$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-UD-Q4_K_XL.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.099.804 I srv llama_server: initializing ... 0.00.099.810 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.099.923 I srv init_listene: The UI is disabled 0.00.099.925 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.100.013 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) 0.00.103.066 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-UD-Q4_K_XL.gguf' 0.01.986.016 I cmn init: llama threadpool init, n_threads = 8 0.02.059.083 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.063.772 I srv llama_server: model loaded 0.02.063.779 I srv llama_server: listening on http://127.0.0.1:8089 0.02.582.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.583.081 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.112.248 I slot print_timing: id 0 | task 0 | prompt eval time = 158.96 ms / 368 tokens ( 0.43 ms per token, 2315.11 tokens per second) 0.03.112.253 I slot print_timing: id 0 | task 0 | eval time = 370.19 ms / 53 tokens ( 7.12 ms per token, 140.47 tokens per second) 0.03.112.254 I slot print_timing: id 0 | task 0 | total time = 529.15 ms / 421 tokens 0.03.112.260 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.03.112.261 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.112.289 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.03.138.921 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 3014411 0.03.168.324 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.03.553.623 I slot print_timing: id 0 | task 56 | prompt eval time = 95.33 ms / 322 tokens ( 0.30 ms per token, 3377.71 tokens per second) 0.03.553.628 I slot print_timing: id 0 | task 56 | eval time = 289.95 ms / 42 tokens ( 7.07 ms per token, 141.41 tokens per second) 0.03.553.629 I slot print_timing: id 0 | task 56 | total time = 385.28 ms / 364 tokens 0.03.553.630 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.03.553.631 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.553.656 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.03.574.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 3455777 0.03.600.401 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.03.987.232 I slot print_timing: id 0 | task 101 | prompt eval time = 93.34 ms / 365 tokens ( 0.26 ms per token, 3910.56 tokens per second) 0.03.987.238 I slot print_timing: id 0 | task 101 | eval time = 293.47 ms / 42 tokens ( 7.16 ms per token, 139.71 tokens per second) 0.03.987.239 I slot print_timing: id 0 | task 101 | total time = 386.81 ms / 407 tokens 0.03.987.240 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.03.987.241 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.987.283 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.04.014.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 3889404 0.04.040.381 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.04.429.856 I slot print_timing: id 0 | task 146 | prompt eval time = 93.79 ms / 397 tokens ( 0.24 ms per token, 4232.82 tokens per second) 0.04.429.861 I slot print_timing: id 0 | task 146 | eval time = 295.66 ms / 43 tokens ( 7.04 ms per token, 142.05 tokens per second) 0.04.429.862 I slot print_timing: id 0 | task 146 | total time = 389.45 ms / 440 tokens 0.04.429.863 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.04.429.864 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.429.900 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.04.449.339 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 0.04.475.228 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.04.942.455 I slot print_timing: id 0 | task 192 | prompt eval time = 96.17 ms / 383 tokens ( 0.25 ms per token, 3982.61 tokens per second) 0.04.942.461 I slot print_timing: id 0 | task 192 | eval time = 371.04 ms / 55 tokens ( 6.87 ms per token, 145.54 tokens per second) 0.04.942.462 I slot print_timing: id 0 | task 192 | total time = 467.21 ms / 438 tokens 0.04.942.463 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.04.942.464 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.04.942.493 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.04.965.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 4844614 0.04.998.450 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.05.463.768 I slot print_timing: id 0 | task 250 | prompt eval time = 92.65 ms / 372 tokens ( 0.25 ms per token, 4015.07 tokens per second) 0.05.463.774 I slot print_timing: id 0 | task 250 | eval time = 372.65 ms / 55 tokens ( 6.90 ms per token, 144.91 tokens per second) 0.05.463.775 I slot print_timing: id 0 | task 250 | total time = 465.30 ms / 427 tokens 0.05.463.776 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.05.463.777 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.463.806 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.05.480.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 5365927 0.05.508.033 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.05.987.437 I slot print_timing: id 0 | task 308 | prompt eval time = 101.58 ms / 422 tokens ( 0.24 ms per token, 4154.16 tokens per second) 0.05.987.442 I slot print_timing: id 0 | task 308 | eval time = 377.80 ms / 55 tokens ( 7.00 ms per token, 142.93 tokens per second) 0.05.987.443 I slot print_timing: id 0 | task 308 | total time = 479.38 ms / 477 tokens 0.05.987.444 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.05.987.445 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.987.478 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.06.012.613 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 5889600 0.06.039.137 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.06.648.565 I slot print_timing: id 0 | task 366 | prompt eval time = 103.92 ms / 470 tokens ( 0.22 ms per token, 4522.49 tokens per second) 0.06.648.571 I slot print_timing: id 0 | task 366 | eval time = 505.48 ms / 72 tokens ( 7.12 ms per token, 140.46 tokens per second) 0.06.648.572 I slot print_timing: id 0 | task 366 | total time = 609.41 ms / 542 tokens 0.06.648.572 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.06.648.573 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.648.607 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.06.676.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 6550728 0.06.702.796 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.07.125.459 I slot print_timing: id 0 | task 441 | prompt eval time = 92.64 ms / 345 tokens ( 0.27 ms per token, 3723.93 tokens per second) 0.07.125.464 I slot print_timing: id 0 | task 441 | eval time = 330.00 ms / 47 tokens ( 7.17 ms per token, 139.39 tokens per second) 0.07.125.466 I slot print_timing: id 0 | task 441 | total time = 422.64 ms / 392 tokens 0.07.125.467 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.07.125.467 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.125.495 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.07.142.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 7027616 0.07.169.610 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.07.539.778 I slot print_timing: id 0 | task 491 | prompt eval time = 91.43 ms / 364 tokens ( 0.25 ms per token, 3981.14 tokens per second) 0.07.539.784 I slot print_timing: id 0 | task 491 | eval time = 278.72 ms / 41 tokens ( 6.97 ms per token, 143.51 tokens per second) 0.07.539.785 I slot print_timing: id 0 | task 491 | total time = 370.15 ms / 405 tokens 0.07.539.786 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.07.539.787 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.539.815 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.07.558.607 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 7441936 0.07.585.137 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.08.960.796 I slot print_timing: id 0 | task 535 | prompt eval time = 93.70 ms / 376 tokens ( 0.25 ms per token, 4012.64 tokens per second) 0.08.960.802 I slot print_timing: id 0 | task 535 | eval time = 1281.94 ms / 185 tokens ( 6.97 ms per token, 143.53 tokens per second) 0.08.960.803 I slot print_timing: id 0 | task 535 | total time = 1375.64 ms / 561 tokens 0.08.960.804 I slot print_timing: id 0 | task 535 | graphs reused = 667 0.08.960.805 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.960.834 I slot release: id 0 | task 535 | stop processing: n_tokens = 560, truncated = 0 0.08.977.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 8862955 0.09.004.774 I slot launch_slot_: id 0 | task 723 | processing task, is_child = 0 0.09.416.481 I slot print_timing: id 0 | task 723 | prompt eval time = 94.54 ms / 412 tokens ( 0.23 ms per token, 4358.08 tokens per second) 0.09.416.487 I slot print_timing: id 0 | task 723 | eval time = 317.15 ms / 47 tokens ( 6.89 ms per token, 145.04 tokens per second) 0.09.416.488 I slot print_timing: id 0 | task 723 | total time = 411.69 ms / 459 tokens 0.09.416.489 I slot print_timing: id 0 | task 723 | graphs reused = 712 0.09.416.489 I slot print_timing: id 0 | task 723 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.416.521 I slot release: id 0 | task 723 | stop processing: n_tokens = 458, truncated = 0 0.09.443.495 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 9318642 0.09.470.626 I slot launch_slot_: id 0 | task 773 | processing task, is_child = 0 0.09.988.252 I slot print_timing: id 0 | task 773 | prompt eval time = 92.42 ms / 376 tokens ( 0.25 ms per token, 4068.34 tokens per second) 0.09.988.257 I slot print_timing: id 0 | task 773 | eval time = 425.19 ms / 62 tokens ( 6.97 ms per token, 143.47 tokens per second) 0.09.988.258 I slot print_timing: id 0 | task 773 | total time = 517.61 ms / 438 tokens 0.09.988.259 I slot print_timing: id 0 | task 773 | graphs reused = 772 0.09.988.260 I slot print_timing: id 0 | task 773 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.988.287 I slot release: id 0 | task 773 | stop processing: n_tokens = 437, truncated = 0 0.10.008.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 9890408 0.10.042.186 I slot launch_slot_: id 0 | task 838 | processing task, is_child = 0 0.10.498.172 I slot print_timing: id 0 | task 838 | prompt eval time = 94.92 ms / 378 tokens ( 0.25 ms per token, 3982.18 tokens per second) 0.10.498.177 I slot print_timing: id 0 | task 838 | eval time = 361.05 ms / 52 tokens ( 7.08 ms per token, 141.26 tokens per second) 0.10.498.178 I slot print_timing: id 0 | task 838 | total time = 455.97 ms / 430 tokens 0.10.498.179 I slot print_timing: id 0 | task 838 | graphs reused = 822 0.10.498.180 I slot print_timing: id 0 | task 838 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.498.210 I slot release: id 0 | task 838 | stop processing: n_tokens = 429, truncated = 0 0.10.524.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 10400331 0.10.550.408 I slot launch_slot_: id 0 | task 893 | processing task, is_child = 0 0.11.082.399 I slot print_timing: id 0 | task 893 | prompt eval time = 93.81 ms / 367 tokens ( 0.26 ms per token, 3912.25 tokens per second) 0.11.082.405 I slot print_timing: id 0 | task 893 | eval time = 438.16 ms / 58 tokens ( 7.69 ms per token, 130.09 tokens per second) 0.11.082.406 I slot print_timing: id 0 | task 893 | total time = 531.97 ms / 425 tokens 0.11.082.407 I slot print_timing: id 0 | task 893 | graphs reused = 878 0.11.082.408 I slot print_timing: id 0 | task 893 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.082.436 I slot release: id 0 | task 893 | stop processing: n_tokens = 424, truncated = 0 0.11.099.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 10984557 0.11.126.068 I slot launch_slot_: id 0 | task 954 | processing task, is_child = 0 0.11.565.335 I slot print_timing: id 0 | task 954 | prompt eval time = 90.84 ms / 347 tokens ( 0.26 ms per token, 3820.03 tokens per second) 0.11.565.341 I slot print_timing: id 0 | task 954 | eval time = 348.41 ms / 51 tokens ( 6.97 ms per token, 143.51 tokens per second) 0.11.565.343 I slot print_timing: id 0 | task 954 | total time = 439.25 ms / 398 tokens 0.11.565.344 I slot print_timing: id 0 | task 954 | graphs reused = 927 0.11.565.345 I slot print_timing: id 0 | task 954 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.565.374 I slot release: id 0 | task 954 | stop processing: n_tokens = 397, truncated = 0 0.11.582.642 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 11467495 0.11.609.043 I slot launch_slot_: id 0 | task 1008 | processing task, is_child = 0 0.14.366.845 I slot print_timing: id 0 | task 1008 | prompt eval time = 91.27 ms / 369 tokens ( 0.25 ms per token, 4042.99 tokens per second) 0.14.366.850 I slot print_timing: id 0 | task 1008 | eval time = 2666.52 ms / 386 tokens ( 6.93 ms per token, 144.38 tokens per second) 0.14.366.851 I slot print_timing: id 0 | task 1008 | total time = 2757.78 ms / 755 tokens 0.14.366.852 I slot print_timing: id 0 | task 1008 | graphs reused = 1310 0.14.366.853 I slot print_timing: id 0 | task 1008 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.366.882 I slot release: id 0 | task 1008 | stop processing: n_tokens = 754, truncated = 0 0.14.384.104 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 14269003 0.14.411.714 I slot launch_slot_: id 0 | task 1397 | processing task, is_child = 0 0.14.784.538 I slot print_timing: id 0 | task 1397 | prompt eval time = 91.32 ms / 352 tokens ( 0.26 ms per token, 3854.70 tokens per second) 0.14.784.544 I slot print_timing: id 0 | task 1397 | eval time = 281.49 ms / 41 tokens ( 7.04 ms per token, 142.10 tokens per second) 0.14.784.545 I slot print_timing: id 0 | task 1397 | total time = 372.81 ms / 393 tokens 0.14.784.546 I slot print_timing: id 0 | task 1397 | graphs reused = 1349 0.14.784.546 I slot print_timing: id 0 | task 1397 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.784.574 I slot release: id 0 | task 1397 | stop processing: n_tokens = 392, truncated = 0 0.14.803.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 14686695 0.14.829.190 I slot launch_slot_: id 0 | task 1441 | processing task, is_child = 0 0.15.206.555 I slot print_timing: id 0 | task 1441 | prompt eval time = 91.06 ms / 349 tokens ( 0.26 ms per token, 3832.64 tokens per second) 0.15.206.561 I slot print_timing: id 0 | task 1441 | eval time = 286.29 ms / 41 tokens ( 7.16 ms per token, 139.72 tokens per second) 0.15.206.562 I slot print_timing: id 0 | task 1441 | total time = 377.35 ms / 390 tokens 0.15.206.562 I slot print_timing: id 0 | task 1441 | graphs reused = 1388 0.15.206.563 I slot print_timing: id 0 | task 1441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.206.589 I slot release: id 0 | task 1441 | stop processing: n_tokens = 389, truncated = 0 0.15.221.794 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 389, t_last = 15108710 0.15.248.594 I slot launch_slot_: id 0 | task 1485 | processing task, is_child = 0 0.15.806.155 I slot print_timing: id 0 | task 1485 | prompt eval time = 93.54 ms / 384 tokens ( 0.24 ms per token, 4105.33 tokens per second) 0.15.806.160 I slot print_timing: id 0 | task 1485 | eval time = 464.00 ms / 63 tokens ( 7.48 ms per token, 133.62 tokens per second) 0.15.806.161 I slot print_timing: id 0 | task 1485 | total time = 557.54 ms / 447 tokens 0.15.806.162 I slot print_timing: id 0 | task 1485 | graphs reused = 1449 0.15.806.163 I slot print_timing: id 0 | task 1485 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.806.192 I slot release: id 0 | task 1485 | stop processing: n_tokens = 446, truncated = 0 0.15.824.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 15708313 0.15.850.630 I slot launch_slot_: id 0 | task 1551 | processing task, is_child = 0 0.16.308.752 I slot print_timing: id 0 | task 1551 | prompt eval time = 90.78 ms / 356 tokens ( 0.26 ms per token, 3921.44 tokens per second) 0.16.308.757 I slot print_timing: id 0 | task 1551 | eval time = 367.32 ms / 54 tokens ( 6.93 ms per token, 144.29 tokens per second) 0.16.308.759 I slot print_timing: id 0 | task 1551 | total time = 458.10 ms / 410 tokens 0.16.308.759 I slot print_timing: id 0 | task 1551 | graphs reused = 1501 0.16.308.760 I slot print_timing: id 0 | task 1551 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.308.787 I slot release: id 0 | task 1551 | stop processing: n_tokens = 409, truncated = 0 0.16.322.854 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 16210908 0.16.348.731 I slot launch_slot_: id 0 | task 1608 | processing task, is_child = 0 0.16.924.377 I slot print_timing: id 0 | task 1608 | prompt eval time = 96.53 ms / 410 tokens ( 0.24 ms per token, 4247.30 tokens per second) 0.16.924.385 I slot print_timing: id 0 | task 1608 | eval time = 479.09 ms / 70 tokens ( 6.94 ms per token, 144.02 tokens per second) 0.16.924.386 I slot print_timing: id 0 | task 1608 | total time = 575.63 ms / 480 tokens 0.16.924.387 I slot print_timing: id 0 | task 1608 | graphs reused = 1569 0.16.924.388 I slot print_timing: id 0 | task 1608 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.924.417 I slot release: id 0 | task 1608 | stop processing: n_tokens = 479, truncated = 0 0.16.950.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 16826538 0.16.976.236 I slot launch_slot_: id 0 | task 1681 | processing task, is_child = 0 0.17.377.482 I slot print_timing: id 0 | task 1681 | prompt eval time = 93.63 ms / 385 tokens ( 0.24 ms per token, 4111.75 tokens per second) 0.17.377.488 I slot print_timing: id 0 | task 1681 | eval time = 307.59 ms / 44 tokens ( 7.15 ms per token, 139.80 tokens per second) 0.17.377.489 I slot print_timing: id 0 | task 1681 | total time = 401.22 ms / 429 tokens 0.17.377.490 I slot print_timing: id 0 | task 1681 | graphs reused = 1611 0.17.377.491 I slot print_timing: id 0 | task 1681 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.377.526 I slot release: id 0 | task 1681 | stop processing: n_tokens = 428, truncated = 0 0.17.399.193 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 428, t_last = 17279647 0.17.428.969 I slot launch_slot_: id 0 | task 1728 | processing task, is_child = 0 0.18.013.069 I slot print_timing: id 0 | task 1728 | prompt eval time = 97.97 ms / 395 tokens ( 0.25 ms per token, 4031.72 tokens per second) 0.18.013.075 I slot print_timing: id 0 | task 1728 | eval time = 486.10 ms / 71 tokens ( 6.94 ms per token, 144.00 tokens per second) 0.18.013.076 I slot print_timing: id 0 | task 1728 | total time = 584.08 ms / 466 tokens 0.18.013.077 I slot print_timing: id 0 | task 1728 | graphs reused = 1680 0.18.013.078 I slot print_timing: id 0 | task 1728 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.013.110 I slot release: id 0 | task 1728 | stop processing: n_tokens = 465, truncated = 0 0.18.038.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 17915231 0.18.066.548 I slot launch_slot_: id 0 | task 1802 | processing task, is_child = 0 0.18.561.478 I slot print_timing: id 0 | task 1802 | prompt eval time = 96.05 ms / 430 tokens ( 0.22 ms per token, 4476.70 tokens per second) 0.18.561.484 I slot print_timing: id 0 | task 1802 | eval time = 398.86 ms / 59 tokens ( 6.88 ms per token, 145.42 tokens per second) 0.18.561.485 I slot print_timing: id 0 | task 1802 | total time = 494.91 ms / 489 tokens 0.18.561.486 I slot print_timing: id 0 | task 1802 | graphs reused = 1737 0.18.561.487 I slot print_timing: id 0 | task 1802 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.561.517 I slot release: id 0 | task 1802 | stop processing: n_tokens = 488, truncated = 0 0.18.565.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 488, t_last = 18463639 0.18.591.865 I slot launch_slot_: id 0 | task 1864 | processing task, is_child = 0 0.19.105.665 I slot print_timing: id 0 | task 1864 | prompt eval time = 95.14 ms / 392 tokens ( 0.24 ms per token, 4120.11 tokens per second) 0.19.105.671 I slot print_timing: id 0 | task 1864 | eval time = 418.64 ms / 62 tokens ( 6.86 ms per token, 145.71 tokens per second) 0.19.105.672 I slot print_timing: id 0 | task 1864 | total time = 513.78 ms / 454 tokens 0.19.105.673 I slot print_timing: id 0 | task 1864 | graphs reused = 1797 0.19.105.674 I slot print_timing: id 0 | task 1864 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.105.703 I slot release: id 0 | task 1864 | stop processing: n_tokens = 453, truncated = 0 0.19.130.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 19007824 0.19.156.724 I slot launch_slot_: id 0 | task 1929 | processing task, is_child = 0 0.19.575.008 I slot print_timing: id 0 | task 1929 | prompt eval time = 88.52 ms / 350 tokens ( 0.25 ms per token, 3953.86 tokens per second) 0.19.575.014 I slot print_timing: id 0 | task 1929 | eval time = 329.74 ms / 49 tokens ( 6.87 ms per token, 145.57 tokens per second) 0.19.575.015 I slot print_timing: id 0 | task 1929 | total time = 418.26 ms / 399 tokens 0.19.575.016 I slot print_timing: id 0 | task 1929 | graphs reused = 1844 0.19.575.017 I slot print_timing: id 0 | task 1929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.575.044 I slot release: id 0 | task 1929 | stop processing: n_tokens = 398, truncated = 0 0.19.601.