.11.537.282 I slot print_timing: id 0 | task 9978 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.537.319 I slot release: id 0 | task 9978 | stop processing: n_tokens = 1704, truncated = 0 2.11.566.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1704, t_last = 131448810 2.11.566.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 2.11.573.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.728 MiB) 2.11.580.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.11.649.807 I slot launch_slot_: id 0 | task 11003 | processing task, is_child = 0 2.12.103.111 I slot print_timing: id 0 | task 11003 | prompt eval time = 153.78 ms / 613 tokens ( 0.25 ms per token, 3986.27 tokens per second) 2.12.103.117 I slot print_timing: id 0 | task 11003 | eval time = 299.51 ms / 31 tokens ( 9.98 ms per token, 100.16 tokens per second) 2.12.103.118 I slot print_timing: id 0 | task 11003 | total time = 453.28 ms / 644 tokens 2.12.103.119 I slot print_timing: id 0 | task 11003 | graphs reused = 10546 2.12.103.120 I slot print_timing: id 0 | task 11003 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.103.157 I slot release: id 0 | task 11003 | stop processing: n_tokens = 668, truncated = 0 2.12.127.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 132014648 2.12.127.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 2.12.158.028 I slot launch_slot_: id 0 | task 11035 | processing task, is_child = 0 2.13.293.111 I slot print_timing: id 0 | task 11035 | prompt eval time = 184.25 ms / 766 tokens ( 0.24 ms per token, 4157.28 tokens per second) 2.13.293.118 I slot print_timing: id 0 | task 11035 | eval time = 950.81 ms / 97 tokens ( 9.90 ms per token, 100.97 tokens per second) 2.13.293.119 I slot print_timing: id 0 | task 11035 | total time = 1135.07 ms / 863 tokens 2.13.293.120 I slot print_timing: id 0 | task 11035 | graphs reused = 10641 2.13.293.121 I slot print_timing: id 0 | task 11035 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.293.166 I slot release: id 0 | task 11035 | stop processing: n_tokens = 887, truncated = 0 2.13.315.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 133204656 2.13.315.506 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.13.355.302 I slot launch_slot_: id 0 | task 11133 | processing task, is_child = 0 2.14.151.853 I slot print_timing: id 0 | task 11133 | prompt eval time = 200.97 ms / 846 tokens ( 0.24 ms per token, 4209.54 tokens per second) 2.14.151.859 I slot print_timing: id 0 | task 11133 | eval time = 595.56 ms / 61 tokens ( 9.93 ms per token, 100.75 tokens per second) 2.14.151.860 I slot print_timing: id 0 | task 11133 | total time = 796.53 ms / 907 tokens 2.14.151.861 I slot print_timing: id 0 | task 11133 | graphs reused = 10700 2.14.151.861 I slot print_timing: id 0 | task 11133 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.151.908 I slot release: id 0 | task 11133 | stop processing: n_tokens = 931, truncated = 0 2.14.175.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 134063399 2.14.175.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.14.180.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 2.14.219.008 I slot launch_slot_: id 0 | task 11195 | processing task, is_child = 0 2.15.135.565 I slot print_timing: id 0 | task 11195 | prompt eval time = 164.94 ms / 650 tokens ( 0.25 ms per token, 3940.85 tokens per second) 2.15.135.573 I slot print_timing: id 0 | task 11195 | eval time = 751.60 ms / 77 tokens ( 9.89 ms per token, 101.12 tokens per second) 2.15.135.574 I slot print_timing: id 0 | task 11195 | total time = 916.54 ms / 727 tokens 2.15.135.576 I slot print_timing: id 0 | task 11195 | graphs reused = 10775 2.15.135.577 I slot print_timing: id 0 | task 11195 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.135.619 I slot release: id 0 | task 11195 | stop processing: n_tokens = 751, truncated = 0 2.15.157.814 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 135047110 2.15.157.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.15.193.862 I slot launch_slot_: id 0 | task 11273 | processing task, is_child = 0 2.15.893.237 I slot print_timing: id 0 | task 11273 | prompt eval time = 176.65 ms / 717 tokens ( 0.25 ms per token, 4058.83 tokens per second) 2.15.893.243 I slot print_timing: id 0 | task 11273 | eval time = 522.71 ms / 53 tokens ( 10.05 ms per token, 99.48 tokens per second) 2.15.893.244 I slot print_timing: id 0 | task 11273 | total time = 699.36 ms / 770 tokens 2.15.893.246 I slot print_timing: id 0 | task 11273 | graphs reused = 10825 2.15.893.247 I slot print_timing: id 0 | task 11273 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.893.287 I slot release: id 0 | task 11273 | stop processing: n_tokens = 794, truncated = 0 2.15.912.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 135804778 2.15.912.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.259 MiB) 2.15.946.713 I slot launch_slot_: id 0 | task 11327 | processing task, is_child = 0 2.16.643.231 I slot print_timing: id 0 | task 11327 | prompt eval time = 121.73 ms / 494 tokens ( 0.25 ms per token, 4058.19 tokens per second) 2.16.643.237 I slot print_timing: id 0 | task 11327 | eval time = 574.77 ms / 59 tokens ( 9.91 ms per token, 100.91 tokens per second) 2.16.643.238 I slot print_timing: id 0 | task 11327 | total time = 696.50 ms / 553 tokens 2.16.643.239 I slot print_timing: id 0 | task 11327 | graphs reused = 10882 2.16.643.239 I slot print_timing: id 0 | task 11327 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.643.273 I slot release: id 0 | task 11327 | stop processing: n_tokens = 577, truncated = 0 2.16.665.