$ 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-Q2_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 0.00.102.150 I srv llama_server: initializing ... 0.00.102.156 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.102.265 I srv init_listene: The UI is disabled 0.00.102.267 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.102.349 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) 0.00.116.560 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--unsloth--Qwen3.5-4B-GGUF\snapshots\e87f176479d0855a907a41277aca2f8ee7a09523\Qwen3.5-4B-UD-Q2_K_XL.gguf' 0.01.655.500 I cmn init: llama threadpool init, n_threads = 8 0.01.723.877 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.728.524 I srv llama_server: model loaded 0.01.728.530 I srv llama_server: listening on http://127.0.0.1:8089 0.02.538.316 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.538.496 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.771.535 I slot print_timing: id 0 | task 0 | prompt eval time = 139.81 ms / 368 tokens ( 0.38 ms per token, 2632.05 tokens per second) 0.03.771.541 I slot print_timing: id 0 | task 0 | eval time = 1093.21 ms / 197 tokens ( 5.58 ms per token, 179.29 tokens per second) 0.03.771.543 I slot print_timing: id 0 | task 0 | total time = 1233.02 ms / 565 tokens 0.03.771.549 I slot print_timing: id 0 | task 0 | graphs reused = 195 0.03.771.550 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.771.582 I slot release: id 0 | task 0 | stop processing: n_tokens = 564, truncated = 0 0.03.775.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 3671414 0.03.803.444 I slot launch_slot_: id 0 | task 200 | processing task, is_child = 0 0.05.442.415 I slot print_timing: id 0 | task 200 | prompt eval time = 98.18 ms / 322 tokens ( 0.30 ms per token, 3279.62 tokens per second) 0.05.442.421 I slot print_timing: id 0 | task 200 | eval time = 1540.77 ms / 277 tokens ( 5.58 ms per token, 179.13 tokens per second) 0.05.442.422 I slot print_timing: id 0 | task 200 | total time = 1638.95 ms / 599 tokens 0.05.442.423 I slot print_timing: id 0 | task 200 | graphs reused = 469 0.05.442.423 I slot print_timing: id 0 | task 200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.442.449 I slot release: id 0 | task 200 | stop processing: n_tokens = 598, truncated = 0 0.05.463.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 5342281 0.05.490.266 I slot launch_slot_: id 0 | task 480 | processing task, is_child = 0 0.06.023.036 I slot print_timing: id 0 | task 480 | prompt eval time = 100.17 ms / 365 tokens ( 0.27 ms per token, 3643.99 tokens per second) 0.06.023.041 I slot print_timing: id 0 | task 480 | eval time = 432.58 ms / 79 tokens ( 5.55 ms per token, 180.31 tokens per second) 0.06.023.043 I slot print_timing: id 0 | task 480 | total time = 532.75 ms / 444 tokens 0.06.023.043 I slot print_timing: id 0 | task 480 | graphs reused = 546 0.06.023.044 I slot print_timing: id 0 | task 480 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.023.074 I slot release: id 0 | task 480 | stop processing: n_tokens = 443, truncated = 0 0.06.026.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 5922906 0.06.053.120 I slot launch_slot_: id 0 | task 562 | processing task, is_child = 0 0.07.412.654 I slot print_timing: id 0 | task 562 | prompt eval time = 106.59 ms / 397 tokens ( 0.27 ms per token, 3724.66 tokens per second) 0.07.412.659 I slot print_timing: id 0 | task 562 | eval time = 1252.93 ms / 228 tokens ( 5.52 ms per token, 181.18 tokens per second) 0.07.412.660 I slot print_timing: id 0 | task 562 | total time = 1359.52 ms / 625 tokens 0.07.412.661 I slot print_timing: id 0 | task 562 | graphs reused = 771 0.07.412.662 I slot print_timing: id 0 | task 562 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.412.693 I slot release: id 0 | task 562 | stop processing: n_tokens = 624, truncated = 0 0.07.440.518 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.072 0.07.468.350 I slot launch_slot_: id 0 | task 793 | processing task, is_child = 0 0.08.558.339 I slot print_timing: id 0 | task 793 | prompt eval time = 101.69 ms / 383 tokens ( 0.27 ms per token, 3766.27 tokens per second) 0.08.558.345 I slot print_timing: id 0 | task 793 | eval time = 988.28 ms / 176 tokens ( 5.65 ms per token, 177.07 tokens per second) 0.08.558.346 I slot print_timing: id 0 | task 793 | total time = 1089.97 ms / 559 tokens 0.08.558.346 I slot print_timing: id 0 | task 793 | graphs reused = 944 0.08.558.347 I slot print_timing: id 0 | task 793 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.558.376 I slot release: id 0 | task 793 | stop processing: n_tokens = 558, truncated = 0 0.08.584.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 8458208 0.08.612.156 I slot launch_slot_: id 0 | task 972 | processing task, is_child = 0 0.09.020.476 I slot print_timing: id 0 | task 972 | prompt eval time = 104.65 ms / 372 tokens ( 0.28 ms per token, 3554.77 tokens per second) 0.09.020.482 I slot print_timing: id 0 | task 972 | eval time = 303.65 ms / 55 tokens ( 5.62 ms per token, 177.83 tokens per second) 0.09.020.483 I slot print_timing: id 0 | task 972 | total time = 408.30 ms / 427 tokens 0.09.020.484 I slot print_timing: id 0 | task 972 | graphs reused = 997 0.09.020.485 I slot print_timing: id 0 | task 972 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.020.511 I slot release: id 0 | task 972 | stop processing: n_tokens = 426, truncated = 0 0.09.024.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8920343 0.09.050.013 I slot launch_slot_: id 0 | task 1030 | processing task, is_child = 0 0.10.746.279 I slot print_timing: id 0 | task 1030 | prompt eval time = 111.81 ms / 422 tokens ( 0.26 ms per token, 3774.39 tokens per second) 0.10.746.285 I slot print_timing: id 0 | task 1030 | eval time = 1584.44 ms / 287 tokens ( 5.54 ms per token, 180.51 tokens per second) 0.10.746.286 I slot print_timing: id 0 | task 1030 | total time = 1696.25 ms / 709 tokens 0.10.746.286 I slot print_timing: id 0 | task 1030 | graphs reused = 1281 0.10.746.287 I slot print_timing: id 0 | task 1030 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.746.318 I slot release: id 0 | task 1030 | stop processing: n_tokens = 708, truncated = 0 0.10.760.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 708, t_last = 10646150 0.10.787.565 I slot launch_slot_: id 0 | task 1320 | processing task, is_child = 0 0.13.053.321 I slot print_timing: id 0 | task 1320 | prompt eval time = 113.61 ms / 470 tokens ( 0.24 ms per token, 4137.07 tokens per second) 0.13.053.327 I slot print_timing: id 0 | task 1320 | eval time = 2152.13 ms / 386 tokens ( 5.59 ms per token, 178.89 tokens per second) 0.13.053.328 I slot print_timing: id 0 | task 1320 | total time = 2265.74 ms / 856 tokens 0.13.053.329 I slot print_timing: id 0 | task 1320 | graphs reused = 1663 0.13.053.330 I slot print_timing: id 0 | task 1320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.053.361 I slot release: id 0 | task 1320 | stop processing: n_tokens = 855, truncated = 0 0.13.057.050 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 12953193 0.13.086.268 I slot launch_slot_: id 0 | task 1709 | processing task, is_child = 0 0.13.443.421 I slot print_timing: id 0 | task 1709 | prompt eval time = 97.67 ms / 345 tokens ( 0.28 ms per token, 3532.12 tokens per second) 0.13.443.427 I slot print_timing: id 0 | task 1709 | eval time = 259.46 ms / 47 tokens ( 5.64 ms per token, 177.29 tokens per second) 0.13.443.428 I slot print_timing: id 0 | task 1709 | total time = 357.13 ms / 392 tokens 0.13.443.429 I slot print_timing: id 0 | task 1709 | graphs reused = 1708 0.13.443.430 I slot print_timing: id 0 | task 1709 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.443.456 I slot release: id 0 | task 1709 | stop processing: n_tokens = 391, truncated = 0 0.13.456.714 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 13343288 0.13.483.473 I slot launch_slot_: id 0 | task 1759 | processing task, is_child = 0 0.14.156.406 I slot print_timing: id 0 | task 1759 | prompt eval time = 101.52 ms / 364 tokens ( 0.28 ms per token, 3585.50 