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 19477165 0.19.638.710 I slot launch_slot_: id 0 | task 1981 | processing task, is_child = 0 0.20.142.450 I slot print_timing: id 0 | task 1981 | prompt eval time = 92.83 ms / 380 tokens ( 0.24 ms per token, 4093.42 tokens per second) 0.20.142.456 I slot print_timing: id 0 | task 1981 | eval time = 410.89 ms / 61 tokens ( 6.85 ms per token, 146.02 tokens per second) 0.20.142.457 I slot print_timing: id 0 | task 1981 | total time = 503.72 ms / 441 tokens 0.20.142.457 I slot print_timing: id 0 | task 1981 | graphs reused = 1903 0.20.142.458 I slot print_timing: id 0 | task 1981 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.142.487 I slot release: id 0 | task 1981 | stop processing: n_tokens = 440, truncated = 0 0.20.160.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 20044608 0.20.186.365 I slot launch_slot_: id 0 | task 2045 | processing task, is_child = 0 0.20.851.734 I slot print_timing: id 0 | task 2045 | prompt eval time = 96.25 ms / 410 tokens ( 0.23 ms per token, 4259.78 tokens per second) 0.20.851.740 I slot print_timing: id 0 | task 2045 | eval time = 569.10 ms / 80 tokens ( 7.20 ms per token, 138.82 tokens per second) 0.20.851.741 I slot print_timing: id 0 | task 2045 | total time = 665.35 ms / 490 tokens 0.20.851.742 I slot print_timing: id 0 | task 2045 | graphs reused = 1981 0.20.851.743 I slot print_timing: id 0 | task 2045 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.851.774 I slot release: id 0 | task 2045 | stop processing: n_tokens = 489, truncated = 0 0.20.873.976 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 20753895 0.20.899.758 I slot launch_slot_: id 0 | task 2128 | processing task, is_child = 0 0.21.451.291 I slot print_timing: id 0 | task 2128 | prompt eval time = 92.88 ms / 387 tokens ( 0.24 ms per token, 4166.85 tokens per second) 0.21.451.298 I slot print_timing: id 0 | task 2128 | eval time = 458.64 ms / 68 tokens ( 6.85 ms per token, 146.08 tokens per second) 0.21.451.299 I slot print_timing: id 0 | task 2128 | total time = 551.51 ms / 455 tokens 0.21.451.300 I slot print_timing: id 0 | task 2128 | graphs reused = 2047 0.21.451.301 I slot print_timing: id 0 | task 2128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.451.330 I slot release: id 0 | task 2128 | stop processing: n_tokens = 454, truncated = 0 0.21.468.097 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 21353451 0.21.494.739 I slot launch_slot_: id 0 | task 2199 | processing task, is_child = 0 0.21.982.316 I slot print_timing: id 0 | task 2199 | prompt eval time = 88.89 ms / 358 tokens ( 0.25 ms per token, 4027.22 tokens per second) 0.21.982.322 I slot print_timing: id 0 | task 2199 | eval time = 398.66 ms / 59 tokens ( 6.87 ms per token, 145.49 tokens per second) 0.21.982.323 I slot print_timing: id 0 | task 2199 | total time = 487.56 ms / 417 tokens 0.21.982.323 I slot print_timing: id 0 | task 2199 | graphs reused = 2104 0.21.982.324 I slot print_timing: id 0 | task 2199 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.982.352 I slot release: id 0 | task 2199 | stop processing: n_tokens = 416, truncated = 0 0.21.997.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 21884473 0.22.022.299 I slot launch_slot_: id 0 | task 2261 | processing task, is_child = 0 0.22.517.130 I slot print_timing: id 0 | task 2261 | prompt eval time = 89.02 ms / 359 tokens ( 0.25 ms per token, 4032.76 tokens per second) 0.22.517.136 I slot print_timing: id 0 | task 2261 | eval time = 405.79 ms / 56 tokens ( 7.38 ms per token, 135.54 tokens per second) 0.22.517.137 I slot print_timing: id 0 | task 2261 | total time = 494.81 ms / 415 tokens 0.22.517.138 I slot print_timing: id 0 | task 2261 | graphs reused = 2158 0.22.517.138 I slot print_timing: id 0 | task 2261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.517.165 I slot release: id 0 | task 2261 | stop processing: n_tokens = 414, truncated = 0 0.22.545.146 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 22419286 0.22.570.476 I slot launch_slot_: id 0 | task 2320 | processing task, is_child = 0 0.23.074.086 I slot print_timing: id 0 | task 2320 | prompt eval time = 92.17 ms / 387 tokens ( 0.24 ms per token, 4198.72 tokens per second) 0.23.074.092 I slot print_timing: id 0 | task 2320 | eval time = 411.42 ms / 61 tokens ( 6.86 ms per token, 145.84 tokens per second) 0.23.074.093 I slot print_timing: id 0 | task 2320 | total time = 503.59 ms / 448 tokens 0.23.074.094 I slot print_timing: id 0 | task 2320 | graphs reused = 2217 0.23.074.095 I slot print_timing: id 0 | task 2320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.074.122 I slot release: id 0 | task 2320 | stop processing: n_tokens = 447, truncated = 0 0.23.088.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 22976243 0.23.114.365 I slot launch_slot_: id 0 | task 2384 | processing task, is_child = 0 0.23.643.894 I slot print_timing: id 0 | task 2384 | prompt eval time = 93.89 ms / 410 tokens ( 0.23 ms per token, 4366.63 tokens per second) 0.23.643.900 I slot print_timing: id 0 | task 2384 | eval time = 435.61 ms / 61 tokens ( 7.26 ms per token, 137.74 tokens per second) 0.23.643.901 I slot print_timing: id 0 | task 2384 | total time = 529.51 ms / 471 tokens 0.23.643.902 I slot print_timing: id 0 | task 2384 | graphs reused = 2276 0.23.643.903 I slot print_timing: id 0 | task 2384 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.643.934 I slot release: id 0 | task 2384 | stop processing: n_tokens = 470, truncated = 0 0.23.666.147 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 23546055 0.23.692.483 I slot launch_slot_: id 0 | task 2448 | processing task, is_child = 0 0.24.117.715 I slot print_timing: id 0 | task 2448 | prompt eval time = 88.81 ms / 351 tokens ( 0.25 ms per token, 3952.17 tokens per second) 0.24.117.721 I slot print_timing: id 0 | task 2448 | eval time = 336.40 ms / 50 tokens ( 6.87 ms per token, 145.66 tokens per second) 0.24.117.722 I slot print_timing: id 0 | task 2448 | total time = 425.21 ms / 401 tokens 0.24.117.723 I slot print_timing: id 0 | task 2448 | graphs reused = 2324 0.24.117.723 I slot print_timing: id 0 | task 2448 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.117.758 I slot release: id 0 | task 2448 | stop processing: n_tokens = 400, truncated = 0 0.24.132.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 24019879 0.24.169.146 I slot launch_slot_: id 0 | task 2501 | processing task, is_child = 0 0.25.782.410 I slot print_timing: id 0 | task 2501 | prompt eval time = 92.21 ms / 393 tokens ( 0.23 ms per token, 4261.87 tokens per second) 0.25.782.416 I slot print_timing: id 0 | task 2501 | eval time = 1521.04 ms / 224 tokens ( 6.82 ms per token, 146.61 tokens per second) 0.25.782.417 I slot print_timing: id 0 | task 2501 | total time = 1613.25 ms / 617 tokens 0.25.782.418 I slot print_timing: id 0 | task 2501 | graphs reused = 2545 0.25.782.419 I slot print_timing: id 0 | task 2501 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.782.449 I slot release: id 0 | task 2501 | stop processing: n_tokens = 616, truncated = 0 0.25.799.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 25684570 0.25.826.307 I slot launch_slot_: id 0 | task 2728 | processing task, is_child = 0 0.26.115.022 I slot print_timing: id 0 | task 2728 | prompt eval time = 87.22 ms / 321 tokens ( 0.27 ms per token, 3680.14 tokens per second) 0.26.115.029 I slot print_timing: id 0 | task 2728 | eval time = 201.47 ms / 30 tokens ( 6.95 ms per token, 143.94 tokens per second) 0.26.115.030 I slot print_timing: id 0 | task 2728 | total time = 288.70 ms / 351 tokens 0.26.115.032 I slot print_timing: id 0 | task 2728 | graphs reused = 2573 0.26.115.033 I slot print_timing: id 0 | task 2728 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.115.060 I slot release: id 0 | task 2728 | stop processing: n_tokens = 350, truncated = 0 0.26.118.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 26017181 0.26.144.633 I slot launch_slot_: id 0 | task 2761 | processing task, is_child = 0 0.26.643.350 I slot print_timing: id 0 | task 2761 | prompt eval time = 87.56 ms / 330 tokens ( 0.27 ms per token, 3768.63 tokens per second) 0.26.643.358 I slot print_timing: id 0 | task 2761 | eval time = 411.12 ms / 61 tokens ( 6.85 ms per token, 145.94 tokens per second) 0.26.643.359 I slot print_timing: id 0 | task 2761 | total time = 498.69 ms / 391 tokens 0.26.643.360 I slot print_timing: id 0 | task 2761 | graphs reused = 2632 0.26.643.361 I slot print_timing: id 0 | task 2761 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.643.388 I slot release: id 0 | task 2761 | stop processing: n_tokens = 390, truncated = 0 0.26.660.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 26545509 0.26.686.066 I slot launch_slot_: id 0 | task 2825 | processing task, is_child = 0 0.26.990.579 I slot print_timing: id 0 | task 2825 | prompt eval time = 89.15 ms / 341 tokens ( 0.26 ms per token, 3824.89 tokens per second) 0.26.990.586 I slot print_timing: id 0 | task 2825 | eval time = 215.34 ms / 32 tokens ( 6.95 ms per token, 143.96 tokens per second) 0.26.990.588 I slot print_timing: id 0 | task 2825 | total time = 304.49 ms / 373 tokens 0.26.990.590 I slot print_timing: id 0 | task 2825 | graphs reused = 2662 0.26.990.590 I slot print_timing: id 0 | task 2825 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.990.620 I slot release: id 0 | task 2825 | stop processing: n_tokens = 372, truncated = 0 0.27.004.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 26892742 0.27.031.282 I slot launch_slot_: id 0 | task 2860 | processing task, is_child = 0 0.27.445.041 I slot print_timing: id 0 | task 2860 | prompt eval time = 91.32 ms / 338 tokens ( 0.27 ms per token, 3701.39 tokens per second) 0.27.445.047 I slot print_timing: id 0 | task 2860 | eval time = 322.43 ms / 48 tokens ( 6.86 ms per token, 145.77 tokens per second) 0.27.445.048 I slot print_timing: id 0 | task 2860 | total time = 413.74 ms / 386 tokens 0.27.445.049 I slot print_timing: id 0 | task 2860 | graphs reused = 2708 0.27.445.049 I slot print_timing: id 0 | task 2860 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.445.075 I slot release: id 0 | task 2860 | stop processing: n_tokens = 385, truncated = 0 0.27.462.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 27347196 0.27.489.414 I slot launch_slot_: id 0 | task 2911 | processing task, is_child = 0 0.27.959.962 I slot print_timing: id 0 | task 2911 | prompt eval time = 94.27 ms / 395 tokens ( 0.24 ms per token, 4190.00 tokens per second) 0.27.959.969 I slot print_timing: id 0 | task 2911 | eval time = 376.26 ms / 56 tokens ( 6.84 ms per token, 146.18 tokens per second) 0.27.959.970 I slot print_timing: id 0 | task 2911 | total time = 470.53 ms / 451 tokens 0.27.959.971 I slot print_timing: id 0 | task 2911 | graphs reused = 2762 0.27.959.972 I slot print_timing: id 0 | task 2911 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.960.004 I slot release: id 0 | task 2911 | stop processing: n_tokens = 450, truncated = 0 0.27.978.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 27862125 0.28.003.932 I slot launch_slot_: id 0 | task 2970 | processing task, is_child = 0 0.28.696.181 I slot print_timing: id 0 | task 2970 | prompt eval time = 130.65 ms / 528 tokens ( 0.25 ms per token, 4041.49 tokens per second) 0.28.696.188 I slot print_timing: id 0 | task 2970 | eval time = 561.58 ms / 83 tokens ( 6.85 ms per token, 146.02 tokens per second) 0.28.696.189 I slot print_timing: id 0 | task 2970 | total time = 692.23 ms / 611 tokens 0.28.696.190 I slot print_timing: id 0 | task 2970 | graphs reused = 2843 0.28.696.191 I slot print_timing: id 0 | task 2970 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.696.229 I slot release: id 0 | task 2970 | stop processing: n_tokens = 610, truncated = 0 0.28.720.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 28598350 0.28.752.299 I slot launch_slot_: id 0 | task 3057 | processing task, is_child = 0 0.29.162.759 I slot print_timing: id 0 | task 3057 | prompt eval time = 106.92 ms / 331 tokens ( 0.32 ms per token, 3095.89 tokens per second) 0.29.162.765 I slot print_timing: id 0 | task 3057 | eval time = 303.52 ms / 45 tokens ( 6.90 ms per token, 144.96 tokens per second) 0.29.162.766 I slot print_timing: id 0 | task 3057 | total time = 410.44 ms / 376 tokens 0.29.162.766 I slot print_timing: id 0 | task 3057 | graphs reused = 2886 0.29.162.767 I slot print_timing: id 0 | task 3057 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.162.795 I slot release: id 0 | task 3057 | stop processing: n_tokens = 387, truncated = 0 0.29.184.393 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 29064916 0.29.216.790 I slot launch_slot_: id 0 | task 3105 | processing task, is_child = 0 0.29.683.637 I slot print_timing: id 0 | task 3105 | prompt eval time = 110.45 ms / 362 tokens ( 0.31 ms per token, 3277.41 tokens per second) 0.29.683.642 I slot print_timing: id 0 | task 3105 | eval time = 356.37 ms / 53 tokens ( 6.85 ms per token, 145.91 tokens per second) 0.29.683.643 I slot print_timing: id 0 | task 3105 | total time = 466.83 ms / 415 tokens 0.29.683.644 I slot print_timing: id 0 | task 3105 | graphs reused = 2937 0.29.683.645 I slot print_timing: id 0 | task 3105 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.683.674 I slot release: id 0 | task 3105 | stop processing: n_tokens = 426, truncated = 0 0.29.699.288 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 29585795 0.29.730.664 I slot launch_slot_: id 0 | task 3161 | processing task, is_child = 0 0.30.310.866 I slot print_timing: id 0 | task 3161 | prompt eval time = 114.14 ms / 419 tokens ( 0.27 ms per token, 3670.83 tokens per second) 0.30.310.872 I slot print_timing: id 0 | task 3161 | eval time = 466.04 ms / 69 tokens ( 6.85 ms per token, 145.91 tokens per second) 0.30.310.873 I slot print_timing: id 0 | task 3161 | total time = 580.18 ms / 488 tokens 0.30.310.874 I slot print_timing: id 0 | task 3161 | graphs reused = 3004 0.30.310.875 I slot print_timing: id 0 | task 3161 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.310.906 I slot release: id 0 | task 3161 | stop processing: n_tokens = 499, truncated = 0 0.30.336.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 30213027 0.30.368.303 I slot launch_slot_: id 0 | task 3233 | processing task, is_child = 0 0.31.035.136 I slot print_timing: id 0 | task 3233 | prompt eval time = 118.43 ms / 423 tokens ( 0.28 ms per token, 3571.61 tokens per second) 0.31.035.142 I slot print_timing: id 0 | task 3233 | eval time = 548.38 ms / 72 tokens ( 7.72 ms per token, 129.47 tokens per second) 0.31.035.143 I slot print_timing: id 0 | task 3233 | total time = 666.81 ms / 495 tokens 0.31.035.144 I slot print_timing: id 0 | task 3233 | graphs reused = 3074 0.31.035.145 I slot print_timing: id 0 | task 3233 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.035.178 I slot release: id 0 | task 3233 | stop processing: n_tokens = 506, truncated = 0 0.31.053.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 30937299 0.31.085.990 I slot launch_slot_: id 0 | task 3308 | processing task, is_child = 0 0.31.482.220 I slot print_timing: id 0 | task 3308 | prompt eval time = 107.07 ms / 341 tokens ( 0.31 ms per token, 3184.92 tokens per second) 0.31.482.226 I slot print_timing: id 0 | task 3308 | eval time = 289.14 ms / 43 tokens ( 6.88 ms per token, 145.26 tokens per second) 0.31.482.226 I slot print_timing: id 0 | task 3308 | total time = 396.21 ms / 384 tokens 0.31.482.227 I slot print_timing: id 0 | task 3308 | graphs reused = 3115 0.31.482.228 I slot print_timing: id 0 | task 3308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.482.255 I slot release: id 0 | task 3308 | stop processing: n_tokens = 395, truncated = 0 0.31.504.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 31384376 0.31.537.746 I slot launch_slot_: id 0 | task 3354 | processing task, is_child = 0 0.31.961.836 I slot print_timing: id 0 | task 3354 | prompt eval time = 107.88 ms / 356 tokens ( 0.30 ms per token, 3299.90 tokens per second) 0.31.961.842 I slot print_timing: id 0 | task 3354 | eval time = 316.19 ms / 47 tokens ( 6.87 ms per token, 145.48 tokens per second) 0.31.961.843 I slot print_timing: id 0 | task 3354 | total time = 424.07 ms / 403 tokens 0.31.961.844 I slot print_timing: id 0 | task 3354 | graphs reused = 3160 0.31.961.845 I slot print_timing: id 0 | task 3354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.961.872 I slot release: id 0 | task 3354 | stop processing: n_tokens = 414, truncated = 0 0.31.988.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 31863994 0.31.988.625 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.32.035.465 I slot launch_slot_: id 0 | task 3404 | processing task, is_child = 0 0.32.455.514 I slot print_timing: id 0 | task 3404 | prompt eval time = 110.63 ms / 362 tokens ( 0.31 ms per token, 3272.20 tokens per second) 0.32.455.520 I slot print_timing: id 0 | task 3404 | eval time = 309.40 ms / 46 tokens ( 6.88 ms per token, 145.44 tokens per second) 0.32.455.521 I slot print_timing: id 0 | task 3404 | total time = 420.03 ms / 408 tokens 0.32.455.522 I slot print_timing: id 0 | task 3404 | graphs reused = 3204 0.32.455.522 I slot print_timing: id 0 | task 3404 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.455.552 I slot release: id 0 | task 3404 | stop processing: n_tokens = 419, truncated = 0 0.32.483.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 32357673 0.32.483.695 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.32.540.017 I slot launch_slot_: id 0 | task 3453 | processing task, is_child = 0 0.33.115.138 I slot print_timing: id 0 | task 3453 | prompt eval time = 117.36 ms / 391 tokens ( 0.30 ms per token, 3331.57 tokens per second) 0.33.115.143 I slot print_timing: id 0 | task 3453 | eval time = 457.74 ms / 68 tokens ( 6.83 ms per token, 146.37 tokens per second) 0.33.115.144 I slot print_timing: id 0 | task 3453 | total time = 575.10 ms / 459 tokens 0.33.115.145 I slot print_timing: id 0 | task 3453 | graphs reused = 3270 0.33.115.146 I slot print_timing: id 0 | task 3453 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.115.178 I slot release: id 0 | task 3453 | stop processing: n_tokens = 470, truncated = 0 0.33.142.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 33017299 0.33.142.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.33.152.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.33.195.937 I slot launch_slot_: id 0 | task 3524 | processing task, is_child = 0 0.33.668.148 I slot print_timing: id 0 | task 3524 | prompt eval time = 108.74 ms / 343 tokens ( 0.32 ms per token, 3154.20 tokens per second) 0.33.668.154 I slot print_timing: id 0 | task 3524 | eval time = 363.45 ms / 54 tokens ( 6.86 ms per token, 145.83 tokens per second) 0.33.668.155 I slot print_timing: id 0 | task 3524 | total time = 472.19 ms / 397 tokens 0.33.668.156 I slot print_timing: id 0 | task 3524 | graphs reused = 3322 0.33.668.156 I slot print_timing: id 0 | task 3524 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.668.183 I slot release: id 0 | task 3524 | stop processing: n_tokens = 408, truncated = 0 0.33.688.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 33570304 0.33.688.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.33.749.802 I slot launch_slot_: id 0 | task 3581 | processing task, is_child = 0 0.34.176.958 I slot print_timing: id 0 | task 3581 | prompt eval time = 117.89 ms / 401 tokens ( 0.29 ms per token, 3401.62 tokens per second) 0.34.176.964 I slot print_timing: id 0 | task 3581 | eval time = 309.25 ms / 46 tokens ( 6.87 ms per token, 145.51 tokens per second) 0.34.176.965 I slot print_timing: id 0 | task 3581 | total time = 427.14 ms / 447 tokens 0.34.176.965 I slot print_timing: id 0 | task 3581 | graphs reused = 3366 0.34.176.966 I slot print_timing: id 0 | task 3581 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.176.995 I slot release: id 0 | task 3581 | stop processing: n_tokens = 458, truncated = 0 0.34.202.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 34079117 0.34.202.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.34.245.463 I slot launch_slot_: id 0 | task 3630 | processing task, is_child = 0 0.34.814.492 I slot print_timing: id 0 | task 3630 | prompt eval time = 109.87 ms / 355 tokens ( 0.31 ms per token, 3231.12 tokens per second) 0.34.814.497 I slot print_timing: id 0 | task 3630 | eval time = 459.14 ms / 68 tokens ( 6.85 ms per token, 145.92 tokens per second) 0.34.814.498 I slot print_timing: id 0 | task 3630 | total time = 569.01 ms / 423 tokens 0.34.814.499 I slot print_timing: id 0 | task 3630 | graphs reused = 3432 0.34.814.500 I slot print_timing: id 0 | task 3630 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.814.528 I slot release: id 0 | task 3630 | stop processing: n_tokens = 434, truncated = 0 0.34.840.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 34716649 0.34.840.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.34.899.826 I slot launch_slot_: id 0 | task 3701 | processing task, is_child = 0 0.35.423.741 I slot print_timing: id 0 | task 3701 | prompt eval time = 110.33 ms / 351 tokens ( 0.31 ms per token, 3181.36 tokens per second) 0.35.423.747 I slot print_timing: id 0 | task 3701 | eval time = 413.56 ms / 57 tokens ( 7.39 ms per token, 135.41 tokens per second) 0.35.423.748 I slot print_timing: id 0 | task 3701 | total time = 523.89 ms / 408 tokens 0.35.423.749 I slot print_timing: id 0 | task 3701 | graphs reused = 3487 0.35.423.749 I slot print_timing: id 0 | task 3701 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.423.779 I slot release: id 0 | task 3701 | stop processing: n_tokens = 419, truncated = 0 0.35.449.