$ 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-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.094.426 I srv llama_server: initializing ... 0.00.094.432 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.094.551 I srv init_listene: The UI is disabled 0.00.094.553 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.094.633 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) 0.00.108.388 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--granite-4.2-8b-GGUF\snapshots\a592100df8fe4931c7cffbac7b28e8176a1d52da\granite-4.2-8b-Q4_K_M.gguf' 0.02.474.922 I cmn init: llama threadpool init, n_threads = 8 0.02.543.875 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.548.586 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.548.605 I srv llama_server: model loaded 0.02.548.607 I srv llama_server: listening on http://127.0.0.1:8089 0.04.545.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.545.292 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.265.919 I slot print_timing: id 0 | task 0 | prompt eval time = 108.55 ms / 368 tokens ( 0.29 ms per token, 3390.17 tokens per second) 0.05.265.925 I slot print_timing: id 0 | task 0 | eval time = 612.06 ms / 61 tokens ( 10.20 ms per token, 98.03 tokens per second) 0.05.265.926 I slot print_timing: id 0 | task 0 | total time = 720.61 ms / 429 tokens 0.05.265.932 I slot print_timing: id 0 | task 0 | graphs reused = 60 0.05.265.933 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.265.967 I slot release: id 0 | task 0 | stop processing: n_tokens = 428, truncated = 0 0.05.294.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 5173580 0.05.309.518 I slot launch_slot_: id 0 | task 62 | processing task, is_child = 0 0.05.828.089 I slot print_timing: id 0 | task 62 | prompt eval time = 81.04 ms / 292 tokens ( 0.28 ms per token, 3603.11 tokens per second) 0.05.828.095 I slot print_timing: id 0 | task 62 | eval time = 437.51 ms / 44 tokens ( 10.17 ms per token, 98.28 tokens per second) 0.05.828.096 I slot print_timing: id 0 | task 62 | total time = 518.55 ms / 336 tokens 0.05.828.097 I slot print_timing: id 0 | task 62 | graphs reused = 102 0.05.828.098 I slot print_timing: id 0 | task 62 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.828.125 I slot release: id 0 | task 62 | stop processing: n_tokens = 360, truncated = 0 0.05.853.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 360, t_last = 5735738 0.05.866.736 I slot launch_slot_: id 0 | task 107 | processing task, is_child = 0 0.06.402.985 I slot print_timing: id 0 | task 107 | prompt eval time = 89.42 ms / 338 tokens ( 0.26 ms per token, 3779.79 tokens per second) 0.06.402.991 I slot print_timing: id 0 | task 107 | eval time = 446.81 ms / 45 tokens ( 10.15 ms per token, 98.48 tokens per second) 0.06.402.991 I slot print_timing: id 0 | task 107 | total time = 536.23 ms / 383 tokens 0.06.402.992 I slot print_timing: id 0 | task 107 | graphs reused = 145 0.06.402.993 I slot print_timing: id 0 | task 107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.403.021 I slot release: id 0 | task 107 | stop processing: n_tokens = 407, truncated = 0 0.06.427.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 407, t_last = 6310635 0.06.441.958 I slot launch_slot_: id 0 | task 153 | processing task, is_child = 0 0.06.988.567 I slot print_timing: id 0 | task 153 | prompt eval time = 89.74 ms / 371 tokens ( 0.24 ms per token, 4134.35 tokens per second) 0.06.988.572 I slot print_timing: id 0 | task 153 | eval time = 456.85 ms / 46 tokens ( 10.15 ms per token, 98.50 tokens per second) 0.06.988.573 I slot print_timing: id 0 | task 153 | total time = 546.59 ms / 417 tokens 0.06.988.574 I slot print_timing: id 0 | task 153 | graphs reused = 189 0.06.988.575 I slot print_timing: id 0 | task 153 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.988.603 I slot release: id 0 | task 153 | stop processing: n_tokens = 441, truncated = 0 0.06.992.780 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 0.07.008.330 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.07.708.093 I slot print_timing: id 0 | task 200 | prompt eval time = 89.93 ms / 345 tokens ( 0.26 ms per token, 3836.32 tokens per second) 0.07.708.099 I slot print_timing: id 0 | task 200 | eval time = 609.82 ms / 61 tokens ( 10.16 ms per token, 98.39 tokens per second) 0.07.708.100 I slot print_timing: id 0 | task 200 | total time = 699.75 ms / 406 tokens 0.07.708.101 I slot print_timing: id 0 | task 200 | graphs reused = 248 0.07.708.102 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.708.131 I slot release: id 0 | task 200 | stop processing: n_tokens = 445, truncated = 0 0.07.733.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 7615744 0.07.750.035 I slot launch_slot_: id 0 | task 262 | processing task, is_child = 0 0.08.478.355 I slot print_timing: id 0 | task 262 | prompt eval time = 89.71 ms / 351 tokens ( 0.26 ms per token, 3912.74 tokens per second) 0.08.478.362 I slot print_timing: id 0 | task 262 | eval time = 638.59 ms / 64 tokens ( 10.14 ms per token, 98.65 tokens per second) 0.08.478.363 I slot print_timing: id 0 | task 262 | total time = 728.30 ms / 415 tokens 0.08.478.364 I slot print_timing: id 0 | task 262 | graphs reused = 310 0.08.478.365 I slot print_timing: id 0 | task 262 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.478.393 I slot release: id 0 | task 262 | stop processing: n_tokens = 439, truncated = 0 0.08.497.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 8386006 0.08.513.572 I slot launch_slot_: id 0 | task 327 | processing task, is_child = 0 0.09.437.922 I slot print_timing: id 0 | task 327 | prompt eval time = 108.90 ms / 395 tokens ( 0.28 ms per token, 3627.15 tokens per second) 0.09.437.928 I slot print_timing: id 0 | task 327 | eval time = 815.43 ms / 79 tokens ( 10.45 ms per token, 95.65 tokens per second) 0.09.437.929 I slot print_timing: id 0 | task 327 | total time = 924.33 ms / 474 tokens 0.09.437.930 I slot print_timing: id 0 | task 327 | graphs reused = 387 0.09.437.931 I slot print_timing: id 0 | task 327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.437.962 I slot release: id 0 | task 327 | stop processing: n_tokens = 498, truncated = 0 0.09.464.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 9345575 0.09.481.903 I slot launch_slot_: id 0 | task 407 | processing task, is_child = 0 0.10.319.107 I slot print_timing: id 0 | task 407 | prompt eval time = 110.30 ms / 446 tokens ( 0.25 ms per token, 4043.44 tokens per second) 0.10.319.113 I slot print_timing: id 0 | task 407 | eval time = 726.88 ms / 72 tokens ( 10.24 ms per token, 97.68 tokens per second) 0.10.319.114 I slot print_timing: id 0 | task 407 | total time = 837.19 ms / 518 tokens 0.10.319.115 I slot print_timing: id 0 | task 407 | graphs reused = 456 0.10.319.116 I slot print_timing: id 0 | task 407 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.319.148 I slot release: id 0 | task 407 | stop processing: n_tokens = 542, truncated = 0 0.10.339.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 10226761 0.10.360.103 I slot launch_slot_: id 0 | task 480 | processing task, is_child = 0 0.10.959.336 I slot print_timing: id 0 | task 480 | prompt eval time = 81.94 ms / 319 tokens ( 0.26 ms per token, 3892.85 tokens per second) 0.10.959.342 I slot print_timing: id 0 | task 480 | eval time = 517.27 ms / 52 tokens ( 10.14 ms per token, 98.59 tokens per second) 0.10.959.343 I slot print_timing: id 0 | task 480 | total time = 599.21 ms / 371 tokens 0.10.959.344 I slot print_timing: id 0 | task 480 | graphs reused = 506 0.10.959.345 I slot print_timing: id 0 | task 480 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.959.373 I slot release: id 0 | task 480 | stop processing: n_tokens = 395, truncated = 0 0.10.978.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 10866986 0.10.993.212 I slot launch_slot_: id 0 | task 533 | processing task, is_child = 0 0.11.492.866 I slot print_timing: id 0 | task 533 | prompt eval time = 82.09 ms / 336 tokens ( 0.24 ms per token, 4093.17 tokens per second) 0.11.492.872 I slot print_timing: id 0 | task 533 | eval time = 417.55 ms / 42 tokens ( 10.18 ms per token, 98.19 tokens per second) 0.11.492.873 I slot print_timing: id 0 | task 533 | total time = 499.64 ms / 378 tokens 0.11.492.874 I slot print_timing: id 0 | task 533 | graphs reused = 546 0.11.492.875 I slot print_timing: id 0 | task 533 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.492.904 I slot release: id 0 | task 533 | stop processing: n_tokens = 402, truncated = 0 0.11.511.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 11400517 0.11.526.490 I slot launch_slot_: id 0 | task 576 | processing task, is_child = 0 0.12.303.278 I slot print_timing: id 0 | task 576 | prompt eval time = 89.75 ms / 352 tokens ( 0.25 ms per token, 3921.96 tokens per second) 0.12.303.284 I slot print_timing: id 0 | task 576 | eval time = 687.02 ms / 68 tokens ( 10.25 ms per token, 97.52 tokens per second) 0.12.303.285 I slot print_timing: id 0 | task 576 | total time = 776.77 ms / 420 tokens 0.12.303.285 I slot print_timing: id 0 | task 576 | graphs reused = 612 0.12.303.286 I slot print_timing: id 0 | task 576 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.303.316 I slot release: id 0 | task 576 | stop processing: n_tokens = 444, truncated = 0 0.12.321.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 12210929 0.12.338.188 I slot launch_slot_: id 0 | task 645 | processing task, is_child = 0 0.12.975.269 I slot print_timing: id 0 | task 645 | prompt eval time = 108.09 ms / 387 tokens ( 0.28 ms per token, 3580.35 tokens per second) 0.12.975.276 I slot print_timing: id 0 | task 645 | eval time = 528.98 ms / 52 tokens ( 10.37 ms per token, 96.41 tokens per second) 0.12.975.277 I slot print_timing: id 0 | task 645 | total time = 637.07 ms / 439 tokens 0.12.975.278 I slot print_timing: id 0 | task 645 | graphs reused = 662 0.12.975.279 I slot print_timing: id 0 | task 645 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.975.314 I slot release: id 0 | task 645 | stop processing: n_tokens = 463, truncated = 0 0.12.992.018 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 12882928 0.13.013.575 I slot launch_slot_: id 0 | task 698 | processing task, is_child = 0 0.13.742.999 I slot print_timing: id 0 | task 698 | prompt eval time = 90.57 ms / 349 tokens ( 0.26 ms per token, 3853.33 tokens per second) 0.13.743.005 I slot print_timing: id 0 | task 698 | eval time = 638.83 ms / 64 tokens ( 10.14 ms per token, 98.62 tokens per second) 0.13.743.007 I slot print_timing: id 0 | task 698 | total time = 729.40 ms / 413 tokens 0.13.743.008 I slot print_timing: id 0 | task 698 | graphs reused = 724 0.13.743.009 I slot print_timing: id 0 | task 698 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.743.041 I slot release: id 0 | task 698 | stop processing: n_tokens = 437, truncated = 0 0.13.747.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13650654 0.13.766.861 I slot launch_slot_: id 0 | task 763 | processing task, is_child = 0 0.14.447.463 I slot print_timing: id 0 | task 763 | prompt eval time = 89.82 ms / 352 tokens ( 0.26 ms per token, 3918.77 tokens per second) 0.14.447.469 I slot print_timing: id 0 | task 763 | eval time = 590.76 ms / 57 tokens ( 10.55 ms per token, 94.79 tokens per second) 0.14.447.470 I slot print_timing: id 0 | task 763 | total time = 680.58 ms / 409 tokens 0.14.447.471 I slot print_timing: id 0 | task 763 | graphs reused = 779 0.14.447.471 I slot print_timing: id 0 | task 763 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.447.500 I slot release: id 0 | task 763 | stop processing: n_tokens = 433, truncated = 0 0.14.465.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 14355113 0.14.483.511 I slot launch_slot_: id 0 | task 821 | processing task, is_child = 0 0.15.262.675 I slot print_timing: id 0 | task 821 | prompt eval time = 89.37 ms / 347 tokens ( 0.26 ms per token, 3882.78 tokens per second) 0.15.262.681 I slot print_timing: id 0 | task 821 | eval time = 689.78 ms / 68 tokens ( 10.30 ms per token, 97.13 tokens per second) 0.15.262.682 I slot print_timing: id 0 | task 821 | total time = 779.15 ms / 415 tokens 0.15.262.683 I slot print_timing: id 0 | task 821 | graphs reused = 845 0.15.262.685 I slot print_timing: id 0 | task 821 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.262.714 I slot release: id 0 | task 821 | stop processing: n_tokens = 439, truncated = 0 0.15.280.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 15170327 0.15.301.456 I slot launch_slot_: id 0 | task 890 | processing task, is_child = 0 0.15.940.416 I slot print_timing: id 0 | task 890 | prompt eval time = 81.67 ms / 320 tokens ( 0.26 ms per token, 3918.02 tokens per second) 0.15.940.421 I slot print_timing: id 0 | task 890 | eval time = 557.27 ms / 56 tokens ( 10.13 ms per token, 98.70 tokens per second) 0.15.940.423 I slot print_timing: id 0 | task 890 | total time = 638.94 ms / 376 tokens 0.15.940.423 I slot print_timing: id 0 | task 890 | graphs reused = 899 0.15.940.424 I slot print_timing: id 0 | task 890 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.940.452 I slot release: id 0 | task 890 | stop processing: n_tokens = 400, truncated = 0 0.15.969.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 15848066 0.15.987.591 I slot launch_slot_: id 0 | task 947 | processing task, is_child = 0 0.16.514.138 I slot print_timing: id 0 | task 947 | prompt eval time = 89.17 ms / 343 tokens ( 0.26 ms per token, 3846.76 tokens per second) 0.16.514.144 I slot print_timing: id 0 | task 947 | eval time = 437.36 ms / 44 tokens ( 10.17 ms per token, 98.32 tokens per second) 0.16.514.145 I slot print_timing: id 0 | task 947 | total time = 526.53 ms / 387 tokens 0.16.514.146 I slot print_timing: id 0 | task 947 | graphs reused = 941 0.16.514.147 I slot print_timing: id 0 | task 947 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.514.173 I slot release: id 0 | task 947 | stop processing: n_tokens = 411, truncated = 0 0.16.531.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 16421786 0.16.549.138 I slot launch_slot_: id 0 | task 992 | processing task, is_child = 0 0.17.198.161 I slot print_timing: id 0 | task 992 | prompt eval time = 81.45 ms / 325 tokens ( 0.25 ms per token, 3989.93 tokens per second) 0.17.198.166 I slot print_timing: id 0 | task 992 | eval time = 567.55 ms / 57 tokens ( 10.13 ms per token, 98.67 tokens per second) 0.17.198.167 I slot print_timing: id 0 | task 992 | total time = 649.01 ms / 382 tokens 0.17.198.168 I slot print_timing: id 0 | task 992 | graphs reused = 996 0.17.198.169 I slot print_timing: id 0 | task 992 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.198.196 I slot release: id 0 | task 992 | stop processing: n_tokens = 406, truncated = 0 0.17.218.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 17105809 0.17.237.265 I slot launch_slot_: id 0 | task 1050 | processing task, is_child = 0 0.17.745.357 I slot print_timing: id 0 | task 1050 | prompt eval time = 81.55 ms / 323 tokens ( 0.25 ms per token, 3960.91 tokens per second) 0.17.745.363 I slot print_timing: id 0 | task 1050 | eval time = 426.53 ms / 43 tokens ( 10.16 ms per token, 98.47 tokens per second) 0.17.745.364 I slot print_timing: id 0 | task 1050 | total time = 508.08 ms / 366 tokens 0.17.745.365 I slot print_timing: id 0 | task 1050 | graphs reused = 1037 0.17.745.366 I slot print_timing: id 0 | task 1050 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.745.393 I slot release: id 0 | task 1050 | stop processing: n_tokens = 390, truncated = 0 0.17.765.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 17653007 0.17.783.103 I slot launch_slot_: id 0 | task 1094 | processing task, is_child = 0 0.18.583.859 I slot print_timing: id 0 | task 1094 | prompt eval time = 89.94 ms / 359 tokens ( 0.25 ms per token, 3991.42 tokens per second) 0.18.583.865 I slot print_timing: id 0 | task 1094 | eval time = 710.80 ms / 69 tokens ( 10.45 ms per token, 95.67 tokens per second) 0.18.583.866 I slot print_timing: id 0 | task 1094 | total time = 800.74 ms / 428 tokens 0.18.583.867 I slot print_timing: id 0 | task 1094 | graphs reused = 1104 0.18.583.868 I slot print_timing: id 0 | task 1094 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.583.896 I slot release: id 0 | task 1094 | stop processing: n_tokens = 452, truncated = 0 0.18.607.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 18491509 0.18.627.997 I slot launch_slot_: id 0 | task 1164 | processing task, is_child = 0 0.19.337.822 I slot print_timing: id 0 | task 1164 | prompt eval time = 82.19 ms / 334 tokens ( 0.25 ms per token, 4063.80 tokens per second) 0.19.337.828 I slot print_timing: id 0 | task 1164 | eval time = 627.62 ms / 63 tokens ( 10.12 ms per token, 98.79 tokens per second) 0.19.337.829 I slot print_timing: id 0 | task 1164 | total time = 709.81 ms / 397 tokens 0.19.337.830 I slot print_timing: id 0 | task 1164 | graphs reused = 1165 0.19.337.831 I slot print_timing: id 0 | task 1164 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.337.861 I slot release: id 0 | task 1164 | stop processing: n_tokens = 421, truncated = 0 0.19.342.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 19245475 0.19.360.960 I slot launch_slot_: id 0 | task 1228 | processing task, is_child = 0 0.20.177.944 I slot print_timing: id 0 | task 1228 | prompt eval time = 90.10 ms / 382 tokens ( 0.24 ms per token, 4239.55 tokens per second) 0.20.177.950 I slot print_timing: id 0 | task 1228 | eval time = 726.86 ms / 73 tokens ( 10.10 ms per token, 99.06 tokens per second) 0.20.177.951 I slot print_timing: id 0 | task 1228 | total time = 816.97 ms / 455 tokens 0.20.177.952 I slot print_timing: id 0 | task 1228 | graphs reused = 1236 0.20.177.953 I slot print_timing: id 0 | task 1228 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.177.983 I slot release: id 0 | task 1228 | stop processing: n_tokens = 479, truncated = 0 0.20.197.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 20085596 0.20.218.754 I slot launch_slot_: id 0 | task 1302 | processing task, is_child = 0 0.20.957.731 I slot print_timing: id 0 | task 1302 | prompt eval time = 90.61 ms / 368 tokens ( 0.25 ms per token, 4061.32 tokens per second) 0.20.957.737 I slot print_timing: id 0 | task 1302 | eval time = 648.35 ms / 65 tokens ( 10.13 ms per token, 98.71 tokens per second) 0.20.957.738 I slot print_timing: id 0 | task 1302 | total time = 738.96 ms / 433 tokens 0.20.957.739 I slot print_timing: id 0 | task 1302 | graphs reused = 1299 0.20.957.740 I slot print_timing: id 0 | task 1302 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.957.772 I slot release: id 0 | task 1302 | stop processing: n_tokens = 457, truncated = 0 0.20.977.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 20865386 0.20.998.769 I slot launch_slot_: id 0 | task 1368 | processing task, is_child = 0 0.21.957.947 I slot print_timing: id 0 | task 1368 | prompt eval time = 90.05 ms / 382 tokens ( 0.24 ms per token, 4242.28 tokens per second) 0.21.957.953 I slot print_timing: id 0 | task 1368 | eval time = 869.11 ms / 87 tokens ( 10.11 ms per token, 98.95 tokens per second) 0.21.957.955 I slot print_timing: id 0 | task 1368 | total time = 959.16 ms / 469 tokens 0.21.957.956 I slot print_timing: id 0 | task 1368 | graphs reused = 1384 0.21.957.957 I slot print_timing: id 0 | task 1368 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.957.992 I slot release: id 0 | task 1368 | stop processing: n_tokens = 493, truncated = 0 0.21.985.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 21865605 0.22.007.427 I slot launch_slot_: id 0 | task 1456 | processing task, is_child = 0 0.22.784.435 I slot print_timing: id 0 | task 1456 | prompt eval time = 109.28 ms / 410 tokens ( 0.27 ms per token, 3751.90 tokens per second) 0.22.784.441 I slot print_timing: id 0 | task 1456 | eval time = 667.71 ms / 67 tokens ( 10.12 ms per token, 98.84 tokens per second) 0.22.784.442 I slot print_timing: id 0 | task 1456 | total time = 776.99 ms / 477 tokens 0.22.784.443 I slot print_timing: id 0 | task 1456 | graphs reused = 1449 0.22.784.444 I slot print_timing: id 0 | task 1456 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.784.475 I slot release: id 0 | task 1456 | stop processing: n_tokens = 501, truncated = 0 0.22.799.786 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 22692089 0.22.822.995 I slot launch_slot_: id 0 | task 1524 | processing task, is_child = 0 0.23.562.037 I slot print_timing: id 0 | task 1524 | prompt eval time = 90.39 ms / 367 tokens ( 0.25 ms per token, 4060.18 tokens per second) 0.23.562.042 I slot print_timing: id 0 | task 1524 | eval time = 648.63 ms / 65 tokens ( 10.13 ms per token, 98.67 tokens per second) 0.23.562.043 I slot print_timing: id 0 | task 1524 | total time = 739.02 ms / 432 tokens 0.23.562.044 I slot print_timing: id 0 | task 1524 | graphs reused = 1512 0.23.562.045 I slot print_timing: id 0 | task 1524 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.562.073 I slot release: id 0 | task 1524 | stop processing: n_tokens = 458, truncated = 0 0.23.576.