$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.092.793 I srv llama_server: initializing ... 0.00.092.800 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.092.925 I srv init_listene: The UI is disabled 0.00.092.927 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.093.007 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.104.796 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-Q4_K_M.gguf' 0.02.000.170 I cmn init: llama threadpool init, n_threads = 8 0.02.069.411 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.073.988 I srv llama_server: model loaded 0.02.073.994 I srv llama_server: listening on http://127.0.0.1:8089 0.02.525.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.525.253 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.02.985.538 I slot print_timing: id 0 | task 0 | prompt eval time = 108.63 ms / 368 tokens ( 0.30 ms per token, 3387.65 tokens per second) 0.02.985.544 I slot print_timing: id 0 | task 0 | eval time = 351.64 ms / 53 tokens ( 6.76 ms per token, 147.88 tokens per second) 0.02.985.545 I slot print_timing: id 0 | task 0 | total time = 460.27 ms / 421 tokens 0.02.985.551 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.02.985.551 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.02.985.581 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.006.217 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 2894778 0.03.031.455 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.393.244 I slot print_timing: id 0 | task 56 | prompt eval time = 84.82 ms / 322 tokens ( 0.26 ms per token, 3796.18 tokens per second) 0.03.393.250 I slot print_timing: id 0 | task 56 | eval time = 276.95 ms / 42 tokens ( 6.75 ms per token, 148.04 tokens per second) 0.03.393.251 I slot print_timing: id 0 | task 56 | total time = 361.77 ms / 364 tokens 0.03.393.253 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.393.254 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.393.281 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.410.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3302478 0.03.437.047 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.03.800.863 I slot print_timing: id 0 | task 101 | prompt eval time = 86.61 ms / 365 tokens ( 0.24 ms per token, 4214.54 tokens per second) 0.03.800.868 I slot print_timing: id 0 | task 101 | eval time = 277.19 ms / 42 tokens ( 6.76 ms per token, 147.91 tokens per second) 0.03.800.870 I slot print_timing: id 0 | task 101 | total time = 363.80 ms / 407 tokens 0.03.800.870 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.03.800.871 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.800.900 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.03.829.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 3710097 0.03.854.734 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.231.326 I slot print_timing: id 0 | task 146 | prompt eval time = 91.11 ms / 397 tokens ( 0.23 ms per token, 4357.18 tokens per second) 0.04.231.332 I slot print_timing: id 0 | task 146 | eval time = 285.46 ms / 43 tokens ( 6.80 ms per token, 147.13 tokens per second) 0.04.231.333 I slot print_timing: id 0 | task 146 | total time = 376.57 ms / 440 tokens 0.04.231.334 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.04.231.335 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.231.365 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.04.245.105 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.04.270.194 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.04.730.307 I slot print_timing: id 0 | task 192 | prompt eval time = 88.86 ms / 383 tokens ( 0.23 ms per token, 4310.01 tokens per second) 0.04.730.313 I slot print_timing: id 0 | task 192 | eval time = 371.23 ms / 55 tokens ( 6.87 ms per token, 145.46 tokens per second) 0.04.730.314 I slot print_timing: id 0 | task 192 | total time = 460.09 ms / 438 tokens 0.04.730.315 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.04.730.316 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.730.349 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.04.734.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 4639546 0.04.761.831 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.05.234.006 I slot print_timing: id 0 | task 250 | prompt eval time = 101.43 ms / 372 tokens ( 0.27 ms per token, 3667.63 tokens per second) 0.05.234.012 I slot print_timing: id 0 | task 250 | eval time = 370.73 ms / 55 tokens ( 6.87 ms per token, 145.66 tokens per second) 0.05.234.013 I slot print_timing: id 0 | task 250 | total time = 472.15 ms / 427 tokens 0.05.234.014 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.05.234.015 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.234.043 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.05.249.699 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5143240 0.05.275.235 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.05.738.456 I slot print_timing: id 0 | task 308 | prompt eval time = 98.11 ms / 422 tokens ( 0.23 ms per token, 4301.12 tokens per second) 0.05.738.461 I slot print_timing: id 0 | task 308 | eval time = 365.09 ms / 55 tokens ( 6.76 ms per token, 147.91 tokens per second) 0.05.738.462 I slot print_timing: id 0 | task 308 | total time = 463.20 ms / 477 tokens 0.05.738.463 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.05.738.464 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.738.495 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.05.742.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 5647693 0.05.770.144 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.06.353.822 I slot print_timing: id 0 | task 366 | prompt eval time = 100.98 ms / 470 tokens ( 0.21 ms per token, 4654.39 tokens per second) 0.06.353.828 I slot print_timing: id 0 | task 366 | eval time = 482.68 ms / 72 tokens ( 6.80 ms per token, 147.10 tokens per second) 0.06.353.829 I slot print_timing: id 0 | task 366 | total time = 583.66 ms / 542 tokens 0.06.353.830 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.06.353.830 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.353.860 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.06.375.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 6263058 0.06.400.919 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.06.797.845 I slot print_timing: id 0 | task 441 | prompt eval time = 86.94 ms / 345 tokens ( 0.25 ms per token, 3968.25 tokens per second) 0.06.797.851 I slot print_timing: id 0 | task 441 | eval time = 309.96 ms / 47 tokens ( 6.74 ms per token, 148.40 tokens per second) 0.06.797.852 I slot print_timing: id 0 | task 441 | total time = 396.90 ms / 392 tokens 0.06.797.853 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.06.797.854 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.797.882 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.06.811.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 6707079 0.06.845.975 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.07.202.950 I slot print_timing: id 0 | task 491 | prompt eval time = 87.79 ms / 364 tokens ( 0.24 ms per token, 4146.45 tokens per second) 0.07.202.956 I slot print_timing: id 0 | task 491 | eval time = 269.17 ms / 41 tokens ( 6.73 ms per token, 148.61 tokens per second) 0.07.202.957 I slot print_timing: id 0 | task 491 | total time = 356.95 ms / 405 tokens 0.07.202.958 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.07.202.959 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.202.985 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.07.218.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 7112183 0.07.244.350 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.07.796.093 I slot print_timing: id 0 | task 535 | prompt eval time = 93.35 ms / 376 tokens ( 0.25 ms per token, 4027.85 tokens per second) 0.07.796.100 I slot print_timing: id 0 | task 535 | eval time = 458.37 ms / 62 tokens ( 7.51 ms per token, 133.08 tokens per second) 0.07.796.101 I slot print_timing: id 0 | task 535 | total time = 551.72 ms / 438 tokens 0.07.796.102 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.07.796.103 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.796.133 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.07.810.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7705330 0.07.840.738 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.08.253.198 I slot print_timing: id 0 | task 600 | prompt eval time = 94.07 ms / 412 tokens ( 0.23 ms per token, 4379.67 tokens per second) 0.08.253.204 I slot print_timing: id 0 | task 600 | eval time = 318.37 ms / 47 tokens ( 6.92 ms per token, 144.49 tokens per second) 0.08.253.205 I slot print_timing: id 0 | task 600 | total time = 412.44 ms / 459 tokens 0.08.253.206 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.08.253.206 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.253.238 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.08.276.214 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 8162435 0.08.303.152 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.08.804.889 I slot print_timing: id 0 | task 650 | prompt eval time = 90.14 ms / 376 tokens ( 0.24 ms per token, 4171.47 tokens per second) 0.08.804.896 I slot print_timing: id 0 | task 650 | eval time = 411.58 ms / 62 tokens ( 6.75 ms per token, 148.21 tokens per second) 0.08.804.898 I slot print_timing: id 0 | task 650 | total time = 501.72 ms / 438 tokens 0.08.804.900 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.08.804.901 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.804.931 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.08.808.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 8714128 0.08.834.304 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.09.269.978 I slot print_timing: id 0 | task 715 | prompt eval time = 91.03 ms / 378 tokens ( 0.24 ms per token, 4152.71 tokens per second) 0.09.269.984 I slot print_timing: id 0 | task 715 | eval time = 344.63 ms / 52 tokens ( 6.76 ms per token, 147.99 tokens per second) 0.09.269.985 I slot print_timing: id 0 | task 715 | total time = 435.65 ms / 430 tokens 0.09.269.986 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.09.269.986 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.270.015 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.09.288.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 9179212 0.09.314.926 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.09.818.917 I slot print_timing: id 0 | task 770 | prompt eval time = 87.97 ms / 367 tokens ( 0.24 ms per token, 4172.07 tokens per second) 0.09.818.923 I slot print_timing: id 0 | task 770 | eval time = 416.00 ms / 58 tokens ( 7.30 ms per token, 137.02 tokens per second) 0.09.818.924 I slot print_timing: id 0 | task 770 | total time = 503.97 ms / 425 tokens 0.09.818.926 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.09.818.927 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.818.955 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.09.841.408 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 9728152 0.09.867.195 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.10.294.424 I slot print_timing: id 0 | task 831 | prompt eval time = 86.78 ms / 347 tokens ( 0.25 ms per token, 3998.57 tokens per second) 0.10.294.429 I slot print_timing: id 0 | task 831 | eval time = 340.43 ms / 51 tokens ( 6.81 ms per token, 146.87 tokens per second) 0.10.294.430 I slot print_timing: id 0 | task 831 | total time = 427.21 ms / 398 tokens 0.10.294.431 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.10.294.432 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.294.459 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.10.308.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 10203656 0.10.334.047 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.12.633.401 I slot print_timing: id 0 | task 885 | prompt eval time = 87.66 ms / 369 tokens ( 0.24 ms per token, 4209.30 tokens per second) 0.12.633.408 I slot print_timing: id 0 | task 885 | eval time = 2211.67 ms / 322 tokens ( 6.89 ms per token, 145.14 tokens per second) 0.12.633.409 I slot print_timing: id 0 | task 885 | total time = 2299.33 ms / 691 tokens 0.12.633.410 I slot print_timing: id 0 | task 885 | graphs reused = 1124 0.12.633.411 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.633.445 I slot release: id 0 | task 885 | stop processing: n_tokens = 690, truncated = 0 0.12.638.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 690, t_last = 12542642 0.12.668.586 I slot launch_slot_: id 0 | task 1210 | processing task, is_child = 0 0.13.043.728 I slot print_timing: id 0 | task 1210 | prompt eval time = 90.66 ms / 352 tokens ( 0.26 ms per token, 3882.60 tokens per second) 0.13.043.735 I slot print_timing: id 0 | task 1210 | eval time = 284.45 ms / 41 tokens ( 7.11 ms per token, 140.62 tokens per second) 0.13.043.737 I slot print_timing: id 0 | task 1210 | total time = 375.12 ms / 393 tokens 0.13.043.738 I slot print_timing: id 0 | task 1210 | graphs reused = 1163 0.13.043.739 I slot print_timing: id 0 | task 1210 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.043.776 I slot release: id 0 | task 1210 | stop processing: n_tokens = 392, truncated = 0 0.13.061.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 12952974 0.13.090.133 I slot launch_slot_: id 0 | task 1254 | processing task, is_child = 0 0.13.455.941 I slot print_timing: id 0 | task 1254 | prompt eval time = 89.68 ms / 349 tokens ( 0.26 ms per token, 3891.74 tokens per second) 0.13.455.949 I slot print_timing: id 0 | task 1254 | eval time = 276.11 ms / 41 tokens ( 6.90 ms per token, 144.87 tokens per second) 0.13.455.950 I slot print_timing: id 0 | task 1254 | total time = 365.78 ms / 390 tokens 0.13.455.951 I slot print_timing: id 0 | task 1254 | graphs reused = 1202 0.13.455.952 I slot print_timing: id 0 | task 1254 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.455.980 I slot release: id 0 | task 1254 | stop processing: n_tokens = 389, truncated = 0 0.13.472.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 13365178 0.13.497.365 I slot launch_slot_: id 0 | task 1298 | processing task, is_child = 0 0.14.036.957 I slot print_timing: id 0 | task 1298 | prompt eval time = 91.64 ms / 384 tokens ( 0.24 ms per token, 4190.17 tokens per second) 0.14.036.963 I slot print_timing: id 0 | task 1298 | eval time = 447.93 ms / 63 tokens ( 7.22 ms per token, 138.41 tokens per second) 0.14.036.964 I slot print_timing: id 0 | task 1298 | total time = 539.57 ms / 447 tokens 0.14.036.965 I slot print_timing: id 0 | task 1298 | graphs reused = 1263 0.14.036.965 I slot print_timing: id 0 | task 1298 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.036.994 I slot release: id 0 | task 1298 | stop processing: n_tokens = 446, truncated = 0 0.14.064.208 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 13946191 0.14.090.136 I slot launch_slot_: id 0 | task 1364 | processing task, is_child = 0 0.14.533.034 I slot print_timing: id 0 | task 1364 | prompt eval time = 87.02 ms / 356 tokens ( 0.24 ms per token, 4091.20 tokens per second) 0.14.533.040 I slot print_timing: id 0 | task 1364 | eval time = 355.86 ms / 54 tokens ( 6.71 ms per token, 148.93 tokens per second) 0.14.533.041 I slot print_timing: id 0 | task 1364 | total time = 442.88 ms / 410 tokens 0.14.533.042 I slot print_timing: id 0 | task 1364 | graphs reused = 1315 0.14.533.043 I slot print_timing: id 0 | task 1364 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.533.072 I slot release: id 0 | task 1364 | stop processing: n_tokens = 409, truncated = 0 0.14.550.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 14442270 0.14.575.416 I slot launch_slot_: id 0 | task 1421 | processing task, is_child = 0 0.15.130.260 I slot print_timing: id 0 | task 1421 | prompt eval time = 93.65 ms / 410 tokens ( 0.23 ms per token, 4378.05 tokens per second) 0.15.130.266 I slot print_timing: id 0 | task 1421 | eval time = 461.18 ms / 70 tokens ( 6.68 ms per token, 149.62 tokens per second) 0.15.130.267 I slot print_timing: id 0 | task 1421 | total time = 554.82 ms / 480 tokens 0.15.130.268 I slot print_timing: id 0 | task 1421 | graphs reused = 1383 0.15.130.269 I slot print_timing: id 0 | task 1421 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.130.297 I slot release: id 0 | task 1421 | stop processing: n_tokens = 479, truncated = 0 0.15.149.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 15039494 0.15.175.277 I slot launch_slot_: id 0 | task 1494 | processing task, is_child = 0 0.15.652.204 I slot print_timing: id 0 | task 1494 | prompt eval time = 94.02 ms / 385 tokens ( 0.24 ms per token, 4094.92 tokens per second) 0.15.652.210 I slot print_timing: id 0 | task 1494 | eval time = 382.89 ms / 58 tokens ( 6.72 ms per token, 148.87 tokens per second) 0.15.652.212 I slot print_timing: id 0 | task 1494 | total time = 476.91 ms / 443 tokens 0.15.652.213 I slot print_timing: id 0 | task 1494 | graphs reused = 1439 0.15.652.214 I slot print_timing: id 0 | task 1494 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.652.243 I slot release: id 0 | task 1494 | stop processing: n_tokens = 442, truncated = 0 0.15.679.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 15561440 0.15.705.074 I slot launch_slot_: id 0 | task 1555 | processing task, is_child = 0 0.16.264.903 I slot print_timing: id 0 | task 1555 | prompt eval time = 91.41 ms / 395 tokens ( 0.23 ms per token, 4321.00 tokens per second) 0.16.264.910 I slot print_timing: id 0 | task 1555 | eval time = 468.39 ms / 71 tokens ( 6.69 ms per token, 149.45 tokens per second) 0.16.264.912 I slot print_timing: id 0 | task 1555 | total time = 559.81 ms / 466 tokens 0.16.264.913 I slot print_timing: id 0 | task 1555 | graphs reused = 1508 0.16.264.914 I slot print_timing: id 0 | task 1555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.264.946 I slot release: id 0 | task 1555 | stop processing: n_tokens = 465, truncated = 0 0.16.285.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 16174143 0.16.310.683 I slot launch_slot_: id 0 | task 1629 | processing task, is_child = 0 0.16.790.627 I slot print_timing: id 0 | task 1629 | prompt eval time = 91.92 ms / 430 tokens ( 0.21 ms per token, 4677.78 tokens per second) 0.16.790.633 I slot print_timing: id 0 | task 1629 | eval time = 388.00 ms / 59 tokens ( 6.69 ms per token, 149.48 tokens per second) 0.16.790.634 I slot print_timing: id 0 | task 1629 | total time = 479.92 ms / 489 tokens 0.16.790.636 I slot print_timing: id 0 | task 1629 | graphs reused = 1565 0.16.790.637 I slot print_timing: id 0 | task 1629 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.790.666 I slot release: id 0 | task 1629 | stop processing: n_tokens = 488, truncated = 0 0.16.816.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 16699863 0.16.841.870 I slot launch_slot_: id 0 | task 1691 | processing task, is_child = 0 0.17.341.414 I slot print_timing: id 0 | task 1691 | prompt eval time = 91.29 ms / 392 tokens ( 0.23 ms per token, 4293.82 tokens per second) 0.17.341.420 I slot print_timing: id 0 | task 1691 | eval time = 408.23 ms / 62 tokens ( 6.69 ms per token, 149.43 tokens per second) 0.17.341.421 I slot print_timing: id 0 | task 1691 | total time = 499.52 ms / 454 tokens 0.17.341.422 I slot print_timing: id 0 | task 1691 | graphs reused = 1625 0.17.341.422 I slot print_timing: id 0 | task 1691 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.341.450 I slot release: id 0 | task 1691 | stop processing: n_tokens = 453, truncated = 0 0.17.369.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 17250648 0.17.394.893 I slot launch_slot_: id 0 | task 1756 | processing task, is_child = 0 0.17.801.860 I slot print_timing: id 0 | task 1756 | prompt eval time = 85.36 ms / 350 tokens ( 0.24 ms per token, 4100.28 tokens per second) 0.17.801.866 I slot print_timing: id 0 | task 1756 | eval time = 321.59 ms / 49 tokens ( 6.70 ms per token, 149.26 tokens per second) 0.17.801.867 I slot print_timing: id 0 | task 1756 | total time = 406.95 ms / 399 tokens 0.17.801.868 I slot print_timing: id 0 | task 1756 | graphs reused = 1672 0.17.801.869 I slot print_timing: id 0 | task 1756 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.801.896 I slot release: id 0 | task 1756 | stop processing: n_tokens = 398, truncated = 0 0.17.821.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 17711094 0.17.847.157 I slot launch_slot_: id 0 | task 1808 | processing task, is_child = 0 0.18.337.979 I slot print_timing: id 0 | task 1808 | prompt eval time = 89.92 ms / 380 tokens ( 0.24 ms per token, 4226.12 tokens per second) 0.18.337.985 I slot print_timing: id 0 | task 1808 | eval time = 400.88 ms / 61 tokens ( 6.68 ms per token, 149.67 tokens per second) 0.18.337.986 I slot print_timing: id 0 | task 1808 | total time = 490.80 ms / 441 tokens 0.18.337.987 I slot print_timing: id 0 | task 1808 | graphs reused = 1731 0.18.337.987 I slot print_timing: id 0 | task 1808 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.338.014 I slot release: id 0 | task 1808 | stop processing: n_tokens = 440, truncated = 0 0.18.354.