$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-IQ4_XS.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.091.745 I srv llama_server: initializing ... 0.00.091.751 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.091.875 I srv init_listene: The UI is disabled 0.00.091.878 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.091.967 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) 0.00.104.443 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-IQ4_XS.gguf' 0.02.057.612 I cmn init: llama threadpool init, n_threads = 8 0.02.126.602 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.131.423 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.131.440 I srv llama_server: model loaded 0.02.131.443 I srv llama_server: listening on http://127.0.0.1:8089 0.02.543.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.544.147 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.187.692 I slot print_timing: id 0 | task 0 | prompt eval time = 93.23 ms / 368 tokens ( 0.25 ms per token, 3947.27 tokens per second) 0.03.187.697 I slot print_timing: id 0 | task 0 | eval time = 550.30 ms / 61 tokens ( 9.17 ms per token, 109.03 tokens per second) 0.03.187.699 I slot print_timing: id 0 | task 0 | total time = 643.53 ms / 429 tokens 0.03.187.704 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.03.187.705 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.187.737 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.03.212.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 3097963 0.03.227.920 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.03.692.123 I slot print_timing: id 0 | task 62 | prompt eval time = 71.97 ms / 292 tokens ( 0.25 ms per token, 4057.13 tokens per second) 0.03.692.128 I slot print_timing: id 0 | task 62 | eval time = 392.22 ms / 44 tokens ( 9.12 ms per token, 109.63 tokens per second) 0.03.692.129 I slot print_timing: id 0 | task 62 | total time = 464.19 ms / 336 tokens 0.03.692.130 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.03.692.131 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.692.157 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.03.711.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 3602382 0.03.724.312 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.04.204.796 I slot print_timing: id 0 | task 107 | prompt eval time = 79.15 ms / 338 tokens ( 0.23 ms per token, 4270.48 tokens per second) 0.04.204.801 I slot print_timing: id 0 | task 107 | eval time = 401.32 ms / 45 tokens ( 9.12 ms per token, 109.64 tokens per second) 0.04.204.802 I slot print_timing: id 0 | task 107 | total time = 480.47 ms / 383 tokens 0.04.204.803 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.04.204.804 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.204.832 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.04.226.236 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 4115057 0.04.240.630 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.04.730.609 I slot print_timing: id 0 | task 153 | prompt eval time = 79.30 ms / 371 tokens ( 0.21 ms per token, 4678.55 tokens per second) 0.04.730.615 I slot print_timing: id 0 | task 153 | eval time = 410.67 ms / 46 tokens ( 9.13 ms per token, 109.58 tokens per second) 0.04.730.616 I slot print_timing: id 0 | task 153 | total time = 489.96 ms / 417 tokens 0.04.730.617 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.04.730.618 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.730.653 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.04.753.132 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 0.04.768.534 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.05.393.823 I slot print_timing: id 0 | task 200 | prompt eval time = 79.08 ms / 345 tokens ( 0.23 ms per token, 4362.56 tokens per second) 0.05.393.828 I slot print_timing: id 0 | task 200 | eval time = 546.19 ms / 61 tokens ( 9.10 ms per token, 109.85 tokens per second) 0.05.393.830 I slot print_timing: id 0 | task 200 | total time = 625.27 ms / 406 tokens 0.05.393.831 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.05.393.832 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.393.860 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.05.409.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 5304085 0.05.424.471 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.06.077.922 I slot print_timing: id 0 | task 262 | prompt eval time = 79.61 ms / 351 tokens ( 0.23 ms per token, 4409.27 tokens per second) 0.06.077.928 I slot print_timing: id 0 | task 262 | eval time = 573.83 ms / 64 tokens ( 9.11 ms per token, 109.79 tokens per second) 0.06.077.929 I slot print_timing: id 0 | task 262 | total time = 653.43 ms / 415 tokens 0.06.077.930 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.06.077.931 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.077.958 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.06.102.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 5988184 0.06.117.786 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.06.743.519 I slot print_timing: id 0 | task 327 | prompt eval time = 96.46 ms / 395 tokens ( 0.24 ms per token, 4094.92 tokens per second) 0.06.743.525 I slot print_timing: id 0 | task 327 | eval time = 529.26 ms / 58 tokens ( 9.29 ms per token, 107.70 tokens per second) 0.06.743.526 I slot print_timing: id 0 | task 327 | total time = 625.72 ms / 453 tokens 0.06.743.527 I slot print_timing: id 0 | task 327 | graphs reused = 366 0.06.743.528 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.743.558 I slot release: id 0 | task 327 | stop processing: n_tokens = 477, truncated = 0 0.06.758.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 6653783 0.06.775.346 I slot launch_slot_: id 0 | task 386 | processing task, is_child = 0 0.07.526.913 I slot print_timing: id 0 | task 386 | prompt eval time = 98.37 ms / 446 tokens ( 0.22 ms per token, 4533.99 tokens per second) 0.07.526.920 I slot print_timing: id 0 | task 386 | eval time = 653.18 ms / 72 tokens ( 9.20 ms per token, 108.70 tokens per second) 0.07.526.921 I slot print_timing: id 0 | task 386 | total time = 751.55 ms / 518 tokens 0.07.526.922 I slot print_timing: id 0 | task 386 | graphs reused = 435 0.07.526.923 I slot print_timing: id 0 | task 386 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.526.960 I slot release: id 0 | task 386 | stop processing: n_tokens = 542, truncated = 0 0.07.531.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 7437185 0.07.553.557 I slot launch_slot_: id 0 | task 459 | processing task, is_child = 0 0.08.090.910 I slot print_timing: id 0 | task 459 | prompt eval time = 72.35 ms / 319 tokens ( 0.23 ms per token, 4408.94 tokens per second) 0.08.090.917 I slot print_timing: id 0 | task 459 | eval time = 464.98 ms / 52 tokens ( 9.12 ms per token, 109.68 tokens per second) 0.08.090.918 I slot print_timing: id 0 | task 459 | total time = 537.34 ms / 371 tokens 0.08.090.919 I slot print_timing: id 0 | task 459 | graphs reused = 485 0.08.090.920 I slot print_timing: id 0 | task 459 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.090.950 I slot release: id 0 | task 459 | stop processing: n_tokens = 395, truncated = 0 0.08.118.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 8001175 0.08.132.171 I slot launch_slot_: id 0 | task 512 | processing task, is_child = 0 0.08.579.473 I slot print_timing: id 0 | task 512 | prompt eval time = 72.59 ms / 336 tokens ( 0.22 ms per token, 4628.86 tokens per second) 0.08.579.479 I slot print_timing: id 0 | task 512 | eval time = 374.70 ms / 42 tokens ( 9.14 ms per token, 109.42 tokens per second) 0.08.579.480 I slot print_timing: id 0 | task 512 | total time = 447.29 ms / 378 tokens 0.08.579.481 I slot print_timing: id 0 | task 512 | graphs reused = 525 0.08.579.482 I slot print_timing: id 0 | task 512 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.579.510 I slot release: id 0 | task 512 | stop processing: n_tokens = 402, truncated = 0 0.08.604.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 8489736 0.08.618.484 I slot launch_slot_: id 0 | task 555 | processing task, is_child = 0 0.09.317.267 I slot print_timing: id 0 | task 555 | prompt eval time = 79.16 ms / 352 tokens ( 0.22 ms per token, 4446.52 tokens per second) 0.09.317.273 I slot print_timing: id 0 | task 555 | eval time = 619.60 ms / 68 tokens ( 9.25 ms per token, 108.13 tokens per second) 0.09.317.275 I slot print_timing: id 0 | task 555 | total time = 698.76 ms / 420 tokens 0.09.317.275 I slot print_timing: id 0 | task 555 | graphs reused = 591 0.09.317.276 I slot print_timing: id 0 | task 555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.317.309 I slot release: id 0 | task 555 | stop processing: n_tokens = 444, truncated = 0 0.09.341.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 9227534 0.09.356.343 I slot launch_slot_: id 0 | task 624 | processing task, is_child = 0 0.09.918.366 I slot print_timing: id 0 | task 624 | prompt eval time = 96.24 ms / 387 tokens ( 0.25 ms per token, 4021.11 tokens per second) 0.09.918.372 I slot print_timing: id 0 | task 624 | eval time = 465.76 ms / 52 tokens ( 9.13 ms per token, 109.50 tokens per second) 0.09.918.374 I slot print_timing: id 0 | task 624 | total time = 562.01 ms / 439 tokens 0.09.918.375 I slot print_timing: id 0 | task 624 | graphs reused = 641 0.09.918.375 I slot print_timing: id 0 | task 624 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.918.411 I slot release: id 0 | task 624 | stop processing: n_tokens = 463, truncated = 0 0.09.946.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 9828636 0.09.962.920 I slot launch_slot_: id 0 | task 677 | processing task, is_child = 0 0.10.615.790 I slot print_timing: id 0 | task 677 | prompt eval time = 79.61 ms / 349 tokens ( 0.23 ms per token, 4383.71 tokens per second) 0.10.615.795 I slot print_timing: id 0 | task 677 | eval time = 573.24 ms / 64 tokens ( 9.10 ms per token, 109.90 tokens per second) 0.10.615.796 I slot print_timing: id 0 | task 677 | total time = 652.85 ms / 413 tokens 0.10.615.797 I slot print_timing: id 0 | task 677 | graphs reused = 703 0.10.615.798 I slot print_timing: id 0 | task 677 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.615.828 I slot release: id 0 | task 677 | stop processing: n_tokens = 437, truncated = 0 0.10.635.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 10526053 0.10.651.166 I slot launch_slot_: id 0 | task 742 | processing task, is_child = 0 0.11.259.942 I slot print_timing: id 0 | task 742 | prompt eval time = 79.17 ms / 352 tokens ( 0.22 ms per token, 4446.41 tokens per second) 0.11.259.947 I slot print_timing: id 0 | task 742 | eval time = 529.60 ms / 57 tokens ( 9.46 ms per token, 105.74 tokens per second) 0.11.259.948 I slot print_timing: id 0 | task 742 | total time = 608.76 ms / 409 tokens 0.11.259.949 I slot print_timing: id 0 | task 742 | graphs reused = 758 0.11.259.950 I slot print_timing: id 0 | task 742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.259.977 I slot release: id 0 | task 742 | stop processing: n_tokens = 433, truncated = 0 0.11.275.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 11170202 0.11.290.439 I slot launch_slot_: id 0 | task 800 | processing task, is_child = 0 0.11.989.140 I slot print_timing: id 0 | task 800 | prompt eval time = 79.20 ms / 347 tokens ( 0.23 ms per token, 4381.20 tokens per second) 0.11.989.145 I slot print_timing: id 0 | task 800 | eval time = 619.48 ms / 68 tokens ( 9.25 ms per token, 108.15 tokens per second) 0.11.989.146 I slot print_timing: id 0 | task 800 | total time = 698.68 ms / 415 tokens 0.11.989.147 I slot print_timing: id 0 | task 800 | graphs reused = 824 0.11.989.148 I slot print_timing: id 0 | task 800 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.989.179 I slot release: id 0 | task 800 | stop processing: n_tokens = 439, truncated = 0 0.12.005.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 11899404 0.12.020.930 I slot launch_slot_: id 0 | task 869 | processing task, is_child = 0 0.12.598.795 I slot print_timing: id 0 | task 869 | prompt eval time = 72.29 ms / 320 tokens ( 0.23 ms per token, 4426.80 tokens per second) 0.12.598.801 I slot print_timing: id 0 | task 869 | eval time = 505.56 ms / 56 tokens ( 9.19 ms per token, 108.79 tokens per second) 0.12.598.802 I slot print_timing: id 0 | task 869 | total time = 577.85 ms / 376 tokens 0.12.598.803 I slot print_timing: id 0 | task 869 | graphs reused = 878 0.12.598.804 I slot print_timing: id 0 | task 869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.598.835 I slot release: id 0 | task 869 | stop processing: n_tokens = 400, truncated = 0 0.12.625.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 12509060 0.12.641.336 I slot launch_slot_: id 0 | task 926 | processing task, is_child = 0 0.13.119.152 I slot print_timing: id 0 | task 926 | prompt eval time = 82.20 ms / 343 tokens ( 0.24 ms per token, 4172.55 tokens per second) 0.13.119.158 I slot print_timing: id 0 | task 926 | eval time = 395.59 ms / 44 tokens ( 9.20 ms per token, 108.70 tokens per second) 0.13.119.159 I slot print_timing: id 0 | task 926 | total time = 477.79 ms / 387 tokens 0.13.119.160 I slot print_timing: id 0 | task 926 | graphs reused = 920 0.13.119.160 I slot print_timing: id 0 | task 926 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.119.189 I slot release: id 0 | task 926 | stop processing: n_tokens = 411, truncated = 0 0.13.135.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 13029414 0.13.149.728 I slot launch_slot_: id 0 | task 971 | processing task, is_child = 0 0.13.616.541 I slot print_timing: id 0 | task 971 | prompt eval time = 72.86 ms / 325 tokens ( 0.22 ms per token, 4460.67 tokens per second) 0.13.616.547 I slot print_timing: id 0 | task 971 | eval time = 393.93 ms / 44 tokens ( 9.16 ms per token, 109.16 tokens per second) 0.13.616.548 I slot print_timing: id 0 | task 971 | total time = 466.79 ms / 369 tokens 0.13.616.549 I slot print_timing: id 0 | task 971 | graphs reused = 962 0.13.616.550 I slot print_timing: id 0 | task 971 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.616.590 I slot release: id 0 | task 971 | stop processing: n_tokens = 393, truncated = 0 0.13.621.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 13526815 0.13.635.955 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.14.093.122 I slot print_timing: id 0 | task 1016 | prompt eval time = 72.76 ms / 323 tokens ( 0.23 ms per token, 4439.13 tokens per second) 0.14.093.127 I slot print_timing: id 0 | task 1016 | eval time = 384.38 ms / 43 tokens ( 9.15 ms per token, 109.27 tokens per second) 0.14.093.129 I slot print_timing: id 0 | task 1016 | total time = 457.15 ms / 366 tokens 0.14.093.129 I slot print_timing: id 0 | task 1016 | graphs reused = 1003 0.14.093.130 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.093.158 I slot release: id 0 | task 1016 | stop processing: n_tokens = 390, truncated = 0 0.14.119.201 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 14003383 0.14.132.923 I slot launch_slot_: id 0 | task 1060 | processing task, is_child = 0 0.14.858.295 I slot print_timing: id 0 | task 1060 | prompt eval time = 79.58 ms / 359 tokens ( 0.22 ms per token, 4511.07 tokens per second) 0.14.858.301 I slot print_timing: id 0 | task 1060 | eval time = 645.77 ms / 69 tokens ( 9.50 ms per token, 105.30 tokens per second) 0.14.858.302 I slot print_timing: id 0 | task 1060 | total time = 725.36 ms / 428 tokens 0.14.858.303 I slot print_timing: id 0 | task 1060 | graphs reused = 1070 0.14.858.304 I slot print_timing: id 0 | task 1060 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.858.331 I slot release: id 0 | task 1060 | stop processing: n_tokens = 452, truncated = 0 0.14.872.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 14768557 0.14.888.173 I slot launch_slot_: id 0 | task 1130 | processing task, is_child = 0 0.15.526.414 I slot print_timing: id 0 | task 1130 | prompt eval time = 73.10 ms / 334 tokens ( 0.22 ms per token, 4569.27 tokens per second) 0.15.526.420 I slot print_timing: id 0 | task 1130 | eval time = 565.13 ms / 63 tokens ( 9.11 ms per token, 109.71 tokens per second) 0.15.526.421 I slot print_timing: id 0 | task 1130 | total time = 638.23 ms / 397 tokens 0.15.526.422 I slot print_timing: id 0 | task 1130 | graphs reused = 1131 0.15.526.423 I slot print_timing: id 0 | task 1130 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.526.453 I slot release: id 0 | task 1130 | stop processing: n_tokens = 421, truncated = 0 0.15.540.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 15436678 0.15.555.939 I slot launch_slot_: id 0 | task 1194 | processing task, is_child = 0 0.16.291.271 I slot print_timing: id 0 | task 1194 | prompt eval time = 79.69 ms / 382 tokens ( 0.21 ms per token, 4793.45 tokens per second) 0.16.291.277 I slot print_timing: id 0 | task 1194 | eval time = 655.62 ms / 73 tokens ( 9.11 ms per token, 109.82 tokens per second) 0.16.291.278 I slot print_timing: id 0 | task 1194 | total time = 735.31 ms / 455 tokens 0.16.291.279 I slot print_timing: id 0 | task 1194 | graphs reused = 1202 0.16.291.280 I slot print_timing: id 0 | task 1194 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.291.311 I slot release: id 0 | task 1194 | stop processing: n_tokens = 479, truncated = 0 0.16.307.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 16201536 0.16.323.584 I slot launch_slot_: id 0 | task 1268 | processing task, is_child = 0 0.16.986.333 I slot print_timing: id 0 | task 1268 | prompt eval time = 79.85 ms / 368 tokens ( 0.22 ms per token, 4608.41 tokens per second) 0.16.986.338 I slot print_timing: id 0 | task 1268 | eval time = 582.88 ms / 65 tokens ( 9.11 ms per token, 109.80 tokens per second) 0.16.986.340 I slot print_timing: id 0 | task 1268 | total time = 662.73 ms / 433 tokens 0.16.986.341 I slot print_timing: id 0 | task 1268 | graphs reused = 1265 0.16.986.342 I slot print_timing: id 0 | task 1268 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.986.371 I slot release: id 0 | task 1268 | stop processing: n_tokens = 457, truncated = 0 0.17.013.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 16896596 0.17.029.595 I slot launch_slot_: id 0 | task 1334 | processing task, is_child = 0 0.17.892.428 I slot print_timing: id 0 | task 1334 | prompt eval time = 79.72 ms / 382 tokens ( 0.21 ms per token, 4792.07 tokens per second) 0.17.892.433 I slot print_timing: id 0 | task 1334 | eval time = 783.10 ms / 87 tokens ( 9.11 ms per token, 109.82 tokens per second) 0.17.892.435 I slot print_timing: id 0 | task 1334 | total time = 862.82 ms / 469 tokens 0.17.892.436 I slot print_timing: id 0 | task 1334 | graphs reused = 1350 0.17.892.437 I slot print_timing: id 0 | task 1334 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.892.469 I slot release: id 0 | task 1334 | stop processing: n_tokens = 493, truncated = 0 0.17.907.545 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 17802694 0.17.924.667 I slot launch_slot_: id 0 | task 1422 | processing task, is_child = 0 0.18.604.160 I slot print_timing: id 0 | task 1422 | prompt eval time = 97.25 ms / 410 tokens ( 0.24 ms per token, 4215.85 tokens per second) 0.18.604.166 I slot print_timing: id 0 | task 1422 | eval time = 582.23 ms / 65 tokens ( 9.10 ms per token, 109.92 tokens per second) 0.18.604.167 I slot print_timing: id 0 | task 1422 | total time = 679.48 ms / 475 tokens 0.18.604.168 I slot print_timing: id 0 | task 1422 | graphs reused = 1413 0.18.604.169 I slot print_timing: id 0 | task 1422 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.604.200 I slot release: id 0 | task 1422 | stop processing: n_tokens = 499, truncated = 0 0.18.621.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 18514425 0.18.638.534 I slot launch_slot_: id 0 | task 1488 | processing task, is_child = 0 0.19.302.174 I slot print_timing: id 0 | task 1488 | prompt eval time = 80.35 ms / 367 tokens ( 0.22 ms per token, 4567.57 tokens per second) 0.19.302.179 I slot print_timing: id 0 | task 1488 | eval time = 583.28 ms / 65 tokens ( 9.11 ms per token, 109.73 tokens per second) 0.19.302.180 I slot print_timing: id 0 | task 1488 | total time = 663.62 ms / 432 tokens 0.19.302.181 I slot print_timing: id 0 | task 1488 | graphs reused = 1476 0.19.302.182 I slot print_timing: id 0 | task 1488 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.302.210 I slot release: id 0 | task 1488 | stop processing: n_tokens = 458, truncated = 0 0.19.306.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 19212435 0.19.321.828 I slot launch_slot_: id 0 | task 1554 | processing task, is_child = 0 0.19.878.522 I slot print_timing: id 0 | task 1554 | prompt eval time = 73.04 ms / 326 tokens ( 0.22 ms per token, 4463.55 tokens per second) 0.19.878.530 I slot print_timing: id 0 | task 1554 | eval time = 483.64 ms / 54 tokens ( 9.13 ms per token, 109.59 tokens per second) 0.19.878.531 I slot print_timing: id 0 | task 1554 | total time = 556.68 ms / 380 tokens 0.19.878.534 I slot print_timing: id 0 | task 1554 | graphs reused = 1528 0.19.878.535 I slot print_timing: id 0 | task 1554 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.878.567 I slot release: id 0 | task 1554 | stop processing: n_tokens = 404, truncated = 0 0.19.905.