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 136554763 2.16.665.152 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.16.669.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.16.698.656 I slot launch_slot_: id 0 | task 11387 | processing task, is_child = 0 2.17.370.757 I slot print_timing: id 0 | task 11387 | prompt eval time = 147.09 ms / 579 tokens ( 0.25 ms per token, 3936.23 tokens per second) 2.17.370.764 I slot print_timing: id 0 | task 11387 | eval time = 524.99 ms / 54 tokens ( 9.91 ms per token, 100.95 tokens per second) 2.17.370.765 I slot print_timing: id 0 | task 11387 | total time = 672.09 ms / 633 tokens 2.17.370.766 I slot print_timing: id 0 | task 11387 | graphs reused = 10934 2.17.370.767 I slot print_timing: id 0 | task 11387 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.370.809 I slot release: id 0 | task 11387 | stop processing: n_tokens = 657, truncated = 0 2.17.398.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 137282300 2.17.398.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 2.17.425.837 I slot launch_slot_: id 0 | task 11442 | processing task, is_child = 0 2.18.378.451 I slot print_timing: id 0 | task 11442 | prompt eval time = 227.99 ms / 919 tokens ( 0.25 ms per token, 4030.95 tokens per second) 2.18.378.458 I slot print_timing: id 0 | task 11442 | eval time = 724.61 ms / 73 tokens ( 10.06 ms per token, 99.36 tokens per second) 2.18.378.459 I slot print_timing: id 0 | task 11442 | total time = 952.60 ms / 992 tokens 2.18.378.460 I slot print_timing: id 0 | task 11442 | graphs reused = 11005 2.18.378.461 I slot print_timing: id 0 | task 11442 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.378.511 I slot release: id 0 | task 11442 | stop processing: n_tokens = 1016, truncated = 0 2.18.409.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 138290002 2.18.409.217 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 2.18.414.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 2.18.453.963 I slot launch_slot_: id 0 | task 11516 | processing task, is_child = 0 2.19.042.822 I slot print_timing: id 0 | task 11516 | prompt eval time = 209.29 ms / 865 tokens ( 0.24 ms per token, 4132.94 tokens per second) 2.19.042.828 I slot print_timing: id 0 | task 11516 | eval time = 379.55 ms / 39 tokens ( 9.99 ms per token, 100.12 tokens per second) 2.19.042.829 I slot print_timing: id 0 | task 11516 | total time = 588.84 ms / 904 tokens 2.19.042.830 I slot print_timing: id 0 | task 11516 | graphs reused = 11042 2.19.042.831 I slot print_timing: id 0 | task 11516 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.042.878 I slot release: id 0 | task 11516 | stop processing: n_tokens = 928, truncated = 0 2.19.069.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 138954368 2.19.069.348 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 2.19.104.356 I slot launch_slot_: id 0 | task 11556 | processing task, is_child = 0 2.22.216.554 I slot print_timing: id 0 | task 11556 | n_gen = 307, tg = 101.83 t/s, tg_3s = 102.17 t/s 2.25.221.180 I slot print_timing: id 0 | task 11556 | n_gen = 611, tg = 101.51 t/s, tg_3s = 101.18 t/s 2.28.227.537 I slot print_timing: id 0 | task 11556 | n_gen = 911, tg = 100.93 t/s, tg_3s = 99.79 t/s 2.29.375.895 I slot print_timing: id 0 | task 11556 | prompt eval time = 107.29 ms / 408 tokens ( 0.26 ms per token, 3802.67 tokens per second) 2.29.375.900 I slot print_timing: id 0 | task 11556 | eval time = 10164.23 ms / 1024 tokens ( 9.94 ms per token, 100.65 tokens per second) 2.29.375.901 I slot print_timing: id 0 | task 11556 | total time = 10271.52 ms / 1432 tokens 2.29.375.902 I slot print_timing: id 0 | task 11556 | graphs reused = 12060 2.29.375.903 I slot print_timing: id 0 | task 11556 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.375.938 I slot release: id 0 | task 11556 | stop processing: n_tokens = 1456, truncated = 0 2.29.402.155 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1456, t_last = 149287429 2.29.402.261 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 2.29.409.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.29.414.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 2.29.481.684 I slot launch_slot_: id 0 | task 12581 | processing task, is_child = 0 2.30.139.655 I slot print_timing: id 0 | task 12581 | prompt eval time = 88.03 ms / 338 tokens ( 0.26 ms per token, 3839.43 tokens per second) 2.30.139.660 I slot print_timing: id 0 | task 12581 | eval time = 569.92 ms / 59 tokens ( 9.83 ms per token, 101.77 tokens per second) 2.30.139.661 I slot print_timing: id 0 | task 12581 | total time = 657.95 ms / 397 tokens 2.30.139.662 I slot print_timing: id 0 | task 12581 | graphs reused = 12117 2.30.139.663 I slot print_timing: id 0 | task 12581 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.139.691 I slot release: id 0 | task 12581 | stop processing: n_tokens = 423, truncated = 0 2.30.161.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 150051181 2.30.175.504 I slot launch_slot_: id 0 | task 12641 | processing task, is_child = 0 2.33.265.717 I slot print_timing: id 0 | task 12641 | n_gen = 306, tg = 101.64 t/s, tg_3s = 101.97 t/s 2.36.273.168 I slot print_timing: id 0 | task 12641 | n_gen = 611, tg = 101.53 t/s, tg_3s = 101.41 t/s 2.39.278.816 I slot print_timing: id 0 | task 12641 | n_gen = 911, tg = 100.96 t/s, tg_3s = 99.81 t/s 2.40.415.508 I slot print_timing: id 0 | task 12641 | prompt eval time = 89.43 ms / 363 tokens ( 0.25 ms per token, 4059.22 tokens per second) 2.40.415.514 I slot print_timing: id 0 | task 12641 | eval time = 10150.56 ms / 1024 tokens ( 9.92 ms per token, 100.78 tokens per second) 2.40.415.515 I slot print_timing: id 0 | task 12641 | total time = 10239.99 ms / 1387 tokens 2.40.415.516 I slot print_timing: id 0 | task 12641 | graphs reused = 13135 2.40.415.517 I slot print_timing: id 0 | task 12641 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.415.544 I slot release: id 0 | task 12641 | stop processing: n_tokens = 1413, truncated = 0 2.40.432.