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 18247211 0.18.379.884 I slot launch_slot_: id 0 | task 1872 | processing task, is_child = 0 0.19.044.518 I slot print_timing: id 0 | task 1872 | prompt eval time = 93.74 ms / 410 tokens ( 0.23 ms per token, 4373.89 tokens per second) 0.19.044.524 I slot print_timing: id 0 | task 1872 | eval time = 570.87 ms / 80 tokens ( 7.23 ms per token, 138.38 tokens per second) 0.19.044.525 I slot print_timing: id 0 | task 1872 | total time = 664.61 ms / 490 tokens 0.19.044.526 I slot print_timing: id 0 | task 1872 | graphs reused = 1809 0.19.044.526 I slot print_timing: id 0 | task 1872 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.044.554 I slot release: id 0 | task 1872 | stop processing: n_tokens = 489, truncated = 0 0.19.058.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 18953751 0.19.084.209 I slot launch_slot_: id 0 | task 1955 | processing task, is_child = 0 0.19.623.998 I slot print_timing: id 0 | task 1955 | prompt eval time = 90.74 ms / 387 tokens ( 0.23 ms per token, 4265.12 tokens per second) 0.19.624.004 I slot print_timing: id 0 | task 1955 | eval time = 449.03 ms / 68 tokens ( 6.70 ms per token, 149.21 tokens per second) 0.19.624.005 I slot print_timing: id 0 | task 1955 | total time = 539.77 ms / 455 tokens 0.19.624.005 I slot print_timing: id 0 | task 1955 | graphs reused = 1875 0.19.624.006 I slot print_timing: id 0 | task 1955 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.624.035 I slot release: id 0 | task 1955 | stop processing: n_tokens = 454, truncated = 0 0.19.640.336 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 19533232 0.19.665.773 I slot launch_slot_: id 0 | task 2026 | processing task, is_child = 0 0.20.138.950 I slot print_timing: id 0 | task 2026 | prompt eval time = 86.12 ms / 358 tokens ( 0.24 ms per token, 4156.99 tokens per second) 0.20.138.956 I slot print_timing: id 0 | task 2026 | eval time = 387.04 ms / 59 tokens ( 6.67 ms per token, 149.86 tokens per second) 0.20.138.957 I slot print_timing: id 0 | task 2026 | total time = 473.16 ms / 417 tokens 0.20.138.958 I slot print_timing: id 0 | task 2026 | graphs reused = 1932 0.20.138.959 I slot print_timing: id 0 | task 2026 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.138.988 I slot release: id 0 | task 2026 | stop processing: n_tokens = 416, truncated = 0 0.20.154.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 20048185 0.20.180.855 I slot launch_slot_: id 0 | task 2088 | processing task, is_child = 0 0.20.667.837 I slot print_timing: id 0 | task 2088 | prompt eval time = 85.51 ms / 359 tokens ( 0.24 ms per token, 4198.54 tokens per second) 0.20.667.843 I slot print_timing: id 0 | task 2088 | eval time = 401.46 ms / 56 tokens ( 7.30 ms per token, 137.00 tokens per second) 0.20.667.844 I slot print_timing: id 0 | task 2088 | total time = 486.97 ms / 415 tokens 0.20.667.845 I slot print_timing: id 0 | task 2088 | graphs reused = 1986 0.20.667.845 I slot print_timing: id 0 | task 2088 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.667.874 I slot release: id 0 | task 2088 | stop processing: n_tokens = 414, truncated = 0 0.20.672.025 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 20577071 0.20.699.768 I slot launch_slot_: id 0 | task 2147 | processing task, is_child = 0 0.21.194.879 I slot print_timing: id 0 | task 2147 | prompt eval time = 91.25 ms / 387 tokens ( 0.24 ms per token, 4240.91 tokens per second) 0.21.194.886 I slot print_timing: id 0 | task 2147 | eval time = 403.84 ms / 61 tokens ( 6.73 ms per token, 148.58 tokens per second) 0.21.194.887 I slot print_timing: id 0 | task 2147 | total time = 495.09 ms / 448 tokens 0.21.194.888 I slot print_timing: id 0 | task 2147 | graphs reused = 2045 0.21.194.889 I slot print_timing: id 0 | task 2147 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.194.922 I slot release: id 0 | task 2147 | stop processing: n_tokens = 447, truncated = 0 0.21.213.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 21104119 0.21.239.627 I slot launch_slot_: id 0 | task 2211 | processing task, is_child = 0 0.21.760.902 I slot print_timing: id 0 | task 2211 | prompt eval time = 91.92 ms / 410 tokens ( 0.22 ms per token, 4460.21 tokens per second) 0.21.760.908 I slot print_timing: id 0 | task 2211 | eval time = 429.33 ms / 61 tokens ( 7.16 ms per token, 139.75 tokens per second) 0.21.760.909 I slot print_timing: id 0 | task 2211 | total time = 521.25 ms / 471 tokens 0.21.760.910 I slot print_timing: id 0 | task 2211 | graphs reused = 2104 0.21.760.911 I slot print_timing: id 0 | task 2211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.760.942 I slot release: id 0 | task 2211 | stop processing: n_tokens = 470, truncated = 0 0.21.775.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 21670139 0.21.801.391 I slot launch_slot_: id 0 | task 2275 | processing task, is_child = 0 0.22.216.727 I slot print_timing: id 0 | task 2275 | prompt eval time = 85.30 ms / 351 tokens ( 0.24 ms per token, 4114.84 tokens per second) 0.22.216.733 I slot print_timing: id 0 | task 2275 | eval time = 330.01 ms / 50 tokens ( 6.73 ms per token, 148.48 tokens per second) 0.22.216.734 I slot print_timing: id 0 | task 2275 | total time = 415.31 ms / 401 tokens 0.22.216.734 I slot print_timing: id 0 | task 2275 | graphs reused = 2152 0.22.216.735 I slot print_timing: id 0 | task 2275 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.216.764 I slot release: id 0 | task 2275 | stop processing: n_tokens = 400, truncated = 0 0.22.220.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 22125961 0.22.245.901 I slot launch_slot_: id 0 | task 2328 | processing task, is_child = 0 0.23.820.704 I slot print_timing: id 0 | task 2328 | prompt eval time = 91.09 ms / 393 tokens ( 0.23 ms per token, 4314.51 tokens per second) 0.23.820.709 I slot print_timing: id 0 | task 2328 | eval time = 1483.69 ms / 224 tokens ( 6.65 ms per token, 150.30 tokens per second) 0.23.820.711 I slot print_timing: id 0 | task 2328 | total time = 1574.77 ms / 617 tokens 0.23.820.712 I slot print_timing: id 0 | task 2328 | graphs reused = 2373 0.23.820.713 I slot print_timing: id 0 | task 2328 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.820.742 I slot release: id 0 | task 2328 | stop processing: n_tokens = 616, truncated = 0 0.23.847.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 23729939 0.23.873.417 I slot launch_slot_: id 0 | task 2555 | processing task, is_child = 0 0.24.153.779 I slot print_timing: id 0 | task 2555 | prompt eval time = 84.54 ms / 321 tokens ( 0.26 ms per token, 3797.06 tokens per second) 0.24.153.785 I slot print_timing: id 0 | task 2555 | eval time = 195.80 ms / 30 tokens ( 6.75 ms per token, 148.11 tokens per second) 0.24.153.786 I slot print_timing: id 0 | task 2555 | total time = 280.34 ms / 351 tokens 0.24.153.787 I slot print_timing: id 0 | task 2555 | graphs reused = 2401 0.24.153.787 I slot print_timing: id 0 | task 2555 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.153.812 I slot release: id 0 | task 2555 | stop processing: n_tokens = 350, truncated = 0 0.24.177.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 24063009 0.24.202.921 I slot launch_slot_: id 0 | task 2588 | processing task, is_child = 0 0.24.589.189 I slot print_timing: id 0 | task 2588 | prompt eval time = 84.90 ms / 330 tokens ( 0.26 ms per token, 3886.88 tokens per second) 0.24.589.195 I slot print_timing: id 0 | task 2588 | eval time = 301.35 ms / 46 tokens ( 6.70 ms per token, 149.33 tokens per second) 0.24.589.196 I slot print_timing: id 0 | task 2588 | total time = 386.25 ms / 376 tokens 0.24.589.198 I slot print_timing: id 0 | task 2588 | graphs reused = 2445 0.24.589.199 I slot print_timing: id 0 | task 2588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.589.226 I slot release: id 0 | task 2588 | stop processing: n_tokens = 375, truncated = 0 0.24.611.698 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 24498424 0.24.636.414 I slot launch_slot_: id 0 | task 2637 | processing task, is_child = 0 0.24.929.698 I slot print_timing: id 0 | task 2637 | prompt eval time = 84.43 ms / 341 tokens ( 0.25 ms per token, 4038.80 tokens per second) 0.24.929.704 I slot print_timing: id 0 | task 2637 | eval time = 208.83 ms / 32 tokens ( 6.74 ms per token, 148.45 tokens per second) 0.24.929.705 I slot print_timing: id 0 | task 2637 | total time = 293.26 ms / 373 tokens 0.24.929.705 I slot print_timing: id 0 | task 2637 | graphs reused = 2475 0.24.929.706 I slot print_timing: id 0 | task 2637 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.929.732 I slot release: id 0 | task 2637 | stop processing: n_tokens = 372, truncated = 0 0.24.951.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 24838929 0.24.984.169 I slot launch_slot_: id 0 | task 2672 | processing task, is_child = 0 0.25.382.916 I slot print_timing: id 0 | task 2672 | prompt eval time = 84.32 ms / 338 tokens ( 0.25 ms per token, 4008.63 tokens per second) 0.25.382.923 I slot print_timing: id 0 | task 2672 | eval time = 314.41 ms / 48 tokens ( 6.69 ms per token, 149.49 tokens per second) 0.25.382.924 I slot print_timing: id 0 | task 2672 | total time = 398.73 ms / 386 tokens 0.25.382.925 I slot print_timing: id 0 | task 2672 | graphs reused = 2521 0.25.382.926 I slot print_timing: id 0 | task 2672 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.382.955 I slot release: id 0 | task 2672 | stop processing: n_tokens = 385, truncated = 0 0.25.409.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 25292152 0.25.434.358 I slot launch_slot_: id 0 | task 2723 | processing task, is_child = 0 0.25.892.856 I slot print_timing: id 0 | task 2723 | prompt eval time = 91.13 ms / 395 tokens ( 0.23 ms per token, 4334.37 tokens per second) 0.25.892.862 I slot print_timing: id 0 | task 2723 | eval time = 367.35 ms / 56 tokens ( 6.68 ms per token, 149.72 tokens per second) 0.25.892.863 I slot print_timing: id 0 | task 2723 | total time = 458.48 ms / 451 tokens 0.25.892.864 I slot print_timing: id 0 | task 2723 | graphs reused = 2575 0.25.892.865 I slot print_timing: id 0 | task 2723 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.892.893 I slot release: id 0 | task 2723 | stop processing: n_tokens = 450, truncated = 0 0.25.920.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 25802091 0.25.946.669 I slot launch_slot_: id 0 | task 2782 | processing task, is_child = 0 0.26.615.620 I slot print_timing: id 0 | task 2782 | prompt eval time = 122.51 ms / 528 tokens ( 0.23 ms per token, 4309.75 tokens per second) 0.26.615.625 I slot print_timing: id 0 | task 2782 | eval time = 546.42 ms / 83 tokens ( 6.66 ms per token, 150.07 tokens per second) 0.26.615.627 I slot print_timing: id 0 | task 2782 | total time = 668.93 ms / 611 tokens 0.26.615.627 I slot print_timing: id 0 | task 2782 | graphs reused = 2656 0.26.615.628 I slot print_timing: id 0 | task 2782 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.615.659 I slot release: id 0 | task 2782 | stop processing: n_tokens = 610, truncated = 0 0.26.642.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 26524857 0.26.677.178 I slot launch_slot_: id 0 | task 2869 | processing task, is_child = 0 0.27.074.709 I slot print_timing: id 0 | task 2869 | prompt eval time = 102.76 ms / 331 tokens ( 0.31 ms per token, 3221.13 tokens per second) 0.27.074.715 I slot print_timing: id 0 | task 2869 | eval time = 294.75 ms / 45 tokens ( 6.70 ms per token, 149.28 tokens per second) 0.27.074.716 I slot print_timing: id 0 | task 2869 | total time = 397.51 ms / 376 tokens 0.27.074.717 I slot print_timing: id 0 | task 2869 | graphs reused = 2699 0.27.074.718 I slot print_timing: id 0 | task 2869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.074.746 I slot release: id 0 | task 2869 | stop processing: n_tokens = 387, truncated = 0 0.27.096.284 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 26983943 0.27.126.845 I slot launch_slot_: id 0 | task 2917 | processing task, is_child = 0 0.27.581.732 I slot print_timing: id 0 | task 2917 | prompt eval time = 107.12 ms / 362 tokens ( 0.30 ms per token, 3379.32 tokens per second) 0.27.581.738 I slot print_timing: id 0 | task 2917 | eval time = 347.74 ms / 53 tokens ( 6.69 ms per token, 149.54 tokens per second) 0.27.581.739 I slot print_timing: id 0 | task 2917 | total time = 454.87 ms / 415 tokens 0.27.581.740 I slot print_timing: id 0 | task 2917 | graphs reused = 2750 0.27.581.741 I slot print_timing: id 0 | task 2917 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.581.770 I slot release: id 0 | task 2917 | stop processing: n_tokens = 426, truncated = 0 0.27.596.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 27490968 0.27.627.676 I slot launch_slot_: id 0 | task 2973 | processing task, is_child = 0 0.28.190.597 I slot print_timing: id 0 | task 2973 | prompt eval time = 109.91 ms / 419 tokens ( 0.26 ms per token, 3812.21 tokens per second) 0.28.190.603 I slot print_timing: id 0 | task 2973 | eval time = 452.99 ms / 69 tokens ( 6.66 ms per token, 150.11 tokens per second) 0.28.190.604 I slot print_timing: id 0 | task 2973 | total time = 562.90 ms / 488 tokens 0.28.190.605 I slot print_timing: id 0 | task 2973 | graphs reused = 2817 0.28.190.606 I slot print_timing: id 0 | task 2973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.190.635 I slot release: id 0 | task 2973 | stop processing: n_tokens = 499, truncated = 0 0.28.207.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 28099832 0.28.241.096 I slot launch_slot_: id 0 | task 3045 | processing task, is_child = 0 0.28.885.088 I slot print_timing: id 0 | task 3045 | prompt eval time = 115.39 ms / 423 tokens ( 0.27 ms per token, 3665.96 tokens per second) 0.28.885.094 I slot print_timing: id 0 | task 3045 | eval time = 528.59 ms / 72 tokens ( 7.44 ms per token, 134.32 tokens per second) 0.28.885.095 I slot print_timing: id 0 | task 3045 | total time = 643.98 ms / 495 tokens 0.28.885.096 I slot print_timing: id 0 | task 3045 | graphs reused = 2887 0.28.885.097 I slot print_timing: id 0 | task 3045 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.885.127 I slot release: id 0 | task 3045 | stop processing: n_tokens = 506, truncated = 0 0.28.906.694 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 28794325 0.28.938.349 I slot launch_slot_: id 0 | task 3120 | processing task, is_child = 0 0.29.323.646 I slot print_timing: id 0 | task 3120 | prompt eval time = 103.89 ms / 341 tokens ( 0.30 ms per token, 3282.44 tokens per second) 0.29.323.652 I slot print_timing: id 0 | task 3120 | eval time = 281.39 ms / 43 tokens ( 6.70 ms per token, 149.26 tokens per second) 0.29.323.653 I slot print_timing: id 0 | task 3120 | total time = 385.28 ms / 384 tokens 0.29.323.654 I slot print_timing: id 0 | task 3120 | graphs reused = 2928 0.29.323.655 I slot print_timing: id 0 | task 3120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.323.682 I slot release: id 0 | task 3120 | stop processing: n_tokens = 395, truncated = 0 0.29.347.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 29232880 0.29.381.325 I slot launch_slot_: id 0 | task 3166 | processing task, is_child = 0 0.29.793.481 I slot print_timing: id 0 | task 3166 | prompt eval time = 104.12 ms / 356 tokens ( 0.29 ms per token, 3419.07 tokens per second) 0.29.793.487 I slot print_timing: id 0 | task 3166 | eval time = 308.01 ms / 47 tokens ( 6.70 ms per token, 149.34 tokens per second) 0.29.793.488 I slot print_timing: id 0 | task 3166 | total time = 412.14 ms / 403 tokens 0.29.793.488 I slot print_timing: id 0 | task 3166 | graphs reused = 2973 0.29.793.489 I slot print_timing: id 0 | task 3166 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.793.516 I slot release: id 0 | task 3166 | stop processing: n_tokens = 414, truncated = 0 0.29.818.484 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 29702714 0.29.818.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.29.860.762 I slot launch_slot_: id 0 | task 3216 | processing task, is_child = 0 0.30.270.294 I slot print_timing: id 0 | task 3216 | prompt eval time = 107.93 ms / 362 tokens ( 0.30 ms per token, 3354.09 tokens per second) 0.30.270.300 I slot print_timing: id 0 | task 3216 | eval time = 301.58 ms / 46 tokens ( 6.70 ms per token, 149.21 tokens per second) 0.30.270.301 I slot print_timing: id 0 | task 3216 | total time = 409.51 ms / 408 tokens 0.30.270.301 I slot print_timing: id 0 | task 3216 | graphs reused = 3017 0.30.270.302 I slot print_timing: id 0 | task 3216 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.270.330 I slot release: id 0 | task 3216 | stop processing: n_tokens = 419, truncated = 0 0.30.285.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 30179528 0.30.285.768 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.30.329.069 I slot launch_slot_: id 0 | task 3265 | processing task, is_child = 0 0.30.885.859 I slot print_timing: id 0 | task 3265 | prompt eval time = 110.07 ms / 391 tokens ( 0.28 ms per token, 3552.35 tokens per second) 0.30.885.864 I slot print_timing: id 0 | task 3265 | eval time = 446.70 ms / 68 tokens ( 6.67 ms per token, 149.99 tokens per second) 0.30.885.865 I slot print_timing: id 0 | task 3265 | total time = 556.77 ms / 459 tokens 0.30.885.866 I slot print_timing: id 0 | task 3265 | graphs reused = 3083 0.30.885.867 I slot print_timing: id 0 | task 3265 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.885.896 I slot release: id 0 | task 3265 | stop processing: n_tokens = 470, truncated = 0 0.30.913.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 30795093 0.30.913.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.30.923.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.30.971.834 I slot launch_slot_: id 0 | task 3336 | processing task, is_child = 0 0.31.431.140 I slot print_timing: id 0 | task 3336 | prompt eval time = 105.31 ms / 343 tokens ( 0.31 ms per token, 3257.05 tokens per second) 0.31.431.146 I slot print_timing: id 0 | task 3336 | eval time = 353.98 ms / 54 tokens ( 6.68 ms per token, 149.73 tokens per second) 0.31.431.147 I slot print_timing: id 0 | task 3336 | total time = 459.29 ms / 397 tokens 0.31.431.148 I slot print_timing: id 0 | task 3336 | graphs reused = 3135 0.31.431.149 I slot print_timing: id 0 | task 3336 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.431.175 I slot release: id 0 | task 3336 | stop processing: n_tokens = 408, truncated = 0 0.31.458.976 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 31340372 0.31.459.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.31.502.162 I slot launch_slot_: id 0 | task 3393 | processing task, is_child = 0 0.31.913.827 I slot print_timing: id 0 | task 3393 | prompt eval time = 110.61 ms / 401 tokens ( 0.28 ms per token, 3625.48 tokens per second) 0.31.913.832 I slot print_timing: id 0 | task 3393 | eval time = 301.04 ms / 46 tokens ( 6.69 ms per token, 149.48 tokens per second) 0.31.913.833 I slot print_timing: id 0 | task 3393 | total time = 411.65 ms / 447 tokens 0.31.913.834 I slot print_timing: id 0 | task 3393 | graphs reused = 3179 0.31.913.835 I slot print_timing: id 0 | task 3393 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.913.866 I slot release: id 0 | task 3393 | stop processing: n_tokens = 458, truncated = 0 0.31.940.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 31823063 0.31.941.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.31.987.810 I slot launch_slot_: id 0 | task 3442 | processing task, is_child = 0 0.32.539.083 I slot print_timing: id 0 | task 3442 | prompt eval time = 104.89 ms / 355 tokens ( 0.30 ms per token, 3384.53 tokens per second) 0.32.539.089 I slot print_timing: id 0 | task 3442 | eval time = 446.36 ms / 68 tokens ( 6.66 ms per token, 150.10 tokens per second) 0.32.539.090 I slot print_timing: id 0 | task 3442 | total time = 551.25 ms / 423 tokens 0.32.539.091 I slot print_timing: id 0 | task 3442 | graphs reused = 3245 0.32.539.091 I slot print_timing: id 0 | task 3442 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.539.119 I slot release: id 0 | task 3442 | stop processing: n_tokens = 434, truncated = 0 0.32.565.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 32448316 0.32.565.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.32.612.106 I slot launch_slot_: id 0 | task 3513 | processing task, is_child = 0 0.33.118.891 I slot print_timing: id 0 | task 3513 | prompt eval time = 105.06 ms / 351 tokens ( 0.30 ms per token, 3340.92 tokens per second) 0.33.118.897 I slot print_timing: id 0 | task 3513 | eval time = 401.70 ms / 57 tokens ( 7.17 ms per token, 139.41 tokens per second) 0.33.118.898 I slot print_timing: id 0 | task 3513 | total time = 506.76 ms / 408 tokens 0.33.118.899 I slot print_timing: id 0 | task 3513 | graphs reused = 3300 0.33.118.900 I slot print_timing: id 0 | task 3513 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.118.931 I slot release: id 0 | task 3513 | stop processing: n_tokens = 419, truncated = 0 0.33.143.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 33028128 0.33.143.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.33.153.