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 19788792 0.19.920.008 I slot launch_slot_: id 0 | task 1609 | processing task, is_child = 0 0.20.574.538 I slot print_timing: id 0 | task 1609 | prompt eval time = 80.12 ms / 351 tokens ( 0.23 ms per token, 4380.76 tokens per second) 0.20.574.544 I slot print_timing: id 0 | task 1609 | eval time = 574.39 ms / 64 tokens ( 9.12 ms per token, 109.68 tokens per second) 0.20.574.546 I slot print_timing: id 0 | task 1609 | total time = 654.52 ms / 415 tokens 0.20.574.547 I slot print_timing: id 0 | task 1609 | graphs reused = 1590 0.20.574.547 I slot print_timing: id 0 | task 1609 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.574.577 I slot release: id 0 | task 1609 | stop processing: n_tokens = 441, truncated = 0 0.20.593.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 20484802 0.20.609.216 I slot launch_slot_: id 0 | task 1674 | processing task, is_child = 0 0.21.398.456 I slot print_timing: id 0 | task 1674 | prompt eval time = 79.34 ms / 379 tokens ( 0.21 ms per token, 4776.67 tokens per second) 0.21.398.461 I slot print_timing: id 0 | task 1674 | eval time = 709.88 ms / 78 tokens ( 9.22 ms per token, 108.47 tokens per second) 0.21.398.463 I slot print_timing: id 0 | task 1674 | total time = 789.22 ms / 457 tokens 0.21.398.464 I slot print_timing: id 0 | task 1674 | graphs reused = 1666 0.21.398.465 I slot print_timing: id 0 | task 1674 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.398.496 I slot release: id 0 | task 1674 | stop processing: n_tokens = 481, truncated = 0 0.21.422.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 21308721 0.21.438.887 I slot launch_slot_: id 0 | task 1753 | processing task, is_child = 0 0.22.161.646 I slot print_timing: id 0 | task 1753 | prompt eval time = 79.62 ms / 356 tokens ( 0.22 ms per token, 4471.41 tokens per second) 0.22.161.652 I slot print_timing: id 0 | task 1753 | eval time = 643.13 ms / 70 tokens ( 9.32 ms per token, 107.29 tokens per second) 0.22.161.653 I slot print_timing: id 0 | task 1753 | total time = 722.74 ms / 426 tokens 0.22.161.654 I slot print_timing: id 0 | task 1753 | graphs reused = 1734 0.22.161.655 I slot print_timing: id 0 | task 1753 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.161.684 I slot release: id 0 | task 1753 | stop processing: n_tokens = 450, truncated = 0 0.22.183.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 22071909 0.22.199.100 I slot launch_slot_: id 0 | task 1824 | processing task, is_child = 0 0.22.819.085 I slot print_timing: id 0 | task 1824 | prompt eval time = 73.12 ms / 331 tokens ( 0.22 ms per token, 4526.74 tokens per second) 0.22.819.091 I slot print_timing: id 0 | task 1824 | eval time = 546.85 ms / 61 tokens ( 9.11 ms per token, 109.72 tokens per second) 0.22.819.092 I slot print_timing: id 0 | task 1824 | total time = 619.97 ms / 392 tokens 0.22.819.093 I slot print_timing: id 0 | task 1824 | graphs reused = 1793 0.22.819.093 I slot print_timing: id 0 | task 1824 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.819.122 I slot release: id 0 | task 1824 | stop processing: n_tokens = 416, truncated = 0 0.22.838.810 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 22729347 0.22.853.116 I slot launch_slot_: id 0 | task 1886 | processing task, is_child = 0 0.23.229.077 I slot print_timing: id 0 | task 1886 | prompt eval time = 73.44 ms / 334 tokens ( 0.22 ms per token, 4547.99 tokens per second) 0.23.229.083 I slot print_timing: id 0 | task 1886 | eval time = 302.51 ms / 34 tokens ( 9.17 ms per token, 109.09 tokens per second) 0.23.229.084 I slot print_timing: id 0 | task 1886 | total time = 375.95 ms / 368 tokens 0.23.229.085 I slot print_timing: id 0 | task 1886 | graphs reused = 1825 0.23.229.086 I slot print_timing: id 0 | task 1886 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.229.113 I slot release: id 0 | task 1886 | stop processing: n_tokens = 392, truncated = 0 0.23.243.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 23139338 0.23.257.787 I slot launch_slot_: id 0 | task 1921 | processing task, is_child = 0 0.23.946.900 I slot print_timing: id 0 | task 1921 | prompt eval time = 79.87 ms / 362 tokens ( 0.22 ms per token, 4532.19 tokens per second) 0.23.946.905 I slot print_timing: id 0 | task 1921 | eval time = 609.23 ms / 68 tokens ( 9.09 ms per token, 109.98 tokens per second) 0.23.946.906 I slot print_timing: id 0 | task 1921 | total time = 689.10 ms / 430 tokens 0.23.946.907 I slot print_timing: id 0 | task 1921 | graphs reused = 1891 0.23.946.908 I slot print_timing: id 0 | task 1921 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.946.937 I slot release: id 0 | task 1921 | stop processing: n_tokens = 454, truncated = 0 0.23.972.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 23857162 0.23.988.097 I slot launch_slot_: id 0 | task 1990 | processing task, is_child = 0 0.24.524.386 I slot print_timing: id 0 | task 1990 | prompt eval time = 79.78 ms / 384 tokens ( 0.21 ms per token, 4813.06 tokens per second) 0.24.524.391 I slot print_timing: id 0 | task 1990 | eval time = 456.49 ms / 51 tokens ( 9.13 ms per token, 109.53 tokens per second) 0.24.524.392 I slot print_timing: id 0 | task 1990 | total time = 536.27 ms / 435 tokens 0.24.524.393 I slot print_timing: id 0 | task 1990 | graphs reused = 1940 0.24.524.394 I slot print_timing: id 0 | task 1990 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.524.423 I slot release: id 0 | task 1990 | stop processing: n_tokens = 459, truncated = 0 0.24.550.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 24434648 0.24.566.052 I slot launch_slot_: id 0 | task 2042 | processing task, is_child = 0 0.25.130.657 I slot print_timing: id 0 | task 2042 | prompt eval time = 73.02 ms / 325 tokens ( 0.22 ms per token, 4451.08 tokens per second) 0.25.130.663 I slot print_timing: id 0 | task 2042 | eval time = 491.57 ms / 55 tokens ( 9.10 ms per token, 109.85 tokens per second) 0.25.130.665 I slot print_timing: id 0 | task 2042 | total time = 564.59 ms / 380 tokens 0.25.130.665 I slot print_timing: id 0 | task 2042 | graphs reused = 1993 0.25.130.666 I slot print_timing: id 0 | task 2042 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.130.694 I slot release: id 0 | task 2042 | stop processing: n_tokens = 404, truncated = 0 0.25.153.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 25040919 0.25.167.891 I slot launch_slot_: id 0 | task 2098 | processing task, is_child = 0 0.25.793.504 I slot print_timing: id 0 | task 2098 | prompt eval time = 80.10 ms / 366 tokens ( 0.22 ms per token, 4569.29 tokens per second) 0.25.793.510 I slot print_timing: id 0 | task 2098 | eval time = 545.50 ms / 59 tokens ( 9.41 ms per token, 106.33 tokens per second) 0.25.793.511 I slot print_timing: id 0 | task 2098 | total time = 625.60 ms / 425 tokens 0.25.793.511 I slot print_timing: id 0 | task 2098 | graphs reused = 2050 0.25.793.512 I slot print_timing: id 0 | task 2098 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.793.542 I slot release: id 0 | task 2098 | stop processing: n_tokens = 449, truncated = 0 0.25.808.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 25703767 0.25.823.916 I slot launch_slot_: id 0 | task 2158 | processing task, is_child = 0 0.26.216.431 I slot print_timing: id 0 | task 2158 | prompt eval time = 72.06 ms / 295 tokens ( 0.24 ms per token, 4094.04 tokens per second) 0.26.216.436 I slot print_timing: id 0 | task 2158 | eval time = 320.44 ms / 36 tokens ( 9.16 ms per token, 109.22 tokens per second) 0.26.216.437 I slot print_timing: id 0 | task 2158 | total time = 392.50 ms / 331 tokens 0.26.216.438 I slot print_timing: id 0 | task 2158 | graphs reused = 2084 0.26.216.439 I slot print_timing: id 0 | task 2158 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.216.467 I slot release: id 0 | task 2158 | stop processing: n_tokens = 355, truncated = 0 0.26.220.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 26126692 0.26.232.999 I slot launch_slot_: id 0 | task 2195 | processing task, is_child = 0 0.26.752.064 I slot print_timing: id 0 | task 2195 | prompt eval time = 72.32 ms / 307 tokens ( 0.24 ms per token, 4245.14 tokens per second) 0.26.752.070 I slot print_timing: id 0 | task 2195 | eval time = 446.73 ms / 50 tokens ( 9.12 ms per token, 109.69 tokens per second) 0.26.752.071 I slot print_timing: id 0 | task 2195 | total time = 519.05 ms / 357 tokens 0.26.752.071 I slot print_timing: id 0 | task 2195 | graphs reused = 2132 0.26.752.072 I slot print_timing: id 0 | task 2195 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.752.101 I slot release: id 0 | task 2195 | stop processing: n_tokens = 381, truncated = 0 0.26.775.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 26662326 0.26.788.958 I slot launch_slot_: id 0 | task 2246 | processing task, is_child = 0 0.27.199.936 I slot print_timing: id 0 | task 2246 | prompt eval time = 72.36 ms / 319 tokens ( 0.23 ms per token, 4408.21 tokens per second) 0.27.199.942 I slot print_timing: id 0 | task 2246 | eval time = 338.60 ms / 38 tokens ( 9.15 ms per token, 109.27 tokens per second) 0.27.199.943 I slot print_timing: id 0 | task 2246 | total time = 410.96 ms / 357 tokens 0.27.199.944 I slot print_timing: id 0 | task 2246 | graphs reused = 2168 0.27.199.944 I slot print_timing: id 0 | task 2246 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.199.972 I slot release: id 0 | task 2246 | stop processing: n_tokens = 381, truncated = 0 0.27.215.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 27110197 0.27.228.436 I slot launch_slot_: id 0 | task 2285 | processing task, is_child = 0 0.27.774.703 I slot print_timing: id 0 | task 2285 | prompt eval time = 72.40 ms / 315 tokens ( 0.23 ms per token, 4350.65 tokens per second) 0.27.774.708 I slot print_timing: id 0 | task 2285 | eval time = 473.85 ms / 53 tokens ( 9.11 ms per token, 109.74 tokens per second) 0.27.774.709 I slot print_timing: id 0 | task 2285 | total time = 546.25 ms / 368 tokens 0.27.774.710 I slot print_timing: id 0 | task 2285 | graphs reused = 2219 0.27.774.710 I slot print_timing: id 0 | task 2285 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.774.736 I slot release: id 0 | task 2285 | stop processing: n_tokens = 392, truncated = 0 0.27.795.307 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 27684961 0.27.809.042 I slot launch_slot_: id 0 | task 2339 | processing task, is_child = 0 0.28.408.181 I slot print_timing: id 0 | task 2339 | prompt eval time = 80.00 ms / 367 tokens ( 0.22 ms per token, 4587.67 tokens per second) 0.28.408.186 I slot print_timing: id 0 | task 2339 | eval time = 519.13 ms / 58 tokens ( 9.11 ms per token, 109.80 tokens per second) 0.28.408.188 I slot print_timing: id 0 | task 2339 | total time = 599.12 ms / 425 tokens 0.28.408.188 I slot print_timing: id 0 | task 2339 | graphs reused = 2275 0.28.408.189 I slot print_timing: id 0 | task 2339 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.408.218 I slot release: id 0 | task 2339 | stop processing: n_tokens = 449, truncated = 0 0.28.437.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 28318443 0.28.452.616 I slot launch_slot_: id 0 | task 2398 | processing task, is_child = 0 0.29.223.370 I slot print_timing: id 0 | task 2398 | prompt eval time = 109.55 ms / 499 tokens ( 0.22 ms per token, 4555.16 tokens per second) 0.29.223.378 I slot print_timing: id 0 | task 2398 | eval time = 661.19 ms / 70 tokens ( 9.58 ms per token, 104.36 tokens per second) 0.29.223.379 I slot print_timing: id 0 | task 2398 | total time = 770.74 ms / 569 tokens 0.29.223.379 I slot print_timing: id 0 | task 2398 | graphs reused = 2343 0.29.223.380 I slot print_timing: id 0 | task 2398 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.223.414 I slot release: id 0 | task 2398 | stop processing: n_tokens = 593, truncated = 0 0.29.244.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 29133639 0.29.265.047 I slot launch_slot_: id 0 | task 2469 | processing task, is_child = 0 0.29.784.952 I slot print_timing: id 0 | task 2469 | prompt eval time = 72.72 ms / 319 tokens ( 0.23 ms per token, 4386.69 tokens per second) 0.29.784.957 I slot print_timing: id 0 | task 2469 | eval time = 447.17 ms / 50 tokens ( 9.13 ms per token, 109.58 tokens per second) 0.29.784.958 I slot print_timing: id 0 | task 2469 | total time = 519.89 ms / 369 tokens 0.29.784.959 I slot print_timing: id 0 | task 2469 | graphs reused = 2391 0.29.784.960 I slot print_timing: id 0 | task 2469 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.784.988 I slot release: id 0 | task 2469 | stop processing: n_tokens = 393, truncated = 0 0.29.809.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 29695213 0.29.823.310 I slot launch_slot_: id 0 | task 2520 | processing task, is_child = 0 0.30.422.712 I slot print_timing: id 0 | task 2520 | prompt eval time = 79.45 ms / 348 tokens ( 0.23 ms per token, 4379.95 tokens per second) 0.30.422.717 I slot print_timing: id 0 | task 2520 | eval time = 519.93 ms / 58 tokens ( 9.12 ms per token, 109.63 tokens per second) 0.30.422.719 I slot print_timing: id 0 | task 2520 | total time = 599.38 ms / 406 tokens 0.30.422.719 I slot print_timing: id 0 | task 2520 | graphs reused = 2447 0.30.422.720 I slot print_timing: id 0 | task 2520 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.422.750 I slot release: id 0 | task 2520 | stop processing: n_tokens = 430, truncated = 0 0.30.447.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 30332975 0.30.462.820 I slot launch_slot_: id 0 | task 2579 | processing task, is_child = 0 0.31.233.372 I slot print_timing: id 0 | task 2579 | prompt eval time = 97.39 ms / 404 tokens ( 0.24 ms per token, 4148.14 tokens per second) 0.31.233.378 I slot print_timing: id 0 | task 2579 | eval time = 673.14 ms / 75 tokens ( 9.10 ms per token, 109.93 tokens per second) 0.31.233.379 I slot print_timing: id 0 | task 2579 | total time = 770.54 ms / 479 tokens 0.31.233.380 I slot print_timing: id 0 | task 2579 | graphs reused = 2520 0.31.233.380 I slot print_timing: id 0 | task 2579 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.233.410 I slot release: id 0 | task 2579 | stop processing: n_tokens = 503, truncated = 0 0.31.237.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 31143635 0.31.254.923 I slot launch_slot_: id 0 | task 2655 | processing task, is_child = 0 0.31.900.793 I slot print_timing: id 0 | task 2655 | prompt eval time = 96.91 ms / 408 tokens ( 0.24 ms per token, 4210.31 tokens per second) 0.31.900.799 I slot print_timing: id 0 | task 2655 | eval time = 548.95 ms / 60 tokens ( 9.30 ms per token, 107.48 tokens per second) 0.31.900.800 I slot print_timing: id 0 | task 2655 | total time = 645.86 ms / 468 tokens 0.31.900.801 I slot print_timing: id 0 | task 2655 | graphs reused = 2578 0.31.900.802 I slot print_timing: id 0 | task 2655 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.900.835 I slot release: id 0 | task 2655 | stop processing: n_tokens = 494, truncated = 0 0.31.920.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 31811060 0.31.937.166 I slot launch_slot_: id 0 | task 2716 | processing task, is_child = 0 0.32.457.544 I slot print_timing: id 0 | task 2716 | prompt eval time = 73.01 ms / 325 tokens ( 0.22 ms per token, 4451.63 tokens per second) 0.32.457.550 I slot print_timing: id 0 | task 2716 | eval time = 447.36 ms / 49 tokens ( 9.32 ms per token, 107.30 tokens per second) 0.32.457.551 I slot print_timing: id 0 | task 2716 | total time = 520.36 ms / 374 tokens 0.32.457.552 I slot print_timing: id 0 | task 2716 | graphs reused = 2625 0.32.457.553 I slot print_timing: id 0 | task 2716 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.457.581 I slot release: id 0 | task 2716 | stop processing: n_tokens = 402, truncated = 0 0.32.483.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 32367806 0.32.497.857 I slot launch_slot_: id 0 | task 2766 | processing task, is_child = 0 0.33.050.647 I slot print_timing: id 0 | task 2766 | prompt eval time = 79.26 ms / 345 tokens ( 0.23 ms per token, 4352.76 tokens per second) 0.33.050.653 I slot print_timing: id 0 | task 2766 | eval time = 473.52 ms / 53 tokens ( 9.11 ms per token, 109.82 tokens per second) 0.33.050.654 I slot print_timing: id 0 | task 2766 | total time = 552.78 ms / 398 tokens 0.33.050.655 I slot print_timing: id 0 | task 2766 | graphs reused = 2676 0.33.050.656 I slot print_timing: id 0 | task 2766 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.050.684 I slot release: id 0 | task 2766 | stop processing: n_tokens = 422, truncated = 0 0.33.064.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 32960909 0.33.079.644 I slot launch_slot_: id 0 | task 2820 | processing task, is_child = 0 0.33.605.825 I slot print_timing: id 0 | task 2820 | prompt eval time = 79.07 ms / 344 tokens ( 0.23 ms per token, 4350.74 tokens per second) 0.33.605.831 I slot print_timing: id 0 | task 2820 | eval time = 447.10 ms / 50 tokens ( 9.12 ms per token, 109.60 tokens per second) 0.33.605.832 I slot print_timing: id 0 | task 2820 | total time = 526.16 ms / 394 tokens 0.33.605.833 I slot print_timing: id 0 | task 2820 | graphs reused = 2724 0.33.605.834 I slot print_timing: id 0 | task 2820 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.605.863 I slot release: id 0 | task 2820 | stop processing: n_tokens = 418, truncated = 0 0.33.625.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 33516088 0.33.640.226 I slot launch_slot_: id 0 | task 2871 | processing task, is_child = 0 0.34.383.560 I slot print_timing: id 0 | task 2871 | prompt eval time = 79.80 ms / 378 tokens ( 0.21 ms per token, 4736.60 tokens per second) 0.34.383.566 I slot print_timing: id 0 | task 2871 | eval time = 663.52 ms / 74 tokens ( 9.09 ms per token, 110.02 tokens per second) 0.34.383.567 I slot print_timing: id 0 | task 2871 | total time = 743.32 ms / 452 tokens 0.34.383.568 I slot print_timing: id 0 | task 2871 | graphs reused = 2796 0.34.383.568 I slot print_timing: id 0 | task 2871 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.383.598 I slot release: id 0 | task 2871 | stop processing: n_tokens = 476, truncated = 0 0.34.404.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 34293823 0.34.420.903 I slot launch_slot_: id 0 | task 2946 | processing task, is_child = 0 0.35.040.574 I slot print_timing: id 0 | task 2946 | prompt eval time = 73.22 ms / 331 tokens ( 0.22 ms per token, 4520.44 tokens per second) 0.35.040.580 I slot print_timing: id 0 | task 2946 | eval time = 546.43 ms / 61 tokens ( 9.11 ms per token, 109.80 tokens per second) 0.35.040.581 I slot print_timing: id 0 | task 2946 | total time = 619.66 ms / 392 tokens 0.35.040.582 I slot print_timing: id 0 | task 2946 | graphs reused = 2855 0.35.040.582 I slot print_timing: id 0 | task 2946 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.040.609 I slot release: id 0 | task 2946 | stop processing: n_tokens = 416, truncated = 0 0.35.059.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 34950834 0.35.074.671 I slot launch_slot_: id 0 | task 3008 | processing task, is_child = 0 0.35.609.561 I slot print_timing: id 0 | task 3008 | prompt eval time = 96.54 ms / 387 tokens ( 0.25 ms per token, 4008.78 tokens per second) 0.35.609.566 I slot print_timing: id 0 | task 3008 | eval time = 438.34 ms / 49 tokens ( 9.13 ms per token, 109.51 tokens per second) 0.35.609.567 I slot print_timing: id 0 | task 3008 | total time = 534.87 ms / 436 tokens 0.35.609.568 I slot print_timing: id 0 | task 3008 | graphs reused = 2902 0.35.609.569 I slot print_timing: id 0 | task 3008 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.609.598 I slot release: id 0 | task 3008 | stop processing: n_tokens = 460, truncated = 0 0.35.638.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 35519823 0.35.654.605 I slot launch_slot_: id 0 | task 3058 | processing task, is_child = 0 0.36.406.817 I slot print_timing: id 0 | task 3058 | prompt eval time = 79.45 ms / 345 tokens ( 0.23 ms per token, 4342.46 tokens per second) 0.36.406.823 I slot print_timing: id 0 | task 3058 | eval time = 672.75 ms / 75 tokens ( 9.09 ms per token, 110.00 tokens per second) 0.36.406.824 I slot print_timing: id 0 | task 3058 | total time = 752.20 ms / 420 tokens 0.36.406.825 I slot print_timing: id 0 | task 3058 | graphs reused = 2975 0.36.406.826 I slot print_timing: id 0 | task 3058 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.406.855 I slot release: id 0 | task 3058 | stop processing: n_tokens = 444, truncated = 0 0.36.429.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 36317080 0.36.444.790 I slot launch_slot_: id 0 | task 3134 | processing task, is_child = 0 0.37.088.405 I slot print_timing: id 0 | task 3134 | prompt eval time = 79.18 ms / 337 tokens ( 0.23 ms per token, 4256.07 tokens per second) 0.37.088.411 I slot print_timing: id 0 | task 3134 | eval time = 564.42 ms / 61 tokens ( 9.41 ms per token, 106.30 tokens per second) 0.37.088.412 I slot print_timing: id 0 | task 3134 | total time = 643.60 ms / 398 tokens 0.37.088.413 I slot print_timing: id 0 | task 3134 | graphs reused = 3034 0.37.088.414 I slot print_timing: id 0 | task 3134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.088.443 I slot release: id 0 | task 3134 | stop processing: n_tokens = 422, truncated = 0 0.37.114.