tokens per second) 0.14.156.412 I slot print_timing: id 0 | task 1759 | eval time = 571.39 ms / 103 tokens ( 5.60 ms per token, 178.51 tokens per second) 0.14.156.413 I slot print_timing: id 0 | task 1759 | total time = 672.91 ms / 467 tokens 0.14.156.414 I slot print_timing: id 0 | task 1759 | graphs reused = 1809 0.14.156.414 I slot print_timing: id 0 | task 1759 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.156.443 I slot release: id 0 | task 1759 | stop processing: n_tokens = 466, truncated = 0 0.14.170.622 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 14056275 0.14.197.759 I slot launch_slot_: id 0 | task 1865 | processing task, is_child = 0 0.15.586.025 I slot print_timing: id 0 | task 1865 | prompt eval time = 102.78 ms / 376 tokens ( 0.27 ms per token, 3658.23 tokens per second) 0.15.586.031 I slot print_timing: id 0 | task 1865 | eval time = 1285.46 ms / 234 tokens ( 5.52 ms per token, 181.26 tokens per second) 0.15.586.032 I slot print_timing: id 0 | task 1865 | total time = 1388.25 ms / 610 tokens 0.15.586.033 I slot print_timing: id 0 | task 1865 | graphs reused = 2040 0.15.586.033 I slot print_timing: id 0 | task 1865 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.586.065 I slot release: id 0 | task 1865 | stop processing: n_tokens = 609, truncated = 0 0.15.605.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 15485897 0.15.632.659 I slot launch_slot_: id 0 | task 2102 | processing task, is_child = 0 0.17.210.311 I slot print_timing: id 0 | task 2102 | prompt eval time = 106.84 ms / 412 tokens ( 0.26 ms per token, 3856.27 tokens per second) 0.17.210.317 I slot print_timing: id 0 | task 2102 | eval time = 1470.79 ms / 264 tokens ( 5.59 ms per token, 178.81 tokens per second) 0.17.210.318 I slot print_timing: id 0 | task 2102 | total time = 1577.63 ms / 676 tokens 0.17.210.319 I slot print_timing: id 0 | task 2102 | graphs reused = 2301 0.17.210.320 I slot print_timing: id 0 | task 2102 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.210.353 I slot release: id 0 | task 2102 | stop processing: n_tokens = 675, truncated = 0 0.17.230.871 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 17110185 0.17.260.181 I slot launch_slot_: id 0 | task 2369 | processing task, is_child = 0 0.18.106.677 I slot print_timing: id 0 | task 2369 | prompt eval time = 105.18 ms / 376 tokens ( 0.28 ms per token, 3574.89 tokens per second) 0.18.106.683 I slot print_timing: id 0 | task 2369 | eval time = 741.30 ms / 133 tokens ( 5.62 ms per token, 178.07 tokens per second) 0.18.106.684 I slot print_timing: id 0 | task 2369 | total time = 846.48 ms / 509 tokens 0.18.106.684 I slot print_timing: id 0 | task 2369 | graphs reused = 2432 0.18.106.685 I slot print_timing: id 0 | task 2369 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.106.712 I slot release: id 0 | task 2369 | stop processing: n_tokens = 508, truncated = 0 0.18.130.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 18006544 0.18.158.774 I slot launch_slot_: id 0 | task 2505 | processing task, is_child = 0 0.18.548.585 I slot print_timing: id 0 | task 2505 | prompt eval time = 105.84 ms / 378 tokens ( 0.28 ms per token, 3571.43 tokens per second) 0.18.548.591 I slot print_timing: id 0 | task 2505 | eval time = 283.95 ms / 52 tokens ( 5.57 ms per token, 179.61 tokens per second) 0.18.548.593 I slot print_timing: id 0 | task 2505 | total time = 389.79 ms / 430 tokens 0.18.548.594 I slot print_timing: id 0 | task 2505 | graphs reused = 2482 0.18.548.595 I slot print_timing: id 0 | task 2505 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.548.633 I slot release: id 0 | task 2505 | stop processing: n_tokens = 429, truncated = 0 0.18.567.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 18448465 0.18.600.632 I slot launch_slot_: id 0 | task 2560 | processing task, is_child = 0 0.19.052.958 I slot print_timing: id 0 | task 2560 | prompt eval time = 102.04 ms / 367 tokens ( 0.28 ms per token, 3596.66 tokens per second) 0.19.052.964 I slot print_timing: id 0 | task 2560 | eval time = 350.26 ms / 58 tokens ( 6.14 ms per token, 162.74 tokens per second) 0.19.052.965 I slot print_timing: id 0 | task 2560 | total time = 452.30 ms / 425 tokens 0.19.052.966 I slot print_timing: id 0 | task 2560 | graphs reused = 2538 0.19.052.966 I slot print_timing: id 0 | task 2560 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.052.994 I slot release: id 0 | task 2560 | stop processing: n_tokens = 424, truncated = 0 0.19.066.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 18952827 0.19.092.246 I slot launch_slot_: id 0 | task 2621 | processing task, is_child = 0 0.19.473.198 I slot print_timing: id 0 | task 2621 | prompt eval time = 100.31 ms / 347 tokens ( 0.29 ms per token, 3459.17 tokens per second) 0.19.473.203 I slot print_timing: id 0 | task 2621 | eval time = 280.62 ms / 51 tokens ( 5.61 ms per token, 178.18 tokens per second) 0.19.473.204 I slot print_timing: id 0 | task 2621 | total time = 380.93 ms / 398 tokens 0.19.473.205 I slot print_timing: id 0 | task 2621 | graphs reused = 2587 0.19.473.206 I slot print_timing: id 0 | task 2621 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.473.236 I slot release: id 0 | task 2621 | stop processing: n_tokens = 397, truncated = 0 0.19.490.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 19373068 0.19.516.688 I slot launch_slot_: id 0 | task 2675 | processing task, is_child = 0 0.22.620.325 I slot print_timing: id 0 | task 2675 | n_gen = 539, tg = 179.10 t/s, tg_3s = 179.44 t/s 0.25.302.763 I slot print_timing: id 0 | task 2675 | prompt eval time = 99.75 ms / 369 tokens ( 0.27 ms per token, 3699.21 tokens per second) 0.25.302.770 I slot print_timing: id 0 | task 2675 | eval time = 5686.30 ms / 1024 tokens ( 5.56 ms per token, 179.91 tokens per second) 0.25.302.771 I slot print_timing: id 0 | task 2675 | total time = 5786.05 ms / 1393 tokens 0.25.302.772 I slot print_timing: id 0 | task 2675 | graphs reused = 3605 0.25.302.773 I slot print_timing: id 0 | task 2675 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.302.801 I slot release: id 0 | task 2675 | stop processing: n_tokens = 1392, truncated = 0 0.25.326.230 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1392, t_last = 25202634 0.25.357.486 I slot launch_slot_: id 0 | task 3702 | processing task, is_child = 0 0.26.092.332 I slot print_timing: id 0 | task 3702 | prompt eval time = 96.00 ms / 352 tokens ( 0.27 ms per token, 3666.78 tokens per second) 0.26.092.337 I slot print_timing: id 0 | task 3702 | eval time = 638.83 ms / 116 tokens ( 5.56 ms per token, 180.02 tokens per second) 0.26.092.338 I slot print_timing: id 0 | task 3702 | total time = 734.83 ms / 468 tokens 0.26.092.339 I slot print_timing: id 0 | task 3702 | graphs reused = 3719 0.26.092.340 I slot print_timing: id 0 | task 3702 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.092.368 I slot release: id 0 | task 3702 | stop processing: n_tokens = 467, truncated = 0 0.26.116.737 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 25992200 0.26.143.359 I slot launch_slot_: id 0 | task 3821 | processing task, is_child = 0 0.26.757.097 I slot print_timing: id 0 | task 3821 | prompt eval time = 97.64 ms / 349 tokens ( 0.28 ms per token, 3574.35 tokens per second) 0.26.757.102 I slot print_timing: id 0 | task 3821 | eval time = 516.08 ms / 95 tokens ( 5.49 ms per token, 182.14 tokens per second) 0.26.757.103 I slot print_timing: id 0 | task 3821 | total time = 613.72 ms / 444 tokens 0.26.757.104 I slot print_timing: id 0 | task 3821 | graphs reused = 3812 0.26.757.105 I slot print_timing: id 0 | task 3821 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.757.130 I slot release: id 0 | task 3821 | stop processing: n_tokens = 443, truncated = 0 0.26.774.