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.33.201.983 I slot launch_slot_: id 0 | task 3573 | processing task, is_child = 0 0.33.938.602 I slot print_timing: id 0 | task 3573 | prompt eval time = 119.35 ms / 475 tokens ( 0.25 ms per token, 3979.76 tokens per second) 0.33.938.608 I slot print_timing: id 0 | task 3573 | eval time = 617.25 ms / 93 tokens ( 6.71 ms per token, 149.05 tokens per second) 0.33.938.609 I slot print_timing: id 0 | task 3573 | total time = 736.60 ms / 568 tokens 0.33.938.610 I slot print_timing: id 0 | task 3573 | graphs reused = 3390 0.33.938.611 I slot print_timing: id 0 | task 3573 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.938.643 I slot release: id 0 | task 3573 | stop processing: n_tokens = 579, truncated = 0 0.33.959.594 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 33847841 0.33.959.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.34.003.673 I slot launch_slot_: id 0 | task 3669 | processing task, is_child = 0 0.34.729.540 I slot print_timing: id 0 | task 3669 | prompt eval time = 116.89 ms / 440 tokens ( 0.27 ms per token, 3764.29 tokens per second) 0.34.729.546 I slot print_timing: id 0 | task 3669 | eval time = 608.96 ms / 92 tokens ( 6.69 ms per token, 149.44 tokens per second) 0.34.729.547 I slot print_timing: id 0 | task 3669 | total time = 725.85 ms / 532 tokens 0.34.729.547 I slot print_timing: id 0 | task 3669 | graphs reused = 3479 0.34.729.548 I slot print_timing: id 0 | task 3669 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.729.579 I slot release: id 0 | task 3669 | stop processing: n_tokens = 543, truncated = 0 0.34.756.415 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 34638777 0.34.756.469 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.34.801.243 I slot launch_slot_: id 0 | task 3764 | processing task, is_child = 0 0.35.266.419 I slot print_timing: id 0 | task 3764 | prompt eval time = 104.45 ms / 345 tokens ( 0.30 ms per token, 3302.98 tokens per second) 0.35.266.425 I slot print_timing: id 0 | task 3764 | eval time = 360.70 ms / 55 tokens ( 6.68 ms per token, 149.71 tokens per second) 0.35.266.426 I slot print_timing: id 0 | task 3764 | total time = 465.16 ms / 400 tokens 0.35.266.427 I slot print_timing: id 0 | task 3764 | graphs reused = 3532 0.35.266.429 I slot print_timing: id 0 | task 3764 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.266.457 I slot release: id 0 | task 3764 | stop processing: n_tokens = 411, truncated = 0 0.35.290.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 35175655 0.35.290.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.35.300.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.35.351.857 I slot launch_slot_: id 0 | task 3822 | processing task, is_child = 0 0.35.825.003 I slot print_timing: id 0 | task 3822 | prompt eval time = 111.70 ms / 382 tokens ( 0.29 ms per token, 3419.91 tokens per second) 0.35.825.009 I slot print_timing: id 0 | task 3822 | eval time = 361.43 ms / 55 tokens ( 6.69 ms per token, 149.41 tokens per second) 0.35.825.010 I slot print_timing: id 0 | task 3822 | total time = 473.13 ms / 437 tokens 0.35.825.011 I slot print_timing: id 0 | task 3822 | graphs reused = 3585 0.35.825.012 I slot print_timing: id 0 | task 3822 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.825.042 I slot release: id 0 | task 3822 | stop processing: n_tokens = 448, truncated = 0 0.35.852.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 35734239 0.35.853.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.35.911.064 I slot launch_slot_: id 0 | task 3880 | processing task, is_child = 0 0.36.310.936 I slot print_timing: id 0 | task 3880 | prompt eval time = 104.57 ms / 337 tokens ( 0.31 ms per token, 3222.81 tokens per second) 0.36.310.942 I slot print_timing: id 0 | task 3880 | eval time = 295.29 ms / 45 tokens ( 6.71 ms per token, 149.01 tokens per second) 0.36.310.943 I slot print_timing: id 0 | task 3880 | total time = 399.85 ms / 382 tokens 0.36.310.944 I slot print_timing: id 0 | task 3880 | graphs reused = 3628 0.36.310.944 I slot print_timing: id 0 | task 3880 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.310.970 I slot release: id 0 | task 3880 | stop processing: n_tokens = 393, truncated = 0 0.36.335.738 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 36220167 0.36.335.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.36.384.229 I slot launch_slot_: id 0 | task 3928 | processing task, is_child = 0 0.36.982.468 I slot print_timing: id 0 | task 3928 | prompt eval time = 110.55 ms / 402 tokens ( 0.27 ms per token, 3636.43 tokens per second) 0.36.982.474 I slot print_timing: id 0 | task 3928 | eval time = 487.67 ms / 70 tokens ( 7.07 ms per token, 141.49 tokens per second) 0.36.982.475 I slot print_timing: id 0 | task 3928 | total time = 598.22 ms / 472 tokens 0.36.982.476 I slot print_timing: id 0 | task 3928 | graphs reused = 3696 0.36.982.476 I slot print_timing: id 0 | task 3928 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.982.507 I slot release: id 0 | task 3928 | stop processing: n_tokens = 483, truncated = 0 0.37.006.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 36891704 0.37.006.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.37.016.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.330 MiB) 0.37.071.248 I slot launch_slot_: id 0 | task 4001 | processing task, is_child = 0 0.37.577.954 I slot print_timing: id 0 | task 4001 | prompt eval time = 131.94 ms / 549 tokens ( 0.24 ms per token, 4160.82 tokens per second) 0.37.577.961 I slot print_timing: id 0 | task 4001 | eval time = 374.74 ms / 57 tokens ( 6.69 ms per token, 149.44 tokens per second) 0.37.577.962 I slot print_timing: id 0 | task 4001 | total time = 506.69 ms / 606 tokens 0.37.577.964 I slot print_timing: id 0 | task 4001 | graphs reused = 3751 0.37.577.964 I slot print_timing: id 0 | task 4001 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.577.997 I slot release: id 0 | task 4001 | stop processing: n_tokens = 617, truncated = 0 0.37.599.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 37487194 0.37.599.188 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.37.651.523 I slot launch_slot_: id 0 | task 4062 | processing task, is_child = 0 0.38.177.678 I slot print_timing: id 0 | task 4062 | prompt eval time = 144.70 ms / 616 tokens ( 0.23 ms per token, 4257.08 tokens per second) 0.38.177.684 I slot print_timing: id 0 | task 4062 | eval time = 381.44 ms / 58 tokens ( 6.69 ms per token, 149.44 tokens per second) 0.38.177.685 I slot print_timing: id 0 | task 4062 | total time = 526.13 ms / 674 tokens 0.38.177.685 I slot print_timing: id 0 | task 4062 | graphs reused = 3807 0.38.177.686 I slot print_timing: id 0 | task 4062 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.177.719 I slot release: id 0 | task 4062 | stop processing: n_tokens = 685, truncated = 0 0.38.206.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 38086917 0.38.206.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.917 MiB) 0.38.216.558 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.38.279.937 I slot launch_slot_: id 0 | task 4124 | processing task, is_child = 0 0.38.830.552 I slot print_timing: id 0 | task 4124 | prompt eval time = 149.75 ms / 665 tokens ( 0.23 ms per token, 4440.68 tokens per second) 0.38.830.558 I slot print_timing: id 0 | task 4124 | eval time = 400.85 ms / 61 tokens ( 6.68 ms per token, 149.68 tokens per second) 0.38.830.559 I slot print_timing: id 0 | task 4124 | total time = 550.60 ms / 726 tokens 0.38.830.560 I slot print_timing: id 0 | task 4124 | graphs reused = 3866 0.38.830.561 I slot print_timing: id 0 | task 4124 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.830.598 I slot release: id 0 | task 4124 | stop processing: n_tokens = 737, truncated = 0 0.38.849.201 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 38739795 0.38.849.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.38.859.359 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.38.917.222 I slot launch_slot_: id 0 | task 4189 | processing task, is_child = 0 0.39.429.024 I slot print_timing: id 0 | task 4189 | prompt eval time = 150.54 ms / 645 tokens ( 0.23 ms per token, 4284.69 tokens per second) 0.39.429.031 I slot print_timing: id 0 | task 4189 | eval time = 361.25 ms / 55 tokens ( 6.69 ms per token, 149.48 tokens per second) 0.39.429.032 I slot print_timing: id 0 | task 4189 | total time = 511.78 ms / 700 tokens 0.39.429.033 I slot print_timing: id 0 | task 4189 | graphs reused = 3919 0.39.429.034 I slot print_timing: id 0 | task 4189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.429.069 I slot release: id 0 | task 4189 | stop processing: n_tokens = 711, truncated = 0 0.39.443.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 39338266 0.39.444.055 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.39.497.458 I slot launch_slot_: id 0 | task 4248 | processing task, is_child = 0 0.39.965.679 I slot print_timing: id 0 | task 4248 | prompt eval time = 122.21 ms / 474 tokens ( 0.26 ms per token, 3878.70 tokens per second) 0.39.965.685 I slot print_timing: id 0 | task 4248 | eval time = 346.00 ms / 52 tokens ( 6.78 ms per token, 147.40 tokens per second) 0.39.965.686 I slot print_timing: id 0 | task 4248 | total time = 468.20 ms / 526 tokens 0.39.965.687 I slot print_timing: id 0 | task 4248 | graphs reused = 3968 0.39.965.687 I slot print_timing: id 0 | task 4248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.965.718 I slot release: id 0 | task 4248 | stop processing: n_tokens = 537, truncated = 0 0.39.989.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 39874915 0.39.989.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.39.999.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.40.048.435 I slot launch_slot_: id 0 | task 4303 | processing task, is_child = 0 0.40.464.817 I slot print_timing: id 0 | task 4303 | prompt eval time = 140.41 ms / 617 tokens ( 0.23 ms per token, 4394.43 tokens per second) 0.40.464.823 I slot print_timing: id 0 | task 4303 | eval time = 275.96 ms / 42 tokens ( 6.73 ms per token, 148.57 tokens per second) 0.40.464.824 I slot print_timing: id 0 | task 4303 | total time = 416.36 ms / 659 tokens 0.40.464.825 I slot print_timing: id 0 | task 4303 | graphs reused = 4008 0.40.464.826 I slot print_timing: id 0 | task 4303 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.464.859 I slot release: id 0 | task 4303 | stop processing: n_tokens = 670, truncated = 0 0.40.487.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 40374056 0.40.487.926 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.40.540.826 I slot launch_slot_: id 0 | task 4349 | processing task, is_child = 0 0.40.999.166 I slot print_timing: id 0 | task 4349 | prompt eval time = 142.38 ms / 601 tokens ( 0.24 ms per token, 4221.10 tokens per second) 0.40.999.172 I slot print_timing: id 0 | task 4349 | eval time = 315.94 ms / 48 tokens ( 6.72 ms per token, 148.76 tokens per second) 0.40.999.173 I slot print_timing: id 0 | task 4349 | total time = 458.32 ms / 649 tokens 0.40.999.174 I slot print_timing: id 0 | task 4349 | graphs reused = 4054 0.40.999.174 I slot print_timing: id 0 | task 4349 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.999.210 I slot release: id 0 | task 4349 | stop processing: n_tokens = 660, truncated = 0 0.41.021.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 40908408 0.41.021.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.41.031.806 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.41.093.155 I slot launch_slot_: id 0 | task 4401 | processing task, is_child = 0 0.41.534.238 I slot print_timing: id 0 | task 4401 | prompt eval time = 132.79 ms / 533 tokens ( 0.25 ms per token, 4013.89 tokens per second) 0.41.534.244 I slot print_timing: id 0 | task 4401 | eval time = 308.27 ms / 47 tokens ( 6.70 ms per token, 149.22 tokens per second) 0.41.534.245 I slot print_timing: id 0 | task 4401 | total time = 441.06 ms / 580 tokens 0.41.534.246 I slot print_timing: id 0 | task 4401 | graphs reused = 4099 0.41.534.247 I slot print_timing: id 0 | task 4401 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.534.278 I slot release: id 0 | task 4401 | stop processing: n_tokens = 591, truncated = 0 0.41.554.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 41443475 0.41.554.938 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.41.620.275 I slot launch_slot_: id 0 | task 4452 | processing task, is_child = 0 0.42.091.492 I slot print_timing: id 0 | task 4452 | prompt eval time = 124.59 ms / 480 tokens ( 0.26 ms per token, 3852.57 tokens per second) 0.42.091.498 I slot print_timing: id 0 | task 4452 | eval time = 346.61 ms / 52 tokens ( 6.80 ms per token, 147.14 tokens per second) 0.42.091.499 I slot print_timing: id 0 | task 4452 | total time = 471.20 ms / 532 tokens 0.42.091.500 I slot print_timing: id 0 | task 4452 | graphs reused = 4148 0.42.091.501 I slot print_timing: id 0 | task 4452 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.091.533 I slot release: id 0 | task 4452 | stop processing: n_tokens = 560, truncated = 0 0.42.096.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 42000731 0.42.096.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.42.107.622 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.42.156.271 I slot launch_slot_: id 0 | task 4507 | processing task, is_child = 0 0.42.565.381 I slot print_timing: id 0 | task 4507 | prompt eval time = 133.91 ms / 567 tokens ( 0.24 ms per token, 4234.22 tokens per second) 0.42.565.387 I slot print_timing: id 0 | task 4507 | eval time = 275.18 ms / 42 tokens ( 6.71 ms per token, 148.99 tokens per second) 0.42.565.388 I slot print_timing: id 0 | task 4507 | total time = 409.09 ms / 609 tokens 0.42.565.388 I slot print_timing: id 0 | task 4507 | graphs reused = 4188 0.42.565.389 I slot print_timing: id 0 | task 4507 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.565.421 I slot release: id 0 | task 4507 | stop processing: n_tokens = 637, truncated = 0 0.42.584.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 42474619 0.42.584.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.42.594.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.42.674.505 I slot launch_slot_: id 0 | task 4553 | processing task, is_child = 0 0.43.217.989 I slot print_timing: id 0 | task 4553 | prompt eval time = 128.57 ms / 506 tokens ( 0.25 ms per token, 3935.66 tokens per second) 0.43.217.996 I slot print_timing: id 0 | task 4553 | eval time = 414.90 ms / 63 tokens ( 6.69 ms per token, 149.44 tokens per second) 0.43.217.998 I slot print_timing: id 0 | task 4553 | total time = 543.46 ms / 569 tokens 0.43.217.998 I slot print_timing: id 0 | task 4553 | graphs reused = 4249 0.43.217.999 I slot print_timing: id 0 | task 4553 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.218.031 I slot release: id 0 | task 4553 | stop processing: n_tokens = 597, truncated = 0 0.43.240.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 43127228 0.43.240.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.43.250.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.43.310.858 I slot launch_slot_: id 0 | task 4619 | processing task, is_child = 0 0.43.691.079 I slot print_timing: id 0 | task 4619 | prompt eval time = 118.46 ms / 436 tokens ( 0.27 ms per token, 3680.66 tokens per second) 0.43.691.085 I slot print_timing: id 0 | task 4619 | eval time = 261.75 ms / 40 tokens ( 6.71 ms per token, 149.00 tokens per second) 0.43.691.086 I slot print_timing: id 0 | task 4619 | total time = 380.20 ms / 476 tokens 0.43.691.087 I slot print_timing: id 0 | task 4619 | graphs reused = 4287 0.43.691.088 I slot print_timing: id 0 | task 4619 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.691.118 I slot release: id 0 | task 4619 | stop processing: n_tokens = 504, truncated = 0 0.43.714.175 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 43600315 0.43.714.225 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.43.778.053 I slot launch_slot_: id 0 | task 4662 | processing task, is_child = 0 0.44.318.605 I slot print_timing: id 0 | task 4662 | prompt eval time = 132.46 ms / 519 tokens ( 0.26 ms per token, 3918.22 tokens per second) 0.44.318.611 I slot print_timing: id 0 | task 4662 | eval time = 408.07 ms / 62 tokens ( 6.69 ms per token, 149.48 tokens per second) 0.44.318.612 I slot print_timing: id 0 | task 4662 | total time = 540.53 ms / 581 tokens 0.44.318.613 I slot print_timing: id 0 | task 4662 | graphs reused = 4347 0.44.318.614 I slot print_timing: id 0 | task 4662 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.318.646 I slot release: id 0 | task 4662 | stop processing: n_tokens = 609, truncated = 0 0.44.338.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 44227843 0.44.338.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.44.349.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.479 MiB) 0.44.429.387 I slot launch_slot_: id 0 | task 4728 | processing task, is_child = 0 0.44.860.470 I slot print_timing: id 0 | task 4728 | prompt eval time = 125.01 ms / 465 tokens ( 0.27 ms per token, 3719.61 tokens per second) 0.44.860.476 I slot print_timing: id 0 | task 4728 | eval time = 306.05 ms / 46 tokens ( 6.80 ms per token, 147.03 tokens per second) 0.44.860.477 I slot print_timing: id 0 | task 4728 | total time = 431.06 ms / 511 tokens 0.44.860.477 I slot print_timing: id 0 | task 4728 | graphs reused = 4390 0.44.860.478 I slot print_timing: id 0 | task 4728 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.860.509 I slot release: id 0 | task 4728 | stop processing: n_tokens = 542, truncated = 0 0.44.885.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 44769706 0.44.885.709 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.44.895.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.44.983.291 I slot launch_slot_: id 0 | task 4777 | processing task, is_child = 0 0.45.375.302 I slot print_timing: id 0 | task 4777 | prompt eval time = 123.23 ms / 431 tokens ( 0.29 ms per token, 3497.41 tokens per second) 0.45.375.308 I slot print_timing: id 0 | task 4777 | eval time = 268.76 ms / 41 tokens ( 6.72 ms per token, 148.83 tokens per second) 0.45.375.309 I slot print_timing: id 0 | task 4777 | total time = 391.99 ms / 472 tokens 0.45.375.310 I slot print_timing: id 0 | task 4777 | graphs reused = 4429 0.45.375.310 I slot print_timing: id 0 | task 4777 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.375.343 I slot release: id 0 | task 4777 | stop processing: n_tokens = 503, truncated = 0 0.45.400.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 45284540 0.45.400.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.45.411.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.45.490.069 I slot launch_slot_: id 0 | task 4821 | processing task, is_child = 0 0.45.908.656 I slot print_timing: id 0 | task 4821 | prompt eval time = 125.00 ms / 457 tokens ( 0.27 ms per token, 3655.88 tokens per second) 0.45.908.662 I slot print_timing: id 0 | task 4821 | eval time = 293.56 ms / 44 tokens ( 6.83 ms per token, 146.48 tokens per second) 0.45.908.663 I slot print_timing: id 0 | task 4821 | total time = 418.57 ms / 501 tokens 0.45.908.663 I slot print_timing: id 0 | task 4821 | graphs reused = 4470 0.45.908.664 I slot print_timing: id 0 | task 4821 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.908.696 I slot release: id 0 | task 4821 | stop processing: n_tokens = 532, truncated = 0 0.45.936.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 45817894 0.45.937.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.46.024.251 I slot launch_slot_: id 0 | task 4868 | processing task, is_child = 0 0.46.421.763 I slot print_timing: id 0 | task 4868 | prompt eval time = 123.21 ms / 439 tokens ( 0.28 ms per token, 3562.96 tokens per second) 0.46.421.769 I slot print_timing: id 0 | task 4868 | eval time = 274.28 ms / 42 tokens ( 6.69 ms per token, 149.48 tokens per second) 0.46.421.770 I slot print_timing: id 0 | task 4868 | total time = 397.49 ms / 481 tokens 0.46.421.771 I slot print_timing: id 0 | task 4868 | graphs reused = 4510 0.46.421.772 I slot print_timing: id 0 | task 4868 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.421.801 I slot release: id 0 | task 4868 | stop processing: n_tokens = 512, truncated = 0 0.46.450.102 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 46330998 0.46.450.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.46.463.328 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.46.543.394 I slot launch_slot_: id 0 | task 4913 | processing task, is_child = 0 0.47.049.586 I slot print_timing: id 0 | task 4913 | prompt eval time = 137.95 ms / 606 tokens ( 0.23 ms per token, 4392.96 tokens per second) 0.47.049.591 I slot print_timing: id 0 | task 4913 | eval time = 368.22 ms / 56 tokens ( 6.69 ms per token, 149.37 tokens per second) 0.47.049.593 I slot print_timing: id 0 | task 4913 | total time = 506.17 ms / 662 tokens 0.47.049.594 I slot print_timing: id 0 | task 4913 | graphs reused = 4564 0.47.049.595 I slot print_timing: id 0 | task 4913 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.049.632 I slot release: id 0 | task 4913 | stop processing: n_tokens = 693, truncated = 0 0.47.076.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 46958829 0.47.076.172 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.47.089.