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 36998668 0.37.129.023 I slot launch_slot_: id 0 | task 3196 | processing task, is_child = 0 0.38.101.531 I slot print_timing: id 0 | task 3196 | prompt eval time = 107.02 ms / 463 tokens ( 0.23 ms per token, 4326.38 tokens per second) 0.38.101.538 I slot print_timing: id 0 | task 3196 | eval time = 865.47 ms / 95 tokens ( 9.21 ms per token, 108.61 tokens per second) 0.38.101.539 I slot print_timing: id 0 | task 3196 | total time = 972.49 ms / 558 tokens 0.38.101.540 I slot print_timing: id 0 | task 3196 | graphs reused = 3126 0.38.101.540 I slot print_timing: id 0 | task 3196 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.101.578 I slot release: id 0 | task 3196 | stop processing: n_tokens = 582, truncated = 0 0.38.126.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 38011803 0.38.145.686 I slot launch_slot_: id 0 | task 3292 | processing task, is_child = 0 0.39.236.091 I slot print_timing: id 0 | task 3292 | prompt eval time = 97.91 ms / 440 tokens ( 0.22 ms per token, 4493.88 tokens per second) 0.39.236.097 I slot print_timing: id 0 | task 3292 | eval time = 992.48 ms / 109 tokens ( 9.19 ms per token, 108.82 tokens per second) 0.39.236.098 I slot print_timing: id 0 | task 3292 | total time = 1090.39 ms / 549 tokens 0.39.236.099 I slot print_timing: id 0 | task 3292 | graphs reused = 3232 0.39.236.100 I slot print_timing: id 0 | task 3292 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.236.131 I slot release: id 0 | task 3292 | stop processing: n_tokens = 573, truncated = 0 0.39.259.504 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 39146357 0.39.279.241 I slot launch_slot_: id 0 | task 3402 | processing task, is_child = 0 0.39.926.148 I slot print_timing: id 0 | task 3402 | prompt eval time = 72.98 ms / 336 tokens ( 0.22 ms per token, 4603.75 tokens per second) 0.39.926.153 I slot print_timing: id 0 | task 3402 | eval time = 573.91 ms / 64 tokens ( 9.11 ms per token, 109.77 tokens per second) 0.39.926.155 I slot print_timing: id 0 | task 3402 | total time = 646.89 ms / 400 tokens 0.39.926.156 I slot print_timing: id 0 | task 3402 | graphs reused = 3294 0.39.926.157 I slot print_timing: id 0 | task 3402 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.926.184 I slot release: id 0 | task 3402 | stop processing: n_tokens = 424, truncated = 0 0.39.954.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 39836409 0.39.969.770 I slot launch_slot_: id 0 | task 3467 | processing task, is_child = 0 0.40.571.594 I slot print_timing: id 0 | task 3467 | prompt eval time = 80.17 ms / 367 tokens ( 0.22 ms per token, 4577.77 tokens per second) 0.40.571.600 I slot print_timing: id 0 | task 3467 | eval time = 521.64 ms / 57 tokens ( 9.31 ms per token, 107.35 tokens per second) 0.40.571.601 I slot print_timing: id 0 | task 3467 | total time = 601.81 ms / 424 tokens 0.40.571.602 I slot print_timing: id 0 | task 3467 | graphs reused = 3349 0.40.571.603 I slot print_timing: id 0 | task 3467 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.571.632 I slot release: id 0 | task 3467 | stop processing: n_tokens = 448, truncated = 0 0.40.590.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 40481857 0.40.605.892 I slot launch_slot_: id 0 | task 3525 | processing task, is_child = 0 0.41.144.210 I slot print_timing: id 0 | task 3525 | prompt eval time = 73.14 ms / 327 tokens ( 0.22 ms per token, 4470.88 tokens per second) 0.41.144.216 I slot print_timing: id 0 | task 3525 | eval time = 465.16 ms / 52 tokens ( 9.12 ms per token, 109.64 tokens per second) 0.41.144.217 I slot print_timing: id 0 | task 3525 | total time = 538.30 ms / 379 tokens 0.41.144.217 I slot print_timing: id 0 | task 3525 | graphs reused = 3399 0.41.144.218 I slot print_timing: id 0 | task 3525 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.144.248 I slot release: id 0 | task 3525 | stop processing: n_tokens = 403, truncated = 0 0.41.167.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 41054473 0.41.182.270 I slot launch_slot_: id 0 | task 3578 | processing task, is_child = 0 0.41.969.226 I slot print_timing: id 0 | task 3578 | prompt eval time = 96.53 ms / 393 tokens ( 0.25 ms per token, 4071.36 tokens per second) 0.41.969.230 I slot print_timing: id 0 | task 3578 | eval time = 690.41 ms / 76 tokens ( 9.21 ms per token, 108.63 tokens per second) 0.41.969.232 I slot print_timing: id 0 | task 3578 | total time = 786.94 ms / 469 tokens 0.41.969.232 I slot print_timing: id 0 | task 3578 | graphs reused = 3473 0.41.969.233 I slot print_timing: id 0 | task 3578 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.969.267 I slot release: id 0 | task 3578 | stop processing: n_tokens = 493, truncated = 0 0.41.988.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 41879492 0.42.005.900 I slot launch_slot_: id 0 | task 3655 | processing task, is_child = 0 0.42.692.507 I slot print_timing: id 0 | task 3655 | prompt eval time = 125.00 ms / 524 tokens ( 0.24 ms per token, 4191.87 tokens per second) 0.42.692.513 I slot print_timing: id 0 | task 3655 | eval time = 561.59 ms / 62 tokens ( 9.21 ms per token, 108.62 tokens per second) 0.42.692.514 I slot print_timing: id 0 | task 3655 | total time = 686.59 ms / 586 tokens 0.42.692.515 I slot print_timing: id 0 | task 3655 | graphs reused = 3533 0.42.692.515 I slot print_timing: id 0 | task 3655 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.692.546 I slot release: id 0 | task 3655 | stop processing: n_tokens = 610, truncated = 0 0.42.709.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 42602771 0.42.729.216 I slot launch_slot_: id 0 | task 3718 | processing task, is_child = 0 0.43.422.506 I slot print_timing: id 0 | task 3718 | prompt eval time = 141.23 ms / 602 tokens ( 0.23 ms per token, 4262.43 tokens per second) 0.43.422.512 I slot print_timing: id 0 | task 3718 | eval time = 552.04 ms / 61 tokens ( 9.20 ms per token, 108.69 tokens per second) 0.43.422.513 I slot print_timing: id 0 | task 3718 | total time = 693.28 ms / 663 tokens 0.43.422.514 I slot print_timing: id 0 | task 3718 | graphs reused = 3592 0.43.422.514 I slot print_timing: id 0 | task 3718 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.422.550 I slot release: id 0 | task 3718 | stop processing: n_tokens = 687, truncated = 0 0.43.451.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 43332775 0.43.474.044 I slot launch_slot_: id 0 | task 3780 | processing task, is_child = 0 0.44.185.452 I slot print_timing: id 0 | task 3780 | prompt eval time = 140.96 ms / 640 tokens ( 0.22 ms per token, 4540.46 tokens per second) 0.44.185.458 I slot print_timing: id 0 | task 3780 | eval time = 570.44 ms / 63 tokens ( 9.20 ms per token, 108.69 tokens per second) 0.44.185.459 I slot print_timing: id 0 | task 3780 | total time = 711.39 ms / 703 tokens 0.44.185.460 I slot print_timing: id 0 | task 3780 | graphs reused = 3653 0.44.185.461 I slot print_timing: id 0 | task 3780 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.185.499 I slot release: id 0 | task 3780 | stop processing: n_tokens = 727, truncated = 0 0.44.208.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 44095724 0.44.231.734 I slot launch_slot_: id 0 | task 3844 | processing task, is_child = 0 0.44.971.989 I slot print_timing: id 0 | task 3844 | prompt eval time = 141.06 ms / 629 tokens ( 0.22 ms per token, 4459.25 tokens per second) 0.44.971.994 I slot print_timing: id 0 | task 3844 | eval time = 599.18 ms / 66 tokens ( 9.22 ms per token, 108.48 tokens per second) 0.44.971.996 I slot print_timing: id 0 | task 3844 | total time = 740.24 ms / 695 tokens 0.44.971.996 I slot print_timing: id 0 | task 3844 | graphs reused = 3717 0.44.971.997 I slot print_timing: id 0 | task 3844 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.972.032 I slot release: id 0 | task 3844 | stop processing: n_tokens = 719, truncated = 0 0.44.995.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 719, t_last = 44882257 0.45.018.809 I slot launch_slot_: id 0 | task 3911 | processing task, is_child = 0 0.45.642.971 I slot print_timing: id 0 | task 3911 | prompt eval time = 106.83 ms / 458 tokens ( 0.23 ms per token, 4287.02 tokens per second) 0.45.642.977 I slot print_timing: id 0 | task 3911 | eval time = 517.31 ms / 57 tokens ( 9.24 ms per token, 108.25 tokens per second) 0.45.642.978 I slot print_timing: id 0 | task 3911 | total time = 624.15 ms / 515 tokens 0.45.642.978 I slot print_timing: id 0 | task 3911 | graphs reused = 3771 0.45.642.979 I slot print_timing: id 0 | task 3911 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.643.010 I slot release: id 0 | task 3911 | stop processing: n_tokens = 539, truncated = 0 0.45.648.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 45553235 0.45.666.743 I slot launch_slot_: id 0 | task 3969 | processing task, is_child = 0 0.46.225.726 I slot print_timing: id 0 | task 3969 | prompt eval time = 134.81 ms / 594 tokens ( 0.23 ms per token, 4406.17 tokens per second) 0.46.225.732 I slot print_timing: id 0 | task 3969 | eval time = 424.15 ms / 47 tokens ( 9.22 ms per token, 108.45 tokens per second) 0.46.225.733 I slot print_timing: id 0 | task 3969 | total time = 558.96 ms / 641 tokens 0.46.225.734 I slot print_timing: id 0 | task 3969 | graphs reused = 3816 0.46.225.735 I slot print_timing: id 0 | task 3969 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.225.769 I slot release: id 0 | task 3969 | stop processing: n_tokens = 665, truncated = 0 0.46.241.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 46135995 0.46.263.161 I slot launch_slot_: id 0 | task 4017 | processing task, is_child = 0 0.46.853.125 I slot print_timing: id 0 | task 4017 | prompt eval time = 128.68 ms / 572 tokens ( 0.22 ms per token, 4445.27 tokens per second) 0.46.853.131 I slot print_timing: id 0 | task 4017 | eval time = 461.27 ms / 51 tokens ( 9.23 ms per token, 108.40 tokens per second) 0.46.853.132 I slot print_timing: id 0 | task 4017 | total time = 589.95 ms / 623 tokens 0.46.853.133 I slot print_timing: id 0 | task 4017 | graphs reused = 3865 0.46.853.134 I slot print_timing: id 0 | task 4017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.853.169 I slot release: id 0 | task 4017 | stop processing: n_tokens = 647, truncated = 0 0.46.878.568 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 46763394 0.46.899.481 I slot launch_slot_: id 0 | task 4069 | processing task, is_child = 0 0.47.461.014 I slot print_timing: id 0 | task 4069 | prompt eval time = 109.58 ms / 502 tokens ( 0.22 ms per token, 4580.92 tokens per second) 0.47.461.020 I slot print_timing: id 0 | task 4069 | eval time = 451.93 ms / 50 tokens ( 9.22 ms per token, 108.42 tokens per second) 0.47.461.022 I slot print_timing: id 0 | task 4069 | total time = 561.52 ms / 552 tokens 0.47.461.022 I slot print_timing: id 0 | task 4069 | graphs reused = 3913 0.47.461.024 I slot print_timing: id 0 | task 4069 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.461.056 I slot release: id 0 | task 4069 | stop processing: n_tokens = 576, truncated = 0 0.47.487.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 47371281 0.47.507.014 I slot launch_slot_: id 0 | task 4120 | processing task, is_child = 0 0.48.115.471 I slot print_timing: id 0 | task 4120 | prompt eval time = 107.23 ms / 479 tokens ( 0.22 ms per token, 4466.95 tokens per second) 0.48.115.477 I slot print_timing: id 0 | task 4120 | eval time = 501.21 ms / 55 tokens ( 9.28 ms per token, 107.74 tokens per second) 0.48.115.478 I slot print_timing: id 0 | task 4120 | total time = 608.44 ms / 534 tokens 0.48.115.478 I slot print_timing: id 0 | task 4120 | graphs reused = 3965 0.48.115.479 I slot print_timing: id 0 | task 4120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.115.510 I slot release: id 0 | task 4120 | stop processing: n_tokens = 558, truncated = 0 0.48.137.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 48025735 0.48.156.082 I slot launch_slot_: id 0 | task 4176 | processing task, is_child = 0 0.48.688.918 I slot print_timing: id 0 | task 4176 | prompt eval time = 125.25 ms / 552 tokens ( 0.23 ms per token, 4407.33 tokens per second) 0.48.688.924 I slot print_timing: id 0 | task 4176 | eval time = 407.57 ms / 45 tokens ( 9.26 ms per token, 107.96 tokens per second) 0.48.688.925 I slot print_timing: id 0 | task 4176 | total time = 532.82 ms / 597 tokens 0.48.688.926 I slot print_timing: id 0 | task 4176 | graphs reused = 4008 0.48.688.927 I slot print_timing: id 0 | task 4176 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.688.961 I slot release: id 0 | task 4176 | stop processing: n_tokens = 621, truncated = 0 0.48.709.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 48599186 0.48.730.483 I slot launch_slot_: id 0 | task 4222 | processing task, is_child = 0 0.49.764.920 I slot print_timing: id 0 | task 4222 | prompt eval time = 117.85 ms / 514 tokens ( 0.23 ms per token, 4361.55 tokens per second) 0.49.764.926 I slot print_timing: id 0 | task 4222 | eval time = 916.58 ms / 101 tokens ( 9.17 ms per token, 109.10 tokens per second) 0.49.764.927 I slot print_timing: id 0 | task 4222 | total time = 1034.42 ms / 615 tokens 0.49.764.927 I slot print_timing: id 0 | task 4222 | graphs reused = 4107 0.49.764.928 I slot print_timing: id 0 | task 4222 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.764.961 I slot release: id 0 | task 4222 | stop processing: n_tokens = 639, truncated = 0 0.49.783.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 49675186 0.49.804.930 I slot launch_slot_: id 0 | task 4324 | processing task, is_child = 0 0.50.277.959 I slot print_timing: id 0 | task 4324 | prompt eval time = 97.69 ms / 428 tokens ( 0.23 ms per token, 4381.07 tokens per second) 0.50.277.965 I slot print_timing: id 0 | task 4324 | eval time = 375.32 ms / 42 tokens ( 9.15 ms per token, 109.24 tokens per second) 0.50.277.966 I slot print_timing: id 0 | task 4324 | total time = 473.01 ms / 470 tokens 0.50.277.967 I slot print_timing: id 0 | task 4324 | graphs reused = 4147 0.50.277.968 I slot print_timing: id 0 | task 4324 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.278.000 I slot release: id 0 | task 4324 | stop processing: n_tokens = 494, truncated = 0 0.50.294.559 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 50188225 0.50.311.679 I slot launch_slot_: id 0 | task 4367 | processing task, is_child = 0 0.51.043.047 I slot print_timing: id 0 | task 4367 | prompt eval time = 121.97 ms / 521 tokens ( 0.23 ms per token, 4271.37 tokens per second) 0.51.043.053 I slot print_timing: id 0 | task 4367 | eval time = 609.38 ms / 66 tokens ( 9.38 ms per token, 106.67 tokens per second) 0.51.043.054 I slot print_timing: id 0 | task 4367 | total time = 731.35 ms / 587 tokens 0.51.043.055 I slot print_timing: id 0 | task 4367 | graphs reused = 4211 0.51.043.056 I slot print_timing: id 0 | task 4367 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.043.090 I slot release: id 0 | task 4367 | stop processing: n_tokens = 611, truncated = 0 0.51.059.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 50953315 0.51.080.100 I slot launch_slot_: id 0 | task 4434 | processing task, is_child = 0 0.51.650.587 I slot print_timing: id 0 | task 4434 | prompt eval time = 106.67 ms / 472 tokens ( 0.23 ms per token, 4425.03 tokens per second) 0.51.650.593 I slot print_timing: id 0 | task 4434 | eval time = 463.80 ms / 51 tokens ( 9.28 ms per token, 107.80 tokens per second) 0.51.650.594 I slot print_timing: id 0 | task 4434 | total time = 570.47 ms / 523 tokens 0.51.650.595 I slot print_timing: id 0 | task 4434 | graphs reused = 4259 0.51.650.596 I slot print_timing: id 0 | task 4434 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.650.628 I slot release: id 0 | task 4434 | stop processing: n_tokens = 547, truncated = 0 0.51.666.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 51560853 0.51.684.947 I slot launch_slot_: id 0 | task 4486 | processing task, is_child = 0 0.52.178.115 I slot print_timing: id 0 | task 4486 | prompt eval time = 97.78 ms / 428 tokens ( 0.23 ms per token, 4377.31 tokens per second) 0.52.178.122 I slot print_timing: id 0 | task 4486 | eval time = 395.37 ms / 44 tokens ( 9.19 ms per token, 108.76 tokens per second) 0.52.178.123 I slot print_timing: id 0 | task 4486 | total time = 493.15 ms / 472 tokens 0.52.178.123 I slot print_timing: id 0 | task 4486 | graphs reused = 4301 0.52.178.124 I slot print_timing: id 0 | task 4486 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.178.161 I slot release: id 0 | task 4486 | stop processing: n_tokens = 496, truncated = 0 0.52.196.575 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 52088386 0.52.214.539 I slot launch_slot_: id 0 | task 4531 | processing task, is_child = 0 0.52.741.651 I slot print_timing: id 0 | task 4531 | prompt eval time = 107.48 ms / 456 tokens ( 0.24 ms per token, 4242.61 tokens per second) 0.52.741.657 I slot print_timing: id 0 | task 4531 | eval time = 419.61 ms / 45 tokens ( 9.54 ms per token, 104.86 tokens per second) 0.52.741.658 I slot print_timing: id 0 | task 4531 | total time = 527.09 ms / 501 tokens 0.52.741.659 I slot print_timing: id 0 | task 4531 | graphs reused = 4343 0.52.741.659 I slot print_timing: id 0 | task 4531 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.741.694 I slot release: id 0 | task 4531 | stop processing: n_tokens = 525, truncated = 0 0.52.768.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 52651919 0.52.785.952 I slot launch_slot_: id 0 | task 4577 | processing task, is_child = 0 0.53.281.408 I slot print_timing: id 0 | task 4577 | prompt eval time = 98.18 ms / 439 tokens ( 0.22 ms per token, 4471.29 tokens per second) 0.53.281.414 I slot print_timing: id 0 | task 4577 | eval time = 397.26 ms / 44 tokens ( 9.24 ms per token, 108.24 tokens per second) 0.53.281.415 I slot print_timing: id 0 | task 4577 | total time = 495.44 ms / 483 tokens 0.53.281.415 I slot print_timing: id 0 | task 4577 | graphs reused = 4385 0.53.281.416 I slot print_timing: id 0 | task 4577 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.281.448 I slot release: id 0 | task 4577 | stop processing: n_tokens = 507, truncated = 0 0.53.296.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 53191673 0.53.313.554 I slot launch_slot_: id 0 | task 4622 | processing task, is_child = 0 0.53.993.844 I slot print_timing: id 0 | task 4622 | prompt eval time = 135.18 ms / 600 tokens ( 0.23 ms per token, 4438.43 tokens per second) 0.53.993.850 I slot print_timing: id 0 | task 4622 | eval time = 545.09 ms / 60 tokens ( 9.24 ms per token, 108.24 tokens per second) 0.53.993.851 I slot print_timing: id 0 | task 4622 | total time = 680.27 ms / 660 tokens 0.53.993.852 I slot print_timing: id 0 | task 4622 | graphs reused = 4443 0.53.993.853 I slot print_timing: id 0 | task 4622 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.993.888 I slot release: id 0 | task 4622 | stop processing: n_tokens = 684, truncated = 0 0.53.998.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 53904113 0.54.021.301 I slot launch_slot_: id 0 | task 4683 | processing task, is_child = 0 0.54.510.982 I slot print_timing: id 0 | task 4683 | prompt eval time = 107.44 ms / 473 tokens ( 0.23 ms per token, 4402.58 tokens per second) 0.54.510.988 I slot print_timing: id 0 | task 4683 | eval time = 382.23 ms / 42 tokens ( 9.32 ms per token, 107.27 tokens per second) 0.54.510.989 I slot print_timing: id 0 | task 4683 | total time = 489.67 ms / 515 tokens 0.54.510.990 I slot print_timing: id 0 | task 4683 | graphs reused = 4482 0.54.510.991 I slot print_timing: id 0 | task 4683 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.511.023 I slot release: id 0 | task 4683 | stop processing: n_tokens = 539, truncated = 0 0.54.535.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 54421248 0.54.554.634 I slot launch_slot_: id 0 | task 4726 | processing task, is_child = 0 0.55.327.273 I slot print_timing: id 0 | task 4726 | prompt eval time = 180.92 ms / 835 tokens ( 0.22 ms per token, 4615.38 tokens per second) 0.55.327.279 I slot print_timing: id 0 | task 4726 | eval time = 591.71 ms / 65 tokens ( 9.25 ms per token, 108.16 tokens per second) 0.55.327.280 I slot print_timing: id 0 | task 4726 | total time = 772.62 ms / 900 tokens 0.55.327.281 I slot print_timing: id 0 | task 4726 | graphs reused = 4545 0.55.327.282 I slot print_timing: id 0 | task 4726 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.327.326 I slot release: id 0 | task 4726 | stop processing: n_tokens = 924, truncated = 0 0.55.351.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 55237551 0.55.380.434 I slot launch_slot_: id 0 | task 4792 | processing task, is_child = 0 0.55.876.140 I slot print_timing: id 0 | task 4792 | prompt eval time = 106.64 ms / 454 tokens ( 0.23 ms per token, 4257.23 tokens per second) 0.55.876.146 I slot print_timing: id 0 | task 4792 | eval time = 389.05 ms / 43 tokens ( 9.26 ms per token, 107.96 tokens per second) 0.55.876.147 I slot print_timing: id 0 | task 4792 | total time = 495.69 ms / 497 tokens 0.55.876.148 I slot print_timing: id 0 | task 4792 | graphs reused = 4585 0.55.876.149 I slot print_timing: id 0 | task 4792 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.876.181 I slot release: id 0 | task 4792 | stop processing: n_tokens = 521, truncated = 0 0.55.900.