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 26656962 0.26.811.488 I slot launch_slot_: id 0 | task 3919 | processing task, is_child = 0 0.27.284.248 I slot print_timing: id 0 | task 3919 | prompt eval time = 103.14 ms / 384 tokens ( 0.27 ms per token, 3723.06 tokens per second) 0.27.284.254 I slot print_timing: id 0 | task 3919 | eval time = 369.60 ms / 63 tokens ( 5.96 ms per token, 167.75 tokens per second) 0.27.284.255 I slot print_timing: id 0 | task 3919 | total time = 472.74 ms / 447 tokens 0.27.284.256 I slot print_timing: id 0 | task 3919 | graphs reused = 3873 0.27.284.257 I slot print_timing: id 0 | task 3919 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.284.287 I slot release: id 0 | task 3919 | stop processing: n_tokens = 446, truncated = 0 0.27.306.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 27184119 0.27.334.092 I slot launch_slot_: id 0 | task 3985 | processing task, is_child = 0 0.27.725.354 I slot print_timing: id 0 | task 3985 | prompt eval time = 97.06 ms / 356 tokens ( 0.27 ms per token, 3667.95 tokens per second) 0.27.725.361 I slot print_timing: id 0 | task 3985 | eval time = 294.19 ms / 54 tokens ( 5.55 ms per token, 180.16 tokens per second) 0.27.725.362 I slot print_timing: id 0 | task 3985 | total time = 391.24 ms / 410 tokens 0.27.725.363 I slot print_timing: id 0 | task 3985 | graphs reused = 3925 0.27.725.365 I slot print_timing: id 0 | task 3985 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.725.396 I slot release: id 0 | task 3985 | stop processing: n_tokens = 409, truncated = 0 0.27.729.466 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 27625228 0.27.754.644 I slot launch_slot_: id 0 | task 4042 | processing task, is_child = 0 0.28.264.395 I slot print_timing: id 0 | task 4042 | prompt eval time = 104.25 ms / 410 tokens ( 0.25 ms per token, 3932.78 tokens per second) 0.28.264.401 I slot print_timing: id 0 | task 4042 | eval time = 405.48 ms / 70 tokens ( 5.88 ms per token, 170.17 tokens per second) 0.28.264.402 I slot print_timing: id 0 | task 4042 | total time = 509.73 ms / 480 tokens 0.28.264.403 I slot print_timing: id 0 | task 4042 | graphs reused = 3993 0.28.264.403 I slot print_timing: id 0 | task 4042 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.264.433 I slot release: id 0 | task 4042 | stop processing: n_tokens = 479, truncated = 0 0.28.293.302 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 28164266 0.28.319.210 I slot launch_slot_: id 0 | task 4115 | processing task, is_child = 0 0.29.524.572 I slot print_timing: id 0 | task 4115 | prompt eval time = 102.42 ms / 385 tokens ( 0.27 ms per token, 3758.99 tokens per second) 0.29.524.578 I slot print_timing: id 0 | task 4115 | eval time = 1102.92 ms / 202 tokens ( 5.49 ms per token, 182.24 tokens per second) 0.29.524.579 I slot print_timing: id 0 | task 4115 | total time = 1205.34 ms / 587 tokens 0.29.524.580 I slot print_timing: id 0 | task 4115 | graphs reused = 4192 0.29.524.580 I slot print_timing: id 0 | task 4115 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.524.611 I slot release: id 0 | task 4115 | stop processing: n_tokens = 586, truncated = 0 0.29.548.377 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 29424443 0.29.574.542 I slot launch_slot_: id 0 | task 4320 | processing task, is_child = 0 0.30.065.154 I slot print_timing: id 0 | task 4320 | prompt eval time = 104.20 ms / 395 tokens ( 0.26 ms per token, 3790.75 tokens per second) 0.30.065.161 I slot print_timing: id 0 | task 4320 | eval time = 386.39 ms / 71 tokens ( 5.52 ms per token, 181.16 tokens per second) 0.30.065.162 I slot print_timing: id 0 | task 4320 | total time = 490.59 ms / 466 tokens 0.30.065.163 I slot print_timing: id 0 | task 4320 | graphs reused = 4261 0.30.065.164 I slot print_timing: id 0 | task 4320 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.065.194 I slot release: id 0 | task 4320 | stop processing: n_tokens = 465, truncated = 0 0.30.092.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 29965026 0.30.118.275 I slot launch_slot_: id 0 | task 4394 | processing task, is_child = 0 0.30.806.450 I slot print_timing: id 0 | task 4394 | prompt eval time = 106.21 ms / 430 tokens ( 0.25 ms per token, 4048.51 tokens per second) 0.30.806.455 I slot print_timing: id 0 | task 4394 | eval time = 581.94 ms / 106 tokens ( 5.54 ms per token, 180.43 tokens per second) 0.30.806.456 I slot print_timing: id 0 | task 4394 | total time = 688.16 ms / 536 tokens 0.30.806.457 I slot print_timing: id 0 | task 4394 | graphs reused = 4364 0.30.806.458 I slot print_timing: id 0 | task 4394 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.806.488 I slot release: id 0 | task 4394 | stop processing: n_tokens = 535, truncated = 0 0.30.820.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 30706321 0.30.847.026 I slot launch_slot_: id 0 | task 4503 | processing task, is_child = 0 0.32.605.944 I slot print_timing: id 0 | task 4503 | prompt eval time = 104.05 ms / 392 tokens ( 0.27 ms per token, 3767.35 tokens per second) 0.32.605.950 I slot print_timing: id 0 | task 4503 | eval time = 1654.85 ms / 303 tokens ( 5.48 ms per token, 182.49 tokens per second) 0.32.605.951 I slot print_timing: id 0 | task 4503 | total time = 1758.90 ms / 695 tokens 0.32.605.952 I slot print_timing: id 0 | task 4503 | graphs reused = 4664 0.32.605.953 I slot print_timing: id 0 | task 4503 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.605.983 I slot release: id 0 | task 4503 | stop processing: n_tokens = 694, truncated = 0 0.32.625.203 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 694, t_last = 32505815 0.32.651.984 I slot launch_slot_: id 0 | task 4809 | processing task, is_child = 0 0.33.013.760 I slot print_timing: id 0 | task 4809 | prompt eval time = 96.11 ms / 350 tokens ( 0.27 ms per token, 3641.77 tokens per second) 0.33.013.765 I slot print_timing: id 0 | task 4809 | eval time = 265.65 ms / 49 tokens ( 5.53 ms per token, 180.69 tokens per second) 0.33.013.766 I slot print_timing: id 0 | task 4809 | total time = 361.76 ms / 399 tokens 0.33.013.767 I slot print_timing: id 0 | task 4809 | graphs reused = 4711 0.33.013.768 I slot print_timing: id 0 | task 4809 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.013.796 I slot release: id 0 | task 4809 | stop processing: n_tokens = 398, truncated = 0 0.33.030.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 32913628 0.33.057.036 I slot launch_slot_: id 0 | task 4861 | processing task, is_child = 0 0.33.491.133 I slot print_timing: id 0 | task 4861 | prompt eval time = 102.16 ms / 380 tokens ( 0.27 ms per token, 3719.76 tokens per second) 0.33.491.139 I slot print_timing: id 0 | task 4861 | eval time = 331.93 ms / 61 tokens ( 5.53 ms per token, 180.76 tokens per second) 0.33.491.140 I slot print_timing: id 0 | task 4861 | total time = 434.08 ms / 441 tokens 0.33.491.141 I slot print_timing: id 0 | task 4861 | graphs reused = 4770 0.33.491.141 I slot print_timing: id 0 | task 4861 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.491.170 I slot release: id 0 | task 4861 | stop processing: n_tokens = 440, truncated = 0 0.33.518.664 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 33391002 0.33.545.480 I slot launch_slot_: id 0 | task 4925 | processing task, is_child = 0 0.34.115.473 I slot print_timing: id 0 | task 4925 | prompt eval time = 106.56 ms / 410 tokens ( 0.26 ms per token, 3847.53 tokens per second) 0.34.115.478 I slot print_timing: id 0 | task 4925 | eval time = 463.42 ms / 80 tokens ( 5.87 ms per token, 170.47 tokens per second) 0.34.115.480 I slot print_timing: id 0 | task 4925 | total time = 569.98 ms / 490 tokens 0.34.115.480 I slot print_timing: id 0 | task 4925 | graphs reused = 4848 0.34.115.481 I slot print_timing: id 0 | task 4925 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.115.512 I slot release: id 0 | task 4925 | stop processing: n_tokens = 489, truncated = 0 0.34.130.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 34015344 0.34.157.864 I slot launch_slot_: id 0 | task 5008 | processing task, is_child = 0 0.34.794.968 I slot print_timing: id 0 | task 5008 | prompt eval time = 103.72 ms / 387 tokens ( 0.27 ms per token, 3731.34 tokens per second) 0.34.794.974 I slot print_timing: id 0 | task 5008 | eval time = 533.37 ms / 92 tokens ( 5.86 ms per token, 170.61 tokens per second) 0.34.794.975 I slot print_timing: id 0 | task 5008 | total time = 637.08 ms / 479 tokens 0.34.794.975 I slot print_timing: id 0 | task 5008 | graphs reused = 4938 0.34.794.977 I slot print_timing: id 0 | task 5008 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.795.005 I slot release: id 0 | task 5008 | stop processing: n_tokens = 478, truncated = 0 0.34.815.