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.47.181.589 I slot launch_slot_: id 0 | task 4973 | processing task, is_child = 0 0.47.578.762 I slot print_timing: id 0 | task 4973 | prompt eval time = 124.29 ms / 477 tokens ( 0.26 ms per token, 3837.89 tokens per second) 0.47.578.768 I slot print_timing: id 0 | task 4973 | eval time = 272.87 ms / 41 tokens ( 6.82 ms per token, 146.59 tokens per second) 0.47.578.768 I slot print_timing: id 0 | task 4973 | total time = 397.15 ms / 518 tokens 0.47.578.769 I slot print_timing: id 0 | task 4973 | graphs reused = 4602 0.47.578.770 I slot print_timing: id 0 | task 4973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.578.802 I slot release: id 0 | task 4973 | stop processing: n_tokens = 549, truncated = 0 0.47.594.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 47487999 0.47.594.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.47.660.145 I slot launch_slot_: id 0 | task 5017 | processing task, is_child = 0 0.48.223.677 I slot print_timing: id 0 | task 5017 | prompt eval time = 167.23 ms / 845 tokens ( 0.20 ms per token, 5053.04 tokens per second) 0.48.223.683 I slot print_timing: id 0 | task 5017 | eval time = 396.29 ms / 60 tokens ( 6.72 ms per token, 148.88 tokens per second) 0.48.223.684 I slot print_timing: id 0 | task 5017 | total time = 563.51 ms / 905 tokens 0.48.223.685 I slot print_timing: id 0 | task 5017 | graphs reused = 4660 0.48.223.685 I slot print_timing: id 0 | task 5017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.223.730 I slot release: id 0 | task 5017 | stop processing: n_tokens = 936, truncated = 0 0.48.247.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 48132927 0.48.247.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.48.260.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.48.351.638 I slot launch_slot_: id 0 | task 5081 | processing task, is_child = 0 0.48.765.356 I slot print_timing: id 0 | task 5081 | prompt eval time = 127.17 ms / 459 tokens ( 0.28 ms per token, 3609.34 tokens per second) 0.48.765.361 I slot print_timing: id 0 | task 5081 | eval time = 286.53 ms / 43 tokens ( 6.82 ms per token, 146.58 tokens per second) 0.48.765.362 I slot print_timing: id 0 | task 5081 | total time = 413.70 ms / 502 tokens 0.48.765.363 I slot print_timing: id 0 | task 5081 | graphs reused = 4700 0.48.765.364 I slot print_timing: id 0 | task 5081 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.765.394 I slot release: id 0 | task 5081 | stop processing: n_tokens = 533, truncated = 0 0.48.781.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 48674591 0.48.781.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.48.866.915 I slot launch_slot_: id 0 | task 5127 | processing task, is_child = 0 0.49.340.160 I slot print_timing: id 0 | task 5127 | prompt eval time = 153.21 ms / 670 tokens ( 0.23 ms per token, 4373.14 tokens per second) 0.49.340.166 I slot print_timing: id 0 | task 5127 | eval time = 320.02 ms / 47 tokens ( 6.96 ms per token, 143.74 tokens per second) 0.49.340.167 I slot print_timing: id 0 | task 5127 | total time = 473.23 ms / 717 tokens 0.49.340.168 I slot print_timing: id 0 | task 5127 | graphs reused = 4745 0.49.340.169 I slot print_timing: id 0 | task 5127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.340.208 I slot release: id 0 | task 5127 | stop processing: n_tokens = 748, truncated = 0 0.49.370.344 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 49249406 0.49.370.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 0.49.383.584 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.49.483.134 I slot launch_slot_: id 0 | task 5178 | processing task, is_child = 0 0.50.099.446 I slot print_timing: id 0 | task 5178 | prompt eval time = 163.41 ms / 775 tokens ( 0.21 ms per token, 4742.58 tokens per second) 0.50.099.453 I slot print_timing: id 0 | task 5178 | eval time = 452.88 ms / 63 tokens ( 7.30 ms per token, 136.90 tokens per second) 0.50.099.454 I slot print_timing: id 0 | task 5178 | total time = 616.29 ms / 838 tokens 0.50.099.455 I slot print_timing: id 0 | task 5178 | graphs reused = 4806 0.50.099.457 I slot print_timing: id 0 | task 5178 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.099.499 I slot release: id 0 | task 5178 | stop processing: n_tokens = 869, truncated = 0 0.50.119.598 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 50008696 0.50.119.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.50.135.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 0.50.210.581 I slot launch_slot_: id 0 | task 5245 | processing task, is_child = 0 0.50.816.874 I slot print_timing: id 0 | task 5245 | prompt eval time = 138.16 ms / 573 tokens ( 0.24 ms per token, 4147.25 tokens per second) 0.50.816.880 I slot print_timing: id 0 | task 5245 | eval time = 468.11 ms / 71 tokens ( 6.69 ms per token, 149.54 tokens per second) 0.50.816.881 I slot print_timing: id 0 | task 5245 | total time = 606.27 ms / 644 tokens 0.50.816.882 I slot print_timing: id 0 | task 5245 | graphs reused = 4875 0.50.816.883 I slot print_timing: id 0 | task 5245 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.816.918 I slot release: id 0 | task 5245 | stop processing: n_tokens = 675, truncated = 0 0.50.838.922 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 50726115 0.50.838.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 0.50.852.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 0.50.951.504 I slot launch_slot_: id 0 | task 5320 | processing task, is_child = 0 0.51.487.413 I slot print_timing: id 0 | task 5320 | prompt eval time = 129.14 ms / 461 tokens ( 0.28 ms per token, 3569.69 tokens per second) 0.51.487.419 I slot print_timing: id 0 | task 5320 | eval time = 406.75 ms / 61 tokens ( 6.78 ms per token, 147.51 tokens per second) 0.51.487.420 I slot print_timing: id 0 | task 5320 | total time = 535.89 ms / 522 tokens 0.51.487.421 I slot print_timing: id 0 | task 5320 | graphs reused = 4933 0.51.487.422 I slot print_timing: id 0 | task 5320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.487.452 I slot release: id 0 | task 5320 | stop processing: n_tokens = 553, truncated = 0 0.51.511.625 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 553, t_last = 51396649 0.51.511.676 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 0.51.584.939 I slot launch_slot_: id 0 | task 5384 | processing task, is_child = 0 0.52.397.695 I slot print_timing: id 0 | task 5384 | prompt eval time = 138.56 ms / 609 tokens ( 0.23 ms per token, 4395.37 tokens per second) 0.52.397.701 I slot print_timing: id 0 | task 5384 | eval time = 674.18 ms / 98 tokens ( 6.95 ms per token, 143.88 tokens per second) 0.52.397.702 I slot print_timing: id 0 | task 5384 | total time = 812.74 ms / 707 tokens 0.52.397.703 I slot print_timing: id 0 | task 5384 | graphs reused = 5029 0.52.397.704 I slot print_timing: id 0 | task 5384 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.397.742 I slot release: id 0 | task 5384 | stop processing: n_tokens = 738, truncated = 0 0.52.414.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 52306939 0.52.414.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 0.52.427.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 0.52.517.070 I slot launch_slot_: id 0 | task 5486 | processing task, is_child = 0 0.53.087.044 I slot print_timing: id 0 | task 5486 | prompt eval time = 166.41 ms / 791 tokens ( 0.21 ms per token, 4753.38 tokens per second) 0.53.087.050 I slot print_timing: id 0 | task 5486 | eval time = 403.55 ms / 61 tokens ( 6.73 ms per token, 148.68 tokens per second) 0.53.087.051 I slot print_timing: id 0 | task 5486 | total time = 569.95 ms / 852 tokens 0.53.087.052 I slot print_timing: id 0 | task 5486 | graphs reused = 5088 0.53.087.052 I slot print_timing: id 0 | task 5486 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.087.093 I slot release: id 0 | task 5486 | stop processing: n_tokens = 883, truncated = 0 0.53.103.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 52996291 0.53.103.361 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 0.53.220.177 I slot launch_slot_: id 0 | task 5551 | processing task, is_child = 0 0.53.722.867 I slot print_timing: id 0 | task 5551 | prompt eval time = 133.56 ms / 533 tokens ( 0.25 ms per token, 3990.60 tokens per second) 0.53.722.873 I slot print_timing: id 0 | task 5551 | eval time = 369.10 ms / 56 tokens ( 6.71 ms per token, 149.01 tokens per second) 0.53.722.874 I slot print_timing: id 0 | task 5551 | total time = 502.67 ms / 589 tokens 0.53.722.875 I slot print_timing: id 0 | task 5551 | graphs reused = 5142 0.53.722.876 I slot print_timing: id 0 | task 5551 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.722.911 I slot release: id 0 | task 5551 | stop processing: n_tokens = 677, truncated = 0 0.53.740.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 53632108 0.53.740.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 0.53.826.008 I slot launch_slot_: id 0 | task 5611 | processing task, is_child = 0 0.54.295.076 I slot print_timing: id 0 | task 5611 | prompt eval time = 138.90 ms / 566 tokens ( 0.25 ms per token, 4075.02 tokens per second) 0.54.295.082 I slot print_timing: id 0 | task 5611 | eval time = 330.15 ms / 46 tokens ( 7.34 ms per token, 136.30 tokens per second) 0.54.295.083 I slot print_timing: id 0 | task 5611 | total time = 469.05 ms / 612 tokens 0.54.295.083 I slot print_timing: id 0 | task 5611 | graphs reused = 5186 0.54.295.084 I slot print_timing: id 0 | task 5611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.295.118 I slot release: id 0 | task 5611 | stop processing: n_tokens = 643, truncated = 0 0.54.318.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 54204315 0.54.318.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 0.54.399.676 I slot launch_slot_: id 0 | task 5661 | processing task, is_child = 0 0.54.809.599 I slot print_timing: id 0 | task 5661 | prompt eval time = 122.67 ms / 443 tokens ( 0.28 ms per token, 3611.23 tokens per second) 0.54.809.605 I slot print_timing: id 0 | task 5661 | eval time = 287.23 ms / 43 tokens ( 6.84 ms per token, 146.22 tokens per second) 0.54.809.606 I slot print_timing: id 0 | task 5661 | total time = 409.90 ms / 486 tokens 0.54.809.606 I slot print_timing: id 0 | task 5661 | graphs reused = 5226 0.54.809.607 I slot print_timing: id 0 | task 5661 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.809.636 I slot release: id 0 | task 5661 | stop processing: n_tokens = 517, truncated = 0 0.54.834.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 54718833 0.54.834.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 0.54.902.073 I slot launch_slot_: id 0 | task 5707 | processing task, is_child = 0 0.55.449.667 I slot print_timing: id 0 | task 5707 | prompt eval time = 119.32 ms / 487 tokens ( 0.25 ms per token, 4081.60 tokens per second) 0.55.449.673 I slot print_timing: id 0 | task 5707 | eval time = 428.26 ms / 65 tokens ( 6.69 ms per token, 149.44 tokens per second) 0.55.449.674 I slot print_timing: id 0 | task 5707 | total time = 547.57 ms / 552 tokens 0.55.449.675 I slot print_timing: id 0 | task 5707 | graphs reused = 5289 0.55.449.675 I slot print_timing: id 0 | task 5707 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.449.706 I slot release: id 0 | task 5707 | stop processing: n_tokens = 583, truncated = 0 0.55.476.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 55358904 0.55.476.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 0.55.544.735 I slot launch_slot_: id 0 | task 5775 | processing task, is_child = 0 0.55.977.888 I slot print_timing: id 0 | task 5775 | prompt eval time = 124.69 ms / 507 tokens ( 0.25 ms per token, 4066.02 tokens per second) 0.55.977.894 I slot print_timing: id 0 | task 5775 | eval time = 308.44 ms / 47 tokens ( 6.71 ms per token, 149.14 tokens per second) 0.55.977.895 I slot print_timing: id 0 | task 5775 | total time = 433.13 ms / 554 tokens 0.55.977.896 I slot print_timing: id 0 | task 5775 | graphs reused = 5334 0.55.977.897 I slot print_timing: id 0 | task 5775 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.977.932 I slot release: id 0 | task 5775 | stop processing: n_tokens = 585, truncated = 0 0.56.007.115 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 55887129 0.56.007.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 0.56.023.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 0.56.105.513 I slot launch_slot_: id 0 | task 5825 | processing task, is_child = 0 0.56.680.839 I slot print_timing: id 0 | task 5825 | prompt eval time = 141.47 ms / 633 tokens ( 0.22 ms per token, 4474.38 tokens per second) 0.56.680.845 I slot print_timing: id 0 | task 5825 | eval time = 433.83 ms / 66 tokens ( 6.67 ms per token, 149.83 tokens per second) 0.56.680.846 I slot print_timing: id 0 | task 5825 | total time = 575.31 ms / 699 tokens 0.56.680.847 I slot print_timing: id 0 | task 5825 | graphs reused = 5398 0.56.680.848 I slot print_timing: id 0 | task 5825 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.680.886 I slot release: id 0 | task 5825 | stop processing: n_tokens = 730, truncated = 0 0.56.707.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 56590083 0.56.707.573 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 0.56.785.530 I slot launch_slot_: id 0 | task 5895 | processing task, is_child = 0 0.57.311.753 I slot print_timing: id 0 | task 5895 | prompt eval time = 137.38 ms / 571 tokens ( 0.24 ms per token, 4156.26 tokens per second) 0.57.311.760 I slot print_timing: id 0 | task 5895 | eval time = 388.82 ms / 59 tokens ( 6.70 ms per token, 149.17 tokens per second) 0.57.311.761 I slot print_timing: id 0 | task 5895 | total time = 526.20 ms / 630 tokens 0.57.311.762 I slot print_timing: id 0 | task 5895 | graphs reused = 5455 0.57.311.763 I slot print_timing: id 0 | task 5895 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.311.797 I slot release: id 0 | task 5895 | stop processing: n_tokens = 661, truncated = 0 0.57.317.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 57220995 0.57.317.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 0.57.391.581 I slot launch_slot_: id 0 | task 5958 | processing task, is_child = 0 0.57.843.988 I slot print_timing: id 0 | task 5958 | prompt eval time = 162.43 ms / 798 tokens ( 0.20 ms per token, 4912.95 tokens per second) 0.57.843.994 I slot print_timing: id 0 | task 5958 | eval time = 289.96 ms / 44 tokens ( 6.74 ms per token, 148.30 tokens per second) 0.57.843.995 I slot print_timing: id 0 | task 5958 | total time = 452.39 ms / 842 tokens 0.57.843.996 I slot print_timing: id 0 | task 5958 | graphs reused = 5497 0.57.843.996 I slot print_timing: id 0 | task 5958 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.844.040 I slot release: id 0 | task 5958 | stop processing: n_tokens = 873, truncated = 0 0.57.861.478 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 57753237 0.57.861.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 0.57.881.016 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 0.57.980.054 I slot launch_slot_: id 0 | task 6006 | processing task, is_child = 0 0.58.400.597 I slot print_timing: id 0 | task 6006 | prompt eval time = 137.59 ms / 572 tokens ( 0.24 ms per token, 4157.40 tokens per second) 0.58.400.603 I slot print_timing: id 0 | task 6006 | eval time = 282.94 ms / 43 tokens ( 6.74 ms per token, 148.44 tokens per second) 0.58.400.604 I slot print_timing: id 0 | task 6006 | total time = 420.52 ms / 615 tokens 0.58.400.605 I slot print_timing: id 0 | task 6006 | graphs reused = 5538 0.58.400.606 I slot print_timing: id 0 | task 6006 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.400.640 I slot release: id 0 | task 6006 | stop processing: n_tokens = 646, truncated = 0 0.58.418.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 58309838 0.58.418.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 0.58.498.009 I slot launch_slot_: id 0 | task 6053 | processing task, is_child = 0 0.59.062.305 I slot print_timing: id 0 | task 6053 | prompt eval time = 142.96 ms / 613 tokens ( 0.23 ms per token, 4287.82 tokens per second) 0.59.062.311 I slot print_timing: id 0 | task 6053 | eval time = 421.31 ms / 64 tokens ( 6.69 ms per token, 149.53 tokens per second) 0.59.062.312 I slot print_timing: id 0 | task 6053 | total time = 564.28 ms / 677 tokens 0.59.062.313 I slot print_timing: id 0 | task 6053 | graphs reused = 5600 0.59.062.314 I slot print_timing: id 0 | task 6053 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.062.353 I slot release: id 0 | task 6053 | stop processing: n_tokens = 708, truncated = 0 0.59.078.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 58971550 0.59.078.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 0.59.162.508 I slot launch_slot_: id 0 | task 6121 | processing task, is_child = 0 0.59.721.777 I slot print_timing: id 0 | task 6121 | prompt eval time = 137.54 ms / 580 tokens ( 0.24 ms per token, 4216.86 tokens per second) 0.59.721.784 I slot print_timing: id 0 | task 6121 | eval time = 421.70 ms / 64 tokens ( 6.69 ms per token, 149.39 tokens per second) 0.59.721.785 I slot print_timing: id 0 | task 6121 | total time = 559.25 ms / 644 tokens 0.59.721.786 I slot print_timing: id 0 | task 6121 | graphs reused = 5662 0.59.721.787 I slot print_timing: id 0 | task 6121 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.721.825 I slot release: id 0 | task 6121 | stop processing: n_tokens = 675, truncated = 0 0.59.744.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 59631023 0.59.744.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 0.59.838.065 I slot launch_slot_: id 0 | task 6189 | processing task, is_child = 0 1.00.326.549 I slot print_timing: id 0 | task 6189 | prompt eval time = 154.25 ms / 716 tokens ( 0.22 ms per token, 4641.85 tokens per second) 1.00.326.555 I slot print_timing: id 0 | task 6189 | eval time = 334.21 ms / 50 tokens ( 6.82 ms per token, 146.61 tokens per second) 1.00.326.556 I slot print_timing: id 0 | task 6189 | total time = 488.46 ms / 766 tokens 1.00.326.557 I slot print_timing: id 0 | task 6189 | graphs reused = 5709 1.00.326.557 I slot print_timing: id 0 | task 6189 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.326.599 I slot release: id 0 | task 6189 | stop processing: n_tokens = 797, truncated = 0 1.00.356.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 60235797 1.00.356.303 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.00.375.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.00.469.429 I slot launch_slot_: id 0 | task 6243 | processing task, is_child = 0 1.01.308.669 I slot print_timing: id 0 | task 6243 | prompt eval time = 164.95 ms / 799 tokens ( 0.21 ms per token, 4843.80 tokens per second) 1.01.308.674 I slot print_timing: id 0 | task 6243 | eval time = 674.27 ms / 102 tokens ( 6.68 ms per token, 149.79 tokens per second) 1.01.308.675 I slot print_timing: id 0 | task 6243 | total time = 839.22 ms / 901 tokens 1.01.308.676 I slot print_timing: id 0 | task 6243 | graphs reused = 5809 1.01.308.677 I slot print_timing: id 0 | task 6243 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.308.721 I slot release: id 0 | task 6243 | stop processing: n_tokens = 932, truncated = 0 1.01.324.922 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 61217918 1.01.324.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.01.401.770 I slot launch_slot_: id 0 | task 6349 | processing task, is_child = 0 1.02.250.321 I slot print_timing: id 0 | task 6349 | prompt eval time = 111.67 ms / 361 tokens ( 0.31 ms per token, 3232.62 tokens per second) 1.02.250.329 I slot print_timing: id 0 | task 6349 | eval time = 736.86 ms / 112 tokens ( 6.64 ms per token, 150.64 tokens per second) 1.02.250.330 I slot print_timing: id 0 | task 6349 | total time = 848.53 ms / 473 tokens 1.02.250.331 I slot print_timing: id 0 | task 6349 | graphs reused = 5919 1.02.250.332 I slot print_timing: id 0 | task 6349 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.250.365 I slot release: id 0 | task 6349 | stop processing: n_tokens = 504, truncated = 0 1.02.277.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 62159562 1.02.277.295 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.02.346.104 I slot launch_slot_: id 0 | task 6464 | processing task, is_child = 0 1.03.171.431 I slot print_timing: id 0 | task 6464 | prompt eval time = 109.75 ms / 381 tokens ( 0.29 ms per token, 3471.37 tokens per second) 1.03.171.437 I slot print_timing: id 0 | task 6464 | eval time = 715.55 ms / 108 tokens ( 6.69 ms per token, 149.53 tokens per second) 1.03.171.438 I slot print_timing: id 0 | task 6464 | total time = 825.31 ms / 489 tokens 1.03.171.439 I slot print_timing: id 0 | task 6464 | graphs reused = 6024 1.03.171.440 I slot print_timing: id 0 | task 6464 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.171.471 I slot release: id 0 | task 6464 | stop processing: n_tokens = 520, truncated = 0 1.03.185.221 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 63080668 1.03.185.269 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.03.248.579 I slot launch_slot_: id 0 | task 6575 | processing task, is_child = 0 1.04.178.660 I slot print_timing: id 0 | task 6575 | prompt eval time = 107.25 ms / 365 tokens ( 0.29 ms per token, 3403.39 tokens per second) 1.04.178.666 I slot print_timing: id 0 | task 6575 | eval time = 822.82 ms / 124 tokens ( 6.69 ms per token, 149.49 tokens per second) 1.04.178.667 I slot print_timing: id 0 | task 6575 | total time = 930.06 ms / 489 tokens 1.04.178.668 I slot print_timing: id 0 | task 6575 | graphs reused = 6145 1.04.178.669 I slot print_timing: id 0 | task 6575 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.178.696 I slot release: id 0 | task 6575 | stop processing: n_tokens = 520, truncated = 0 1.04.199.