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 55786406 0.55.918.680 I slot launch_slot_: id 0 | task 4836 | processing task, is_child = 0 0.56.501.715 I slot print_timing: id 0 | task 4836 | prompt eval time = 148.96 ms / 667 tokens ( 0.22 ms per token, 4477.74 tokens per second) 0.56.501.721 I slot print_timing: id 0 | task 4836 | eval time = 434.06 ms / 48 tokens ( 9.24 ms per token, 108.28 tokens per second) 0.56.501.722 I slot print_timing: id 0 | task 4836 | total time = 583.02 ms / 715 tokens 0.56.501.723 I slot print_timing: id 0 | task 4836 | graphs reused = 4631 0.56.501.724 I slot print_timing: id 0 | task 4836 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.501.764 I slot release: id 0 | task 4836 | stop processing: n_tokens = 741, truncated = 0 0.56.523.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 56411989 0.56.561.240 I slot launch_slot_: id 0 | task 4885 | processing task, is_child = 0 0.57.359.721 I slot print_timing: id 0 | task 4885 | prompt eval time = 141.59 ms / 628 tokens ( 0.23 ms per token, 4435.34 tokens per second) 0.57.359.727 I slot print_timing: id 0 | task 4885 | eval time = 656.87 ms / 69 tokens ( 9.66 ms per token, 103.52 tokens per second) 0.57.359.728 I slot print_timing: id 0 | task 4885 | total time = 798.46 ms / 697 tokens 0.57.359.729 I slot print_timing: id 0 | task 4885 | graphs reused = 4698 0.57.359.729 I slot print_timing: id 0 | task 4885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.359.772 I slot release: id 0 | task 4885 | stop processing: n_tokens = 858, truncated = 0 0.57.383.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 57269997 0.57.410.592 I slot launch_slot_: id 0 | task 4955 | processing task, is_child = 0 0.58.231.766 I slot print_timing: id 0 | task 4955 | prompt eval time = 131.82 ms / 578 tokens ( 0.23 ms per token, 4384.73 tokens per second) 0.58.231.772 I slot print_timing: id 0 | task 4955 | eval time = 689.34 ms / 76 tokens ( 9.19 ms per token, 108.80 tokens per second) 0.58.231.773 I slot print_timing: id 0 | task 4955 | total time = 821.16 ms / 654 tokens 0.58.231.773 I slot print_timing: id 0 | task 4955 | graphs reused = 4772 0.58.231.774 I slot print_timing: id 0 | task 4955 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.231.815 I slot release: id 0 | task 4955 | stop processing: n_tokens = 678, truncated = 0 0.58.260.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 58142040 0.58.283.586 I slot launch_slot_: id 0 | task 5032 | processing task, is_child = 0 0.58.973.230 I slot print_timing: id 0 | task 5032 | prompt eval time = 107.50 ms / 461 tokens ( 0.23 ms per token, 4288.45 tokens per second) 0.58.973.236 I slot print_timing: id 0 | task 5032 | eval time = 582.13 ms / 64 tokens ( 9.24 ms per token, 108.22 tokens per second) 0.58.973.238 I slot print_timing: id 0 | task 5032 | total time = 689.62 ms / 525 tokens 0.58.973.238 I slot print_timing: id 0 | task 5032 | graphs reused = 4833 0.58.973.239 I slot print_timing: id 0 | task 5032 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.973.272 I slot release: id 0 | task 5032 | stop processing: n_tokens = 549, truncated = 0 0.58.993.677 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 58883497 0.59.011.988 I slot launch_slot_: id 0 | task 5097 | processing task, is_child = 0 0.59.748.201 I slot print_timing: id 0 | task 5097 | prompt eval time = 138.37 ms / 613 tokens ( 0.23 ms per token, 4430.12 tokens per second) 0.59.748.206 I slot print_timing: id 0 | task 5097 | eval time = 597.83 ms / 66 tokens ( 9.20 ms per token, 108.73 tokens per second) 0.59.748.208 I slot print_timing: id 0 | task 5097 | total time = 736.20 ms / 679 tokens 0.59.748.208 I slot print_timing: id 0 | task 5097 | graphs reused = 4897 0.59.748.209 I slot print_timing: id 0 | task 5097 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.748.246 I slot release: id 0 | task 5097 | stop processing: n_tokens = 703, truncated = 0 0.59.776.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 59658471 0.59.799.494 I slot launch_slot_: id 0 | task 5164 | processing task, is_child = 0 1.00.563.784 I slot print_timing: id 0 | task 5164 | prompt eval time = 172.52 ms / 794 tokens ( 0.22 ms per token, 4602.36 tokens per second) 1.00.563.790 I slot print_timing: id 0 | task 5164 | eval time = 591.75 ms / 65 tokens ( 9.25 ms per token, 108.15 tokens per second) 1.00.563.791 I slot print_timing: id 0 | task 5164 | total time = 764.27 ms / 859 tokens 1.00.563.792 I slot print_timing: id 0 | task 5164 | graphs reused = 4960 1.00.563.793 I slot print_timing: id 0 | task 5164 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.563.837 I slot release: id 0 | task 5164 | stop processing: n_tokens = 883, truncated = 0 1.00.583.899 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 60474062 1.00.630.428 I slot launch_slot_: id 0 | task 5230 | processing task, is_child = 0 1.01.255.255 I slot print_timing: id 0 | task 5230 | prompt eval time = 98.84 ms / 431 tokens ( 0.23 ms per token, 4360.63 tokens per second) 1.01.255.261 I slot print_timing: id 0 | task 5230 | eval time = 525.97 ms / 58 tokens ( 9.23 ms per token, 108.37 tokens per second) 1.01.255.262 I slot print_timing: id 0 | task 5230 | total time = 624.81 ms / 489 tokens 1.01.255.263 I slot print_timing: id 0 | task 5230 | graphs reused = 5016 1.01.255.264 I slot print_timing: id 0 | task 5230 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.255.301 I slot release: id 0 | task 5230 | stop processing: n_tokens = 687, truncated = 0 1.01.285.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 61165526 1.01.307.556 I slot launch_slot_: id 0 | task 5289 | processing task, is_child = 0 1.01.898.555 I slot print_timing: id 0 | task 5289 | prompt eval time = 128.06 ms / 563 tokens ( 0.23 ms per token, 4396.38 tokens per second) 1.01.898.561 I slot print_timing: id 0 | task 5289 | eval time = 462.92 ms / 50 tokens ( 9.45 ms per token, 105.85 tokens per second) 1.01.898.562 I slot print_timing: id 0 | task 5289 | total time = 590.98 ms / 613 tokens 1.01.898.563 I slot print_timing: id 0 | task 5289 | graphs reused = 5064 1.01.898.564 I slot print_timing: id 0 | task 5289 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.898.598 I slot release: id 0 | task 5289 | stop processing: n_tokens = 637, truncated = 0 1.01.918.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 61808823 1.01.953.816 I slot launch_slot_: id 0 | task 5340 | processing task, is_child = 0 1.02.459.943 I slot print_timing: id 0 | task 5340 | prompt eval time = 73.50 ms / 331 tokens ( 0.22 ms per token, 4503.40 tokens per second) 1.02.459.947 I slot print_timing: id 0 | task 5340 | eval time = 432.60 ms / 48 tokens ( 9.20 ms per token, 108.65 tokens per second) 1.02.459.948 I slot print_timing: id 0 | task 5340 | total time = 506.10 ms / 379 tokens 1.02.459.949 I slot print_timing: id 0 | task 5340 | graphs reused = 5109 1.02.459.950 I slot print_timing: id 0 | task 5340 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.459.984 I slot release: id 0 | task 5340 | stop processing: n_tokens = 513, truncated = 0 1.02.479.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 62370209 1.02.497.906 I slot launch_slot_: id 0 | task 5389 | processing task, is_child = 0 1.03.216.087 I slot print_timing: id 0 | task 5389 | prompt eval time = 109.81 ms / 489 tokens ( 0.22 ms per token, 4453.27 tokens per second) 1.03.216.093 I slot print_timing: id 0 | task 5389 | eval time = 608.36 ms / 67 tokens ( 9.22 ms per token, 108.49 tokens per second) 1.03.216.094 I slot print_timing: id 0 | task 5389 | total time = 718.16 ms / 556 tokens 1.03.216.095 I slot print_timing: id 0 | task 5389 | graphs reused = 5174 1.03.216.096 I slot print_timing: id 0 | task 5389 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.216.131 I slot release: id 0 | task 5389 | stop processing: n_tokens = 580, truncated = 0 1.03.234.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 63126356 1.03.255.300 I slot launch_slot_: id 0 | task 5457 | processing task, is_child = 0 1.03.853.317 I slot print_timing: id 0 | task 5457 | prompt eval time = 109.80 ms / 510 tokens ( 0.22 ms per token, 4644.72 tokens per second) 1.03.853.323 I slot print_timing: id 0 | task 5457 | eval time = 488.20 ms / 54 tokens ( 9.21 ms per token, 108.56 tokens per second) 1.03.853.324 I slot print_timing: id 0 | task 5457 | total time = 598.00 ms / 564 tokens 1.03.853.325 I slot print_timing: id 0 | task 5457 | graphs reused = 5226 1.03.853.326 I slot print_timing: id 0 | task 5457 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.853.362 I slot release: id 0 | task 5457 | stop processing: n_tokens = 588, truncated = 0 1.03.876.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 63763587 1.03.896.678 I slot launch_slot_: id 0 | task 5512 | processing task, is_child = 0 1.04.682.496 I slot print_timing: id 0 | task 5512 | prompt eval time = 140.95 ms / 631 tokens ( 0.22 ms per token, 4476.86 tokens per second) 1.04.682.502 I slot print_timing: id 0 | task 5512 | eval time = 644.86 ms / 71 tokens ( 9.21 ms per token, 108.55 tokens per second) 1.04.682.503 I slot print_timing: id 0 | task 5512 | total time = 785.80 ms / 702 tokens 1.04.682.504 I slot print_timing: id 0 | task 5512 | graphs reused = 5295 1.04.682.505 I slot print_timing: id 0 | task 5512 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.682.543 I slot release: id 0 | task 5512 | stop processing: n_tokens = 726, truncated = 0 1.04.704.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 64592768 1.04.733.476 I slot launch_slot_: id 0 | task 5584 | processing task, is_child = 0 1.05.351.670 I slot print_timing: id 0 | task 5584 | prompt eval time = 128.60 ms / 570 tokens ( 0.23 ms per token, 4432.24 tokens per second) 1.05.351.675 I slot print_timing: id 0 | task 5584 | eval time = 489.57 ms / 54 tokens ( 9.24 ms per token, 108.26 tokens per second) 1.05.351.677 I slot print_timing: id 0 | task 5584 | total time = 618.18 ms / 624 tokens 1.05.351.678 I slot print_timing: id 0 | task 5584 | graphs reused = 5347 1.05.351.679 I slot print_timing: id 0 | task 5584 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.351.714 I slot release: id 0 | task 5584 | stop processing: n_tokens = 648, truncated = 0 1.05.376.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 65261939 1.05.397.949 I slot launch_slot_: id 0 | task 5639 | processing task, is_child = 0 1.06.014.263 I slot print_timing: id 0 | task 5639 | prompt eval time = 171.76 ms / 792 tokens ( 0.22 ms per token, 4610.95 tokens per second) 1.06.014.269 I slot print_timing: id 0 | task 5639 | eval time = 444.53 ms / 49 tokens ( 9.26 ms per token, 107.98 tokens per second) 1.06.014.270 I slot print_timing: id 0 | task 5639 | total time = 616.30 ms / 841 tokens 1.06.014.272 I slot print_timing: id 0 | task 5639 | graphs reused = 5394 1.06.014.273 I slot print_timing: id 0 | task 5639 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.014.314 I slot release: id 0 | task 5639 | stop processing: n_tokens = 867, truncated = 0 1.06.035.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 65924540 1.06.063.870 I slot launch_slot_: id 0 | task 5689 | processing task, is_child = 0 1.06.608.435 I slot print_timing: id 0 | task 5689 | prompt eval time = 127.93 ms / 564 tokens ( 0.23 ms per token, 4408.63 tokens per second) 1.06.608.440 I slot print_timing: id 0 | task 5689 | eval time = 416.62 ms / 45 tokens ( 9.47 ms per token, 105.61 tokens per second) 1.06.608.441 I slot print_timing: id 0 | task 5689 | total time = 544.55 ms / 609 tokens 1.06.608.443 I slot print_timing: id 0 | task 5689 | graphs reused = 5437 1.06.608.443 I slot print_timing: id 0 | task 5689 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.608.480 I slot release: id 0 | task 5689 | stop processing: n_tokens = 635, truncated = 0 1.06.625.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 66518705 1.06.646.275 I slot launch_slot_: id 0 | task 5735 | processing task, is_child = 0 1.07.429.019 I slot print_timing: id 0 | task 5735 | prompt eval time = 138.22 ms / 617 tokens ( 0.22 ms per token, 4463.77 tokens per second) 1.07.429.025 I slot print_timing: id 0 | task 5735 | eval time = 644.51 ms / 71 tokens ( 9.21 ms per token, 108.61 tokens per second) 1.07.429.026 I slot print_timing: id 0 | task 5735 | total time = 782.73 ms / 688 tokens 1.07.429.027 I slot print_timing: id 0 | task 5735 | graphs reused = 5506 1.07.429.028 I slot print_timing: id 0 | task 5735 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.429.065 I slot release: id 0 | task 5735 | stop processing: n_tokens = 712, truncated = 0 1.07.455.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 712, t_last = 67339291 1.07.478.909 I slot launch_slot_: id 0 | task 5807 | processing task, is_child = 0 1.08.228.546 I slot print_timing: id 0 | task 5807 | prompt eval time = 128.66 ms / 572 tokens ( 0.22 ms per token, 4445.72 tokens per second) 1.08.228.552 I slot print_timing: id 0 | task 5807 | eval time = 620.96 ms / 67 tokens ( 9.41 ms per token, 106.29 tokens per second) 1.08.228.553 I slot print_timing: id 0 | task 5807 | total time = 749.62 ms / 639 tokens 1.08.228.554 I slot print_timing: id 0 | task 5807 | graphs reused = 5571 1.08.228.555 I slot print_timing: id 0 | task 5807 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.228.595 I slot release: id 0 | task 5807 | stop processing: n_tokens = 663, truncated = 0 1.08.235.491 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 68138820 1.08.262.386 I slot launch_slot_: id 0 | task 5875 | processing task, is_child = 0 1.08.926.983 I slot print_timing: id 0 | task 5875 | prompt eval time = 166.96 ms / 712 tokens ( 0.23 ms per token, 4264.60 tokens per second) 1.08.926.990 I slot print_timing: id 0 | task 5875 | eval time = 497.62 ms / 54 tokens ( 9.39 ms per token, 106.51 tokens per second) 1.08.926.991 I slot print_timing: id 0 | task 5875 | total time = 664.57 ms / 766 tokens 1.08.926.992 I slot print_timing: id 0 | task 5875 | graphs reused = 5622 1.08.926.992 I slot print_timing: id 0 | task 5875 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.927.034 I slot release: id 0 | task 5875 | stop processing: n_tokens = 790, truncated = 0 1.08.952.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 68837259 1.08.978.142 I slot launch_slot_: id 0 | task 5930 | processing task, is_child = 0 1.10.148.058 I slot print_timing: id 0 | task 5930 | prompt eval time = 172.30 ms / 791 tokens ( 0.22 ms per token, 4590.80 tokens per second) 1.10.148.064 I slot print_timing: id 0 | task 5930 | eval time = 997.60 ms / 107 tokens ( 9.41 ms per token, 106.26 tokens per second) 1.10.148.065 I slot print_timing: id 0 | task 5930 | total time = 1169.90 ms / 898 tokens 1.10.148.066 I slot print_timing: id 0 | task 5930 | graphs reused = 5727 1.10.148.067 I slot print_timing: id 0 | task 5930 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.148.110 I slot release: id 0 | task 5930 | stop processing: n_tokens = 922, truncated = 0 1.10.165.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 922, t_last = 70058335 1.10.195.359 I slot launch_slot_: id 0 | task 6038 | processing task, is_child = 0 1.13.278.965 I slot print_timing: id 0 | task 6038 | n_gen = 330, tg = 109.52 t/s, tg_3s = 109.85 t/s 1.16.279.622 I slot print_timing: id 0 | task 6038 | n_gen = 656, tg = 109.08 t/s, tg_3s = 108.64 t/s 1.19.286.278 I slot print_timing: id 0 | task 6038 | n_gen = 965, tg = 106.98 t/s, tg_3s = 102.77 t/s 1.19.861.079 I slot print_timing: id 0 | task 6038 | prompt eval time = 79.48 ms / 369 tokens ( 0.22 ms per token, 4642.85 tokens per second) 1.19.861.084 I slot print_timing: id 0 | task 6038 | eval time = 9586.23 ms / 1024 tokens ( 9.37 ms per token, 106.72 tokens per second) 1.19.861.086 I slot print_timing: id 0 | task 6038 | total time = 9665.70 ms / 1393 tokens 1.19.861.086 I slot print_timing: id 0 | task 6038 | graphs reused = 6745 1.19.861.087 I slot print_timing: id 0 | task 6038 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.861.117 I slot release: id 0 | task 6038 | stop processing: n_tokens = 1417, truncated = 0 1.19.876.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1417, t_last = 79771342 1.19.876.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.19.925.797 I slot launch_slot_: id 0 | task 7063 | processing task, is_child = 0 1.20.580.913 I slot print_timing: id 0 | task 7063 | prompt eval time = 96.97 ms / 388 tokens ( 0.25 ms per token, 4001.03 tokens per second) 1.20.580.920 I slot print_timing: id 0 | task 7063 | eval time = 558.12 ms / 62 tokens ( 9.15 ms per token, 109.29 tokens per second) 1.20.580.921 I slot print_timing: id 0 | task 7063 | total time = 655.10 ms / 450 tokens 1.20.580.922 I slot print_timing: id 0 | task 7063 | graphs reused = 6805 1.20.580.923 I slot print_timing: id 0 | task 7063 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.580.956 I slot release: id 0 | task 7063 | stop processing: n_tokens = 474, truncated = 0 1.20.585.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 80491181 1.20.585.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.20.605.867 I slot launch_slot_: id 0 | task 7126 | processing task, is_child = 0 1.21.278.597 I slot print_timing: id 0 | task 7126 | prompt eval time = 79.53 ms / 370 tokens ( 0.21 ms per token, 4652.04 tokens per second) 1.21.278.602 I slot print_timing: id 0 | task 7126 | eval time = 593.17 ms / 66 tokens ( 9.13 ms per token, 109.58 tokens per second) 1.21.278.604 I slot print_timing: id 0 | task 7126 | total time = 672.71 ms / 436 tokens 1.21.278.604 I slot print_timing: id 0 | task 7126 | graphs reused = 6869 1.21.278.605 I slot print_timing: id 0 | task 7126 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.278.635 I slot release: id 0 | task 7126 | stop processing: n_tokens = 460, truncated = 0 1.21.306.385 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 81188860 1.21.306.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.21.327.076 I slot launch_slot_: id 0 | task 7193 | processing task, is_child = 0 1.21.945.036 I slot print_timing: id 0 | task 7193 | prompt eval time = 79.31 ms / 340 tokens ( 0.23 ms per token, 4287.14 tokens per second) 1.21.945.042 I slot print_timing: id 0 | task 7193 | eval time = 538.64 ms / 60 tokens ( 9.13 ms per token, 109.54 tokens per second) 1.21.945.043 I slot print_timing: id 0 | task 7193 | total time = 617.95 ms / 400 tokens 1.21.945.043 I slot print_timing: id 0 | task 7193 | graphs reused = 6927 1.21.945.044 I slot print_timing: id 0 | task 7193 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.945.073 I slot release: id 0 | task 7193 | stop processing: n_tokens = 424, truncated = 0 1.21.964.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 81855299 1.21.964.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.21.983.865 I slot launch_slot_: id 0 | task 7254 | processing task, is_child = 0 1.22.783.570 I slot print_timing: id 0 | task 7254 | prompt eval time = 97.31 ms / 409 tokens ( 0.24 ms per token, 4203.24 tokens per second) 1.22.783.576 I slot print_timing: id 0 | task 7254 | eval time = 702.38 ms / 78 tokens ( 9.12 ms per token, 109.63 tokens per second) 1.22.783.577 I slot print_timing: id 0 | task 7254 | total time = 799.69 ms / 487 tokens 1.22.783.578 I slot print_timing: id 0 | task 7254 | graphs reused = 7003 1.22.783.579 I slot print_timing: id 0 | task 7254 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.783.612 I slot release: id 0 | task 7254 | stop processing: n_tokens = 511, truncated = 0 1.22.805.287 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 82693837 1.22.805.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.22.827.964 I slot launch_slot_: id 0 | task 7333 | processing task, is_child = 0 1.23.778.921 I slot print_timing: id 0 | task 7333 | prompt eval time = 97.63 ms / 422 tokens ( 0.23 ms per token, 4322.57 tokens per second) 1.23.778.927 I slot print_timing: id 0 | task 7333 | eval time = 853.32 ms / 94 tokens ( 9.18 ms per token, 108.99 tokens per second) 1.23.778.928 I slot print_timing: id 0 | task 7333 | total time = 950.94 ms / 516 tokens 1.23.778.929 I slot print_timing: id 0 | task 7333 | graphs reused = 7094 1.23.778.929 I slot print_timing: id 0 | task 7333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.778.960 I slot release: id 0 | task 7333 | stop processing: n_tokens = 540, truncated = 0 1.23.783.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 83689185 1.23.783.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.23.787.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.538 MiB) 1.23.811.457 I slot launch_slot_: id 0 | task 7428 | processing task, is_child = 0 1.24.942.942 I slot print_timing: id 0 | task 7428 | prompt eval time = 109.62 ms / 499 tokens ( 0.22 ms per token, 4552.26 tokens per second) 1.24.942.949 I slot print_timing: id 0 | task 7428 | eval time = 1021.85 ms / 112 tokens ( 9.21 ms per token, 108.63 tokens per second) 1.24.942.951 I slot print_timing: id 0 | task 7428 | total time = 1131.47 ms / 611 tokens 1.24.942.952 I slot print_timing: id 0 | task 7428 | graphs reused = 7204 1.24.942.953 I slot print_timing: id 0 | task 7428 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.942.990 I slot release: id 0 | task 7428 | stop processing: n_tokens = 639, truncated = 0 1.24.947.