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 34694838 0.34.841.469 I slot launch_slot_: id 0 | task 5103 | processing task, is_child = 0 0.35.258.803 I slot print_timing: id 0 | task 5103 | prompt eval time = 96.62 ms / 358 tokens ( 0.27 ms per token, 3705.35 tokens per second) 0.35.258.808 I slot print_timing: id 0 | task 5103 | eval time = 320.70 ms / 59 tokens ( 5.53 ms per token, 180.86 tokens per second) 0.35.258.810 I slot print_timing: id 0 | task 5103 | total time = 417.31 ms / 417 tokens 0.35.258.810 I slot print_timing: id 0 | task 5103 | graphs reused = 4995 0.35.258.811 I slot print_timing: id 0 | task 5103 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.258.839 I slot release: id 0 | task 5103 | stop processing: n_tokens = 416, truncated = 0 0.35.282.931 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 35158671 0.35.312.291 I slot launch_slot_: id 0 | task 5165 | processing task, is_child = 0 0.35.855.375 I slot print_timing: id 0 | task 5165 | prompt eval time = 96.74 ms / 359 tokens ( 0.27 ms per token, 3711.02 tokens per second) 0.35.855.380 I slot print_timing: id 0 | task 5165 | eval time = 446.33 ms / 77 tokens ( 5.87 ms per token, 170.28 tokens per second) 0.35.855.381 I slot print_timing: id 0 | task 5165 | total time = 543.07 ms / 436 tokens 0.35.855.382 I slot print_timing: id 0 | task 5165 | graphs reused = 5070 0.35.855.383 I slot print_timing: id 0 | task 5165 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.855.409 I slot release: id 0 | task 5165 | stop processing: n_tokens = 435, truncated = 0 0.35.876.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 435, t_last = 35755241 0.35.904.140 I slot launch_slot_: id 0 | task 5245 | processing task, is_child = 0 0.36.337.584 I slot print_timing: id 0 | task 5245 | prompt eval time = 101.83 ms / 387 tokens ( 0.26 ms per token, 3800.38 tokens per second) 0.36.337.591 I slot print_timing: id 0 | task 5245 | eval time = 331.59 ms / 61 tokens ( 5.53 ms per token, 180.95 tokens per second) 0.36.337.592 I slot print_timing: id 0 | task 5245 | total time = 433.42 ms / 448 tokens 0.36.337.593 I slot print_timing: id 0 | task 5245 | graphs reused = 5129 0.36.337.594 I slot print_timing: id 0 | task 5245 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.337.628 I slot release: id 0 | task 5245 | stop processing: n_tokens = 447, truncated = 0 0.36.361.441 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 36237460 0.36.388.228 I slot launch_slot_: id 0 | task 5309 | processing task, is_child = 0 0.36.752.746 I slot print_timing: id 0 | task 5309 | prompt eval time = 103.61 ms / 410 tokens ( 0.25 ms per token, 3956.99 tokens per second) 0.36.752.751 I slot print_timing: id 0 | task 5309 | eval time = 260.89 ms / 48 tokens ( 5.55 ms per token, 180.15 tokens per second) 0.36.752.752 I slot print_timing: id 0 | task 5309 | total time = 364.50 ms / 458 tokens 0.36.752.753 I slot print_timing: id 0 | task 5309 | graphs reused = 5175 0.36.752.754 I slot print_timing: id 0 | task 5309 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.752.783 I slot release: id 0 | task 5309 | stop processing: n_tokens = 457, truncated = 0 0.36.766.754 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 36652615 0.36.792.382 I slot launch_slot_: id 0 | task 5360 | processing task, is_child = 0 0.37.160.258 I slot print_timing: id 0 | task 5360 | prompt eval time = 96.78 ms / 351 tokens ( 0.28 ms per token, 3626.78 tokens per second) 0.37.160.263 I slot print_timing: id 0 | task 5360 | eval time = 271.07 ms / 50 tokens ( 5.53 ms per token, 180.76 tokens per second) 0.37.160.264 I slot print_timing: id 0 | task 5360 | total time = 367.86 ms / 401 tokens 0.37.160.265 I slot print_timing: id 0 | task 5360 | graphs reused = 5223 0.37.160.266 I slot print_timing: id 0 | task 5360 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.160.295 I slot release: id 0 | task 5360 | stop processing: n_tokens = 400, truncated = 0 0.37.186.789 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 37060127 0.37.219.918 I slot launch_slot_: id 0 | task 5413 | processing task, is_child = 0 0.37.625.708 I slot print_timing: id 0 | task 5413 | prompt eval time = 102.06 ms / 393 tokens ( 0.26 ms per token, 3850.49 tokens per second) 0.37.625.714 I slot print_timing: id 0 | task 5413 | eval time = 303.71 ms / 56 tokens ( 5.52 ms per token, 181.09 tokens per second) 0.37.625.715 I slot print_timing: id 0 | task 5413 | total time = 405.77 ms / 449 tokens 0.37.625.716 I slot print_timing: id 0 | task 5413 | graphs reused = 5277 0.37.625.717 I slot print_timing: id 0 | task 5413 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.625.746 I slot release: id 0 | task 5413 | stop processing: n_tokens = 448, truncated = 0 0.37.653.874 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 37525578 0.37.680.030 I slot launch_slot_: id 0 | task 5472 | processing task, is_child = 0 0.38.116.465 I slot print_timing: id 0 | task 5472 | prompt eval time = 95.26 ms / 321 tokens ( 0.30 ms per token, 3369.80 tokens per second) 0.38.116.471 I slot print_timing: id 0 | task 5472 | eval time = 341.16 ms / 63 tokens ( 5.50 ms per token, 181.73 tokens per second) 0.38.116.472 I slot print_timing: id 0 | task 5472 | total time = 436.42 ms / 384 tokens 0.38.116.473 I slot print_timing: id 0 | task 5472 | graphs reused = 5338 0.38.116.474 I slot print_timing: id 0 | task 5472 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.116.499 I slot release: id 0 | task 5472 | stop processing: n_tokens = 383, truncated = 0 0.38.144.270 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 38016331 0.38.170.174 I slot launch_slot_: id 0 | task 5538 | processing task, is_child = 0 0.39.325.744 I slot print_timing: id 0 | task 5538 | prompt eval time = 96.22 ms / 330 tokens ( 0.29 ms per token, 3429.46 tokens per second) 0.39.325.750 I slot print_timing: id 0 | task 5538 | eval time = 1059.32 ms / 194 tokens ( 5.49 ms per token, 182.19 tokens per second) 0.39.325.751 I slot print_timing: id 0 | task 5538 | total time = 1155.55 ms / 524 tokens 0.39.325.752 I slot print_timing: id 0 | task 5538 | graphs reused = 5529 0.39.325.753 I slot print_timing: id 0 | task 5538 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.325.779 I slot release: id 0 | task 5538 | stop processing: n_tokens = 523, truncated = 0 0.39.351.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 39225611 0.39.378.833 I slot launch_slot_: id 0 | task 5735 | processing task, is_child = 0 0.40.767.139 I slot print_timing: id 0 | task 5735 | prompt eval time = 95.72 ms / 341 tokens ( 0.28 ms per token, 3562.59 tokens per second) 0.40.767.145 I slot print_timing: id 0 | task 5735 | eval time = 1292.57 ms / 237 tokens ( 5.48 ms per token, 182.58 tokens per second) 0.40.767.146 I slot print_timing: id 0 | task 5735 | total time = 1388.29 ms / 578 tokens 0.40.767.147 I slot print_timing: id 0 | task 5735 | graphs reused = 5763 0.40.767.148 I slot print_timing: id 0 | task 5735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.767.176 I slot release: id 0 | task 5735 | stop processing: n_tokens = 577, truncated = 0 0.40.790.