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 23469686 0.23.598.264 I slot launch_slot_: id 0 | task 1590 | processing task, is_child = 0 0.24.217.098 I slot print_timing: id 0 | task 1590 | prompt eval time = 81.79 ms / 326 tokens ( 0.25 ms per token, 3985.67 tokens per second) 0.24.217.104 I slot print_timing: id 0 | task 1590 | eval time = 537.02 ms / 54 tokens ( 10.13 ms per token, 98.69 tokens per second) 0.24.217.105 I slot print_timing: id 0 | task 1590 | total time = 618.82 ms / 380 tokens 0.24.217.106 I slot print_timing: id 0 | task 1590 | graphs reused = 1564 0.24.217.107 I slot print_timing: id 0 | task 1590 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.217.136 I slot release: id 0 | task 1590 | stop processing: n_tokens = 404, truncated = 0 0.24.233.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 24124749 0.24.252.587 I slot launch_slot_: id 0 | task 1645 | processing task, is_child = 0 0.24.979.579 I slot print_timing: id 0 | task 1645 | prompt eval time = 89.67 ms / 351 tokens ( 0.26 ms per token, 3914.53 tokens per second) 0.24.979.585 I slot print_timing: id 0 | task 1645 | eval time = 637.31 ms / 64 tokens ( 10.12 ms per token, 98.85 tokens per second) 0.24.979.586 I slot print_timing: id 0 | task 1645 | total time = 726.97 ms / 415 tokens 0.24.979.587 I slot print_timing: id 0 | task 1645 | graphs reused = 1626 0.24.979.588 I slot print_timing: id 0 | task 1645 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.979.618 I slot release: id 0 | task 1645 | stop processing: n_tokens = 441, truncated = 0 0.24.997.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 24887231 0.25.016.443 I slot launch_slot_: id 0 | task 1710 | processing task, is_child = 0 0.25.896.937 I slot print_timing: id 0 | task 1710 | prompt eval time = 89.89 ms / 379 tokens ( 0.24 ms per token, 4216.26 tokens per second) 0.25.896.943 I slot print_timing: id 0 | task 1710 | eval time = 790.59 ms / 78 tokens ( 10.27 ms per token, 97.40 tokens per second) 0.25.896.944 I slot print_timing: id 0 | task 1710 | total time = 880.48 ms / 457 tokens 0.25.896.946 I slot print_timing: id 0 | task 1710 | graphs reused = 1702 0.25.896.946 I slot print_timing: id 0 | task 1710 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.896.979 I slot release: id 0 | task 1710 | stop processing: n_tokens = 481, truncated = 0 0.25.922.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 25804592 0.25.948.142 I slot launch_slot_: id 0 | task 1789 | processing task, is_child = 0 0.26.735.406 I slot print_timing: id 0 | task 1789 | prompt eval time = 89.72 ms / 356 tokens ( 0.25 ms per token, 3967.90 tokens per second) 0.26.735.412 I slot print_timing: id 0 | task 1789 | eval time = 697.53 ms / 70 tokens ( 10.11 ms per token, 98.92 tokens per second) 0.26.735.413 I slot print_timing: id 0 | task 1789 | total time = 787.25 ms / 426 tokens 0.26.735.413 I slot print_timing: id 0 | task 1789 | graphs reused = 1770 0.26.735.414 I slot print_timing: id 0 | task 1789 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.735.443 I slot release: id 0 | task 1789 | stop processing: n_tokens = 450, truncated = 0 0.26.739.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 26643057 0.26.761.631 I slot launch_slot_: id 0 | task 1860 | processing task, is_child = 0 0.27.451.443 I slot print_timing: id 0 | task 1860 | prompt eval time = 82.09 ms / 331 tokens ( 0.25 ms per token, 4032.16 tokens per second) 0.27.451.450 I slot print_timing: id 0 | task 1860 | eval time = 607.71 ms / 61 tokens ( 10.13 ms per token, 98.73 tokens per second) 0.27.451.451 I slot print_timing: id 0 | task 1860 | total time = 689.80 ms / 392 tokens 0.27.451.451 I slot print_timing: id 0 | task 1860 | graphs reused = 1829 0.27.451.452 I slot print_timing: id 0 | task 1860 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.451.482 I slot release: id 0 | task 1860 | stop processing: n_tokens = 416, truncated = 0 0.27.477.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 27359095 0.27.495.743 I slot launch_slot_: id 0 | task 1922 | processing task, is_child = 0 0.28.216.678 I slot print_timing: id 0 | task 1922 | prompt eval time = 82.03 ms / 334 tokens ( 0.25 ms per token, 4071.83 tokens per second) 0.28.216.683 I slot print_timing: id 0 | task 1922 | eval time = 638.89 ms / 62 tokens ( 10.47 ms per token, 95.48 tokens per second) 0.28.216.684 I slot print_timing: id 0 | task 1922 | total time = 720.92 ms / 396 tokens 0.28.216.685 I slot print_timing: id 0 | task 1922 | graphs reused = 1889 0.28.216.686 I slot print_timing: id 0 | task 1922 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.216.714 I slot release: id 0 | task 1922 | stop processing: n_tokens = 420, truncated = 0 0.28.232.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 28124327 0.28.252.038 I slot launch_slot_: id 0 | task 1985 | processing task, is_child = 0 0.29.018.926 I slot print_timing: id 0 | task 1985 | prompt eval time = 90.25 ms / 362 tokens ( 0.25 ms per token, 4011.30 tokens per second) 0.29.018.932 I slot print_timing: id 0 | task 1985 | eval time = 676.63 ms / 68 tokens ( 10.10 ms per token, 99.02 tokens per second) 0.29.018.933 I slot print_timing: id 0 | task 1985 | total time = 766.87 ms / 430 tokens 0.29.018.934 I slot print_timing: id 0 | task 1985 | graphs reused = 1955 0.29.018.934 I slot print_timing: id 0 | task 1985 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.018.966 I slot release: id 0 | task 1985 | stop processing: n_tokens = 454, truncated = 0 0.29.045.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 28926579 0.29.066.426 I slot launch_slot_: id 0 | task 2054 | processing task, is_child = 0 0.29.815.163 I slot print_timing: id 0 | task 2054 | prompt eval time = 90.14 ms / 384 tokens ( 0.23 ms per token, 4259.90 tokens per second) 0.29.815.169 I slot print_timing: id 0 | task 2054 | eval time = 658.57 ms / 66 tokens ( 10.13 ms per token, 98.70 tokens per second) 0.29.815.170 I slot print_timing: id 0 | task 2054 | total time = 748.72 ms / 450 tokens 0.29.815.171 I slot print_timing: id 0 | task 2054 | graphs reused = 2019 0.29.815.172 I slot print_timing: id 0 | task 2054 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.815.204 I slot release: id 0 | task 2054 | stop processing: n_tokens = 474, truncated = 0 0.29.837.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 29722817 0.29.868.988 I slot launch_slot_: id 0 | task 2121 | processing task, is_child = 0 0.30.499.161 I slot print_timing: id 0 | task 2121 | prompt eval time = 81.81 ms / 325 tokens ( 0.25 ms per token, 3972.86 tokens per second) 0.30.499.165 I slot print_timing: id 0 | task 2121 | eval time = 548.35 ms / 55 tokens ( 10.15 ms per token, 98.48 tokens per second) 0.30.499.167 I slot print_timing: id 0 | task 2121 | total time = 630.15 ms / 380 tokens 0.30.499.167 I slot print_timing: id 0 | task 2121 | graphs reused = 2072 0.30.499.168 I slot print_timing: id 0 | task 2121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.499.197 I slot release: id 0 | task 2121 | stop processing: n_tokens = 404, truncated = 0 0.30.523.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 30406811 0.30.541.546 I slot launch_slot_: id 0 | task 2177 | processing task, is_child = 0 0.31.233.377 I slot print_timing: id 0 | task 2177 | prompt eval time = 90.45 ms / 366 tokens ( 0.25 ms per token, 4046.21 tokens per second) 0.31.233.382 I slot print_timing: id 0 | task 2177 | eval time = 601.36 ms / 59 tokens ( 10.37 ms per token, 96.45 tokens per second) 0.31.233.384 I slot print_timing: id 0 | task 2177 | total time = 691.81 ms / 425 tokens 0.31.233.384 I slot print_timing: id 0 | task 2177 | graphs reused = 2129 0.31.233.385 I slot print_timing: id 0 | task 2177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.233.417 I slot release: id 0 | task 2177 | stop processing: n_tokens = 449, truncated = 0 0.31.250.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 31141031 0.31.270.654 I slot launch_slot_: id 0 | task 2237 | processing task, is_child = 0 0.31.707.448 I slot print_timing: id 0 | task 2237 | prompt eval time = 80.58 ms / 295 tokens ( 0.27 ms per token, 3660.73 tokens per second) 0.31.707.454 I slot print_timing: id 0 | task 2237 | eval time = 356.19 ms / 36 tokens ( 10.18 ms per token, 98.26 tokens per second) 0.31.707.455 I slot print_timing: id 0 | task 2237 | total time = 436.77 ms / 331 tokens 0.31.707.456 I slot print_timing: id 0 | task 2237 | graphs reused = 2163 0.31.707.456 I slot print_timing: id 0 | task 2237 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.707.493 I slot release: id 0 | task 2237 | stop processing: n_tokens = 355, truncated = 0 0.31.721.963 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 31615107 0.31.739.804 I slot launch_slot_: id 0 | task 2274 | processing task, is_child = 0 0.32.317.374 I slot print_timing: id 0 | task 2274 | prompt eval time = 81.18 ms / 307 tokens ( 0.26 ms per token, 3781.67 tokens per second) 0.32.317.380 I slot print_timing: id 0 | task 2274 | eval time = 496.37 ms / 50 tokens ( 10.13 ms per token, 98.72 tokens per second) 0.32.317.381 I slot print_timing: id 0 | task 2274 | total time = 577.55 ms / 357 tokens 0.32.317.382 I slot print_timing: id 0 | task 2274 | graphs reused = 2211 0.32.317.383 I slot print_timing: id 0 | task 2274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.317.411 I slot release: id 0 | task 2274 | stop processing: n_tokens = 381, truncated = 0 0.32.343.317 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 32225025 0.32.360.474 I slot launch_slot_: id 0 | task 2325 | processing task, is_child = 0 0.32.817.434 I slot print_timing: id 0 | task 2325 | prompt eval time = 81.28 ms / 319 tokens ( 0.25 ms per token, 3924.85 tokens per second) 0.32.817.440 I slot print_timing: id 0 | task 2325 | eval time = 375.67 ms / 38 tokens ( 10.15 ms per token, 98.49 tokens per second) 0.32.817.441 I slot print_timing: id 0 | task 2325 | total time = 456.94 ms / 357 tokens 0.32.817.442 I slot print_timing: id 0 | task 2325 | graphs reused = 2247 0.32.817.443 I slot print_timing: id 0 | task 2325 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.817.470 I slot release: id 0 | task 2325 | stop processing: n_tokens = 381, truncated = 0 0.32.842.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 32725084 0.32.860.130 I slot launch_slot_: id 0 | task 2364 | processing task, is_child = 0 0.33.468.422 I slot print_timing: id 0 | task 2364 | prompt eval time = 81.58 ms / 315 tokens ( 0.26 ms per token, 3861.29 tokens per second) 0.33.468.427 I slot print_timing: id 0 | task 2364 | eval time = 526.70 ms / 53 tokens ( 10.13 ms per token, 98.73 tokens per second) 0.33.468.429 I slot print_timing: id 0 | task 2364 | total time = 608.27 ms / 368 tokens 0.33.468.429 I slot print_timing: id 0 | task 2364 | graphs reused = 2298 0.33.468.430 I slot print_timing: id 0 | task 2364 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.468.458 I slot release: id 0 | task 2364 | stop processing: n_tokens = 392, truncated = 0 0.33.483.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 33376071 0.33.501.431 I slot launch_slot_: id 0 | task 2418 | processing task, is_child = 0 0.34.167.922 I slot print_timing: id 0 | task 2418 | prompt eval time = 90.36 ms / 367 tokens ( 0.25 ms per token, 4061.53 tokens per second) 0.34.167.927 I slot print_timing: id 0 | task 2418 | eval time = 576.11 ms / 58 tokens ( 10.11 ms per token, 98.94 tokens per second) 0.34.167.928 I slot print_timing: id 0 | task 2418 | total time = 666.47 ms / 425 tokens 0.34.167.929 I slot print_timing: id 0 | task 2418 | graphs reused = 2354 0.34.167.930 I slot print_timing: id 0 | task 2418 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.167.961 I slot release: id 0 | task 2418 | stop processing: n_tokens = 449, truncated = 0 0.34.184.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 34075575 0.34.204.154 I slot launch_slot_: id 0 | task 2477 | processing task, is_child = 0 0.34.864.254 I slot print_timing: id 0 | task 2477 | prompt eval time = 124.00 ms / 499 tokens ( 0.25 ms per token, 4024.36 tokens per second) 0.34.864.260 I slot print_timing: id 0 | task 2477 | eval time = 536.09 ms / 52 tokens ( 10.51 ms per token, 95.13 tokens per second) 0.34.864.261 I slot print_timing: id 0 | task 2477 | total time = 660.08 ms / 551 tokens 0.34.864.262 I slot print_timing: id 0 | task 2477 | graphs reused = 2404 0.34.864.263 I slot print_timing: id 0 | task 2477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.864.296 I slot release: id 0 | task 2477 | stop processing: n_tokens = 575, truncated = 0 0.34.884.360 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 34771910 0.34.909.314 I slot launch_slot_: id 0 | task 2530 | processing task, is_child = 0 0.35.486.997 I slot print_timing: id 0 | task 2530 | prompt eval time = 81.58 ms / 319 tokens ( 0.26 ms per token, 3910.51 tokens per second) 0.35.487.003 I slot print_timing: id 0 | task 2530 | eval time = 496.09 ms / 50 tokens ( 10.12 ms per token, 98.77 tokens per second) 0.35.487.004 I slot print_timing: id 0 | task 2530 | total time = 577.67 ms / 369 tokens 0.35.487.005 I slot print_timing: id 0 | task 2530 | graphs reused = 2452 0.35.487.006 I slot print_timing: id 0 | task 2530 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.487.033 I slot release: id 0 | task 2530 | stop processing: n_tokens = 393, truncated = 0 0.35.491.255 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 35394646 0.35.508.926 I slot launch_slot_: id 0 | task 2581 | processing task, is_child = 0 0.36.175.673 I slot print_timing: id 0 | task 2581 | prompt eval time = 89.84 ms / 348 tokens ( 0.26 ms per token, 3873.68 tokens per second) 0.36.175.679 I slot print_timing: id 0 | task 2581 | eval time = 576.89 ms / 58 tokens ( 10.12 ms per token, 98.81 tokens per second) 0.36.175.680 I slot print_timing: id 0 | task 2581 | total time = 666.73 ms / 406 tokens 0.36.175.681 I slot print_timing: id 0 | task 2581 | graphs reused = 2508 0.36.175.682 I slot print_timing: id 0 | task 2581 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.175.715 I slot release: id 0 | task 2581 | stop processing: n_tokens = 430, truncated = 0 0.36.197.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 36083328 0.36.217.428 I slot launch_slot_: id 0 | task 2640 | processing task, is_child = 0 0.37.076.265 I slot print_timing: id 0 | task 2640 | prompt eval time = 109.42 ms / 404 tokens ( 0.27 ms per token, 3692.26 tokens per second) 0.37.076.271 I slot print_timing: id 0 | task 2640 | eval time = 749.40 ms / 75 tokens ( 10.13 ms per token, 98.75 tokens per second) 0.37.076.272 I slot print_timing: id 0 | task 2640 | total time = 858.82 ms / 479 tokens 0.37.076.273 I slot print_timing: id 0 | task 2640 | graphs reused = 2581 0.37.076.274 I slot print_timing: id 0 | task 2640 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.076.304 I slot release: id 0 | task 2640 | stop processing: n_tokens = 503, truncated = 0 0.37.104.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 36983918 0.37.126.998 I slot launch_slot_: id 0 | task 2716 | processing task, is_child = 0 0.37.851.676 I slot print_timing: id 0 | task 2716 | prompt eval time = 109.29 ms / 408 tokens ( 0.27 ms per token, 3733.05 tokens per second) 0.37.851.682 I slot print_timing: id 0 | task 2716 | eval time = 615.36 ms / 60 tokens ( 10.43 ms per token, 95.88 tokens per second) 0.37.851.683 I slot print_timing: id 0 | task 2716 | total time = 724.66 ms / 468 tokens 0.37.851.683 I slot print_timing: id 0 | task 2716 | graphs reused = 2639 0.37.851.684 I slot print_timing: id 0 | task 2716 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.851.718 I slot release: id 0 | task 2716 | stop processing: n_tokens = 494, truncated = 0 0.37.871.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 37759331 0.37.893.011 I slot launch_slot_: id 0 | task 2777 | processing task, is_child = 0 0.38.478.588 I slot print_timing: id 0 | task 2777 | prompt eval time = 81.82 ms / 325 tokens ( 0.25 ms per token, 3972.09 tokens per second) 0.38.478.593 I slot print_timing: id 0 | task 2777 | eval time = 503.74 ms / 49 tokens ( 10.49 ms per token, 95.29 tokens per second) 0.38.478.594 I slot print_timing: id 0 | task 2777 | total time = 585.56 ms / 374 tokens 0.38.478.595 I slot print_timing: id 0 | task 2777 | graphs reused = 2686 0.38.478.596 I slot print_timing: id 0 | task 2777 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.478.626 I slot release: id 0 | task 2777 | stop processing: n_tokens = 402, truncated = 0 0.38.497.229 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 38386239 0.38.515.176 I slot launch_slot_: id 0 | task 2827 | processing task, is_child = 0 0.39.132.073 I slot print_timing: id 0 | task 2827 | prompt eval time = 89.71 ms / 345 tokens ( 0.26 ms per token, 3845.77 tokens per second) 0.39.132.079 I slot print_timing: id 0 | task 2827 | eval time = 527.17 ms / 53 tokens ( 10.14 ms per token, 98.64 tokens per second) 0.39.132.080 I slot print_timing: id 0 | task 2827 | total time = 616.88 ms / 398 tokens 0.39.132.081 I slot print_timing: id 0 | task 2827 | graphs reused = 2737 0.39.132.082 I slot print_timing: id 0 | task 2827 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.132.112 I slot release: id 0 | task 2827 | stop processing: n_tokens = 422, truncated = 0 0.39.152.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 39039725 0.39.170.579 I slot launch_slot_: id 0 | task 2881 | processing task, is_child = 0 0.39.759.195 I slot print_timing: id 0 | task 2881 | prompt eval time = 89.64 ms / 344 tokens ( 0.26 ms per token, 3837.62 tokens per second) 0.39.759.202 I slot print_timing: id 0 | task 2881 | eval time = 498.96 ms / 50 tokens ( 10.18 ms per token, 98.20 tokens per second) 0.39.759.203 I slot print_timing: id 0 | task 2881 | total time = 588.60 ms / 394 tokens 0.39.759.204 I slot print_timing: id 0 | task 2881 | graphs reused = 2785 0.39.759.205 I slot print_timing: id 0 | task 2881 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.759.244 I slot release: id 0 | task 2881 | stop processing: n_tokens = 418, truncated = 0 0.39.764.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 39666857 0.39.781.939 I slot launch_slot_: id 0 | task 2932 | processing task, is_child = 0 0.40.611.822 I slot print_timing: id 0 | task 2932 | prompt eval time = 90.28 ms / 378 tokens ( 0.24 ms per token, 4187.11 tokens per second) 0.40.611.830 I slot print_timing: id 0 | task 2932 | eval time = 739.59 ms / 74 tokens ( 10.13 ms per token, 98.70 tokens per second) 0.40.611.832 I slot print_timing: id 0 | task 2932 | total time = 829.86 ms / 452 tokens 0.40.611.833 I slot print_timing: id 0 | task 2932 | graphs reused = 2857 0.40.611.834 I slot print_timing: id 0 | task 2932 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.611.884 I slot release: id 0 | task 2932 | stop processing: n_tokens = 476, truncated = 0 0.40.629.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 40519497 0.40.650.902 I slot launch_slot_: id 0 | task 3007 | processing task, is_child = 0 0.41.342.141 I slot print_timing: id 0 | task 3007 | prompt eval time = 82.34 ms / 331 tokens ( 0.25 ms per token, 4020.11 tokens per second) 0.41.342.147 I slot print_timing: id 0 | task 3007 | eval time = 608.88 ms / 61 tokens ( 10.15 ms per token, 98.54 tokens per second) 0.41.342.148 I slot print_timing: id 0 | task 3007 | total time = 691.22 ms / 392 tokens 0.41.342.149 I slot print_timing: id 0 | task 3007 | graphs reused = 2916 0.41.342.150 I slot print_timing: id 0 | task 3007 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.342.179 I slot release: id 0 | task 3007 | stop processing: n_tokens = 416, truncated = 0 0.41.361.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 41249792 0.41.377.432 I slot launch_slot_: id 0 | task 3069 | processing task, is_child = 0 0.41.972.674 I slot print_timing: id 0 | task 3069 | prompt eval time = 108.70 ms / 387 tokens ( 0.28 ms per token, 3560.39 tokens per second) 0.41.972.679 I slot print_timing: id 0 | task 3069 | eval time = 486.53 ms / 49 tokens ( 10.14 ms per token, 98.66 tokens per second) 0.41.972.680 I slot print_timing: id 0 | task 3069 | total time = 595.23 ms / 436 tokens 0.41.972.681 I slot print_timing: id 0 | task 3069 | graphs reused = 2963 0.41.972.682 I slot print_timing: id 0 | task 3069 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.972.715 I slot release: id 0 | task 3069 | stop processing: n_tokens = 460, truncated = 0 0.42.000.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 41880328 0.42.021.000 I slot launch_slot_: id 0 | task 3119 | processing task, is_child = 0 0.42.857.810 I slot print_timing: id 0 | task 3119 | prompt eval time = 89.80 ms / 345 tokens ( 0.26 ms per token, 3842.00 tokens per second) 0.42.857.818 I slot print_timing: id 0 | task 3119 | eval time = 746.99 ms / 75 tokens ( 10.09 ms per token, 99.06 tokens per second) 0.42.857.819 I slot print_timing: id 0 | task 3119 | total time = 836.79 ms / 420 tokens 0.42.857.820 I slot print_timing: id 0 | task 3119 | graphs reused = 3036 0.42.857.821 I slot print_timing: id 0 | task 3119 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.857.870 I slot release: id 0 | task 3119 | stop processing: n_tokens = 444, truncated = 0 0.42.873.