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 35325900 0.35.449.168 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.35.459.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.35.505.137 I slot launch_slot_: id 0 | task 3761 | processing task, is_child = 0 0.36.265.665 I slot print_timing: id 0 | task 3761 | prompt eval time = 125.68 ms / 475 tokens ( 0.26 ms per token, 3779.56 tokens per second) 0.36.265.671 I slot print_timing: id 0 | task 3761 | eval time = 634.83 ms / 93 tokens ( 6.90 ms per token, 144.92 tokens per second) 0.36.265.672 I slot print_timing: id 0 | task 3761 | total time = 760.51 ms / 568 tokens 0.36.265.673 I slot print_timing: id 0 | task 3761 | graphs reused = 3577 0.36.265.673 I slot print_timing: id 0 | task 3761 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.265.706 I slot release: id 0 | task 3761 | stop processing: n_tokens = 579, truncated = 0 0.36.290.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 36167827 0.36.290.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.36.335.023 I slot launch_slot_: id 0 | task 3857 | processing task, is_child = 0 0.37.087.065 I slot print_timing: id 0 | task 3857 | prompt eval time = 120.74 ms / 440 tokens ( 0.27 ms per token, 3644.07 tokens per second) 0.37.087.071 I slot print_timing: id 0 | task 3857 | eval time = 631.28 ms / 92 tokens ( 6.94 ms per token, 144.15 tokens per second) 0.37.087.072 I slot print_timing: id 0 | task 3857 | total time = 752.02 ms / 532 tokens 0.37.087.073 I slot print_timing: id 0 | task 3857 | graphs reused = 3666 0.37.087.073 I slot print_timing: id 0 | task 3857 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.087.104 I slot release: id 0 | task 3857 | stop processing: n_tokens = 543, truncated = 0 0.37.112.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 36989225 0.37.112.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.265 MiB) 0.37.157.474 I slot launch_slot_: id 0 | task 3952 | processing task, is_child = 0 0.37.643.893 I slot print_timing: id 0 | task 3952 | prompt eval time = 108.66 ms / 345 tokens ( 0.31 ms per token, 3175.16 tokens per second) 0.37.643.899 I slot print_timing: id 0 | task 3952 | eval time = 377.74 ms / 56 tokens ( 6.87 ms per token, 145.60 tokens per second) 0.37.643.900 I slot print_timing: id 0 | task 3952 | total time = 486.39 ms / 401 tokens 0.37.643.900 I slot print_timing: id 0 | task 3952 | graphs reused = 3720 0.37.643.901 I slot print_timing: id 0 | task 3952 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.643.931 I slot release: id 0 | task 3952 | stop processing: n_tokens = 412, truncated = 0 0.37.661.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 37546053 0.37.661.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.37.671.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.37.731.961 I slot launch_slot_: id 0 | task 4011 | processing task, is_child = 0 0.38.220.099 I slot print_timing: id 0 | task 4011 | prompt eval time = 117.62 ms / 382 tokens ( 0.31 ms per token, 3247.69 tokens per second) 0.38.220.105 I slot print_timing: id 0 | task 4011 | eval time = 370.50 ms / 55 tokens ( 6.86 ms per token, 145.75 tokens per second) 0.38.220.106 I slot print_timing: id 0 | task 4011 | total time = 488.12 ms / 437 tokens 0.38.220.106 I slot print_timing: id 0 | task 4011 | graphs reused = 3773 0.38.220.107 I slot print_timing: id 0 | task 4011 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.220.139 I slot release: id 0 | task 4011 | stop processing: n_tokens = 448, truncated = 0 0.38.240.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 38122260 0.38.240.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.38.283.480 I slot launch_slot_: id 0 | task 4069 | processing task, is_child = 0 0.38.695.363 I slot print_timing: id 0 | task 4069 | prompt eval time = 108.87 ms / 337 tokens ( 0.32 ms per token, 3095.38 tokens per second) 0.38.695.369 I slot print_timing: id 0 | task 4069 | eval time = 303.00 ms / 45 tokens ( 6.89 ms per token, 145.22 tokens per second) 0.38.695.370 I slot print_timing: id 0 | task 4069 | total time = 411.87 ms / 382 tokens 0.38.695.371 I slot print_timing: id 0 | task 4069 | graphs reused = 3816 0.38.695.371 I slot print_timing: id 0 | task 4069 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.695.399 I slot release: id 0 | task 4069 | stop processing: n_tokens = 393, truncated = 0 0.38.724.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 38597520 0.38.724.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.38.782.549 I slot launch_slot_: id 0 | task 4117 | processing task, is_child = 0 0.39.401.280 I slot print_timing: id 0 | task 4117 | prompt eval time = 118.73 ms / 402 tokens ( 0.30 ms per token, 3385.80 tokens per second) 0.39.401.286 I slot print_timing: id 0 | task 4117 | eval time = 499.98 ms / 70 tokens ( 7.25 ms per token, 138.00 tokens per second) 0.39.401.287 I slot print_timing: id 0 | task 4117 | total time = 618.71 ms / 472 tokens 0.39.401.288 I slot print_timing: id 0 | task 4117 | graphs reused = 3884 0.39.401.289 I slot print_timing: id 0 | task 4117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.401.318 I slot release: id 0 | task 4117 | stop processing: n_tokens = 483, truncated = 0 0.39.426.589 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 39303440 0.39.426.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.39.436.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 174.332 MiB) 0.39.482.197 I slot launch_slot_: id 0 | task 4190 | processing task, is_child = 0 0.39.999.357 I slot print_timing: id 0 | task 4190 | prompt eval time = 132.45 ms / 549 tokens ( 0.24 ms per token, 4145.02 tokens per second) 0.39.999.363 I slot print_timing: id 0 | task 4190 | eval time = 384.69 ms / 57 tokens ( 6.87 ms per token, 145.57 tokens per second) 0.39.999.365 I slot print_timing: id 0 | task 4190 | total time = 517.14 ms / 606 tokens 0.39.999.365 I slot print_timing: id 0 | task 4190 | graphs reused = 3939 0.39.999.366 I slot print_timing: id 0 | task 4190 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.999.399 I slot release: id 0 | task 4190 | stop processing: n_tokens = 617, truncated = 0 0.40.022.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 39901521 0.40.022.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.40.074.226 I slot launch_slot_: id 0 | task 4251 | processing task, is_child = 0 0.40.612.163 I slot print_timing: id 0 | task 4251 | prompt eval time = 146.40 ms / 616 tokens ( 0.24 ms per token, 4207.68 tokens per second) 0.40.612.169 I slot print_timing: id 0 | task 4251 | eval time = 391.52 ms / 58 tokens ( 6.87 ms per token, 145.59 tokens per second) 0.40.612.170 I slot print_timing: id 0 | task 4251 | total time = 537.92 ms / 674 tokens 0.40.612.171 I slot print_timing: id 0 | task 4251 | graphs reused = 3995 0.40.612.171 I slot print_timing: id 0 | task 4251 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.612.207 I slot release: id 0 | task 4251 | stop processing: n_tokens = 685, truncated = 0 0.40.632.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 40514329 0.40.632.882 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.917 MiB) 0.40.642.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.40.715.909 I slot launch_slot_: id 0 | task 4313 | processing task, is_child = 0 0.41.277.451 I slot print_timing: id 0 | task 4313 | prompt eval time = 150.00 ms / 665 tokens ( 0.23 ms per token, 4433.36 tokens per second) 0.41.277.457 I slot print_timing: id 0 | task 4313 | eval time = 411.52 ms / 61 tokens ( 6.86 ms per token, 145.80 tokens per second) 0.41.277.457 I slot print_timing: id 0 | task 4313 | total time = 561.52 ms / 726 tokens 0.41.277.458 I slot print_timing: id 0 | task 4313 | graphs reused = 4054 0.41.277.459 I slot print_timing: id 0 | task 4313 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.277.495 I slot release: id 0 | task 4313 | stop processing: n_tokens = 737, truncated = 0 0.41.293.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 41179617 0.41.293.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.41.303.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.41.357.262 I slot launch_slot_: id 0 | task 4378 | processing task, is_child = 0 0.41.878.503 I slot print_timing: id 0 | task 4378 | prompt eval time = 148.79 ms / 645 tokens ( 0.23 ms per token, 4335.03 tokens per second) 0.41.878.509 I slot print_timing: id 0 | task 4378 | eval time = 372.43 ms / 55 tokens ( 6.90 ms per token, 144.99 tokens per second) 0.41.878.510 I slot print_timing: id 0 | task 4378 | total time = 521.22 ms / 700 tokens 0.41.878.511 I slot print_timing: id 0 | task 4378 | graphs reused = 4107 0.41.878.512 I slot print_timing: id 0 | task 4378 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.878.549 I slot release: id 0 | task 4378 | stop processing: n_tokens = 711, truncated = 0 0.41.902.132 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 41780670 0.41.902.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.137 MiB) 0.41.955.860 I slot launch_slot_: id 0 | task 4437 | processing task, is_child = 0 0.42.435.017 I slot print_timing: id 0 | task 4437 | prompt eval time = 123.15 ms / 474 tokens ( 0.26 ms per token, 3849.06 tokens per second) 0.42.435.024 I slot print_timing: id 0 | task 4437 | eval time = 355.99 ms / 52 tokens ( 6.98 ms per token, 143.26 tokens per second) 0.42.435.025 I slot print_timing: id 0 | task 4437 | total time = 479.14 ms / 526 tokens 0.42.435.026 I slot print_timing: id 0 | task 4437 | graphs reused = 4156 0.42.435.027 I slot print_timing: id 0 | task 4437 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.435.072 I slot release: id 0 | task 4437 | stop processing: n_tokens = 537, truncated = 0 0.42.453.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 42337193 0.42.453.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.42.464.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.013 MiB) 0.42.518.413 I slot launch_slot_: id 0 | task 4492 | processing task, is_child = 0 0.42.941.877 I slot print_timing: id 0 | task 4492 | prompt eval time = 140.67 ms / 617 tokens ( 0.23 ms per token, 4386.12 tokens per second) 0.42.941.883 I slot print_timing: id 0 | task 4492 | eval time = 282.78 ms / 42 tokens ( 6.90 ms per token, 144.99 tokens per second) 0.42.941.884 I slot print_timing: id 0 | task 4492 | total time = 423.45 ms / 659 tokens 0.42.941.885 I slot print_timing: id 0 | task 4492 | graphs reused = 4196 0.42.941.886 I slot print_timing: id 0 | task 4492 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.941.920 I slot release: id 0 | task 4492 | stop processing: n_tokens = 670, truncated = 0 0.42.970.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 42844042 0.42.970.501 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.43.022.176 I slot launch_slot_: id 0 | task 4538 | processing task, is_child = 0 0.43.487.178 I slot print_timing: id 0 | task 4538 | prompt eval time = 141.22 ms / 601 tokens ( 0.23 ms per token, 4255.77 tokens per second) 0.43.487.183 I slot print_timing: id 0 | task 4538 | eval time = 323.76 ms / 48 tokens ( 6.89 ms per token, 145.17 tokens per second) 0.43.487.185 I slot print_timing: id 0 | task 4538 | total time = 464.98 ms / 649 tokens 0.43.487.185 I slot print_timing: id 0 | task 4538 | graphs reused = 4242 0.43.487.186 I slot print_timing: id 0 | task 4538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.487.221 I slot release: id 0 | task 4538 | stop processing: n_tokens = 660, truncated = 0 0.43.502.630 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 43389342 0.43.502.689 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.43.512.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.43.585.441 I slot launch_slot_: id 0 | task 4590 | processing task, is_child = 0 0.44.040.031 I slot print_timing: id 0 | task 4590 | prompt eval time = 137.10 ms / 533 tokens ( 0.26 ms per token, 3887.56 tokens per second) 0.44.040.037 I slot print_timing: id 0 | task 4590 | eval time = 317.47 ms / 47 tokens ( 6.90 ms per token, 144.90 tokens per second) 0.44.040.038 I slot print_timing: id 0 | task 4590 | total time = 454.57 ms / 580 tokens 0.44.040.039 I slot print_timing: id 0 | task 4590 | graphs reused = 4287 0.44.040.039 I slot print_timing: id 0 | task 4590 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.040.071 I slot release: id 0 | task 4590 | stop processing: n_tokens = 591, truncated = 0 0.44.067.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 43942193 0.44.067.706 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.44.132.599 I slot launch_slot_: id 0 | task 4641 | processing task, is_child = 0 0.44.615.512 I slot print_timing: id 0 | task 4641 | prompt eval time = 127.25 ms / 480 tokens ( 0.27 ms per token, 3772.01 tokens per second) 0.44.615.518 I slot print_timing: id 0 | task 4641 | eval time = 355.64 ms / 52 tokens ( 6.97 ms per token, 143.40 tokens per second) 0.44.615.520 I slot print_timing: id 0 | task 4641 | total time = 482.89 ms / 532 tokens 0.44.615.520 I slot print_timing: id 0 | task 4641 | graphs reused = 4336 0.44.615.521 I slot print_timing: id 0 | task 4641 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.615.556 I slot release: id 0 | task 4641 | stop processing: n_tokens = 560, truncated = 0 0.44.619.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 44517678 0.44.620.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.44.630.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.44.703.474 I slot launch_slot_: id 0 | task 4696 | processing task, is_child = 0 0.45.121.802 I slot print_timing: id 0 | task 4696 | prompt eval time = 135.17 ms / 567 tokens ( 0.24 ms per token, 4194.62 tokens per second) 0.45.121.808 I slot print_timing: id 0 | task 4696 | eval time = 283.14 ms / 42 tokens ( 6.91 ms per token, 144.81 tokens per second) 0.45.121.809 I slot print_timing: id 0 | task 4696 | total time = 418.31 ms / 609 tokens 0.45.121.811 I slot print_timing: id 0 | task 4696 | graphs reused = 4376 0.45.121.811 I slot print_timing: id 0 | task 4696 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.121.844 I slot release: id 0 | task 4696 | stop processing: n_tokens = 637, truncated = 0 0.45.141.330 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 45023966 0.45.141.387 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.45.151.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.45.216.327 I slot launch_slot_: id 0 | task 4742 | processing task, is_child = 0 0.45.776.847 I slot print_timing: id 0 | task 4742 | prompt eval time = 134.01 ms / 506 tokens ( 0.26 ms per token, 3775.70 tokens per second) 0.45.776.852 I slot print_timing: id 0 | task 4742 | eval time = 426.49 ms / 63 tokens ( 6.88 ms per token, 145.37 tokens per second) 0.45.776.853 I slot print_timing: id 0 | task 4742 | total time = 560.50 ms / 569 tokens 0.45.776.854 I slot print_timing: id 0 | task 4742 | graphs reused = 4437 0.45.776.855 I slot print_timing: id 0 | task 4742 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.776.887 I slot release: id 0 | task 4742 | stop processing: n_tokens = 597, truncated = 0 0.45.796.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 45679008 0.45.797.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.45.807.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.45.880.141 I slot launch_slot_: id 0 | task 4808 | processing task, is_child = 0 0.46.275.854 I slot print_timing: id 0 | task 4808 | prompt eval time = 127.00 ms / 436 tokens ( 0.29 ms per token, 3433.21 tokens per second) 0.46.275.860 I slot print_timing: id 0 | task 4808 | eval time = 268.70 ms / 40 tokens ( 6.89 ms per token, 145.14 tokens per second) 0.46.275.861 I slot print_timing: id 0 | task 4808 | total time = 395.69 ms / 476 tokens 0.46.275.862 I slot print_timing: id 0 | task 4808 | graphs reused = 4475 0.46.275.862 I slot print_timing: id 0 | task 4808 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.275.892 I slot release: id 0 | task 4808 | stop processing: n_tokens = 504, truncated = 0 0.46.295.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 46178013 0.46.295.142 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.46.351.643 I slot launch_slot_: id 0 | task 4851 | processing task, is_child = 0 0.46.902.883 I slot print_timing: id 0 | task 4851 | prompt eval time = 132.61 ms / 519 tokens ( 0.26 ms per token, 3913.67 tokens per second) 0.46.902.888 I slot print_timing: id 0 | task 4851 | eval time = 418.61 ms / 62 tokens ( 6.86 ms per token, 145.72 tokens per second) 0.46.902.890 I slot print_timing: id 0 | task 4851 | total time = 551.22 ms / 581 tokens 0.46.902.890 I slot print_timing: id 0 | task 4851 | graphs reused = 4535 0.46.902.891 I slot print_timing: id 0 | task 4851 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.902.925 I slot release: id 0 | task 4851 | stop processing: n_tokens = 609, truncated = 0 0.46.929.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 46805047 0.46.929.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.46.939.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.948 MiB) 0.47.011.463 I slot launch_slot_: id 0 | task 4917 | processing task, is_child = 0 0.47.453.892 I slot print_timing: id 0 | task 4917 | prompt eval time = 127.63 ms / 465 tokens ( 0.27 ms per token, 3643.23 tokens per second) 0.47.453.898 I slot print_timing: id 0 | task 4917 | eval time = 314.78 ms / 46 tokens ( 7.00 ms per token, 142.96 tokens per second) 0.47.453.899 I slot print_timing: id 0 | task 4917 | total time = 442.41 ms / 511 tokens 0.47.453.900 I slot print_timing: id 0 | task 4917 | graphs reused = 4578 0.47.453.900 I slot print_timing: id 0 | task 4917 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.453.932 I slot release: id 0 | task 4917 | stop processing: n_tokens = 542, truncated = 0 0.47.480.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 47356053 0.47.480.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.47.490.203 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.47.575.100 I slot launch_slot_: id 0 | task 4966 | processing task, is_child = 0 0.47.975.347 I slot print_timing: id 0 | task 4966 | prompt eval time = 124.88 ms / 431 tokens ( 0.29 ms per token, 3451.31 tokens per second) 0.47.975.353 I slot print_timing: id 0 | task 4966 | eval time = 275.35 ms / 41 tokens ( 6.88 ms per token, 145.27 tokens per second) 0.47.975.354 I slot print_timing: id 0 | task 4966 | total time = 400.23 ms / 472 tokens 0.47.975.355 I slot print_timing: id 0 | task 4966 | graphs reused = 4617 0.47.975.355 I slot print_timing: id 0 | task 4966 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.975.387 I slot release: id 0 | task 4966 | stop processing: n_tokens = 503, truncated = 0 0.47.998.730 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 47877509 0.47.998.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.48.008.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.48.077.182 I slot launch_slot_: id 0 | task 5010 | processing task, is_child = 0 0.48.504.486 I slot print_timing: id 0 | task 5010 | prompt eval time = 127.09 ms / 457 tokens ( 0.28 ms per token, 3595.85 tokens per second) 0.48.504.491 I slot print_timing: id 0 | task 5010 | eval time = 300.19 ms / 44 tokens ( 6.98 ms per token, 143.24 tokens per second) 0.48.504.492 I slot print_timing: id 0 | task 5010 | total time = 427.28 ms / 501 tokens 0.48.504.493 I slot print_timing: id 0 | task 5010 | graphs reused = 4658 0.48.504.494 I slot print_timing: id 0 | task 5010 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.504.528 I slot release: id 0 | task 5010 | stop processing: n_tokens = 532, truncated = 0 0.48.529.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 48406650 0.48.529.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.48.612.754 I slot launch_slot_: id 0 | task 5057 | processing task, is_child = 0 0.49.020.202 I slot print_timing: id 0 | task 5057 | prompt eval time = 124.97 ms / 439 tokens ( 0.28 ms per token, 3512.76 tokens per second) 0.49.020.208 I slot print_timing: id 0 | task 5057 | eval time = 282.46 ms / 42 tokens ( 6.89 ms per token, 145.15 tokens per second) 0.49.020.209 I slot print_timing: id 0 | task 5057 | total time = 407.43 ms / 481 tokens 0.49.020.210 I slot print_timing: id 0 | task 5057 | graphs reused = 4698 0.49.020.211 I slot print_timing: id 0 | task 5057 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.020.241 I slot release: id 0 | task 5057 | stop processing: n_tokens = 512, truncated = 0 0.49.044.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 48922363 0.49.045.022 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 0.49.057.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 0.49.129.730 I slot launch_slot_: id 0 | task 5102 | processing task, is_child = 0 0.49.646.912 I slot print_timing: id 0 | task 5102 | prompt eval time = 138.81 ms / 606 tokens ( 0.23 ms per token, 4365.59 tokens per second) 0.49.646.918 I slot print_timing: id 0 | task 5102 | eval time = 378.35 ms / 56 tokens ( 6.88 ms per token, 145.37 tokens per second) 0.49.646.919 I slot print_timing: id 0 | task 5102 | total time = 517.16 ms / 662 tokens 0.49.646.920 I slot print_timing: id 0 | task 5102 | graphs reused = 4752 0.49.646.920 I slot print_timing: id 0 | task 5102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.646.958 I slot release: id 0 | task 5102 | stop processing: n_tokens = 693, truncated = 0 0.49.667.