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 64087894 1.04.199.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.04.269.175 I slot launch_slot_: id 0 | task 6702 | processing task, is_child = 0 1.05.106.081 I slot print_timing: id 0 | task 6702 | prompt eval time = 107.44 ms / 333 tokens ( 0.32 ms per token, 3099.38 tokens per second) 1.05.106.086 I slot print_timing: id 0 | task 6702 | eval time = 729.45 ms / 107 tokens ( 6.88 ms per token, 145.32 tokens per second) 1.05.106.087 I slot print_timing: id 0 | task 6702 | total time = 836.89 ms / 440 tokens 1.05.106.088 I slot print_timing: id 0 | task 6702 | graphs reused = 6250 1.05.106.089 I slot print_timing: id 0 | task 6702 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.106.117 I slot release: id 0 | task 6702 | stop processing: n_tokens = 471, truncated = 0 1.05.129.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 65015314 1.05.184.631 I slot launch_slot_: id 0 | task 6812 | processing task, is_child = 0 1.06.214.001 I slot print_timing: id 0 | task 6812 | prompt eval time = 110.84 ms / 403 tokens ( 0.28 ms per token, 3635.90 tokens per second) 1.06.214.007 I slot print_timing: id 0 | task 6812 | eval time = 918.51 ms / 138 tokens ( 6.70 ms per token, 149.15 tokens per second) 1.06.214.008 I slot print_timing: id 0 | task 6812 | total time = 1029.35 ms / 541 tokens 1.06.214.009 I slot print_timing: id 0 | task 6812 | graphs reused = 6385 1.06.214.010 I slot print_timing: id 0 | task 6812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.214.040 I slot release: id 0 | task 6812 | stop processing: n_tokens = 572, truncated = 0 1.06.241.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 66123237 1.06.241.737 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.06.330.254 I slot launch_slot_: id 0 | task 6953 | processing task, is_child = 0 1.07.669.891 I slot print_timing: id 0 | task 6953 | prompt eval time = 112.73 ms / 411 tokens ( 0.27 ms per token, 3645.75 tokens per second) 1.07.669.897 I slot print_timing: id 0 | task 6953 | eval time = 1226.88 ms / 185 tokens ( 6.67 ms per token, 149.97 tokens per second) 1.07.669.898 I slot print_timing: id 0 | task 6953 | total time = 1339.62 ms / 596 tokens 1.07.669.899 I slot print_timing: id 0 | task 6953 | graphs reused = 6567 1.07.669.899 I slot print_timing: id 0 | task 6953 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.669.929 I slot release: id 0 | task 6953 | stop processing: n_tokens = 627, truncated = 0 1.07.692.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 67579126 1.07.692.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.07.780.052 I slot launch_slot_: id 0 | task 7141 | processing task, is_child = 0 1.09.391.517 I slot print_timing: id 0 | task 7141 | prompt eval time = 125.00 ms / 490 tokens ( 0.26 ms per token, 3920.13 tokens per second) 1.09.391.523 I slot print_timing: id 0 | task 7141 | eval time = 1486.45 ms / 225 tokens ( 6.64 ms per token, 150.69 tokens per second) 1.09.391.524 I slot print_timing: id 0 | task 7141 | total time = 1611.45 ms / 715 tokens 1.09.391.525 I slot print_timing: id 0 | task 7141 | graphs reused = 6790 1.09.391.525 I slot print_timing: id 0 | task 7141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.391.557 I slot release: id 0 | task 7141 | stop processing: n_tokens = 746, truncated = 0 1.09.404.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 69300755 1.09.404.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.09.494.019 I slot launch_slot_: id 0 | task 7369 | processing task, is_child = 0 1.11.862.849 I slot print_timing: id 0 | task 7369 | prompt eval time = 106.85 ms / 344 tokens ( 0.31 ms per token, 3219.50 tokens per second) 1.11.862.854 I slot print_timing: id 0 | task 7369 | eval time = 2261.96 ms / 342 tokens ( 6.63 ms per token, 150.75 tokens per second) 1.11.862.855 I slot print_timing: id 0 | task 7369 | total time = 2368.81 ms / 686 tokens 1.11.862.856 I slot print_timing: id 0 | task 7369 | graphs reused = 7129 1.11.862.857 I slot print_timing: id 0 | task 7369 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.862.886 I slot release: id 0 | task 7369 | stop processing: n_tokens = 717, truncated = 0 1.11.888.827 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 717, t_last = 71772083 1.11.888.888 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.798 MiB) 1.11.965.622 I slot launch_slot_: id 0 | task 7714 | processing task, is_child = 0 1.13.202.251 I slot print_timing: id 0 | task 7714 | prompt eval time = 105.70 ms / 347 tokens ( 0.30 ms per token, 3282.97 tokens per second) 1.13.202.257 I slot print_timing: id 0 | task 7714 | eval time = 1130.91 ms / 171 tokens ( 6.65 ms per token, 150.32 tokens per second) 1.13.202.258 I slot print_timing: id 0 | task 7714 | total time = 1236.61 ms / 518 tokens 1.13.202.258 I slot print_timing: id 0 | task 7714 | graphs reused = 7297 1.13.202.259 I slot print_timing: id 0 | task 7714 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.202.287 I slot release: id 0 | task 7714 | stop processing: n_tokens = 549, truncated = 0 1.13.229.877 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 73111485 1.13.229.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.834 MiB) 1.13.309.725 I slot launch_slot_: id 0 | task 7888 | processing task, is_child = 0 1.14.258.809 I slot print_timing: id 0 | task 7888 | prompt eval time = 113.02 ms / 401 tokens ( 0.28 ms per token, 3548.14 tokens per second) 1.14.258.815 I slot print_timing: id 0 | task 7888 | eval time = 836.04 ms / 126 tokens ( 6.69 ms per token, 149.51 tokens per second) 1.14.258.816 I slot print_timing: id 0 | task 7888 | total time = 949.06 ms / 527 tokens 1.14.258.817 I slot print_timing: id 0 | task 7888 | graphs reused = 7420 1.14.258.817 I slot print_timing: id 0 | task 7888 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.258.848 I slot release: id 0 | task 7888 | stop processing: n_tokens = 558, truncated = 0 1.14.276.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 74168045 1.14.276.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.14.351.922 I slot launch_slot_: id 0 | task 8017 | processing task, is_child = 0 1.15.255.268 I slot print_timing: id 0 | task 8017 | prompt eval time = 120.60 ms / 456 tokens ( 0.26 ms per token, 3781.19 tokens per second) 1.15.255.273 I slot print_timing: id 0 | task 8017 | eval time = 782.73 ms / 114 tokens ( 6.93 ms per token, 144.37 tokens per second) 1.15.255.274 I slot print_timing: id 0 | task 8017 | total time = 903.33 ms / 570 tokens 1.15.255.275 I slot print_timing: id 0 | task 8017 | graphs reused = 7531 1.15.255.276 I slot print_timing: id 0 | task 8017 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.255.312 I slot release: id 0 | task 8017 | stop processing: n_tokens = 601, truncated = 0 1.15.275.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 1.15.275.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.15.349.656 I slot launch_slot_: id 0 | task 8134 | processing task, is_child = 0 1.16.207.022 I slot print_timing: id 0 | task 8134 | prompt eval time = 114.67 ms / 406 tokens ( 0.28 ms per token, 3540.53 tokens per second) 1.16.207.028 I slot print_timing: id 0 | task 8134 | eval time = 742.67 ms / 112 tokens ( 6.69 ms per token, 149.46 tokens per second) 1.16.207.029 I slot print_timing: id 0 | task 8134 | total time = 857.35 ms / 518 tokens 1.16.207.029 I slot print_timing: id 0 | task 8134 | graphs reused = 7640 1.16.207.030 I slot print_timing: id 0 | task 8134 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.207.060 I slot release: id 0 | task 8134 | stop processing: n_tokens = 549, truncated = 0 1.16.226.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 76116257 1.16.270.123 I slot launch_slot_: id 0 | task 8249 | processing task, is_child = 0 1.18.248.118 I slot print_timing: id 0 | task 8249 | prompt eval time = 111.06 ms / 406 tokens ( 0.27 ms per token, 3655.78 tokens per second) 1.18.248.124 I slot print_timing: id 0 | task 8249 | eval time = 1866.92 ms / 282 tokens ( 6.64 ms per token, 150.52 tokens per second) 1.18.248.125 I slot print_timing: id 0 | task 8249 | total time = 1977.97 ms / 688 tokens 1.18.248.125 I slot print_timing: id 0 | task 8249 | graphs reused = 7919 1.18.248.126 I slot print_timing: id 0 | task 8249 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.248.157 I slot release: id 0 | task 8249 | stop processing: n_tokens = 719, truncated = 0 1.18.267.101 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 719, t_last = 78157355 1.18.267.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.18.351.521 I slot launch_slot_: id 0 | task 8534 | processing task, is_child = 0 1.19.382.450 I slot print_timing: id 0 | task 8534 | prompt eval time = 116.28 ms / 444 tokens ( 0.26 ms per token, 3818.34 tokens per second) 1.19.382.455 I slot print_timing: id 0 | task 8534 | eval time = 914.63 ms / 134 tokens ( 6.88 ms per token, 145.41 tokens per second) 1.19.382.457 I slot print_timing: id 0 | task 8534 | total time = 1030.91 ms / 578 tokens 1.19.382.457 I slot print_timing: id 0 | task 8534 | graphs reused = 8050 1.19.382.458 I slot print_timing: id 0 | task 8534 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.382.490 I slot release: id 0 | task 8534 | stop processing: n_tokens = 609, truncated = 0 1.19.406.196 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 79291687 1.19.406.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.19.487.739 I slot launch_slot_: id 0 | task 8671 | processing task, is_child = 0 1.20.275.536 I slot print_timing: id 0 | task 8671 | prompt eval time = 109.79 ms / 372 tokens ( 0.30 ms per token, 3388.35 tokens per second) 1.20.275.541 I slot print_timing: id 0 | task 8671 | eval time = 677.99 ms / 103 tokens ( 6.65 ms per token, 150.44 tokens per second) 1.20.275.542 I slot print_timing: id 0 | task 8671 | total time = 787.78 ms / 475 tokens 1.20.275.543 I slot print_timing: id 0 | task 8671 | graphs reused = 8151 1.20.275.544 I slot print_timing: id 0 | task 8671 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.275.571 I slot release: id 0 | task 8671 | stop processing: n_tokens = 506, truncated = 0 1.20.297.459 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 80184768 1.20.297.509 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.20.381.246 I slot launch_slot_: id 0 | task 8777 | processing task, is_child = 0 1.22.023.523 I slot print_timing: id 0 | task 8777 | prompt eval time = 116.59 ms / 454 tokens ( 0.26 ms per token, 3893.89 tokens per second) 1.22.023.529 I slot print_timing: id 0 | task 8777 | eval time = 1525.66 ms / 230 tokens ( 6.66 ms per token, 150.10 tokens per second) 1.22.023.530 I slot print_timing: id 0 | task 8777 | total time = 1642.26 ms / 684 tokens 1.22.023.530 I slot print_timing: id 0 | task 8777 | graphs reused = 8378 1.22.023.531 I slot print_timing: id 0 | task 8777 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.023.562 I slot release: id 0 | task 8777 | stop processing: n_tokens = 715, truncated = 0 1.22.044.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 81932759 1.22.045.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.22.126.584 I slot launch_slot_: id 0 | task 9010 | processing task, is_child = 0 1.23.750.019 I slot print_timing: id 0 | task 9010 | prompt eval time = 110.82 ms / 354 tokens ( 0.31 ms per token, 3194.37 tokens per second) 1.23.750.025 I slot print_timing: id 0 | task 9010 | eval time = 1512.59 ms / 228 tokens ( 6.66 ms per token, 150.07 tokens per second) 1.23.750.026 I slot print_timing: id 0 | task 9010 | total time = 1623.41 ms / 582 tokens 1.23.750.028 I slot print_timing: id 0 | task 9010 | graphs reused = 8603 1.23.750.028 I slot print_timing: id 0 | task 9010 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.750.059 I slot release: id 0 | task 9010 | stop processing: n_tokens = 613, truncated = 0 1.23.766.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 613, t_last = 83659256 1.23.766.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.23.853.413 I slot launch_slot_: id 0 | task 9241 | processing task, is_child = 0 1.24.890.982 I slot print_timing: id 0 | task 9241 | prompt eval time = 107.62 ms / 334 tokens ( 0.32 ms per token, 3103.43 tokens per second) 1.24.890.987 I slot print_timing: id 0 | task 9241 | eval time = 929.93 ms / 140 tokens ( 6.69 ms per token, 149.47 tokens per second) 1.24.890.989 I slot print_timing: id 0 | task 9241 | total time = 1037.55 ms / 474 tokens 1.24.890.989 I slot print_timing: id 0 | task 9241 | graphs reused = 8741 1.24.890.990 I slot print_timing: id 0 | task 9241 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.891.017 I slot release: id 0 | task 9241 | stop processing: n_tokens = 505, truncated = 0 1.24.906.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 84800215 1.24.906.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 1.24.988.901 I slot launch_slot_: id 0 | task 9384 | processing task, is_child = 0 1.26.262.908 I slot print_timing: id 0 | task 9384 | prompt eval time = 114.49 ms / 426 tokens ( 0.27 ms per token, 3720.82 tokens per second) 1.26.262.914 I slot print_timing: id 0 | task 9384 | eval time = 1159.50 ms / 175 tokens ( 6.66 ms per token, 150.07 tokens per second) 1.26.262.915 I slot print_timing: id 0 | task 9384 | total time = 1273.99 ms / 601 tokens 1.26.262.916 I slot print_timing: id 0 | task 9384 | graphs reused = 8913 1.26.262.917 I slot print_timing: id 0 | task 9384 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.262.949 I slot release: id 0 | task 9384 | stop processing: n_tokens = 632, truncated = 0 1.26.291.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 86172146 1.26.291.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.26.365.330 I slot launch_slot_: id 0 | task 9562 | processing task, is_child = 0 1.27.249.574 I slot print_timing: id 0 | task 9562 | prompt eval time = 108.89 ms / 366 tokens ( 0.30 ms per token, 3361.04 tokens per second) 1.27.249.580 I slot print_timing: id 0 | task 9562 | eval time = 775.33 ms / 117 tokens ( 6.68 ms per token, 149.61 tokens per second) 1.27.249.581 I slot print_timing: id 0 | task 9562 | total time = 884.22 ms / 483 tokens 1.27.249.581 I slot print_timing: id 0 | task 9562 | graphs reused = 9027 1.27.249.582 I slot print_timing: id 0 | task 9562 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.249.612 I slot release: id 0 | task 9562 | stop processing: n_tokens = 514, truncated = 0 1.27.276.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 87158809 1.27.276.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.27.346.192 I slot launch_slot_: id 0 | task 9682 | processing task, is_child = 0 1.29.805.699 I slot print_timing: id 0 | task 9682 | prompt eval time = 120.28 ms / 462 tokens ( 0.26 ms per token, 3840.97 tokens per second) 1.29.805.705 I slot print_timing: id 0 | task 9682 | eval time = 2339.21 ms / 353 tokens ( 6.65 ms per token, 150.48 tokens per second) 1.29.805.706 I slot print_timing: id 0 | task 9682 | total time = 2459.49 ms / 815 tokens 1.29.805.706 I slot print_timing: id 0 | task 9682 | graphs reused = 9376 1.29.805.707 I slot print_timing: id 0 | task 9682 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.805.738 I slot release: id 0 | task 9682 | stop processing: n_tokens = 846, truncated = 0 1.29.821.148 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 846, t_last = 89714935 1.29.821.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.29.903.131 I slot launch_slot_: id 0 | task 10038 | processing task, is_child = 0 1.30.937.164 I slot print_timing: id 0 | task 10038 | prompt eval time = 112.61 ms / 396 tokens ( 0.28 ms per token, 3516.41 tokens per second) 1.30.937.170 I slot print_timing: id 0 | task 10038 | eval time = 921.40 ms / 139 tokens ( 6.68 ms per token, 149.77 tokens per second) 1.30.937.171 I slot print_timing: id 0 | task 10038 | total time = 1034.01 ms / 535 tokens 1.30.937.172 I slot print_timing: id 0 | task 10038 | graphs reused = 9512 1.30.937.173 I slot print_timing: id 0 | task 10038 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.937.202 I slot release: id 0 | task 10038 | stop processing: n_tokens = 566, truncated = 0 1.30.955.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 90846399 1.31.003.910 I slot launch_slot_: id 0 | task 10180 | processing task, is_child = 0 1.32.189.593 I slot print_timing: id 0 | task 10180 | prompt eval time = 117.92 ms / 458 tokens ( 0.26 ms per token, 3884.12 tokens per second) 1.32.189.599 I slot print_timing: id 0 | task 10180 | eval time = 1067.75 ms / 161 tokens ( 6.67 ms per token, 149.85 tokens per second) 1.32.189.600 I slot print_timing: id 0 | task 10180 | total time = 1185.66 ms / 619 tokens 1.32.189.601 I slot print_timing: id 0 | task 10180 | graphs reused = 9670 1.32.189.602 I slot print_timing: id 0 | task 10180 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.189.634 I slot release: id 0 | task 10180 | stop processing: n_tokens = 650, truncated = 0 1.32.204.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 92098831 1.32.204.476 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.32.295.125 I slot launch_slot_: id 0 | task 10344 | processing task, is_child = 0 1.33.608.871 I slot print_timing: id 0 | task 10344 | prompt eval time = 119.46 ms / 458 tokens ( 0.26 ms per token, 3834.05 tokens per second) 1.33.608.878 I slot print_timing: id 0 | task 10344 | eval time = 1194.27 ms / 176 tokens ( 6.82 ms per token, 146.53 tokens per second) 1.33.608.878 I slot print_timing: id 0 | task 10344 | total time = 1313.72 ms / 634 tokens 1.33.608.879 I slot print_timing: id 0 | task 10344 | graphs reused = 9843 1.33.608.880 I slot print_timing: id 0 | task 10344 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.608.914 I slot release: id 0 | task 10344 | stop processing: n_tokens = 665, truncated = 0 1.33.627.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 93518112 1.33.627.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.33.709.729 I slot launch_slot_: id 0 | task 10523 | processing task, is_child = 0 1.35.219.372 I slot print_timing: id 0 | task 10523 | prompt eval time = 118.66 ms / 452 tokens ( 0.26 ms per token, 3809.17 tokens per second) 1.35.219.377 I slot print_timing: id 0 | task 10523 | eval time = 1390.96 ms / 210 tokens ( 6.66 ms per token, 150.26 tokens per second) 1.35.219.378 I slot print_timing: id 0 | task 10523 | total time = 1509.62 ms / 662 tokens 1.35.219.379 I slot print_timing: id 0 | task 10523 | graphs reused = 10050 1.35.219.380 I slot print_timing: id 0 | task 10523 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.219.412 I slot release: id 0 | task 10523 | stop processing: n_tokens = 693, truncated = 0 1.35.235.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 95128610 1.35.235.207 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.35.318.675 I slot launch_slot_: id 0 | task 10736 | processing task, is_child = 0 1.36.188.420 I slot print_timing: id 0 | task 10736 | prompt eval time = 114.57 ms / 404 tokens ( 0.28 ms per token, 3526.29 tokens per second) 1.36.188.425 I slot print_timing: id 0 | task 10736 | eval time = 755.16 ms / 114 tokens ( 6.68 ms per token, 149.64 tokens per second) 1.36.188.426 I slot print_timing: id 0 | task 10736 | total time = 869.73 ms / 518 tokens 1.36.188.427 I slot print_timing: id 0 | task 10736 | graphs reused = 10161 1.36.188.428 I slot print_timing: id 0 | task 10736 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.188.456 I slot release: id 0 | task 10736 | stop processing: n_tokens = 549, truncated = 0 1.36.202.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 96097654 1.36.202.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.36.272.249 I slot launch_slot_: id 0 | task 10853 | processing task, is_child = 0 1.37.076.904 I slot print_timing: id 0 | task 10853 | prompt eval time = 106.88 ms / 345 tokens ( 0.31 ms per token, 3227.86 tokens per second) 1.37.076.910 I slot print_timing: id 0 | task 10853 | eval time = 697.75 ms / 106 tokens ( 6.65 ms per token, 150.48 tokens per second) 1.37.076.911 I slot print_timing: id 0 | task 10853 | total time = 804.63 ms / 451 tokens 1.37.076.911 I slot print_timing: id 0 | task 10853 | graphs reused = 10265 1.37.076.912 I slot print_timing: id 0 | task 10853 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.076.942 I slot release: id 0 | task 10853 | stop processing: n_tokens = 482, truncated = 0 1.37.093.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 96986139 1.37.093.