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 42765484 0.42.894.905 I slot launch_slot_: id 0 | task 3195 | processing task, is_child = 0 0.43.611.696 I slot print_timing: id 0 | task 3195 | prompt eval time = 89.32 ms / 337 tokens ( 0.27 ms per token, 3773.12 tokens per second) 0.43.611.702 I slot print_timing: id 0 | task 3195 | eval time = 627.46 ms / 61 tokens ( 10.46 ms per token, 95.62 tokens per second) 0.43.611.703 I slot print_timing: id 0 | task 3195 | total time = 716.77 ms / 398 tokens 0.43.611.703 I slot print_timing: id 0 | task 3195 | graphs reused = 3095 0.43.611.705 I slot print_timing: id 0 | task 3195 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.611.734 I slot release: id 0 | task 3195 | stop processing: n_tokens = 422, truncated = 0 0.43.631.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 43519347 0.43.649.462 I slot launch_slot_: id 0 | task 3257 | processing task, is_child = 0 0.44.731.010 I slot print_timing: id 0 | task 3257 | prompt eval time = 121.31 ms / 463 tokens ( 0.26 ms per token, 3816.83 tokens per second) 0.44.731.016 I slot print_timing: id 0 | task 3257 | eval time = 960.22 ms / 95 tokens ( 10.22 ms per token, 97.89 tokens per second) 0.44.731.017 I slot print_timing: id 0 | task 3257 | total time = 1081.53 ms / 558 tokens 0.44.731.017 I slot print_timing: id 0 | task 3257 | graphs reused = 3187 0.44.731.018 I slot print_timing: id 0 | task 3257 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.731.053 I slot release: id 0 | task 3257 | stop processing: n_tokens = 582, truncated = 0 0.44.751.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 44638666 0.44.777.230 I slot launch_slot_: id 0 | task 3353 | processing task, is_child = 0 0.45.988.823 I slot print_timing: id 0 | task 3353 | prompt eval time = 110.58 ms / 440 tokens ( 0.25 ms per token, 3978.98 tokens per second) 0.45.988.829 I slot print_timing: id 0 | task 3353 | eval time = 1100.99 ms / 109 tokens ( 10.19 ms per token, 98.09 tokens per second) 0.45.988.830 I slot print_timing: id 0 | task 3353 | total time = 1211.57 ms / 549 tokens 0.45.988.831 I slot print_timing: id 0 | task 3353 | graphs reused = 3293 0.45.988.832 I slot print_timing: id 0 | task 3353 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.988.864 I slot release: id 0 | task 3353 | stop processing: n_tokens = 573, truncated = 0 0.46.015.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 45896477 0.46.037.392 I slot launch_slot_: id 0 | task 3463 | processing task, is_child = 0 0.46.755.602 I slot print_timing: id 0 | task 3463 | prompt eval time = 82.19 ms / 336 tokens ( 0.24 ms per token, 4087.84 tokens per second) 0.46.755.608 I slot print_timing: id 0 | task 3463 | eval time = 636.00 ms / 64 tokens ( 10.10 ms per token, 99.06 tokens per second) 0.46.755.609 I slot print_timing: id 0 | task 3463 | total time = 718.19 ms / 400 tokens 0.46.755.610 I slot print_timing: id 0 | task 3463 | graphs reused = 3355 0.46.755.611 I slot print_timing: id 0 | task 3463 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.755.640 I slot release: id 0 | task 3463 | stop processing: n_tokens = 424, truncated = 0 0.46.781.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 46663253 0.46.800.628 I slot launch_slot_: id 0 | task 3528 | processing task, is_child = 0 0.47.465.851 I slot print_timing: id 0 | task 3528 | prompt eval time = 90.68 ms / 367 tokens ( 0.25 ms per token, 4047.20 tokens per second) 0.47.465.856 I slot print_timing: id 0 | task 3528 | eval time = 574.52 ms / 57 tokens ( 10.26 ms per token, 97.47 tokens per second) 0.47.465.857 I slot print_timing: id 0 | task 3528 | total time = 665.20 ms / 424 tokens 0.47.465.858 I slot print_timing: id 0 | task 3528 | graphs reused = 3410 0.47.465.859 I slot print_timing: id 0 | task 3528 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.465.891 I slot release: id 0 | task 3528 | stop processing: n_tokens = 448, truncated = 0 0.47.483.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 47373504 0.47.502.537 I slot launch_slot_: id 0 | task 3586 | processing task, is_child = 0 0.48.099.522 I slot print_timing: id 0 | task 3586 | prompt eval time = 82.06 ms / 327 tokens ( 0.25 ms per token, 3985.13 tokens per second) 0.48.099.528 I slot print_timing: id 0 | task 3586 | eval time = 514.91 ms / 52 tokens ( 10.10 ms per token, 99.05 tokens per second) 0.48.099.529 I slot print_timing: id 0 | task 3586 | total time = 596.97 ms / 379 tokens 0.48.099.530 I slot print_timing: id 0 | task 3586 | graphs reused = 3460 0.48.099.531 I slot print_timing: id 0 | task 3586 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.099.559 I slot release: id 0 | task 3586 | stop processing: n_tokens = 403, truncated = 0 0.48.121.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 48007172 0.48.139.716 I slot launch_slot_: id 0 | task 3639 | processing task, is_child = 0 0.49.028.981 I slot print_timing: id 0 | task 3639 | prompt eval time = 110.50 ms / 393 tokens ( 0.28 ms per token, 3556.56 tokens per second) 0.49.028.987 I slot print_timing: id 0 | task 3639 | eval time = 778.75 ms / 76 tokens ( 10.38 ms per token, 96.31 tokens per second) 0.49.028.988 I slot print_timing: id 0 | task 3639 | total time = 889.25 ms / 469 tokens 0.49.028.988 I slot print_timing: id 0 | task 3639 | graphs reused = 3534 0.49.028.989 I slot print_timing: id 0 | task 3639 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.029.020 I slot release: id 0 | task 3639 | stop processing: n_tokens = 493, truncated = 0 0.49.058.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 493, t_last = 48936633 0.49.080.332 I slot launch_slot_: id 0 | task 3716 | processing task, is_child = 0 0.49.844.774 I slot print_timing: id 0 | task 3716 | prompt eval time = 141.31 ms / 524 tokens ( 0.27 ms per token, 3708.21 tokens per second) 0.49.844.780 I slot print_timing: id 0 | task 3716 | eval time = 623.12 ms / 62 tokens ( 10.22 ms per token, 97.89 tokens per second) 0.49.844.781 I slot print_timing: id 0 | task 3716 | total time = 764.43 ms / 586 tokens 0.49.844.782 I slot print_timing: id 0 | task 3716 | graphs reused = 3594 0.49.844.783 I slot print_timing: id 0 | task 3716 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.844.816 I slot release: id 0 | task 3716 | stop processing: n_tokens = 610, truncated = 0 0.49.860.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 49752430 0.49.887.986 I slot launch_slot_: id 0 | task 3779 | processing task, is_child = 0 0.50.658.994 I slot print_timing: id 0 | task 3779 | prompt eval time = 158.82 ms / 602 tokens ( 0.26 ms per token, 3790.41 tokens per second) 0.50.658.999 I slot print_timing: id 0 | task 3779 | eval time = 612.16 ms / 61 tokens ( 10.20 ms per token, 98.01 tokens per second) 0.50.659.001 I slot print_timing: id 0 | task 3779 | total time = 770.99 ms / 663 tokens 0.50.659.001 I slot print_timing: id 0 | task 3779 | graphs reused = 3653 0.50.659.002 I slot print_timing: id 0 | task 3779 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.659.038 I slot release: id 0 | task 3779 | stop processing: n_tokens = 687, truncated = 0 0.50.674.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 50566651 0.50.702.758 I slot launch_slot_: id 0 | task 3841 | processing task, is_child = 0 0.51.505.093 I slot print_timing: id 0 | task 3841 | prompt eval time = 159.30 ms / 640 tokens ( 0.25 ms per token, 4017.65 tokens per second) 0.51.505.099 I slot print_timing: id 0 | task 3841 | eval time = 643.02 ms / 63 tokens ( 10.37 ms per token, 96.42 tokens per second) 0.51.505.100 I slot print_timing: id 0 | task 3841 | total time = 802.32 ms / 703 tokens 0.51.505.101 I slot print_timing: id 0 | task 3841 | graphs reused = 3714 0.51.505.101 I slot print_timing: id 0 | task 3841 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.505.139 I slot release: id 0 | task 3841 | stop processing: n_tokens = 727, truncated = 0 0.51.534.180 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 51412752 0.51.564.868 I slot launch_slot_: id 0 | task 3905 | processing task, is_child = 0 0.52.345.597 I slot print_timing: id 0 | task 3905 | prompt eval time = 158.95 ms / 629 tokens ( 0.25 ms per token, 3957.19 tokens per second) 0.52.345.603 I slot print_timing: id 0 | task 3905 | eval time = 621.76 ms / 62 tokens ( 10.19 ms per token, 98.11 tokens per second) 0.52.345.604 I slot print_timing: id 0 | task 3905 | total time = 780.71 ms / 691 tokens 0.52.345.605 I slot print_timing: id 0 | task 3905 | graphs reused = 3774 0.52.345.606 I slot print_timing: id 0 | task 3905 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.345.641 I slot release: id 0 | task 3905 | stop processing: n_tokens = 715, truncated = 0 0.52.369.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 52253254 0.52.398.759 I slot launch_slot_: id 0 | task 3968 | processing task, is_child = 0 0.53.094.535 I slot print_timing: id 0 | task 3968 | prompt eval time = 121.77 ms / 458 tokens ( 0.27 ms per token, 3761.25 tokens per second) 0.53.094.541 I slot print_timing: id 0 | task 3968 | eval time = 573.99 ms / 57 tokens ( 10.25 ms per token, 97.56 tokens per second) 0.53.094.542 I slot print_timing: id 0 | task 3968 | total time = 695.76 ms / 515 tokens 0.53.094.543 I slot print_timing: id 0 | task 3968 | graphs reused = 3828 0.53.094.545 I slot print_timing: id 0 | task 3968 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.094.576 I slot release: id 0 | task 3968 | stop processing: n_tokens = 539, truncated = 0 0.53.122.402 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 53002189 0.53.145.531 I slot launch_slot_: id 0 | task 4026 | processing task, is_child = 0 0.53.930.694 I slot print_timing: id 0 | task 4026 | prompt eval time = 151.83 ms / 594 tokens ( 0.26 ms per token, 3912.32 tokens per second) 0.53.930.700 I slot print_timing: id 0 | task 4026 | eval time = 633.32 ms / 63 tokens ( 10.21 ms per token, 97.90 tokens per second) 0.53.930.701 I slot print_timing: id 0 | task 4026 | total time = 785.15 ms / 657 tokens 0.53.930.701 I slot print_timing: id 0 | task 4026 | graphs reused = 3889 0.53.930.702 I slot print_timing: id 0 | task 4026 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.930.737 I slot release: id 0 | task 4026 | stop processing: n_tokens = 681, truncated = 0 0.53.959.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 681, t_last = 53838350 0.53.987.905 I slot launch_slot_: id 0 | task 4090 | processing task, is_child = 0 0.54.644.289 I slot print_timing: id 0 | task 4090 | prompt eval time = 146.06 ms / 572 tokens ( 0.26 ms per token, 3916.28 tokens per second) 0.54.644.295 I slot print_timing: id 0 | task 4090 | eval time = 510.31 ms / 51 tokens ( 10.21 ms per token, 97.98 tokens per second) 0.54.644.296 I slot print_timing: id 0 | task 4090 | total time = 656.37 ms / 623 tokens 0.54.644.297 I slot print_timing: id 0 | task 4090 | graphs reused = 3938 0.54.644.298 I slot print_timing: id 0 | task 4090 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.644.335 I slot release: id 0 | task 4090 | stop processing: n_tokens = 647, truncated = 0 0.54.674.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 647, t_last = 54551949 0.54.701.595 I slot launch_slot_: id 0 | task 4142 | processing task, is_child = 0 0.55.327.131 I slot print_timing: id 0 | task 4142 | prompt eval time = 124.61 ms / 502 tokens ( 0.25 ms per token, 4028.50 tokens per second) 0.55.327.137 I slot print_timing: id 0 | task 4142 | eval time = 500.91 ms / 50 tokens ( 10.22 ms per token, 97.82 tokens per second) 0.55.327.138 I slot print_timing: id 0 | task 4142 | total time = 625.52 ms / 552 tokens 0.55.327.138 I slot print_timing: id 0 | task 4142 | graphs reused = 3986 0.55.327.139 I slot print_timing: id 0 | task 4142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.327.173 I slot release: id 0 | task 4142 | stop processing: n_tokens = 576, truncated = 0 0.55.346.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 55234786 0.55.370.929 I slot launch_slot_: id 0 | task 4193 | processing task, is_child = 0 0.56.067.026 I slot print_timing: id 0 | task 4193 | prompt eval time = 121.33 ms / 479 tokens ( 0.25 ms per token, 3947.81 tokens per second) 0.56.067.032 I slot print_timing: id 0 | task 4193 | eval time = 574.75 ms / 57 tokens ( 10.26 ms per token, 97.43 tokens per second) 0.56.067.033 I slot print_timing: id 0 | task 4193 | total time = 696.08 ms / 536 tokens 0.56.067.034 I slot print_timing: id 0 | task 4193 | graphs reused = 4040 0.56.067.034 I slot print_timing: id 0 | task 4193 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.067.066 I slot release: id 0 | task 4193 | stop processing: n_tokens = 560, truncated = 0 0.56.095.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 55974679 0.56.123.032 I slot launch_slot_: id 0 | task 4251 | processing task, is_child = 0 0.56.715.754 I slot print_timing: id 0 | task 4251 | prompt eval time = 142.47 ms / 552 tokens ( 0.26 ms per token, 3874.53 tokens per second) 0.56.715.760 I slot print_timing: id 0 | task 4251 | eval time = 450.23 ms / 45 tokens ( 10.23 ms per token, 97.73 tokens per second) 0.56.715.761 I slot print_timing: id 0 | task 4251 | total time = 592.70 ms / 597 tokens 0.56.715.762 I slot print_timing: id 0 | task 4251 | graphs reused = 4083 0.56.715.763 I slot print_timing: id 0 | task 4251 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.715.798 I slot release: id 0 | task 4251 | stop processing: n_tokens = 621, truncated = 0 0.56.721.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 621, t_last = 56623411 0.56.747.871 I slot launch_slot_: id 0 | task 4297 | processing task, is_child = 0 0.59.892.413 I slot print_timing: id 0 | task 4297 | n_gen = 297, tg = 98.40 t/s, tg_3s = 98.74 t/s 1.02.896.297 I slot print_timing: id 0 | task 4297 | n_gen = 591, tg = 98.14 t/s, tg_3s = 97.87 t/s 1.05.906.449 I slot print_timing: id 0 | task 4297 | n_gen = 881, tg = 97.54 t/s, tg_3s = 96.34 t/s 1.07.401.142 I slot print_timing: id 0 | task 4297 | prompt eval time = 136.53 ms / 514 tokens ( 0.27 ms per token, 3764.82 tokens per second) 1.07.401.148 I slot print_timing: id 0 | task 4297 | eval time = 10516.73 ms / 1024 tokens ( 10.28 ms per token, 97.27 tokens per second) 1.07.401.149 I slot print_timing: id 0 | task 4297 | total time = 10653.25 ms / 1538 tokens 1.07.401.150 I slot print_timing: id 0 | task 4297 | graphs reused = 5101 1.07.401.150 I slot print_timing: id 0 | task 4297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.401.186 I slot release: id 0 | task 4297 | stop processing: n_tokens = 1562, truncated = 0 1.07.421.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1562, t_last = 67308799 1.07.485.072 I slot launch_slot_: id 0 | task 5322 | processing task, is_child = 0 1.08.013.220 I slot print_timing: id 0 | task 5322 | prompt eval time = 110.39 ms / 428 tokens ( 0.26 ms per token, 3877.23 tokens per second) 1.08.013.226 I slot print_timing: id 0 | task 5322 | eval time = 417.69 ms / 42 tokens ( 10.19 ms per token, 98.16 tokens per second) 1.08.013.227 I slot print_timing: id 0 | task 5322 | total time = 528.08 ms / 470 tokens 1.08.013.228 I slot print_timing: id 0 | task 5322 | graphs reused = 5141 1.08.013.229 I slot print_timing: id 0 | task 5322 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.013.262 I slot release: id 0 | task 5322 | stop processing: n_tokens = 494, truncated = 0 1.08.028.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 67920875 1.08.049.702 I slot launch_slot_: id 0 | task 5365 | processing task, is_child = 0 1.08.864.308 I slot print_timing: id 0 | task 5365 | prompt eval time = 138.22 ms / 521 tokens ( 0.27 ms per token, 3769.38 tokens per second) 1.08.864.315 I slot print_timing: id 0 | task 5365 | eval time = 676.37 ms / 66 tokens ( 10.41 ms per token, 96.10 tokens per second) 1.08.864.316 I slot print_timing: id 0 | task 5365 | total time = 814.59 ms / 587 tokens 1.08.864.317 I slot print_timing: id 0 | task 5365 | graphs reused = 5205 1.08.864.318 I slot print_timing: id 0 | task 5365 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.864.355 I slot release: id 0 | task 5365 | stop processing: n_tokens = 611, truncated = 0 1.08.869.437 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 68771969 1.08.896.372 I slot launch_slot_: id 0 | task 5432 | processing task, is_child = 0 1.09.534.147 I slot print_timing: id 0 | task 5432 | prompt eval time = 121.56 ms / 472 tokens ( 0.26 ms per token, 3882.70 tokens per second) 1.09.534.154 I slot print_timing: id 0 | task 5432 | eval time = 516.19 ms / 51 tokens ( 10.32 ms per token, 96.86 tokens per second) 1.09.534.155 I slot print_timing: id 0 | task 5432 | total time = 637.76 ms / 523 tokens 1.09.534.156 I slot print_timing: id 0 | task 5432 | graphs reused = 5253 1.09.534.157 I slot print_timing: id 0 | task 5432 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.534.188 I slot release: id 0 | task 5432 | stop processing: n_tokens = 547, truncated = 0 1.09.552.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 69441802 1.09.576.248 I slot launch_slot_: id 0 | task 5484 | processing task, is_child = 0 1.10.124.918 I slot print_timing: id 0 | task 5484 | prompt eval time = 110.13 ms / 428 tokens ( 0.26 ms per token, 3886.21 tokens per second) 1.10.124.924 I slot print_timing: id 0 | task 5484 | eval time = 438.52 ms / 44 tokens ( 10.20 ms per token, 98.06 tokens per second) 1.10.124.925 I slot print_timing: id 0 | task 5484 | total time = 548.65 ms / 472 tokens 1.10.124.926 I slot print_timing: id 0 | task 5484 | graphs reused = 5295 1.10.124.927 I slot print_timing: id 0 | task 5484 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.124.963 I slot release: id 0 | task 5484 | stop processing: n_tokens = 496, truncated = 0 1.10.148.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 70032577 1.10.170.965 I slot launch_slot_: id 0 | task 5529 | processing task, is_child = 0 1.10.745.100 I slot print_timing: id 0 | task 5529 | prompt eval time = 121.32 ms / 456 tokens ( 0.27 ms per token, 3758.65 tokens per second) 1.10.745.106 I slot print_timing: id 0 | task 5529 | eval time = 452.80 ms / 45 tokens ( 10.29 ms per token, 97.17 tokens per second) 1.10.745.107 I slot print_timing: id 0 | task 5529 | total time = 574.12 ms / 501 tokens 1.10.745.108 I slot print_timing: id 0 | task 5529 | graphs reused = 5337 1.10.745.109 I slot print_timing: id 0 | task 5529 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.745.141 I slot release: id 0 | task 5529 | stop processing: n_tokens = 525, truncated = 0 1.10.769.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 70652754 1.10.792.672 I slot launch_slot_: id 0 | task 5575 | processing task, is_child = 0 1.11.340.157 I slot print_timing: id 0 | task 5575 | prompt eval time = 110.75 ms / 439 tokens ( 0.25 ms per token, 3963.95 tokens per second) 1.11.340.162 I slot print_timing: id 0 | task 5575 | eval time = 436.72 ms / 44 tokens ( 10.16 ms per token, 98.46 tokens per second) 1.11.340.163 I slot print_timing: id 0 | task 5575 | total time = 547.47 ms / 483 tokens 1.11.340.165 I slot print_timing: id 0 | task 5575 | graphs reused = 5379 1.11.340.165 I slot print_timing: id 0 | task 5575 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.340.198 I slot release: id 0 | task 5575 | stop processing: n_tokens = 507, truncated = 0 1.11.366.058 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 507, t_last = 71247811 1.11.387.614 I slot launch_slot_: id 0 | task 5620 | processing task, is_child = 0 1.12.140.984 I slot print_timing: id 0 | task 5620 | prompt eval time = 152.23 ms / 600 tokens ( 0.25 ms per token, 3941.48 tokens per second) 1.12.140.990 I slot print_timing: id 0 | task 5620 | eval time = 601.13 ms / 60 tokens ( 10.19 ms per token, 98.15 tokens per second) 1.12.140.991 I slot print_timing: id 0 | task 5620 | total time = 753.35 ms / 660 tokens 1.12.140.992 I slot print_timing: id 0 | task 5620 | graphs reused = 5437 1.12.140.993 I slot print_timing: id 0 | task 5620 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.141.032 I slot release: id 0 | task 5620 | stop processing: n_tokens = 684, truncated = 0 1.12.158.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 72048645 1.12.187.986 I slot launch_slot_: id 0 | task 5681 | processing task, is_child = 0 1.12.732.268 I slot print_timing: id 0 | task 5681 | prompt eval time = 121.37 ms / 473 tokens ( 0.26 ms per token, 3897.30 tokens per second) 1.12.732.273 I slot print_timing: id 0 | task 5681 | eval time = 422.90 ms / 42 tokens ( 10.31 ms per token, 96.95 tokens per second) 1.12.732.274 I slot print_timing: id 0 | task 5681 | total time = 544.26 ms / 515 tokens 1.12.732.275 I slot print_timing: id 0 | task 5681 | graphs reused = 5476 1.12.732.276 I slot print_timing: id 0 | task 5681 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.732.309 I slot release: id 0 | task 5681 | stop processing: n_tokens = 539, truncated = 0 1.12.748.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 539, t_last = 72639922 1.12.772.239 I slot launch_slot_: id 0 | task 5724 | processing task, is_child = 0 1.13.633.083 I slot print_timing: id 0 | task 5724 | prompt eval time = 204.13 ms / 835 tokens ( 0.24 ms per token, 4090.51 tokens per second) 1.13.633.089 I slot print_timing: id 0 | task 5724 | eval time = 656.70 ms / 65 tokens ( 10.26 ms per token, 97.46 tokens per second) 1.13.633.090 I slot print_timing: id 0 | task 5724 | total time = 860.83 ms / 900 tokens 1.13.633.091 I slot print_timing: id 0 | task 5724 | graphs reused = 5539 1.13.633.092 I slot print_timing: id 0 | task 5724 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.633.137 I slot release: id 0 | task 5724 | stop processing: n_tokens = 924, truncated = 0 1.13.650.