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 49549079 0.49.667.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.827 MiB) 0.49.681.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 0.49.783.316 I slot launch_slot_: id 0 | task 5162 | processing task, is_child = 0 0.50.193.173 I slot print_timing: id 0 | task 5162 | prompt eval time = 129.50 ms / 477 tokens ( 0.27 ms per token, 3683.26 tokens per second) 0.50.193.179 I slot print_timing: id 0 | task 5162 | eval time = 280.33 ms / 41 tokens ( 7.01 ms per token, 142.69 tokens per second) 0.50.193.180 I slot print_timing: id 0 | task 5162 | total time = 409.84 ms / 518 tokens 0.50.193.180 I slot print_timing: id 0 | task 5162 | graphs reused = 4790 0.50.193.181 I slot print_timing: id 0 | task 5162 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.193.213 I slot release: id 0 | task 5162 | stop processing: n_tokens = 549, truncated = 0 0.50.213.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 50095334 0.50.213.271 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 0.50.275.302 I slot launch_slot_: id 0 | task 5206 | processing task, is_child = 0 0.50.848.585 I slot print_timing: id 0 | task 5206 | prompt eval time = 167.03 ms / 845 tokens ( 0.20 ms per token, 5059.00 tokens per second) 0.50.848.590 I slot print_timing: id 0 | task 5206 | eval time = 406.23 ms / 60 tokens ( 6.89 ms per token, 145.24 tokens per second) 0.50.848.591 I slot print_timing: id 0 | task 5206 | total time = 573.26 ms / 905 tokens 0.50.848.592 I slot print_timing: id 0 | task 5206 | graphs reused = 4848 0.50.848.593 I slot print_timing: id 0 | task 5206 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.848.638 I slot release: id 0 | task 5206 | stop processing: n_tokens = 936, truncated = 0 0.50.866.626 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 50750759 0.50.866.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.50.881.590 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 0.50.957.817 I slot launch_slot_: id 0 | task 5270 | processing task, is_child = 0 0.51.375.629 I slot print_timing: id 0 | task 5270 | prompt eval time = 123.83 ms / 459 tokens ( 0.27 ms per token, 3706.78 tokens per second) 0.51.375.635 I slot print_timing: id 0 | task 5270 | eval time = 293.96 ms / 43 tokens ( 7.00 ms per token, 142.87 tokens per second) 0.51.375.636 I slot print_timing: id 0 | task 5270 | total time = 417.79 ms / 502 tokens 0.51.375.637 I slot print_timing: id 0 | task 5270 | graphs reused = 4888 0.51.375.638 I slot print_timing: id 0 | task 5270 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.375.670 I slot release: id 0 | task 5270 | stop processing: n_tokens = 533, truncated = 0 0.51.395.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 51277791 0.51.395.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 0.51.478.027 I slot launch_slot_: id 0 | task 5316 | processing task, is_child = 0 0.51.942.403 I slot print_timing: id 0 | task 5316 | prompt eval time = 146.92 ms / 670 tokens ( 0.22 ms per token, 4560.37 tokens per second) 0.51.942.409 I slot print_timing: id 0 | task 5316 | eval time = 317.44 ms / 47 tokens ( 6.90 ms per token, 144.91 tokens per second) 0.51.942.411 I slot print_timing: id 0 | task 5316 | total time = 464.36 ms / 717 tokens 0.51.942.411 I slot print_timing: id 0 | task 5316 | graphs reused = 4933 0.51.942.412 I slot print_timing: id 0 | task 5316 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.942.456 I slot release: id 0 | task 5316 | stop processing: n_tokens = 748, truncated = 0 0.51.960.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 51844578 0.51.960.743 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 0.51.973.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 0.52.072.837 I slot launch_slot_: id 0 | task 5367 | processing task, is_child = 0 0.52.699.001 I slot print_timing: id 0 | task 5367 | prompt eval time = 163.86 ms / 775 tokens ( 0.21 ms per token, 4729.73 tokens per second) 0.52.699.008 I slot print_timing: id 0 | task 5367 | eval time = 462.29 ms / 63 tokens ( 7.46 ms per token, 134.12 tokens per second) 0.52.699.009 I slot print_timing: id 0 | task 5367 | total time = 626.14 ms / 838 tokens 0.52.699.010 I slot print_timing: id 0 | task 5367 | graphs reused = 4994 0.52.699.010 I slot print_timing: id 0 | task 5367 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.699.056 I slot release: id 0 | task 5367 | stop processing: n_tokens = 869, truncated = 0 0.52.719.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 52601177 0.52.719.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 0.52.732.896 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 0.52.832.285 I slot launch_slot_: id 0 | task 5434 | processing task, is_child = 0 0.53.470.667 I slot print_timing: id 0 | task 5434 | prompt eval time = 147.99 ms / 573 tokens ( 0.26 ms per token, 3871.94 tokens per second) 0.53.470.673 I slot print_timing: id 0 | task 5434 | eval time = 490.37 ms / 71 tokens ( 7.01 ms per token, 142.75 tokens per second) 0.53.470.674 I slot print_timing: id 0 | task 5434 | total time = 638.36 ms / 644 tokens 0.53.470.675 I slot print_timing: id 0 | task 5434 | graphs reused = 5063 0.53.470.675 I slot print_timing: id 0 | task 5434 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.470.712 I slot release: id 0 | task 5434 | stop processing: n_tokens = 675, truncated = 0 0.53.474.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 53372833 0.53.474.745 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 0.53.488.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.887 MiB) 0.53.575.388 I slot launch_slot_: id 0 | task 5509 | processing task, is_child = 0 0.54.121.084 I slot print_timing: id 0 | task 5509 | prompt eval time = 128.52 ms / 461 tokens ( 0.28 ms per token, 3586.88 tokens per second) 0.54.121.090 I slot print_timing: id 0 | task 5509 | eval time = 417.15 ms / 61 tokens ( 6.95 ms per token, 143.83 tokens per second) 0.54.121.091 I slot print_timing: id 0 | task 5509 | total time = 545.68 ms / 522 tokens 0.54.121.091 I slot print_timing: id 0 | task 5509 | graphs reused = 5121 0.54.121.092 I slot print_timing: id 0 | task 5509 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.121.123 I slot release: id 0 | task 5509 | stop processing: n_tokens = 553, truncated = 0 0.54.147.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 553, t_last = 54023245 0.54.147.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 0.54.208.715 I slot launch_slot_: id 0 | task 5573 | processing task, is_child = 0 0.54.614.486 I slot print_timing: id 0 | task 5573 | prompt eval time = 139.01 ms / 609 tokens ( 0.23 ms per token, 4381.04 tokens per second) 0.54.614.492 I slot print_timing: id 0 | task 5573 | eval time = 266.74 ms / 39 tokens ( 7.02 ms per token, 142.46 tokens per second) 0.54.614.493 I slot print_timing: id 0 | task 5573 | total time = 405.75 ms / 648 tokens 0.54.614.493 I slot print_timing: id 0 | task 5573 | graphs reused = 5158 0.54.614.494 I slot print_timing: id 0 | task 5573 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.614.533 I slot release: id 0 | task 5573 | stop processing: n_tokens = 679, truncated = 0 0.54.619.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 54516655 0.54.619.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 0.54.632.681 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 0.54.731.595 I slot launch_slot_: id 0 | task 5616 | processing task, is_child = 0 0.55.310.291 I slot print_timing: id 0 | task 5616 | prompt eval time = 164.07 ms / 791 tokens ( 0.21 ms per token, 4821.20 tokens per second) 0.55.310.297 I slot print_timing: id 0 | task 5616 | eval time = 414.61 ms / 61 tokens ( 6.91 ms per token, 144.71 tokens per second) 0.55.310.298 I slot print_timing: id 0 | task 5616 | total time = 578.68 ms / 852 tokens 0.55.310.299 I slot print_timing: id 0 | task 5616 | graphs reused = 5217 0.55.310.299 I slot print_timing: id 0 | task 5616 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.310.341 I slot release: id 0 | task 5616 | stop processing: n_tokens = 883, truncated = 0 0.55.325.067 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 55212462 0.55.325.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 0.55.437.351 I slot launch_slot_: id 0 | task 5681 | processing task, is_child = 0 0.55.951.747 I slot print_timing: id 0 | task 5681 | prompt eval time = 136.58 ms / 533 tokens ( 0.26 ms per token, 3902.53 tokens per second) 0.55.951.753 I slot print_timing: id 0 | task 5681 | eval time = 377.80 ms / 56 tokens ( 6.87 ms per token, 145.58 tokens per second) 0.55.951.754 I slot print_timing: id 0 | task 5681 | total time = 514.38 ms / 589 tokens 0.55.951.755 I slot print_timing: id 0 | task 5681 | graphs reused = 5271 0.55.951.756 I slot print_timing: id 0 | task 5681 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.951.790 I slot release: id 0 | task 5681 | stop processing: n_tokens = 677, truncated = 0 0.55.976.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 55853911 0.55.976.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 0.56.059.959 I slot launch_slot_: id 0 | task 5741 | processing task, is_child = 0 0.56.545.102 I slot print_timing: id 0 | task 5741 | prompt eval time = 140.88 ms / 566 tokens ( 0.25 ms per token, 4017.55 tokens per second) 0.56.545.108 I slot print_timing: id 0 | task 5741 | eval time = 344.24 ms / 46 tokens ( 7.65 ms per token, 130.72 tokens per second) 0.56.545.109 I slot print_timing: id 0 | task 5741 | total time = 485.12 ms / 612 tokens 0.56.545.110 I slot print_timing: id 0 | task 5741 | graphs reused = 5315 0.56.545.110 I slot print_timing: id 0 | task 5741 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.545.145 I slot release: id 0 | task 5741 | stop processing: n_tokens = 643, truncated = 0 0.56.565.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 56447266 0.56.565.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 0.56.675.373 I slot launch_slot_: id 0 | task 5791 | processing task, is_child = 0 0.57.099.278 I slot print_timing: id 0 | task 5791 | prompt eval time = 128.84 ms / 443 tokens ( 0.29 ms per token, 3438.40 tokens per second) 0.57.099.283 I slot print_timing: id 0 | task 5791 | eval time = 295.05 ms / 43 tokens ( 7.02 ms per token, 142.35 tokens per second) 0.57.099.284 I slot print_timing: id 0 | task 5791 | total time = 423.88 ms / 486 tokens 0.57.099.285 I slot print_timing: id 0 | task 5791 | graphs reused = 5355 0.57.099.286 I slot print_timing: id 0 | task 5791 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.099.316 I slot release: id 0 | task 5791 | stop processing: n_tokens = 517, truncated = 0 0.57.113.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 57001437 0.57.113.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 0.57.180.215 I slot launch_slot_: id 0 | task 5837 | processing task, is_child = 0 0.57.745.723 I slot print_timing: id 0 | task 5837 | prompt eval time = 125.69 ms / 487 tokens ( 0.26 ms per token, 3874.67 tokens per second) 0.57.745.729 I slot print_timing: id 0 | task 5837 | eval time = 439.80 ms / 65 tokens ( 6.87 ms per token, 145.52 tokens per second) 0.57.745.730 I slot print_timing: id 0 | task 5837 | total time = 565.49 ms / 552 tokens 0.57.745.731 I slot print_timing: id 0 | task 5837 | graphs reused = 5418 0.57.745.731 I slot print_timing: id 0 | task 5837 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.745.765 I slot release: id 0 | task 5837 | stop processing: n_tokens = 583, truncated = 0 0.57.766.531 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 57647886 0.57.766.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 0.57.852.852 I slot launch_slot_: id 0 | task 5905 | processing task, is_child = 0 0.58.302.402 I slot print_timing: id 0 | task 5905 | prompt eval time = 129.98 ms / 507 tokens ( 0.26 ms per token, 3900.54 tokens per second) 0.58.302.408 I slot print_timing: id 0 | task 5905 | eval time = 319.55 ms / 47 tokens ( 6.95 ms per token, 143.95 tokens per second) 0.58.302.409 I slot print_timing: id 0 | task 5905 | total time = 449.53 ms / 554 tokens 0.58.302.410 I slot print_timing: id 0 | task 5905 | graphs reused = 5463 0.58.302.411 I slot print_timing: id 0 | task 5905 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.302.446 I slot release: id 0 | task 5905 | stop processing: n_tokens = 585, truncated = 0 0.58.326.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 58204567 0.58.326.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 0.58.343.144 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 0.58.419.930 I slot launch_slot_: id 0 | task 5955 | processing task, is_child = 0 0.59.009.864 I slot print_timing: id 0 | task 5955 | prompt eval time = 142.98 ms / 633 tokens ( 0.23 ms per token, 4427.29 tokens per second) 0.59.009.870 I slot print_timing: id 0 | task 5955 | eval time = 446.94 ms / 66 tokens ( 6.88 ms per token, 145.43 tokens per second) 0.59.009.870 I slot print_timing: id 0 | task 5955 | total time = 589.91 ms / 699 tokens 0.59.009.871 I slot print_timing: id 0 | task 5955 | graphs reused = 5527 0.59.009.872 I slot print_timing: id 0 | task 5955 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.009.910 I slot release: id 0 | task 5955 | stop processing: n_tokens = 730, truncated = 0 0.59.034.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 58912031 0.59.034.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 0.59.107.918 I slot launch_slot_: id 0 | task 6025 | processing task, is_child = 0 0.59.645.745 I slot print_timing: id 0 | task 6025 | prompt eval time = 139.47 ms / 571 tokens ( 0.24 ms per token, 4094.16 tokens per second) 0.59.645.751 I slot print_timing: id 0 | task 6025 | eval time = 398.34 ms / 59 tokens ( 6.87 ms per token, 145.60 tokens per second) 0.59.645.752 I slot print_timing: id 0 | task 6025 | total time = 537.81 ms / 630 tokens 0.59.645.753 I slot print_timing: id 0 | task 6025 | graphs reused = 5584 0.59.645.753 I slot print_timing: id 0 | task 6025 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.645.790 I slot release: id 0 | task 6025 | stop processing: n_tokens = 661, truncated = 0 0.59.671.585 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 59547911 0.59.671.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 0.59.776.690 I slot launch_slot_: id 0 | task 6088 | processing task, is_child = 0 1.00.236.648 I slot print_timing: id 0 | task 6088 | prompt eval time = 162.51 ms / 798 tokens ( 0.20 ms per token, 4910.38 tokens per second) 1.00.236.654 I slot print_timing: id 0 | task 6088 | eval time = 297.43 ms / 44 tokens ( 6.92 ms per token, 144.57 tokens per second) 1.00.236.655 I slot print_timing: id 0 | task 6088 | total time = 459.94 ms / 842 tokens 1.00.236.656 I slot print_timing: id 0 | task 6088 | graphs reused = 5626 1.00.236.656 I slot print_timing: id 0 | task 6088 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.236.699 I slot release: id 0 | task 6088 | stop processing: n_tokens = 873, truncated = 0 1.00.266.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 60138820 1.00.266.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.00.285.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.00.379.984 I slot launch_slot_: id 0 | task 6136 | processing task, is_child = 0 1.00.808.585 I slot print_timing: id 0 | task 6136 | prompt eval time = 138.25 ms / 572 tokens ( 0.24 ms per token, 4137.34 tokens per second) 1.00.808.591 I slot print_timing: id 0 | task 6136 | eval time = 290.33 ms / 43 tokens ( 6.91 ms per token, 144.66 tokens per second) 1.00.808.592 I slot print_timing: id 0 | task 6136 | total time = 428.58 ms / 615 tokens 1.00.808.593 I slot print_timing: id 0 | task 6136 | graphs reused = 5667 1.00.808.593 I slot print_timing: id 0 | task 6136 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.808.631 I slot release: id 0 | task 6136 | stop processing: n_tokens = 646, truncated = 0 1.00.827.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 60710752 1.00.827.664 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.00.921.605 I slot launch_slot_: id 0 | task 6183 | processing task, is_child = 0 1.01.504.721 I slot print_timing: id 0 | task 6183 | prompt eval time = 142.55 ms / 613 tokens ( 0.23 ms per token, 4300.22 tokens per second) 1.01.504.729 I slot print_timing: id 0 | task 6183 | eval time = 440.54 ms / 64 tokens ( 6.99 ms per token, 143.01 tokens per second) 1.01.504.730 I slot print_timing: id 0 | task 6183 | total time = 583.09 ms / 677 tokens 1.01.504.732 I slot print_timing: id 0 | task 6183 | graphs reused = 5729 1.01.504.733 I slot print_timing: id 0 | task 6183 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.504.782 I slot release: id 0 | task 6183 | stop processing: n_tokens = 708, truncated = 0 1.01.532.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 61406903 1.01.532.778 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.01.637.540 I slot launch_slot_: id 0 | task 6251 | processing task, is_child = 0 1.02.209.865 I slot print_timing: id 0 | task 6251 | prompt eval time = 139.14 ms / 580 tokens ( 0.24 ms per token, 4168.40 tokens per second) 1.02.209.871 I slot print_timing: id 0 | task 6251 | eval time = 433.16 ms / 64 tokens ( 6.88 ms per token, 145.44 tokens per second) 1.02.209.872 I slot print_timing: id 0 | task 6251 | total time = 572.31 ms / 644 tokens 1.02.209.873 I slot print_timing: id 0 | task 6251 | graphs reused = 5791 1.02.209.874 I slot print_timing: id 0 | task 6251 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.209.910 I slot release: id 0 | task 6251 | stop processing: n_tokens = 675, truncated = 0 1.02.238.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 62112031 1.02.238.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.02.334.750 I slot launch_slot_: id 0 | task 6319 | processing task, is_child = 0 1.02.831.361 I slot print_timing: id 0 | task 6319 | prompt eval time = 154.34 ms / 716 tokens ( 0.22 ms per token, 4639.20 tokens per second) 1.02.831.367 I slot print_timing: id 0 | task 6319 | eval time = 342.26 ms / 50 tokens ( 6.98 ms per token, 143.17 tokens per second) 1.02.831.368 I slot print_timing: id 0 | task 6319 | total time = 496.59 ms / 766 tokens 1.02.831.369 I slot print_timing: id 0 | task 6319 | graphs reused = 5838 1.02.831.370 I slot print_timing: id 0 | task 6319 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.831.410 I slot release: id 0 | task 6319 | stop processing: n_tokens = 797, truncated = 0 1.02.858.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 62733531 1.02.858.968 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.02.880.918 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.02.967.046 I slot launch_slot_: id 0 | task 6373 | processing task, is_child = 0 1.03.824.968 I slot print_timing: id 0 | task 6373 | prompt eval time = 165.45 ms / 799 tokens ( 0.21 ms per token, 4829.14 tokens per second) 1.03.824.974 I slot print_timing: id 0 | task 6373 | eval time = 692.45 ms / 102 tokens ( 6.86 ms per token, 145.86 tokens per second) 1.03.824.975 I slot print_timing: id 0 | task 6373 | total time = 857.90 ms / 901 tokens 1.03.824.976 I slot print_timing: id 0 | task 6373 | graphs reused = 5938 1.03.824.977 I slot print_timing: id 0 | task 6373 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.825.019 I slot release: id 0 | task 6373 | stop processing: n_tokens = 932, truncated = 0 1.03.853.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 63727141 1.03.853.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.03.929.423 I slot launch_slot_: id 0 | task 6479 | processing task, is_child = 0 1.04.797.685 I slot print_timing: id 0 | task 6479 | prompt eval time = 112.65 ms / 361 tokens ( 0.31 ms per token, 3204.56 tokens per second) 1.04.797.690 I slot print_timing: id 0 | task 6479 | eval time = 755.59 ms / 112 tokens ( 6.81 ms per token, 146.90 tokens per second) 1.04.797.691 I slot print_timing: id 0 | task 6479 | total time = 868.24 ms / 473 tokens 1.04.797.693 I slot print_timing: id 0 | task 6479 | graphs reused = 6048 1.04.797.693 I slot print_timing: id 0 | task 6479 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.797.724 I slot release: id 0 | task 6479 | stop processing: n_tokens = 504, truncated = 0 1.04.823.187 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 64699845 1.04.823.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.04.909.830 I slot launch_slot_: id 0 | task 6594 | processing task, is_child = 0 1.05.758.613 I slot print_timing: id 0 | task 6594 | prompt eval time = 114.04 ms / 381 tokens ( 0.30 ms per token, 3340.99 tokens per second) 1.05.758.620 I slot print_timing: id 0 | task 6594 | eval time = 734.73 ms / 108 tokens ( 6.87 ms per token, 145.63 tokens per second) 1.05.758.621 I slot print_timing: id 0 | task 6594 | total time = 848.76 ms / 489 tokens 1.05.758.621 I slot print_timing: id 0 | task 6594 | graphs reused = 6153 1.05.758.622 I slot print_timing: id 0 | task 6594 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.758.653 I slot release: id 0 | task 6594 | stop processing: n_tokens = 520, truncated = 0 1.05.785.