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 160327035 2.40.432.439 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 2.40.437.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 2.40.495.214 I slot launch_slot_: id 0 | task 13666 | processing task, is_child = 0 2.41.590.825 I slot print_timing: id 0 | task 13666 | prompt eval time = 79.99 ms / 317 tokens ( 0.25 ms per token, 3963.19 tokens per second) 2.41.590.831 I slot print_timing: id 0 | task 13666 | eval time = 1015.61 ms / 105 tokens ( 9.77 ms per token, 102.40 tokens per second) 2.41.590.832 I slot print_timing: id 0 | task 13666 | total time = 1095.60 ms / 422 tokens 2.41.590.833 I slot print_timing: id 0 | task 13666 | graphs reused = 13238 2.41.590.834 I slot print_timing: id 0 | task 13666 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.590.861 I slot release: id 0 | task 13666 | stop processing: n_tokens = 448, truncated = 0 2.41.616.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 161502352 2.41.616.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 2.41.642.879 I slot launch_slot_: id 0 | task 13772 | processing task, is_child = 0 2.44.751.709 I slot print_timing: id 0 | task 13772 | n_gen = 307, tg = 101.93 t/s, tg_3s = 102.27 t/s 2.44.898.861 I slot print_timing: id 0 | task 13772 | prompt eval time = 106.82 ms / 389 tokens ( 0.27 ms per token, 3641.67 tokens per second) 2.44.898.866 I slot print_timing: id 0 | task 13772 | eval time = 3149.15 ms / 322 tokens ( 9.81 ms per token, 101.93 tokens per second) 2.44.898.867 I slot print_timing: id 0 | task 13772 | total time = 3255.97 ms / 711 tokens 2.44.898.868 I slot print_timing: id 0 | task 13772 | graphs reused = 13557 2.44.898.869 I slot print_timing: id 0 | task 13772 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.898.899 I slot release: id 0 | task 13772 | stop processing: n_tokens = 735, truncated = 0 2.44.925.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 164810389 2.44.925.761 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.788 MiB) 2.44.955.312 I slot launch_slot_: id 0 | task 14095 | processing task, is_child = 0 2.45.330.988 I slot print_timing: id 0 | task 14095 | prompt eval time = 79.36 ms / 300 tokens ( 0.26 ms per token, 3780.43 tokens per second) 2.45.330.993 I slot print_timing: id 0 | task 14095 | eval time = 296.30 ms / 31 tokens ( 9.88 ms per token, 101.25 tokens per second) 2.45.330.994 I slot print_timing: id 0 | task 14095 | total time = 375.66 ms / 331 tokens 2.45.330.995 I slot print_timing: id 0 | task 14095 | graphs reused = 13586 2.45.330.996 I slot print_timing: id 0 | task 14095 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.331.021 I slot release: id 0 | task 14095 | stop processing: n_tokens = 355, truncated = 0 2.45.347.045 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 165242512 2.45.361.341 I slot launch_slot_: id 0 | task 14127 | processing task, is_child = 0 2.45.891.690 I slot print_timing: id 0 | task 14127 | prompt eval time = 88.27 ms / 341 tokens ( 0.26 ms per token, 3863.10 tokens per second) 2.45.891.696 I slot print_timing: id 0 | task 14127 | eval time = 442.06 ms / 46 tokens ( 9.82 ms per token, 101.79 tokens per second) 2.45.891.697 I slot print_timing: id 0 | task 14127 | total time = 530.34 ms / 387 tokens 2.45.891.697 I slot print_timing: id 0 | task 14127 | graphs reused = 13630 2.45.891.698 I slot print_timing: id 0 | task 14127 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.891.726 I slot release: id 0 | task 14127 | stop processing: n_tokens = 411, truncated = 0 2.45.913.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 165803216 2.45.913.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.759 MiB) 2.45.935.367 I slot launch_slot_: id 0 | task 14174 | processing task, is_child = 0 2.47.380.796 I slot print_timing: id 0 | task 14174 | prompt eval time = 80.59 ms / 332 tokens ( 0.24 ms per token, 4119.41 tokens per second) 2.47.380.801 I slot print_timing: id 0 | task 14174 | eval time = 1364.82 ms / 141 tokens ( 9.75 ms per token, 102.58 tokens per second) 2.47.380.802 I slot print_timing: id 0 | task 14174 | total time = 1445.41 ms / 473 tokens 2.47.380.803 I slot print_timing: id 0 | task 14174 | graphs reused = 13769 2.47.380.804 I slot print_timing: id 0 | task 14174 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.380.831 I slot release: id 0 | task 14174 | stop processing: n_tokens = 497, truncated = 0 2.47.404.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 497, t_last = 167292322 2.47.404.