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 73540751 1.13.687.576 I slot launch_slot_: id 0 | task 5790 | processing task, is_child = 0 1.14.242.452 I slot print_timing: id 0 | task 5790 | prompt eval time = 121.21 ms / 454 tokens ( 0.27 ms per token, 3745.44 tokens per second) 1.14.242.457 I slot print_timing: id 0 | task 5790 | eval time = 433.64 ms / 43 tokens ( 10.32 ms per token, 96.85 tokens per second) 1.14.242.459 I slot print_timing: id 0 | task 5790 | total time = 554.86 ms / 497 tokens 1.14.242.459 I slot print_timing: id 0 | task 5790 | graphs reused = 5579 1.14.242.460 I slot print_timing: id 0 | task 5790 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.242.495 I slot release: id 0 | task 5790 | stop processing: n_tokens = 521, truncated = 0 1.14.270.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 74150108 1.14.293.465 I slot launch_slot_: id 0 | task 5834 | processing task, is_child = 0 1.14.946.141 I slot print_timing: id 0 | task 5834 | prompt eval time = 169.12 ms / 667 tokens ( 0.25 ms per token, 3943.83 tokens per second) 1.14.946.147 I slot print_timing: id 0 | task 5834 | eval time = 483.53 ms / 48 tokens ( 10.29 ms per token, 97.20 tokens per second) 1.14.946.148 I slot print_timing: id 0 | task 5834 | total time = 652.66 ms / 715 tokens 1.14.946.149 I slot print_timing: id 0 | task 5834 | graphs reused = 5625 1.14.946.150 I slot print_timing: id 0 | task 5834 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.946.192 I slot release: id 0 | task 5834 | stop processing: n_tokens = 741, truncated = 0 1.14.972.406 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 741, t_last = 74853805 1.15.016.357 I slot launch_slot_: id 0 | task 5883 | processing task, is_child = 0 1.15.901.308 I slot print_timing: id 0 | task 5883 | prompt eval time = 160.16 ms / 628 tokens ( 0.26 ms per token, 3920.98 tokens per second) 1.15.901.314 I slot print_timing: id 0 | task 5883 | eval time = 724.77 ms / 69 tokens ( 10.66 ms per token, 93.82 tokens per second) 1.15.901.315 I slot print_timing: id 0 | task 5883 | total time = 884.93 ms / 697 tokens 1.15.901.316 I slot print_timing: id 0 | task 5883 | graphs reused = 5692 1.15.901.317 I slot print_timing: id 0 | task 5883 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.901.361 I slot release: id 0 | task 5883 | stop processing: n_tokens = 858, truncated = 0 1.15.922.390 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 858, t_last = 75808974 1.15.959.136 I slot launch_slot_: id 0 | task 5953 | processing task, is_child = 0 1.16.877.845 I slot print_timing: id 0 | task 5953 | prompt eval time = 149.56 ms / 578 tokens ( 0.26 ms per token, 3864.77 tokens per second) 1.16.877.851 I slot print_timing: id 0 | task 5953 | eval time = 769.13 ms / 76 tokens ( 10.26 ms per token, 97.51 tokens per second) 1.16.877.852 I slot print_timing: id 0 | task 5953 | total time = 918.69 ms / 654 tokens 1.16.877.853 I slot print_timing: id 0 | task 5953 | graphs reused = 5766 1.16.877.853 I slot print_timing: id 0 | task 5953 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.877.893 I slot release: id 0 | task 5953 | stop processing: n_tokens = 678, truncated = 0 1.16.883.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 76785506 1.16.915.758 I slot launch_slot_: id 0 | task 6030 | processing task, is_child = 0 1.17.704.127 I slot print_timing: id 0 | task 6030 | prompt eval time = 121.60 ms / 461 tokens ( 0.26 ms per token, 3791.06 tokens per second) 1.17.704.133 I slot print_timing: id 0 | task 6030 | eval time = 666.75 ms / 66 tokens ( 10.26 ms per token, 97.49 tokens per second) 1.17.704.134 I slot print_timing: id 0 | task 6030 | total time = 788.35 ms / 527 tokens 1.17.704.135 I slot print_timing: id 0 | task 6030 | graphs reused = 5829 1.17.704.135 I slot print_timing: id 0 | task 6030 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.704.167 I slot release: id 0 | task 6030 | stop processing: n_tokens = 551, truncated = 0 1.17.724.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 551, t_last = 77611780 1.17.748.044 I slot launch_slot_: id 0 | task 6097 | processing task, is_child = 0 1.18.393.703 I slot print_timing: id 0 | task 6097 | prompt eval time = 156.11 ms / 613 tokens ( 0.25 ms per token, 3926.82 tokens per second) 1.18.393.709 I slot print_timing: id 0 | task 6097 | eval time = 489.54 ms / 48 tokens ( 10.42 ms per token, 96.01 tokens per second) 1.18.393.710 I slot print_timing: id 0 | task 6097 | total time = 645.64 ms / 661 tokens 1.18.393.711 I slot print_timing: id 0 | task 6097 | graphs reused = 5875 1.18.393.712 I slot print_timing: id 0 | task 6097 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.393.748 I slot release: id 0 | task 6097 | stop processing: n_tokens = 685, truncated = 0 1.18.411.657 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 78301361 1.18.439.717 I slot launch_slot_: id 0 | task 6146 | processing task, is_child = 0 1.19.289.721 I slot print_timing: id 0 | task 6146 | prompt eval time = 194.36 ms / 794 tokens ( 0.24 ms per token, 4085.12 tokens per second) 1.19.289.728 I slot print_timing: id 0 | task 6146 | eval time = 655.62 ms / 65 tokens ( 10.24 ms per token, 97.62 tokens per second) 1.19.289.730 I slot print_timing: id 0 | task 6146 | total time = 849.99 ms / 859 tokens 1.19.289.731 I slot print_timing: id 0 | task 6146 | graphs reused = 5938 1.19.289.731 I slot print_timing: id 0 | task 6146 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.289.785 I slot release: id 0 | task 6146 | stop processing: n_tokens = 883, truncated = 0 1.19.308.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 79197399 1.19.363.718 I slot launch_slot_: id 0 | task 6212 | processing task, is_child = 0 1.20.058.527 I slot print_timing: id 0 | task 6212 | prompt eval time = 111.09 ms / 431 tokens ( 0.26 ms per token, 3879.77 tokens per second) 1.20.058.534 I slot print_timing: id 0 | task 6212 | eval time = 583.70 ms / 58 tokens ( 10.24 ms per token, 97.65 tokens per second) 1.20.058.535 I slot print_timing: id 0 | task 6212 | total time = 694.79 ms / 489 tokens 1.20.058.536 I slot print_timing: id 0 | task 6212 | graphs reused = 5994 1.20.058.537 I slot print_timing: id 0 | task 6212 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.058.573 I slot release: id 0 | task 6212 | stop processing: n_tokens = 687, truncated = 0 1.20.073.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 79966187 1.20.097.344 I slot launch_slot_: id 0 | task 6271 | processing task, is_child = 0 1.20.755.545 I slot print_timing: id 0 | task 6271 | prompt eval time = 144.97 ms / 563 tokens ( 0.26 ms per token, 3883.67 tokens per second) 1.20.755.551 I slot print_timing: id 0 | task 6271 | eval time = 513.22 ms / 50 tokens ( 10.47 ms per token, 95.48 tokens per second) 1.20.755.552 I slot print_timing: id 0 | task 6271 | total time = 658.18 ms / 613 tokens 1.20.755.553 I slot print_timing: id 0 | task 6271 | graphs reused = 6042 1.20.755.554 I slot print_timing: id 0 | task 6271 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.755.591 I slot release: id 0 | task 6271 | stop processing: n_tokens = 637, truncated = 0 1.20.773.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 80663204 1.20.813.304 I slot launch_slot_: id 0 | task 6322 | processing task, is_child = 0 1.21.377.606 I slot print_timing: id 0 | task 6322 | prompt eval time = 82.33 ms / 331 tokens ( 0.25 ms per token, 4020.26 tokens per second) 1.21.377.611 I slot print_timing: id 0 | task 6322 | eval time = 481.95 ms / 48 tokens ( 10.25 ms per token, 97.52 tokens per second) 1.21.377.613 I slot print_timing: id 0 | task 6322 | total time = 564.28 ms / 379 tokens 1.21.377.614 I slot print_timing: id 0 | task 6322 | graphs reused = 6087 1.21.377.614 I slot print_timing: id 0 | task 6322 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.377.648 I slot release: id 0 | task 6322 | stop processing: n_tokens = 513, truncated = 0 1.21.395.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 81285262 1.21.414.317 I slot launch_slot_: id 0 | task 6371 | processing task, is_child = 0 1.22.214.125 I slot print_timing: id 0 | task 6371 | prompt eval time = 123.42 ms / 489 tokens ( 0.25 ms per token, 3962.02 tokens per second) 1.22.214.130 I slot print_timing: id 0 | task 6371 | eval time = 676.37 ms / 67 tokens ( 10.25 ms per token, 97.58 tokens per second) 1.22.214.132 I slot print_timing: id 0 | task 6371 | total time = 799.79 ms / 556 tokens 1.22.214.132 I slot print_timing: id 0 | task 6371 | graphs reused = 6152 1.22.214.133 I slot print_timing: id 0 | task 6371 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.214.168 I slot release: id 0 | task 6371 | stop processing: n_tokens = 580, truncated = 0 1.22.236.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 82121781 1.22.262.947 I slot launch_slot_: id 0 | task 6439 | processing task, is_child = 0 1.22.931.256 I slot print_timing: id 0 | task 6439 | prompt eval time = 124.56 ms / 510 tokens ( 0.24 ms per token, 4094.41 tokens per second) 1.22.931.262 I slot print_timing: id 0 | task 6439 | eval time = 543.73 ms / 54 tokens ( 10.26 ms per token, 97.48 tokens per second) 1.22.931.263 I slot print_timing: id 0 | task 6439 | total time = 668.29 ms / 564 tokens 1.22.931.264 I slot print_timing: id 0 | task 6439 | graphs reused = 6204 1.22.931.265 I slot print_timing: id 0 | task 6439 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.931.301 I slot release: id 0 | task 6439 | stop processing: n_tokens = 588, truncated = 0 1.22.956.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 82838914 1.22.981.253 I slot launch_slot_: id 0 | task 6494 | processing task, is_child = 0 1.23.857.824 I slot print_timing: id 0 | task 6494 | prompt eval time = 159.50 ms / 631 tokens ( 0.25 ms per token, 3956.16 tokens per second) 1.23.857.830 I slot print_timing: id 0 | task 6494 | eval time = 717.05 ms / 71 tokens ( 10.24 ms per token, 97.62 tokens per second) 1.23.857.831 I slot print_timing: id 0 | task 6494 | total time = 876.55 ms / 702 tokens 1.23.857.831 I slot print_timing: id 0 | task 6494 | graphs reused = 6273 1.23.857.832 I slot print_timing: id 0 | task 6494 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.857.870 I slot release: id 0 | task 6494 | stop processing: n_tokens = 726, truncated = 0 1.23.877.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 726, t_last = 83765484 1.23.908.949 I slot launch_slot_: id 0 | task 6566 | processing task, is_child = 0 1.24.600.699 I slot print_timing: id 0 | task 6566 | prompt eval time = 145.72 ms / 570 tokens ( 0.26 ms per token, 3911.66 tokens per second) 1.24.600.705 I slot print_timing: id 0 | task 6566 | eval time = 546.01 ms / 54 tokens ( 10.30 ms per token, 97.07 tokens per second) 1.24.600.706 I slot print_timing: id 0 | task 6566 | total time = 691.73 ms / 624 tokens 1.24.600.706 I slot print_timing: id 0 | task 6566 | graphs reused = 6325 1.24.600.707 I slot print_timing: id 0 | task 6566 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.600.741 I slot release: id 0 | task 6566 | stop processing: n_tokens = 648, truncated = 0 1.24.621.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 84508355 1.24.648.902 I slot launch_slot_: id 0 | task 6621 | processing task, is_child = 0 1.25.343.383 I slot print_timing: id 0 | task 6621 | prompt eval time = 197.65 ms / 792 tokens ( 0.25 ms per token, 4007.18 tokens per second) 1.25.343.388 I slot print_timing: id 0 | task 6621 | eval time = 496.82 ms / 49 tokens ( 10.35 ms per token, 96.61 tokens per second) 1.25.343.390 I slot print_timing: id 0 | task 6621 | total time = 694.47 ms / 841 tokens 1.25.343.390 I slot print_timing: id 0 | task 6621 | graphs reused = 6372 1.25.343.391 I slot print_timing: id 0 | task 6621 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.343.435 I slot release: id 0 | task 6621 | stop processing: n_tokens = 867, truncated = 0 1.25.364.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 867, t_last = 85251048 1.25.400.403 I slot launch_slot_: id 0 | task 6671 | processing task, is_child = 0 1.25.997.225 I slot print_timing: id 0 | task 6671 | prompt eval time = 145.16 ms / 564 tokens ( 0.26 ms per token, 3885.50 tokens per second) 1.25.997.231 I slot print_timing: id 0 | task 6671 | eval time = 451.65 ms / 45 tokens ( 10.26 ms per token, 97.42 tokens per second) 1.25.997.232 I slot print_timing: id 0 | task 6671 | total time = 596.80 ms / 609 tokens 1.25.997.233 I slot print_timing: id 0 | task 6671 | graphs reused = 6415 1.25.997.234 I slot print_timing: id 0 | task 6671 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.997.273 I slot release: id 0 | task 6671 | stop processing: n_tokens = 635, truncated = 0 1.26.016.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 85904886 1.26.044.118 I slot launch_slot_: id 0 | task 6717 | processing task, is_child = 0 1.26.756.948 I slot print_timing: id 0 | task 6717 | prompt eval time = 159.94 ms / 617 tokens ( 0.26 ms per token, 3857.79 tokens per second) 1.26.756.954 I slot print_timing: id 0 | task 6717 | eval time = 552.88 ms / 55 tokens ( 10.24 ms per token, 97.67 tokens per second) 1.26.756.955 I slot print_timing: id 0 | task 6717 | total time = 712.81 ms / 672 tokens 1.26.756.956 I slot print_timing: id 0 | task 6717 | graphs reused = 6468 1.26.756.957 I slot print_timing: id 0 | task 6717 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.756.995 I slot release: id 0 | task 6717 | stop processing: n_tokens = 696, truncated = 0 1.26.778.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 696, t_last = 86664609 1.26.807.581 I slot launch_slot_: id 0 | task 6773 | processing task, is_child = 0 1.27.629.064 I slot print_timing: id 0 | task 6773 | prompt eval time = 145.53 ms / 572 tokens ( 0.25 ms per token, 3930.41 tokens per second) 1.27.629.070 I slot print_timing: id 0 | task 6773 | eval time = 675.93 ms / 67 tokens ( 10.24 ms per token, 97.64 tokens per second) 1.27.629.071 I slot print_timing: id 0 | task 6773 | total time = 821.47 ms / 639 tokens 1.27.629.072 I slot print_timing: id 0 | task 6773 | graphs reused = 6533 1.27.629.073 I slot print_timing: id 0 | task 6773 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.629.110 I slot release: id 0 | task 6773 | stop processing: n_tokens = 663, truncated = 0 1.27.654.202 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 663, t_last = 87536723 1.27.682.661 I slot launch_slot_: id 0 | task 6841 | processing task, is_child = 0 1.28.410.107 I slot print_timing: id 0 | task 6841 | prompt eval time = 179.86 ms / 712 tokens ( 0.25 ms per token, 3958.70 tokens per second) 1.28.410.113 I slot print_timing: id 0 | task 6841 | eval time = 547.57 ms / 54 tokens ( 10.33 ms per token, 96.79 tokens per second) 1.28.410.114 I slot print_timing: id 0 | task 6841 | total time = 727.43 ms / 766 tokens 1.28.410.114 I slot print_timing: id 0 | task 6841 | graphs reused = 6584 1.28.410.115 I slot print_timing: id 0 | task 6841 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.410.157 I slot release: id 0 | task 6841 | stop processing: n_tokens = 790, truncated = 0 1.28.434.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 88317770 1.28.473.391 I slot launch_slot_: id 0 | task 6896 | processing task, is_child = 0 1.29.753.867 I slot print_timing: id 0 | task 6896 | prompt eval time = 194.78 ms / 791 tokens ( 0.25 ms per token, 4061.10 tokens per second) 1.29.753.873 I slot print_timing: id 0 | task 6896 | eval time = 1085.68 ms / 107 tokens ( 10.24 ms per token, 97.63 tokens per second) 1.29.753.874 I slot print_timing: id 0 | task 6896 | total time = 1280.46 ms / 898 tokens 1.29.753.875 I slot print_timing: id 0 | task 6896 | graphs reused = 6689 1.29.753.876 I slot print_timing: id 0 | task 6896 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.753.919 I slot release: id 0 | task 6896 | stop processing: n_tokens = 922, truncated = 0 1.29.773.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 922, t_last = 89661533 1.29.824.244 I slot launch_slot_: id 0 | task 7004 | processing task, is_child = 0 1.32.918.721 I slot print_timing: id 0 | task 7004 | n_gen = 297, tg = 98.52 t/s, tg_3s = 98.85 t/s 1.35.925.555 I slot print_timing: id 0 | task 7004 | n_gen = 591, tg = 98.15 t/s, tg_3s = 97.78 t/s 1.37.830.881 I slot print_timing: id 0 | task 7004 | prompt eval time = 89.90 ms / 369 tokens ( 0.24 ms per token, 4104.38 tokens per second) 1.37.830.887 I slot print_timing: id 0 | task 7004 | eval time = 7916.71 ms / 773 tokens ( 10.25 ms per token, 97.52 tokens per second) 1.37.830.888 I slot print_timing: id 0 | task 7004 | total time = 8006.62 ms / 1142 tokens 1.37.830.888 I slot print_timing: id 0 | task 7004 | graphs reused = 7457 1.37.830.889 I slot print_timing: id 0 | task 7004 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.830.921 I slot release: id 0 | task 7004 | stop processing: n_tokens = 1166, truncated = 0 1.37.858.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1166, t_last = 97738534 1.37.858.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.881 MiB) 1.37.862.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 56.255 MiB) 1.37.865.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.599 MiB) 1.37.932.283 I slot launch_slot_: id 0 | task 7778 | processing task, is_child = 0 1.38.660.857 I slot print_timing: id 0 | task 7778 | prompt eval time = 108.75 ms / 388 tokens ( 0.28 ms per token, 3567.82 tokens per second) 1.38.660.863 I slot print_timing: id 0 | task 7778 | eval time = 619.80 ms / 62 tokens ( 10.16 ms per token, 98.42 tokens per second) 1.38.660.865 I slot print_timing: id 0 | task 7778 | total time = 728.55 ms / 450 tokens 1.38.660.865 I slot print_timing: id 0 | task 7778 | graphs reused = 7517 1.38.660.866 I slot print_timing: id 0 | task 7778 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.660.898 I slot release: id 0 | task 7778 | stop processing: n_tokens = 474, truncated = 0 1.38.684.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 98568511 1.38.684.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.38.717.043 I slot launch_slot_: id 0 | task 7841 | processing task, is_child = 0 1.39.469.156 I slot print_timing: id 0 | task 7841 | prompt eval time = 90.30 ms / 370 tokens ( 0.24 ms per token, 4097.50 tokens per second) 1.39.469.162 I slot print_timing: id 0 | task 7841 | eval time = 661.79 ms / 66 tokens ( 10.18 ms per token, 98.22 tokens per second) 1.39.469.163 I slot print_timing: id 0 | task 7841 | total time = 752.09 ms / 436 tokens 1.39.469.164 I slot print_timing: id 0 | task 7841 | graphs reused = 7581 1.39.469.165 I slot print_timing: id 0 | task 7841 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.469.195 I slot release: id 0 | task 7841 | stop processing: n_tokens = 460, truncated = 0 1.39.488.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 99376808 1.39.488.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.537 MiB) 1.39.515.098 I slot launch_slot_: id 0 | task 7908 | processing task, is_child = 0 1.40.203.080 I slot print_timing: id 0 | task 7908 | prompt eval time = 89.73 ms / 340 tokens ( 0.26 ms per token, 3789.19 tokens per second) 1.40.203.086 I slot print_timing: id 0 | task 7908 | eval time = 598.24 ms / 60 tokens ( 10.14 ms per token, 98.62 tokens per second) 1.40.203.087 I slot print_timing: id 0 | task 7908 | total time = 687.96 ms / 400 tokens 1.40.203.088 I slot print_timing: id 0 | task 7908 | graphs reused = 7639 1.40.203.089 I slot print_timing: id 0 | task 7908 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.203.120 I slot release: id 0 | task 7908 | stop processing: n_tokens = 424, truncated = 0 1.40.207.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 100110733 1.40.207.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.40.231.373 I slot launch_slot_: id 0 | task 7969 | processing task, is_child = 0 1.41.128.236 I slot print_timing: id 0 | task 7969 | prompt eval time = 109.42 ms / 409 tokens ( 0.27 ms per token, 3737.72 tokens per second) 1.41.128.243 I slot print_timing: id 0 | task 7969 | eval time = 787.42 ms / 78 tokens ( 10.23 ms per token, 97.79 tokens per second) 1.41.128.244 I slot print_timing: id 0 | task 7969 | total time = 896.84 ms / 487 tokens 1.41.128.245 I slot print_timing: id 0 | task 7969 | graphs reused = 7715 1.41.128.246 I slot print_timing: id 0 | task 7969 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.128.280 I slot release: id 0 | task 7969 | stop processing: n_tokens = 511, truncated = 0 1.41.152.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 101035893 1.41.152.122 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.819 MiB) 1.41.180.789 I slot launch_slot_: id 0 | task 8048 | processing task, is_child = 0 1.42.245.225 I slot print_timing: id 0 | task 8048 | prompt eval time = 110.06 ms / 422 tokens ( 0.26 ms per token, 3834.27 tokens per second) 1.42.245.231 I slot print_timing: id 0 | task 8048 | eval time = 954.36 ms / 94 tokens ( 10.26 ms per token, 97.45 tokens per second) 1.42.245.232 I slot print_timing: id 0 | task 8048 | total time = 1064.42 ms / 516 tokens 1.42.245.233 I slot print_timing: id 0 | task 8048 | graphs reused = 7806 1.42.245.234 I slot print_timing: id 0 | task 8048 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.245.266 I slot release: id 0 | task 8048 | stop processing: n_tokens = 540, truncated = 0 1.42.269.