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 65660774 1.05.785.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.05.849.163 I slot launch_slot_: id 0 | task 6705 | processing task, is_child = 0 1.06.805.064 I slot print_timing: id 0 | task 6705 | prompt eval time = 112.20 ms / 365 tokens ( 0.31 ms per token, 3253.18 tokens per second) 1.06.805.070 I slot print_timing: id 0 | task 6705 | eval time = 843.68 ms / 124 tokens ( 6.86 ms per token, 145.79 tokens per second) 1.06.805.071 I slot print_timing: id 0 | task 6705 | total time = 955.88 ms / 489 tokens 1.06.805.072 I slot print_timing: id 0 | task 6705 | graphs reused = 6274 1.06.805.073 I slot print_timing: id 0 | task 6705 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.805.101 I slot release: id 0 | task 6705 | stop processing: n_tokens = 520, truncated = 0 1.06.832.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 66707223 1.06.832.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.06.906.408 I slot launch_slot_: id 0 | task 6832 | processing task, is_child = 0 1.07.740.690 I slot print_timing: id 0 | task 6832 | prompt eval time = 109.99 ms / 333 tokens ( 0.33 ms per token, 3027.47 tokens per second) 1.07.740.696 I slot print_timing: id 0 | task 6832 | eval time = 724.27 ms / 107 tokens ( 6.83 ms per token, 146.35 tokens per second) 1.07.740.697 I slot print_timing: id 0 | task 6832 | total time = 834.26 ms / 440 tokens 1.07.740.698 I slot print_timing: id 0 | task 6832 | graphs reused = 6379 1.07.740.699 I slot print_timing: id 0 | task 6832 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.740.726 I slot release: id 0 | task 6832 | stop processing: n_tokens = 471, truncated = 0 1.07.757.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 67642848 1.07.800.077 I slot launch_slot_: id 0 | task 6942 | processing task, is_child = 0 1.08.852.840 I slot print_timing: id 0 | task 6942 | prompt eval time = 114.65 ms / 403 tokens ( 0.28 ms per token, 3515.17 tokens per second) 1.08.852.846 I slot print_timing: id 0 | task 6942 | eval time = 938.10 ms / 138 tokens ( 6.85 ms per token, 146.04 tokens per second) 1.08.852.847 I slot print_timing: id 0 | task 6942 | total time = 1052.74 ms / 541 tokens 1.08.852.848 I slot print_timing: id 0 | task 6942 | graphs reused = 6514 1.08.852.848 I slot print_timing: id 0 | task 6942 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.852.879 I slot release: id 0 | task 6942 | stop processing: n_tokens = 572, truncated = 0 1.08.874.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 68755000 1.08.874.538 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.08.956.219 I slot launch_slot_: id 0 | task 7083 | processing task, is_child = 0 1.10.329.964 I slot print_timing: id 0 | task 7083 | prompt eval time = 116.58 ms / 411 tokens ( 0.28 ms per token, 3525.51 tokens per second) 1.10.329.969 I slot print_timing: id 0 | task 7083 | eval time = 1257.15 ms / 185 tokens ( 6.83 ms per token, 146.36 tokens per second) 1.10.329.970 I slot print_timing: id 0 | task 7083 | total time = 1373.73 ms / 596 tokens 1.10.329.971 I slot print_timing: id 0 | task 7083 | graphs reused = 6696 1.10.329.971 I slot print_timing: id 0 | task 7083 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.330.001 I slot release: id 0 | task 7083 | stop processing: n_tokens = 627, truncated = 0 1.10.353.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 70232122 1.10.353.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.10.444.830 I slot launch_slot_: id 0 | task 7271 | processing task, is_child = 0 1.12.101.117 I slot print_timing: id 0 | task 7271 | prompt eval time = 130.95 ms / 490 tokens ( 0.27 ms per token, 3741.89 tokens per second) 1.12.101.125 I slot print_timing: id 0 | task 7271 | eval time = 1525.32 ms / 225 tokens ( 6.81 ms per token, 146.85 tokens per second) 1.12.101.126 I slot print_timing: id 0 | task 7271 | total time = 1656.27 ms / 715 tokens 1.12.101.127 I slot print_timing: id 0 | task 7271 | graphs reused = 6919 1.12.101.128 I slot print_timing: id 0 | task 7271 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.101.162 I slot release: id 0 | task 7271 | stop processing: n_tokens = 746, truncated = 0 1.12.123.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 72003284 1.12.123.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.12.203.078 I slot launch_slot_: id 0 | task 7499 | processing task, is_child = 0 1.14.628.806 I slot print_timing: id 0 | task 7499 | prompt eval time = 112.02 ms / 344 tokens ( 0.33 ms per token, 3070.83 tokens per second) 1.14.628.811 I slot print_timing: id 0 | task 7499 | eval time = 2313.69 ms / 341 tokens ( 6.80 ms per token, 146.95 tokens per second) 1.14.628.812 I slot print_timing: id 0 | task 7499 | total time = 2425.71 ms / 685 tokens 1.14.628.813 I slot print_timing: id 0 | task 7499 | graphs reused = 7257 1.14.628.814 I slot print_timing: id 0 | task 7499 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.628.842 I slot release: id 0 | task 7499 | stop processing: n_tokens = 716, truncated = 0 1.14.651.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 716, t_last = 74530963 1.14.651.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.798 MiB) 1.14.732.736 I slot launch_slot_: id 0 | task 7843 | processing task, is_child = 0 1.16.005.472 I slot print_timing: id 0 | task 7843 | prompt eval time = 111.12 ms / 347 tokens ( 0.32 ms per token, 3122.67 tokens per second) 1.16.005.480 I slot print_timing: id 0 | task 7843 | eval time = 1161.60 ms / 171 tokens ( 6.83 ms per token, 146.35 tokens per second) 1.16.005.482 I slot print_timing: id 0 | task 7843 | total time = 1272.72 ms / 518 tokens 1.16.005.483 I slot print_timing: id 0 | task 7843 | graphs reused = 7425 1.16.005.484 I slot print_timing: id 0 | task 7843 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.005.512 I slot release: id 0 | task 7843 | stop processing: n_tokens = 549, truncated = 0 1.16.032.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 75907633 1.16.032.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.989 MiB) 1.16.107.796 I slot launch_slot_: id 0 | task 8017 | processing task, is_child = 0 1.17.082.798 I slot print_timing: id 0 | task 8017 | prompt eval time = 117.49 ms / 401 tokens ( 0.29 ms per token, 3412.97 tokens per second) 1.17.082.804 I slot print_timing: id 0 | task 8017 | eval time = 857.49 ms / 126 tokens ( 6.86 ms per token, 145.77 tokens per second) 1.17.082.805 I slot print_timing: id 0 | task 8017 | total time = 974.98 ms / 527 tokens 1.17.082.806 I slot print_timing: id 0 | task 8017 | graphs reused = 7548 1.17.082.806 I slot print_timing: id 0 | task 8017 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.082.835 I slot release: id 0 | task 8017 | stop processing: n_tokens = 558, truncated = 0 1.17.103.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 76984957 1.17.103.694 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.17.176.417 I slot launch_slot_: id 0 | task 8146 | processing task, is_child = 0 1.18.109.842 I slot print_timing: id 0 | task 8146 | prompt eval time = 123.10 ms / 456 tokens ( 0.27 ms per token, 3704.43 tokens per second) 1.18.109.848 I slot print_timing: id 0 | task 8146 | eval time = 810.31 ms / 114 tokens ( 7.17 ms per token, 139.45 tokens per second) 1.18.109.849 I slot print_timing: id 0 | task 8146 | total time = 933.41 ms / 570 tokens 1.18.109.850 I slot print_timing: id 0 | task 8146 | graphs reused = 7659 1.18.109.851 I slot print_timing: id 0 | task 8146 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.109.883 I slot release: id 0 | task 8146 | stop processing: n_tokens = 601, truncated = 0 1.18.136.216 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 1.18.136.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.18.209.391 I slot launch_slot_: id 0 | task 8263 | processing task, is_child = 0 1.19.088.717 I slot print_timing: id 0 | task 8263 | prompt eval time = 116.87 ms / 406 tokens ( 0.29 ms per token, 3474.03 tokens per second) 1.19.088.723 I slot print_timing: id 0 | task 8263 | eval time = 762.44 ms / 112 tokens ( 6.87 ms per token, 145.59 tokens per second) 1.19.088.724 I slot print_timing: id 0 | task 8263 | total time = 879.31 ms / 518 tokens 1.19.088.725 I slot print_timing: id 0 | task 8263 | graphs reused = 7768 1.19.088.725 I slot print_timing: id 0 | task 8263 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.088.757 I slot release: id 0 | task 8263 | stop processing: n_tokens = 549, truncated = 0 1.19.102.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 78990879 1.19.146.090 I slot launch_slot_: id 0 | task 8378 | processing task, is_child = 0 1.20.479.242 I slot print_timing: id 0 | task 8378 | prompt eval time = 114.61 ms / 406 tokens ( 0.28 ms per token, 3542.48 tokens per second) 1.20.479.247 I slot print_timing: id 0 | task 8378 | eval time = 1218.52 ms / 179 tokens ( 6.85 ms per token, 146.08 tokens per second) 1.20.479.248 I slot print_timing: id 0 | task 8378 | total time = 1333.13 ms / 585 tokens 1.20.479.249 I slot print_timing: id 0 | task 8378 | graphs reused = 7944 1.20.479.249 I slot print_timing: id 0 | task 8378 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.479.279 I slot release: id 0 | task 8378 | stop processing: n_tokens = 616, truncated = 0 1.20.506.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 80381401 1.20.506.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.20.608.775 I slot launch_slot_: id 0 | task 8560 | processing task, is_child = 0 1.21.667.380 I slot print_timing: id 0 | task 8560 | prompt eval time = 122.30 ms / 444 tokens ( 0.28 ms per token, 3630.51 tokens per second) 1.21.667.386 I slot print_timing: id 0 | task 8560 | eval time = 936.29 ms / 134 tokens ( 7.04 ms per token, 142.05 tokens per second) 1.21.667.387 I slot print_timing: id 0 | task 8560 | total time = 1058.58 ms / 578 tokens 1.21.667.388 I slot print_timing: id 0 | task 8560 | graphs reused = 8075 1.21.667.389 I slot print_timing: id 0 | task 8560 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.667.420 I slot release: id 0 | task 8560 | stop processing: n_tokens = 609, truncated = 0 1.21.691.075 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 81569541 1.21.691.132 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.21.771.141 I slot launch_slot_: id 0 | task 8697 | processing task, is_child = 0 1.22.584.282 I slot print_timing: id 0 | task 8697 | prompt eval time = 116.18 ms / 372 tokens ( 0.31 ms per token, 3202.04 tokens per second) 1.22.584.288 I slot print_timing: id 0 | task 8697 | eval time = 696.95 ms / 103 tokens ( 6.83 ms per token, 146.35 tokens per second) 1.22.584.290 I slot print_timing: id 0 | task 8697 | total time = 813.12 ms / 475 tokens 1.22.584.291 I slot print_timing: id 0 | task 8697 | graphs reused = 8176 1.22.584.291 I slot print_timing: id 0 | task 8697 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.584.323 I slot release: id 0 | task 8697 | stop processing: n_tokens = 506, truncated = 0 1.22.610.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 82486444 1.22.610.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.22.687.196 I slot launch_slot_: id 0 | task 8803 | processing task, is_child = 0 1.24.374.098 I slot print_timing: id 0 | task 8803 | prompt eval time = 122.76 ms / 454 tokens ( 0.27 ms per token, 3698.27 tokens per second) 1.24.374.104 I slot print_timing: id 0 | task 8803 | eval time = 1564.12 ms / 230 tokens ( 6.83 ms per token, 146.41 tokens per second) 1.24.374.105 I slot print_timing: id 0 | task 8803 | total time = 1686.88 ms / 684 tokens 1.24.374.106 I slot print_timing: id 0 | task 8803 | graphs reused = 8403 1.24.374.107 I slot print_timing: id 0 | task 8803 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.374.138 I slot release: id 0 | task 8803 | stop processing: n_tokens = 715, truncated = 0 1.24.389.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 84276259 1.24.389.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.24.468.952 I slot launch_slot_: id 0 | task 9036 | processing task, is_child = 0 1.26.117.161 I slot print_timing: id 0 | task 9036 | prompt eval time = 113.47 ms / 354 tokens ( 0.32 ms per token, 3119.85 tokens per second) 1.26.117.166 I slot print_timing: id 0 | task 9036 | eval time = 1534.72 ms / 226 tokens ( 6.82 ms per token, 146.61 tokens per second) 1.26.117.167 I slot print_timing: id 0 | task 9036 | total time = 1648.19 ms / 580 tokens 1.26.117.168 I slot print_timing: id 0 | task 9036 | graphs reused = 8626 1.26.117.169 I slot print_timing: id 0 | task 9036 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.117.198 I slot release: id 0 | task 9036 | stop processing: n_tokens = 611, truncated = 0 1.26.140.999 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 86019319 1.26.141.058 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.26.225.293 I slot launch_slot_: id 0 | task 9265 | processing task, is_child = 0 1.27.284.065 I slot print_timing: id 0 | task 9265 | prompt eval time = 112.07 ms / 334 tokens ( 0.34 ms per token, 2980.33 tokens per second) 1.27.284.071 I slot print_timing: id 0 | task 9265 | eval time = 946.68 ms / 140 tokens ( 6.81 ms per token, 146.83 tokens per second) 1.27.284.072 I slot print_timing: id 0 | task 9265 | total time = 1058.75 ms / 474 tokens 1.27.284.073 I slot print_timing: id 0 | task 9265 | graphs reused = 8764 1.27.284.074 I slot print_timing: id 0 | task 9265 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.284.103 I slot release: id 0 | task 9265 | stop processing: n_tokens = 505, truncated = 0 1.27.298.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 87186224 1.27.298.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.426 MiB) 1.27.376.472 I slot launch_slot_: id 0 | task 9408 | processing task, is_child = 0 1.28.686.184 I slot print_timing: id 0 | task 9408 | prompt eval time = 120.48 ms / 426 tokens ( 0.28 ms per token, 3535.86 tokens per second) 1.28.686.190 I slot print_timing: id 0 | task 9408 | eval time = 1189.21 ms / 175 tokens ( 6.83 ms per token, 146.32 tokens per second) 1.28.686.191 I slot print_timing: id 0 | task 9408 | total time = 1309.69 ms / 601 tokens 1.28.686.192 I slot print_timing: id 0 | task 9408 | graphs reused = 8936 1.28.686.193 I slot print_timing: id 0 | task 9408 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.686.222 I slot release: id 0 | task 9408 | stop processing: n_tokens = 632, truncated = 0 1.28.709.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 88588344 1.28.710.042 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.28.784.571 I slot launch_slot_: id 0 | task 9586 | processing task, is_child = 0 1.29.813.970 I slot print_timing: id 0 | task 9586 | prompt eval time = 119.08 ms / 366 tokens ( 0.33 ms per token, 3073.49 tokens per second) 1.29.813.976 I slot print_timing: id 0 | task 9586 | eval time = 910.30 ms / 134 tokens ( 6.84 ms per token, 146.11 tokens per second) 1.29.813.977 I slot print_timing: id 0 | task 9586 | total time = 1029.38 ms / 500 tokens 1.29.813.978 I slot print_timing: id 0 | task 9586 | graphs reused = 9067 1.29.813.979 I slot print_timing: id 0 | task 9586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.814.008 I slot release: id 0 | task 9586 | stop processing: n_tokens = 531, truncated = 0 1.29.832.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 89716129 1.29.832.350 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.29.906.076 I slot launch_slot_: id 0 | task 9723 | processing task, is_child = 0 1.32.413.134 I slot print_timing: id 0 | task 9723 | prompt eval time = 124.94 ms / 462 tokens ( 0.27 ms per token, 3697.83 tokens per second) 1.32.413.139 I slot print_timing: id 0 | task 9723 | eval time = 2382.10 ms / 350 tokens ( 6.83 ms per token, 146.51 tokens per second) 1.32.413.141 I slot print_timing: id 0 | task 9723 | total time = 2507.04 ms / 812 tokens 1.32.413.141 I slot print_timing: id 0 | task 9723 | graphs reused = 9413 1.32.413.142 I slot print_timing: id 0 | task 9723 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.413.173 I slot release: id 0 | task 9723 | stop processing: n_tokens = 843, truncated = 0 1.32.436.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 843, t_last = 92315294 1.32.436.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.895 MiB) 1.32.508.478 I slot launch_slot_: id 0 | task 10076 | processing task, is_child = 0 1.33.568.856 I slot print_timing: id 0 | task 10076 | prompt eval time = 113.95 ms / 396 tokens ( 0.29 ms per token, 3475.18 tokens per second) 1.33.568.862 I slot print_timing: id 0 | task 10076 | eval time = 946.41 ms / 139 tokens ( 6.86 ms per token, 145.81 tokens per second) 1.33.568.863 I slot print_timing: id 0 | task 10076 | total time = 1060.36 ms / 535 tokens 1.33.568.864 I slot print_timing: id 0 | task 10076 | graphs reused = 9549 1.33.568.864 I slot print_timing: id 0 | task 10076 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.568.893 I slot release: id 0 | task 10076 | stop processing: n_tokens = 566, truncated = 0 1.33.584.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 93471014 1.33.631.778 I slot launch_slot_: id 0 | task 10218 | processing task, is_child = 0 1.34.847.791 I slot print_timing: id 0 | task 10218 | prompt eval time = 120.50 ms / 458 tokens ( 0.26 ms per token, 3800.92 tokens per second) 1.34.847.797 I slot print_timing: id 0 | task 10218 | eval time = 1095.50 ms / 161 tokens ( 6.85 ms per token, 146.05 tokens per second) 1.34.847.798 I slot print_timing: id 0 | task 10218 | total time = 1216.00 ms / 619 tokens 1.34.847.799 I slot print_timing: id 0 | task 10218 | graphs reused = 9707 1.34.847.799 I slot print_timing: id 0 | task 10218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.847.832 I slot release: id 0 | task 10218 | stop processing: n_tokens = 650, truncated = 0 1.34.862.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 94749953 1.34.863.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.863 MiB) 1.34.946.124 I slot launch_slot_: id 0 | task 10382 | processing task, is_child = 0 1.36.303.105 I slot print_timing: id 0 | task 10382 | prompt eval time = 124.70 ms / 458 tokens ( 0.27 ms per token, 3672.87 tokens per second) 1.36.303.115 I slot print_timing: id 0 | task 10382 | eval time = 1232.26 ms / 176 tokens ( 7.04 ms per token, 142.02 tokens per second) 1.36.303.116 I slot print_timing: id 0 | task 10382 | total time = 1356.96 ms / 634 tokens 1.36.303.120 I slot print_timing: id 0 | task 10382 | graphs reused = 9880 1.36.303.121 I slot print_timing: id 0 | task 10382 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.303.154 I slot release: id 0 | task 10382 | stop processing: n_tokens = 665, truncated = 0 1.36.320.660 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 96205275 1.36.320.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 1.36.401.322 I slot launch_slot_: id 0 | task 10561 | processing task, is_child = 0 1.37.967.871 I slot print_timing: id 0 | task 10561 | prompt eval time = 124.11 ms / 452 tokens ( 0.27 ms per token, 3642.05 tokens per second) 1.37.967.876 I slot print_timing: id 0 | task 10561 | eval time = 1442.42 ms / 210 tokens ( 6.90 ms per token, 144.89 tokens per second) 1.37.967.877 I slot print_timing: id 0 | task 10561 | total time = 1566.53 ms / 662 tokens 1.37.967.879 I slot print_timing: id 0 | task 10561 | graphs reused = 10087 1.37.967.879 I slot print_timing: id 0 | task 10561 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.967.911 I slot release: id 0 | task 10561 | stop processing: n_tokens = 693, truncated = 0 1.37.986.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 97870032 1.37.986.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 1.38.061.851 I slot launch_slot_: id 0 | task 10774 | processing task, is_child = 0 1.38.961.540 I slot print_timing: id 0 | task 10774 | prompt eval time = 120.53 ms / 404 tokens ( 0.30 ms per token, 3351.95 tokens per second) 1.38.961.546 I slot print_timing: id 0 | task 10774 | eval time = 779.14 ms / 114 tokens ( 6.90 ms per token, 145.03 tokens per second) 1.38.961.547 I slot print_timing: id 0 | task 10774 | total time = 899.67 ms / 518 tokens 1.38.961.547 I slot print_timing: id 0 | task 10774 | graphs reused = 10198 1.38.961.548 I slot print_timing: id 0 | task 10774 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.961.578 I slot release: id 0 | task 10774 | stop processing: n_tokens = 549, truncated = 0 1.38.983.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 98863700 1.38.983.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 1.39.055.872 I slot launch_slot_: id 0 | task 10891 | processing task, is_child = 0 1.39.883.386 I slot print_timing: id 0 | task 10891 | prompt eval time = 110.83 ms / 345 tokens ( 0.32 ms per token, 3112.79 tokens per second) 1.39.883.391 I slot print_timing: id 0 | task 10891 | eval time = 716.66 ms / 106 tokens ( 6.83 ms per token, 146.51 tokens per second) 1.39.883.392 I slot print_timing: id 0 | task 10891 | total time = 827.49 ms / 451 tokens 1.39.883.393 I slot print_timing: id 0 | task 10891 | graphs reused = 10302 1.39.883.394 I slot print_timing: id 0 | task 10891 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.883.425 I slot release: id 0 | task 10891 | stop processing: n_tokens = 482, truncated = 0 1.39.902.603 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 99785546 1.39.902.