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 2.47.430.338 I slot launch_slot_: id 0 | task 14316 | processing task, is_child = 0 2.48.682.245 I slot print_timing: id 0 | task 14316 | prompt eval time = 71.24 ms / 269 tokens ( 0.26 ms per token, 3776.07 tokens per second) 2.48.682.251 I slot print_timing: id 0 | task 14316 | eval time = 1180.65 ms / 122 tokens ( 9.76 ms per token, 102.49 tokens per second) 2.48.682.252 I slot print_timing: id 0 | task 14316 | total time = 1251.89 ms / 391 tokens 2.48.682.253 I slot print_timing: id 0 | task 14316 | graphs reused = 13889 2.48.682.253 I slot print_timing: id 0 | task 14316 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.682.279 I slot release: id 0 | task 14316 | stop processing: n_tokens = 415, truncated = 0 2.48.705.226 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 168593769 2.48.719.785 I slot launch_slot_: id 0 | task 14439 | processing task, is_child = 0 2.49.270.060 I slot print_timing: id 0 | task 14439 | prompt eval time = 88.14 ms / 341 tokens ( 0.26 ms per token, 3868.98 tokens per second) 2.49.270.066 I slot print_timing: id 0 | task 14439 | eval time = 462.12 ms / 48 tokens ( 9.83 ms per token, 101.70 tokens per second) 2.49.270.067 I slot print_timing: id 0 | task 14439 | total time = 550.26 ms / 389 tokens 2.49.270.068 I slot print_timing: id 0 | task 14439 | graphs reused = 13935 2.49.270.069 I slot print_timing: id 0 | task 14439 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.270.099 I slot release: id 0 | task 14439 | stop processing: n_tokens = 413, truncated = 0 2.49.297.301 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 169181590 2.49.297.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.49.320.202 I slot launch_slot_: id 0 | task 14488 | processing task, is_child = 0 2.49.963.181 I slot print_timing: id 0 | task 14488 | prompt eval time = 88.72 ms / 343 tokens ( 0.26 ms per token, 3866.10 tokens per second) 2.49.963.186 I slot print_timing: id 0 | task 14488 | eval time = 554.24 ms / 56 tokens ( 10.08 ms per token, 99.23 tokens per second) 2.49.963.187 I slot print_timing: id 0 | task 14488 | total time = 642.96 ms / 399 tokens 2.49.963.188 I slot print_timing: id 0 | task 14488 | graphs reused = 13989 2.49.963.189 I slot print_timing: id 0 | task 14488 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.963.215 I slot release: id 0 | task 14488 | stop processing: n_tokens = 423, truncated = 0 2.49.979.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 423, t_last = 169874706 2.49.994.750 I slot launch_slot_: id 0 | task 14545 | processing task, is_child = 0 2.53.087.534 I slot print_timing: id 0 | task 14545 | n_gen = 307, tg = 101.87 t/s, tg_3s = 102.21 t/s 2.56.094.593 I slot print_timing: id 0 | task 14545 | n_gen = 612, tg = 101.65 t/s, tg_3s = 101.43 t/s 2.56.953.970 I slot print_timing: id 0 | task 14545 | prompt eval time = 89.01 ms / 347 tokens ( 0.26 ms per token, 3898.48 tokens per second) 2.56.953.976 I slot print_timing: id 0 | task 14545 | eval time = 6870.19 ms / 698 tokens ( 9.86 ms per token, 101.45 tokens per second) 2.56.953.977 I slot print_timing: id 0 | task 14545 | total time = 6959.20 ms / 1045 tokens 2.56.953.978 I slot print_timing: id 0 | task 14545 | graphs reused = 14682 2.56.953.979 I slot print_timing: id 0 | task 14545 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.954.010 I slot release: id 0 | task 14545 | stop processing: n_tokens = 1069, truncated = 0 2.56.958.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1069, t_last = 176865501 2.56.958.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 2.56.964.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 2.57.008.069 I slot launch_slot_: id 0 | task 15244 | processing task, is_child = 0 3.00.097.192 I slot print_timing: id 0 | task 15244 | n_gen = 308, tg = 102.04 t/s, tg_3s = 102.37 t/s 3.01.311.201 I slot print_timing: id 0 | task 15244 | prompt eval time = 80.51 ms / 332 tokens ( 0.24 ms per token, 4123.87 tokens per second) 3.01.311.207 I slot print_timing: id 0 | task 15244 | eval time = 4222.61 ms / 431 tokens ( 9.82 ms per token, 101.83 tokens per second) 3.01.311.208 I slot print_timing: id 0 | task 15244 | total time = 4303.12 ms / 763 tokens 3.01.311.208 I slot print_timing: id 0 | task 15244 | graphs reused = 15109 3.01.311.209 I slot print_timing: id 0 | task 15244 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.311.239 I slot release: id 0 | task 15244 | stop processing: n_tokens = 787, truncated = 0 3.01.325.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 787, t_last = 181222729 3.01.325.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 3.01.358.745 I slot launch_slot_: id 0 | task 15676 | processing task, is_child = 0 3.02.425.318 I slot print_timing: id 0 | task 15676 | prompt eval time = 80.41 ms / 332 tokens ( 0.24 ms per token, 4128.99 tokens per second) 3.02.425.324 I slot print_timing: id 0 | task 15676 | eval time = 986.15 ms / 102 tokens ( 9.76 ms per token, 102.42 tokens per second) 3.02.425.325 I slot print_timing: id 0 | task 15676 | total time = 1066.56 ms / 434 tokens 3.02.425.326 I slot print_timing: id 0 | task 15676 | graphs reused = 15209 3.02.425.326 I slot print_timing: id 0 | task 15676 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.425.355 I slot release: id 0 | task 15676 | stop processing: n_tokens = 458, truncated = 0 3.02.453.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 182336846 3.02.453.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 3.02.476.015 I slot launch_slot_: id 0 | task 15779 | processing task, is_child = 0 3.03.249.747 I slot print_timing: id 0 | task 15779 | prompt eval time = 88.47 ms / 354 tokens ( 0.25 ms per token, 4001.13 tokens per second) 3.03.249.754 I slot print_timing: id 0 | task 15779 | eval time = 685.24 ms / 71 tokens ( 9.79 ms per token, 102.15 tokens per second) 3.03.249.755 I slot print_timing: id 0 | task 15779 | total time = 773.72 ms / 425 tokens 3.03.249.756 I slot print_timing: id 0 | task 15779 | graphs reused = 15278 3.03.249.757 I slot print_timing: id 0 | task 15779 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.249.790 I slot release: id 0 | task 15779 | stop processing: n_tokens = 449, truncated = 0 3.03.271.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 183161280 3.03.271.