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 102152879 1.42.269.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.695 MiB) 1.42.300.079 I slot launch_slot_: id 0 | task 8143 | processing task, is_child = 0 1.43.566.643 I slot print_timing: id 0 | task 8143 | prompt eval time = 124.15 ms / 499 tokens ( 0.25 ms per token, 4019.27 tokens per second) 1.43.566.650 I slot print_timing: id 0 | task 8143 | eval time = 1142.39 ms / 112 tokens ( 10.29 ms per token, 97.16 tokens per second) 1.43.566.651 I slot print_timing: id 0 | task 8143 | total time = 1266.55 ms / 611 tokens 1.43.566.652 I slot print_timing: id 0 | task 8143 | graphs reused = 7916 1.43.566.653 I slot print_timing: id 0 | task 8143 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.566.687 I slot release: id 0 | task 8143 | stop processing: n_tokens = 639, truncated = 0 1.43.591.785 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 103474300 1.43.591.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.724 MiB) 1.43.623.313 I slot launch_slot_: id 0 | task 8256 | processing task, is_child = 0 1.44.150.371 I slot print_timing: id 0 | task 8256 | prompt eval time = 89.67 ms / 345 tokens ( 0.26 ms per token, 3847.27 tokens per second) 1.44.150.377 I slot print_timing: id 0 | task 8256 | eval time = 437.37 ms / 44 tokens ( 10.17 ms per token, 98.32 tokens per second) 1.44.150.378 I slot print_timing: id 0 | task 8256 | total time = 527.04 ms / 389 tokens 1.44.150.379 I slot print_timing: id 0 | task 8256 | graphs reused = 7958 1.44.150.380 I slot print_timing: id 0 | task 8256 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.150.411 I slot release: id 0 | task 8256 | stop processing: n_tokens = 413, truncated = 0 1.44.169.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 104058024 1.44.169.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 1.44.193.346 I slot launch_slot_: id 0 | task 8301 | processing task, is_child = 0 1.44.719.233 I slot print_timing: id 0 | task 8301 | prompt eval time = 89.98 ms / 348 tokens ( 0.26 ms per token, 3867.44 tokens per second) 1.44.719.239 I slot print_timing: id 0 | task 8301 | eval time = 435.89 ms / 44 tokens ( 10.14 ms per token, 98.65 tokens per second) 1.44.719.240 I slot print_timing: id 0 | task 8301 | total time = 525.87 ms / 392 tokens 1.44.719.241 I slot print_timing: id 0 | task 8301 | graphs reused = 8000 1.44.719.242 I slot print_timing: id 0 | task 8301 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.719.272 I slot release: id 0 | task 8301 | stop processing: n_tokens = 416, truncated = 0 1.44.746.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 104626885 1.44.746.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.381 MiB) 1.44.773.923 I slot launch_slot_: id 0 | task 8346 | processing task, is_child = 0 1.45.562.502 I slot print_timing: id 0 | task 8346 | prompt eval time = 110.20 ms / 408 tokens ( 0.27 ms per token, 3702.43 tokens per second) 1.45.562.508 I slot print_timing: id 0 | task 8346 | eval time = 678.36 ms / 68 tokens ( 10.12 ms per token, 98.77 tokens per second) 1.45.562.509 I slot print_timing: id 0 | task 8346 | total time = 788.56 ms / 476 tokens 1.45.562.510 I slot print_timing: id 0 | task 8346 | graphs reused = 8066 1.45.562.511 I slot print_timing: id 0 | task 8346 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.562.542 I slot release: id 0 | task 8346 | stop processing: n_tokens = 500, truncated = 0 1.45.588.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 105470155 1.45.589.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 72.350 MiB) 1.45.593.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.287 MiB) 1.45.620.939 I slot launch_slot_: id 0 | task 8415 | processing task, is_child = 0 1.46.359.317 I slot print_timing: id 0 | task 8415 | prompt eval time = 121.08 ms / 465 tokens ( 0.26 ms per token, 3840.31 tokens per second) 1.46.359.323 I slot print_timing: id 0 | task 8415 | eval time = 617.27 ms / 61 tokens ( 10.29 ms per token, 97.20 tokens per second) 1.46.359.324 I slot print_timing: id 0 | task 8415 | total time = 738.36 ms / 526 tokens 1.46.359.324 I slot print_timing: id 0 | task 8415 | graphs reused = 8124 1.46.359.326 I slot print_timing: id 0 | task 8415 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.359.361 I slot release: id 0 | task 8415 | stop processing: n_tokens = 550, truncated = 0 1.46.363.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 550, t_last = 106266974 1.46.363.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.662 MiB) 1.46.387.210 I slot launch_slot_: id 0 | task 8477 | processing task, is_child = 0 1.47.095.352 I slot print_timing: id 0 | task 8477 | prompt eval time = 109.28 ms / 399 tokens ( 0.27 ms per token, 3651.14 tokens per second) 1.47.095.358 I slot print_timing: id 0 | task 8477 | eval time = 598.84 ms / 60 tokens ( 10.15 ms per token, 98.52 tokens per second) 1.47.095.359 I slot print_timing: id 0 | task 8477 | total time = 708.12 ms / 459 tokens 1.47.095.359 I slot print_timing: id 0 | task 8477 | graphs reused = 8182 1.47.095.360 I slot print_timing: id 0 | task 8477 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.095.393 I slot release: id 0 | task 8477 | stop processing: n_tokens = 500, truncated = 0 1.47.109.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 107003006 1.47.109.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.600 MiB) 1.47.136.399 I slot launch_slot_: id 0 | task 8538 | processing task, is_child = 0 1.47.970.707 I slot print_timing: id 0 | task 8538 | prompt eval time = 109.79 ms / 419 tokens ( 0.26 ms per token, 3816.52 tokens per second) 1.47.970.713 I slot print_timing: id 0 | task 8538 | eval time = 724.51 ms / 72 tokens ( 10.20 ms per token, 98.00 tokens per second) 1.47.970.714 I slot print_timing: id 0 | task 8538 | total time = 834.29 ms / 491 tokens 1.47.970.715 I slot print_timing: id 0 | task 8538 | graphs reused = 8251 1.47.970.716 I slot print_timing: id 0 | task 8538 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.970.748 I slot release: id 0 | task 8538 | stop processing: n_tokens = 515, truncated = 0 1.47.996.502 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 107878361 1.47.996.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.506 MiB) 1.48.023.954 I slot launch_slot_: id 0 | task 8611 | processing task, is_child = 0 1.48.856.524 I slot print_timing: id 0 | task 8611 | prompt eval time = 117.87 ms / 440 tokens ( 0.27 ms per token, 3732.83 tokens per second) 1.48.856.530 I slot print_timing: id 0 | task 8611 | eval time = 714.68 ms / 71 tokens ( 10.21 ms per token, 97.95 tokens per second) 1.48.856.531 I slot print_timing: id 0 | task 8611 | total time = 832.55 ms / 511 tokens 1.48.856.532 I slot print_timing: id 0 | task 8611 | graphs reused = 8319 1.48.856.533 I slot print_timing: id 0 | task 8611 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.856.565 I slot release: id 0 | task 8611 | stop processing: n_tokens = 535, truncated = 0 1.48.881.909 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 108764178 1.48.881.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.224 MiB) 1.48.909.103 I slot launch_slot_: id 0 | task 8683 | processing task, is_child = 0 1.49.516.325 I slot print_timing: id 0 | task 8683 | prompt eval time = 89.93 ms / 372 tokens ( 0.24 ms per token, 4136.46 tokens per second) 1.49.516.331 I slot print_timing: id 0 | task 8683 | eval time = 517.27 ms / 52 tokens ( 10.14 ms per token, 98.59 tokens per second) 1.49.516.332 I slot print_timing: id 0 | task 8683 | total time = 607.21 ms / 424 tokens 1.49.516.333 I slot print_timing: id 0 | task 8683 | graphs reused = 8369 1.49.516.334 I slot print_timing: id 0 | task 8683 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.516.364 I slot release: id 0 | task 8683 | stop processing: n_tokens = 448, truncated = 0 1.49.520.939 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 109423977 1.49.520.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.443 MiB) 1.49.524.995 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 60.943 MiB) 1.49.549.544 I slot launch_slot_: id 0 | task 8736 | processing task, is_child = 0 1.50.254.421 I slot print_timing: id 0 | task 8736 | prompt eval time = 120.91 ms / 449 tokens ( 0.27 ms per token, 3713.38 tokens per second) 1.50.254.427 I slot print_timing: id 0 | task 8736 | eval time = 583.95 ms / 58 tokens ( 10.24 ms per token, 97.61 tokens per second) 1.50.254.428 I slot print_timing: id 0 | task 8736 | total time = 704.86 ms / 507 tokens 1.50.254.429 I slot print_timing: id 0 | task 8736 | graphs reused = 8424 1.50.254.430 I slot print_timing: id 0 | task 8736 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.254.463 I slot release: id 0 | task 8736 | stop processing: n_tokens = 531, truncated = 0 1.50.270.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 110162076 1.50.270.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.631 MiB) 1.50.299.852 I slot launch_slot_: id 0 | task 8795 | processing task, is_child = 0 1.51.008.474 I slot print_timing: id 0 | task 8795 | prompt eval time = 90.51 ms / 360 tokens ( 0.25 ms per token, 3977.42 tokens per second) 1.51.008.481 I slot print_timing: id 0 | task 8795 | eval time = 618.09 ms / 62 tokens ( 10.13 ms per token, 98.69 tokens per second) 1.51.008.482 I slot print_timing: id 0 | task 8795 | total time = 708.60 ms / 422 tokens 1.51.008.483 I slot print_timing: id 0 | task 8795 | graphs reused = 8484 1.51.008.484 I slot print_timing: id 0 | task 8795 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.008.518 I slot release: id 0 | task 8795 | stop processing: n_tokens = 446, truncated = 0 1.51.033.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 110916131 1.51.033.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.787 MiB) 1.51.058.506 I slot launch_slot_: id 0 | task 8858 | processing task, is_child = 0 1.51.696.106 I slot print_timing: id 0 | task 8858 | prompt eval time = 89.87 ms / 346 tokens ( 0.26 ms per token, 3850.05 tokens per second) 1.51.696.111 I slot print_timing: id 0 | task 8858 | eval time = 547.71 ms / 55 tokens ( 10.14 ms per token, 98.59 tokens per second) 1.51.696.113 I slot print_timing: id 0 | task 8858 | total time = 637.58 ms / 401 tokens 1.51.696.113 I slot print_timing: id 0 | task 8858 | graphs reused = 8537 1.51.696.114 I slot print_timing: id 0 | task 8858 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.696.143 I slot release: id 0 | task 8858 | stop processing: n_tokens = 425, truncated = 0 1.51.700.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 111603757 1.51.700.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.850 MiB) 1.51.725.573 I slot launch_slot_: id 0 | task 8914 | processing task, is_child = 0 1.52.354.615 I slot print_timing: id 0 | task 8914 | prompt eval time = 110.93 ms / 434 tokens ( 0.26 ms per token, 3912.34 tokens per second) 1.52.354.621 I slot print_timing: id 0 | task 8914 | eval time = 518.09 ms / 52 tokens ( 10.16 ms per token, 98.44 tokens per second) 1.52.354.622 I slot print_timing: id 0 | task 8914 | total time = 629.03 ms / 486 tokens 1.52.354.622 I slot print_timing: id 0 | task 8914 | graphs reused = 8587 1.52.354.623 I slot print_timing: id 0 | task 8914 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.354.655 I slot release: id 0 | task 8914 | stop processing: n_tokens = 510, truncated = 0 1.52.371.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 112262268 1.52.371.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.412 MiB) 1.52.404.475 I slot launch_slot_: id 0 | task 8967 | processing task, is_child = 0 1.53.102.142 I slot print_timing: id 0 | task 8967 | prompt eval time = 89.99 ms / 369 tokens ( 0.24 ms per token, 4100.36 tokens per second) 1.53.102.147 I slot print_timing: id 0 | task 8967 | eval time = 607.65 ms / 59 tokens ( 10.48 ms per token, 95.45 tokens per second) 1.53.102.148 I slot print_timing: id 0 | task 8967 | total time = 697.65 ms / 428 tokens 1.53.102.149 I slot print_timing: id 0 | task 8967 | graphs reused = 8644 1.53.102.150 I slot print_timing: id 0 | task 8967 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.102.181 I slot release: id 0 | task 8967 | stop processing: n_tokens = 452, truncated = 0 1.53.120.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 113009794 1.53.120.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 1.53.153.893 I slot launch_slot_: id 0 | task 9027 | processing task, is_child = 0 1.54.052.749 I slot print_timing: id 0 | task 9027 | prompt eval time = 111.20 ms / 446 tokens ( 0.25 ms per token, 4010.90 tokens per second) 1.54.052.755 I slot print_timing: id 0 | task 9027 | eval time = 787.64 ms / 78 tokens ( 10.23 ms per token, 97.76 tokens per second) 1.54.052.756 I slot print_timing: id 0 | task 9027 | total time = 898.84 ms / 524 tokens 1.54.052.757 I slot print_timing: id 0 | task 9027 | graphs reused = 8719 1.54.052.758 I slot print_timing: id 0 | task 9027 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.052.791 I slot release: id 0 | task 9027 | stop processing: n_tokens = 548, truncated = 0 1.54.079.072 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 113960404 1.54.079.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.288 MiB) 1.54.110.124 I slot launch_slot_: id 0 | task 9106 | processing task, is_child = 0 1.54.696.441 I slot print_timing: id 0 | task 9106 | prompt eval time = 109.18 ms / 396 tokens ( 0.28 ms per token, 3627.04 tokens per second) 1.54.696.447 I slot print_timing: id 0 | task 9106 | eval time = 477.12 ms / 48 tokens ( 10.15 ms per token, 98.51 tokens per second) 1.54.696.448 I slot print_timing: id 0 | task 9106 | total time = 586.30 ms / 444 tokens 1.54.696.450 I slot print_timing: id 0 | task 9106 | graphs reused = 8765 1.54.696.450 I slot print_timing: id 0 | task 9106 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.696.483 I slot release: id 0 | task 9106 | stop processing: n_tokens = 470, truncated = 0 1.54.720.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 114604096 1.54.720.274 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.569 MiB) 1.54.747.365 I slot launch_slot_: id 0 | task 9155 | processing task, is_child = 0 1.55.759.583 I slot print_timing: id 0 | task 9155 | prompt eval time = 121.15 ms / 466 tokens ( 0.26 ms per token, 3846.34 tokens per second) 1.55.759.589 I slot print_timing: id 0 | task 9155 | eval time = 891.05 ms / 88 tokens ( 10.24 ms per token, 97.64 tokens per second) 1.55.759.590 I slot print_timing: id 0 | task 9155 | total time = 1012.20 ms / 554 tokens 1.55.759.591 I slot print_timing: id 0 | task 9155 | graphs reused = 8850 1.55.759.592 I slot print_timing: id 0 | task 9155 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.759.625 I slot release: id 0 | task 9155 | stop processing: n_tokens = 578, truncated = 0 1.55.777.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 115667239 1.55.777.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 1.55.812.005 I slot launch_slot_: id 0 | task 9244 | processing task, is_child = 0 1.56.611.723 I slot print_timing: id 0 | task 9244 | prompt eval time = 121.24 ms / 467 tokens ( 0.26 ms per token, 3851.83 tokens per second) 1.56.611.729 I slot print_timing: id 0 | task 9244 | eval time = 678.46 ms / 66 tokens ( 10.44 ms per token, 95.81 tokens per second) 1.56.611.730 I slot print_timing: id 0 | task 9244 | total time = 799.70 ms / 533 tokens 1.56.611.730 I slot print_timing: id 0 | task 9244 | graphs reused = 8913 1.56.611.731 I slot print_timing: id 0 | task 9244 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.611.765 I slot release: id 0 | task 9244 | stop processing: n_tokens = 557, truncated = 0 1.56.635.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 116519378 1.56.636.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 68.912 MiB) 1.56.640.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 75.163 MiB) 1.56.670.634 I slot launch_slot_: id 0 | task 9311 | processing task, is_child = 0 1.57.532.789 I slot print_timing: id 0 | task 9311 | prompt eval time = 121.07 ms / 454 tokens ( 0.27 ms per token, 3750.02 tokens per second) 1.57.532.795 I slot print_timing: id 0 | task 9311 | eval time = 741.07 ms / 71 tokens ( 10.59 ms per token, 94.46 tokens per second) 1.57.532.797 I slot print_timing: id 0 | task 9311 | total time = 862.14 ms / 525 tokens 1.57.532.798 I slot print_timing: id 0 | task 9311 | graphs reused = 8981 1.57.532.799 I slot print_timing: id 0 | task 9311 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.532.837 I slot release: id 0 | task 9311 | stop processing: n_tokens = 549, truncated = 0 1.57.537.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 117440451 1.57.537.277 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.319 MiB) 1.57.564.882 I slot launch_slot_: id 0 | task 9383 | processing task, is_child = 0 1.58.293.526 I slot print_timing: id 0 | task 9383 | prompt eval time = 109.76 ms / 409 tokens ( 0.27 ms per token, 3726.28 tokens per second) 1.58.293.533 I slot print_timing: id 0 | task 9383 | eval time = 618.87 ms / 62 tokens ( 10.15 ms per token, 98.57 tokens per second) 1.58.293.534 I slot print_timing: id 0 | task 9383 | total time = 728.63 ms / 471 tokens 1.58.293.535 I slot print_timing: id 0 | task 9383 | graphs reused = 9041 1.58.293.536 I slot print_timing: id 0 | task 9383 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.293.568 I slot release: id 0 | task 9383 | stop processing: n_tokens = 495, truncated = 0 1.58.308.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 118201181 1.58.308.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 1.58.335.513 I slot launch_slot_: id 0 | task 9446 | processing task, is_child = 0 1.59.548.410 I slot print_timing: id 0 | task 9446 | prompt eval time = 90.10 ms / 349 tokens ( 0.26 ms per token, 3873.30 tokens per second) 1.59.548.416 I slot print_timing: id 0 | task 9446 | eval time = 1122.77 ms / 112 tokens ( 10.12 ms per token, 98.86 tokens per second) 1.59.548.417 I slot print_timing: id 0 | task 9446 | total time = 1212.88 ms / 461 tokens 1.59.548.418 I slot print_timing: id 0 | task 9446 | graphs reused = 9151 1.59.548.419 I slot print_timing: id 0 | task 9446 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.548.449 I slot release: id 0 | task 9446 | stop processing: n_tokens = 485, truncated = 0 1.59.573.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 485, t_last = 119456062 1.59.573.342 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.631 MiB) 1.59.603.826 I slot launch_slot_: id 0 | task 9559 | processing task, is_child = 0 2.00.301.330 I slot print_timing: id 0 | task 9559 | prompt eval time = 110.69 ms / 435 tokens ( 0.25 ms per token, 3929.89 tokens per second) 2.00.301.338 I slot print_timing: id 0 | task 9559 | eval time = 586.80 ms / 58 tokens ( 10.29 ms per token, 97.14 tokens per second) 2.00.301.339 I slot print_timing: id 0 | task 9559 | total time = 697.49 ms / 493 tokens 2.00.301.340 I slot print_timing: id 0 | task 9559 | graphs reused = 9206 2.00.301.341 I slot print_timing: id 0 | task 9559 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.301.376 I slot release: id 0 | task 9559 | stop processing: n_tokens = 517, truncated = 0 2.00.315.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 120208990 2.00.315.722 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.944 MiB) 2.00.344.051 I slot launch_slot_: id 0 | task 9618 | processing task, is_child = 0 2.00.915.785 I slot print_timing: id 0 | task 9618 | prompt eval time = 82.22 ms / 322 tokens ( 0.26 ms per token, 3916.37 tokens per second) 2.00.915.791 I slot print_timing: id 0 | task 9618 | eval time = 489.50 ms / 47 tokens ( 10.64 ms per token, 93.97 tokens per second) 2.00.915.792 I slot print_timing: id 0 | task 9618 | total time = 571.72 ms / 369 tokens 2.00.915.793 I slot print_timing: id 0 | task 9618 | graphs reused = 9251 2.00.915.794 I slot print_timing: id 0 | task 9618 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.915.823 I slot release: id 0 | task 9618 | stop processing: n_tokens = 393, truncated = 0 2.00.939.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 120823436 2.00.939.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 2.00.962.534 I slot launch_slot_: id 0 | task 9666 | processing task, is_child = 0 2.01.634.807 I slot print_timing: id 0 | task 9666 | prompt eval time = 90.50 ms / 360 tokens ( 0.25 ms per token, 3977.77 tokens per second) 2.01.634.813 I slot print_timing: id 0 | task 9666 | eval time = 581.75 ms / 56 tokens ( 10.58 ms per token, 94.54 tokens per second) 2.01.634.814 I slot print_timing: id 0 | task 9666 | total time = 672.25 ms / 416 tokens 2.01.634.815 I slot print_timing: id 0 | task 9666 | graphs reused = 9305 2.01.634.816 I slot print_timing: id 0 | task 9666 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.634.849 I slot release: id 0 | task 9666 | stop processing: n_tokens = 440, truncated = 0 2.01.656.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 121542462 2.01.656.