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 84853215 1.24.947.372 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.24.974.472 I slot launch_slot_: id 0 | task 7541 | processing task, is_child = 0 1.25.448.987 I slot print_timing: id 0 | task 7541 | prompt eval time = 79.53 ms / 345 tokens ( 0.23 ms per token, 4337.88 tokens per second) 1.25.448.993 I slot print_timing: id 0 | task 7541 | eval time = 394.97 ms / 44 tokens ( 9.19 ms per token, 108.87 tokens per second) 1.25.448.994 I slot print_timing: id 0 | task 7541 | total time = 474.50 ms / 389 tokens 1.25.448.995 I slot print_timing: id 0 | task 7541 | graphs reused = 7246 1.25.448.996 I slot print_timing: id 0 | task 7541 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.449.025 I slot release: id 0 | task 7541 | stop processing: n_tokens = 413, truncated = 0 1.25.475.331 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 85359250 1.25.475.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.25.494.171 I slot launch_slot_: id 0 | task 7586 | processing task, is_child = 0 1.25.967.857 I slot print_timing: id 0 | task 7586 | prompt eval time = 79.35 ms / 348 tokens ( 0.23 ms per token, 4385.41 tokens per second) 1.25.967.863 I slot print_timing: id 0 | task 7586 | eval time = 394.32 ms / 44 tokens ( 9.17 ms per token, 109.05 tokens per second) 1.25.967.864 I slot print_timing: id 0 | task 7586 | total time = 473.67 ms / 392 tokens 1.25.967.865 I slot print_timing: id 0 | task 7586 | graphs reused = 7288 1.25.967.866 I slot print_timing: id 0 | task 7586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.967.896 I slot release: id 0 | task 7586 | stop processing: n_tokens = 416, truncated = 0 1.25.991.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 85878122 1.25.991.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.26.010.368 I slot launch_slot_: id 0 | task 7631 | processing task, is_child = 0 1.26.718.016 I slot print_timing: id 0 | task 7631 | prompt eval time = 96.65 ms / 408 tokens ( 0.24 ms per token, 4221.29 tokens per second) 1.26.718.022 I slot print_timing: id 0 | task 7631 | eval time = 610.98 ms / 68 tokens ( 9.12 ms per token, 109.66 tokens per second) 1.26.718.023 I slot print_timing: id 0 | task 7631 | total time = 707.63 ms / 476 tokens 1.26.718.024 I slot print_timing: id 0 | task 7631 | graphs reused = 7354 1.26.718.024 I slot print_timing: id 0 | task 7631 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.718.053 I slot release: id 0 | task 7631 | stop processing: n_tokens = 500, truncated = 0 1.26.739.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 86628278 1.26.739.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 1.26.761.668 I slot launch_slot_: id 0 | task 7700 | processing task, is_child = 0 1.27.435.189 I slot print_timing: id 0 | task 7700 | prompt eval time = 107.27 ms / 465 tokens ( 0.23 ms per token, 4334.69 tokens per second) 1.27.435.195 I slot print_timing: id 0 | task 7700 | eval time = 566.23 ms / 61 tokens ( 9.44 ms per token, 105.96 tokens per second) 1.27.435.196 I slot print_timing: id 0 | task 7700 | total time = 673.50 ms / 526 tokens 1.27.435.197 I slot print_timing: id 0 | task 7700 | graphs reused = 7412 1.27.435.197 I slot print_timing: id 0 | task 7700 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.435.229 I slot release: id 0 | task 7700 | stop processing: n_tokens = 550, truncated = 0 1.27.456.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 87345454 1.27.456.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 1.27.479.975 I slot launch_slot_: id 0 | task 7762 | processing task, is_child = 0 1.28.124.554 I slot print_timing: id 0 | task 7762 | prompt eval time = 96.81 ms / 399 tokens ( 0.24 ms per token, 4121.26 tokens per second) 1.28.124.559 I slot print_timing: id 0 | task 7762 | eval time = 547.75 ms / 60 tokens ( 9.28 ms per token, 107.71 tokens per second) 1.28.124.561 I slot print_timing: id 0 | task 7762 | total time = 644.56 ms / 459 tokens 1.28.124.561 I slot print_timing: id 0 | task 7762 | graphs reused = 7470 1.28.124.562 I slot print_timing: id 0 | task 7762 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.124.593 I slot release: id 0 | task 7762 | stop processing: n_tokens = 500, truncated = 0 1.28.148.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 88034818 1.28.148.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 1.28.169.963 I slot launch_slot_: id 0 | task 7823 | processing task, is_child = 0 1.28.928.151 I slot print_timing: id 0 | task 7823 | prompt eval time = 97.40 ms / 419 tokens ( 0.23 ms per token, 4301.72 tokens per second) 1.28.928.157 I slot print_timing: id 0 | task 7823 | eval time = 660.77 ms / 72 tokens ( 9.31 ms per token, 107.45 tokens per second) 1.28.928.158 I slot print_timing: id 0 | task 7823 | total time = 758.17 ms / 491 tokens 1.28.928.159 I slot print_timing: id 0 | task 7823 | graphs reused = 7539 1.28.928.160 I slot print_timing: id 0 | task 7823 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.928.191 I slot release: id 0 | task 7823 | stop processing: n_tokens = 515, truncated = 0 1.28.956.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 88838416 1.28.956.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 1.28.960.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.28.982.459 I slot launch_slot_: id 0 | task 7896 | processing task, is_child = 0 1.29.724.729 I slot print_timing: id 0 | task 7896 | prompt eval time = 98.06 ms / 440 tokens ( 0.22 ms per token, 4486.96 tokens per second) 1.29.724.735 I slot print_timing: id 0 | task 7896 | eval time = 644.19 ms / 71 tokens ( 9.20 ms per token, 108.66 tokens per second) 1.29.724.738 I slot print_timing: id 0 | task 7896 | total time = 742.25 ms / 511 tokens 1.29.724.739 I slot print_timing: id 0 | task 7896 | graphs reused = 7607 1.29.724.740 I slot print_timing: id 0 | task 7896 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.724.771 I slot release: id 0 | task 7896 | stop processing: n_tokens = 535, truncated = 0 1.29.749.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 89634996 1.29.749.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 1.29.771.531 I slot launch_slot_: id 0 | task 7968 | processing task, is_child = 0 1.30.318.167 I slot print_timing: id 0 | task 7968 | prompt eval time = 79.66 ms / 372 tokens ( 0.21 ms per token, 4669.85 tokens per second) 1.30.318.173 I slot print_timing: id 0 | task 7968 | eval time = 466.96 ms / 52 tokens ( 9.16 ms per token, 109.22 tokens per second) 1.30.318.174 I slot print_timing: id 0 | task 7968 | total time = 546.62 ms / 424 tokens 1.30.318.175 I slot print_timing: id 0 | task 7968 | graphs reused = 7657 1.30.318.176 I slot print_timing: id 0 | task 7968 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.318.211 I slot release: id 0 | task 7968 | stop processing: n_tokens = 448, truncated = 0 1.30.344.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 90228436 1.30.344.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 1.30.364.315 I slot launch_slot_: id 0 | task 8021 | processing task, is_child = 0 1.30.997.713 I slot print_timing: id 0 | task 8021 | prompt eval time = 106.53 ms / 449 tokens ( 0.24 ms per token, 4214.66 tokens per second) 1.30.997.719 I slot print_timing: id 0 | task 8021 | eval time = 526.85 ms / 58 tokens ( 9.24 ms per token, 108.19 tokens per second) 1.30.997.720 I slot print_timing: id 0 | task 8021 | total time = 633.38 ms / 507 tokens 1.30.997.721 I slot print_timing: id 0 | task 8021 | graphs reused = 7712 1.30.997.722 I slot print_timing: id 0 | task 8021 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.997.754 I slot release: id 0 | task 8021 | stop processing: n_tokens = 531, truncated = 0 1.31.013.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 90907979 1.31.013.931 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.31.035.682 I slot launch_slot_: id 0 | task 8080 | processing task, is_child = 0 1.31.672.503 I slot print_timing: id 0 | task 8080 | prompt eval time = 80.26 ms / 360 tokens ( 0.22 ms per token, 4485.31 tokens per second) 1.31.672.509 I slot print_timing: id 0 | task 8080 | eval time = 556.54 ms / 62 tokens ( 9.12 ms per token, 109.60 tokens per second) 1.31.672.510 I slot print_timing: id 0 | task 8080 | total time = 636.81 ms / 422 tokens 1.31.672.510 I slot print_timing: id 0 | task 8080 | graphs reused = 7772 1.31.672.511 I slot print_timing: id 0 | task 8080 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.672.544 I slot release: id 0 | task 8080 | stop processing: n_tokens = 446, truncated = 0 1.31.700.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 91582770 1.31.700.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 1.31.720.143 I slot launch_slot_: id 0 | task 8143 | processing task, is_child = 0 1.32.292.526 I slot print_timing: id 0 | task 8143 | prompt eval time = 79.35 ms / 346 tokens ( 0.23 ms per token, 4360.37 tokens per second) 1.32.292.532 I slot print_timing: id 0 | task 8143 | eval time = 493.02 ms / 55 tokens ( 9.13 ms per token, 109.53 tokens per second) 1.32.292.533 I slot print_timing: id 0 | task 8143 | total time = 572.37 ms / 401 tokens 1.32.292.534 I slot print_timing: id 0 | task 8143 | graphs reused = 7825 1.32.292.535 I slot print_timing: id 0 | task 8143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.292.563 I slot release: id 0 | task 8143 | stop processing: n_tokens = 425, truncated = 0 1.32.307.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 92202788 1.32.307.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 1.32.327.046 I slot launch_slot_: id 0 | task 8199 | processing task, is_child = 0 1.32.891.934 I slot print_timing: id 0 | task 8199 | prompt eval time = 97.93 ms / 434 tokens ( 0.23 ms per token, 4431.56 tokens per second) 1.32.891.939 I slot print_timing: id 0 | task 8199 | eval time = 466.94 ms / 52 tokens ( 9.16 ms per token, 109.22 tokens per second) 1.32.891.940 I slot print_timing: id 0 | task 8199 | total time = 564.87 ms / 486 tokens 1.32.891.941 I slot print_timing: id 0 | task 8199 | graphs reused = 7875 1.32.891.942 I slot print_timing: id 0 | task 8199 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.891.972 I slot release: id 0 | task 8199 | stop processing: n_tokens = 510, truncated = 0 1.32.915.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 92802197 1.32.915.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 1.32.937.535 I slot launch_slot_: id 0 | task 8252 | processing task, is_child = 0 1.33.556.775 I slot print_timing: id 0 | task 8252 | prompt eval time = 79.40 ms / 369 tokens ( 0.22 ms per token, 4647.30 tokens per second) 1.33.556.780 I slot print_timing: id 0 | task 8252 | eval time = 539.82 ms / 59 tokens ( 9.31 ms per token, 107.44 tokens per second) 1.33.556.782 I slot print_timing: id 0 | task 8252 | total time = 619.22 ms / 428 tokens 1.33.556.782 I slot print_timing: id 0 | task 8252 | graphs reused = 7932 1.33.556.784 I slot print_timing: id 0 | task 8252 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.556.816 I slot release: id 0 | task 8252 | stop processing: n_tokens = 452, truncated = 0 1.33.573.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 93467041 1.33.573.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 1.33.594.062 I slot launch_slot_: id 0 | task 8312 | processing task, is_child = 0 1.34.402.387 I slot print_timing: id 0 | task 8312 | prompt eval time = 98.34 ms / 446 tokens ( 0.22 ms per token, 4535.06 tokens per second) 1.34.402.393 I slot print_timing: id 0 | task 8312 | eval time = 709.96 ms / 78 tokens ( 9.22 ms per token, 108.46 tokens per second) 1.34.402.394 I slot print_timing: id 0 | task 8312 | total time = 808.31 ms / 524 tokens 1.34.402.395 I slot print_timing: id 0 | task 8312 | graphs reused = 8007 1.34.402.396 I slot print_timing: id 0 | task 8312 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.402.428 I slot release: id 0 | task 8312 | stop processing: n_tokens = 548, truncated = 0 1.34.429.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 94312653 1.34.429.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 1.34.433.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.34.457.512 I slot launch_slot_: id 0 | task 8391 | processing task, is_child = 0 1.34.984.466 I slot print_timing: id 0 | task 8391 | prompt eval time = 96.95 ms / 396 tokens ( 0.24 ms per token, 4084.66 tokens per second) 1.34.984.472 I slot print_timing: id 0 | task 8391 | eval time = 429.99 ms / 48 tokens ( 9.15 ms per token, 109.31 tokens per second) 1.34.984.473 I slot print_timing: id 0 | task 8391 | total time = 526.94 ms / 444 tokens 1.34.984.474 I slot print_timing: id 0 | task 8391 | graphs reused = 8053 1.34.984.475 I slot print_timing: id 0 | task 8391 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.984.505 I slot release: id 0 | task 8391 | stop processing: n_tokens = 470, truncated = 0 1.35.007.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 94894730 1.35.007.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.975 MiB) 1.35.028.228 I slot launch_slot_: id 0 | task 8440 | processing task, is_child = 0 1.35.937.674 I slot print_timing: id 0 | task 8440 | prompt eval time = 106.85 ms / 466 tokens ( 0.23 ms per token, 4361.29 tokens per second) 1.35.937.679 I slot print_timing: id 0 | task 8440 | eval time = 802.58 ms / 88 tokens ( 9.23 ms per token, 108.40 tokens per second) 1.35.937.681 I slot print_timing: id 0 | task 8440 | total time = 909.43 ms / 554 tokens 1.35.937.682 I slot print_timing: id 0 | task 8440 | graphs reused = 8138 1.35.937.682 I slot print_timing: id 0 | task 8440 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.937.714 I slot release: id 0 | task 8440 | stop processing: n_tokens = 578, truncated = 0 1.35.956.311 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 95847939 1.35.956.371 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 1.35.980.500 I slot launch_slot_: id 0 | task 8529 | processing task, is_child = 0 1.36.707.085 I slot print_timing: id 0 | task 8529 | prompt eval time = 106.83 ms / 467 tokens ( 0.23 ms per token, 4371.27 tokens per second) 1.36.707.091 I slot print_timing: id 0 | task 8529 | eval time = 619.74 ms / 66 tokens ( 9.53 ms per token, 104.88 tokens per second) 1.36.707.093 I slot print_timing: id 0 | task 8529 | total time = 726.57 ms / 533 tokens 1.36.707.093 I slot print_timing: id 0 | task 8529 | graphs reused = 8201 1.36.707.094 I slot print_timing: id 0 | task 8529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.707.126 I slot release: id 0 | task 8529 | stop processing: n_tokens = 557, truncated = 0 1.36.722.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 96617351 1.36.722.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.36.745.740 I slot launch_slot_: id 0 | task 8596 | processing task, is_child = 0 1.37.500.026 I slot print_timing: id 0 | task 8596 | prompt eval time = 106.80 ms / 454 tokens ( 0.24 ms per token, 4250.94 tokens per second) 1.37.500.032 I slot print_timing: id 0 | task 8596 | eval time = 647.47 ms / 71 tokens ( 9.25 ms per token, 108.11 tokens per second) 1.37.500.033 I slot print_timing: id 0 | task 8596 | total time = 754.27 ms / 525 tokens 1.37.500.034 I slot print_timing: id 0 | task 8596 | graphs reused = 8269 1.37.500.035 I slot print_timing: id 0 | task 8596 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.500.070 I slot release: id 0 | task 8596 | stop processing: n_tokens = 549, truncated = 0 1.37.504.159 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 97410295 1.37.504.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.37.527.463 I slot launch_slot_: id 0 | task 8668 | processing task, is_child = 0 1.38.180.637 I slot print_timing: id 0 | task 8668 | prompt eval time = 96.89 ms / 409 tokens ( 0.24 ms per token, 4221.41 tokens per second) 1.38.180.643 I slot print_timing: id 0 | task 8668 | eval time = 556.27 ms / 62 tokens ( 9.12 ms per token, 109.66 tokens per second) 1.38.180.644 I slot print_timing: id 0 | task 8668 | total time = 653.16 ms / 471 tokens 1.38.180.645 I slot print_timing: id 0 | task 8668 | graphs reused = 8329 1.38.180.646 I slot print_timing: id 0 | task 8668 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.180.679 I slot release: id 0 | task 8668 | stop processing: n_tokens = 495, truncated = 0 1.38.197.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 98090904 1.38.197.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 1.38.219.674 I slot launch_slot_: id 0 | task 8731 | processing task, is_child = 0 1.38.810.221 I slot print_timing: id 0 | task 8731 | prompt eval time = 79.35 ms / 349 tokens ( 0.23 ms per token, 4398.29 tokens per second) 1.38.810.227 I slot print_timing: id 0 | task 8731 | eval time = 511.18 ms / 57 tokens ( 9.13 ms per token, 109.55 tokens per second) 1.38.810.228 I slot print_timing: id 0 | task 8731 | total time = 590.53 ms / 406 tokens 1.38.810.229 I slot print_timing: id 0 | task 8731 | graphs reused = 8384 1.38.810.230 I slot print_timing: id 0 | task 8731 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.810.260 I slot release: id 0 | task 8731 | stop processing: n_tokens = 430, truncated = 0 1.38.839.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 98720485 1.38.839.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 1.38.858.831 I slot launch_slot_: id 0 | task 8789 | processing task, is_child = 0 1.39.481.856 I slot print_timing: id 0 | task 8789 | prompt eval time = 98.35 ms / 435 tokens ( 0.23 ms per token, 4422.89 tokens per second) 1.39.481.862 I slot print_timing: id 0 | task 8789 | eval time = 524.66 ms / 58 tokens ( 9.20 ms per token, 108.64 tokens per second) 1.39.481.863 I slot print_timing: id 0 | task 8789 | total time = 623.01 ms / 493 tokens 1.39.481.864 I slot print_timing: id 0 | task 8789 | graphs reused = 8439 1.39.481.865 I slot print_timing: id 0 | task 8789 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.481.898 I slot release: id 0 | task 8789 | stop processing: n_tokens = 517, truncated = 0 1.39.510.504 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 99392123 1.39.510.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.39.514.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.39.537.307 I slot launch_slot_: id 0 | task 8848 | processing task, is_child = 0 1.40.047.926 I slot print_timing: id 0 | task 8848 | prompt eval time = 73.27 ms / 322 tokens ( 0.23 ms per token, 4394.82 tokens per second) 1.40.047.932 I slot print_timing: id 0 | task 8848 | eval time = 437.34 ms / 47 tokens ( 9.51 ms per token, 105.18 tokens per second) 1.40.047.933 I slot print_timing: id 0 | task 8848 | total time = 510.60 ms / 369 tokens 1.40.047.934 I slot print_timing: id 0 | task 8848 | graphs reused = 8484 1.40.047.935 I slot print_timing: id 0 | task 8848 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.047.963 I slot release: id 0 | task 8848 | stop processing: n_tokens = 393, truncated = 0 1.40.071.549 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 99958188 1.40.071.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 1.40.089.945 I slot launch_slot_: id 0 | task 8896 | processing task, is_child = 0 1.40.672.656 I slot print_timing: id 0 | task 8896 | prompt eval time = 80.08 ms / 360 tokens ( 0.22 ms per token, 4495.67 tokens per second) 1.40.672.662 I slot print_timing: id 0 | task 8896 | eval time = 502.62 ms / 56 tokens ( 9.14 ms per token, 109.43 tokens per second) 1.40.672.663 I slot print_timing: id 0 | task 8896 | total time = 582.69 ms / 416 tokens 1.40.672.664 I slot print_timing: id 0 | task 8896 | graphs reused = 8538 1.40.672.665 I slot print_timing: id 0 | task 8896 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.672.696 I slot release: id 0 | task 8896 | stop processing: n_tokens = 440, truncated = 0 1.40.692.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 100582921 1.40.692.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.725 MiB) 1.40.712.628 I slot launch_slot_: id 0 | task 8953 | processing task, is_child = 0 1.41.474.074 I slot print_timing: id 0 | task 8953 | prompt eval time = 98.20 ms / 443 tokens ( 0.22 ms per token, 4511.16 tokens per second) 1.41.474.080 I slot print_timing: id 0 | task 8953 | eval time = 663.23 ms / 73 tokens ( 9.21 ms per token, 108.56 tokens per second) 1.41.474.081 I slot print_timing: id 0 | task 8953 | total time = 761.43 ms / 516 tokens 1.41.474.082 I slot print_timing: id 0 | task 8953 | graphs reused = 8608 1.41.474.083 I slot print_timing: id 0 | task 8953 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.474.119 I slot release: id 0 | task 8953 | stop processing: n_tokens = 540, truncated = 0 1.41.500.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 101384344 1.41.500.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.41.523.672 I slot launch_slot_: id 0 | task 9027 | processing task, is_child = 0 1.42.015.410 I slot print_timing: id 0 | task 9027 | prompt eval time = 98.04 ms / 442 tokens ( 0.22 ms per token, 4508.18 tokens per second) 1.42.015.416 I slot print_timing: id 0 | task 9027 | eval time = 393.68 ms / 44 tokens ( 9.16 ms per token, 109.23 tokens per second) 1.42.015.417 I slot print_timing: id 0 | task 9027 | total time = 491.72 ms / 486 tokens 1.42.015.418 I slot print_timing: id 0 | task 9027 | graphs reused = 8650 1.42.015.419 I slot print_timing: id 0 | task 9027 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.015.450 I slot release: id 0 | task 9027 | stop processing: n_tokens = 510, truncated = 0 1.42.045.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 101925675 1.42.045.