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 3.03.294.539 I slot launch_slot_: id 0 | task 15851 | processing task, is_child = 0 3.04.693.372 I slot print_timing: id 0 | task 15851 | prompt eval time = 88.46 ms / 354 tokens ( 0.25 ms per token, 4001.81 tokens per second) 3.04.693.378 I slot print_timing: id 0 | task 15851 | eval time = 1310.36 ms / 135 tokens ( 9.78 ms per token, 102.26 tokens per second) 3.04.693.379 I slot print_timing: id 0 | task 15851 | total time = 1398.82 ms / 489 tokens 3.04.693.380 I slot print_timing: id 0 | task 15851 | graphs reused = 15410 3.04.693.381 I slot print_timing: id 0 | task 15851 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.693.411 I slot release: id 0 | task 15851 | stop processing: n_tokens = 513, truncated = 0 3.04.721.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 184604902 3.04.721.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 3.04.745.081 I slot launch_slot_: id 0 | task 15987 | processing task, is_child = 0 3.05.421.378 I slot print_timing: id 0 | task 15987 | prompt eval time = 87.98 ms / 339 tokens ( 0.26 ms per token, 3853.06 tokens per second) 3.05.421.383 I slot print_timing: id 0 | task 15987 | eval time = 588.30 ms / 61 tokens ( 9.80 ms per token, 101.99 tokens per second) 3.05.421.384 I slot print_timing: id 0 | task 15987 | total time = 676.28 ms / 400 tokens 3.05.421.385 I slot print_timing: id 0 | task 15987 | graphs reused = 15469 3.05.421.386 I slot print_timing: id 0 | task 15987 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.421.413 I slot release: id 0 | task 15987 | stop processing: n_tokens = 424, truncated = 0 3.05.439.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 185332903 3.05.453.776 I slot launch_slot_: id 0 | task 16049 | processing task, is_child = 0 3.08.551.388 I slot print_timing: id 0 | task 16049 | n_gen = 308, tg = 102.03 t/s, tg_3s = 102.36 t/s 3.11.559.797 I slot print_timing: id 0 | task 16049 | n_gen = 613, tg = 101.70 t/s, tg_3s = 101.38 t/s 3.14.563.161 I slot print_timing: id 0 | task 16049 | n_gen = 913, tg = 101.10 t/s, tg_3s = 99.89 t/s 3.15.679.961 I slot print_timing: id 0 | task 16049 | prompt eval time = 88.54 ms / 351 tokens ( 0.25 ms per token, 3964.27 tokens per second) 3.15.679.967 I slot print_timing: id 0 | task 16049 | eval time = 10137.63 ms / 1024 tokens ( 9.91 ms per token, 100.91 tokens per second) 3.15.679.968 I slot print_timing: id 0 | task 16049 | total time = 10226.17 ms / 1375 tokens 3.15.679.969 I slot print_timing: id 0 | task 16049 | graphs reused = 16487 3.15.679.969 I slot print_timing: id 0 | task 16049 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.679.999 I slot release: id 0 | task 16049 | stop processing: n_tokens = 1399, truncated = 0 3.15.694.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1399, t_last = 195591490 3.15.694.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 3.15.703.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 3.15.757.775 I slot launch_slot_: id 0 | task 17074 | processing task, is_child = 0 3.17.292.425 I slot print_timing: id 0 | task 17074 | prompt eval time = 80.35 ms / 325 tokens ( 0.25 ms per token, 4044.80 tokens per second) 3.17.292.431 I slot print_timing: id 0 | task 17074 | eval time = 1454.28 ms / 150 tokens ( 9.76 ms per token, 102.46 tokens per second) 3.17.292.432 I slot print_timing: id 0 | task 17074 | total time = 1534.63 ms / 475 tokens 3.17.292.433 I slot print_timing: id 0 | task 17074 | graphs reused = 16635 3.17.292.435 I slot print_timing: id 0 | task 17074 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.292.462 I slot release: id 0 | task 17074 | stop processing: n_tokens = 499, truncated = 0 3.17.312.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 197203953 3.17.312.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.759 MiB) 3.17.335.979 I slot launch_slot_: id 0 | task 17225 | processing task, is_child = 0 3.17.968.195 I slot print_timing: id 0 | task 17225 | prompt eval time = 79.77 ms / 308 tokens ( 0.26 ms per token, 3861.34 tokens per second) 3.17.968.201 I slot print_timing: id 0 | task 17225 | eval time = 552.43 ms / 56 tokens ( 10.04 ms per token, 99.56 tokens per second) 3.17.968.203 I slot print_timing: id 0 | task 17225 | total time = 632.20 ms / 364 tokens 3.17.968.204 I slot print_timing: id 0 | task 17225 | graphs reused = 16689 3.17.968.205 I slot print_timing: id 0 | task 17225 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.968.234 I slot release: id 0 | task 17225 | stop processing: n_tokens = 388, truncated = 0 3.17.986.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 197879725 3.18.000.335 I slot launch_slot_: id 0 | task 17282 | processing task, is_child = 0 3.21.094.697 I slot print_timing: id 0 | task 17282 | n_gen = 306, tg = 101.47 t/s, tg_3s = 101.80 t/s 3.21.889.334 I slot print_timing: id 0 | task 17282 | prompt eval time = 88.44 ms / 349 tokens ( 0.25 ms per token, 3946.31 tokens per second) 3.21.889.340 I slot print_timing: id 0 | task 17282 | eval time = 3800.54 ms / 387 tokens ( 9.85 ms per token, 101.56 tokens per second) 3.21.889.341 I slot print_timing: id 0 | task 17282 | total time = 3888.98 ms / 736 tokens 3.21.889.341 I slot print_timing: id 0 | task 17282 | graphs reused = 17073 3.21.889.342 I slot print_timing: id 0 | task 17282 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.889.372 I slot release: id 0 | task 17282 | stop processing: n_tokens = 760, truncated = 0 3.21.915.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 201800862 3.21.915.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 3.21.921.