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.39.970.559 I slot launch_slot_: id 0 | task 11000 | processing task, is_child = 0 1.40.806.182 I slot print_timing: id 0 | task 11000 | prompt eval time = 119.88 ms / 430 tokens ( 0.28 ms per token, 3587.04 tokens per second) 1.40.806.188 I slot print_timing: id 0 | task 11000 | eval time = 715.73 ms / 105 tokens ( 6.88 ms per token, 145.31 tokens per second) 1.40.806.189 I slot print_timing: id 0 | task 11000 | total time = 835.60 ms / 535 tokens 1.40.806.189 I slot print_timing: id 0 | task 11000 | graphs reused = 10404 1.40.806.190 I slot print_timing: id 0 | task 11000 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.806.221 I slot release: id 0 | task 11000 | stop processing: n_tokens = 566, truncated = 0 1.40.823.636 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 100708342 1.40.823.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 1.40.901.513 I slot launch_slot_: id 0 | task 11108 | processing task, is_child = 0 1.41.612.769 I slot print_timing: id 0 | task 11108 | prompt eval time = 108.28 ms / 316 tokens ( 0.34 ms per token, 2918.44 tokens per second) 1.41.612.775 I slot print_timing: id 0 | task 11108 | eval time = 602.96 ms / 85 tokens ( 7.18 ms per token, 139.31 tokens per second) 1.41.612.776 I slot print_timing: id 0 | task 11108 | total time = 711.24 ms / 401 tokens 1.41.612.777 I slot print_timing: id 0 | task 11108 | graphs reused = 10487 1.41.612.778 I slot print_timing: id 0 | task 11108 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.612.805 I slot release: id 0 | task 11108 | stop processing: n_tokens = 432, truncated = 0 1.41.637.581 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 101514926 1.41.637.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 1.41.706.312 I slot launch_slot_: id 0 | task 11196 | processing task, is_child = 0 1.42.545.819 I slot print_timing: id 0 | task 11196 | prompt eval time = 113.63 ms / 354 tokens ( 0.32 ms per token, 3115.35 tokens per second) 1.42.545.825 I slot print_timing: id 0 | task 11196 | eval time = 725.86 ms / 107 tokens ( 6.85 ms per token, 146.03 tokens per second) 1.42.545.826 I slot print_timing: id 0 | task 11196 | total time = 839.49 ms / 461 tokens 1.42.545.827 I slot print_timing: id 0 | task 11196 | graphs reused = 10592 1.42.545.828 I slot print_timing: id 0 | task 11196 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.545.859 I slot release: id 0 | task 11196 | stop processing: n_tokens = 492, truncated = 0 1.42.571.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 102447980 1.42.571.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 1.42.642.767 I slot launch_slot_: id 0 | task 11306 | processing task, is_child = 0 1.43.843.055 I slot print_timing: id 0 | task 11306 | prompt eval time = 122.96 ms / 438 tokens ( 0.28 ms per token, 3562.16 tokens per second) 1.43.843.061 I slot print_timing: id 0 | task 11306 | eval time = 1077.31 ms / 158 tokens ( 6.86 ms per token, 145.73 tokens per second) 1.43.843.062 I slot print_timing: id 0 | task 11306 | total time = 1200.26 ms / 596 tokens 1.43.843.063 I slot print_timing: id 0 | task 11306 | graphs reused = 10747 1.43.843.063 I slot print_timing: id 0 | task 11306 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.843.096 I slot release: id 0 | task 11306 | stop processing: n_tokens = 627, truncated = 0 1.43.866.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 103745217 1.43.866.209 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.43.938.183 I slot launch_slot_: id 0 | task 11467 | processing task, is_child = 0 1.44.540.061 I slot print_timing: id 0 | task 11467 | prompt eval time = 123.38 ms / 457 tokens ( 0.27 ms per token, 3704.12 tokens per second) 1.44.540.068 I slot print_timing: id 0 | task 11467 | eval time = 478.48 ms / 70 tokens ( 6.93 ms per token, 144.21 tokens per second) 1.44.540.070 I slot print_timing: id 0 | task 11467 | total time = 601.86 ms / 527 tokens 1.44.540.071 I slot print_timing: id 0 | task 11467 | graphs reused = 10814 1.44.540.072 I slot print_timing: id 0 | task 11467 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.540.106 I slot release: id 0 | task 11467 | stop processing: n_tokens = 558, truncated = 0 1.44.557.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 104442228 1.44.558.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 1.44.651.369 I slot launch_slot_: id 0 | task 11540 | processing task, is_child = 0 1.45.447.619 I slot print_timing: id 0 | task 11540 | prompt eval time = 127.75 ms / 473 tokens ( 0.27 ms per token, 3702.60 tokens per second) 1.45.447.625 I slot print_timing: id 0 | task 11540 | eval time = 668.48 ms / 98 tokens ( 6.89 ms per token, 145.10 tokens per second) 1.45.447.626 I slot print_timing: id 0 | task 11540 | total time = 796.23 ms / 571 tokens 1.45.447.626 I slot print_timing: id 0 | task 11540 | graphs reused = 10909 1.45.447.627 I slot print_timing: id 0 | task 11540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.447.659 I slot release: id 0 | task 11540 | stop processing: n_tokens = 602, truncated = 0 1.45.471.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 105349780 1.45.471.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.895 MiB) 1.45.539.446 I slot launch_slot_: id 0 | task 11641 | processing task, is_child = 0 1.45.849.394 I slot print_timing: id 0 | task 11641 | prompt eval time = 123.40 ms / 476 tokens ( 0.26 ms per token, 3857.37 tokens per second) 1.45.849.400 I slot print_timing: id 0 | task 11641 | eval time = 186.53 ms / 27 tokens ( 7.17 ms per token, 139.39 tokens per second) 1.45.849.401 I slot print_timing: id 0 | task 11641 | total time = 309.93 ms / 503 tokens 1.45.849.402 I slot print_timing: id 0 | task 11641 | graphs reused = 10933 1.45.849.403 I slot print_timing: id 0 | task 11641 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.849.439 I slot release: id 0 | task 11641 | stop processing: n_tokens = 534, truncated = 0 1.45.865.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 105751561 1.45.865.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.45.957.266 I slot launch_slot_: id 0 | task 11671 | processing task, is_child = 0 1.46.812.651 I slot print_timing: id 0 | task 11671 | prompt eval time = 126.09 ms / 466 tokens ( 0.27 ms per token, 3695.66 tokens per second) 1.46.812.657 I slot print_timing: id 0 | task 11671 | eval time = 729.27 ms / 107 tokens ( 6.88 ms per token, 145.35 tokens per second) 1.46.812.658 I slot print_timing: id 0 | task 11671 | total time = 855.37 ms / 573 tokens 1.46.812.659 I slot print_timing: id 0 | task 11671 | graphs reused = 11037 1.46.812.660 I slot print_timing: id 0 | task 11671 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.812.693 I slot release: id 0 | task 11671 | stop processing: n_tokens = 604, truncated = 0 1.46.841.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 106714814 1.46.841.138 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.46.916.915 I slot launch_slot_: id 0 | task 11781 | processing task, is_child = 0 1.47.575.268 I slot print_timing: id 0 | task 11781 | prompt eval time = 113.65 ms / 415 tokens ( 0.27 ms per token, 3651.50 tokens per second) 1.47.575.274 I slot print_timing: id 0 | task 11781 | eval time = 544.68 ms / 78 tokens ( 7.07 ms per token, 141.37 tokens per second) 1.47.575.274 I slot print_timing: id 0 | task 11781 | total time = 658.33 ms / 493 tokens 1.47.575.275 I slot print_timing: id 0 | task 11781 | graphs reused = 11112 1.47.575.276 I slot print_timing: id 0 | task 11781 | graph reallocs = 0 / 0 (same size) / (changed size) 1.47.575.305 I slot release: id 0 | task 11781 | stop processing: n_tokens = 524, truncated = 0 1.47.598.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 107477426 1.47.598.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.299 MiB) 1.47.680.613 I slot launch_slot_: id 0 | task 11862 | processing task, is_child = 0 1.48.226.054 I slot print_timing: id 0 | task 11862 | prompt eval time = 114.30 ms / 352 tokens ( 0.32 ms per token, 3079.64 tokens per second) 1.48.226.060 I slot print_timing: id 0 | task 11862 | eval time = 431.12 ms / 64 tokens ( 6.84 ms per token, 146.13 tokens per second) 1.48.226.061 I slot print_timing: id 0 | task 11862 | total time = 545.42 ms / 416 tokens 1.48.226.062 I slot print_timing: id 0 | task 11862 | graphs reused = 11174 1.48.226.063 I slot print_timing: id 0 | task 11862 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.226.091 I slot release: id 0 | task 11862 | stop processing: n_tokens = 447, truncated = 0 1.48.253.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 108128212 1.48.253.971 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.48.332.201 I slot launch_slot_: id 0 | task 11929 | processing task, is_child = 0 1.49.366.263 I slot print_timing: id 0 | task 11929 | prompt eval time = 133.49 ms / 550 tokens ( 0.24 ms per token, 4120.19 tokens per second) 1.49.366.268 I slot print_timing: id 0 | task 11929 | eval time = 900.55 ms / 133 tokens ( 6.82 ms per token, 146.58 tokens per second) 1.49.366.269 I slot print_timing: id 0 | task 11929 | total time = 1034.04 ms / 683 tokens 1.49.366.270 I slot print_timing: id 0 | task 11929 | graphs reused = 11305 1.49.366.271 I slot print_timing: id 0 | task 11929 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.366.305 I slot release: id 0 | task 11929 | stop processing: n_tokens = 714, truncated = 0 1.49.393.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 109268426 1.49.393.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 1.49.472.710 I slot launch_slot_: id 0 | task 12066 | processing task, is_child = 0 1.51.167.794 I slot print_timing: id 0 | task 12066 | prompt eval time = 155.66 ms / 772 tokens ( 0.20 ms per token, 4959.62 tokens per second) 1.51.167.800 I slot print_timing: id 0 | task 12066 | eval time = 1539.41 ms / 226 tokens ( 6.84 ms per token, 146.16 tokens per second) 1.51.167.802 I slot print_timing: id 0 | task 12066 | total time = 1695.06 ms / 998 tokens 1.51.167.802 I slot print_timing: id 0 | task 12066 | graphs reused = 11528 1.51.167.803 I slot print_timing: id 0 | task 12066 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.167.842 I slot release: id 0 | task 12066 | stop processing: n_tokens = 1029, truncated = 0 1.51.183.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 111069964 1.51.183.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.51.279.324 I slot launch_slot_: id 0 | task 12296 | processing task, is_child = 0 1.52.666.884 I slot print_timing: id 0 | task 12296 | prompt eval time = 152.25 ms / 683 tokens ( 0.22 ms per token, 4486.01 tokens per second) 1.52.666.890 I slot print_timing: id 0 | task 12296 | eval time = 1235.29 ms / 181 tokens ( 6.86 ms per token, 145.72 tokens per second) 1.52.666.891 I slot print_timing: id 0 | task 12296 | total time = 1387.54 ms / 864 tokens 1.52.666.892 I slot print_timing: id 0 | task 12296 | graphs reused = 11706 1.52.666.893 I slot print_timing: id 0 | task 12296 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.666.930 I slot release: id 0 | task 12296 | stop processing: n_tokens = 895, truncated = 0 1.52.689.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 112569051 1.52.689.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 1.52.779.215 I slot launch_slot_: id 0 | task 12481 | processing task, is_child = 0 1.54.405.641 I slot print_timing: id 0 | task 12481 | prompt eval time = 141.54 ms / 579 tokens ( 0.24 ms per token, 4090.83 tokens per second) 1.54.405.647 I slot print_timing: id 0 | task 12481 | eval time = 1484.87 ms / 218 tokens ( 6.84 ms per token, 146.14 tokens per second) 1.54.405.648 I slot print_timing: id 0 | task 12481 | total time = 1626.41 ms / 797 tokens 1.54.405.648 I slot print_timing: id 0 | task 12481 | graphs reused = 11921 1.54.405.649 I slot print_timing: id 0 | task 12481 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.405.685 I slot release: id 0 | task 12481 | stop processing: n_tokens = 828, truncated = 0 1.54.432.718 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 114307807 1.54.432.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 1.54.452.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 1.54.544.276 I slot launch_slot_: id 0 | task 12703 | processing task, is_child = 0 1.55.396.989 I slot print_timing: id 0 | task 12703 | prompt eval time = 134.19 ms / 500 tokens ( 0.27 ms per token, 3725.92 tokens per second) 1.55.396.994 I slot print_timing: id 0 | task 12703 | eval time = 718.50 ms / 106 tokens ( 6.84 ms per token, 146.14 tokens per second) 1.55.396.995 I slot print_timing: id 0 | task 12703 | total time = 852.69 ms / 606 tokens 1.55.396.996 I slot print_timing: id 0 | task 12703 | graphs reused = 12025 1.55.396.997 I slot print_timing: id 0 | task 12703 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.397.030 I slot release: id 0 | task 12703 | stop processing: n_tokens = 637, truncated = 0 1.55.420.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 115299151 1.55.420.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 1.55.487.188 I slot launch_slot_: id 0 | task 12812 | processing task, is_child = 0 1.57.064.531 I slot print_timing: id 0 | task 12812 | prompt eval time = 158.71 ms / 776 tokens ( 0.20 ms per token, 4889.48 tokens per second) 1.57.064.537 I slot print_timing: id 0 | task 12812 | eval time = 1418.62 ms / 209 tokens ( 6.82 ms per token, 146.62 tokens per second) 1.57.064.538 I slot print_timing: id 0 | task 12812 | total time = 1577.32 ms / 985 tokens 1.57.064.539 I slot print_timing: id 0 | task 12812 | graphs reused = 12232 1.57.064.539 I slot print_timing: id 0 | task 12812 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.064.580 I slot release: id 0 | task 12812 | stop processing: n_tokens = 1016, truncated = 0 1.57.089.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 116966701 1.57.089.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 1.57.169.661 I slot launch_slot_: id 0 | task 13025 | processing task, is_child = 0 1.58.635.017 I slot print_timing: id 0 | task 13025 | prompt eval time = 130.33 ms / 504 tokens ( 0.26 ms per token, 3867.17 tokens per second) 1.58.635.022 I slot print_timing: id 0 | task 13025 | eval time = 1335.01 ms / 197 tokens ( 6.81 ms per token, 146.82 tokens per second) 1.58.635.023 I slot print_timing: id 0 | task 13025 | total time = 1465.34 ms / 701 tokens 1.58.635.024 I slot print_timing: id 0 | task 13025 | graphs reused = 12427 1.58.635.025 I slot print_timing: id 0 | task 13025 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.635.058 I slot release: id 0 | task 13025 | stop processing: n_tokens = 732, truncated = 0 1.58.650.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 118537179 1.58.650.656 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.110 MiB) 1.58.718.708 I slot launch_slot_: id 0 | task 13225 | processing task, is_child = 0 2.00.272.103 I slot print_timing: id 0 | task 13225 | prompt eval time = 144.16 ms / 633 tokens ( 0.23 ms per token, 4391.02 tokens per second) 2.00.272.109 I slot print_timing: id 0 | task 13225 | eval time = 1409.22 ms / 207 tokens ( 6.84 ms per token, 146.18 tokens per second) 2.00.272.110 I slot print_timing: id 0 | task 13225 | total time = 1553.38 ms / 840 tokens 2.00.272.111 I slot print_timing: id 0 | task 13225 | graphs reused = 12631 2.00.272.111 I slot print_timing: id 0 | task 13225 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.272.148 I slot release: id 0 | task 13225 | stop processing: n_tokens = 871, truncated = 0 2.00.287.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 120174269 2.00.287.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.867 MiB) 2.00.368.361 I slot launch_slot_: id 0 | task 13436 | processing task, is_child = 0 2.01.399.609 I slot print_timing: id 0 | task 13436 | prompt eval time = 121.21 ms / 395 tokens ( 0.31 ms per token, 3258.78 tokens per second) 2.01.399.615 I slot print_timing: id 0 | task 13436 | eval time = 910.02 ms / 134 tokens ( 6.84 ms per token, 146.15 tokens per second) 2.01.399.616 I slot print_timing: id 0 | task 13436 | total time = 1031.23 ms / 529 tokens 2.01.399.616 I slot print_timing: id 0 | task 13436 | graphs reused = 12762 2.01.399.617 I slot print_timing: id 0 | task 13436 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.399.647 I slot release: id 0 | task 13436 | stop processing: n_tokens = 560, truncated = 0 2.01.428.588 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 121301768 2.01.428.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.01.495.410 I slot launch_slot_: id 0 | task 13573 | processing task, is_child = 0 2.03.054.983 I slot print_timing: id 0 | task 13573 | prompt eval time = 137.45 ms / 584 tokens ( 0.24 ms per token, 4248.76 tokens per second) 2.03.054.989 I slot print_timing: id 0 | task 13573 | eval time = 1422.10 ms / 209 tokens ( 6.84 ms per token, 146.26 tokens per second) 2.03.054.990 I slot print_timing: id 0 | task 13573 | total time = 1559.55 ms / 793 tokens 2.03.054.991 I slot print_timing: id 0 | task 13573 | graphs reused = 12968 2.03.054.992 I slot print_timing: id 0 | task 13573 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.055.029 I slot release: id 0 | task 13573 | stop processing: n_tokens = 824, truncated = 0 2.03.079.342 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 122957150 2.03.079.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.03.167.752 I slot launch_slot_: id 0 | task 13786 | processing task, is_child = 0 2.04.916.047 I slot print_timing: id 0 | task 13786 | prompt eval time = 152.28 ms / 695 tokens ( 0.22 ms per token, 4563.90 tokens per second) 2.04.916.052 I slot print_timing: id 0 | task 13786 | eval time = 1595.99 ms / 230 tokens ( 6.97 ms per token, 143.48 tokens per second) 2.04.916.053 I slot print_timing: id 0 | task 13786 | total time = 1748.27 ms / 925 tokens 2.04.916.054 I slot print_timing: id 0 | task 13786 | graphs reused = 13195 2.04.916.055 I slot print_timing: id 0 | task 13786 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.916.094 I slot release: id 0 | task 13786 | stop processing: n_tokens = 956, truncated = 0 2.04.932.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 124818215 2.04.932.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.05.030.484 I slot launch_slot_: id 0 | task 14020 | processing task, is_child = 0 2.06.495.465 I slot print_timing: id 0 | task 14020 | prompt eval time = 165.63 ms / 769 tokens ( 0.22 ms per token, 4642.77 tokens per second) 2.06.495.471 I slot print_timing: id 0 | task 14020 | eval time = 1299.33 ms / 191 tokens ( 6.84 ms per token, 146.23 tokens per second) 2.06.495.472 I slot print_timing: id 0 | task 14020 | total time = 1464.96 ms / 960 tokens 2.06.495.473 I slot print_timing: id 0 | task 14020 | graphs reused = 13384 2.06.495.474 I slot print_timing: id 0 | task 14020 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.495.513 I slot release: id 0 | task 14020 | stop processing: n_tokens = 991, truncated = 0 2.06.500.023 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 126397634 2.06.500.092 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.06.519.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.06.616.104 I slot launch_slot_: id 0 | task 14215 | processing task, is_child = 0 2.07.596.660 I slot print_timing: id 0 | task 14215 | prompt eval time = 137.51 ms / 576 tokens ( 0.24 ms per token, 4188.69 tokens per second) 2.07.596.666 I slot print_timing: id 0 | task 14215 | eval time = 843.02 ms / 124 tokens ( 6.85 ms per token, 145.90 tokens per second) 2.07.596.667 I slot print_timing: id 0 | task 14215 | total time = 980.54 ms / 700 tokens 2.07.596.667 I slot print_timing: id 0 | task 14215 | graphs reused = 13506 2.07.596.668 I slot print_timing: id 0 | task 14215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.596.703 I slot release: id 0 | task 14215 | stop processing: n_tokens = 731, truncated = 0 2.07.625.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 127498824 2.07.625.824 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.07.704.139 I slot launch_slot_: id 0 | task 14343 | processing task, is_child = 0 2.09.728.183 I slot print_timing: id 0 | task 14343 | prompt eval time = 148.30 ms / 655 tokens ( 0.23 ms per token, 4416.66 tokens per second) 2.09.728.189 I slot print_timing: id 0 | task 14343 | eval time = 1875.72 ms / 275 tokens ( 6.85 ms per token, 146.08 tokens per second) 2.09.728.190 I slot print_timing: id 0 | task 14343 | total time = 2024.03 ms / 930 tokens 2.09.728.191 I slot print_timing: id 0 | task 14343 | graphs reused = 13778 2.09.728.192 I slot print_timing: id 0 | task 14343 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.728.229 I slot release: id 0 | task 14343 | stop processing: n_tokens = 961, truncated = 0 2.09.743.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 129630350 2.09.743.