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.42.066.853 I slot launch_slot_: id 0 | task 9072 | processing task, is_child = 0 1.42.574.809 I slot print_timing: id 0 | task 9072 | prompt eval time = 107.31 ms / 470 tokens ( 0.23 ms per token, 4379.92 tokens per second) 1.42.574.815 I slot print_timing: id 0 | task 9072 | eval time = 400.63 ms / 44 tokens ( 9.32 ms per token, 107.33 tokens per second) 1.42.574.816 I slot print_timing: id 0 | task 9072 | total time = 507.94 ms / 514 tokens 1.42.574.819 I slot print_timing: id 0 | task 9072 | graphs reused = 8691 1.42.574.819 I slot print_timing: id 0 | task 9072 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.574.852 I slot release: id 0 | task 9072 | stop processing: n_tokens = 538, truncated = 0 1.42.593.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 102485077 1.42.593.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 1.42.615.004 I slot launch_slot_: id 0 | task 9117 | processing task, is_child = 0 1.43.033.729 I slot print_timing: id 0 | task 9117 | prompt eval time = 107.93 ms / 483 tokens ( 0.22 ms per token, 4475.25 tokens per second) 1.43.033.734 I slot print_timing: id 0 | task 9117 | eval time = 310.78 ms / 34 tokens ( 9.42 ms per token, 106.18 tokens per second) 1.43.033.735 I slot print_timing: id 0 | task 9117 | total time = 418.71 ms / 517 tokens 1.43.033.738 I slot print_timing: id 0 | task 9117 | graphs reused = 8722 1.43.033.738 I slot print_timing: id 0 | task 9117 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.033.772 I slot release: id 0 | task 9117 | stop processing: n_tokens = 541, truncated = 0 1.43.038.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 102943998 1.43.038.521 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.43.042.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 1.43.065.181 I slot launch_slot_: id 0 | task 9152 | processing task, is_child = 0 1.43.673.539 I slot print_timing: id 0 | task 9152 | prompt eval time = 107.20 ms / 463 tokens ( 0.23 ms per token, 4318.83 tokens per second) 1.43.673.544 I slot print_timing: id 0 | task 9152 | eval time = 501.14 ms / 55 tokens ( 9.28 ms per token, 107.76 tokens per second) 1.43.673.545 I slot print_timing: id 0 | task 9152 | total time = 608.34 ms / 518 tokens 1.43.673.546 I slot print_timing: id 0 | task 9152 | graphs reused = 8774 1.43.673.547 I slot print_timing: id 0 | task 9152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.673.578 I slot release: id 0 | task 9152 | stop processing: n_tokens = 542, truncated = 0 1.43.691.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 103583804 1.43.691.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 1.43.713.946 I slot launch_slot_: id 0 | task 9208 | processing task, is_child = 0 1.44.259.812 I slot print_timing: id 0 | task 9208 | prompt eval time = 97.50 ms / 421 tokens ( 0.23 ms per token, 4317.73 tokens per second) 1.44.259.818 I slot print_timing: id 0 | task 9208 | eval time = 448.34 ms / 50 tokens ( 9.15 ms per token, 109.29 tokens per second) 1.44.259.819 I slot print_timing: id 0 | task 9208 | total time = 545.85 ms / 471 tokens 1.44.259.820 I slot print_timing: id 0 | task 9208 | graphs reused = 8822 1.44.259.821 I slot print_timing: id 0 | task 9208 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.259.852 I slot release: id 0 | task 9208 | stop processing: n_tokens = 495, truncated = 0 1.44.285.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 104170077 1.44.285.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 1.44.307.637 I slot launch_slot_: id 0 | task 9259 | processing task, is_child = 0 1.44.773.133 I slot print_timing: id 0 | task 9259 | prompt eval time = 80.33 ms / 360 tokens ( 0.22 ms per token, 4481.57 tokens per second) 1.44.773.139 I slot print_timing: id 0 | task 9259 | eval time = 385.15 ms / 43 tokens ( 9.17 ms per token, 109.05 tokens per second) 1.44.773.140 I slot print_timing: id 0 | task 9259 | total time = 465.48 ms / 403 tokens 1.44.773.141 I slot print_timing: id 0 | task 9259 | graphs reused = 8863 1.44.773.141 I slot print_timing: id 0 | task 9259 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.773.172 I slot release: id 0 | task 9259 | stop processing: n_tokens = 427, truncated = 0 1.44.798.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 104683397 1.44.798.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 92.664 MiB) 1.44.819.405 I slot launch_slot_: id 0 | task 9303 | processing task, is_child = 0 1.45.574.666 I slot print_timing: id 0 | task 9303 | prompt eval time = 128.26 ms / 547 tokens ( 0.23 ms per token, 4264.84 tokens per second) 1.45.574.672 I slot print_timing: id 0 | task 9303 | eval time = 626.98 ms / 69 tokens ( 9.22 ms per token, 108.46 tokens per second) 1.45.574.673 I slot print_timing: id 0 | task 9303 | total time = 755.24 ms / 616 tokens 1.45.574.674 I slot print_timing: id 0 | task 9303 | graphs reused = 8930 1.45.574.675 I slot print_timing: id 0 | task 9303 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.574.710 I slot release: id 0 | task 9303 | stop processing: n_tokens = 640, truncated = 0 1.45.581.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 105484935 1.45.581.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 1.45.605.876 I slot launch_slot_: id 0 | task 9373 | processing task, is_child = 0 1.46.751.371 I slot print_timing: id 0 | task 9373 | prompt eval time = 168.26 ms / 749 tokens ( 0.22 ms per token, 4451.47 tokens per second) 1.46.751.377 I slot print_timing: id 0 | task 9373 | eval time = 977.22 ms / 107 tokens ( 9.22 ms per token, 108.47 tokens per second) 1.46.751.378 I slot print_timing: id 0 | task 9373 | total time = 1145.48 ms / 856 tokens 1.46.751.379 I slot print_timing: id 0 | task 9373 | graphs reused = 9035 1.46.751.380 I slot print_timing: id 0 | task 9373 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.751.422 I slot release: id 0 | task 9373 | stop processing: n_tokens = 880, truncated = 0 1.46.772.796 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 106661647 1.46.772.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 1.46.777.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 1.46.811.206 I slot launch_slot_: id 0 | task 9481 | processing task, is_child = 0 1.47.399.758 I slot print_timing: id 0 | task 9481 | prompt eval time = 153.28 ms / 678 tokens ( 0.23 ms per token, 4423.31 tokens per second) 1.47.399.764 I slot print_timing: id 0 | task 9481 | eval time = 435.25 ms / 48 tokens ( 9.26 ms per token, 107.98 tokens per second) 1.47.399.766 I slot print_timing: id 0 | task 9481 | total time = 588.53 ms / 726 tokens 1.47.399.767 I slot print_timing: id 0 | task 9481 | graphs reused = 9081 1.47.399.767 I slot print_timing: id 0 | task 9481 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.399.806 I slot release: id 0 | task 9481 | stop processing: n_tokens = 750, truncated = 0 1.47.425.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 107310031 1.47.425.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 1.47.430.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.47.459.576 I slot launch_slot_: id 0 | task 9530 | processing task, is_child = 0 1.48.115.884 I slot print_timing: id 0 | task 9530 | prompt eval time = 128.82 ms / 567 tokens ( 0.23 ms per token, 4401.39 tokens per second) 1.48.115.889 I slot print_timing: id 0 | task 9530 | eval time = 527.47 ms / 57 tokens ( 9.42 ms per token, 106.17 tokens per second) 1.48.115.890 I slot print_timing: id 0 | task 9530 | total time = 656.29 ms / 624 tokens 1.48.115.891 I slot print_timing: id 0 | task 9530 | graphs reused = 9136 1.48.115.892 I slot print_timing: id 0 | task 9530 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.115.929 I slot release: id 0 | task 9530 | stop processing: n_tokens = 648, truncated = 0 1.48.142.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 108026154 1.48.142.498 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.48.146.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 1.48.172.863 I slot launch_slot_: id 0 | task 9588 | processing task, is_child = 0 1.48.809.707 I slot print_timing: id 0 | task 9588 | prompt eval time = 109.65 ms / 501 tokens ( 0.22 ms per token, 4568.96 tokens per second) 1.48.809.712 I slot print_timing: id 0 | task 9588 | eval time = 527.17 ms / 58 tokens ( 9.25 ms per token, 108.12 tokens per second) 1.48.809.713 I slot print_timing: id 0 | task 9588 | total time = 636.83 ms / 559 tokens 1.48.809.714 I slot print_timing: id 0 | task 9588 | graphs reused = 9192 1.48.809.715 I slot print_timing: id 0 | task 9588 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.809.749 I slot release: id 0 | task 9588 | stop processing: n_tokens = 583, truncated = 0 1.48.839.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 108719975 1.48.839.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.48.863.033 I slot launch_slot_: id 0 | task 9647 | processing task, is_child = 0 1.49.599.603 I slot print_timing: id 0 | task 9647 | prompt eval time = 171.71 ms / 769 tokens ( 0.22 ms per token, 4478.59 tokens per second) 1.49.599.608 I slot print_timing: id 0 | task 9647 | eval time = 564.85 ms / 62 tokens ( 9.26 ms per token, 107.99 tokens per second) 1.49.599.609 I slot print_timing: id 0 | task 9647 | total time = 736.55 ms / 831 tokens 1.49.599.610 I slot print_timing: id 0 | task 9647 | graphs reused = 9252 1.49.599.611 I slot print_timing: id 0 | task 9647 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.599.651 I slot release: id 0 | task 9647 | stop processing: n_tokens = 855, truncated = 0 1.49.617.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 109509876 1.49.617.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 1.49.621.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 1.49.653.151 I slot launch_slot_: id 0 | task 9710 | processing task, is_child = 0 1.50.316.270 I slot print_timing: id 0 | task 9710 | prompt eval time = 109.63 ms / 500 tokens ( 0.22 ms per token, 4560.92 tokens per second) 1.50.316.276 I slot print_timing: id 0 | task 9710 | eval time = 553.48 ms / 61 tokens ( 9.22 ms per token, 108.41 tokens per second) 1.50.316.277 I slot print_timing: id 0 | task 9710 | total time = 663.10 ms / 561 tokens 1.50.316.278 I slot print_timing: id 0 | task 9710 | graphs reused = 9311 1.50.316.279 I slot print_timing: id 0 | task 9710 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.316.314 I slot release: id 0 | task 9710 | stop processing: n_tokens = 585, truncated = 0 1.50.335.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 110226539 1.50.335.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 1.50.361.343 I slot launch_slot_: id 0 | task 9772 | processing task, is_child = 0 1.51.039.226 I slot print_timing: id 0 | task 9772 | prompt eval time = 141.18 ms / 632 tokens ( 0.22 ms per token, 4476.68 tokens per second) 1.51.039.231 I slot print_timing: id 0 | task 9772 | eval time = 536.69 ms / 58 tokens ( 9.42 ms per token, 106.21 tokens per second) 1.51.039.233 I slot print_timing: id 0 | task 9772 | total time = 677.87 ms / 690 tokens 1.51.039.234 I slot print_timing: id 0 | task 9772 | graphs reused = 9367 1.51.039.234 I slot print_timing: id 0 | task 9772 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.039.272 I slot release: id 0 | task 9772 | stop processing: n_tokens = 714, truncated = 0 1.51.067.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 110949497 1.51.067.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 1.51.096.449 I slot launch_slot_: id 0 | task 9831 | processing task, is_child = 0 1.51.524.034 I slot print_timing: id 0 | task 9831 | prompt eval time = 96.54 ms / 395 tokens ( 0.24 ms per token, 4091.74 tokens per second) 1.51.524.040 I slot print_timing: id 0 | task 9831 | eval time = 331.03 ms / 37 tokens ( 9.20 ms per token, 108.75 tokens per second) 1.51.524.041 I slot print_timing: id 0 | task 9831 | total time = 427.57 ms / 432 tokens 1.51.524.042 I slot print_timing: id 0 | task 9831 | graphs reused = 9402 1.51.524.043 I slot print_timing: id 0 | task 9831 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.524.071 I slot release: id 0 | task 9831 | stop processing: n_tokens = 456, truncated = 0 1.51.553.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 111434296 1.51.553.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 1.51.574.589 I slot launch_slot_: id 0 | task 9869 | processing task, is_child = 0 1.52.273.832 I slot print_timing: id 0 | task 9869 | prompt eval time = 132.04 ms / 579 tokens ( 0.23 ms per token, 4385.10 tokens per second) 1.52.273.838 I slot print_timing: id 0 | task 9869 | eval time = 567.19 ms / 59 tokens ( 9.78 ms per token, 102.26 tokens per second) 1.52.273.839 I slot print_timing: id 0 | task 9869 | total time = 699.23 ms / 638 tokens 1.52.273.839 I slot print_timing: id 0 | task 9869 | graphs reused = 9459 1.52.273.840 I slot print_timing: id 0 | task 9869 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.273.878 I slot release: id 0 | task 9869 | stop processing: n_tokens = 662, truncated = 0 1.52.301.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 112184103 1.52.302.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 1.52.306.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 1.52.337.066 I slot launch_slot_: id 0 | task 9929 | processing task, is_child = 0 1.53.030.070 I slot print_timing: id 0 | task 9929 | prompt eval time = 152.73 ms / 689 tokens ( 0.22 ms per token, 4511.32 tokens per second) 1.53.030.076 I slot print_timing: id 0 | task 9929 | eval time = 540.26 ms / 59 tokens ( 9.31 ms per token, 107.36 tokens per second) 1.53.030.077 I slot print_timing: id 0 | task 9929 | total time = 692.99 ms / 748 tokens 1.53.030.078 I slot print_timing: id 0 | task 9929 | graphs reused = 9515 1.53.030.079 I slot print_timing: id 0 | task 9929 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.030.117 I slot release: id 0 | task 9929 | stop processing: n_tokens = 772, truncated = 0 1.53.053.155 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 112940342 1.53.053.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.53.083.374 I slot launch_slot_: id 0 | task 9989 | processing task, is_child = 0 1.53.865.809 I slot print_timing: id 0 | task 9989 | prompt eval time = 164.01 ms / 752 tokens ( 0.22 ms per token, 4585.03 tokens per second) 1.53.865.815 I slot print_timing: id 0 | task 9989 | eval time = 618.41 ms / 66 tokens ( 9.51 ms per token, 105.11 tokens per second) 1.53.865.817 I slot print_timing: id 0 | task 9989 | total time = 782.42 ms / 818 tokens 1.53.865.817 I slot print_timing: id 0 | task 9989 | graphs reused = 9579 1.53.865.819 I slot print_timing: id 0 | task 9989 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.865.861 I slot release: id 0 | task 9989 | stop processing: n_tokens = 842, truncated = 0 1.53.892.762 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 113776086 1.53.892.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 1.53.898.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 1.53.933.780 I slot launch_slot_: id 0 | task 10056 | processing task, is_child = 0 1.54.673.202 I slot print_timing: id 0 | task 10056 | prompt eval time = 132.06 ms / 582 tokens ( 0.23 ms per token, 4406.95 tokens per second) 1.54.673.208 I slot print_timing: id 0 | task 10056 | eval time = 607.34 ms / 67 tokens ( 9.20 ms per token, 108.67 tokens per second) 1.54.673.209 I slot print_timing: id 0 | task 10056 | total time = 739.40 ms / 649 tokens 1.54.673.210 I slot print_timing: id 0 | task 10056 | graphs reused = 9644 1.54.673.211 I slot print_timing: id 0 | task 10056 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.673.247 I slot release: id 0 | task 10056 | stop processing: n_tokens = 673, truncated = 0 1.54.678.356 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 114583472 1.54.678.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 1.54.707.808 I slot launch_slot_: id 0 | task 10124 | processing task, is_child = 0 1.57.862.340 I slot print_timing: id 0 | task 10124 | n_gen = 327, tg = 108.44 t/s, tg_3s = 108.77 t/s 1.58.366.583 I slot print_timing: id 0 | task 10124 | prompt eval time = 148.14 ms / 656 tokens ( 0.23 ms per token, 4428.24 tokens per second) 1.58.366.589 I slot print_timing: id 0 | task 10124 | eval time = 3510.62 ms / 379 tokens ( 9.29 ms per token, 107.67 tokens per second) 1.58.366.590 I slot print_timing: id 0 | task 10124 | total time = 3658.76 ms / 1035 tokens 1.58.366.591 I slot print_timing: id 0 | task 10124 | graphs reused = 10019 1.58.366.592 I slot print_timing: id 0 | task 10124 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.366.631 I slot release: id 0 | task 10124 | stop processing: n_tokens = 1059, truncated = 0 1.58.382.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1059, t_last = 118276856 1.58.382.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 112.353 MiB) 1.58.426.432 I slot launch_slot_: id 0 | task 10504 | processing task, is_child = 0 1.58.843.432 I slot print_timing: id 0 | task 10504 | prompt eval time = 137.99 ms / 613 tokens ( 0.23 ms per token, 4442.51 tokens per second) 1.58.843.437 I slot print_timing: id 0 | task 10504 | eval time = 279.00 ms / 31 tokens ( 9.30 ms per token, 107.53 tokens per second) 1.58.843.439 I slot print_timing: id 0 | task 10504 | total time = 416.98 ms / 644 tokens 1.58.843.439 I slot print_timing: id 0 | task 10504 | graphs reused = 10048 1.58.843.440 I slot print_timing: id 0 | task 10504 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.843.477 I slot release: id 0 | task 10504 | stop processing: n_tokens = 668, truncated = 0 1.58.849.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 118753702 1.58.849.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 1.58.877.684 I slot launch_slot_: id 0 | task 10536 | processing task, is_child = 0 1.59.928.297 I slot print_timing: id 0 | task 10536 | prompt eval time = 164.80 ms / 766 tokens ( 0.22 ms per token, 4647.95 tokens per second) 1.59.928.302 I slot print_timing: id 0 | task 10536 | eval time = 885.79 ms / 97 tokens ( 9.23 ms per token, 108.38 tokens per second) 1.59.928.303 I slot print_timing: id 0 | task 10536 | total time = 1050.60 ms / 863 tokens 1.59.928.305 I slot print_timing: id 0 | task 10536 | graphs reused = 10143 1.59.928.306 I slot print_timing: id 0 | task 10536 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.928.352 I slot release: id 0 | task 10536 | stop processing: n_tokens = 887, truncated = 0 1.59.959.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 119838578 1.59.959.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.915 MiB) 1.59.966.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.00.001.837 I slot launch_slot_: id 0 | task 10634 | processing task, is_child = 0 2.01.489.819 I slot print_timing: id 0 | task 10634 | prompt eval time = 180.66 ms / 846 tokens ( 0.21 ms per token, 4682.75 tokens per second) 2.01.489.825 I slot print_timing: id 0 | task 10634 | eval time = 1307.30 ms / 143 tokens ( 9.21 ms per token, 108.62 tokens per second) 2.01.489.826 I slot print_timing: id 0 | task 10634 | total time = 1487.97 ms / 989 tokens 2.01.489.827 I slot print_timing: id 0 | task 10634 | graphs reused = 10284 2.01.489.828 I slot print_timing: id 0 | task 10634 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.489.873 I slot release: id 0 | task 10634 | stop processing: n_tokens = 1013, truncated = 0 2.01.516.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1013, t_last = 121400098 2.01.516.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.01.555.174 I slot launch_slot_: id 0 | task 10778 | processing task, is_child = 0 2.02.402.808 I slot print_timing: id 0 | task 10778 | prompt eval time = 148.32 ms / 650 tokens ( 0.23 ms per token, 4382.36 tokens per second) 2.02.402.814 I slot print_timing: id 0 | task 10778 | eval time = 699.29 ms / 77 tokens ( 9.20 ms per token, 108.68 tokens per second) 2.02.402.815 I slot print_timing: id 0 | task 10778 | total time = 847.62 ms / 727 tokens 2.02.402.816 I slot print_timing: id 0 | task 10778 | graphs reused = 10359 2.02.402.817 I slot print_timing: id 0 | task 10778 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.402.857 I slot release: id 0 | task 10778 | stop processing: n_tokens = 751, truncated = 0 2.02.408.913 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 122313082 2.02.408.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.195 MiB) 2.02.414.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.02.454.050 I slot launch_slot_: id 0 | task 10856 | processing task, is_child = 0 2.03.100.944 I slot print_timing: id 0 | task 10856 | prompt eval time = 158.82 ms / 717 tokens ( 0.22 ms per token, 4514.63 tokens per second) 2.03.100.952 I slot print_timing: id 0 | task 10856 | eval time = 488.06 ms / 53 tokens ( 9.39 ms per token, 106.54 tokens per second) 2.03.100.953 I slot print_timing: id 0 | task 10856 | total time = 646.88 ms / 770 tokens 2.03.100.954 I slot print_timing: id 0 | task 10856 | graphs reused = 10409 2.03.100.955 I slot print_timing: id 0 | task 10856 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.100.997 I slot release: id 0 | task 10856 | stop processing: n_tokens = 794, truncated = 0 2.03.123.322 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 123011222 2.03.123.388 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 2.03.156.510 I slot launch_slot_: id 0 | task 10910 | processing task, is_child = 0 2.03.801.114 I slot print_timing: id 0 | task 10910 | prompt eval time = 109.49 ms / 494 tokens ( 0.22 ms per token, 4511.95 tokens per second) 2.03.801.119 I slot print_timing: id 0 | task 10910 | eval time = 535.10 ms / 59 tokens ( 9.23 ms per token, 108.39 tokens per second) 2.03.801.121 I slot print_timing: id 0 | task 10910 | total time = 644.58 ms / 553 tokens 2.03.801.121 I slot print_timing: id 0 | task 10910 | graphs reused = 10466 2.03.801.122 I slot print_timing: id 0 | task 10910 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.801.155 I slot release: id 0 | task 10910 | stop processing: n_tokens = 577, truncated = 0 2.03.824.