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 40667008 0.40.822.548 I slot launch_slot_: id 0 | task 5975 | processing task, is_child = 0 0.41.178.284 I slot print_timing: id 0 | task 5975 | prompt eval time = 95.50 ms / 338 tokens ( 0.28 ms per token, 3539.27 tokens per second) 0.41.178.290 I slot print_timing: id 0 | task 5975 | eval time = 260.21 ms / 48 tokens ( 5.54 ms per token, 180.62 tokens per second) 0.41.178.291 I slot print_timing: id 0 | task 5975 | total time = 355.71 ms / 386 tokens 0.41.178.292 I slot print_timing: id 0 | task 5975 | graphs reused = 5809 0.41.178.293 I slot print_timing: id 0 | task 5975 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.178.322 I slot release: id 0 | task 5975 | stop processing: n_tokens = 385, truncated = 0 0.41.198.519 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 41078154 0.41.223.715 I slot launch_slot_: id 0 | task 6026 | processing task, is_child = 0 0.42.749.619 I slot print_timing: id 0 | task 6026 | prompt eval time = 104.77 ms / 395 tokens ( 0.27 ms per token, 3770.02 tokens per second) 0.42.749.624 I slot print_timing: id 0 | task 6026 | eval time = 1421.11 ms / 260 tokens ( 5.49 ms per token, 182.25 tokens per second) 0.42.749.625 I slot print_timing: id 0 | task 6026 | total time = 1525.89 ms / 655 tokens 0.42.749.626 I slot print_timing: id 0 | task 6026 | graphs reused = 6066 0.42.749.627 I slot print_timing: id 0 | task 6026 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.749.658 I slot release: id 0 | task 6026 | stop processing: n_tokens = 654, truncated = 0 0.42.765.057 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 654, t_last = 42649490 0.42.792.227 I slot launch_slot_: id 0 | task 6289 | processing task, is_child = 0 0.44.726.510 I slot print_timing: id 0 | task 6289 | prompt eval time = 139.81 ms / 528 tokens ( 0.26 ms per token, 3776.66 tokens per second) 0.44.726.515 I slot print_timing: id 0 | task 6289 | eval time = 1794.46 ms / 328 tokens ( 5.49 ms per token, 182.23 tokens per second) 0.44.726.516 I slot print_timing: id 0 | task 6289 | total time = 1934.26 ms / 856 tokens 0.44.726.517 I slot print_timing: id 0 | task 6289 | graphs reused = 6391 0.44.726.518 I slot print_timing: id 0 | task 6289 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.726.550 I slot release: id 0 | task 6289 | stop processing: n_tokens = 855, truncated = 0 0.44.754.323 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 44626382 0.44.787.878 I slot launch_slot_: id 0 | task 6621 | processing task, is_child = 0 0.45.233.405 I slot print_timing: id 0 | task 6621 | prompt eval time = 114.64 ms / 331 tokens ( 0.35 ms per token, 2887.37 tokens per second) 0.45.233.411 I slot print_timing: id 0 | task 6621 | eval time = 330.87 ms / 61 tokens ( 5.51 ms per token, 181.34 tokens per second) 0.45.233.412 I slot print_timing: id 0 | task 6621 | total time = 445.51 ms / 392 tokens 0.45.233.413 I slot print_timing: id 0 | task 6621 | graphs reused = 6450 0.45.233.413 I slot print_timing: id 0 | task 6621 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.233.440 I slot release: id 0 | task 6621 | stop processing: n_tokens = 403, truncated = 0 0.45.253.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 45133272 0.45.285.198 I slot launch_slot_: id 0 | task 6685 | processing task, is_child = 0 0.45.693.322 I slot print_timing: id 0 | task 6685 | prompt eval time = 120.71 ms / 362 tokens ( 0.33 ms per token, 2998.90 tokens per second) 0.45.693.328 I slot print_timing: id 0 | task 6685 | eval time = 287.39 ms / 53 tokens ( 5.53 ms per token, 180.94 tokens per second) 0.45.693.329 I slot print_timing: id 0 | task 6685 | total time = 408.11 ms / 415 tokens 0.45.693.329 I slot print_timing: id 0 | task 6685 | graphs reused = 6501 0.45.693.330 I slot print_timing: id 0 | task 6685 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.693.361 I slot release: id 0 | task 6685 | stop processing: n_tokens = 426, truncated = 0 0.45.708.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 45593193 0.45.740.041 I slot launch_slot_: id 0 | task 6741 | processing task, is_child = 0 0.46.238.963 I slot print_timing: id 0 | task 6741 | prompt eval time = 123.80 ms / 419 tokens ( 0.30 ms per token, 3384.55 tokens per second) 0.46.238.969 I slot print_timing: id 0 | task 6741 | eval time = 375.10 ms / 69 tokens ( 5.52 ms per token, 181.28 tokens per second) 0.46.238.970 I slot print_timing: id 0 | task 6741 | total time = 498.90 ms / 488 tokens 0.46.238.971 I slot print_timing: id 0 | task 6741 | graphs reused = 6568 0.46.238.971 I slot print_timing: id 0 | task 6741 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.239.003 I slot release: id 0 | task 6741 | stop processing: n_tokens = 499, truncated = 0 0.46.254.805 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 46138835 0.46.286.851 I slot launch_slot_: id 0 | task 6813 | processing task, is_child = 0 0.46.655.140 I slot print_timing: id 0 | task 6813 | prompt eval time = 129.63 ms / 423 tokens ( 0.31 ms per token, 3263.01 tokens per second) 0.46.655.146 I slot print_timing: id 0 | task 6813 | eval time = 238.63 ms / 44 tokens ( 5.55 ms per token, 180.19 tokens per second) 0.46.655.147 I slot print_timing: id 0 | task 6813 | total time = 368.27 ms / 467 tokens 0.46.655.148 I slot print_timing: id 0 | task 6813 | graphs reused = 6610 0.46.655.149 I slot print_timing: id 0 | task 6813 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.655.180 I slot release: id 0 | task 6813 | stop processing: n_tokens = 478, truncated = 0 0.46.676.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 46555012 0.46.708.340 I slot launch_slot_: id 0 | task 6860 | processing task, is_child = 0 0.47.295.395 I slot print_timing: id 0 | task 6860 | prompt eval time = 114.97 ms / 341 tokens ( 0.34 ms per token, 2965.91 tokens per second) 0.47.295.401 I slot print_timing: id 0 | task 6860 | eval time = 472.06 ms / 87 tokens ( 5.49 ms per token, 182.18 tokens per second) 0.47.295.402 I slot print_timing: id 0 | task 6860 | total time = 587.04 ms / 428 tokens 0.47.295.403 I slot print_timing: id 0 | task 6860 | graphs reused = 6695 0.47.295.404 I slot print_timing: id 0 | task 6860 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.295.432 I slot release: id 0 | task 6860 | stop processing: n_tokens = 439, truncated = 0 0.47.319.444 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 47195264 0.47.350.540 I slot launch_slot_: id 0 | task 6950 | processing task, is_child = 0 0.47.721.701 I slot print_timing: id 0 | task 6950 | prompt eval time = 115.85 ms / 356 tokens ( 0.33 ms per token, 3072.94 tokens per second) 0.47.721.707 I slot print_timing: id 0 | task 6950 | eval time = 255.29 ms / 47 tokens ( 5.55 ms per token, 180.19 tokens per second) 0.47.721.708 I slot print_timing: id 0 | task 6950 | total time = 371.14 ms / 403 tokens 0.47.721.709 I slot print_timing: id 0 | task 6950 | graphs reused = 6740 0.47.721.709 I slot print_timing: id 0 | task 6950 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.721.740 I slot release: id 0 | task 6950 | stop processing: n_tokens = 414, truncated = 0 0.47.739.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 47621572 0.47.739.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.390 MiB) 0.47.750.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.453 MiB) 0.47.793.865 I slot launch_slot_: id 0 | task 7000 | processing task, is_child = 0 0.48.164.213 I slot print_timing: id 0 | task 7000 | prompt eval time = 120.22 ms / 362 tokens ( 0.33 ms per token, 3011.07 tokens per second) 0.48.164.219 I slot print_timing: id 0 | task 7000 | eval time = 250.11 ms / 46 tokens ( 5.56 ms per token, 179.92 tokens per second) 0.48.164.221 I slot print_timing: id 0 | task 7000 | total time = 370.33 ms / 408 tokens 0.48.164.221 I slot print_timing: id 0 | task 7000 | graphs reused = 6784 0.48.164.222 I slot print_timing: id 0 | task 7000 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.164.255 I slot release: id 0 | task 7000 | stop processing: n_tokens = 419, truncated = 0 0.48.192.073 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 48064087 0.48.192.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.606 MiB) 0.48.239.401 I slot launch_slot_: id 0 | task 7049 | processing task, is_child = 0 0.48.734.433 I slot print_timing: id 0 | task 7049 | prompt eval time = 124.81 ms / 391 tokens ( 0.32 ms per token, 3132.74 tokens per second) 0.48.734.439 I slot print_timing: id 0 | task 7049 | eval time = 370.20 ms / 68 tokens ( 5.53 ms per token, 180.98 tokens per second) 0.48.734.440 I slot print_timing: id 0 | task 7049 | total time = 495.02 ms / 459 tokens 0.48.734.441 I slot print_timing: id 0 | task 7049 | graphs reused = 6850 0.48.734.442 I slot print_timing: id 0 | task 7049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.734.474 I slot release: id 0 | task 7049 | stop processing: n_tokens = 470, truncated = 0 0.48.754.292 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 48634306 0.48.754.