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.37.157.230 I slot launch_slot_: id 0 | task 10962 | processing task, is_child = 0 1.37.971.390 I slot print_timing: id 0 | task 10962 | prompt eval time = 117.97 ms / 430 tokens ( 0.27 ms per token, 3645.15 tokens per second) 1.37.971.396 I slot print_timing: id 0 | task 10962 | eval time = 696.17 ms / 105 tokens ( 6.69 ms per token, 149.39 tokens per second) 1.37.971.397 I slot print_timing: id 0 | task 10962 | total time = 814.14 ms / 535 tokens 1.37.971.398 I slot print_timing: id 0 | task 10962 | graphs reused = 10367 1.37.971.399 I slot print_timing: id 0 | task 10962 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.971.428 I slot release: id 0 | task 10962 | stop processing: n_tokens = 566, truncated = 0 1.37.999.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 97880626 1.37.999.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.38.072.809 I slot launch_slot_: id 0 | task 11070 | processing task, is_child = 0 1.38.762.267 I slot print_timing: id 0 | task 11070 | prompt eval time = 103.18 ms / 316 tokens ( 0.33 ms per token, 3062.70 tokens per second) 1.38.762.274 I slot print_timing: id 0 | task 11070 | eval time = 586.26 ms / 85 tokens ( 6.98 ms per token, 143.28 tokens per second) 1.38.762.275 I slot print_timing: id 0 | task 11070 | total time = 689.44 ms / 401 tokens 1.38.762.275 I slot print_timing: id 0 | task 11070 | graphs reused = 10450 1.38.762.276 I slot print_timing: id 0 | task 11070 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.762.303 I slot release: id 0 | task 11070 | stop processing: n_tokens = 432, truncated = 0 1.38.780.879 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 98671500 1.38.780.921 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 1.38.850.332 I slot launch_slot_: id 0 | task 11158 | processing task, is_child = 0 1.39.663.295 I slot print_timing: id 0 | task 11158 | prompt eval time = 108.62 ms / 354 tokens ( 0.31 ms per token, 3258.95 tokens per second) 1.39.663.301 I slot print_timing: id 0 | task 11158 | eval time = 704.32 ms / 107 tokens ( 6.64 ms per token, 150.50 tokens per second) 1.39.663.302 I slot print_timing: id 0 | task 11158 | total time = 812.94 ms / 461 tokens 1.39.663.303 I slot print_timing: id 0 | task 11158 | graphs reused = 10555 1.39.663.304 I slot print_timing: id 0 | task 11158 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.663.332 I slot release: id 0 | task 11158 | stop processing: n_tokens = 492, truncated = 0 1.39.684.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 99572529 1.39.684.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 1.39.752.845 I slot launch_slot_: id 0 | task 11268 | processing task, is_child = 0 1.40.524.122 I slot print_timing: id 0 | task 11268 | prompt eval time = 120.28 ms / 438 tokens ( 0.27 ms per token, 3641.65 tokens per second) 1.40.524.128 I slot print_timing: id 0 | task 11268 | eval time = 650.98 ms / 98 tokens ( 6.71 ms per token, 149.01 tokens per second) 1.40.524.129 I slot print_timing: id 0 | task 11268 | total time = 771.26 ms / 536 tokens 1.40.524.130 I slot print_timing: id 0 | task 11268 | graphs reused = 10650 1.40.524.130 I slot print_timing: id 0 | task 11268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.524.161 I slot release: id 0 | task 11268 | stop processing: n_tokens = 567, truncated = 0 1.40.551.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 100433358 1.40.551.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.40.620.406 I slot launch_slot_: id 0 | task 11369 | processing task, is_child = 0 1.41.205.835 I slot print_timing: id 0 | task 11369 | prompt eval time = 119.34 ms / 457 tokens ( 0.26 ms per token, 3829.43 tokens per second) 1.41.205.841 I slot print_timing: id 0 | task 11369 | eval time = 466.07 ms / 70 tokens ( 6.75 ms per token, 148.05 tokens per second) 1.41.205.842 I slot print_timing: id 0 | task 11369 | total time = 585.41 ms / 527 tokens 1.41.205.843 I slot print_timing: id 0 | task 11369 | graphs reused = 10717 1.41.205.843 I slot print_timing: id 0 | task 11369 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.205.876 I slot release: id 0 | task 11369 | stop processing: n_tokens = 558, truncated = 0 1.41.226.324 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 101115073 1.41.226.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 1.41.292.320 I slot launch_slot_: id 0 | task 11442 | processing task, is_child = 0 1.42.067.221 I slot print_timing: id 0 | task 11442 | prompt eval time = 122.83 ms / 473 tokens ( 0.26 ms per token, 3851.01 tokens per second) 1.42.067.227 I slot print_timing: id 0 | task 11442 | eval time = 652.06 ms / 98 tokens ( 6.72 ms per token, 148.76 tokens per second) 1.42.067.228 I slot print_timing: id 0 | task 11442 | total time = 774.88 ms / 571 tokens 1.42.067.229 I slot print_timing: id 0 | task 11442 | graphs reused = 10812 1.42.067.230 I slot print_timing: id 0 | task 11442 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.067.261 I slot release: id 0 | task 11442 | stop processing: n_tokens = 602, truncated = 0 1.42.083.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 101976458 1.42.083.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.926 MiB) 1.42.153.929 I slot launch_slot_: id 0 | task 11543 | processing task, is_child = 0 1.42.458.215 I slot print_timing: id 0 | task 11543 | prompt eval time = 123.37 ms / 476 tokens ( 0.26 ms per token, 3858.37 tokens per second) 1.42.458.221 I slot print_timing: id 0 | task 11543 | eval time = 180.90 ms / 27 tokens ( 6.96 ms per token, 143.73 tokens per second) 1.42.458.222 I slot print_timing: id 0 | task 11543 | total time = 304.26 ms / 503 tokens 1.42.458.222 I slot print_timing: id 0 | task 11543 | graphs reused = 10836 1.42.458.223 I slot print_timing: id 0 | task 11543 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.458.255 I slot release: id 0 | task 11543 | stop processing: n_tokens = 534, truncated = 0 1.42.474.455 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 102367452 1.42.474.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.42.541.671 I slot launch_slot_: id 0 | task 11573 | processing task, is_child = 0 1.43.376.016 I slot print_timing: id 0 | task 11573 | prompt eval time = 123.94 ms / 466 tokens ( 0.27 ms per token, 3759.91 tokens per second) 1.43.376.021 I slot print_timing: id 0 | task 11573 | eval time = 710.39 ms / 107 tokens ( 6.70 ms per token, 149.21 tokens per second) 1.43.376.022 I slot print_timing: id 0 | task 11573 | total time = 834.33 ms / 573 tokens 1.43.376.024 I slot print_timing: id 0 | task 11573 | graphs reused = 10940 1.43.376.024 I slot print_timing: id 0 | task 11573 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.376.056 I slot release: id 0 | task 11573 | stop processing: n_tokens = 604, truncated = 0 1.43.391.432 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 103285253 1.43.391.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.43.457.536 I slot launch_slot_: id 0 | task 11683 | processing task, is_child = 0 1.44.090.345 I slot print_timing: id 0 | task 11683 | prompt eval time = 114.99 ms / 415 tokens ( 0.28 ms per token, 3608.92 tokens per second) 1.44.090.350 I slot print_timing: id 0 | task 11683 | eval time = 517.80 ms / 78 tokens ( 6.72 ms per token, 148.71 tokens per second) 1.44.090.352 I slot print_timing: id 0 | task 11683 | total time = 632.79 ms / 493 tokens 1.44.090.353 I slot print_timing: id 0 | task 11683 | graphs reused = 11015 1.44.090.353 I slot print_timing: id 0 | task 11683 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.090.383 I slot release: id 0 | task 11683 | stop processing: n_tokens = 524, truncated = 0 1.44.106.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 103999581 1.44.106.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.299 MiB) 1.44.182.525 I slot launch_slot_: id 0 | task 11764 | processing task, is_child = 0 1.44.711.044 I slot print_timing: id 0 | task 11764 | prompt eval time = 107.65 ms / 352 tokens ( 0.31 ms per token, 3269.95 tokens per second) 1.44.711.050 I slot print_timing: id 0 | task 11764 | eval time = 420.85 ms / 64 tokens ( 6.68 ms per token, 149.70 tokens per second) 1.44.711.051 I slot print_timing: id 0 | task 11764 | total time = 528.50 ms / 416 tokens 1.44.711.053 I slot print_timing: id 0 | task 11764 | graphs reused = 11077 1.44.711.054 I slot print_timing: id 0 | task 11764 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.711.083 I slot release: id 0 | task 11764 | stop processing: n_tokens = 447, truncated = 0 1.44.731.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 104620281 1.44.731.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.44.810.324 I slot launch_slot_: id 0 | task 11831 | processing task, is_child = 0 1.45.821.912 I slot print_timing: id 0 | task 11831 | prompt eval time = 132.68 ms / 550 tokens ( 0.24 ms per token, 4145.19 tokens per second) 1.45.821.918 I slot print_timing: id 0 | task 11831 | eval time = 878.88 ms / 133 tokens ( 6.66 ms per token, 150.19 tokens per second) 1.45.821.919 I slot print_timing: id 0 | task 11831 | total time = 1011.57 ms / 683 tokens 1.45.821.920 I slot print_timing: id 0 | task 11831 | graphs reused = 11208 1.45.821.921 I slot print_timing: id 0 | task 11831 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.821.958 I slot release: id 0 | task 11831 | stop processing: n_tokens = 714, truncated = 0 1.45.845.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 105731155 1.45.845.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.989 MiB) 1.45.926.963 I slot launch_slot_: id 0 | task 11968 | processing task, is_child = 0 1.47.585.657 I slot print_timing: id 0 | task 11968 | prompt eval time = 158.11 ms / 772 tokens ( 0.20 ms per token, 4882.61 tokens per second) 1.47.585.663 I slot print_timing: id 0 | task 11968 | eval time = 1500.56 ms / 226 tokens ( 6.67 ms per token, 149.94 tokens per second) 1.47.585.664 I slot print_timing: id 0 | task 11968 | total time = 1658.68 ms / 998 tokens 1.47.585.665 I slot print_timing: id 0 | task 11968 | graphs reused = 11431 1.47.585.666 I slot print_timing: id 0 | task 11968 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.585.705 I slot release: id 0 | task 11968 | stop processing: n_tokens = 1029, truncated = 0 1.47.607.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 107494903 1.47.607.935 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.47.697.421 I slot launch_slot_: id 0 | task 12198 | processing task, is_child = 0 1.49.063.185 I slot print_timing: id 0 | task 12198 | prompt eval time = 154.46 ms / 683 tokens ( 0.23 ms per token, 4421.83 tokens per second) 1.49.063.190 I slot print_timing: id 0 | task 12198 | eval time = 1211.28 ms / 181 tokens ( 6.73 ms per token, 148.60 tokens per second) 1.49.063.191 I slot print_timing: id 0 | task 12198 | total time = 1365.74 ms / 864 tokens 1.49.063.192 I slot print_timing: id 0 | task 12198 | graphs reused = 11609 1.49.063.193 I slot print_timing: id 0 | task 12198 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.063.228 I slot release: id 0 | task 12198 | stop processing: n_tokens = 895, truncated = 0 1.49.083.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 108972426 1.49.083.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 1.49.166.250 I slot launch_slot_: id 0 | task 12383 | processing task, is_child = 0 1.51.387.994 I slot print_timing: id 0 | task 12383 | prompt eval time = 140.48 ms / 579 tokens ( 0.24 ms per token, 4121.67 tokens per second) 1.51.388.000 I slot print_timing: id 0 | task 12383 | eval time = 2081.24 ms / 314 tokens ( 6.65 ms per token, 150.39 tokens per second) 1.51.388.001 I slot print_timing: id 0 | task 12383 | total time = 2221.72 ms / 893 tokens 1.51.388.002 I slot print_timing: id 0 | task 12383 | graphs reused = 11920 1.51.388.002 I slot print_timing: id 0 | task 12383 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.388.036 I slot release: id 0 | task 12383 | stop processing: n_tokens = 924, truncated = 0 1.51.412.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 924, t_last = 111297233 1.51.412.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 1.51.432.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.674 MiB) 1.51.533.390 I slot launch_slot_: id 0 | task 12701 | processing task, is_child = 0 1.52.363.540 I slot print_timing: id 0 | task 12701 | prompt eval time = 129.76 ms / 500 tokens ( 0.26 ms per token, 3853.30 tokens per second) 1.52.363.546 I slot print_timing: id 0 | task 12701 | eval time = 700.37 ms / 106 tokens ( 6.67 ms per token, 149.92 tokens per second) 1.52.363.547 I slot print_timing: id 0 | task 12701 | total time = 830.13 ms / 606 tokens 1.52.363.547 I slot print_timing: id 0 | task 12701 | graphs reused = 12024 1.52.363.548 I slot print_timing: id 0 | task 12701 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.363.580 I slot release: id 0 | task 12701 | stop processing: n_tokens = 637, truncated = 0 1.52.392.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 112272777 1.52.392.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 1.52.460.446 I slot launch_slot_: id 0 | task 12810 | processing task, is_child = 0 1.53.386.149 I slot print_timing: id 0 | task 12810 | prompt eval time = 160.34 ms / 776 tokens ( 0.21 ms per token, 4839.63 tokens per second) 1.53.386.155 I slot print_timing: id 0 | task 12810 | eval time = 765.34 ms / 116 tokens ( 6.66 ms per token, 150.26 tokens per second) 1.53.386.156 I slot print_timing: id 0 | task 12810 | total time = 925.68 ms / 892 tokens 1.53.386.157 I slot print_timing: id 0 | task 12810 | graphs reused = 12138 1.53.386.158 I slot print_timing: id 0 | task 12810 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.386.198 I slot release: id 0 | task 12810 | stop processing: n_tokens = 923, truncated = 0 1.53.407.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 923, t_last = 113295396 1.53.407.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 1.53.486.758 I slot launch_slot_: id 0 | task 12930 | processing task, is_child = 0 1.54.915.886 I slot print_timing: id 0 | task 12930 | prompt eval time = 128.86 ms / 504 tokens ( 0.26 ms per token, 3911.25 tokens per second) 1.54.915.891 I slot print_timing: id 0 | task 12930 | eval time = 1300.25 ms / 197 tokens ( 6.63 ms per token, 150.74 tokens per second) 1.54.915.892 I slot print_timing: id 0 | task 12930 | total time = 1429.11 ms / 701 tokens 1.54.915.892 I slot print_timing: id 0 | task 12930 | graphs reused = 12333 1.54.915.893 I slot print_timing: id 0 | task 12930 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.915.926 I slot release: id 0 | task 12930 | stop processing: n_tokens = 732, truncated = 0 1.54.937.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 114825124 1.54.937.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 1.55.012.683 I slot launch_slot_: id 0 | task 13130 | processing task, is_child = 0 1.56.530.467 I slot print_timing: id 0 | task 13130 | prompt eval time = 144.53 ms / 633 tokens ( 0.23 ms per token, 4379.68 tokens per second) 1.56.530.474 I slot print_timing: id 0 | task 13130 | eval time = 1373.23 ms / 207 tokens ( 6.67 ms per token, 150.01 tokens per second) 1.56.530.475 I slot print_timing: id 0 | task 13130 | total time = 1517.76 ms / 840 tokens 1.56.530.475 I slot print_timing: id 0 | task 13130 | graphs reused = 12537 1.56.530.476 I slot print_timing: id 0 | task 13130 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.530.513 I slot release: id 0 | task 13130 | stop processing: n_tokens = 871, truncated = 0 1.56.547.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 116439710 1.56.547.356 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.961 MiB) 1.56.631.831 I slot launch_slot_: id 0 | task 13341 | processing task, is_child = 0 1.57.637.649 I slot print_timing: id 0 | task 13341 | prompt eval time = 118.14 ms / 395 tokens ( 0.30 ms per token, 3343.52 tokens per second) 1.57.637.655 I slot print_timing: id 0 | task 13341 | eval time = 887.66 ms / 134 tokens ( 6.67 ms per token, 149.83 tokens per second) 1.57.637.656 I slot print_timing: id 0 | task 13341 | total time = 1005.80 ms / 529 tokens 1.57.637.656 I slot print_timing: id 0 | task 13341 | graphs reused = 12668 1.57.637.657 I slot print_timing: id 0 | task 13341 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.637.687 I slot release: id 0 | task 13341 | stop processing: n_tokens = 560, truncated = 0 1.57.653.211 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 117546884 1.57.653.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 1.57.725.790 I slot launch_slot_: id 0 | task 13478 | processing task, is_child = 0 1.59.247.886 I slot print_timing: id 0 | task 13478 | prompt eval time = 137.72 ms / 584 tokens ( 0.24 ms per token, 4240.36 tokens per second) 1.59.247.892 I slot print_timing: id 0 | task 13478 | eval time = 1384.35 ms / 209 tokens ( 6.66 ms per token, 150.25 tokens per second) 1.59.247.893 I slot print_timing: id 0 | task 13478 | total time = 1522.08 ms / 793 tokens 1.59.247.894 I slot print_timing: id 0 | task 13478 | graphs reused = 12874 1.59.247.895 I slot print_timing: id 0 | task 13478 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.247.928 I slot release: id 0 | task 13478 | stop processing: n_tokens = 824, truncated = 0 1.59.272.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 119157126 1.59.272.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 1.59.356.230 I slot launch_slot_: id 0 | task 13691 | processing task, is_child = 0 2.01.036.081 I slot print_timing: id 0 | task 13691 | prompt eval time = 154.26 ms / 695 tokens ( 0.22 ms per token, 4505.26 tokens per second) 2.01.036.086 I slot print_timing: id 0 | task 13691 | eval time = 1525.57 ms / 230 tokens ( 6.66 ms per token, 150.11 tokens per second) 2.01.036.088 I slot print_timing: id 0 | task 13691 | total time = 1679.83 ms / 925 tokens 2.01.036.088 I slot print_timing: id 0 | task 13691 | graphs reused = 13101 2.01.036.089 I slot print_timing: id 0 | task 13691 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.036.127 I slot release: id 0 | task 13691 | stop processing: n_tokens = 956, truncated = 0 2.01.054.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 120945324 2.01.054.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.01.143.917 I slot launch_slot_: id 0 | task 13925 | processing task, is_child = 0 2.02.569.024 I slot print_timing: id 0 | task 13925 | prompt eval time = 161.28 ms / 769 tokens ( 0.21 ms per token, 4767.96 tokens per second) 2.02.569.031 I slot print_timing: id 0 | task 13925 | eval time = 1263.80 ms / 191 tokens ( 6.65 ms per token, 150.34 tokens per second) 2.02.569.032 I slot print_timing: id 0 | task 13925 | total time = 1425.09 ms / 960 tokens 2.02.569.032 I slot print_timing: id 0 | task 13925 | graphs reused = 13290 2.02.569.033 I slot print_timing: id 0 | task 13925 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.569.072 I slot release: id 0 | task 13925 | stop processing: n_tokens = 991, truncated = 0 2.02.597.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 122478269 2.02.597.678 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.02.617.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.02.712.584 I slot launch_slot_: id 0 | task 14120 | processing task, is_child = 0 2.03.669.655 I slot print_timing: id 0 | task 14120 | prompt eval time = 140.16 ms / 576 tokens ( 0.24 ms per token, 4109.62 tokens per second) 2.03.669.661 I slot print_timing: id 0 | task 14120 | eval time = 816.89 ms / 124 tokens ( 6.64 ms per token, 150.57 tokens per second) 2.03.669.662 I slot print_timing: id 0 | task 14120 | total time = 957.05 ms / 700 tokens 2.03.669.662 I slot print_timing: id 0 | task 14120 | graphs reused = 13412 2.03.669.663 I slot print_timing: id 0 | task 14120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.669.698 I slot release: id 0 | task 14120 | stop processing: n_tokens = 731, truncated = 0 2.03.690.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 123578895 2.03.690.190 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.03.762.671 I slot launch_slot_: id 0 | task 14248 | processing task, is_child = 0 2.05.738.861 I slot print_timing: id 0 | task 14248 | prompt eval time = 149.94 ms / 655 tokens ( 0.23 ms per token, 4368.44 tokens per second) 2.05.738.866 I slot print_timing: id 0 | task 14248 | eval time = 1826.23 ms / 275 tokens ( 6.67 ms per token, 150.04 tokens per second) 2.05.738.868 I slot print_timing: id 0 | task 14248 | total time = 1976.17 ms / 930 tokens 2.05.738.868 I slot print_timing: id 0 | task 14248 | graphs reused = 13684 2.05.738.869 I slot print_timing: id 0 | task 14248 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.738.907 I slot release: id 0 | task 14248 | stop processing: n_tokens = 961, truncated = 0 2.05.767.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 125648104 2.05.767.783 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.05.852.689 I slot launch_slot_: id 0 | task 14527 | processing task, is_child = 0 2.06.804.101 I slot print_timing: id 0 | task 14527 | prompt eval time = 147.24 ms / 621 tokens ( 0.24 ms per token, 4217.58 tokens per second) 2.06.804.107 I slot print_timing: id 0 | task 14527 | eval time = 804.15 ms / 121 tokens ( 6.70 ms per token, 149.23 tokens per second) 2.06.804.108 I slot print_timing: id 0 | task 14527 | total time = 951.39 ms / 742 tokens 2.06.804.109 I slot print_timing: id 0 | task 14527 | graphs reused = 13802 2.06.804.110 I slot print_timing: id 0 | task 14527 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.804.147 I slot release: id 0 | task 14527 | stop processing: n_tokens = 773, truncated = 0 2.06.830.