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 123711380 2.03.824.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.03.849.460 I slot launch_slot_: id 0 | task 10970 | processing task, is_child = 0 2.04.470.706 I slot print_timing: id 0 | task 10970 | prompt eval time = 132.02 ms / 579 tokens ( 0.23 ms per token, 4385.67 tokens per second) 2.04.470.711 I slot print_timing: id 0 | task 10970 | eval time = 489.21 ms / 54 tokens ( 9.23 ms per token, 108.34 tokens per second) 2.04.470.712 I slot print_timing: id 0 | task 10970 | total time = 621.23 ms / 633 tokens 2.04.470.713 I slot print_timing: id 0 | task 10970 | graphs reused = 10518 2.04.470.714 I slot print_timing: id 0 | task 10970 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.470.751 I slot release: id 0 | task 10970 | stop processing: n_tokens = 657, truncated = 0 2.04.493.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 124380976 2.04.494.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.04.523.120 I slot launch_slot_: id 0 | task 11025 | processing task, is_child = 0 2.05.412.124 I slot print_timing: id 0 | task 11025 | prompt eval time = 204.88 ms / 919 tokens ( 0.22 ms per token, 4485.66 tokens per second) 2.05.412.129 I slot print_timing: id 0 | task 11025 | eval time = 684.11 ms / 73 tokens ( 9.50 ms per token, 105.25 tokens per second) 2.05.412.131 I slot print_timing: id 0 | task 11025 | total time = 888.99 ms / 992 tokens 2.05.412.131 I slot print_timing: id 0 | task 11025 | graphs reused = 10589 2.05.412.132 I slot print_timing: id 0 | task 11025 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.412.179 I slot release: id 0 | task 11025 | stop processing: n_tokens = 1016, truncated = 0 2.05.430.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 125322404 2.05.430.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 2.05.435.796 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 2.05.473.443 I slot launch_slot_: id 0 | task 11099 | processing task, is_child = 0 2.06.013.617 I slot print_timing: id 0 | task 11099 | prompt eval time = 187.09 ms / 865 tokens ( 0.22 ms per token, 4623.37 tokens per second) 2.06.013.623 I slot print_timing: id 0 | task 11099 | eval time = 353.06 ms / 39 tokens ( 9.29 ms per token, 107.63 tokens per second) 2.06.013.624 I slot print_timing: id 0 | task 11099 | total time = 540.16 ms / 904 tokens 2.06.013.625 I slot print_timing: id 0 | task 11099 | graphs reused = 10626 2.06.013.626 I slot print_timing: id 0 | task 11099 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.013.673 I slot release: id 0 | task 11099 | stop processing: n_tokens = 928, truncated = 0 2.06.034.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 125923898 2.06.034.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 2.06.039.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 2.06.074.307 I slot launch_slot_: id 0 | task 11139 | processing task, is_child = 0 2.09.172.574 I slot print_timing: id 0 | task 11139 | n_gen = 329, tg = 109.29 t/s, tg_3s = 109.62 t/s 2.12.180.636 I slot print_timing: id 0 | task 11139 | n_gen = 655, tg = 108.83 t/s, tg_3s = 108.38 t/s 2.14.197.105 I slot print_timing: id 0 | task 11139 | prompt eval time = 97.04 ms / 408 tokens ( 0.24 ms per token, 4204.37 tokens per second) 2.14.197.111 I slot print_timing: id 0 | task 11139 | eval time = 8025.74 ms / 871 tokens ( 9.22 ms per token, 108.40 tokens per second) 2.14.197.112 I slot print_timing: id 0 | task 11139 | total time = 8122.78 ms / 1279 tokens 2.14.197.113 I slot print_timing: id 0 | task 11139 | graphs reused = 11491 2.14.197.114 I slot print_timing: id 0 | task 11139 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.197.144 I slot release: id 0 | task 11139 | stop processing: n_tokens = 1303, truncated = 0 2.14.201.542 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1303, t_last = 134107369 2.14.201.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 2.14.208.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.14.262.554 I slot launch_slot_: id 0 | task 12011 | processing task, is_child = 0 2.14.862.340 I slot print_timing: id 0 | task 12011 | prompt eval time = 79.25 ms / 338 tokens ( 0.23 ms per token, 4264.77 tokens per second) 2.14.862.346 I slot print_timing: id 0 | task 12011 | eval time = 520.51 ms / 58 tokens ( 9.13 ms per token, 109.51 tokens per second) 2.14.862.347 I slot print_timing: id 0 | task 12011 | total time = 599.77 ms / 396 tokens 2.14.862.347 I slot print_timing: id 0 | task 12011 | graphs reused = 11547 2.14.862.348 I slot print_timing: id 0 | task 12011 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.862.375 I slot release: id 0 | task 12011 | stop processing: n_tokens = 422, truncated = 0 2.14.883.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 134772600 2.14.883.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 2.14.907.722 I slot launch_slot_: id 0 | task 12070 | processing task, is_child = 0 2.17.736.348 I slot print_timing: id 0 | task 12070 | prompt eval time = 80.18 ms / 363 tokens ( 0.22 ms per token, 4527.14 tokens per second) 2.17.736.353 I slot print_timing: id 0 | task 12070 | eval time = 2748.43 ms / 302 tokens ( 9.13 ms per token, 109.52 tokens per second) 2.17.736.354 I slot print_timing: id 0 | task 12070 | total time = 2828.61 ms / 665 tokens 2.17.736.355 I slot print_timing: id 0 | task 12070 | graphs reused = 11846 2.17.736.356 I slot print_timing: id 0 | task 12070 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.736.385 I slot release: id 0 | task 12070 | stop processing: n_tokens = 691, truncated = 0 2.17.740.551 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 691, t_last = 137646610 2.17.763.468 I slot launch_slot_: id 0 | task 12373 | processing task, is_child = 0 2.20.838.420 I slot print_timing: id 0 | task 12373 | n_gen = 330, tg = 109.58 t/s, tg_3s = 109.92 t/s 2.23.838.997 I slot print_timing: id 0 | task 12373 | n_gen = 657, tg = 109.28 t/s, tg_3s = 108.98 t/s 2.24.518.960 I slot print_timing: id 0 | task 12373 | prompt eval time = 72.64 ms / 317 tokens ( 0.23 ms per token, 4364.11 tokens per second) 2.24.518.966 I slot print_timing: id 0 | task 12373 | eval time = 6682.84 ms / 730 tokens ( 9.17 ms per token, 109.09 tokens per second) 2.24.518.967 I slot print_timing: id 0 | task 12373 | total time = 6755.48 ms / 1047 tokens 2.24.518.967 I slot print_timing: id 0 | task 12373 | graphs reused = 12571 2.24.518.968 I slot print_timing: id 0 | task 12373 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.518.995 I slot release: id 0 | task 12373 | stop processing: n_tokens = 1073, truncated = 0 2.24.544.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1073, t_last = 144429220 2.24.544.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 2.24.549.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 2.24.593.972 I slot launch_slot_: id 0 | task 13104 | processing task, is_child = 0 2.27.697.038 I slot print_timing: id 0 | task 13104 | n_gen = 328, tg = 108.76 t/s, tg_3s = 109.10 t/s 2.30.704.046 I slot print_timing: id 0 | task 13104 | n_gen = 654, tg = 108.59 t/s, tg_3s = 108.41 t/s 2.33.709.542 I slot print_timing: id 0 | task 13104 | n_gen = 975, tg = 107.99 t/s, tg_3s = 106.80 t/s 2.34.169.645 I slot print_timing: id 0 | task 13104 | prompt eval time = 96.57 ms / 389 tokens ( 0.25 ms per token, 4028.33 tokens per second) 2.34.169.651 I slot print_timing: id 0 | task 13104 | eval time = 9479.09 ms / 1024 tokens ( 9.27 ms per token, 107.92 tokens per second) 2.34.169.652 I slot print_timing: id 0 | task 13104 | total time = 9575.65 ms / 1413 tokens 2.34.169.653 I slot print_timing: id 0 | task 13104 | graphs reused = 13589 2.34.169.653 I slot print_timing: id 0 | task 13104 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.169.682 I slot release: id 0 | task 13104 | stop processing: n_tokens = 1437, truncated = 0 2.34.173.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1437, t_last = 154079908 2.34.173.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 2.34.182.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.788 MiB) 2.34.234.155 I slot launch_slot_: id 0 | task 14129 | processing task, is_child = 0 2.34.582.290 I slot print_timing: id 0 | task 14129 | prompt eval time = 72.08 ms / 300 tokens ( 0.24 ms per token, 4161.75 tokens per second) 2.34.582.296 I slot print_timing: id 0 | task 14129 | eval time = 276.03 ms / 31 tokens ( 9.20 ms per token, 108.68 tokens per second) 2.34.582.297 I slot print_timing: id 0 | task 14129 | total time = 348.12 ms / 331 tokens 2.34.582.298 I slot print_timing: id 0 | task 14129 | graphs reused = 13618 2.34.582.299 I slot print_timing: id 0 | task 14129 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.582.325 I slot release: id 0 | task 14129 | stop processing: n_tokens = 355, truncated = 0 2.34.606.710 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 154492550 2.34.606.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 109.853 MiB) 2.34.625.867 I slot launch_slot_: id 0 | task 14161 | processing task, is_child = 0 2.37.711.064 I slot print_timing: id 0 | task 14161 | n_gen = 329, tg = 109.11 t/s, tg_3s = 109.44 t/s 2.40.713.452 I slot print_timing: id 0 | task 14161 | n_gen = 655, tg = 108.85 t/s, tg_3s = 108.58 t/s 2.43.715.553 I slot print_timing: id 0 | task 14161 | n_gen = 976, tg = 108.21 t/s, tg_3s = 106.93 t/s 2.44.006.087 I slot print_timing: id 0 | task 14161 | prompt eval time = 79.11 ms / 341 tokens ( 0.23 ms per token, 4310.62 tokens per second) 2.44.006.092 I slot print_timing: id 0 | task 14161 | eval time = 9301.10 ms / 1007 tokens ( 9.25 ms per token, 108.16 tokens per second) 2.44.006.093 I slot print_timing: id 0 | task 14161 | total time = 9380.20 ms / 1348 tokens 2.44.006.094 I slot print_timing: id 0 | task 14161 | graphs reused = 14619 2.44.006.095 I slot print_timing: id 0 | task 14161 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.006.123 I slot release: id 0 | task 14161 | stop processing: n_tokens = 1372, truncated = 0 2.44.030.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1372, t_last = 163916348 2.44.030.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 2.44.085.765 I slot launch_slot_: id 0 | task 15169 | processing task, is_child = 0 2.45.384.387 I slot print_timing: id 0 | task 15169 | prompt eval time = 73.67 ms / 332 tokens ( 0.22 ms per token, 4506.28 tokens per second) 2.45.384.392 I slot print_timing: id 0 | task 15169 | eval time = 1224.93 ms / 136 tokens ( 9.07 ms per token, 110.21 tokens per second) 2.45.384.393 I slot print_timing: id 0 | task 15169 | total time = 1298.60 ms / 468 tokens 2.45.384.394 I slot print_timing: id 0 | task 15169 | graphs reused = 14753 2.45.384.395 I slot print_timing: id 0 | task 15169 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.384.423 I slot release: id 0 | task 15169 | stop processing: n_tokens = 492, truncated = 0 2.45.404.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 165294648 2.45.405.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.45.430.154 I slot launch_slot_: id 0 | task 15306 | processing task, is_child = 0 2.46.060.673 I slot print_timing: id 0 | task 15306 | prompt eval time = 65.32 ms / 269 tokens ( 0.24 ms per token, 4118.06 tokens per second) 2.46.060.679 I slot print_timing: id 0 | task 15306 | eval time = 565.18 ms / 63 tokens ( 9.12 ms per token, 109.70 tokens per second) 2.46.060.680 I slot print_timing: id 0 | task 15306 | total time = 630.50 ms / 332 tokens 2.46.060.681 I slot print_timing: id 0 | task 15306 | graphs reused = 14814 2.46.060.682 I slot print_timing: id 0 | task 15306 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.060.707 I slot release: id 0 | task 15306 | stop processing: n_tokens = 356, truncated = 0 2.46.087.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 356, t_last = 165970933 2.46.087.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 2.46.106.642 I slot launch_slot_: id 0 | task 15370 | processing task, is_child = 0 2.47.338.653 I slot print_timing: id 0 | task 15370 | prompt eval time = 79.40 ms / 341 tokens ( 0.23 ms per token, 4294.60 tokens per second) 2.47.338.658 I slot print_timing: id 0 | task 15370 | eval time = 1152.59 ms / 128 tokens ( 9.08 ms per token, 110.19 tokens per second) 2.47.338.659 I slot print_timing: id 0 | task 15370 | total time = 1231.99 ms / 469 tokens 2.47.338.660 I slot print_timing: id 0 | task 15370 | graphs reused = 14940 2.47.338.661 I slot print_timing: id 0 | task 15370 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.338.689 I slot release: id 0 | task 15370 | stop processing: n_tokens = 493, truncated = 0 2.47.366.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 167248914 2.47.383.704 I slot launch_slot_: id 0 | task 15499 | processing task, is_child = 0 2.48.751.463 I slot print_timing: id 0 | task 15499 | prompt eval time = 79.61 ms / 343 tokens ( 0.23 ms per token, 4308.50 tokens per second) 2.48.751.469 I slot print_timing: id 0 | task 15499 | eval time = 1288.13 ms / 143 tokens ( 9.07 ms per token, 110.24 tokens per second) 2.48.751.470 I slot print_timing: id 0 | task 15499 | total time = 1367.74 ms / 486 tokens 2.48.751.471 I slot print_timing: id 0 | task 15499 | graphs reused = 15081 2.48.751.471 I slot print_timing: id 0 | task 15499 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.751.498 I slot release: id 0 | task 15499 | stop processing: n_tokens = 510, truncated = 0 2.48.755.533 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 168661723 2.48.755.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 2.48.778.448 I slot launch_slot_: id 0 | task 15643 | processing task, is_child = 0 2.51.861.030 I slot print_timing: id 0 | task 15643 | n_gen = 330, tg = 109.56 t/s, tg_3s = 109.89 t/s 2.54.867.397 I slot print_timing: id 0 | task 15643 | n_gen = 657, tg = 109.16 t/s, tg_3s = 108.77 t/s 2.57.368.497 I slot print_timing: id 0 | task 15643 | prompt eval time = 79.60 ms / 347 tokens ( 0.23 ms per token, 4359.41 tokens per second) 2.57.368.503 I slot print_timing: id 0 | task 15643 | eval time = 8510.44 ms / 924 tokens ( 9.22 ms per token, 108.46 tokens per second) 2.57.368.504 I slot print_timing: id 0 | task 15643 | total time = 8590.03 ms / 1271 tokens 2.57.368.505 I slot print_timing: id 0 | task 15643 | graphs reused = 15999 2.57.368.506 I slot print_timing: id 0 | task 15643 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.368.533 I slot release: id 0 | task 15643 | stop processing: n_tokens = 1295, truncated = 0 2.57.391.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1295, t_last = 177278758 2.57.391.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 2.57.397.311 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 2.57.402.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 2.57.456.187 I slot launch_slot_: id 0 | task 16568 | processing task, is_child = 0 3.00.538.973 I slot print_timing: id 0 | task 16568 | n_gen = 331, tg = 109.67 t/s, tg_3s = 110.00 t/s 3.03.540.640 I slot print_timing: id 0 | task 16568 | n_gen = 658, tg = 109.30 t/s, tg_3s = 108.94 t/s 3.06.549.114 I slot print_timing: id 0 | task 16568 | n_gen = 980, tg = 108.55 t/s, tg_3s = 107.03 t/s 3.06.961.601 I slot print_timing: id 0 | task 16568 | prompt eval time = 73.70 ms / 332 tokens ( 0.22 ms per token, 4504.87 tokens per second) 3.06.961.607 I slot print_timing: id 0 | task 16568 | eval time = 9431.70 ms / 1024 tokens ( 9.22 ms per token, 108.46 tokens per second) 3.06.961.608 I slot print_timing: id 0 | task 16568 | total time = 9505.40 ms / 1356 tokens 3.06.961.609 I slot print_timing: id 0 | task 16568 | graphs reused = 17017 3.06.961.610 I slot print_timing: id 0 | task 16568 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.961.639 I slot release: id 0 | task 16568 | stop processing: n_tokens = 1380, truncated = 0 3.06.966.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1380, t_last = 186871864 3.06.966.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 3.06.972.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 3.07.027.165 I slot launch_slot_: id 0 | task 17593 | processing task, is_child = 0 3.07.692.413 I slot print_timing: id 0 | task 17593 | prompt eval time = 73.31 ms / 332 tokens ( 0.22 ms per token, 4528.59 tokens per second) 3.07.692.418 I slot print_timing: id 0 | task 17593 | eval time = 591.92 ms / 66 tokens ( 9.11 ms per token, 109.81 tokens per second) 3.07.692.420 I slot print_timing: id 0 | task 17593 | total time = 665.23 ms / 398 tokens 3.07.692.420 I slot print_timing: id 0 | task 17593 | graphs reused = 17081 3.07.692.421 I slot print_timing: id 0 | task 17593 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.692.449 I slot release: id 0 | task 17593 | stop processing: n_tokens = 422, truncated = 0 3.07.716.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 187602674 3.07.730.809 I slot launch_slot_: id 0 | task 17660 | processing task, is_child = 0 3.10.811.986 I slot print_timing: id 0 | task 17660 | n_gen = 330, tg = 109.61 t/s, tg_3s = 109.95 t/s 3.13.818.018 I slot print_timing: id 0 | task 17660 | n_gen = 655, tg = 108.86 t/s, tg_3s = 108.12 t/s 3.16.826.820 I slot print_timing: id 0 | task 17660 | n_gen = 977, tg = 108.25 t/s, tg_3s = 107.02 t/s 3.17.268.646 I slot print_timing: id 0 | task 17660 | prompt eval time = 79.75 ms / 354 tokens ( 0.23 ms per token, 4439.09 tokens per second) 3.17.268.654 I slot print_timing: id 0 | task 17660 | eval time = 9458.08 ms / 1024 tokens ( 9.25 ms per token, 108.16 tokens per second) 3.17.268.655 I slot print_timing: id 0 | task 17660 | total time = 9537.82 ms / 1378 tokens 3.17.268.656 I slot print_timing: id 0 | task 17660 | graphs reused = 18099 3.17.268.657 I slot print_timing: id 0 | task 17660 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.268.686 I slot release: id 0 | task 17660 | stop processing: n_tokens = 1402, truncated = 0 3.17.293.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 197178911 3.17.293.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 3.17.299.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.259 MiB) 3.17.354.566 I slot launch_slot_: id 0 | task 18685 | processing task, is_child = 0 3.19.882.065 I slot print_timing: id 0 | task 18685 | prompt eval time = 80.37 ms / 354 tokens ( 0.23 ms per token, 4404.57 tokens per second) 3.19.882.071 I slot print_timing: id 0 | task 18685 | eval time = 2447.11 ms / 269 tokens ( 9.13 ms per token, 109.52 tokens per second) 3.19.882.072 I slot print_timing: id 0 | task 18685 | total time = 2527.48 ms / 623 tokens 3.19.882.073 I slot print_timing: id 0 | task 18685 | graphs reused = 18365 3.19.882.074 I slot print_timing: id 0 | task 18685 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.882.103 I slot release: id 0 | task 18685 | stop processing: n_tokens = 647, truncated = 0 3.19.908.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 199792328 3.19.908.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 3.19.938.010 I slot launch_slot_: id 0 | task 18955 | processing task, is_child = 0 3.23.017.839 I slot print_timing: id 0 | task 18955 | n_gen = 328, tg = 108.98 t/s, tg_3s = 109.31 t/s 3.26.020.867 I slot print_timing: id 0 | task 18955 | n_gen = 655, tg = 108.93 t/s, tg_3s = 108.89 t/s 3.29.020.885 I slot print_timing: id 0 | task 18955 | n_gen = 976, tg = 108.29 t/s, tg_3s = 107.00 t/s 3.29.471.032 I slot print_timing: id 0 | task 18955 | prompt eval time = 79.15 ms / 339 tokens ( 0.23 ms per token, 4283.01 tokens per second) 3.29.471.038 I slot print_timing: id 0 | task 18955 | eval time = 9453.86 ms / 1024 tokens ( 9.24 ms per token, 108.21 tokens per second) 3.29.471.039 I slot print_timing: id 0 | task 18955 | total time = 9533.01 ms / 1363 tokens 3.29.471.040 I slot print_timing: id 0 | task 18955 | graphs reused = 19383 3.29.471.041 I slot print_timing: id 0 | task 18955 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.471.070 I slot release: id 0 | task 18955 | stop processing: n_tokens = 1387, truncated = 0 3.29.475.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1387, t_last = 209381295 3.29.475.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 3.29.483.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.074 MiB) 3.29.537.750 I slot launch_slot_: id 0 | task 19980 | processing task, is_child = 0 3.32.583.306 I slot print_timing: id 0 | task 19980 | prompt eval time = 79.76 ms / 351 tokens ( 0.23 ms per token, 4400.70 tokens per second) 3.32.583.311 I slot print_timing: id 0 | task 19980 | eval time = 2965.78 ms / 326 tokens ( 9.13 ms per token, 109.58 tokens per second) 3.32.583.312 I slot print_timing: id 0 | task 19980 | total time = 3045.54 ms / 677 tokens 3.32.583.313 I slot print_timing: id 0 | task 19980 | graphs reused = 19706 3.32.583.314 I slot print_timing: id 0 | task 19980 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.583.343 I slot release: id 0 | task 19980 | stop processing: n_tokens = 701, truncated = 0 3.32.607.