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.266 MiB) 0.48.799.128 I slot launch_slot_: id 0 | task 7120 | processing task, is_child = 0 0.49.208.827 I slot print_timing: id 0 | task 7120 | prompt eval time = 116.28 ms / 343 tokens ( 0.34 ms per token, 2949.67 tokens per second) 0.49.208.833 I slot print_timing: id 0 | task 7120 | eval time = 293.39 ms / 54 tokens ( 5.54 ms per token, 180.65 tokens per second) 0.49.208.835 I slot print_timing: id 0 | task 7120 | total time = 409.68 ms / 397 tokens 0.49.208.835 I slot print_timing: id 0 | task 7120 | graphs reused = 6902 0.49.208.836 I slot print_timing: id 0 | task 7120 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.208.866 I slot release: id 0 | task 7120 | stop processing: n_tokens = 408, truncated = 0 0.49.236.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 49108698 0.49.236.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.202 MiB) 0.49.277.716 I slot launch_slot_: id 0 | task 7177 | processing task, is_child = 0 0.49.650.767 I slot print_timing: id 0 | task 7177 | prompt eval time = 123.54 ms / 401 tokens ( 0.31 ms per token, 3245.94 tokens per second) 0.49.650.773 I slot print_timing: id 0 | task 7177 | eval time = 249.49 ms / 46 tokens ( 5.54 ms per token, 180.37 tokens per second) 0.49.650.774 I slot print_timing: id 0 | task 7177 | total time = 373.03 ms / 447 tokens 0.49.650.775 I slot print_timing: id 0 | task 7177 | graphs reused = 6946 0.49.650.775 I slot print_timing: id 0 | task 7177 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.650.804 I slot release: id 0 | task 7177 | stop processing: n_tokens = 458, truncated = 0 0.49.674.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 49550637 0.49.674.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.49.685.013 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.893 MiB) 0.49.728.885 I slot launch_slot_: id 0 | task 7226 | processing task, is_child = 0 0.50.202.085 I slot print_timing: id 0 | task 7226 | prompt eval time = 115.44 ms / 355 tokens ( 0.33 ms per token, 3075.19 tokens per second) 0.50.202.091 I slot print_timing: id 0 | task 7226 | eval time = 357.74 ms / 66 tokens ( 5.50 ms per token, 181.70 tokens per second) 0.50.202.093 I slot print_timing: id 0 | task 7226 | total time = 473.18 ms / 421 tokens 0.50.202.094 I slot print_timing: id 0 | task 7226 | graphs reused = 7010 0.50.202.094 I slot print_timing: id 0 | task 7226 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.202.125 I slot release: id 0 | task 7226 | stop processing: n_tokens = 432, truncated = 0 0.50.219.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 50101957 0.50.219.585 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 177.490 MiB) 0.50.267.844 I slot launch_slot_: id 0 | task 7295 | processing task, is_child = 0 0.50.730.427 I slot print_timing: id 0 | task 7295 | prompt eval time = 120.21 ms / 351 tokens ( 0.34 ms per token, 2919.82 tokens per second) 0.50.730.433 I slot print_timing: id 0 | task 7295 | eval time = 342.35 ms / 57 tokens ( 6.11 ms per token, 163.57 tokens per second) 0.50.730.434 I slot print_timing: id 0 | task 7295 | total time = 462.56 ms / 408 tokens 0.50.730.435 I slot print_timing: id 0 | task 7295 | graphs reused = 7065 0.50.730.436 I slot print_timing: id 0 | task 7295 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.730.464 I slot release: id 0 | task 7295 | stop processing: n_tokens = 419, truncated = 0 0.50.751.179 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 50630296 0.50.751.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.50.794.738 I slot launch_slot_: id 0 | task 7355 | processing task, is_child = 0 0.51.437.520 I slot print_timing: id 0 | task 7355 | prompt eval time = 131.69 ms / 475 tokens ( 0.28 ms per token, 3607.09 tokens per second) 0.51.437.526 I slot print_timing: id 0 | task 7355 | eval time = 511.08 ms / 93 tokens ( 5.56 ms per token, 180.01 tokens per second) 0.51.437.527 I slot print_timing: id 0 | task 7355 | total time = 642.76 ms / 568 tokens 0.51.437.528 I slot print_timing: id 0 | task 7355 | graphs reused = 7155 0.51.437.529 I slot print_timing: id 0 | task 7355 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.437.561 I slot release: id 0 | task 7355 | stop processing: n_tokens = 579, truncated = 0 0.51.455.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 51337393 0.51.455.651 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.325 MiB) 0.51.465.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.797 MiB) 0.51.514.137 I slot launch_slot_: id 0 | task 7451 | processing task, is_child = 0 0.52.149.562 I slot print_timing: id 0 | task 7451 | prompt eval time = 129.87 ms / 440 tokens ( 0.30 ms per token, 3388.06 tokens per second) 0.52.149.568 I slot print_timing: id 0 | task 7451 | eval time = 505.54 ms / 92 tokens ( 5.56 ms per token, 180.01 tokens per second) 0.52.149.569 I slot print_timing: id 0 | task 7451 | total time = 635.41 ms / 532 tokens 0.52.149.569 I slot print_timing: id 0 | task 7451 | graphs reused = 7244 0.52.149.570 I slot print_timing: id 0 | task 7451 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.149.601 I slot release: id 0 | task 7451 | stop processing: n_tokens = 543, truncated = 0 0.52.168.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 52049433 0.52.168.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.861 MiB) 0.52.226.306 I slot launch_slot_: id 0 | task 7546 | processing task, is_child = 0 0.52.648.171 I slot print_timing: id 0 | task 7546 | prompt eval time = 117.70 ms / 345 tokens ( 0.34 ms per token, 2931.21 tokens per second) 0.52.648.177 I slot print_timing: id 0 | task 7546 | eval time = 304.15 ms / 56 tokens ( 5.53 ms per token, 180.83 tokens per second) 0.52.648.178 I slot print_timing: id 0 | task 7546 | total time = 421.85 ms / 401 tokens 0.52.648.179 I slot print_timing: id 0 | task 7546 | graphs reused = 7298 0.52.648.180 I slot print_timing: id 0 | task 7546 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.648.209 I slot release: id 0 | task 7546 | stop processing: n_tokens = 412, truncated = 0 0.52.664.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 52548041 0.52.664.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.639 MiB) 0.52.718.521 I slot launch_slot_: id 0 | task 7605 | processing task, is_child = 0 0.53.137.852 I slot print_timing: id 0 | task 7605 | prompt eval time = 120.75 ms / 382 tokens ( 0.32 ms per token, 3163.69 tokens per second) 0.53.137.858 I slot print_timing: id 0 | task 7605 | eval time = 298.57 ms / 55 tokens ( 5.53 ms per token, 180.86 tokens per second) 0.53.137.859 I slot print_timing: id 0 | task 7605 | total time = 419.31 ms / 437 tokens 0.53.137.860 I slot print_timing: id 0 | task 7605 | graphs reused = 7351 0.53.137.860 I slot print_timing: id 0 | task 7605 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.137.891 I slot release: id 0 | task 7605 | stop processing: n_tokens = 448, truncated = 0 0.53.163.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 53037723 0.53.163.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.53.214.543 I slot launch_slot_: id 0 | task 7663 | processing task, is_child = 0 0.53.576.634 I slot print_timing: id 0 | task 7663 | prompt eval time = 117.83 ms / 337 tokens ( 0.35 ms per token, 2860.13 tokens per second) 0.53.576.639 I slot print_timing: id 0 | task 7663 | eval time = 244.25 ms / 45 tokens ( 5.55 ms per token, 180.15 tokens per second) 0.53.576.640 I slot print_timing: id 0 | task 7663 | total time = 362.07 ms / 382 tokens 0.53.576.641 I slot print_timing: id 0 | task 7663 | graphs reused = 7394 0.53.576.642 I slot print_timing: id 0 | task 7663 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.576.669 I slot release: id 0 | task 7663 | stop processing: n_tokens = 393, truncated = 0 0.53.601.268 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 53476501 0.53.601.