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.09.825.464 I slot launch_slot_: id 0 | task 14622 | processing task, is_child = 0 2.10.795.915 I slot print_timing: id 0 | task 14622 | prompt eval time = 145.11 ms / 621 tokens ( 0.23 ms per token, 4279.54 tokens per second) 2.10.795.920 I slot print_timing: id 0 | task 14622 | eval time = 825.32 ms / 121 tokens ( 6.88 ms per token, 145.40 tokens per second) 2.10.795.921 I slot print_timing: id 0 | task 14622 | total time = 970.43 ms / 742 tokens 2.10.795.922 I slot print_timing: id 0 | task 14622 | graphs reused = 13896 2.10.795.923 I slot print_timing: id 0 | task 14622 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.795.959 I slot release: id 0 | task 14622 | stop processing: n_tokens = 773, truncated = 0 2.10.823.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 130698080 2.10.823.909 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.10.906.422 I slot launch_slot_: id 0 | task 14747 | processing task, is_child = 0 2.12.306.682 I slot print_timing: id 0 | task 14747 | prompt eval time = 157.90 ms / 767 tokens ( 0.21 ms per token, 4857.60 tokens per second) 2.12.306.688 I slot print_timing: id 0 | task 14747 | eval time = 1242.34 ms / 178 tokens ( 7.02 ms per token, 142.47 tokens per second) 2.12.306.689 I slot print_timing: id 0 | task 14747 | total time = 1400.24 ms / 945 tokens 2.12.306.690 I slot print_timing: id 0 | task 14747 | graphs reused = 14072 2.12.306.691 I slot print_timing: id 0 | task 14747 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.306.738 I slot release: id 0 | task 14747 | stop processing: n_tokens = 976, truncated = 0 2.12.330.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 132208860 2.12.330.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.12.427.017 I slot launch_slot_: id 0 | task 14929 | processing task, is_child = 0 2.14.022.758 I slot print_timing: id 0 | task 14929 | prompt eval time = 175.04 ms / 864 tokens ( 0.20 ms per token, 4935.93 tokens per second) 2.14.022.764 I slot print_timing: id 0 | task 14929 | eval time = 1420.68 ms / 203 tokens ( 7.03 ms per token, 142.19 tokens per second) 2.14.022.765 I slot print_timing: id 0 | task 14929 | total time = 1595.72 ms / 1067 tokens 2.14.022.766 I slot print_timing: id 0 | task 14929 | graphs reused = 14272 2.14.022.767 I slot print_timing: id 0 | task 14929 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.022.819 I slot release: id 0 | task 14929 | stop processing: n_tokens = 1098, truncated = 0 2.14.047.991 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 133924941 2.14.048.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.14.067.572 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.14.164.685 I slot launch_slot_: id 0 | task 15136 | processing task, is_child = 0 2.15.196.094 I slot print_timing: id 0 | task 15136 | prompt eval time = 151.20 ms / 646 tokens ( 0.23 ms per token, 4272.52 tokens per second) 2.15.196.100 I slot print_timing: id 0 | task 15136 | eval time = 880.19 ms / 129 tokens ( 6.88 ms per token, 145.42 tokens per second) 2.15.196.101 I slot print_timing: id 0 | task 15136 | total time = 1031.39 ms / 775 tokens 2.15.196.102 I slot print_timing: id 0 | task 15136 | graphs reused = 14398 2.15.196.103 I slot print_timing: id 0 | task 15136 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.196.142 I slot release: id 0 | task 15136 | stop processing: n_tokens = 806, truncated = 0 2.15.223.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 135098263 2.15.224.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.15.299.137 I slot launch_slot_: id 0 | task 15269 | processing task, is_child = 0 2.17.006.363 I slot print_timing: id 0 | task 15269 | prompt eval time = 155.42 ms / 720 tokens ( 0.22 ms per token, 4632.64 tokens per second) 2.17.006.369 I slot print_timing: id 0 | task 15269 | eval time = 1551.79 ms / 219 tokens ( 7.12 ms per token, 140.48 tokens per second) 2.17.006.370 I slot print_timing: id 0 | task 15269 | total time = 1707.21 ms / 939 tokens 2.17.006.371 I slot print_timing: id 0 | task 15269 | graphs reused = 14614 2.17.006.371 I slot print_timing: id 0 | task 15269 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.006.412 I slot release: id 0 | task 15269 | stop processing: n_tokens = 970, truncated = 0 2.17.030.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 136908533 2.17.031.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.203 MiB) 2.17.108.027 I slot launch_slot_: id 0 | task 15492 | processing task, is_child = 0 2.18.695.210 I slot print_timing: id 0 | task 15492 | prompt eval time = 134.76 ms / 509 tokens ( 0.26 ms per token, 3777.09 tokens per second) 2.18.695.215 I slot print_timing: id 0 | task 15492 | eval time = 1452.40 ms / 214 tokens ( 6.82 ms per token, 146.65 tokens per second) 2.18.695.216 I slot print_timing: id 0 | task 15492 | total time = 1587.16 ms / 723 tokens 2.18.695.217 I slot print_timing: id 0 | task 15492 | graphs reused = 14826 2.18.695.218 I slot print_timing: id 0 | task 15492 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.695.251 I slot release: id 0 | task 15492 | stop processing: n_tokens = 754, truncated = 0 2.18.715.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 138597372 2.18.715.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.18.785.125 I slot launch_slot_: id 0 | task 15709 | processing task, is_child = 0 2.20.573.265 I slot print_timing: id 0 | task 15709 | prompt eval time = 138.28 ms / 581 tokens ( 0.24 ms per token, 4201.56 tokens per second) 2.20.573.271 I slot print_timing: id 0 | task 15709 | eval time = 1649.84 ms / 242 tokens ( 6.85 ms per token, 146.07 tokens per second) 2.20.573.272 I slot print_timing: id 0 | task 15709 | total time = 1788.12 ms / 823 tokens 2.20.573.273 I slot print_timing: id 0 | task 15709 | graphs reused = 15065 2.20.573.274 I slot print_timing: id 0 | task 15709 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.573.312 I slot release: id 0 | task 15709 | stop processing: n_tokens = 854, truncated = 0 2.20.594.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 140475434 2.20.594.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.20.677.735 I slot launch_slot_: id 0 | task 15955 | processing task, is_child = 0 2.22.361.887 I slot print_timing: id 0 | task 15955 | prompt eval time = 178.29 ms / 925 tokens ( 0.19 ms per token, 5188.09 tokens per second) 2.22.361.893 I slot print_timing: id 0 | task 15955 | eval time = 1505.84 ms / 220 tokens ( 6.88 ms per token, 145.43 tokens per second) 2.22.361.894 I slot print_timing: id 0 | task 15955 | total time = 1684.13 ms / 1145 tokens 2.22.361.894 I slot print_timing: id 0 | task 15955 | graphs reused = 15282 2.22.361.895 I slot print_timing: id 0 | task 15955 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.361.942 I slot release: id 0 | task 15955 | stop processing: n_tokens = 1176, truncated = 0 2.22.390.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 142264063 2.22.390.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 2.22.478.949 I slot launch_slot_: id 0 | task 16179 | processing task, is_child = 0 2.24.355.219 I slot print_timing: id 0 | task 16179 | prompt eval time = 173.37 ms / 885 tokens ( 0.20 ms per token, 5104.81 tokens per second) 2.24.355.227 I slot print_timing: id 0 | task 16179 | eval time = 1702.88 ms / 245 tokens ( 6.98 ms per token, 143.29 tokens per second) 2.24.355.228 I slot print_timing: id 0 | task 16179 | total time = 1876.25 ms / 1130 tokens 2.24.355.229 I slot print_timing: id 0 | task 16179 | graphs reused = 15524 2.24.355.230 I slot print_timing: id 0 | task 16179 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.355.275 I slot release: id 0 | task 16179 | stop processing: n_tokens = 1161, truncated = 0 2.24.380.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 144257396 2.24.380.958 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 2.24.478.753 I slot launch_slot_: id 0 | task 16428 | processing task, is_child = 0 2.25.932.739 I slot print_timing: id 0 | task 16428 | prompt eval time = 120.80 ms / 392 tokens ( 0.31 ms per token, 3245.17 tokens per second) 2.25.932.745 I slot print_timing: id 0 | task 16428 | eval time = 1333.17 ms / 196 tokens ( 6.84 ms per token, 146.27 tokens per second) 2.25.932.747 I slot print_timing: id 0 | task 16428 | total time = 1453.97 ms / 588 tokens 2.25.932.747 I slot print_timing: id 0 | task 16428 | graphs reused = 15717 2.25.932.748 I slot print_timing: id 0 | task 16428 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.932.779 I slot release: id 0 | task 16428 | stop processing: n_tokens = 619, truncated = 0 2.25.958.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 145834900 2.25.958.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 2.26.035.557 I slot launch_slot_: id 0 | task 16627 | processing task, is_child = 0 2.26.507.731 I slot print_timing: id 0 | task 16627 | prompt eval time = 115.89 ms / 331 tokens ( 0.35 ms per token, 2856.06 tokens per second) 2.26.507.737 I slot print_timing: id 0 | task 16627 | eval time = 356.26 ms / 53 tokens ( 6.85 ms per token, 145.96 tokens per second) 2.26.507.738 I slot print_timing: id 0 | task 16627 | total time = 472.16 ms / 384 tokens 2.26.507.739 I slot print_timing: id 0 | task 16627 | graphs reused = 15768 2.26.507.740 I slot print_timing: id 0 | task 16627 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.507.767 I slot release: id 0 | task 16627 | stop processing: n_tokens = 415, truncated = 0 2.26.523.841 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 146409888 2.26.523.883 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 2.26.623.096 I slot launch_slot_: id 0 | task 16683 | processing task, is_child = 0 2.27.784.504 I slot print_timing: id 0 | task 16683 | prompt eval time = 113.55 ms / 357 tokens ( 0.32 ms per token, 3143.91 tokens per second) 2.27.784.509 I slot print_timing: id 0 | task 16683 | eval time = 1047.84 ms / 154 tokens ( 6.85 ms per token, 146.02 tokens per second) 2.27.784.510 I slot print_timing: id 0 | task 16683 | total time = 1161.39 ms / 511 tokens 2.27.784.511 I slot print_timing: id 0 | task 16683 | graphs reused = 15919 2.27.784.512 I slot print_timing: id 0 | task 16683 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.784.539 I slot release: id 0 | task 16683 | stop processing: n_tokens = 542, truncated = 0 2.27.810.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 147686660 2.27.810.340 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 2.27.883.683 I slot launch_slot_: id 0 | task 16840 | processing task, is_child = 0 2.28.333.897 I slot print_timing: id 0 | task 16840 | prompt eval time = 119.47 ms / 315 tokens ( 0.38 ms per token, 2636.60 tokens per second) 2.28.333.902 I slot print_timing: id 0 | task 16840 | eval time = 330.72 ms / 49 tokens ( 6.89 ms per token, 145.14 tokens per second) 2.28.333.903 I slot print_timing: id 0 | task 16840 | total time = 450.19 ms / 364 tokens 2.28.333.904 I slot print_timing: id 0 | task 16840 | graphs reused = 15966 2.28.333.905 I slot print_timing: id 0 | task 16840 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.333.932 I slot release: id 0 | task 16840 | stop processing: n_tokens = 395, truncated = 0 2.28.356.394 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 148236053 2.28.356.438 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 2.28.426.642 I slot launch_slot_: id 0 | task 16892 | processing task, is_child = 0 2.28.942.145 I slot print_timing: id 0 | task 16892 | prompt eval time = 110.41 ms / 378 tokens ( 0.29 ms per token, 3423.57 tokens per second) 2.28.942.151 I slot print_timing: id 0 | task 16892 | eval time = 405.07 ms / 60 tokens ( 6.87 ms per token, 145.65 tokens per second) 2.28.942.152 I slot print_timing: id 0 | task 16892 | total time = 515.48 ms / 438 tokens 2.28.942.153 I slot print_timing: id 0 | task 16892 | graphs reused = 16024 2.28.942.154 I slot print_timing: id 0 | task 16892 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.942.185 I slot release: id 0 | task 16892 | stop processing: n_tokens = 469, truncated = 0 2.28.961.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 148844306 2.28.962.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 2.29.032.431 I slot launch_slot_: id 0 | task 16955 | processing task, is_child = 0 2.29.325.107 I slot print_timing: id 0 | task 16955 | prompt eval time = 104.15 ms / 295 tokens ( 0.35 ms per token, 2832.34 tokens per second) 2.29.325.113 I slot print_timing: id 0 | task 16955 | eval time = 188.50 ms / 28 tokens ( 6.98 ms per token, 143.23 tokens per second) 2.29.325.114 I slot print_timing: id 0 | task 16955 | total time = 292.66 ms / 323 tokens 2.29.325.115 I slot print_timing: id 0 | task 16955 | graphs reused = 16050 2.29.325.115 I slot print_timing: id 0 | task 16955 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.325.144 I slot release: id 0 | task 16955 | stop processing: n_tokens = 354, truncated = 0 2.29.352.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 149227265 2.29.352.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 2.29.446.747 I slot launch_slot_: id 0 | task 16986 | processing task, is_child = 0 2.30.869.895 I slot print_timing: id 0 | task 16986 | prompt eval time = 111.31 ms / 337 tokens ( 0.33 ms per token, 3027.53 tokens per second) 2.30.869.901 I slot print_timing: id 0 | task 16986 | eval time = 1311.82 ms / 193 tokens ( 6.83 ms per token, 146.36 tokens per second) 2.30.869.902 I slot print_timing: id 0 | task 16986 | total time = 1423.13 ms / 530 tokens 2.30.869.903 I slot print_timing: id 0 | task 16986 | graphs reused = 16240 2.30.869.904 I slot print_timing: id 0 | task 16986 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.869.931 I slot release: id 0 | task 16986 | stop processing: n_tokens = 561, truncated = 0 2.30.892.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 150772052 2.30.892.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 2.30.962.276 I slot launch_slot_: id 0 | task 17182 | processing task, is_child = 0 2.31.657.510 I slot print_timing: id 0 | task 17182 | prompt eval time = 106.43 ms / 325 tokens ( 0.33 ms per token, 3053.59 tokens per second) 2.31.657.516 I slot print_timing: id 0 | task 17182 | eval time = 588.78 ms / 86 tokens ( 6.93 ms per token, 144.37 tokens per second) 2.31.657.517 I slot print_timing: id 0 | task 17182 | total time = 695.22 ms / 411 tokens 2.31.657.518 I slot print_timing: id 0 | task 17182 | graphs reused = 16324 2.31.657.519 I slot print_timing: id 0 | task 17182 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.657.550 I slot release: id 0 | task 17182 | stop processing: n_tokens = 442, truncated = 0 2.31.673.642 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.072 2.31.741.035 I slot launch_slot_: id 0 | task 17271 | processing task, is_child = 0 2.33.709.149 I slot print_timing: id 0 | task 17271 | prompt eval time = 103.10 ms / 264 tokens ( 0.39 ms per token, 2560.67 tokens per second) 2.33.709.155 I slot print_timing: id 0 | task 17271 | eval time = 1864.99 ms / 275 tokens ( 6.81 ms per token, 146.92 tokens per second) 2.33.709.157 I slot print_timing: id 0 | task 17271 | total time = 1968.09 ms / 539 tokens 2.33.709.157 I slot print_timing: id 0 | task 17271 | graphs reused = 16596 2.33.709.158 I slot print_timing: id 0 | task 17271 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.709.186 I slot release: id 0 | task 17271 | stop processing: n_tokens = 570, truncated = 0 2.33.730.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 570, t_last = 153611308 2.33.730.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 2.33.809.427 I slot launch_slot_: id 0 | task 17549 | processing task, is_child = 0 2.33.985.681 I slot print_timing: id 0 | task 17549 | prompt eval time = 116.54 ms / 331 tokens ( 0.35 ms per token, 2840.23 tokens per second) 2.33.985.686 I slot print_timing: id 0 | task 17549 | eval time = 59.70 ms / 9 tokens ( 7.46 ms per token, 134.01 tokens per second) 2.33.985.687 I slot print_timing: id 0 | task 17549 | total time = 176.24 ms / 340 tokens 2.33.985.688 I slot print_timing: id 0 | task 17549 | graphs reused = 16603 2.33.985.689 I slot print_timing: id 0 | task 17549 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.985.715 I slot release: id 0 | task 17549 | stop processing: n_tokens = 371, truncated = 0 2.34.012.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 371, t_last = 153887837 2.34.012.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 2.34.090.662 I slot launch_slot_: id 0 | task 17561 | processing task, is_child = 0 2.34.976.075 I slot print_timing: id 0 | task 17561 | prompt eval time = 112.59 ms / 333 tokens ( 0.34 ms per token, 2957.61 tokens per second) 2.34.976.081 I slot print_timing: id 0 | task 17561 | eval time = 772.80 ms / 114 tokens ( 6.84 ms per token, 146.22 tokens per second) 2.34.976.082 I slot print_timing: id 0 | task 17561 | total time = 885.39 ms / 447 tokens 2.34.976.082 I slot print_timing: id 0 | task 17561 | graphs reused = 16715 2.34.976.083 I slot print_timing: id 0 | task 17561 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.976.110 I slot release: id 0 | task 17561 | stop processing: n_tokens = 478, truncated = 0 2.34.992.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 154878231 2.34.992.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 2.35.066.917 I slot launch_slot_: id 0 | task 17678 | processing task, is_child = 0 2.36.887.677 I slot print_timing: id 0 | task 17678 | prompt eval time = 112.83 ms / 346 tokens ( 0.33 ms per token, 3066.67 tokens per second) 2.36.887.683 I slot print_timing: id 0 | task 17678 | eval time = 1707.91 ms / 251 tokens ( 6.83 ms per token, 146.38 tokens per second) 2.36.887.684 I slot print_timing: id 0 | task 17678 | total time = 1820.74 ms / 597 tokens 2.36.887.685 I slot print_timing: id 0 | task 17678 | graphs reused = 16963 2.36.887.686 I slot print_timing: id 0 | task 17678 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.887.715 I slot release: id 0 | task 17678 | stop processing: n_tokens = 628, truncated = 0 2.36.908.205 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 628, t_last = 156789836 2.36.908.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 2.36.981.620 I slot launch_slot_: id 0 | task 17932 | processing task, is_child = 0 2.37.361.563 I slot print_timing: id 0 | task 17932 | prompt eval time = 111.23 ms / 325 tokens ( 0.34 ms per token, 2921.79 tokens per second) 2.37.361.569 I slot print_timing: id 0 | task 17932 | eval time = 268.69 ms / 40 tokens ( 6.89 ms per token, 145.15 tokens per second) 2.37.361.570 I slot print_timing: id 0 | task 17932 | total time = 379.92 ms / 365 tokens 2.37.361.570 I slot print_timing: id 0 | task 17932 | graphs reused = 17001 2.37.361.571 I slot print_timing: id 0 | task 17932 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.361.600 I slot release: id 0 | task 17932 | stop processing: n_tokens = 396, truncated = 0 2.37.375.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 157263721 2.37.375.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 2.37.466.774 I slot launch_slot_: id 0 | task 17975 | processing task, is_child = 0 2.39.101.691 I slot print_timing: id 0 | task 17975 | prompt eval time = 112.81 ms / 322 tokens ( 0.35 ms per token, 2854.46 tokens per second) 2.39.101.696 I slot print_timing: id 0 | task 17975 | eval time = 1522.09 ms / 224 tokens ( 6.83 ms per token, 146.51 tokens per second) 2.39.101.697 I slot print_timing: id 0 | task 17975 | total time = 1634.90 ms / 546 tokens 2.39.101.698 I slot print_timing: id 0 | task 17975 | graphs reused = 17222 2.39.101.699 I slot print_timing: id 0 | task 17975 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.101.726 I slot release: id 0 | task 17975 | stop processing: n_tokens = 577, truncated = 0 2.39.124.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 159003848 2.39.124.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 2.39.194.673 I slot launch_slot_: id 0 | task 18202 | processing task, is_child = 0 2.41.141.598 I slot print_timing: id 0 | task 18202 | prompt eval time = 107.89 ms / 338 tokens ( 0.32 ms per token, 3132.85 tokens per second) 2.41.141.604 I slot print_timing: id 0 | task 18202 | eval time = 1839.02 ms / 271 tokens ( 6.81 ms per token, 146.82 tokens per second) 2.41.141.605 I slot print_timing: id 0 | task 18202 | total time = 1946.91 ms / 609 tokens 2.41.141.606 I slot print_timing: id 0 | task 18202 | graphs reused = 17490 2.41.141.607 I slot print_timing: id 0 | task 18202 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.141.633 I slot release: id 0 | task 18202 | stop processing: n_tokens = 640, truncated = 0 2.41.159.941 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 640, t_last = 161043755 2.41.204.258 I slot launch_slot_: id 0 | task 18476 | processing task, is_child = 0 2.44.318.160 I slot print_timing: id 0 | task 18476 | n_gen = 441, tg = 146.43 t/s, tg_3s = 146.76 t/s 2.47.320.859 I slot print_timing: id 0 | task 18476 | n_gen = 881, tg = 146.48 t/s, tg_3s = 146.53 t/s 2.48.301.481 I slot print_timing: id 0 | task 18476 | prompt eval time = 109.05 ms / 347 tokens ( 0.31 ms per token, 3182.08 tokens per second) 2.48.301.487 I slot print_timing: id 0 | task 18476 | eval time = 6988.16 ms / 1024 tokens ( 6.83 ms per token, 146.39 tokens per second) 2.48.301.488 I slot print_timing: id 0 | task 18476 | total time = 7097.20 ms / 1371 tokens 2.48.301.489 I slot print_timing: id 0 | task 18476 | graphs reused = 18508 2.48.301.490 I slot print_timing: id 0 | task 18476 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.301.519 I slot release: id 0 | task 18476 | stop processing: n_tokens = 1402, truncated = 0 2.48.318.