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 701, t_last = 212493568 3.32.629.976 I slot launch_slot_: id 0 | task 20307 | processing task, is_child = 0 3.34.008.855 I slot print_timing: id 0 | task 20307 | prompt eval time = 73.07 ms / 325 tokens ( 0.22 ms per token, 4447.91 tokens per second) 3.34.008.860 I slot print_timing: id 0 | task 20307 | eval time = 1305.80 ms / 145 tokens ( 9.07 ms per token, 110.28 tokens per second) 3.34.008.861 I slot print_timing: id 0 | task 20307 | total time = 1378.86 ms / 470 tokens 3.34.008.862 I slot print_timing: id 0 | task 20307 | graphs reused = 19849 3.34.008.863 I slot print_timing: id 0 | task 20307 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.008.890 I slot release: id 0 | task 20307 | stop processing: n_tokens = 494, truncated = 0 3.34.022.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 213919115 3.34.022.844 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 221.423 MiB) 3.34.053.831 I slot launch_slot_: id 0 | task 20453 | processing task, is_child = 0 3.34.501.068 I slot print_timing: id 0 | task 20453 | prompt eval time = 72.29 ms / 308 tokens ( 0.23 ms per token, 4260.38 tokens per second) 3.34.501.074 I slot print_timing: id 0 | task 20453 | eval time = 374.93 ms / 42 tokens ( 9.14 ms per token, 109.35 tokens per second) 3.34.501.075 I slot print_timing: id 0 | task 20453 | total time = 447.22 ms / 350 tokens 3.34.501.075 I slot print_timing: id 0 | task 20453 | graphs reused = 19889 3.34.501.076 I slot print_timing: id 0 | task 20453 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.501.104 I slot release: id 0 | task 20453 | stop processing: n_tokens = 374, truncated = 0 3.34.528.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 374, t_last = 214411329 3.34.542.108 I slot launch_slot_: id 0 | task 20496 | processing task, is_child = 0 3.37.622.256 I slot print_timing: id 0 | task 20496 | n_gen = 330, tg = 109.65 t/s, tg_3s = 109.98 t/s 3.38.955.985 I slot print_timing: id 0 | task 20496 | prompt eval time = 79.56 ms / 349 tokens ( 0.23 ms per token, 4386.46 tokens per second) 3.38.955.990 I slot print_timing: id 0 | task 20496 | eval time = 4334.30 ms / 475 tokens ( 9.14 ms per token, 109.36 tokens per second) 3.38.955.991 I slot print_timing: id 0 | task 20496 | total time = 4413.86 ms / 824 tokens 3.38.955.993 I slot print_timing: id 0 | task 20496 | graphs reused = 20360 3.38.955.994 I slot print_timing: id 0 | task 20496 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.956.023 I slot release: id 0 | task 20496 | stop processing: n_tokens = 848, truncated = 0 3.38.971.455 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 218866248 3.38.971.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 3.39.004.017 I slot launch_slot_: id 0 | task 20972 | processing task, is_child = 0 3.40.462.850 I slot print_timing: id 0 | task 20972 | prompt eval time = 79.61 ms / 371 tokens ( 0.21 ms per token, 4660.28 tokens per second) 3.40.462.856 I slot print_timing: id 0 | task 20972 | eval time = 1379.21 ms / 152 tokens ( 9.13 ms per token, 109.48 tokens per second) 3.40.462.857 I slot print_timing: id 0 | task 20972 | total time = 1458.81 ms / 523 tokens 3.40.462.858 I slot print_timing: id 0 | task 20972 | graphs reused = 20509 3.40.462.859 I slot print_timing: id 0 | task 20972 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.462.889 I slot release: id 0 | task 20972 | stop processing: n_tokens = 552, truncated = 0 3.40.487.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 552, t_last = 220373114 3.40.487.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 3.40.511.619 I slot launch_slot_: id 0 | task 21125 | processing task, is_child = 0 3.43.590.324 I slot print_timing: id 0 | task 21125 | n_gen = 331, tg = 109.77 t/s, tg_3s = 110.10 t/s 3.46.590.486 I slot print_timing: id 0 | task 21125 | n_gen = 658, tg = 109.38 t/s, tg_3s = 108.99 t/s 3.47.958.534 I slot print_timing: id 0 | task 21125 | prompt eval time = 72.27 ms / 303 tokens ( 0.24 ms per token, 4192.61 tokens per second) 3.47.958.540 I slot print_timing: id 0 | task 21125 | eval time = 7374.63 ms / 805 tokens ( 9.17 ms per token, 109.02 tokens per second) 3.47.958.541 I slot print_timing: id 0 | task 21125 | total time = 7446.90 ms / 1108 tokens 3.47.958.542 I slot print_timing: id 0 | task 21125 | graphs reused = 21309 3.47.958.543 I slot print_timing: id 0 | task 21125 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.958.570 I slot release: id 0 | task 21125 | stop processing: n_tokens = 1132, truncated = 0 3.47.978.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1132, t_last = 227868795 3.47.978.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 3.47.982.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 3.47.987.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 3.48.031.899 I slot launch_slot_: id 0 | task 21931 | processing task, is_child = 0 3.50.260.957 I slot print_timing: id 0 | task 21931 | prompt eval time = 71.93 ms / 312 tokens ( 0.23 ms per token, 4337.73 tokens per second) 3.50.260.962 I slot print_timing: id 0 | task 21931 | eval time = 2157.11 ms / 238 tokens ( 9.10 ms per token, 109.87 tokens per second) 3.50.260.963 I slot print_timing: id 0 | task 21931 | total time = 2229.04 ms / 550 tokens 3.50.260.964 I slot print_timing: id 0 | task 21931 | graphs reused = 21544 3.50.260.966 I slot print_timing: id 0 | task 21931 | graph reallocs = 0 / 0 (same size) / (changed size) 3.50.260.996 I slot release: id 0 | task 21931 | stop processing: n_tokens = 574, truncated = 0 3.50.281.842 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 574, t_last = 230171221 3.50.281.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 3.50.307.698 I slot launch_slot_: id 0 | task 22170 | processing task, is_child = 0 3.53.380.290 I slot print_timing: id 0 | task 22170 | n_gen = 328, tg = 109.00 t/s, tg_3s = 109.33 t/s 3.56.382.339 I slot print_timing: id 0 | task 22170 | n_gen = 652, tg = 108.46 t/s, tg_3s = 107.93 t/s 3.59.388.347 I slot print_timing: id 0 | task 22170 | n_gen = 974, tg = 108.01 t/s, tg_3s = 107.12 t/s 3.59.858.460 I slot print_timing: id 0 | task 22170 | prompt eval time = 72.46 ms / 311 tokens ( 0.23 ms per token, 4292.08 tokens per second) 3.59.858.466 I slot print_timing: id 0 | task 22170 | eval time = 9478.29 ms / 1024 tokens ( 9.27 ms per token, 107.93 tokens per second) 3.59.858.467 I slot print_timing: id 0 | task 22170 | total time = 9550.75 ms / 1335 tokens 3.59.858.468 I slot print_timing: id 0 | task 22170 | graphs reused = 22562 3.59.858.469 I slot print_timing: id 0 | task 22170 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.858.496 I slot release: id 0 | task 22170 | stop processing: n_tokens = 1359, truncated = 0 3.59.886.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1359, t_last = 239768721 3.59.886.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 3.59.890.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 3.59.894.774 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 3.59.947.604 I slot launch_slot_: id 0 | task 23195 | processing task, is_child = 0 4.01.273.624 I slot print_timing: id 0 | task 23195 | prompt eval time = 73.14 ms / 331 tokens ( 0.22 ms per token, 4525.88 tokens per second) 4.01.273.629 I slot print_timing: id 0 | task 23195 | eval time = 1252.87 ms / 139 tokens ( 9.08 ms per token, 110.15 tokens per second) 4.01.273.630 I slot print_timing: id 0 | task 23195 | total time = 1326.00 ms / 470 tokens 4.01.273.631 I slot print_timing: id 0 | task 23195 | graphs reused = 22699 4.01.273.632 I slot print_timing: id 0 | task 23195 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.273.659 I slot release: id 0 | task 23195 | stop processing: n_tokens = 494, truncated = 0 4.01.292.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 241183884 4.01.292.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 4.01.315.434 I slot launch_slot_: id 0 | task 23335 | processing task, is_child = 0 4.04.396.452 I slot print_timing: id 0 | task 23335 | n_gen = 330, tg = 109.40 t/s, tg_3s = 109.73 t/s 4.07.400.889 I slot print_timing: id 0 | task 23335 | n_gen = 657, tg = 109.12 t/s, tg_3s = 108.84 t/s 4.10.408.002 I slot print_timing: id 0 | task 23335 | n_gen = 975, tg = 107.99 t/s, tg_3s = 105.75 t/s 4.10.868.285 I slot print_timing: id 0 | task 23335 | prompt eval time = 73.58 ms / 335 tokens ( 0.22 ms per token, 4552.56 tokens per second) 4.10.868.291 I slot print_timing: id 0 | task 23335 | eval time = 9479.25 ms / 1024 tokens ( 9.27 ms per token, 107.92 tokens per second) 4.10.868.292 I slot print_timing: id 0 | task 23335 | total time = 9552.84 ms / 1359 tokens 4.10.868.293 I slot print_timing: id 0 | task 23335 | graphs reused = 23717 4.10.868.294 I slot print_timing: id 0 | task 23335 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.868.323 I slot release: id 0 | task 23335 | stop processing: n_tokens = 1383, truncated = 0 4.10.897.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1383, t_last = 250778548 4.10.897.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 4.10.902.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 4.10.957.249 I slot launch_slot_: id 0 | task 24360 | processing task, is_child = 0 4.11.369.112 I slot print_timing: id 0 | task 24360 | prompt eval time = 73.42 ms / 331 tokens ( 0.22 ms per token, 4508.00 tokens per second) 4.11.369.118 I slot print_timing: id 0 | task 24360 | eval time = 338.42 ms / 38 tokens ( 9.15 ms per token, 109.33 tokens per second) 4.11.369.119 I slot print_timing: id 0 | task 24360 | total time = 411.85 ms / 369 tokens 4.11.369.120 I slot print_timing: id 0 | task 24360 | graphs reused = 23753 4.11.369.121 I slot print_timing: id 0 | task 24360 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.369.146 I slot release: id 0 | task 24360 | stop processing: n_tokens = 393, truncated = 0 4.11.395.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 251279372 4.11.395.605 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 4.11.415.104 I slot launch_slot_: id 0 | task 24399 | processing task, is_child = 0 4.12.659.451 I slot print_timing: id 0 | task 24399 | prompt eval time = 73.14 ms / 328 tokens ( 0.22 ms per token, 4484.30 tokens per second) 4.12.659.457 I slot print_timing: id 0 | task 24399 | eval time = 1171.19 ms / 130 tokens ( 9.08 ms per token, 110.14 tokens per second) 4.12.659.458 I slot print_timing: id 0 | task 24399 | total time = 1244.33 ms / 458 tokens 4.12.659.459 I slot print_timing: id 0 | task 24399 | graphs reused = 23881 4.12.659.460 I slot print_timing: id 0 | task 24399 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.659.488 I slot release: id 0 | task 24399 | stop processing: n_tokens = 482, truncated = 0 4.12.683.698 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 252569713 4.12.683.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 4.12.704.806 I slot launch_slot_: id 0 | task 24530 | processing task, is_child = 0 4.13.697.358 I slot print_timing: id 0 | task 24530 | prompt eval time = 73.48 ms / 331 tokens ( 0.22 ms per token, 4504.57 tokens per second) 4.13.697.364 I slot print_timing: id 0 | task 24530 | eval time = 919.06 ms / 102 tokens ( 9.10 ms per token, 109.90 tokens per second) 4.13.697.365 I slot print_timing: id 0 | task 24530 | total time = 992.54 ms / 433 tokens 4.13.697.366 I slot print_timing: id 0 | task 24530 | graphs reused = 23981 4.13.697.366 I slot print_timing: id 0 | task 24530 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.697.393 I slot release: id 0 | task 24530 | stop processing: n_tokens = 457, truncated = 0 4.13.719.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 253607618 4.13.719.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 4.13.740.723 I slot launch_slot_: id 0 | task 24633 | processing task, is_child = 0 4.14.304.998 I slot print_timing: id 0 | task 24633 | prompt eval time = 79.50 ms / 348 tokens ( 0.23 ms per token, 4377.41 tokens per second) 4.14.305.004 I slot print_timing: id 0 | task 24633 | eval time = 484.76 ms / 54 tokens ( 9.15 ms per token, 109.33 tokens per second) 4.14.305.005 I slot print_timing: id 0 | task 24633 | total time = 564.26 ms / 402 tokens 4.14.305.006 I slot print_timing: id 0 | task 24633 | graphs reused = 24033 4.14.305.007 I slot print_timing: id 0 | task 24633 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.305.035 I slot release: id 0 | task 24633 | stop processing: n_tokens = 426, truncated = 0 4.14.324.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 254215260 4.14.324.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.694 MiB) 4.14.344.570 I slot launch_slot_: id 0 | task 24688 | processing task, is_child = 0 4.14.893.348 I slot print_timing: id 0 | task 24688 | prompt eval time = 73.54 ms / 332 tokens ( 0.22 ms per token, 4514.49 tokens per second) 4.14.893.353 I slot print_timing: id 0 | task 24688 | eval time = 475.22 ms / 53 tokens ( 9.14 ms per token, 109.42 tokens per second) 4.14.893.354 I slot print_timing: id 0 | task 24688 | total time = 548.76 ms / 385 tokens 4.14.893.355 I slot print_timing: id 0 | task 24688 | graphs reused = 24084 4.14.893.356 I slot print_timing: id 0 | task 24688 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.893.383 I slot release: id 0 | task 24688 | stop processing: n_tokens = 411, truncated = 0 4.14.907.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 254803608 4.14.907.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.412 MiB) 4.14.926.606 I slot launch_slot_: id 0 | task 24742 | processing task, is_child = 0 4.18.010.323 I slot print_timing: id 0 | task 24742 | n_gen = 330, tg = 109.51 t/s, tg_3s = 109.84 t/s 4.21.015.949 I slot print_timing: id 0 | task 24742 | n_gen = 657, tg = 109.15 t/s, tg_3s = 108.80 t/s 4.21.571.031 I slot print_timing: id 0 | task 24742 | prompt eval time = 79.45 ms / 339 tokens ( 0.23 ms per token, 4267.00 tokens per second) 4.21.571.037 I slot print_timing: id 0 | task 24742 | eval time = 6564.96 ms / 716 tokens ( 9.18 ms per token, 108.91 tokens per second) 4.21.571.038 I slot print_timing: id 0 | task 24742 | total time = 6644.41 ms / 1055 tokens 4.21.571.039 I slot print_timing: id 0 | task 24742 | graphs reused = 24795 4.21.571.040 I slot print_timing: id 0 | task 24742 | graph reallocs = 0 / 0 (same size) / (changed size) 4.21.571.069 I slot release: id 0 | task 24742 | stop processing: n_tokens = 1079, truncated = 0 4.21.592.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 261481294 4.21.592.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.694 MiB) 4.21.597.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 4.21.637.060 I slot launch_slot_: id 0 | task 25459 | processing task, is_child = 0 4.22.001.472 I slot print_timing: id 0 | task 25459 | prompt eval time = 79.48 ms / 343 tokens ( 0.23 ms per token, 4315.33 tokens per second) 4.22.001.478 I slot print_timing: id 0 | task 25459 | eval time = 284.91 ms / 32 tokens ( 9.19 ms per token, 108.81 tokens per second) 4.22.001.479 I slot print_timing: id 0 | task 25459 | total time = 364.40 ms / 375 tokens 4.22.001.479 I slot print_timing: id 0 | task 25459 | graphs reused = 24825 4.22.001.480 I slot print_timing: id 0 | task 25459 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.001.510 I slot release: id 0 | task 25459 | stop processing: n_tokens = 399, truncated = 0 4.22.028.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 261911735 4.22.029.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.632 MiB) 4.22.049.221 I slot launch_slot_: id 0 | task 25492 | processing task, is_child = 0 4.25.135.924 I slot print_timing: id 0 | task 25492 | n_gen = 330, tg = 109.43 t/s, tg_3s = 109.76 t/s 4.28.139.212 I slot print_timing: id 0 | task 25492 | n_gen = 656, tg = 108.99 t/s, tg_3s = 108.55 t/s 4.30.502.245 I slot print_timing: id 0 | task 25492 | prompt eval time = 80.18 ms / 360 tokens ( 0.22 ms per token, 4490.12 tokens per second) 4.30.502.251 I slot print_timing: id 0 | task 25492 | eval time = 8372.83 ms / 909 tokens ( 9.22 ms per token, 108.45 tokens per second) 4.30.502.252 I slot print_timing: id 0 | task 25492 | total time = 8453.01 ms / 1269 tokens 4.30.502.252 I slot print_timing: id 0 | task 25492 | graphs reused = 25728 4.30.502.253 I slot print_timing: id 0 | task 25492 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.502.284 I slot release: id 0 | task 25492 | stop processing: n_tokens = 1293, truncated = 0 4.30.523.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1293, t_last = 270412509 4.30.523.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 73.444 MiB) 4.30.527.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.320 MiB) 4.30.579.165 I slot launch_slot_: id 0 | task 26402 | processing task, is_child = 0 4.31.667.610 I slot print_timing: id 0 | task 26402 | prompt eval time = 79.50 ms / 341 tokens ( 0.23 ms per token, 4289.52 tokens per second) 4.31.667.616 I slot print_timing: id 0 | task 26402 | eval time = 1008.93 ms / 112 tokens ( 9.09 ms per token, 110.02 tokens per second) 4.31.667.617 I slot print_timing: id 0 | task 26402 | total time = 1088.42 ms / 453 tokens 4.31.667.618 I slot print_timing: id 0 | task 26402 | graphs reused = 25838 4.31.667.619 I slot print_timing: id 0 | task 26402 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.667.648 I slot release: id 0 | task 26402 | stop processing: n_tokens = 477, truncated = 0 4.31.691.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 477, t_last = 271577874 4.31.691.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.039 MiB) 4.31.713.413 I slot launch_slot_: id 0 | task 26515 | processing task, is_child = 0 4.34.799.657 I slot print_timing: id 0 | task 26515 | n_gen = 330, tg = 109.44 t/s, tg_3s = 109.77 t/s 4.37.254.193 I slot print_timing: id 0 | task 26515 | prompt eval time = 80.08 ms / 358 tokens ( 0.22 ms per token, 4470.75 tokens per second) 4.37.254.199 I slot print_timing: id 0 | task 26515 | eval time = 5460.69 ms / 597 tokens ( 9.16 ms per token, 109.14 tokens per second) 4.37.254.200 I slot print_timing: id 0 | task 26515 | total time = 5540.77 ms / 955 tokens 4.37.254.201 I slot print_timing: id 0 | task 26515 | graphs reused = 26431 4.37.254.202 I slot print_timing: id 0 | task 26515 | graph reallocs = 0 / 0 (same size) / (changed size) 4.37.254.232 I slot release: id 0 | task 26515 | stop processing: n_tokens = 979, truncated = 0 4.37.269.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 979, t_last = 277164457 4.37.269.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.788 MiB) 4.37.274.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.350 MiB) 4.37.310.705 I slot launch_slot_: id 0 | task 27113 | processing task, is_child = 0 4.40.397.706 I slot print_timing: id 0 | task 27113 | n_gen = 330, tg = 109.41 t/s, tg_3s = 109.75 t/s 4.43.400.047 I slot print_timing: id 0 | task 27113 | n_gen = 656, tg = 109.00 t/s, tg_3s = 108.58 t/s 4.46.401.913 I slot print_timing: id 0 | task 27113 | n_gen = 977, tg = 108.31 t/s, tg_3s = 106.93 t/s 4.46.843.666 I slot print_timing: id 0 | task 27113 | prompt eval time = 80.04 ms / 358 tokens ( 0.22 ms per token, 4472.71 tokens per second) 4.46.843.671 I slot print_timing: id 0 | task 27113 | eval time = 9452.90 ms / 1024 tokens ( 9.24 ms per token, 108.22 tokens per second) 4.46.843.672 I slot print_timing: id 0 | task 27113 | total time = 9532.94 ms / 1382 tokens 4.46.843.673 I slot print_timing: id 0 | task 27113 | graphs reused = 27449 4.46.843.674 I slot print_timing: id 0 | task 27113 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.843.703 I slot release: id 0 | task 27113 | stop processing: n_tokens = 1409, truncated = 0 4.46.864.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1409, t_last = 286753928 4.46.864.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 4.46.868.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.788 MiB) 4.46.873.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 4.46.923.107 I slot launch_slot_: id 0 | task 28138 | processing task, is_child = 0 4.48.373.456 I slot print_timing: id 0 | task 28138 | prompt eval time = 97.18 ms / 387 tokens ( 0.25 ms per token, 3982.38 tokens per second) 4.48.373.461 I slot print_timing: id 0 | task 28138 | eval time = 1353.15 ms / 149 tokens ( 9.14 ms per token, 109.37 tokens per second) 4.48.373.462 I slot print_timing: id 0 | task 28138 | total time = 1450.33 ms / 536 tokens 4.48.373.463 I slot print_timing: id 0 | task 28138 | graphs reused = 27595 4.48.373.463 I slot print_timing: id 0 | task 28138 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.373.491 I slot release: id 0 | task 28138 | stop processing: n_tokens = 560, truncated = 0 4.48.401.049 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 288283716 4.48.401.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.756 MiB) 4.48.424.525 I slot launch_slot_: id 0 | task 28288 | processing task, is_child = 0 4.49.062.748 I slot print_timing: id 0 | task 28288 | prompt eval time = 73.37 ms / 333 tokens ( 0.22 ms per token, 4538.45 tokens per second) 4.49.062.754 I slot print_timing: id 0 | task 28288 | eval time = 564.83 ms / 61 tokens ( 9.41 ms per token, 106.23 tokens per second) 4.49.062.755 I slot print_timing: id 0 | task 28288 | total time = 638.21 ms / 394 tokens 4.49.062.756 I slot print_timing: id 0 | task 28288 | graphs reused = 27654 4.49.062.757 I slot print_timing: id 0 | task 28288 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.062.784 I slot release: id 0 | task 28288 | stop processing: n_tokens = 418, truncated = 0