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.53.611.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.53.654.278 I slot launch_slot_: id 0 | task 7711 | processing task, is_child = 0 0.54.184.825 I slot print_timing: id 0 | task 7711 | prompt eval time = 121.33 ms / 402 tokens ( 0.30 ms per token, 3313.33 tokens per second) 0.54.184.831 I slot print_timing: id 0 | task 7711 | eval time = 409.20 ms / 70 tokens ( 5.93 ms per token, 168.62 tokens per second) 0.54.184.832 I slot print_timing: id 0 | task 7711 | total time = 530.53 ms / 472 tokens 0.54.184.834 I slot print_timing: id 0 | task 7711 | graphs reused = 7462 0.54.184.835 I slot print_timing: id 0 | task 7711 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.184.867 I slot release: id 0 | task 7711 | stop processing: n_tokens = 483, truncated = 0 0.54.199.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 54084699 0.54.199.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 194.284 MiB) 0.54.249.799 I slot launch_slot_: id 0 | task 7784 | processing task, is_child = 0 0.55.611.032 I slot print_timing: id 0 | task 7784 | prompt eval time = 147.29 ms / 549 tokens ( 0.27 ms per token, 3727.21 tokens per second) 0.55.611.038 I slot print_timing: id 0 | task 7784 | eval time = 1213.92 ms / 222 tokens ( 5.49 ms per token, 182.05 tokens per second) 0.55.611.040 I slot print_timing: id 0 | task 7784 | total time = 1361.21 ms / 771 tokens 0.55.611.040 I slot print_timing: id 0 | task 7784 | graphs reused = 7681 0.55.611.041 I slot print_timing: id 0 | task 7784 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.611.073 I slot release: id 0 | task 7784 | stop processing: n_tokens = 782, truncated = 0 0.55.640.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 782, t_last = 55510906 0.55.640.462 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.356 MiB) 0.55.689.381 I slot launch_slot_: id 0 | task 8010 | processing task, is_child = 0 0.56.454.044 I slot print_timing: id 0 | task 8010 | prompt eval time = 160.68 ms / 616 tokens ( 0.26 ms per token, 3833.66 tokens per second) 0.56.454.050 I slot print_timing: id 0 | task 8010 | eval time = 603.96 ms / 110 tokens ( 5.54 ms per token, 180.48 tokens per second) 0.56.454.051 I slot print_timing: id 0 | task 8010 | total time = 764.64 ms / 726 tokens 0.56.454.052 I slot print_timing: id 0 | task 8010 | graphs reused = 7789 0.56.454.053 I slot print_timing: id 0 | task 8010 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.454.089 I slot release: id 0 | task 8010 | stop processing: n_tokens = 737, truncated = 0 0.56.479.325 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 56353921 0.56.479.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.606 MiB) 0.56.489.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.56.541.242 I slot launch_slot_: id 0 | task 8124 | processing task, is_child = 0 0.57.050.869 I slot print_timing: id 0 | task 8124 | prompt eval time = 172.87 ms / 665 tokens ( 0.26 ms per token, 3846.89 tokens per second) 0.57.050.875 I slot print_timing: id 0 | task 8124 | eval time = 336.74 ms / 61 tokens ( 5.61 ms per token, 178.18 tokens per second) 0.57.050.876 I slot print_timing: id 0 | task 8124 | total time = 509.61 ms / 726 tokens 0.57.050.877 I slot print_timing: id 0 | task 8124 | graphs reused = 7848 0.57.050.878 I slot print_timing: id 0 | task 8124 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.050.926 I slot release: id 0 | task 8124 | stop processing: n_tokens = 737, truncated = 0 0.57.055.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 56950758 0.57.055.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.57.068.355 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.57.123.965 I slot launch_slot_: id 0 | task 8189 | processing task, is_child = 0 0.57.595.002 I slot print_timing: id 0 | task 8189 | prompt eval time = 171.43 ms / 645 tokens ( 0.27 ms per token, 3762.45 tokens per second) 0.57.595.007 I slot print_timing: id 0 | task 8189 | eval time = 299.58 ms / 55 tokens ( 5.55 ms per token, 180.25 tokens per second) 0.57.595.008 I slot print_timing: id 0 | task 8189 | total time = 471.01 ms / 700 tokens 0.57.595.009 I slot print_timing: id 0 | task 8189 | graphs reused = 7901 0.57.595.010 I slot print_timing: id 0 | task 8189 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.595.044 I slot release: id 0 | task 8189 | stop processing: n_tokens = 711, truncated = 0 0.57.621.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 57494876 0.57.621.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 169.078 MiB) 0.57.674.135 I slot launch_slot_: id 0 | task 8248 | processing task, is_child = 0 0.58.331.573 I slot print_timing: id 0 | task 8248 | prompt eval time = 134.56 ms / 474 tokens ( 0.28 ms per token, 3522.67 tokens per second) 0.58.331.579 I slot print_timing: id 0 | task 8248 | eval time = 522.86 ms / 95 tokens ( 5.56 ms per token, 179.78 tokens per second) 0.58.331.581 I slot print_timing: id 0 | task 8248 | total time = 657.42 ms / 569 tokens 0.58.331.581 I slot print_timing: id 0 | task 8248 | graphs reused = 7993 0.58.331.582 I slot print_timing: id 0 | task 8248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.331.612 I slot release: id 0 | task 8248 | stop processing: n_tokens = 580, truncated = 0 0.58.356.348 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 58231444 0.58.356.403 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.58.366.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.483 MiB) 0.58.415.124 I slot launch_slot_: id 0 | task 8346 | processing task, is_child = 0 0.58.799.536 I slot print_timing: id 0 | task 8346 | prompt eval time = 154.69 ms / 617 tokens ( 0.25 ms per token, 3988.60 tokens per second) 0.58.799.542 I slot print_timing: id 0 | task 8346 | eval time = 229.70 ms / 42 tokens ( 5.60 ms per token, 178.49 tokens per second) 0.58.799.543 I slot print_timing: id 0 | task 8346 | total time = 384.39 ms / 659 tokens 0.58.799.544 I slot print_timing: id 0 | task 8346 | graphs reused = 8033 0.58.799.545 I slot print_timing: id 0 | task 8346 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.799.580 I slot release: id 0 | task 8346 | stop processing: n_tokens = 670, truncated = 0 0.58.825.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 58699412 0.58.825.179 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 172.455 MiB) 0.58.874.077 I slot launch_slot_: id 0 | task 8392 | processing task, is_child = 0 0.59.290.858 I slot print_timing: id 0 | task 8392 | prompt eval time = 155.45 ms / 601 tokens ( 0.26 ms per token, 3866.24 tokens per second) 0.59.290.864 I slot print_timing: id 0 | task 8392 | eval time = 261.31 ms / 48 tokens ( 5.56 ms per token, 179.86 tokens per second) 0.59.290.865 I slot print_timing: id 0 | task 8392 | total time = 416.76 ms / 649 tokens 0.59.290.866 I slot print_timing: id 0 | task 8392 | graphs reused = 8079 0.59.290.867 I slot print_timing: id 0 | task 8392 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.290.903 I slot release: id 0 | task 8392 | stop processing: n_tokens = 660, truncated = 0 0.59.304.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 59190735 0.59.304.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 0.59.314.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.59.365.715 I slot launch_slot_: id 0 | task 8444 | processing task, is_child = 0 0.59.767.289 I slot print_timing: id 0 | task 8444 | prompt eval time = 145.88 ms / 533 tokens ( 0.27 ms per token, 3653.69 tokens per second) 0.59.767.294 I slot print_timing: id 0 | task 8444 | eval time = 255.68 ms / 47 tokens ( 5.56 ms per token, 179.91 tokens per second) 0.59.767.295 I slot print_timing: id 0 | task 8444 | total time = 401.56 ms / 580 tokens 0.59.767.296 I slot print_timing: id 0 | task 8444 | graphs reused = 8124 0.59.767.297 I slot print_timing: id 0 | task 8444 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.767.330 I slot release: id 0 | task 8444 | stop processing: n_tokens = 591, truncated = 0 0.59.793.434 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 59667162 0.59.793.