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 168203640 2.48.318.518 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 2.48.405.764 I slot launch_slot_: id 0 | task 19503 | processing task, is_child = 0 2.49.916.120 I slot print_timing: id 0 | task 19503 | prompt eval time = 116.35 ms / 331 tokens ( 0.35 ms per token, 2844.94 tokens per second) 2.49.916.125 I slot print_timing: id 0 | task 19503 | eval time = 1393.99 ms / 205 tokens ( 6.83 ms per token, 146.34 tokens per second) 2.49.916.126 I slot print_timing: id 0 | task 19503 | total time = 1510.34 ms / 536 tokens 2.49.916.127 I slot print_timing: id 0 | task 19503 | graphs reused = 18710 2.49.916.127 I slot print_timing: id 0 | task 19503 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.916.155 I slot release: id 0 | task 19503 | stop processing: n_tokens = 567, truncated = 0 2.49.942.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 169818276 2.49.942.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 2.50.022.173 I slot launch_slot_: id 0 | task 19711 | processing task, is_child = 0 2.50.524.803 I slot print_timing: id 0 | task 19711 | prompt eval time = 118.47 ms / 345 tokens ( 0.34 ms per token, 2912.25 tokens per second) 2.50.524.809 I slot print_timing: id 0 | task 19711 | eval time = 384.15 ms / 57 tokens ( 6.86 ms per token, 145.78 tokens per second) 2.50.524.810 I slot print_timing: id 0 | task 19711 | total time = 502.61 ms / 402 tokens 2.50.524.811 I slot print_timing: id 0 | task 19711 | graphs reused = 18765 2.50.524.811 I slot print_timing: id 0 | task 19711 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.524.840 I slot release: id 0 | task 19711 | stop processing: n_tokens = 433, truncated = 0 2.50.548.303 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 170426961 2.50.548.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 2.50.646.916 I slot launch_slot_: id 0 | task 19771 | processing task, is_child = 0 2.51.202.061 I slot print_timing: id 0 | task 19771 | prompt eval time = 111.47 ms / 320 tokens ( 0.35 ms per token, 2870.65 tokens per second) 2.51.202.068 I slot print_timing: id 0 | task 19771 | eval time = 443.65 ms / 66 tokens ( 6.83 ms per token, 146.51 tokens per second) 2.51.202.069 I slot print_timing: id 0 | task 19771 | total time = 555.13 ms / 386 tokens 2.51.202.069 I slot print_timing: id 0 | task 19771 | graphs reused = 18829 2.51.202.070 I slot print_timing: id 0 | task 19771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.202.099 I slot release: id 0 | task 19771 | stop processing: n_tokens = 417, truncated = 0 2.51.218.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 171104220 2.51.218.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 2.51.287.539 I slot launch_slot_: id 0 | task 19840 | processing task, is_child = 0 2.51.742.163 I slot print_timing: id 0 | task 19840 | prompt eval time = 106.29 ms / 297 tokens ( 0.36 ms per token, 2794.14 tokens per second) 2.51.742.168 I slot print_timing: id 0 | task 19840 | eval time = 348.31 ms / 47 tokens ( 7.57 ms per token, 132.07 tokens per second) 2.51.742.170 I slot print_timing: id 0 | task 19840 | total time = 454.60 ms / 344 tokens 2.51.742.171 I slot print_timing: id 0 | task 19840 | graphs reused = 18874 2.51.742.171 I slot print_timing: id 0 | task 19840 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.742.198 I slot release: id 0 | task 19840 | stop processing: n_tokens = 375, truncated = 0 2.51.770.226 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 171644319 2.51.770.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 2.51.864.021 I slot launch_slot_: id 0 | task 19890 | processing task, is_child = 0 2.52.702.198 I slot print_timing: id 0 | task 19890 | prompt eval time = 114.22 ms / 343 tokens ( 0.33 ms per token, 3002.85 tokens per second) 2.52.702.205 I slot print_timing: id 0 | task 19890 | eval time = 723.93 ms / 107 tokens ( 6.83 ms per token, 146.42 tokens per second) 2.52.702.206 I slot print_timing: id 0 | task 19890 | total time = 838.16 ms / 450 tokens 2.52.702.207 I slot print_timing: id 0 | task 19890 | graphs reused = 18979 2.52.702.208 I slot print_timing: id 0 | task 19890 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.702.239 I slot release: id 0 | task 19890 | stop processing: n_tokens = 481, truncated = 0 2.52.721.062 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 172604360 2.52.767.754 I slot launch_slot_: id 0 | task 20000 | processing task, is_child = 0 2.53.582.164 I slot print_timing: id 0 | task 20000 | prompt eval time = 112.31 ms / 371 tokens ( 0.30 ms per token, 3303.45 tokens per second) 2.53.582.170 I slot print_timing: id 0 | task 20000 | eval time = 702.09 ms / 104 tokens ( 6.82 ms per token, 146.71 tokens per second) 2.53.582.171 I slot print_timing: id 0 | task 20000 | total time = 814.39 ms / 475 tokens 2.53.582.172 I slot print_timing: id 0 | task 20000 | graphs reused = 19081 2.53.582.172 I slot print_timing: id 0 | task 20000 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.582.202 I slot release: id 0 | task 20000 | stop processing: n_tokens = 506, truncated = 0 2.53.598.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 173484323 2.53.598.109 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 2.53.678.382 I slot launch_slot_: id 0 | task 20107 | processing task, is_child = 0 2.54.440.221 I slot print_timing: id 0 | task 20107 | prompt eval time = 107.34 ms / 292 tokens ( 0.37 ms per token, 2720.20 tokens per second) 2.54.440.227 I slot print_timing: id 0 | task 20107 | eval time = 654.48 ms / 97 tokens ( 6.82 ms per token, 146.68 tokens per second) 2.54.440.228 I slot print_timing: id 0 | task 20107 | total time = 761.82 ms / 389 tokens 2.54.440.229 I slot print_timing: id 0 | task 20107 | graphs reused = 19176 2.54.440.229 I slot print_timing: id 0 | task 20107 | graph reallocs = 0 / 0 (same size) / (changed size) 2.54.440.256 I slot release: id 0 | task 20107 | stop processing: n_tokens = 420, truncated = 0 2.54.461.110 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 174342377 2.54.461.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 2.54.549.541 I slot launch_slot_: id 0 | task 20207 | processing task, is_child = 0 2.55.216.392 I slot print_timing: id 0 | task 20207 | prompt eval time = 107.53 ms / 301 tokens ( 0.36 ms per token, 2799.27 tokens per second) 2.55.216.399 I slot print_timing: id 0 | task 20207 | eval time = 559.30 ms / 83 tokens ( 6.82 ms per token, 146.61 tokens per second) 2.55.216.400 I slot print_timing: id 0 | task 20207 | total time = 666.83 ms / 384 tokens 2.55.216.401 I slot print_timing: id 0 | task 20207 | graphs reused = 19257 2.55.216.402 I slot print_timing: id 0 | task 20207 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.216.431 I slot release: id 0 | task 20207 | stop processing: n_tokens = 415, truncated = 0 2.55.240.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 175118552 2.55.240.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 2.55.318.992 I slot launch_slot_: id 0 | task 20293 | processing task, is_child = 0 2.55.845.840 I slot print_timing: id 0 | task 20293 | prompt eval time = 109.10 ms / 303 tokens ( 0.36 ms per token, 2777.34 tokens per second) 2.55.845.846 I slot print_timing: id 0 | task 20293 | eval time = 417.73 ms / 62 tokens ( 6.85 ms per token, 146.03 tokens per second) 2.55.845.847 I slot print_timing: id 0 | task 20293 | total time = 526.83 ms / 365 tokens 2.55.845.848 I slot print_timing: id 0 | task 20293 | graphs reused = 19317 2.55.845.849 I slot print_timing: id 0 | task 20293 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.845.874 I slot release: id 0 | task 20293 | stop processing: n_tokens = 396, truncated = 0 2.55.860.370 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 396, t_last = 175747996 2.55.860.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 2.55.947.850 I slot launch_slot_: id 0 | task 20358 | processing task, is_child = 0 2.56.413.894 I slot print_timing: id 0 | task 20358 | prompt eval time = 109.05 ms / 321 tokens ( 0.34 ms per token, 2943.60 tokens per second) 2.56.413.899 I slot print_timing: id 0 | task 20358 | eval time = 356.97 ms / 53 tokens ( 6.86 ms per token, 145.67 tokens per second) 2.56.413.900 I slot print_timing: id 0 | task 20358 | total time = 466.02 ms / 374 tokens 2.56.413.901 I slot print_timing: id 0 | task 20358 | graphs reused = 19368 2.56.413.901 I slot print_timing: id 0 | task 20358 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.413.930 I slot release: id 0 | task 20358 | stop processing: n_tokens = 405, truncated = 0 2.56.441.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 176316051 2.56.441.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.56.508.851 I slot launch_slot_: id 0 | task 20414 | processing task, is_child = 0 2.56.834.612 I slot print_timing: id 0 | task 20414 | prompt eval time = 109.49 ms / 322 tokens ( 0.34 ms per token, 2940.93 tokens per second) 2.56.834.619 I slot print_timing: id 0 | task 20414 | eval time = 216.25 ms / 32 tokens ( 6.98 ms per token, 143.35 tokens per second) 2.56.834.620 I slot print_timing: id 0 | task 20414 | total time = 325.74 ms / 354 tokens 2.56.834.621 I slot print_timing: id 0 | task 20414 | graphs reused = 19398 2.56.834.622 I slot print_timing: id 0 | task 20414 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.834.654 I slot release: id 0 | task 20414 | stop processing: n_tokens = 385, truncated = 0 2.56.849.290 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 176736775 2.56.849.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.482 MiB) 2.56.937.191 I slot launch_slot_: id 0 | task 20449 | processing task, is_child = 0 2.57.423.246 I slot print_timing: id 0 | task 20449 | prompt eval time = 108.74 ms / 323 tokens ( 0.34 ms per token, 2970.44 tokens per second) 2.57.423.252 I slot print_timing: id 0 | task 20449 | eval time = 377.30 ms / 56 tokens ( 6.86 ms per token, 145.77 tokens per second) 2.57.423.253 I slot print_timing: id 0 | task 20449 | total time = 486.04 ms / 379 tokens 2.57.423.254 I slot print_timing: id 0 | task 20449 | graphs reused = 19452 2.57.423.254 I slot print_timing: id 0 | task 20449 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.423.285 I slot release: id 0 | task 20449 | stop processing: n_tokens = 410, truncated = 0 2.57.443.462 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 410, t_last = 177325406 2.57.443.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 2.57.510.086 I slot launch_slot_: id 0 | task 20508 | processing task, is_child = 0 3.00.632.914 I slot print_timing: id 0 | task 20508 | n_gen = 442, tg = 146.83 t/s, tg_3s = 147.16 t/s 3.02.881.754 I slot print_timing: id 0 | task 20508 | prompt eval time = 119.35 ms / 321 tokens ( 0.37 ms per token, 2689.66 tokens per second) 3.02.881.760 I slot print_timing: id 0 | task 20508 | eval time = 5252.30 ms / 768 tokens ( 6.85 ms per token, 146.03 tokens per second) 3.02.881.761 I slot print_timing: id 0 | task 20508 | total time = 5371.65 ms / 1089 tokens 3.02.881.762 I slot print_timing: id 0 | task 20508 | graphs reused = 20215 3.02.881.762 I slot print_timing: id 0 | task 20508 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.881.792 I slot release: id 0 | task 20508 | stop processing: n_tokens = 1120, truncated = 0 3.02.907.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1120, t_last = 182783914 3.02.907.171 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.856 MiB) 3.02.977.745 I slot launch_slot_: id 0 | task 21279 | processing task, is_child = 0 3.04.771.498 I slot print_timing: id 0 | task 21279 | prompt eval time = 108.65 ms / 322 tokens ( 0.34 ms per token, 2963.54 tokens per second) 3.04.771.504 I slot print_timing: id 0 | task 21279 | eval time = 1685.08 ms / 248 tokens ( 6.82 ms per token, 146.58 tokens per second) 3.04.771.505 I slot print_timing: id 0 | task 21279 | total time = 1793.73 ms / 570 tokens 3.04.771.506 I slot print_timing: id 0 | task 21279 | graphs reused = 20460 3.04.771.507 I slot print_timing: id 0 | task 21279 | graph reallocs = 0 / 0 (same size) / (changed size) 3.04.771.535 I slot release: id 0 | task 21279 | stop processing: n_tokens = 601, truncated = 0 3.04.792.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 601, t_last = 184673656 3.04.792.114 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.171 MiB) 3.04.860.760 I slot launch_slot_: id 0 | task 21530 | processing task, is_child = 0 3.05.282.360 I slot print_timing: id 0 | task 21530 | prompt eval time = 111.78 ms / 337 tokens ( 0.33 ms per token, 3014.80 tokens per second) 3.05.282.366 I slot print_timing: id 0 | task 21530 | eval time = 309.80 ms / 46 tokens ( 6.88 ms per token, 145.26 tokens per second) 3.05.282.367 I slot print_timing: id 0 | task 21530 | total time = 421.58 ms / 383 tokens 3.05.282.368 I slot print_timing: id 0 | task 21530 | graphs reused = 20504 3.05.282.369 I slot print_timing: id 0 | task 21530 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.282.401 I slot release: id 0 | task 21530 | stop processing: n_tokens = 414, truncated = 0 3.05.301.335 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 185184522 3.05.301.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.05.368.246 I slot launch_slot_: id 0 | task 21579 | processing task, is_child = 0 3.05.795.333 I slot print_timing: id 0 | task 21579 | prompt eval time = 110.00 ms / 325 tokens ( 0.34 ms per token, 2954.60 tokens per second) 3.05.795.339 I slot print_timing: id 0 | task 21579 | eval time = 317.07 ms / 47 tokens ( 6.89 ms per token, 145.08 tokens per second) 3.05.795.340 I slot print_timing: id 0 | task 21579 | total time = 427.07 ms / 372 tokens 3.05.795.341 I slot print_timing: id 0 | task 21579 | graphs reused = 20549 3.05.795.341 I slot print_timing: id 0 | task 21579 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.795.370 I slot release: id 0 | task 21579 | stop processing: n_tokens = 403, truncated = 0 3.05.814.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 185697491 3.05.814.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 3.05.903.800 I slot launch_slot_: id 0 | task 21629 | processing task, is_child = 0 3.06.508.209 I slot print_timing: id 0 | task 21629 | prompt eval time = 110.51 ms / 331 tokens ( 0.33 ms per token, 2995.12 tokens per second) 3.06.508.215 I slot print_timing: id 0 | task 21629 | eval time = 493.88 ms / 73 tokens ( 6.86 ms per token, 145.79 tokens per second) 3.06.508.216 I slot print_timing: id 0 | task 21629 | total time = 604.39 ms / 404 tokens 3.06.508.217 I slot print_timing: id 0 | task 21629 | graphs reused = 20620 3.06.508.217 I slot print_timing: id 0 | task 21629 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.508.245 I slot release: id 0 | task 21629 | stop processing: n_tokens = 435, truncated = 0 3.06.532.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 186410366 3.06.532.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.326 MiB) 3.06.599.082 I slot launch_slot_: id 0 | task 21705 | processing task, is_child = 0 3.07.473.163 I slot print_timing: id 0 | task 21705 | prompt eval time = 110.02 ms / 336 tokens ( 0.33 ms per token, 3053.93 tokens per second) 3.07.473.169 I slot print_timing: id 0 | task 21705 | eval time = 764.04 ms / 113 tokens ( 6.82 ms per token, 146.59 tokens per second) 3.07.473.170 I slot print_timing: id 0 | task 21705 | total time = 874.06 ms / 449 tokens 3.07.473.170 I slot print_timing: id 0 | task 21705 | graphs reused = 20731 3.07.473.171 I slot print_timing: id 0 | task 21705 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.473.199 I slot release: id 0 | task 21705 | stop processing: n_tokens = 480, truncated = 0 3.07.500.706 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 187375320 3.07.500.759 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.329 MiB) 3.07.566.568 I slot launch_slot_: id 0 | task 21821 | processing task, is_child = 0 3.07.803.076 I slot print_timing: id 0 | task 21821 | prompt eval time = 109.53 ms / 349 tokens ( 0.31 ms per token, 3186.37 tokens per second) 3.07.803.082 I slot print_timing: id 0 | task 21821 | eval time = 126.96 ms / 19 tokens ( 7.05 ms per token, 141.78 tokens per second) 3.07.803.083 I slot print_timing: id 0 | task 21821 | total time = 236.49 ms / 368 tokens 3.07.803.083 I slot print_timing: id 0 | task 21821 | graphs reused = 20748 3.07.803.084 I slot print_timing: id 0 | task 21821 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.803.113 I slot release: id 0 | task 21821 | stop processing: n_tokens = 399, truncated = 0 3.07.827.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 187705235 3.07.827.381 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.106 MiB) 3.07.920.371 I slot launch_slot_: id 0 | task 21843 | processing task, is_child = 0 3.11.033.858 I slot print_timing: id 0 | task 21843 | n_gen = 441, tg = 146.45 t/s, tg_3s = 146.78 t/s 3.12.889.741 I slot print_timing: id 0 | task 21843 | prompt eval time = 109.07 ms / 336 tokens ( 0.32 ms per token, 3080.56 tokens per second) 3.12.889.747 I slot print_timing: id 0 | task 21843 | eval time = 4860.28 ms / 712 tokens ( 6.84 ms per token, 146.29 tokens per second) 3.12.889.747 I slot print_timing: id 0 | task 21843 | total time = 4969.35 ms / 1048 tokens 3.12.889.748 I slot print_timing: id 0 | task 21843 | graphs reused = 21455 3.12.889.749 I slot print_timing: id 0 | task 21843 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.889.776 I slot release: id 0 | task 21843 | stop processing: n_tokens = 1079, truncated = 0 3.12.915.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1079, t_last = 192791898 3.12.915.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.452 MiB) 3.12.985.058 I slot launch_slot_: id 0 | task 22558 | processing task, is_child = 0 3.15.511.558 I slot print_timing: id 0 | task 22558 | prompt eval time = 107.65 ms / 349 tokens ( 0.31 ms per token, 3241.90 tokens per second) 3.15.511.564 I slot print_timing: id 0 | task 22558 | eval time = 2418.83 ms / 356 tokens ( 6.81 ms per token, 146.77 tokens per second) 3.15.511.565 I slot print_timing: id 0 | task 22558 | total time = 2526.48 ms / 705 tokens 3.15.511.566 I slot print_timing: id 0 | task 22558 | graphs reused = 21808 3.15.511.567 I slot print_timing: id 0 | task 22558 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.511.596 I slot release: id 0 | task 22558 | stop processing: n_tokens = 736, truncated = 0 3.15.527.134 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 736, t_last = 195413717 3.15.527.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.143 MiB) 3.15.595.509 I slot launch_slot_: id 0 | task 22917 | processing task, is_child = 0 3.16.075.330 I slot print_timing: id 0 | task 22917 | prompt eval time = 108.00 ms / 349 tokens ( 0.31 ms per token, 3231.45 tokens per second) 3.16.075.336 I slot print_timing: id 0 | task 22917 | eval time = 371.80 ms / 55 tokens ( 6.89 ms per token, 145.24 tokens per second) 3.16.075.337 I slot print_timing: id 0 | task 22917 | total time = 479.80 ms / 404 tokens 3.16.075.337 I slot print_timing: id 0 | task 22917 | graphs reused = 21861 3.16.075.338 I slot print_timing: id 0 | task 22917 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.075.366 I slot release: id 0 | task 22917 | stop processing: n_tokens = 435, truncated = 0 3.16.079.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 195977487 3.16.079.045 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.888 MiB) 3.16.145.168 I slot launch_slot_: id 0 | task 22975 | processing task, is_child = 0 3.16.540.260 I slot print_timing: id 0 | task 22975 | prompt eval time = 112.57 ms / 385 tokens ( 0.29 ms per token, 3420.09 tokens per second) 3.16.540.266 I slot print_timing: id 0 | task 22975 | eval time = 282.50 ms / 42 tokens ( 6.89 ms per token, 145.13 tokens per second) 3.16.540.267 I slot print_timing: id 0 | task 22975 | total time = 395.07 ms / 427 tokens 3.16.540.267 I slot print_timing: id 0 | task 22975 | graphs reused = 21901 3.16.540.268 I slot print_timing: id 0 | task 22975 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.540.298 I slot release: id 0 | task 22975 | stop processing: n_tokens = 458, truncated = 0 3.16.564.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 196442419 3.16.564.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.548 MiB) 3.16.653.443 I slot launch_slot_: id 0 | task 23020 | processing task, is_child = 0 3.17.175.440 I slot print_timing: id 0 | task 23020 | prompt eval time = 122.03 ms / 328 tokens ( 0.37 ms per token, 2687.93 tokens per second) 3.17.175.447 I slot print_timing: id 0 | task 23020 | eval time = 399.94 ms / 57 tokens ( 7.14 ms per token, 140.02 tokens per second) 3.17.175.448 I slot print_timing: id 0 | task 23020 | total time = 521.97 ms / 385 tokens 3.17.175.449 I slot print_timing: id 0 | task 23020 | graphs reused = 21956 3.17.175.450 I slot print_timing: id 0 | task 23020 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.175.483 I slot release: id 0 | task 23020 | stop processing: n_tokens = 416, truncated = 0