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 63.131 MiB) 2.01.681.944 I slot launch_slot_: id 0 | task 9723 | processing task, is_child = 0 2.02.531.900 I slot print_timing: id 0 | task 9723 | prompt eval time = 110.97 ms / 443 tokens ( 0.25 ms per token, 3991.93 tokens per second) 2.02.531.907 I slot print_timing: id 0 | task 9723 | eval time = 738.96 ms / 73 tokens ( 10.26 ms per token, 97.43 tokens per second) 2.02.531.908 I slot print_timing: id 0 | task 9723 | total time = 849.94 ms / 516 tokens 2.02.531.909 I slot print_timing: id 0 | task 9723 | graphs reused = 9375 2.02.531.910 I slot print_timing: id 0 | task 9723 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.531.943 I slot release: id 0 | task 9723 | stop processing: n_tokens = 540, truncated = 0 2.02.560.566 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 540, t_last = 122439557 2.02.560.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 2.02.590.127 I slot launch_slot_: id 0 | task 9797 | processing task, is_child = 0 2.03.138.329 I slot print_timing: id 0 | task 9797 | prompt eval time = 111.26 ms / 442 tokens ( 0.25 ms per token, 3972.78 tokens per second) 2.03.138.334 I slot print_timing: id 0 | task 9797 | eval time = 436.93 ms / 44 tokens ( 10.16 ms per token, 98.41 tokens per second) 2.03.138.335 I slot print_timing: id 0 | task 9797 | total time = 548.18 ms / 486 tokens 2.03.138.336 I slot print_timing: id 0 | task 9797 | graphs reused = 9417 2.03.138.337 I slot print_timing: id 0 | task 9797 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.138.366 I slot release: id 0 | task 9797 | stop processing: n_tokens = 510, truncated = 0 2.03.153.373 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 123045980 2.03.153.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 55.474 MiB) 2.03.156.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 2.03.183.926 I slot launch_slot_: id 0 | task 9842 | processing task, is_child = 0 2.03.749.422 I slot print_timing: id 0 | task 9842 | prompt eval time = 121.67 ms / 470 tokens ( 0.26 ms per token, 3863.07 tokens per second) 2.03.749.427 I slot print_timing: id 0 | task 9842 | eval time = 443.81 ms / 44 tokens ( 10.32 ms per token, 96.89 tokens per second) 2.03.749.429 I slot print_timing: id 0 | task 9842 | total time = 565.48 ms / 514 tokens 2.03.749.431 I slot print_timing: id 0 | task 9842 | graphs reused = 9458 2.03.749.432 I slot print_timing: id 0 | task 9842 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.749.464 I slot release: id 0 | task 9842 | stop processing: n_tokens = 538, truncated = 0 2.03.778.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 538, t_last = 123657077 2.03.778.513 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 59.537 MiB) 2.03.813.873 I slot launch_slot_: id 0 | task 9887 | processing task, is_child = 0 2.04.279.183 I slot print_timing: id 0 | task 9887 | prompt eval time = 122.18 ms / 483 tokens ( 0.25 ms per token, 3953.15 tokens per second) 2.04.279.189 I slot print_timing: id 0 | task 9887 | eval time = 343.11 ms / 34 tokens ( 10.40 ms per token, 96.18 tokens per second) 2.04.279.190 I slot print_timing: id 0 | task 9887 | total time = 465.29 ms / 517 tokens 2.04.279.191 I slot print_timing: id 0 | task 9887 | graphs reused = 9489 2.04.279.193 I slot print_timing: id 0 | task 9887 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.279.228 I slot release: id 0 | task 9887 | stop processing: n_tokens = 541, truncated = 0 2.04.306.800 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 124186841 2.04.306.864 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.255 MiB) 2.04.335.829 I slot launch_slot_: id 0 | task 9922 | processing task, is_child = 0 2.05.011.954 I slot print_timing: id 0 | task 9922 | prompt eval time = 121.42 ms / 463 tokens ( 0.26 ms per token, 3813.15 tokens per second) 2.05.011.960 I slot print_timing: id 0 | task 9922 | eval time = 554.69 ms / 55 tokens ( 10.27 ms per token, 97.35 tokens per second) 2.05.011.961 I slot print_timing: id 0 | task 9922 | total time = 676.11 ms / 518 tokens 2.05.011.962 I slot print_timing: id 0 | task 9922 | graphs reused = 9541 2.05.011.962 I slot print_timing: id 0 | task 9922 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.011.995 I slot release: id 0 | task 9922 | stop processing: n_tokens = 542, truncated = 0 2.05.040.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 124919608 2.05.040.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.162 MiB) 2.05.044.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.851 MiB) 2.05.074.565 I slot launch_slot_: id 0 | task 9978 | processing task, is_child = 0 2.05.682.538 I slot print_timing: id 0 | task 9978 | prompt eval time = 110.02 ms / 421 tokens ( 0.26 ms per token, 3826.58 tokens per second) 2.05.682.544 I slot print_timing: id 0 | task 9978 | eval time = 497.94 ms / 50 tokens ( 10.16 ms per token, 98.41 tokens per second) 2.05.682.545 I slot print_timing: id 0 | task 9978 | total time = 607.96 ms / 471 tokens 2.05.682.546 I slot print_timing: id 0 | task 9978 | graphs reused = 9589 2.05.682.547 I slot print_timing: id 0 | task 9978 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.682.579 I slot release: id 0 | task 9978 | stop processing: n_tokens = 495, truncated = 0 2.05.697.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 125590192 2.05.697.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 61.412 MiB) 2.05.729.892 I slot launch_slot_: id 0 | task 10029 | processing task, is_child = 0 2.06.248.353 I slot print_timing: id 0 | task 10029 | prompt eval time = 90.61 ms / 360 tokens ( 0.25 ms per token, 3973.12 tokens per second) 2.06.248.359 I slot print_timing: id 0 | task 10029 | eval time = 427.83 ms / 43 tokens ( 10.19 ms per token, 98.17 tokens per second) 2.06.248.360 I slot print_timing: id 0 | task 10029 | total time = 518.44 ms / 403 tokens 2.06.248.361 I slot print_timing: id 0 | task 10029 | graphs reused = 9630 2.06.248.362 I slot print_timing: id 0 | task 10029 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.248.392 I slot release: id 0 | task 10029 | stop processing: n_tokens = 427, truncated = 0 2.06.271.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 126156005 2.06.272.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 67.193 MiB) 2.06.305.882 I slot launch_slot_: id 0 | task 10073 | processing task, is_child = 0 2.07.634.178 I slot print_timing: id 0 | task 10073 | prompt eval time = 144.59 ms / 547 tokens ( 0.26 ms per token, 3783.16 tokens per second) 2.07.634.184 I slot print_timing: id 0 | task 10073 | eval time = 1183.69 ms / 117 tokens ( 10.20 ms per token, 98.00 tokens per second) 2.07.634.185 I slot print_timing: id 0 | task 10073 | total time = 1328.28 ms / 664 tokens 2.07.634.186 I slot print_timing: id 0 | task 10073 | graphs reused = 9745 2.07.634.187 I slot print_timing: id 0 | task 10073 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.634.224 I slot release: id 0 | task 10073 | stop processing: n_tokens = 688, truncated = 0 2.07.654.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 127541838 2.07.654.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.600 MiB) 2.07.691.176 I slot launch_slot_: id 0 | task 10191 | processing task, is_child = 0 2.08.968.638 I slot print_timing: id 0 | task 10191 | prompt eval time = 191.16 ms / 749 tokens ( 0.26 ms per token, 3918.27 tokens per second) 2.08.968.644 I slot print_timing: id 0 | task 10191 | eval time = 1086.29 ms / 107 tokens ( 10.25 ms per token, 97.58 tokens per second) 2.08.968.645 I slot print_timing: id 0 | task 10191 | total time = 1277.44 ms / 856 tokens 2.08.968.646 I slot print_timing: id 0 | task 10191 | graphs reused = 9850 2.08.968.647 I slot print_timing: id 0 | task 10191 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.968.690 I slot release: id 0 | task 10191 | stop processing: n_tokens = 880, truncated = 0 2.08.992.828 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 128876303 2.08.992.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.08.997.735 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.818 MiB) 2.09.040.034 I slot launch_slot_: id 0 | task 10299 | processing task, is_child = 0 2.09.696.336 I slot print_timing: id 0 | task 10299 | prompt eval time = 173.49 ms / 678 tokens ( 0.26 ms per token, 3908.07 tokens per second) 2.09.696.342 I slot print_timing: id 0 | task 10299 | eval time = 482.80 ms / 48 tokens ( 10.27 ms per token, 97.35 tokens per second) 2.09.696.343 I slot print_timing: id 0 | task 10299 | total time = 656.28 ms / 726 tokens 2.09.696.344 I slot print_timing: id 0 | task 10299 | graphs reused = 9896 2.09.696.344 I slot print_timing: id 0 | task 10299 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.696.384 I slot release: id 0 | task 10299 | stop processing: n_tokens = 750, truncated = 0 2.09.717.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 129603998 2.09.717.377 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.09.721.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.381 MiB) 2.09.754.927 I slot launch_slot_: id 0 | task 10348 | processing task, is_child = 0 2.10.483.495 I slot print_timing: id 0 | task 10348 | prompt eval time = 145.12 ms / 567 tokens ( 0.26 ms per token, 3907.03 tokens per second) 2.10.483.500 I slot print_timing: id 0 | task 10348 | eval time = 583.43 ms / 57 tokens ( 10.42 ms per token, 95.98 tokens per second) 2.10.483.501 I slot print_timing: id 0 | task 10348 | total time = 728.55 ms / 624 tokens 2.10.483.502 I slot print_timing: id 0 | task 10348 | graphs reused = 9951 2.10.483.503 I slot print_timing: id 0 | task 10348 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.483.542 I slot release: id 0 | task 10348 | stop processing: n_tokens = 648, truncated = 0 2.10.512.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 648, t_last = 130391155 2.10.512.148 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 2.10.545.361 I slot launch_slot_: id 0 | task 10406 | processing task, is_child = 0 2.11.253.122 I slot print_timing: id 0 | task 10406 | prompt eval time = 123.89 ms / 501 tokens ( 0.25 ms per token, 4044.04 tokens per second) 2.11.253.127 I slot print_timing: id 0 | task 10406 | eval time = 583.86 ms / 58 tokens ( 10.24 ms per token, 97.63 tokens per second) 2.11.253.129 I slot print_timing: id 0 | task 10406 | total time = 707.74 ms / 559 tokens 2.11.253.129 I slot print_timing: id 0 | task 10406 | graphs reused = 10007 2.11.253.130 I slot print_timing: id 0 | task 10406 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.253.164 I slot release: id 0 | task 10406 | stop processing: n_tokens = 583, truncated = 0 2.11.279.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 131160777 2.11.279.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 2.11.317.950 I slot launch_slot_: id 0 | task 10465 | processing task, is_child = 0 2.12.140.182 I slot print_timing: id 0 | task 10465 | prompt eval time = 194.45 ms / 769 tokens ( 0.25 ms per token, 3954.78 tokens per second) 2.12.140.187 I slot print_timing: id 0 | task 10465 | eval time = 627.76 ms / 62 tokens ( 10.29 ms per token, 97.17 tokens per second) 2.12.140.188 I slot print_timing: id 0 | task 10465 | total time = 822.21 ms / 831 tokens 2.12.140.190 I slot print_timing: id 0 | task 10465 | graphs reused = 10067 2.12.140.191 I slot print_timing: id 0 | task 10465 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.140.233 I slot release: id 0 | task 10465 | stop processing: n_tokens = 855, truncated = 0 2.12.156.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 132047847 2.12.156.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.943 MiB) 2.12.160.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.945 MiB) 2.12.206.256 I slot launch_slot_: id 0 | task 10528 | processing task, is_child = 0 2.12.949.604 I slot print_timing: id 0 | task 10528 | prompt eval time = 124.26 ms / 500 tokens ( 0.25 ms per token, 4023.92 tokens per second) 2.12.949.612 I slot print_timing: id 0 | task 10528 | eval time = 619.07 ms / 61 tokens ( 10.32 ms per token, 96.92 tokens per second) 2.12.949.613 I slot print_timing: id 0 | task 10528 | total time = 743.33 ms / 561 tokens 2.12.949.615 I slot print_timing: id 0 | task 10528 | graphs reused = 10126 2.12.949.616 I slot print_timing: id 0 | task 10528 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.949.655 I slot release: id 0 | task 10528 | stop processing: n_tokens = 585, truncated = 0 2.12.978.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 132857268 2.12.978.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 89.539 MiB) 2.13.010.291 I slot launch_slot_: id 0 | task 10590 | processing task, is_child = 0 2.13.778.143 I slot print_timing: id 0 | task 10590 | prompt eval time = 167.45 ms / 632 tokens ( 0.26 ms per token, 3774.17 tokens per second) 2.13.778.149 I slot print_timing: id 0 | task 10590 | eval time = 600.37 ms / 58 tokens ( 10.53 ms per token, 94.94 tokens per second) 2.13.778.150 I slot print_timing: id 0 | task 10590 | total time = 767.83 ms / 690 tokens 2.13.778.151 I slot print_timing: id 0 | task 10590 | graphs reused = 10182 2.13.778.152 I slot print_timing: id 0 | task 10590 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.778.192 I slot release: id 0 | task 10590 | stop processing: n_tokens = 714, truncated = 0 2.13.783.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 133685806 2.13.783.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 2.13.787.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 2.13.823.598 I slot launch_slot_: id 0 | task 10649 | processing task, is_child = 0 2.14.302.560 I slot print_timing: id 0 | task 10649 | prompt eval time = 109.28 ms / 395 tokens ( 0.28 ms per token, 3614.73 tokens per second) 2.14.302.566 I slot print_timing: id 0 | task 10649 | eval time = 369.67 ms / 37 tokens ( 10.27 ms per token, 97.38 tokens per second) 2.14.302.567 I slot print_timing: id 0 | task 10649 | total time = 478.94 ms / 432 tokens 2.14.302.568 I slot print_timing: id 0 | task 10649 | graphs reused = 10217 2.14.302.569 I slot print_timing: id 0 | task 10649 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.302.599 I slot release: id 0 | task 10649 | stop processing: n_tokens = 456, truncated = 0 2.14.330.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 134210212 2.14.330.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 62.974 MiB) 2.14.355.564 I slot launch_slot_: id 0 | task 10687 | processing task, is_child = 0 2.15.121.418 I slot print_timing: id 0 | task 10687 | prompt eval time = 149.89 ms / 579 tokens ( 0.26 ms per token, 3862.94 tokens per second) 2.15.121.424 I slot print_timing: id 0 | task 10687 | eval time = 615.95 ms / 59 tokens ( 10.62 ms per token, 94.16 tokens per second) 2.15.121.425 I slot print_timing: id 0 | task 10687 | total time = 765.84 ms / 638 tokens 2.15.121.426 I slot print_timing: id 0 | task 10687 | graphs reused = 10274 2.15.121.427 I slot print_timing: id 0 | task 10687 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.121.466 I slot release: id 0 | task 10687 | stop processing: n_tokens = 662, truncated = 0 2.15.146.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 662, t_last = 135029079 2.15.146.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.038 MiB) 2.15.181.180 I slot launch_slot_: id 0 | task 10747 | processing task, is_child = 0 2.15.954.064 I slot print_timing: id 0 | task 10747 | prompt eval time = 172.68 ms / 689 tokens ( 0.25 ms per token, 3990.06 tokens per second) 2.15.954.070 I slot print_timing: id 0 | task 10747 | eval time = 600.19 ms / 59 tokens ( 10.35 ms per token, 96.64 tokens per second) 2.15.954.071 I slot print_timing: id 0 | task 10747 | total time = 772.87 ms / 748 tokens 2.15.954.072 I slot print_timing: id 0 | task 10747 | graphs reused = 10330 2.15.954.073 I slot print_timing: id 0 | task 10747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.954.113 I slot release: id 0 | task 10747 | stop processing: n_tokens = 772, truncated = 0 2.15.971.084 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 135861726 2.15.971.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.320 MiB) 2.15.976.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 2.16.019.738 I slot launch_slot_: id 0 | task 10807 | processing task, is_child = 0 2.16.887.134 I slot print_timing: id 0 | task 10807 | prompt eval time = 186.62 ms / 752 tokens ( 0.25 ms per token, 4029.62 tokens per second) 2.16.887.139 I slot print_timing: id 0 | task 10807 | eval time = 680.76 ms / 66 tokens ( 10.47 ms per token, 95.48 tokens per second) 2.16.887.140 I slot print_timing: id 0 | task 10807 | total time = 867.38 ms / 818 tokens 2.16.887.141 I slot print_timing: id 0 | task 10807 | graphs reused = 10394 2.16.887.142 I slot print_timing: id 0 | task 10807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.887.185 I slot release: id 0 | task 10807 | stop processing: n_tokens = 842, truncated = 0 2.16.915.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 842, t_last = 136794799 2.16.915.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.603 MiB) 2.16.963.104 I slot launch_slot_: id 0 | task 10874 | processing task, is_child = 0 2.17.790.712 I slot print_timing: id 0 | task 10874 | prompt eval time = 149.94 ms / 582 tokens ( 0.26 ms per token, 3881.68 tokens per second) 2.17.790.718 I slot print_timing: id 0 | task 10874 | eval time = 677.65 ms / 67 tokens ( 10.27 ms per token, 97.40 tokens per second) 2.17.790.719 I slot print_timing: id 0 | task 10874 | total time = 827.59 ms / 649 tokens 2.17.790.719 I slot print_timing: id 0 | task 10874 | graphs reused = 10459 2.17.790.720 I slot print_timing: id 0 | task 10874 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.790.758 I slot release: id 0 | task 10874 | stop processing: n_tokens = 673, truncated = 0 2.17.819.790 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 673, t_last = 137698371 2.17.819.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 111.728 MiB) 2.17.857.036 I slot launch_slot_: id 0 | task 10942 | processing task, is_child = 0 2.18.803.169 I slot print_timing: id 0 | task 10942 | prompt eval time = 168.04 ms / 656 tokens ( 0.26 ms per token, 3903.76 tokens per second) 2.18.803.175 I slot print_timing: id 0 | task 10942 | eval time = 778.07 ms / 77 tokens ( 10.24 ms per token, 97.68 tokens per second) 2.18.803.176 I slot print_timing: id 0 | task 10942 | total time = 946.12 ms / 733 tokens 2.18.803.177 I slot print_timing: id 0 | task 10942 | graphs reused = 10534 2.18.803.178 I slot print_timing: id 0 | task 10942 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.803.215 I slot release: id 0 | task 10942 | stop processing: n_tokens = 757, truncated = 0 2.18.833.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 138710829 2.18.833.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.18.877.727 I slot launch_slot_: id 0 | task 11020 | processing task, is_child = 0 2.19.342.689 I slot print_timing: id 0 | task 11020 | prompt eval time = 156.20 ms / 613 tokens ( 0.25 ms per token, 3924.41 tokens per second) 2.19.342.694 I slot print_timing: id 0 | task 11020 | eval time = 308.74 ms / 31 tokens ( 10.29 ms per token, 97.17 tokens per second) 2.19.342.696 I slot print_timing: id 0 | task 11020 | total time = 464.94 ms / 644 tokens 2.19.342.697 I slot print_timing: id 0 | task 11020 | graphs reused = 10563 2.19.342.698 I slot print_timing: id 0 | task 11020 | graph reallocs = 0 / 0 (same size) / (changed size) 2.19.342.736 I slot release: id 0 | task 11020 | stop processing: n_tokens = 668, truncated = 0 2.19.362.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 668, t_last = 139250349 2.19.363.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.415 MiB) 2.19.400.017 I slot launch_slot_: id 0 | task 11052 | processing task, is_child = 0 2.22.596.413 I slot print_timing: id 0 | task 11052 | n_gen = 282, tg = 93.39 t/s, tg_3s = 93.72 t/s 2.25.602.792 I slot print_timing: id 0 | task 11052 | n_gen = 551, tg = 91.43 t/s, tg_3s = 89.48 t/s 2.28.606.461 I slot print_timing: id 0 | task 11052 | n_gen = 829, tg = 91.81 t/s, tg_3s = 92.55 t/s 2.30.666.309 I slot print_timing: id 0 | task 11052 | prompt eval time = 187.34 ms / 766 tokens ( 0.24 ms per token, 4088.84 tokens per second) 2.30.666.315 I slot print_timing: id 0 | task 11052 | eval time = 11078.93 ms / 1024 tokens ( 10.83 ms per token, 92.34 tokens per second) 2.30.666.316 I slot print_timing: id 0 | task 11052 | total time = 11266.27 ms / 1790 tokens 2.30.666.316 I slot print_timing: id 0 | task 11052 | graphs reused = 11581 2.30.666.317 I slot print_timing: id 0 | task 11052 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.666.365 I slot release: id 0 | task 11052 | stop processing: n_tokens = 1814, truncated = 0 2.30.693.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1814, t_last = 150573979 2.30.693.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.102 MiB) 2.30.699.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.008 MiB) 2.30.705.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 87.507 MiB) 2.30.789.857 I slot launch_slot_: id 0 | task 12077 | processing task, is_child = 0 2.31.613.308 I slot print_timing: id 0 | task 12077 | prompt eval time = 206.63 ms / 846 tokens ( 0.24 ms per token, 4094.31 tokens per second) 2.31.613.314 I slot print_timing: id 0 | task 12077 | eval time = 616.80 ms / 61 tokens ( 10.28 ms per token, 97.28 tokens per second) 2.31.613.315 I slot print_timing: id 0 | task 12077 | total time = 823.43 ms / 907 tokens 2.31.613.316 I slot print_timing: id 0 | task 12077 | graphs reused = 11640 2.31.613.317 I slot print_timing: id 0 | task 12077 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.613.364 I slot release: id 0 | task 12077 | stop processing: n_tokens = 931, truncated = 0 2.31.619.112 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 931, t_last = 151520978 2.31.619.