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 3.21.957.399 I slot launch_slot_: id 0 | task 17670 | processing task, is_child = 0 3.23.452.938 I slot print_timing: id 0 | task 17670 | prompt eval time = 88.31 ms / 371 tokens ( 0.24 ms per token, 4200.97 tokens per second) 3.23.452.944 I slot print_timing: id 0 | task 17670 | eval time = 1407.21 ms / 144 tokens ( 9.84 ms per token, 101.62 tokens per second) 3.23.452.945 I slot print_timing: id 0 | task 17670 | total time = 1495.52 ms / 515 tokens 3.23.452.946 I slot print_timing: id 0 | task 17670 | graphs reused = 17214 3.23.452.946 I slot print_timing: id 0 | task 17670 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.452.978 I slot release: id 0 | task 17670 | stop processing: n_tokens = 544, truncated = 0 3.23.482.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 544, t_last = 203364468 3.23.500.822 I slot launch_slot_: id 0 | task 17815 | processing task, is_child = 0 3.24.808.531 I slot print_timing: id 0 | task 17815 | prompt eval time = 79.40 ms / 303 tokens ( 0.26 ms per token, 3816.12 tokens per second) 3.24.808.536 I slot print_timing: id 0 | task 17815 | eval time = 1228.29 ms / 127 tokens ( 9.75 ms per token, 102.58 tokens per second) 3.24.808.537 I slot print_timing: id 0 | task 17815 | total time = 1307.69 ms / 430 tokens 3.24.808.538 I slot print_timing: id 0 | task 17815 | graphs reused = 17339 3.24.808.539 I slot print_timing: id 0 | task 17815 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.808.566 I slot release: id 0 | task 17815 | stop processing: n_tokens = 454, truncated = 0 3.24.836.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 204720057 3.24.836.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.074 MiB) 3.24.861.620 I slot launch_slot_: id 0 | task 17943 | processing task, is_child = 0 3.25.916.723 I slot print_timing: id 0 | task 17943 | prompt eval time = 79.65 ms / 312 tokens ( 0.26 ms per token, 3916.99 tokens per second) 3.25.916.728 I slot print_timing: id 0 | task 17943 | eval time = 975.43 ms / 101 tokens ( 9.75 ms per token, 102.52 tokens per second) 3.25.916.730 I slot print_timing: id 0 | task 17943 | total time = 1055.09 ms / 413 tokens 3.25.916.730 I slot print_timing: id 0 | task 17943 | graphs reused = 17438 3.25.916.731 I slot print_timing: id 0 | task 17943 | graph reallocs = 0 / 0 (same size) / (changed size) 3.25.916.756 I slot release: id 0 | task 17943 | stop processing: n_tokens = 437, truncated = 0 3.25.944.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 205828247 3.25.959.819 I slot launch_slot_: id 0 | task 18045 | processing task, is_child = 0 3.29.047.329 I slot print_timing: id 0 | task 18045 | n_gen = 308, tg = 102.07 t/s, tg_3s = 102.40 t/s 3.32.050.124 I slot print_timing: id 0 | task 18045 | n_gen = 613, tg = 101.82 t/s, tg_3s = 101.57 t/s 3.35.060.008 I slot print_timing: id 0 | task 18045 | n_gen = 915, tg = 101.33 t/s, tg_3s = 100.34 t/s 3.36.158.808 I slot print_timing: id 0 | task 18045 | prompt eval time = 79.73 ms / 311 tokens ( 0.26 ms per token, 3900.42 tokens per second) 3.36.158.813 I slot print_timing: id 0 | task 18045 | eval time = 10119.24 ms / 1024 tokens ( 9.89 ms per token, 101.09 tokens per second) 3.36.158.814 I slot print_timing: id 0 | task 18045 | total time = 10198.97 ms / 1335 tokens 3.36.158.815 I slot print_timing: id 0 | task 18045 | graphs reused = 18456 3.36.158.816 I slot print_timing: id 0 | task 18045 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.158.842 I slot release: id 0 | task 18045 | stop processing: n_tokens = 1359, truncated = 0 3.36.181.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1359, t_last = 216070333 3.36.181.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.858 MiB) 3.36.239.645 I slot launch_slot_: id 0 | task 19070 | processing task, is_child = 0 3.36.695.378 I slot print_timing: id 0 | task 19070 | prompt eval time = 80.70 ms / 331 tokens ( 0.24 ms per token, 4101.66 tokens per second) 3.36.695.384 I slot print_timing: id 0 | task 19070 | eval time = 375.02 ms / 39 tokens ( 9.87 ms per token, 101.33 tokens per second) 3.36.695.385 I slot print_timing: id 0 | task 19070 | total time = 455.72 ms / 370 tokens 3.36.695.386 I slot print_timing: id 0 | task 19070 | graphs reused = 18493 3.36.695.387 I slot print_timing: id 0 | task 19070 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.695.415 I slot release: id 0 | task 19070 | stop processing: n_tokens = 394, truncated = 0 3.36.715.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 394, t_last = 216606905 3.36.715.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 3.36.737.777 I slot launch_slot_: id 0 | task 19110 | processing task, is_child = 0 3.38.628.864 I slot print_timing: id 0 | task 19110 | prompt eval time = 80.67 ms / 335 tokens ( 0.24 ms per token, 4152.62 tokens per second) 3.38.628.870 I slot print_timing: id 0 | task 19110 | eval time = 1810.40 ms / 186 tokens ( 9.79 ms per token, 102.19 tokens per second) 3.38.628.872 I slot print_timing: id 0 | task 19110 | total time = 1891.07 ms / 521 tokens 3.38.628.872 I slot print_timing: id 0 | task 19110 | graphs reused = 18676 3.38.628.873 I slot print_timing: id 0 | task 19110 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.628.902 I slot release: id 0 | task 19110 | stop processing: n_tokens = 545, truncated = 0 3.38.647.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 218540392 3.38.647.