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 126713344 2.06.831.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.06.917.073 I slot launch_slot_: id 0 | task 14652 | processing task, is_child = 0 2.08.284.702 I slot print_timing: id 0 | task 14652 | prompt eval time = 159.68 ms / 767 tokens ( 0.21 ms per token, 4803.48 tokens per second) 2.08.284.708 I slot print_timing: id 0 | task 14652 | eval time = 1207.93 ms / 178 tokens ( 6.82 ms per token, 146.53 tokens per second) 2.08.284.709 I slot print_timing: id 0 | task 14652 | total time = 1367.61 ms / 945 tokens 2.08.284.710 I slot print_timing: id 0 | task 14652 | graphs reused = 13978 2.08.284.710 I slot print_timing: id 0 | task 14652 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.284.753 I slot release: id 0 | task 14652 | stop processing: n_tokens = 976, truncated = 0 2.08.302.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 128193951 2.08.302.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.08.393.776 I slot launch_slot_: id 0 | task 14834 | processing task, is_child = 0 2.09.948.250 I slot print_timing: id 0 | task 14834 | prompt eval time = 175.57 ms / 864 tokens ( 0.20 ms per token, 4921.14 tokens per second) 2.09.948.257 I slot print_timing: id 0 | task 14834 | eval time = 1378.88 ms / 203 tokens ( 6.83 ms per token, 146.50 tokens per second) 2.09.948.258 I slot print_timing: id 0 | task 14834 | total time = 1554.45 ms / 1067 tokens 2.09.948.259 I slot print_timing: id 0 | task 14834 | graphs reused = 14178 2.09.948.260 I slot print_timing: id 0 | task 14834 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.948.309 I slot release: id 0 | task 14834 | stop processing: n_tokens = 1098, truncated = 0 2.09.975.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 129857506 2.09.975.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.09.995.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.10.092.616 I slot launch_slot_: id 0 | task 15041 | processing task, is_child = 0 2.11.101.981 I slot print_timing: id 0 | task 15041 | prompt eval time = 152.02 ms / 646 tokens ( 0.24 ms per token, 4249.36 tokens per second) 2.11.101.988 I slot print_timing: id 0 | task 15041 | eval time = 857.32 ms / 129 tokens ( 6.70 ms per token, 149.30 tokens per second) 2.11.101.989 I slot print_timing: id 0 | task 15041 | total time = 1009.34 ms / 775 tokens 2.11.101.991 I slot print_timing: id 0 | task 15041 | graphs reused = 14304 2.11.101.992 I slot print_timing: id 0 | task 15041 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.102.034 I slot release: id 0 | task 15041 | stop processing: n_tokens = 806, truncated = 0 2.11.131.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 131011231 2.11.131.204 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.11.207.875 I slot launch_slot_: id 0 | task 15174 | processing task, is_child = 0 2.12.874.045 I slot print_timing: id 0 | task 15174 | prompt eval time = 156.27 ms / 720 tokens ( 0.22 ms per token, 4607.50 tokens per second) 2.12.874.052 I slot print_timing: id 0 | task 15174 | eval time = 1509.88 ms / 219 tokens ( 6.93 ms per token, 144.38 tokens per second) 2.12.874.053 I slot print_timing: id 0 | task 15174 | total time = 1666.15 ms / 939 tokens 2.12.874.053 I slot print_timing: id 0 | task 15174 | graphs reused = 14520 2.12.874.055 I slot print_timing: id 0 | task 15174 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.874.094 I slot release: id 0 | task 15174 | stop processing: n_tokens = 970, truncated = 0 2.12.891.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 132783292 2.12.891.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.12.982.141 I slot launch_slot_: id 0 | task 15397 | processing task, is_child = 0 2.14.527.291 I slot print_timing: id 0 | task 15397 | prompt eval time = 132.07 ms / 509 tokens ( 0.26 ms per token, 3853.96 tokens per second) 2.14.527.297 I slot print_timing: id 0 | task 15397 | eval time = 1413.06 ms / 214 tokens ( 6.63 ms per token, 150.74 tokens per second) 2.14.527.298 I slot print_timing: id 0 | task 15397 | total time = 1545.13 ms / 723 tokens 2.14.527.299 I slot print_timing: id 0 | task 15397 | graphs reused = 14732 2.14.527.300 I slot print_timing: id 0 | task 15397 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.527.332 I slot release: id 0 | task 15397 | stop processing: n_tokens = 754, truncated = 0 2.14.531.861 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 134436529 2.14.531.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.14.599.932 I slot launch_slot_: id 0 | task 15614 | processing task, is_child = 0 2.16.343.321 I slot print_timing: id 0 | task 15614 | prompt eval time = 138.67 ms / 581 tokens ( 0.24 ms per token, 4189.92 tokens per second) 2.16.343.326 I slot print_timing: id 0 | task 15614 | eval time = 1604.70 ms / 242 tokens ( 6.66 ms per token, 150.18 tokens per second) 2.16.343.328 I slot print_timing: id 0 | task 15614 | total time = 1743.37 ms / 823 tokens 2.16.343.328 I slot print_timing: id 0 | task 15614 | graphs reused = 14971 2.16.343.329 I slot print_timing: id 0 | task 15614 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.343.365 I slot release: id 0 | task 15614 | stop processing: n_tokens = 854, truncated = 0 2.16.371.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 136252562 2.16.371.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.16.454.699 I slot launch_slot_: id 0 | task 15860 | processing task, is_child = 0 2.18.097.572 I slot print_timing: id 0 | task 15860 | prompt eval time = 180.60 ms / 925 tokens ( 0.20 ms per token, 5121.67 tokens per second) 2.18.097.579 I slot print_timing: id 0 | task 15860 | eval time = 1462.25 ms / 220 tokens ( 6.68 ms per token, 149.77 tokens per second) 2.18.097.580 I slot print_timing: id 0 | task 15860 | total time = 1642.85 ms / 1145 tokens 2.18.097.580 I slot print_timing: id 0 | task 15860 | graphs reused = 15188 2.18.097.581 I slot print_timing: id 0 | task 15860 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.097.627 I slot release: id 0 | task 15860 | stop processing: n_tokens = 1176, truncated = 0 2.18.121.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 138006825 2.18.121.116 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.18.212.888 I slot launch_slot_: id 0 | task 16084 | processing task, is_child = 0 2.20.050.363 I slot print_timing: id 0 | task 16084 | prompt eval time = 174.58 ms / 885 tokens ( 0.20 ms per token, 5069.22 tokens per second) 2.20.050.370 I slot print_timing: id 0 | task 16084 | eval time = 1662.87 ms / 245 tokens ( 6.82 ms per token, 146.73 tokens per second) 2.20.050.371 I slot print_timing: id 0 | task 16084 | total time = 1837.46 ms / 1130 tokens 2.20.050.372 I slot print_timing: id 0 | task 16084 | graphs reused = 15430 2.20.050.372 I slot print_timing: id 0 | task 16084 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.050.416 I slot release: id 0 | task 16084 | stop processing: n_tokens = 1161, truncated = 0 2.20.079.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 139959613 2.20.079.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.20.174.174 I slot launch_slot_: id 0 | task 16333 | processing task, is_child = 0 2.21.632.697 I slot print_timing: id 0 | task 16333 | prompt eval time = 117.48 ms / 392 tokens ( 0.30 ms per token, 3336.65 tokens per second) 2.21.632.704 I slot print_timing: id 0 | task 16333 | eval time = 1341.02 ms / 203 tokens ( 6.64 ms per token, 150.63 tokens per second) 2.21.632.705 I slot print_timing: id 0 | task 16333 | total time = 1458.51 ms / 595 tokens 2.21.632.705 I slot print_timing: id 0 | task 16333 | graphs reused = 15630 2.21.632.706 I slot print_timing: id 0 | task 16333 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.632.738 I slot release: id 0 | task 16333 | stop processing: n_tokens = 626, truncated = 0 2.21.658.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 626, t_last = 141541936 2.21.658.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 2.21.741.404 I slot launch_slot_: id 0 | task 16539 | processing task, is_child = 0 2.22.189.759 I slot print_timing: id 0 | task 16539 | prompt eval time = 107.48 ms / 331 tokens ( 0.32 ms per token, 3079.67 tokens per second) 2.22.189.765 I slot print_timing: id 0 | task 16539 | eval time = 340.86 ms / 52 tokens ( 6.68 ms per token, 149.62 tokens per second) 2.22.189.766 I slot print_timing: id 0 | task 16539 | total time = 448.34 ms / 383 tokens 2.22.189.766 I slot print_timing: id 0 | task 16539 | graphs reused = 15680 2.22.189.767 I slot print_timing: id 0 | task 16539 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.189.793 I slot release: id 0 | task 16539 | stop processing: n_tokens = 414, truncated = 0 2.22.206.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 142098990 2.22.206.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.22.287.082 I slot launch_slot_: id 0 | task 16594 | processing task, is_child = 0 2.23.687.199 I slot print_timing: id 0 | task 16594 | prompt eval time = 109.11 ms / 357 tokens ( 0.31 ms per token, 3272.08 tokens per second) 2.23.687.205 I slot print_timing: id 0 | task 16594 | eval time = 1290.99 ms / 193 tokens ( 6.72 ms per token, 148.72 tokens per second) 2.23.687.206 I slot print_timing: id 0 | task 16594 | total time = 1400.10 ms / 550 tokens 2.23.687.207 I slot print_timing: id 0 | task 16594 | graphs reused = 15870 2.23.687.208 I slot print_timing: id 0 | task 16594 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.687.235 I slot release: id 0 | task 16594 | stop processing: n_tokens = 581, truncated = 0 2.23.702.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 143596432 2.23.702.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.650 MiB) 2.23.783.628 I slot launch_slot_: id 0 | task 16790 | processing task, is_child = 0 2.24.371.951 I slot print_timing: id 0 | task 16790 | prompt eval time = 107.75 ms / 315 tokens ( 0.34 ms per token, 2923.33 tokens per second) 2.24.371.957 I slot print_timing: id 0 | task 16790 | eval time = 480.55 ms / 73 tokens ( 6.67 ms per token, 149.83 tokens per second) 2.24.371.958 I slot print_timing: id 0 | task 16790 | total time = 588.30 ms / 388 tokens 2.24.371.958 I slot print_timing: id 0 | task 16790 | graphs reused = 15941 2.24.371.959 I slot print_timing: id 0 | task 16790 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.371.985 I slot release: id 0 | task 16790 | stop processing: n_tokens = 419, truncated = 0 2.24.391.732 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 144281182 2.24.391.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.24.461.330 I slot launch_slot_: id 0 | task 16866 | processing task, is_child = 0 2.24.966.808 I slot print_timing: id 0 | task 16866 | prompt eval time = 110.30 ms / 378 tokens ( 0.29 ms per token, 3427.14 tokens per second) 2.24.966.815 I slot print_timing: id 0 | task 16866 | eval time = 395.16 ms / 60 tokens ( 6.70 ms per token, 149.31 tokens per second) 2.24.966.816 I slot print_timing: id 0 | task 16866 | total time = 505.46 ms / 438 tokens 2.24.966.817 I slot print_timing: id 0 | task 16866 | graphs reused = 15999 2.24.966.817 I slot print_timing: id 0 | task 16866 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.966.848 I slot release: id 0 | task 16866 | stop processing: n_tokens = 469, truncated = 0 2.24.982.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 144876045 2.24.982.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.619 MiB) 2.25.055.415 I slot launch_slot_: id 0 | task 16929 | processing task, is_child = 0 2.25.341.090 I slot print_timing: id 0 | task 16929 | prompt eval time = 102.86 ms / 295 tokens ( 0.35 ms per token, 2867.92 tokens per second) 2.25.341.096 I slot print_timing: id 0 | task 16929 | eval time = 182.79 ms / 28 tokens ( 6.77 ms per token, 147.71 tokens per second) 2.25.341.097 I slot print_timing: id 0 | task 16929 | total time = 285.66 ms / 323 tokens 2.25.341.098 I slot print_timing: id 0 | task 16929 | graphs reused = 16025 2.25.341.099 I slot print_timing: id 0 | task 16929 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.341.126 I slot release: id 0 | task 16929 | stop processing: n_tokens = 354, truncated = 0 2.25.358.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 145250323 2.25.358.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 2.25.422.678 I slot launch_slot_: id 0 | task 16960 | processing task, is_child = 0 2.26.931.455 I slot print_timing: id 0 | task 16960 | prompt eval time = 106.70 ms / 337 tokens ( 0.32 ms per token, 3158.42 tokens per second) 2.26.931.461 I slot print_timing: id 0 | task 16960 | eval time = 1402.06 ms / 212 tokens ( 6.64 ms per token, 150.49 tokens per second) 2.26.931.462 I slot print_timing: id 0 | task 16960 | total time = 1508.76 ms / 549 tokens 2.26.931.463 I slot print_timing: id 0 | task 16960 | graphs reused = 16234 2.26.931.464 I slot print_timing: id 0 | task 16960 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.931.495 I slot release: id 0 | task 16960 | stop processing: n_tokens = 580, truncated = 0 2.26.945.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 146840692 2.26.945.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 2.27.015.847 I slot launch_slot_: id 0 | task 17175 | processing task, is_child = 0 2.27.650.494 I slot print_timing: id 0 | task 17175 | prompt eval time = 108.32 ms / 325 tokens ( 0.33 ms per token, 3000.40 tokens per second) 2.27.650.500 I slot print_timing: id 0 | task 17175 | eval time = 526.31 ms / 80 tokens ( 6.66 ms per token, 150.10 tokens per second) 2.27.650.503 I slot print_timing: id 0 | task 17175 | total time = 634.63 ms / 405 tokens 2.27.650.503 I slot print_timing: id 0 | task 17175 | graphs reused = 16312 2.27.650.504 I slot print_timing: id 0 | task 17175 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.650.533 I slot release: id 0 | task 17175 | stop processing: n_tokens = 436, truncated = 0 2.27.676.488 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.073 2.27.718.728 I slot launch_slot_: id 0 | task 17258 | processing task, is_child = 0 2.28.935.581 I slot print_timing: id 0 | task 17258 | prompt eval time = 96.12 ms / 264 tokens ( 0.36 ms per token, 2746.57 tokens per second) 2.28.935.586 I slot print_timing: id 0 | task 17258 | eval time = 1120.71 ms / 170 tokens ( 6.63 ms per token, 150.80 tokens per second) 2.28.935.587 I slot print_timing: id 0 | task 17258 | total time = 1216.83 ms / 434 tokens 2.28.935.588 I slot print_timing: id 0 | task 17258 | graphs reused = 16480 2.28.935.589 I slot print_timing: id 0 | task 17258 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.935.611 I slot release: id 0 | task 17258 | stop processing: n_tokens = 465, truncated = 0 2.28.955.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 148844808 2.28.955.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 2.29.031.078 I slot launch_slot_: id 0 | task 17431 | processing task, is_child = 0 2.29.194.038 I slot print_timing: id 0 | task 17431 | prompt eval time = 105.67 ms / 331 tokens ( 0.32 ms per token, 3132.39 tokens per second) 2.29.194.044 I slot print_timing: id 0 | task 17431 | eval time = 57.27 ms / 9 tokens ( 7.16 ms per token, 139.69 tokens per second) 2.29.194.045 I slot print_timing: id 0 | task 17431 | total time = 162.94 ms / 340 tokens 2.29.194.046 I slot print_timing: id 0 | task 17431 | graphs reused = 16487 2.29.194.047 I slot print_timing: id 0 | task 17431 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.194.075 I slot release: id 0 | task 17431 | stop processing: n_tokens = 371, truncated = 0 2.29.220.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 371, t_last = 149103272 2.29.220.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 2.29.297.703 I slot launch_slot_: id 0 | task 17443 | processing task, is_child = 0 2.30.075.540 I slot print_timing: id 0 | task 17443 | prompt eval time = 106.30 ms / 333 tokens ( 0.32 ms per token, 3132.61 tokens per second) 2.30.075.546 I slot print_timing: id 0 | task 17443 | eval time = 671.52 ms / 102 tokens ( 6.65 ms per token, 150.41 tokens per second) 2.30.075.547 I slot print_timing: id 0 | task 17443 | total time = 777.82 ms / 435 tokens 2.30.075.548 I slot print_timing: id 0 | task 17443 | graphs reused = 16587 2.30.075.549 I slot print_timing: id 0 | task 17443 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.075.575 I slot release: id 0 | task 17443 | stop processing: n_tokens = 466, truncated = 0 2.30.094.285 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 149984772 2.30.094.331 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 2.30.171.567 I slot launch_slot_: id 0 | task 17548 | processing task, is_child = 0 2.33.285.370 I slot print_timing: id 0 | task 17548 | n_gen = 453, tg = 150.52 t/s, tg_3s = 150.86 t/s 2.34.966.441 I slot print_timing: id 0 | task 17548 | prompt eval time = 110.95 ms / 346 tokens ( 0.32 ms per token, 3118.58 tokens per second) 2.34.966.447 I slot print_timing: id 0 | task 17548 | eval time = 4683.90 ms / 704 tokens ( 6.66 ms per token, 150.09 tokens per second) 2.34.966.448 I slot print_timing: id 0 | task 17548 | total time = 4794.85 ms / 1050 tokens 2.34.966.448 I slot print_timing: id 0 | task 17548 | graphs reused = 17286 2.34.966.449 I slot print_timing: id 0 | task 17548 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.966.479 I slot release: id 0 | task 17548 | stop processing: n_tokens = 1081, truncated = 0 2.34.987.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1081, t_last = 154875676 2.34.987.663 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 2.35.068.980 I slot launch_slot_: id 0 | task 18255 | processing task, is_child = 0 2.35.438.441 I slot print_timing: id 0 | task 18255 | prompt eval time = 107.51 ms / 325 tokens ( 0.33 ms per token, 3023.00 tokens per second) 2.35.438.446 I slot print_timing: id 0 | task 18255 | eval time = 261.93 ms / 40 tokens ( 6.72 ms per token, 148.89 tokens per second) 2.35.438.447 I slot print_timing: id 0 | task 18255 | total time = 369.44 ms / 365 tokens 2.35.438.448 I slot print_timing: id 0 | task 18255 | graphs reused = 17324 2.35.438.449 I slot print_timing: id 0 | task 18255 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.438.475 I slot release: id 0 | task 18255 | stop processing: n_tokens = 396, truncated = 0 2.35.453.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 155347673 2.35.453.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 2.35.521.104 I slot launch_slot_: id 0 | task 18298 | processing task, is_child = 0 2.36.909.418 I slot print_timing: id 0 | task 18298 | prompt eval time = 105.71 ms / 322 tokens ( 0.33 ms per token, 3046.04 tokens per second) 2.36.909.423 I slot print_timing: id 0 | task 18298 | eval time = 1282.58 ms / 194 tokens ( 6.65 ms per token, 150.48 tokens per second) 2.36.909.424 I slot print_timing: id 0 | task 18298 | total time = 1388.29 ms / 516 tokens 2.36.909.425 I slot print_timing: id 0 | task 18298 | graphs reused = 17515 2.36.909.426 I slot print_timing: id 0 | task 18298 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.909.453 I slot release: id 0 | task 18298 | stop processing: n_tokens = 547, truncated = 0 2.36.937.621 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 156818650 2.36.937.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 2.37.010.171 I slot launch_slot_: id 0 | task 18495 | processing task, is_child = 0 2.38.982.172 I slot print_timing: id 0 | task 18495 | prompt eval time = 107.61 ms / 338 tokens ( 0.32 ms per token, 3140.91 tokens per second) 2.38.982.178 I slot print_timing: id 0 | task 18495 | eval time = 1864.37 ms / 282 tokens ( 6.63 ms per token, 150.72 tokens per second) 2.38.982.179 I slot print_timing: id 0 | task 18495 | total time = 1971.98 ms / 620 tokens 2.38.982.180 I slot print_timing: id 0 | task 18495 | graphs reused = 17794 2.38.982.181 I slot print_timing: id 0 | task 18495 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.982.209 I slot release: id 0 | task 18495 | stop processing: n_tokens = 651, truncated = 0 2.39.000.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 651, t_last = 158891407 2.39.044.046 I slot launch_slot_: id 0 | task 18780 | processing task, is_child = 0 2.42.151.362 I slot print_timing: id 0 | task 18780 | n_gen = 453, tg = 150.66 t/s, tg_3s = 150.99 t/s 2.45.151.504 I slot print_timing: id 0 | task 18780 | n_gen = 904, tg = 150.49 t/s, tg_3s = 150.33 t/s 2.45.948.845 I slot print_timing: id 0 | task 18780 | prompt eval time = 107.12 ms / 347 tokens ( 0.31 ms per token, 3239.33 tokens per second) 2.45.948.851 I slot print_timing: id 0 | task 18780 | eval time = 6797.65 ms / 1024 tokens ( 6.64 ms per token, 150.49 tokens per second) 2.45.948.852 I slot print_timing: id 0 | task 18780 | total time = 6904.77 ms / 1371 tokens 2.45.948.853 I slot print_timing: id 0 | task 18780 | graphs reused = 18812 2.45.948.854 I slot print_timing: id 0 | task 18780 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.948.883 I slot release: id 0 | task 18780 | stop processing: n_tokens = 1402, truncated = 0 2.45.974.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 165858080 2.45.974.