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 97.039 MiB) 2.31.625.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 244.081 MiB) 2.31.679.317 I slot launch_slot_: id 0 | task 12139 | processing task, is_child = 0 2.32.633.909 I slot print_timing: id 0 | task 12139 | prompt eval time = 173.01 ms / 650 tokens ( 0.27 ms per token, 3756.94 tokens per second) 2.32.633.915 I slot print_timing: id 0 | task 12139 | eval time = 781.56 ms / 77 tokens ( 10.28 ms per token, 97.24 tokens per second) 2.32.633.916 I slot print_timing: id 0 | task 12139 | total time = 954.57 ms / 727 tokens 2.32.633.917 I slot print_timing: id 0 | task 12139 | graphs reused = 11715 2.32.633.918 I slot print_timing: id 0 | task 12139 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.633.959 I slot release: id 0 | task 12139 | stop processing: n_tokens = 751, truncated = 0 2.32.656.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 152541573 2.32.685.091 I slot launch_slot_: id 0 | task 12217 | processing task, is_child = 0 2.33.405.525 I slot print_timing: id 0 | task 12217 | prompt eval time = 179.74 ms / 717 tokens ( 0.25 ms per token, 3989.05 tokens per second) 2.33.405.530 I slot print_timing: id 0 | task 12217 | eval time = 540.67 ms / 53 tokens ( 10.40 ms per token, 96.18 tokens per second) 2.33.405.532 I slot print_timing: id 0 | task 12217 | total time = 720.41 ms / 770 tokens 2.33.405.532 I slot print_timing: id 0 | task 12217 | graphs reused = 11765 2.33.405.533 I slot print_timing: id 0 | task 12217 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.405.575 I slot release: id 0 | task 12217 | stop processing: n_tokens = 794, truncated = 0 2.33.422.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 794, t_last = 153313188 2.33.456.105 I slot launch_slot_: id 0 | task 12271 | processing task, is_child = 0 2.34.176.814 I slot print_timing: id 0 | task 12271 | prompt eval time = 125.36 ms / 494 tokens ( 0.25 ms per token, 3940.75 tokens per second) 2.34.176.820 I slot print_timing: id 0 | task 12271 | eval time = 595.33 ms / 59 tokens ( 10.26 ms per token, 97.42 tokens per second) 2.34.176.821 I slot print_timing: id 0 | task 12271 | total time = 720.69 ms / 553 tokens 2.34.176.822 I slot print_timing: id 0 | task 12271 | graphs reused = 11822 2.34.176.822 I slot print_timing: id 0 | task 12271 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.176.859 I slot release: id 0 | task 12271 | stop processing: n_tokens = 577, truncated = 0 2.34.201.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 154084472 2.34.201.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.194 MiB) 2.34.206.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 95.477 MiB) 2.34.239.361 I slot launch_slot_: id 0 | task 12331 | processing task, is_child = 0 2.34.932.786 I slot print_timing: id 0 | task 12331 | prompt eval time = 149.72 ms / 579 tokens ( 0.26 ms per token, 3867.24 tokens per second) 2.34.932.792 I slot print_timing: id 0 | task 12331 | eval time = 543.68 ms / 54 tokens ( 10.26 ms per token, 97.48 tokens per second) 2.34.932.793 I slot print_timing: id 0 | task 12331 | total time = 693.40 ms / 633 tokens 2.34.932.794 I slot print_timing: id 0 | task 12331 | graphs reused = 11874 2.34.932.795 I slot print_timing: id 0 | task 12331 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.932.835 I slot release: id 0 | task 12331 | stop processing: n_tokens = 657, truncated = 0 2.34.963.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 657, t_last = 154840448 2.34.963.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.476 MiB) 2.34.995.616 I slot launch_slot_: id 0 | task 12386 | processing task, is_child = 0 2.35.993.839 I slot print_timing: id 0 | task 12386 | prompt eval time = 233.58 ms / 919 tokens ( 0.25 ms per token, 3934.34 tokens per second) 2.35.993.845 I slot print_timing: id 0 | task 12386 | eval time = 764.62 ms / 73 tokens ( 10.62 ms per token, 94.16 tokens per second) 2.35.993.846 I slot print_timing: id 0 | task 12386 | total time = 998.20 ms / 992 tokens 2.35.993.847 I slot print_timing: id 0 | task 12386 | graphs reused = 11945 2.35.993.848 I slot print_timing: id 0 | task 12386 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.993.896 I slot release: id 0 | task 12386 | stop processing: n_tokens = 1016, truncated = 0 2.36.020.007 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 155901510 2.36.020.080 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 77.507 MiB) 2.36.024.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.038 MiB) 2.36.074.381 I slot launch_slot_: id 0 | task 12460 | processing task, is_child = 0 2.36.678.742 I slot print_timing: id 0 | task 12460 | prompt eval time = 212.28 ms / 865 tokens ( 0.25 ms per token, 4074.90 tokens per second) 2.36.678.747 I slot print_timing: id 0 | task 12460 | eval time = 392.07 ms / 39 tokens ( 10.32 ms per token, 96.92 tokens per second) 2.36.678.748 I slot print_timing: id 0 | task 12460 | total time = 604.34 ms / 904 tokens 2.36.678.749 I slot print_timing: id 0 | task 12460 | graphs reused = 11982 2.36.678.750 I slot print_timing: id 0 | task 12460 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.678.794 I slot release: id 0 | task 12460 | stop processing: n_tokens = 928, truncated = 0 2.36.703.672 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 156586407 2.36.703.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.225 MiB) 2.36.746.401 I slot launch_slot_: id 0 | task 12500 | processing task, is_child = 0 2.39.859.444 I slot print_timing: id 0 | task 12500 | n_gen = 296, tg = 98.24 t/s, tg_3s = 98.57 t/s 2.42.869.330 I slot print_timing: id 0 | task 12500 | n_gen = 591, tg = 98.12 t/s, tg_3s = 98.01 t/s 2.45.869.916 I slot print_timing: id 0 | task 12500 | n_gen = 880, tg = 97.52 t/s, tg_3s = 96.31 t/s 2.47.370.092 I slot print_timing: id 0 | task 12500 | prompt eval time = 110.06 ms / 408 tokens ( 0.27 ms per token, 3707.17 tokens per second) 2.47.370.098 I slot print_timing: id 0 | task 12500 | eval time = 10513.62 ms / 1024 tokens ( 10.28 ms per token, 97.30 tokens per second) 2.47.370.099 I slot print_timing: id 0 | task 12500 | total time = 10623.67 ms / 1432 tokens 2.47.370.100 I slot print_timing: id 0 | task 12500 | graphs reused = 13000 2.47.370.101 I slot print_timing: id 0 | task 12500 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.370.136 I slot release: id 0 | task 12500 | stop processing: n_tokens = 1456, truncated = 0 2.47.384.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1456, t_last = 167277750 2.47.384.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 106.884 MiB) 2.47.391.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.226 MiB) 2.47.396.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.387 MiB) 2.47.469.976 I slot launch_slot_: id 0 | task 13525 | processing task, is_child = 0 2.48.097.384 I slot print_timing: id 0 | task 13525 | prompt eval time = 89.51 ms / 338 tokens ( 0.26 ms per token, 3775.95 tokens per second) 2.48.097.389 I slot print_timing: id 0 | task 13525 | eval time = 537.87 ms / 54 tokens ( 10.15 ms per token, 98.54 tokens per second) 2.48.097.390 I slot print_timing: id 0 | task 13525 | total time = 627.39 ms / 392 tokens 2.48.097.392 I slot print_timing: id 0 | task 13525 | graphs reused = 13052 2.48.097.393 I slot print_timing: id 0 | task 13525 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.097.422 I slot release: id 0 | task 13525 | stop processing: n_tokens = 418, truncated = 0 2.48.127.032 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 168005035 2.48.147.063 I slot launch_slot_: id 0 | task 13580 | processing task, is_child = 0 2.51.239.723 I slot print_timing: id 0 | task 13580 | n_gen = 297, tg = 98.59 t/s, tg_3s = 98.92 t/s 2.54.248.093 I slot print_timing: id 0 | task 13580 | n_gen = 592, tg = 98.32 t/s, tg_3s = 98.06 t/s 2.57.250.209 I slot print_timing: id 0 | task 13580 | n_gen = 882, tg = 97.75 t/s, tg_3s = 96.60 t/s 2.58.751.036 I slot print_timing: id 0 | task 13580 | prompt eval time = 90.33 ms / 363 tokens ( 0.25 ms per token, 4018.51 tokens per second) 2.58.751.042 I slot print_timing: id 0 | task 13580 | eval time = 10513.62 ms / 1024 tokens ( 10.28 ms per token, 97.30 tokens per second) 2.58.751.043 I slot print_timing: id 0 | task 13580 | total time = 10603.96 ms / 1387 tokens 2.58.751.044 I slot print_timing: id 0 | task 13580 | graphs reused = 14070 2.58.751.045 I slot print_timing: id 0 | task 13580 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.751.074 I slot release: id 0 | task 13580 | stop processing: n_tokens = 1413, truncated = 0 2.58.765.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1413, t_last = 178658687 2.58.765.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 81.413 MiB) 2.58.770.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 115.791 MiB) 2.58.840.610 I slot launch_slot_: id 0 | task 14605 | processing task, is_child = 0 3.00.437.885 I slot print_timing: id 0 | task 14605 | prompt eval time = 81.77 ms / 317 tokens ( 0.26 ms per token, 3876.63 tokens per second) 3.00.437.891 I slot print_timing: id 0 | task 14605 | eval time = 1515.48 ms / 151 tokens ( 10.10 ms per token, 98.98 tokens per second) 3.00.437.892 I slot print_timing: id 0 | task 14605 | total time = 1597.26 ms / 468 tokens 3.00.437.893 I slot print_timing: id 0 | task 14605 | graphs reused = 14219 3.00.437.894 I slot print_timing: id 0 | task 14605 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.437.923 I slot release: id 0 | task 14605 | stop processing: n_tokens = 494, truncated = 0 3.00.457.483 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 494, t_last = 180345536 3.00.457.532 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 134.073 MiB) 3.00.488.532 I slot launch_slot_: id 0 | task 14757 | processing task, is_child = 0 3.03.607.693 I slot print_timing: id 0 | task 14757 | n_gen = 297, tg = 98.35 t/s, tg_3s = 98.68 t/s 3.05.517.497 I slot print_timing: id 0 | task 14757 | prompt eval time = 109.33 ms / 389 tokens ( 0.28 ms per token, 3557.91 tokens per second) 3.05.517.504 I slot print_timing: id 0 | task 14757 | eval time = 4919.61 ms / 484 tokens ( 10.19 ms per token, 98.18 tokens per second) 3.05.517.505 I slot print_timing: id 0 | task 14757 | total time = 5028.95 ms / 873 tokens 3.05.517.506 I slot print_timing: id 0 | task 14757 | graphs reused = 14699 3.05.517.507 I slot print_timing: id 0 | task 14757 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.517.542 I slot release: id 0 | task 14757 | stop processing: n_tokens = 897, truncated = 0 3.05.546.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 897, t_last = 185425155 3.05.546.577 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 86.101 MiB) 3.05.594.167 I slot launch_slot_: id 0 | task 15242 | processing task, is_child = 0 3.05.982.242 I slot print_timing: id 0 | task 15242 | prompt eval time = 81.11 ms / 300 tokens ( 0.27 ms per token, 3698.73 tokens per second) 3.05.982.248 I slot print_timing: id 0 | task 15242 | eval time = 306.95 ms / 31 tokens ( 10.23 ms per token, 97.74 tokens per second) 3.05.982.249 I slot print_timing: id 0 | task 15242 | total time = 388.06 ms / 331 tokens 3.05.982.251 I slot print_timing: id 0 | task 15242 | graphs reused = 14728 3.05.982.252 I slot print_timing: id 0 | task 15242 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.982.279 I slot release: id 0 | task 15242 | stop processing: n_tokens = 355, truncated = 0 3.05.996.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 185889893 3.05.996.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.040 MiB) 3.06.020.122 I slot launch_slot_: id 0 | task 15274 | processing task, is_child = 0 3.07.180.270 I slot print_timing: id 0 | task 15274 | prompt eval time = 89.68 ms / 341 tokens ( 0.26 ms per token, 3802.49 tokens per second) 3.07.180.276 I slot print_timing: id 0 | task 15274 | eval time = 1070.45 ms / 107 tokens ( 10.10 ms per token, 99.02 tokens per second) 3.07.180.277 I slot print_timing: id 0 | task 15274 | total time = 1160.13 ms / 448 tokens 3.07.180.277 I slot print_timing: id 0 | task 15274 | graphs reused = 14833 3.07.180.278 I slot print_timing: id 0 | task 15274 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.180.306 I slot release: id 0 | task 15274 | stop processing: n_tokens = 472, truncated = 0 3.07.201.165 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 472, t_last = 187087919 3.07.222.492 I slot launch_slot_: id 0 | task 15382 | processing task, is_child = 0 3.08.732.106 I slot print_timing: id 0 | task 15382 | prompt eval time = 82.30 ms / 332 tokens ( 0.25 ms per token, 4033.92 tokens per second) 3.08.732.111 I slot print_timing: id 0 | task 15382 | eval time = 1427.30 ms / 142 tokens ( 10.12 ms per token, 98.79 tokens per second) 3.08.732.112 I slot print_timing: id 0 | task 15382 | total time = 1509.60 ms / 474 tokens 3.08.732.113 I slot print_timing: id 0 | task 15382 | graphs reused = 14973 3.08.732.114 I slot print_timing: id 0 | task 15382 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.732.143 I slot release: id 0 | task 15382 | stop processing: n_tokens = 498, truncated = 0 3.08.752.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 188639756 3.08.752.581 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 137.980 MiB) 3.08.785.066 I slot launch_slot_: id 0 | task 15525 | processing task, is_child = 0 3.09.607.676 I slot print_timing: id 0 | task 15525 | prompt eval time = 72.88 ms / 269 tokens ( 0.27 ms per token, 3691.10 tokens per second) 3.09.607.682 I slot print_timing: id 0 | task 15525 | eval time = 749.71 ms / 75 tokens ( 10.13 ms per token, 98.70 tokens per second) 3.09.607.683 I slot print_timing: id 0 | task 15525 | total time = 822.59 ms / 344 tokens 3.09.607.684 I slot print_timing: id 0 | task 15525 | graphs reused = 15046 3.09.607.685 I slot print_timing: id 0 | task 15525 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.607.711 I slot release: id 0 | task 15525 | stop processing: n_tokens = 368, truncated = 0 3.09.626.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 368, t_last = 189515324 3.09.642.225 I slot launch_slot_: id 0 | task 15601 | processing task, is_child = 0 3.12.738.165 I slot print_timing: id 0 | task 15601 | n_gen = 297, tg = 98.47 t/s, tg_3s = 98.80 t/s 3.15.744.010 I slot print_timing: id 0 | task 15601 | n_gen = 589, tg = 97.81 t/s, tg_3s = 97.14 t/s 3.16.866.882 I slot print_timing: id 0 | task 15601 | prompt eval time = 89.91 ms / 341 tokens ( 0.26 ms per token, 3792.81 tokens per second) 3.16.866.887 I slot print_timing: id 0 | task 15601 | eval time = 7134.73 ms / 698 tokens ( 10.24 ms per token, 97.69 tokens per second) 3.16.866.888 I slot print_timing: id 0 | task 15601 | total time = 7224.64 ms / 1039 tokens 3.16.866.889 I slot print_timing: id 0 | task 15601 | graphs reused = 15739 3.16.866.890 I slot print_timing: id 0 | task 15601 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.866.921 I slot release: id 0 | task 15601 | stop processing: n_tokens = 1063, truncated = 0 3.16.890.659 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1063, t_last = 196774534 3.16.890.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 107.353 MiB) 3.16.897.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.539 MiB) 3.16.955.091 I slot launch_slot_: id 0 | task 16300 | processing task, is_child = 0 3.18.598.779 I slot print_timing: id 0 | task 16300 | prompt eval time = 90.01 ms / 343 tokens ( 0.26 ms per token, 3810.77 tokens per second) 3.18.598.786 I slot print_timing: id 0 | task 16300 | eval time = 1553.66 ms / 154 tokens ( 10.15 ms per token, 98.48 tokens per second) 3.18.598.787 I slot print_timing: id 0 | task 16300 | total time = 1643.67 ms / 497 tokens 3.18.598.789 I slot print_timing: id 0 | task 16300 | graphs reused = 15890 3.18.598.789 I slot print_timing: id 0 | task 16300 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.598.820 I slot release: id 0 | task 16300 | stop processing: n_tokens = 521, truncated = 0 3.18.614.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 198506433 3.18.614.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.163 MiB) 3.18.642.586 I slot launch_slot_: id 0 | task 16455 | processing task, is_child = 0 3.21.738.664 I slot print_timing: id 0 | task 16455 | n_gen = 297, tg = 98.47 t/s, tg_3s = 98.80 t/s 3.24.747.646 I slot print_timing: id 0 | task 16455 | n_gen = 592, tg = 98.26 t/s, tg_3s = 98.04 t/s 3.27.755.949 I slot print_timing: id 0 | task 16455 | n_gen = 883, tg = 97.75 t/s, tg_3s = 96.73 t/s 3.27.921.942 I slot print_timing: id 0 | task 16455 | prompt eval time = 90.08 ms / 347 tokens ( 0.26 ms per token, 3851.92 tokens per second) 3.27.921.948 I slot print_timing: id 0 | task 16455 | eval time = 9189.25 ms / 899 tokens ( 10.23 ms per token, 97.72 tokens per second) 3.27.921.949 I slot print_timing: id 0 | task 16455 | total time = 9279.34 ms / 1246 tokens 3.27.921.950 I slot print_timing: id 0 | task 16455 | graphs reused = 16784 3.27.921.951 I slot print_timing: id 0 | task 16455 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.921.983 I slot release: id 0 | task 16455 | stop processing: n_tokens = 1270, truncated = 0 3.27.926.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1270, t_last = 207829596 3.27.926.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 90.633 MiB) 3.27.932.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 91.883 MiB) 3.27.999.848 I slot launch_slot_: id 0 | task 17355 | processing task, is_child = 0 3.29.848.419 I slot print_timing: id 0 | task 17355 | prompt eval time = 83.00 ms / 332 tokens ( 0.25 ms per token, 4000.10 tokens per second) 3.29.848.425 I slot print_timing: id 0 | task 17355 | eval time = 1765.55 ms / 175 tokens ( 10.15 ms per token, 98.55 tokens per second) 3.29.848.426 I slot print_timing: id 0 | task 17355 | total time = 1848.55 ms / 507 tokens 3.29.848.427 I slot print_timing: id 0 | task 17355 | graphs reused = 16956 3.29.848.428 I slot print_timing: id 0 | task 17355 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.848.457 I slot release: id 0 | task 17355 | stop processing: n_tokens = 531, truncated = 0 3.29.861.534 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 209756070 3.29.861.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 113.447 MiB) 3.29.893.068 I slot launch_slot_: id 0 | task 17531 | processing task, is_child = 0 3.30.503.110 I slot print_timing: id 0 | task 17531 | prompt eval time = 82.38 ms / 332 tokens ( 0.25 ms per token, 4029.91 tokens per second) 3.30.503.115 I slot print_timing: id 0 | task 17531 | eval time = 527.64 ms / 53 tokens ( 10.15 ms per token, 98.55 tokens per second) 3.30.503.116 I slot print_timing: id 0 | task 17531 | total time = 610.02 ms / 385 tokens 3.30.503.117 I slot print_timing: id 0 | task 17531 | graphs reused = 17007 3.30.503.118 I slot print_timing: id 0 | task 17531 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.503.147 I slot release: id 0 | task 17531 | stop processing: n_tokens = 409, truncated = 0 3.30.529.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 210410760 3.30.529.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 101.258 MiB) 3.30.554.771 I slot launch_slot_: id 0 | task 17585 | processing task, is_child = 0 3.31.849.526 I slot print_timing: id 0 | task 17585 | prompt eval time = 90.54 ms / 354 tokens ( 0.26 ms per token, 3909.74 tokens per second) 3.31.849.532 I slot print_timing: id 0 | task 17585 | eval time = 1204.19 ms / 120 tokens ( 10.12 ms per token, 98.82 tokens per second) 3.31.849.534 I slot print_timing: id 0 | task 17585 | total time = 1294.74 ms / 474 tokens 3.31.849.534 I slot print_timing: id 0 | task 17585 | graphs reused = 17125 3.31.849.536 I slot print_timing: id 0 | task 17585 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.849.567 I slot release: id 0 | task 17585 | stop processing: n_tokens = 498, truncated = 0 3.31.871.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 211757180 3.31.894.808 I slot launch_slot_: id 0 | task 17706 | processing task, is_child = 0 3.33.434.976 I slot print_timing: id 0 | task 17706 | prompt eval time = 90.24 ms / 354 tokens ( 0.25 ms per token, 3922.79 tokens per second) 3.33.434.981 I slot print_timing: id 0 | task 17706 | eval time = 1449.91 ms / 144 tokens ( 10.14 ms per token, 98.63 tokens per second) 3.33.434.982 I slot print_timing: id 0 | task 17706 | total time = 1540.15 ms / 498 tokens 3.33.434.983 I slot print_timing: id 0 | task 17706 | graphs reused = 17266 3.33.434.984 I slot print_timing: id 0 | task 17706 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.435.013 I slot release: id 0 | task 17706 | stop processing: n_tokens = 522, truncated = 0 3.33.454.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 522, t_last = 213342627 3.33.455.