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 3.38.671.433 I slot launch_slot_: id 0 | task 19297 | processing task, is_child = 0 3.40.020.058 I slot print_timing: id 0 | task 19297 | prompt eval time = 80.56 ms / 331 tokens ( 0.24 ms per token, 4108.59 tokens per second) 3.40.020.063 I slot print_timing: id 0 | task 19297 | eval time = 1268.04 ms / 131 tokens ( 9.75 ms per token, 102.52 tokens per second) 3.40.020.064 I slot print_timing: id 0 | task 19297 | total time = 1348.61 ms / 462 tokens 3.40.020.065 I slot print_timing: id 0 | task 19297 | graphs reused = 18805 3.40.020.066 I slot print_timing: id 0 | task 19297 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.020.096 I slot release: id 0 | task 19297 | stop processing: n_tokens = 486, truncated = 0 3.40.036.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 219931586 3.40.036.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 3.40.040.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 3.40.063.447 I slot launch_slot_: id 0 | task 19429 | processing task, is_child = 0 3.41.835.703 I slot print_timing: id 0 | task 19429 | prompt eval time = 80.75 ms / 328 tokens ( 0.25 ms per token, 4061.82 tokens per second) 3.41.835.709 I slot print_timing: id 0 | task 19429 | eval time = 1691.49 ms / 174 tokens ( 9.78 ms per token, 102.28 tokens per second) 3.41.835.710 I slot print_timing: id 0 | task 19429 | total time = 1772.24 ms / 502 tokens 3.41.835.711 I slot print_timing: id 0 | task 19429 | graphs reused = 18976 3.41.835.712 I slot print_timing: id 0 | task 19429 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.835.738 I slot release: id 0 | task 19429 | stop processing: n_tokens = 526, truncated = 0 3.41.850.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 526, t_last = 221747229 3.41.850.922 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 3.41.873.882 I slot launch_slot_: id 0 | task 19604 | processing task, is_child = 0 3.42.882.555 I slot print_timing: id 0 | task 19604 | prompt eval time = 80.52 ms / 331 tokens ( 0.24 ms per token, 4110.78 tokens per second) 3.42.882.561 I slot print_timing: id 0 | task 19604 | eval time = 928.14 ms / 96 tokens ( 9.77 ms per token, 102.36 tokens per second) 3.42.882.562 I slot print_timing: id 0 | task 19604 | total time = 1008.66 ms / 427 tokens 3.42.882.563 I slot print_timing: id 0 | task 19604 | graphs reused = 19070 3.42.882.563 I slot print_timing: id 0 | task 19604 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.882.591 I slot release: id 0 | task 19604 | stop processing: n_tokens = 451, truncated = 0 3.42.901.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 451, t_last = 222794081 3.42.917.646 I slot launch_slot_: id 0 | task 19701 | processing task, is_child = 0 3.43.525.951 I slot print_timing: id 0 | task 19701 | prompt eval time = 88.58 ms / 348 tokens ( 0.25 ms per token, 3928.52 tokens per second) 3.43.525.956 I slot print_timing: id 0 | task 19701 | eval time = 519.71 ms / 54 tokens ( 9.81 ms per token, 101.98 tokens per second) 3.43.525.958 I slot print_timing: id 0 | task 19701 | total time = 608.29 ms / 402 tokens 3.43.525.958 I slot print_timing: id 0 | task 19701 | graphs reused = 19122 3.43.525.959 I slot print_timing: id 0 | task 19701 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.525.989 I slot release: id 0 | task 19701 | stop processing: n_tokens = 426, truncated = 0 3.43.544.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 223437480 3.43.544.763 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 3.43.566.872 I slot launch_slot_: id 0 | task 19756 | processing task, is_child = 0 3.44.157.043 I slot print_timing: id 0 | task 19756 | prompt eval time = 80.58 ms / 332 tokens ( 0.24 ms per token, 4120.28 tokens per second) 3.44.157.049 I slot print_timing: id 0 | task 19756 | eval time = 509.58 ms / 53 tokens ( 9.80 ms per token, 102.05 tokens per second) 3.44.157.050 I slot print_timing: id 0 | task 19756 | total time = 590.16 ms / 385 tokens 3.44.157.051 I slot print_timing: id 0 | task 19756 | graphs reused = 19173 3.44.157.052 I slot print_timing: id 0 | task 19756 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.157.079 I slot release: id 0 | task 19756 | stop processing: n_tokens = 411, truncated = 0 3.44.182.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 224068570 3.44.182.218 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 3.44.200.819 I slot launch_slot_: id 0 | task 19810 | processing task, is_child = 0 3.45.459.131 I slot print_timing: id 0 | task 19810 | prompt eval time = 88.16 ms / 339 tokens ( 0.26 ms per token, 3845.50 tokens per second) 3.45.459.137 I slot print_timing: id 0 | task 19810 | eval time = 1170.14 ms / 121 tokens ( 9.75 ms per token, 102.55 tokens per second) 3.45.459.138 I slot print_timing: id 0 | task 19810 | total time = 1258.30 ms / 460 tokens 3.45.459.139 I slot print_timing: id 0 | task 19810 | graphs reused = 19292 3.45.459.139 I slot print_timing: id 0 | task 19810 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.459.165 I slot release: id 0 | task 19810 | stop processing: n_tokens = 484, truncated = 0 3.45.474.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 484, t_last = 225370656 3.45.474.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 3.45.495.738 I slot launch_slot_: id 0 | task 19932 | processing task, is_child = 0 3.46.219.910 I slot print_timing: id 0 | task 19932 | prompt eval time = 88.34 ms / 343 tokens ( 0.26 ms per token, 3882.51 tokens per second) 3.46.219.916 I slot print_timing: id 0 | task 19932 | eval time = 635.81 ms / 66 tokens ( 9.78 ms per token, 102.23 tokens per second) 3.46.219.917 I slot print_timing: id 0 | task 19932 | total time = 724.16 ms / 409 tokens 3.46.219.918 I slot print_timing: id 0 | task 19932 | graphs reused = 19356 3.46.219.919 I slot print_timing: id 0 | task 19932 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.219.946 I slot release: id 0 | task 19932 | stop processing: n_tokens = 433, truncated = 0 3.46.243.