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 2.46.064.179 I slot launch_slot_: id 0 | task 19807 | processing task, is_child = 0 2.47.575.244 I slot print_timing: id 0 | task 19807 | prompt eval time = 108.82 ms / 331 tokens ( 0.33 ms per token, 3041.69 tokens per second) 2.47.575.250 I slot print_timing: id 0 | task 19807 | eval time = 1402.22 ms / 212 tokens ( 6.65 ms per token, 150.48 tokens per second) 2.47.575.251 I slot print_timing: id 0 | task 19807 | total time = 1511.05 ms / 543 tokens 2.47.575.252 I slot print_timing: id 0 | task 19807 | graphs reused = 19021 2.47.575.252 I slot print_timing: id 0 | task 19807 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.575.278 I slot release: id 0 | task 19807 | stop processing: n_tokens = 574, truncated = 0 2.47.592.669 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 574, t_last = 167484475 2.47.592.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 2.47.674.308 I slot launch_slot_: id 0 | task 20022 | processing task, is_child = 0 2.48.371.921 I slot print_timing: id 0 | task 20022 | prompt eval time = 106.40 ms / 345 tokens ( 0.31 ms per token, 3242.54 tokens per second) 2.48.371.926 I slot print_timing: id 0 | task 20022 | eval time = 591.19 ms / 90 tokens ( 6.64 ms per token, 150.54 tokens per second) 2.48.371.927 I slot print_timing: id 0 | task 20022 | total time = 697.59 ms / 435 tokens 2.48.371.928 I slot print_timing: id 0 | task 20022 | graphs reused = 19109 2.48.371.929 I slot print_timing: id 0 | task 20022 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.371.956 I slot release: id 0 | task 20022 | stop processing: n_tokens = 466, truncated = 0 2.48.394.111 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 168281154 2.48.394.155 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 2.48.470.137 I slot launch_slot_: id 0 | task 20115 | processing task, is_child = 0 2.49.016.587 I slot print_timing: id 0 | task 20115 | prompt eval time = 106.15 ms / 320 tokens ( 0.33 ms per token, 3014.49 tokens per second) 2.49.016.594 I slot print_timing: id 0 | task 20115 | eval time = 440.28 ms / 67 tokens ( 6.67 ms per token, 149.91 tokens per second) 2.49.016.595 I slot print_timing: id 0 | task 20115 | total time = 546.43 ms / 387 tokens 2.49.016.595 I slot print_timing: id 0 | task 20115 | graphs reused = 19174 2.49.016.596 I slot print_timing: id 0 | task 20115 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.016.623 I slot release: id 0 | task 20115 | stop processing: n_tokens = 418, truncated = 0 2.49.032.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 168925820 2.49.033.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 2.49.105.937 I slot launch_slot_: id 0 | task 20185 | processing task, is_child = 0 2.49.545.572 I slot print_timing: id 0 | task 20185 | prompt eval time = 104.25 ms / 297 tokens ( 0.35 ms per token, 2849.06 tokens per second) 2.49.545.578 I slot print_timing: id 0 | task 20185 | eval time = 335.37 ms / 47 tokens ( 7.29 ms per token, 137.16 tokens per second) 2.49.545.579 I slot print_timing: id 0 | task 20185 | total time = 439.62 ms / 344 tokens 2.49.545.580 I slot print_timing: id 0 | task 20185 | graphs reused = 19219 2.49.545.581 I slot print_timing: id 0 | task 20185 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.545.606 I slot release: id 0 | task 20185 | stop processing: n_tokens = 375, truncated = 0 2.49.567.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 169454803 2.49.567.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 2.49.636.528 I slot launch_slot_: id 0 | task 20235 | processing task, is_child = 0 2.50.460.644 I slot print_timing: id 0 | task 20235 | prompt eval time = 107.86 ms / 343 tokens ( 0.31 ms per token, 3179.90 tokens per second) 2.50.460.650 I slot print_timing: id 0 | task 20235 | eval time = 716.23 ms / 109 tokens ( 6.63 ms per token, 150.79 tokens per second) 2.50.460.651 I slot print_timing: id 0 | task 20235 | total time = 824.10 ms / 452 tokens 2.50.460.652 I slot print_timing: id 0 | task 20235 | graphs reused = 19326 2.50.460.653 I slot print_timing: id 0 | task 20235 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.460.680 I slot release: id 0 | task 20235 | stop processing: n_tokens = 483, truncated = 0 2.50.487.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 170369877 2.50.529.969 I slot launch_slot_: id 0 | task 20347 | processing task, is_child = 0 2.51.535.073 I slot print_timing: id 0 | task 20347 | prompt eval time = 110.52 ms / 371 tokens ( 0.30 ms per token, 3356.74 tokens per second) 2.51.535.079 I slot print_timing: id 0 | task 20347 | eval time = 894.56 ms / 132 tokens ( 6.83 ms per token, 146.44 tokens per second) 2.51.535.080 I slot print_timing: id 0 | task 20347 | total time = 1005.09 ms / 503 tokens 2.51.535.081 I slot print_timing: id 0 | task 20347 | graphs reused = 19455 2.51.535.082 I slot print_timing: id 0 | task 20347 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.535.112 I slot release: id 0 | task 20347 | stop processing: n_tokens = 534, truncated = 0 2.51.538.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 171444310 2.51.538.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 2.51.628.225 I slot launch_slot_: id 0 | task 20482 | processing task, is_child = 0 2.52.836.784 I slot print_timing: id 0 | task 20482 | prompt eval time = 104.93 ms / 292 tokens ( 0.36 ms per token, 2782.75 tokens per second) 2.52.836.791 I slot print_timing: id 0 | task 20482 | eval time = 1103.61 ms / 167 tokens ( 6.65 ms per token, 150.42 tokens per second) 2.52.836.792 I slot print_timing: id 0 | task 20482 | total time = 1208.54 ms / 459 tokens 2.52.836.793 I slot print_timing: id 0 | task 20482 | graphs reused = 19620 2.52.836.794 I slot print_timing: id 0 | task 20482 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.836.822 I slot release: id 0 | task 20482 | stop processing: n_tokens = 490, truncated = 0 2.52.857.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 172746019 2.52.857.669 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 2.52.951.649 I slot launch_slot_: id 0 | task 20652 | processing task, is_child = 0 2.53.553.765 I slot print_timing: id 0 | task 20652 | prompt eval time = 102.78 ms / 301 tokens ( 0.34 ms per token, 2928.67 tokens per second) 2.53.553.771 I slot print_timing: id 0 | task 20652 | eval time = 499.32 ms / 76 tokens ( 6.66 ms per token, 150.21 tokens per second) 2.53.553.771 I slot print_timing: id 0 | task 20652 | total time = 602.09 ms / 377 tokens 2.53.553.774 I slot print_timing: id 0 | task 20652 | graphs reused = 19694 2.53.553.774 I slot print_timing: id 0 | task 20652 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.553.799 I slot release: id 0 | task 20652 | stop processing: n_tokens = 408, truncated = 0 2.53.574.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 173462997 2.53.575.035 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 2.53.656.232 I slot launch_slot_: id 0 | task 20731 | processing task, is_child = 0 2.54.285.449 I slot print_timing: id 0 | task 20731 | prompt eval time = 102.63 ms / 303 tokens ( 0.34 ms per token, 2952.38 tokens per second) 2.54.285.454 I slot print_timing: id 0 | task 20731 | eval time = 526.57 ms / 80 tokens ( 6.67 ms per token, 150.03 tokens per second) 2.54.285.455 I slot print_timing: id 0 | task 20731 | total time = 629.20 ms / 383 tokens 2.54.285.457 I slot print_timing: id 0 | task 20731 | graphs reused = 19772 2.54.285.458 I slot print_timing: id 0 | task 20731 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.285.483 I slot release: id 0 | task 20731 | stop processing: n_tokens = 414, truncated = 0 2.54.305.643 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 174194680 2.54.305.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 2.54.386.159 I slot launch_slot_: id 0 | task 20814 | processing task, is_child = 0 2.54.707.981 I slot print_timing: id 0 | task 20814 | prompt eval time = 106.39 ms / 321 tokens ( 0.33 ms per token, 3017.34 tokens per second) 2.54.707.986 I slot print_timing: id 0 | task 20814 | eval time = 215.42 ms / 33 tokens ( 6.73 ms per token, 148.55 tokens per second) 2.54.707.987 I slot print_timing: id 0 | task 20814 | total time = 321.80 ms / 354 tokens 2.54.707.989 I slot print_timing: id 0 | task 20814 | graphs reused = 19803 2.54.707.989 I slot print_timing: id 0 | task 20814 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.708.016 I slot release: id 0 | task 20814 | stop processing: n_tokens = 385, truncated = 0 2.54.724.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 174617213 2.54.724.936 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.080 MiB) 2.54.795.314 I slot launch_slot_: id 0 | task 20850 | processing task, is_child = 0 2.55.293.815 I slot print_timing: id 0 | task 20850 | prompt eval time = 110.86 ms / 322 tokens ( 0.34 ms per token, 2904.46 tokens per second) 2.55.293.821 I slot print_timing: id 0 | task 20850 | eval time = 387.62 ms / 59 tokens ( 6.68 ms per token, 149.63 tokens per second) 2.55.293.822 I slot print_timing: id 0 | task 20850 | total time = 498.48 ms / 381 tokens 2.55.293.824 I slot print_timing: id 0 | task 20850 | graphs reused = 19860 2.55.293.825 I slot print_timing: id 0 | task 20850 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.293.852 I slot release: id 0 | task 20850 | stop processing: n_tokens = 412, truncated = 0 2.55.318.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 175203049 2.55.318.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.451 MiB) 2.55.386.549 I slot launch_slot_: id 0 | task 20912 | processing task, is_child = 0 2.56.428.584 I slot print_timing: id 0 | task 20912 | prompt eval time = 106.40 ms / 323 tokens ( 0.33 ms per token, 3035.66 tokens per second) 2.56.428.590 I slot print_timing: id 0 | task 20912 | eval time = 935.61 ms / 142 tokens ( 6.64 ms per token, 150.70 tokens per second) 2.56.428.592 I slot print_timing: id 0 | task 20912 | total time = 1042.02 ms / 465 tokens 2.56.428.593 I slot print_timing: id 0 | task 20912 | graphs reused = 20000 2.56.428.594 I slot print_timing: id 0 | task 20912 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.428.623 I slot release: id 0 | task 20912 | stop processing: n_tokens = 496, truncated = 0 2.56.457.099 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 176337821 2.56.457.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.673 MiB) 2.56.522.160 I slot launch_slot_: id 0 | task 21057 | processing task, is_child = 0 2.59.633.366 I slot print_timing: id 0 | task 21057 | n_gen = 453, tg = 150.41 t/s, tg_3s = 150.74 t/s 3.01.623.890 I slot print_timing: id 0 | task 21057 | prompt eval time = 106.08 ms / 321 tokens ( 0.33 ms per token, 3026.02 tokens per second) 3.01.623.896 I slot print_timing: id 0 | task 21057 | eval time = 4995.63 ms / 752 tokens ( 6.65 ms per token, 150.33 tokens per second) 3.01.623.897 I slot print_timing: id 0 | task 21057 | total time = 5101.71 ms / 1073 tokens 3.01.623.897 I slot print_timing: id 0 | task 21057 | graphs reused = 20747 3.01.623.898 I slot print_timing: id 0 | task 21057 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.623.924 I slot release: id 0 | task 21057 | stop processing: n_tokens = 1104, truncated = 0 3.01.648.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1104, t_last = 181533121 3.01.649.031 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.607 MiB) 3.01.719.088 I slot launch_slot_: id 0 | task 21812 | processing task, is_child = 0 3.04.827.922 I slot print_timing: id 0 | task 21812 | n_gen = 453, tg = 150.47 t/s, tg_3s = 150.80 t/s 3.07.830.758 I slot print_timing: id 0 | task 21812 | n_gen = 905, tg = 150.50 t/s, tg_3s = 150.52 t/s 3.08.626.208 I slot print_timing: id 0 | task 21812 | prompt eval time = 104.81 ms / 322 tokens ( 0.33 ms per token, 3072.26 tokens per second) 3.08.626.214 I slot print_timing: id 0 | task 21812 | eval time = 6802.29 ms / 1024 tokens ( 6.65 ms per token, 150.39 tokens per second) 3.08.626.215 I slot print_timing: id 0 | task 21812 | total time = 6907.10 ms / 1346 tokens 3.08.626.216 I slot print_timing: id 0 | task 21812 | graphs reused = 21765 3.08.626.217 I slot print_timing: id 0 | task 21812 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.626.249 I slot release: id 0 | task 21812 | stop processing: n_tokens = 1377, truncated = 0 3.08.644.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1377, t_last = 188535446 3.08.644.419 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 3.08.718.669 I slot launch_slot_: id 0 | task 22839 | processing task, is_child = 0 3.09.127.947 I slot print_timing: id 0 | task 22839 | prompt eval time = 107.20 ms / 337 tokens ( 0.32 ms per token, 3143.74 tokens per second) 3.09.127.953 I slot print_timing: id 0 | task 22839 | eval time = 302.06 ms / 46 tokens ( 6.71 ms per token, 148.98 tokens per second) 3.09.127.954 I slot print_timing: id 0 | task 22839 | total time = 409.26 ms / 383 tokens 3.09.127.955 I slot print_timing: id 0 | task 22839 | graphs reused = 21809 3.09.127.956 I slot print_timing: id 0 | task 22839 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.127.985 I slot release: id 0 | task 22839 | stop processing: n_tokens = 414, truncated = 0 3.09.143.140 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 189037182 3.09.143.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.09.210.205 I slot launch_slot_: id 0 | task 22888 | processing task, is_child = 0 3.09.625.603 I slot print_timing: id 0 | task 22888 | prompt eval time = 106.65 ms / 325 tokens ( 0.33 ms per token, 3047.35 tokens per second) 3.09.625.609 I slot print_timing: id 0 | task 22888 | eval time = 308.73 ms / 47 tokens ( 6.71 ms per token, 149.00 tokens per second) 3.09.625.611 I slot print_timing: id 0 | task 22888 | total time = 415.38 ms / 372 tokens 3.09.625.611 I slot print_timing: id 0 | task 22888 | graphs reused = 21854 3.09.625.613 I slot print_timing: id 0 | task 22888 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.625.644 I slot release: id 0 | task 22888 | stop processing: n_tokens = 403, truncated = 0 3.09.643.778 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 189534841 3.09.643.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.642 MiB) 3.09.710.580 I slot launch_slot_: id 0 | task 22938 | processing task, is_child = 0 3.10.158.093 I slot print_timing: id 0 | task 22938 | prompt eval time = 106.68 ms / 331 tokens ( 0.32 ms per token, 3102.80 tokens per second) 3.10.158.099 I slot print_timing: id 0 | task 22938 | eval time = 340.81 ms / 52 tokens ( 6.68 ms per token, 149.64 tokens per second) 3.10.158.100 I slot print_timing: id 0 | task 22938 | total time = 447.49 ms / 383 tokens 3.10.158.101 I slot print_timing: id 0 | task 22938 | graphs reused = 21904 3.10.158.101 I slot print_timing: id 0 | task 22938 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.158.128 I slot release: id 0 | task 22938 | stop processing: n_tokens = 414, truncated = 0 3.10.174.938 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 190067325 3.10.174.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.139 MiB) 3.10.240.974 I slot launch_slot_: id 0 | task 22993 | processing task, is_child = 0 3.10.979.696 I slot print_timing: id 0 | task 22993 | prompt eval time = 107.46 ms / 336 tokens ( 0.32 ms per token, 3126.72 tokens per second) 3.10.979.703 I slot print_timing: id 0 | task 22993 | eval time = 631.24 ms / 96 tokens ( 6.64 ms per token, 150.50 tokens per second) 3.10.979.704 I slot print_timing: id 0 | task 22993 | total time = 738.70 ms / 432 tokens 3.10.979.704 I slot print_timing: id 0 | task 22993 | graphs reused = 21998 3.10.979.705 I slot print_timing: id 0 | task 22993 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.979.732 I slot release: id 0 | task 22993 | stop processing: n_tokens = 463, truncated = 0 3.11.001.053 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 190888929 3.11.001.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.046 MiB) 3.11.067.447 I slot launch_slot_: id 0 | task 23092 | processing task, is_child = 0 3.11.298.278 I slot print_timing: id 0 | task 23092 | prompt eval time = 107.59 ms / 349 tokens ( 0.31 ms per token, 3243.74 tokens per second) 3.11.298.284 I slot print_timing: id 0 | task 23092 | eval time = 123.22 ms / 19 tokens ( 6.85 ms per token, 146.08 tokens per second) 3.11.298.285 I slot print_timing: id 0 | task 23092 | total time = 230.81 ms / 368 tokens 3.11.298.286 I slot print_timing: id 0 | task 23092 | graphs reused = 22015 3.11.298.287 I slot print_timing: id 0 | task 23092 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.298.314 I slot release: id 0 | task 23092 | stop processing: n_tokens = 399, truncated = 0 3.11.327.250 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 191207511 3.11.327.284 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.106 MiB) 3.11.403.299 I slot launch_slot_: id 0 | task 23114 | processing task, is_child = 0 3.14.513.570 I slot print_timing: id 0 | task 23114 | n_gen = 453, tg = 150.51 t/s, tg_3s = 150.84 t/s 3.16.887.307 I slot print_timing: id 0 | task 23114 | prompt eval time = 107.05 ms / 336 tokens ( 0.32 ms per token, 3138.60 tokens per second) 3.16.887.312 I slot print_timing: id 0 | task 23114 | eval time = 5376.93 ms / 810 tokens ( 6.65 ms per token, 150.46 tokens per second) 3.16.887.313 I slot print_timing: id 0 | task 23114 | total time = 5483.99 ms / 1146 tokens 3.16.887.314 I slot print_timing: id 0 | task 23114 | graphs reused = 22820 3.16.887.315 I slot print_timing: id 0 | task 23114 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.887.345 I slot release: id 0 | task 23114 | stop processing: n_tokens = 1177, truncated = 0 3.16.916.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1177, t_last = 196796542 3.16.916.621 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.077 MiB) 3.16.989.386 I slot launch_slot_: id 0 | task 23927 | processing task, is_child = 0 3.20.098.248 I slot print_timing: id 0 | task 23927 | n_gen = 452, tg = 150.24 t/s, tg_3s = 150.58 t/s 3.20.343.165 I slot print_timing: id 0 | task 23927 | prompt eval time = 107.04 ms / 349 tokens ( 0.31 ms per token, 3260.37 tokens per second) 3.20.343.171 I slot print_timing: id 0 | task 23927 | eval time = 3246.72 ms / 489 tokens ( 6.65 ms per token, 150.31 tokens per second) 3.20.343.172 I slot print_timing: id 0 | task 23927 | total time = 3353.76 ms / 838 tokens 3.20.343.173 I slot print_timing: id 0 | task 23927 | graphs reused = 23305 3.20.343.174 I slot print_timing: id 0 | task 23927 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.343.205 I slot release: id 0 | task 23927 | stop processing: n_tokens = 869, truncated = 0 3.20.371.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 200252402 3.20.371.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 335.310 MiB) 3.20.445.506 I slot launch_slot_: id 0 | task 24419 | processing task, is_child = 0 3.20.934.699 I slot print_timing: id 0 | task 24419 | prompt eval time = 107.84 ms / 349 tokens ( 0.31 ms per token, 3236.34 tokens per second) 3.20.934.705 I slot print_timing: id 0 | task 24419 | eval time = 381.33 ms / 58 tokens ( 6.69 ms per token, 149.48 tokens per second) 3.20.934.706 I slot print_timing: id 0 | task 24419 | total time = 489.17 ms / 407 tokens 3.20.934.707 I slot print_timing: id 0 | task 24419 | graphs reused = 23361 3.20.934.708 I slot print_timing: id 0 | task 24419 | graph reallocs = 0 / 0 (same size) / (changed size) 3.20.934.734 I slot release: id 0 | task 24419 | stop processing: n_tokens = 438, truncated = 0 3.20.951.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 200843932 3.20.951.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 3.21.014.525 I slot launch_slot_: id 0 | task 24480 | processing task, is_child = 0 3.21.399.907 I slot print_timing: id 0 | task 24480 | prompt eval time = 111.13 ms / 385 tokens ( 0.29 ms per token, 3464.50 tokens per second) 3.21.399.912 I slot print_timing: id 0 | task 24480 | eval time = 274.24 ms / 42 tokens ( 6.69 ms per token, 149.51 tokens per second) 3.21.399.913 I slot print_timing: id 0 | task 24480 | total time = 385.37 ms / 427 tokens 3.21.399.914 I slot print_timing: id 0 | task 24480 | graphs reused = 23401 3.21.399.915 I slot print_timing: id 0 | task 24480 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.399.942 I slot release: id 0 | task 24480 | stop processing: n_tokens = 458, truncated = 0 3.21.418.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 201309139 3.21.418.973 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.610 MiB) 3.21.489.547 I slot launch_slot_: id 0 | task 24525 | processing task, is_child = 0 3.21.969.638 I slot print_timing: id 0 | task 24525 | prompt eval time = 105.96 ms / 328 tokens ( 0.32 ms per token, 3095.45 tokens per second) 3.21.969.644 I slot print_timing: id 0 | task 24525 | eval time = 374.11 ms / 57 tokens ( 6.68 ms per token, 149.69 tokens per second) 3.21.969.645 I slot print_timing: id 0 | task 24525 | total time = 480.07 ms / 385 tokens 3.21.969.645 I slot print_timing: id 0 | task 24525 | graphs reused = 23456 3.21.969.646 I slot print_timing: id 0 | task 24525 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.969.672 I slot release: id 0 | task 24525 | stop processing: n_tokens = 416, truncated = 0