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 135.480 MiB) 3.33.486.571 I slot launch_slot_: id 0 | task 17851 | processing task, is_child = 0 3.34.043.244 I slot print_timing: id 0 | task 17851 | prompt eval time = 89.56 ms / 339 tokens ( 0.26 ms per token, 3785.26 tokens per second) 3.34.043.250 I slot print_timing: id 0 | task 17851 | eval time = 467.10 ms / 47 tokens ( 10.15 ms per token, 98.48 tokens per second) 3.34.043.251 I slot print_timing: id 0 | task 17851 | total time = 556.65 ms / 386 tokens 3.34.043.252 I slot print_timing: id 0 | task 17851 | graphs reused = 17311 3.34.043.252 I slot print_timing: id 0 | task 17851 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.043.282 I slot release: id 0 | task 17851 | stop processing: n_tokens = 410, truncated = 0 3.34.063.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 213950895 3.34.082.381 I slot launch_slot_: id 0 | task 17899 | processing task, is_child = 0 3.35.203.648 I slot print_timing: id 0 | task 17899 | prompt eval time = 90.03 ms / 351 tokens ( 0.26 ms per token, 3898.57 tokens per second) 3.35.203.654 I slot print_timing: id 0 | task 17899 | eval time = 1031.22 ms / 103 tokens ( 10.11 ms per token, 98.91 tokens per second) 3.35.203.655 I slot print_timing: id 0 | task 17899 | total time = 1121.25 ms / 454 tokens 3.35.203.656 I slot print_timing: id 0 | task 17899 | graphs reused = 17412 3.35.203.657 I slot print_timing: id 0 | task 17899 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.203.688 I slot release: id 0 | task 17899 | stop processing: n_tokens = 478, truncated = 0 3.35.232.892 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 215111301 3.35.232.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.227 MiB) 3.35.261.414 I slot launch_slot_: id 0 | task 18003 | processing task, is_child = 0 3.36.807.157 I slot print_timing: id 0 | task 18003 | prompt eval time = 82.12 ms / 325 tokens ( 0.25 ms per token, 3957.38 tokens per second) 3.36.807.162 I slot print_timing: id 0 | task 18003 | eval time = 1463.60 ms / 146 tokens ( 10.09 ms per token, 99.07 tokens per second) 3.36.807.163 I slot print_timing: id 0 | task 18003 | total time = 1545.73 ms / 471 tokens 3.36.807.164 I slot print_timing: id 0 | task 18003 | graphs reused = 17556 3.36.807.165 I slot print_timing: id 0 | task 18003 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.807.195 I slot release: id 0 | task 18003 | stop processing: n_tokens = 495, truncated = 0 3.36.833.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 216714808 3.36.833.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 108.759 MiB) 3.36.863.460 I slot launch_slot_: id 0 | task 18150 | processing task, is_child = 0 3.37.514.942 I slot print_timing: id 0 | task 18150 | prompt eval time = 81.34 ms / 308 tokens ( 0.26 ms per token, 3786.53 tokens per second) 3.37.514.949 I slot print_timing: id 0 | task 18150 | eval time = 570.12 ms / 56 tokens ( 10.37 ms per token, 96.47 tokens per second) 3.37.514.950 I slot print_timing: id 0 | task 18150 | total time = 651.46 ms / 364 tokens 3.37.514.951 I slot print_timing: id 0 | task 18150 | graphs reused = 17610 3.37.514.951 I slot print_timing: id 0 | task 18150 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.514.985 I slot release: id 0 | task 18150 | stop processing: n_tokens = 388, truncated = 0 3.37.531.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 217422598 3.37.549.611 I slot launch_slot_: id 0 | task 18207 | processing task, is_child = 0 3.40.643.454 I slot print_timing: id 0 | task 18207 | n_gen = 297, tg = 98.57 t/s, tg_3s = 98.90 t/s 3.43.646.955 I slot print_timing: id 0 | task 18207 | n_gen = 590, tg = 98.06 t/s, tg_3s = 97.55 t/s 3.45.006.913 I slot print_timing: id 0 | task 18207 | prompt eval time = 90.73 ms / 349 tokens ( 0.26 ms per token, 3846.45 tokens per second) 3.45.006.918 I slot print_timing: id 0 | task 18207 | eval time = 7366.55 ms / 722 tokens ( 10.22 ms per token, 97.87 tokens per second) 3.45.006.919 I slot print_timing: id 0 | task 18207 | total time = 7457.28 ms / 1071 tokens 3.45.006.920 I slot print_timing: id 0 | task 18207 | graphs reused = 18327 3.45.006.921 I slot print_timing: id 0 | task 18207 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.006.956 I slot release: id 0 | task 18207 | stop processing: n_tokens = 1095, truncated = 0 3.45.035.131 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1095, t_last = 224914569 3.45.035.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 103.602 MiB) 3.45.041.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 123.447 MiB) 3.45.098.380 I slot launch_slot_: id 0 | task 18930 | processing task, is_child = 0 3.48.083.577 I slot print_timing: id 0 | task 18930 | prompt eval time = 89.84 ms / 371 tokens ( 0.24 ms per token, 4129.56 tokens per second) 3.48.083.583 I slot print_timing: id 0 | task 18930 | eval time = 2895.34 ms / 286 tokens ( 10.16 ms per token, 98.43 tokens per second) 3.48.083.584 I slot print_timing: id 0 | task 18930 | total time = 2985.18 ms / 657 tokens 3.48.083.585 I slot print_timing: id 0 | task 18930 | graphs reused = 18610 3.48.083.586 I slot print_timing: id 0 | task 18930 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.083.617 I slot release: id 0 | task 18930 | stop processing: n_tokens = 686, truncated = 0 3.48.102.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 686, t_last = 227991231 3.48.102.486 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 144.074 MiB) 3.48.142.017 I slot launch_slot_: id 0 | task 19217 | processing task, is_child = 0 3.49.507.858 I slot print_timing: id 0 | task 19217 | prompt eval time = 81.72 ms / 303 tokens ( 0.27 ms per token, 3707.87 tokens per second) 3.49.507.864 I slot print_timing: id 0 | task 19217 | eval time = 1284.11 ms / 128 tokens ( 10.11 ms per token, 98.90 tokens per second) 3.49.507.864 I slot print_timing: id 0 | task 19217 | total time = 1365.82 ms / 431 tokens 3.49.507.865 I slot print_timing: id 0 | task 19217 | graphs reused = 18736 3.49.507.866 I slot print_timing: id 0 | task 19217 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.507.893 I slot release: id 0 | task 19217 | stop processing: n_tokens = 455, truncated = 0 3.49.534.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 455, t_last = 229415506 3.49.554.344 I slot launch_slot_: id 0 | task 19346 | processing task, is_child = 0 3.52.028.412 I slot print_timing: id 0 | task 19346 | prompt eval time = 81.43 ms / 312 tokens ( 0.26 ms per token, 3831.56 tokens per second) 3.52.028.419 I slot print_timing: id 0 | task 19346 | eval time = 2392.62 ms / 236 tokens ( 10.18 ms per token, 98.22 tokens per second) 3.52.028.421 I slot print_timing: id 0 | task 19346 | total time = 2474.05 ms / 548 tokens 3.52.028.421 I slot print_timing: id 0 | task 19346 | graphs reused = 18969 3.52.028.422 I slot print_timing: id 0 | task 19346 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.028.452 I slot release: id 0 | task 19346 | stop processing: n_tokens = 572, truncated = 0 3.52.049.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 231936066 3.52.049.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 182.202 MiB) 3.52.085.241 I slot launch_slot_: id 0 | task 19583 | processing task, is_child = 0 3.55.167.663 I slot print_timing: id 0 | task 19583 | n_gen = 297, tg = 98.65 t/s, tg_3s = 98.98 t/s 3.58.139.601 I slot print_timing: id 0 | task 19583 | prompt eval time = 81.75 ms / 311 tokens ( 0.26 ms per token, 3804.05 tokens per second) 3.58.139.606 I slot print_timing: id 0 | task 19583 | eval time = 5972.59 ms / 587 tokens ( 10.19 ms per token, 98.11 tokens per second) 3.58.139.607 I slot print_timing: id 0 | task 19583 | total time = 6054.34 ms / 898 tokens 3.58.139.608 I slot print_timing: id 0 | task 19583 | graphs reused = 19552 3.58.139.609 I slot print_timing: id 0 | task 19583 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.139.637 I slot release: id 0 | task 19583 | stop processing: n_tokens = 922, truncated = 0 3.58.167.672 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 922, t_last = 238047250 3.58.167.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 74.069 MiB) 3.58.218.336 I slot launch_slot_: id 0 | task 20171 | processing task, is_child = 0 3.58.697.004 I slot print_timing: id 0 | task 20171 | prompt eval time = 82.19 ms / 331 tokens ( 0.25 ms per token, 4027.40 tokens per second) 3.58.697.009 I slot print_timing: id 0 | task 20171 | eval time = 396.46 ms / 40 tokens ( 10.17 ms per token, 98.37 tokens per second) 3.58.697.010 I slot print_timing: id 0 | task 20171 | total time = 478.65 ms / 371 tokens 3.58.697.011 I slot print_timing: id 0 | task 20171 | graphs reused = 19590 3.58.697.012 I slot print_timing: id 0 | task 20171 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.697.041 I slot release: id 0 | task 20171 | stop processing: n_tokens = 395, truncated = 0 3.58.714.763 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 238604654 3.58.714.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 71.881 MiB) 3.58.738.417 I slot launch_slot_: id 0 | task 20212 | processing task, is_child = 0 4.00.061.566 I slot print_timing: id 0 | task 20212 | prompt eval time = 82.52 ms / 335 tokens ( 0.25 ms per token, 4059.72 tokens per second) 4.00.061.572 I slot print_timing: id 0 | task 20212 | eval time = 1240.61 ms / 124 tokens ( 10.09 ms per token, 99.14 tokens per second) 4.00.061.574 I slot print_timing: id 0 | task 20212 | total time = 1323.13 ms / 459 tokens 4.00.061.574 I slot print_timing: id 0 | task 20212 | graphs reused = 19712 4.00.061.576 I slot print_timing: id 0 | task 20212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.061.609 I slot release: id 0 | task 20212 | stop processing: n_tokens = 483, truncated = 0 4.00.084.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 239969222 4.00.084.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 66.256 MiB) 4.00.110.387 I slot launch_slot_: id 0 | task 20337 | processing task, is_child = 0 4.01.800.460 I slot print_timing: id 0 | task 20337 | prompt eval time = 82.38 ms / 331 tokens ( 0.25 ms per token, 4018.16 tokens per second) 4.01.800.466 I slot print_timing: id 0 | task 20337 | eval time = 1607.68 ms / 160 tokens ( 10.11 ms per token, 98.90 tokens per second) 4.01.800.467 I slot print_timing: id 0 | task 20337 | total time = 1690.06 ms / 491 tokens 4.01.800.468 I slot print_timing: id 0 | task 20337 | graphs reused = 19869 4.01.800.469 I slot print_timing: id 0 | task 20337 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.800.498 I slot release: id 0 | task 20337 | stop processing: n_tokens = 515, truncated = 0 4.01.822.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 241708112 4.01.822.576 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 79.851 MiB) 4.01.849.786 I slot launch_slot_: id 0 | task 20498 | processing task, is_child = 0 4.03.102.717 I slot print_timing: id 0 | task 20498 | prompt eval time = 82.27 ms / 328 tokens ( 0.25 ms per token, 3986.87 tokens per second) 4.03.102.723 I slot print_timing: id 0 | task 20498 | eval time = 1170.65 ms / 117 tokens ( 10.09 ms per token, 99.09 tokens per second) 4.03.102.724 I slot print_timing: id 0 | task 20498 | total time = 1252.92 ms / 445 tokens 4.03.102.725 I slot print_timing: id 0 | task 20498 | graphs reused = 19984 4.03.102.726 I slot print_timing: id 0 | task 20498 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.102.757 I slot release: id 0 | task 20498 | stop processing: n_tokens = 469, truncated = 0 4.03.130.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 243010370 4.03.131.025 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 84.382 MiB) 4.03.158.326 I slot launch_slot_: id 0 | task 20616 | processing task, is_child = 0 4.04.221.771 I slot print_timing: id 0 | task 20616 | prompt eval time = 82.42 ms / 331 tokens ( 0.25 ms per token, 4016.16 tokens per second) 4.04.221.777 I slot print_timing: id 0 | task 20616 | eval time = 981.01 ms / 98 tokens ( 10.11 ms per token, 98.88 tokens per second) 4.04.221.778 I slot print_timing: id 0 | task 20616 | total time = 1063.43 ms / 429 tokens 4.04.221.779 I slot print_timing: id 0 | task 20616 | graphs reused = 20080 4.04.221.780 I slot print_timing: id 0 | task 20616 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.221.811 I slot release: id 0 | task 20616 | stop processing: n_tokens = 453, truncated = 0 4.04.238.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 244129425 4.04.238.338 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 99.852 MiB) 4.04.267.520 I slot launch_slot_: id 0 | task 20715 | processing task, is_child = 0 4.04.899.909 I slot print_timing: id 0 | task 20715 | prompt eval time = 90.16 ms / 348 tokens ( 0.26 ms per token, 3859.93 tokens per second) 4.04.899.916 I slot print_timing: id 0 | task 20715 | eval time = 542.21 ms / 54 tokens ( 10.23 ms per token, 97.75 tokens per second) 4.04.899.917 I slot print_timing: id 0 | task 20715 | total time = 632.37 ms / 402 tokens 4.04.899.917 I slot print_timing: id 0 | task 20715 | graphs reused = 20132 4.04.899.918 I slot print_timing: id 0 | task 20715 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.899.951 I slot release: id 0 | task 20715 | stop processing: n_tokens = 426, truncated = 0 4.04.922.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 244807564 4.04.942.641 I slot launch_slot_: id 0 | task 20770 | processing task, is_child = 0 4.05.554.146 I slot print_timing: id 0 | task 20770 | prompt eval time = 82.57 ms / 332 tokens ( 0.25 ms per token, 4020.93 tokens per second) 4.05.554.153 I slot print_timing: id 0 | task 20770 | eval time = 528.92 ms / 53 tokens ( 10.17 ms per token, 98.31 tokens per second) 4.05.554.154 I slot print_timing: id 0 | task 20770 | total time = 611.49 ms / 385 tokens 4.05.554.156 I slot print_timing: id 0 | task 20770 | graphs reused = 20183 4.05.554.156 I slot print_timing: id 0 | task 20770 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.554.186 I slot release: id 0 | task 20770 | stop processing: n_tokens = 411, truncated = 0 4.05.558.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 245461799 4.05.558.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 64.537 MiB) 4.05.578.523 I slot launch_slot_: id 0 | task 20824 | processing task, is_child = 0 4.07.186.619 I slot print_timing: id 0 | task 20824 | prompt eval time = 89.66 ms / 339 tokens ( 0.26 ms per token, 3780.87 tokens per second) 4.07.186.624 I slot print_timing: id 0 | task 20824 | eval time = 1518.42 ms / 151 tokens ( 10.12 ms per token, 98.79 tokens per second) 4.07.186.625 I slot print_timing: id 0 | task 20824 | total time = 1608.08 ms / 490 tokens 4.07.186.626 I slot print_timing: id 0 | task 20824 | graphs reused = 20331 4.07.186.627 I slot print_timing: id 0 | task 20824 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.186.657 I slot release: id 0 | task 20824 | stop processing: n_tokens = 514, truncated = 0 4.07.213.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 247094270 4.07.213.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 65.006 MiB) 4.07.242.740 I slot launch_slot_: id 0 | task 20976 | processing task, is_child = 0 4.07.869.821 I slot print_timing: id 0 | task 20976 | prompt eval time = 89.53 ms / 343 tokens ( 0.26 ms per token, 3831.12 tokens per second) 4.07.869.826 I slot print_timing: id 0 | task 20976 | eval time = 537.53 ms / 54 tokens ( 10.14 ms per token, 98.60 tokens per second) 4.07.869.827 I slot print_timing: id 0 | task 20976 | total time = 627.06 ms / 397 tokens 4.07.869.828 I slot print_timing: id 0 | task 20976 | graphs reused = 20383 4.07.869.829 I slot print_timing: id 0 | task 20976 | graph reallocs = 0 / 0 (same size) / (changed size) 4.07.869.857 I slot release: id 0 | task 20976 | stop processing: n_tokens = 421, truncated = 0 4.07.895.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 247777471 4.07.895.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 4.07.919.361 I slot launch_slot_: id 0 | task 21031 | processing task, is_child = 0 4.09.270.937 I slot print_timing: id 0 | task 21031 | prompt eval time = 90.35 ms / 360 tokens ( 0.25 ms per token, 3984.64 tokens per second) 4.09.270.942 I slot print_timing: id 0 | task 21031 | eval time = 1261.21 ms / 126 tokens ( 10.09 ms per token, 99.11 tokens per second) 4.09.270.943 I slot print_timing: id 0 | task 21031 | total time = 1351.56 ms / 486 tokens 4.09.270.944 I slot print_timing: id 0 | task 21031 | graphs reused = 20507 4.09.270.945 I slot print_timing: id 0 | task 21031 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.270.975 I slot release: id 0 | task 21031 | stop processing: n_tokens = 510, truncated = 0 4.09.294.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 249178588 4.09.294.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 85.945 MiB) 4.09.322.352 I slot launch_slot_: id 0 | task 21158 | processing task, is_child = 0 4.09.888.279 I slot print_timing: id 0 | task 21158 | prompt eval time = 89.61 ms / 341 tokens ( 0.26 ms per token, 3805.42 tokens per second) 4.09.888.285 I slot print_timing: id 0 | task 21158 | eval time = 476.30 ms / 48 tokens ( 10.13 ms per token, 98.68 tokens per second) 4.09.888.286 I slot print_timing: id 0 | task 21158 | total time = 565.91 ms / 389 tokens 4.09.888.286 I slot print_timing: id 0 | task 21158 | graphs reused = 20553 4.09.888.287 I slot print_timing: id 0 | task 21158 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.888.316 I slot release: id 0 | task 21158 | stop processing: n_tokens = 413, truncated = 0 4.09.902.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 249795930 4.09.902.832 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 78.132 MiB) 4.09.926.640 I slot launch_slot_: id 0 | task 21207 | processing task, is_child = 0 4.13.020.702 I slot print_timing: id 0 | task 21207 | n_gen = 297, tg = 98.55 t/s, tg_3s = 98.88 t/s 4.13.598.958 I slot print_timing: id 0 | task 21207 | prompt eval time = 90.35 ms / 358 tokens ( 0.25 ms per token, 3962.37 tokens per second) 4.13.598.963 I slot print_timing: id 0 | task 21207 | eval time = 3581.95 ms / 354 tokens ( 10.15 ms per token, 98.55 tokens per second) 4.13.598.964 I slot print_timing: id 0 | task 21207 | total time = 3672.30 ms / 712 tokens 4.13.598.965 I slot print_timing: id 0 | task 21207 | graphs reused = 20904 4.13.598.966 I slot print_timing: id 0 | task 21207 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.598.997 I slot release: id 0 | task 21207 | stop processing: n_tokens = 736, truncated = 0 4.13.623.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 736, t_last = 253506610 4.13.623.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 80.476 MiB) 4.13.659.308 I slot launch_slot_: id 0 | task 21562 | processing task, is_child = 0 4.16.755.831 I slot print_timing: id 0 | task 21562 | n_gen = 297, tg = 98.46 t/s, tg_3s = 98.79 t/s 4.19.756.528 I slot print_timing: id 0 | task 21562 | n_gen = 591, tg = 98.22 t/s, tg_3s = 97.98 t/s 4.22.759.581 I slot print_timing: id 0 | task 21562 | n_gen = 882, tg = 97.78 t/s, tg_3s = 96.90 t/s 4.24.238.878 I slot print_timing: id 0 | task 21562 | prompt eval time = 90.27 ms / 358 tokens ( 0.25 ms per token, 3965.79 tokens per second) 4.24.238.883 I slot print_timing: id 0 | task 21562 | eval time = 10489.28 ms / 1024 tokens ( 10.25 ms per token, 97.53 tokens per second) 4.24.238.884 I slot print_timing: id 0 | task 21562 | total time = 10579.55 ms / 1382 tokens 4.24.238.885 I slot print_timing: id 0 | task 21562 | graphs reused = 21922 4.24.238.886 I slot print_timing: id 0 | task 21562 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.238.918 I slot release: id 0 | task 21562 | stop processing: n_tokens = 1409, truncated = 0 4.24.257.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1409, t_last = 264146531 4.24.257.519 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 83.601 MiB) 4.24.262.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 70.006 MiB) 4.24.266.847 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 82.976 MiB) 4.24.340.642 I slot launch_slot_: id 0 | task 22587 | processing task, is_child = 0 4.25.614.066 I slot print_timing: id 0 | task 22587 | prompt eval time = 108.76 ms / 387 tokens ( 0.28 ms per token, 3558.39 tokens per second) 4.25.614.072 I slot print_timing: id 0 | task 22587 | eval time = 1164.65 ms / 116 tokens ( 10.13 ms per token, 98.74 tokens per second) 4.25.614.073 I slot print_timing: id 0 | task 22587 | total time = 1273.41 ms / 503 tokens 4.25.614.073 I slot print_timing: id 0 | task 22587 | graphs reused = 22035 4.25.614.074 I slot print_timing: id 0 | task 22587 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.614.103 I slot release: id 0 | task 22587 | stop processing: n_tokens = 527, truncated = 0 4.25.635.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 527, t_last = 265521716 4.25.635.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 69.694 MiB) 4.25.662.931 I slot launch_slot_: id 0 | task 22704 | processing task, is_child = 0 4.26.369.602 I slot print_timing: id 0 | task 22704 | prompt eval time = 82.06 ms / 333 tokens ( 0.25 ms per token, 4057.96 tokens per second) 4.26.369.609 I slot print_timing: id 0 | task 22704 | eval time = 624.59 ms / 61 tokens ( 10.41 ms per token, 96.06 tokens per second) 4.26.369.610 I slot print_timing: id 0 | task 22704 | total time = 706.65 ms / 394 tokens 4.26.369.611 I slot print_timing: id 0 | task 22704 | graphs reused = 22094 4.26.369.612 I slot print_timing: id 0 | task 22704 | graph reallocs = 0 / 0 (same size) / (changed size) 4.26.369.645 I slot release: id 0 | task 22704 | stop processing: n_tokens = 418, truncated = 0