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 226131436 3.46.243.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 3.46.264.796 I slot launch_slot_: id 0 | task 19999 | processing task, is_child = 0 3.49.363.187 I slot print_timing: id 0 | task 19999 | n_gen = 308, tg = 102.01 t/s, tg_3s = 102.34 t/s 3.49.932.053 I slot print_timing: id 0 | task 19999 | prompt eval time = 88.88 ms / 360 tokens ( 0.25 ms per token, 4050.36 tokens per second) 3.49.932.058 I slot print_timing: id 0 | task 19999 | eval time = 3578.36 ms / 366 tokens ( 9.80 ms per token, 102.00 tokens per second) 3.49.932.059 I slot print_timing: id 0 | task 19999 | total time = 3667.24 ms / 726 tokens 3.49.932.060 I slot print_timing: id 0 | task 19999 | graphs reused = 19719 3.49.932.061 I slot print_timing: id 0 | task 19999 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.932.090 I slot release: id 0 | task 19999 | stop processing: n_tokens = 750, truncated = 0 3.49.947.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 229843580 3.49.947.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 3.49.978.270 I slot launch_slot_: id 0 | task 20366 | processing task, is_child = 0 3.50.508.472 I slot print_timing: id 0 | task 20366 | prompt eval time = 88.26 ms / 341 tokens ( 0.26 ms per token, 3863.63 tokens per second) 3.50.508.478 I slot print_timing: id 0 | task 20366 | eval time = 441.93 ms / 46 tokens ( 9.82 ms per token, 101.83 tokens per second) 3.50.508.479 I slot print_timing: id 0 | task 20366 | total time = 530.19 ms / 387 tokens 3.50.508.480 I slot print_timing: id 0 | task 20366 | graphs reused = 19763 3.50.508.481 I slot print_timing: id 0 | task 20366 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.508.509 I slot release: id 0 | task 20366 | stop processing: n_tokens = 411, truncated = 0 3.50.527.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 230419999 3.50.527.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 3.50.551.684 I slot launch_slot_: id 0 | task 20413 | processing task, is_child = 0 3.53.649.176 I slot print_timing: id 0 | task 20413 | n_gen = 308, tg = 102.03 t/s, tg_3s = 102.37 t/s 3.54.395.419 I slot print_timing: id 0 | task 20413 | prompt eval time = 88.68 ms / 358 tokens ( 0.25 ms per token, 4036.90 tokens per second) 3.54.395.424 I slot print_timing: id 0 | task 20413 | eval time = 3755.03 ms / 384 tokens ( 9.80 ms per token, 102.00 tokens per second) 3.54.395.425 I slot print_timing: id 0 | task 20413 | total time = 3843.72 ms / 742 tokens 3.54.395.427 I slot print_timing: id 0 | task 20413 | graphs reused = 20144 3.54.395.428 I slot print_timing: id 0 | task 20413 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.395.456 I slot release: id 0 | task 20413 | stop processing: n_tokens = 766, truncated = 0 3.54.415.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 766, t_last = 234306947 3.54.415.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 3.54.420.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 3.54.452.251 I slot launch_slot_: id 0 | task 20798 | processing task, is_child = 0 3.55.226.751 I slot print_timing: id 0 | task 20798 | prompt eval time = 88.94 ms / 358 tokens ( 0.25 ms per token, 4025.32 tokens per second) 3.55.226.757 I slot print_timing: id 0 | task 20798 | eval time = 685.55 ms / 67 tokens ( 10.39 ms per token, 96.27 tokens per second) 3.55.226.758 I slot print_timing: id 0 | task 20798 | total time = 774.48 ms / 425 tokens 3.55.226.758 I slot print_timing: id 0 | task 20798 | graphs reused = 20209 3.55.226.759 I slot print_timing: id 0 | task 20798 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.226.789 I slot release: id 0 | task 20798 | stop processing: n_tokens = 452, truncated = 0 3.55.253.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 235138280 3.55.253.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 3.55.275.523 I slot launch_slot_: id 0 | task 20866 | processing task, is_child = 0 3.55.825.843 I slot print_timing: id 0 | task 20866 | prompt eval time = 107.77 ms / 387 tokens ( 0.28 ms per token, 3591.15 tokens per second) 3.55.825.848 I slot print_timing: id 0 | task 20866 | eval time = 442.53 ms / 46 tokens ( 9.83 ms per token, 101.69 tokens per second) 3.55.825.850 I slot print_timing: id 0 | task 20866 | total time = 550.30 ms / 433 tokens 3.55.825.850 I slot print_timing: id 0 | task 20866 | graphs reused = 20253 3.55.825.851 I slot print_timing: id 0 | task 20866 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.825.882 I slot release: id 0 | task 20866 | stop processing: n_tokens = 457, truncated = 0 3.55.849.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 235737373 3.55.849.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 3.55.870.405 I slot launch_slot_: id 0 | task 20913 | processing task, is_child = 0 3.56.557.306 I slot print_timing: id 0 | task 20913 | prompt eval time = 80.62 ms / 333 tokens ( 0.24 ms per token, 4130.44 tokens per second) 3.56.557.312 I slot print_timing: id 0 | task 20913 | eval time = 606.26 ms / 61 tokens ( 10.10 ms per token, 98.97 tokens per second) 3.56.557.313 I slot print_timing: id 0 | task 20913 | total time = 686.88 ms / 394 tokens 3.56.557.314 I slot print_timing: id 0 | task 20913 | graphs reused = 20312 3.56.557.315 I slot print_timing: id 0 | task 20913 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.557.342 I slot release: id 0 | task 20913 | stop processing: n_tokens = 418, truncated = 0