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.59.803.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.700 MiB) 0.59.854.504 I slot launch_slot_: id 0 | task 8495 | processing task, is_child = 0 1.00.278.748 I slot print_timing: id 0 | task 8495 | prompt eval time = 136.31 ms / 480 tokens ( 0.28 ms per token, 3521.46 tokens per second) 1.00.278.754 I slot print_timing: id 0 | task 8495 | eval time = 287.92 ms / 52 tokens ( 5.65 ms per token, 177.13 tokens per second) 1.00.278.755 I slot print_timing: id 0 | task 8495 | total time = 424.23 ms / 532 tokens 1.00.278.756 I slot print_timing: id 0 | task 8495 | graphs reused = 8173 1.00.278.757 I slot print_timing: id 0 | task 8495 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.278.789 I slot release: id 0 | task 8495 | stop processing: n_tokens = 560, truncated = 0 1.00.293.098 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 60178621 1.00.293.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.00.349.522 I slot launch_slot_: id 0 | task 8550 | processing task, is_child = 0 1.00.726.760 I slot print_timing: id 0 | task 8550 | prompt eval time = 148.75 ms / 567 tokens ( 0.26 ms per token, 3811.82 tokens per second) 1.00.726.766 I slot print_timing: id 0 | task 8550 | eval time = 228.47 ms / 42 tokens ( 5.57 ms per token, 179.46 tokens per second) 1.00.726.767 I slot print_timing: id 0 | task 8550 | total time = 377.22 ms / 609 tokens 1.00.726.768 I slot print_timing: id 0 | task 8550 | graphs reused = 8213 1.00.726.769 I slot print_timing: id 0 | task 8550 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.726.803 I slot release: id 0 | task 8550 | stop processing: n_tokens = 637, truncated = 0 1.00.745.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 60626635 1.00.745.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.356 MiB) 1.00.755.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.00.813.678 I slot launch_slot_: id 0 | task 8596 | processing task, is_child = 0 1.01.876.972 I slot print_timing: id 0 | task 8596 | prompt eval time = 141.95 ms / 506 tokens ( 0.28 ms per token, 3564.59 tokens per second) 1.01.876.978 I slot print_timing: id 0 | task 8596 | eval time = 921.32 ms / 169 tokens ( 5.48 ms per token, 182.35 tokens per second) 1.01.876.979 I slot print_timing: id 0 | task 8596 | total time = 1063.28 ms / 675 tokens 1.01.876.980 I slot print_timing: id 0 | task 8596 | graphs reused = 8380 1.01.876.981 I slot print_timing: id 0 | task 8596 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.877.013 I slot release: id 0 | task 8596 | stop processing: n_tokens = 703, truncated = 0 1.01.896.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 703, t_last = 61776846 1.01.897.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.044 MiB) 1.01.907.239 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.01.958.333 I slot launch_slot_: id 0 | task 8768 | processing task, is_child = 0 1.02.304.848 I slot print_timing: id 0 | task 8768 | prompt eval time = 129.12 ms / 436 tokens ( 0.30 ms per token, 3376.68 tokens per second) 1.02.304.854 I slot print_timing: id 0 | task 8768 | eval time = 217.38 ms / 40 tokens ( 5.57 ms per token, 179.41 tokens per second) 1.02.304.856 I slot print_timing: id 0 | task 8768 | total time = 346.50 ms / 476 tokens 1.02.304.856 I slot print_timing: id 0 | task 8768 | graphs reused = 8418 1.02.304.857 I slot print_timing: id 0 | task 8768 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.304.887 I slot release: id 0 | task 8768 | stop processing: n_tokens = 504, truncated = 0 1.02.318.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 62204719 1.02.318.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.762 MiB) 1.02.329.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.729 MiB) 1.02.378.758 I slot launch_slot_: id 0 | task 8811 | processing task, is_child = 0 1.02.857.302 I slot print_timing: id 0 | task 8811 | prompt eval time = 141.00 ms / 519 tokens ( 0.27 ms per token, 3680.72 tokens per second) 1.02.857.308 I slot print_timing: id 0 | task 8811 | eval time = 337.52 ms / 62 tokens ( 5.53 ms per token, 180.73 tokens per second) 1.02.857.309 I slot print_timing: id 0 | task 8811 | total time = 478.53 ms / 581 tokens 1.02.857.310 I slot print_timing: id 0 | task 8811 | graphs reused = 8478 1.02.857.310 I slot print_timing: id 0 | task 8811 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.857.343 I slot release: id 0 | task 8811 | stop processing: n_tokens = 609, truncated = 0 1.02.882.001 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 62757175 1.02.882.055 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.108 MiB) 1.02.935.818 I slot launch_slot_: id 0 | task 8877 | processing task, is_child = 0 1.03.320.830 I slot print_timing: id 0 | task 8877 | prompt eval time = 129.93 ms / 465 tokens ( 0.28 ms per token, 3578.88 tokens per second) 1.03.320.837 I slot print_timing: id 0 | task 8877 | eval time = 255.06 ms / 46 tokens ( 5.67 ms per token, 176.43 tokens per second) 1.03.320.838 I slot print_timing: id 0 | task 8877 | total time = 384.99 ms / 511 tokens 1.03.320.838 I slot print_timing: id 0 | task 8877 | graphs reused = 8521 1.03.320.839 I slot print_timing: id 0 | task 8877 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.320.870 I slot release: id 0 | task 8877 | stop processing: n_tokens = 542, truncated = 0 1.03.335.046 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 63220702 1.03.335.099 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.796 MiB) 1.03.345.483 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.03.399.241 I slot launch_slot_: id 0 | task 8926 | processing task, is_child = 0 1.03.751.348 I slot print_timing: id 0 | task 8926 | prompt eval time = 130.01 ms / 431 tokens ( 0.30 ms per token, 3315.10 tokens per second) 1.03.751.354 I slot print_timing: id 0 | task 8926 | eval time = 222.08 ms / 41 tokens ( 5.55 ms per token, 180.12 tokens per second) 1.03.751.355 I slot print_timing: id 0 | task 8926 | total time = 352.09 ms / 472 tokens 1.03.751.356 I slot print_timing: id 0 | task 8926 | graphs reused = 8560 1.03.751.357 I slot print_timing: id 0 | task 8926 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.751.387 I slot release: id 0 | task 8926 | stop processing: n_tokens = 503, truncated = 0 1.03.771.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 63651219 1.03.771.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 171.204 MiB) 1.03.781.951 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 227.741 MiB) 1.03.844.772 I slot launch_slot_: id 0 | task 8970 | processing task, is_child = 0 1.04.359.905 I slot print_timing: id 0 | task 8970 | prompt eval time = 129.28 ms / 457 tokens ( 0.28 ms per token, 3534.85 tokens per second) 1.04.359.911 I slot print_timing: id 0 | task 8970 | eval time = 385.83 ms / 70 tokens ( 5.59 ms per token, 178.84 tokens per second) 1.04.359.912 I slot print_timing: id 0 | task 8970 | total time = 515.11 ms / 527 tokens 1.04.359.913 I slot print_timing: id 0 | task 8970 | graphs reused = 8627 1.04.359.914 I slot print_timing: id 0 | task 8970 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.359.947 I slot release: id 0 | task 8970 | stop processing: n_tokens = 558, truncated = 0 1.04.381.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 64259779 1.04.381.578 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.605 MiB) 1.04.394.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.04.455.742 I slot launch_slot_: id 0 | task 9043 | processing task, is_child = 0 1.04.987.204 I slot print_timing: id 0 | task 9043 | prompt eval time = 129.66 ms / 439 tokens ( 0.30 ms per token, 3385.73 tokens per second) 1.04.987.210 I slot print_timing: id 0 | task 9043 | eval time = 401.78 ms / 73 tokens ( 5.58 ms per token, 179.20 tokens per second) 1.04.987.211 I slot print_timing: id 0 | task 9043 | total time = 531.44 ms / 512 tokens 1.04.987.212 I slot print_timing: id 0 | task 9043 | graphs reused = 8697 1.04.987.213 I slot print_timing: id 0 | task 9043 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.987.242 I slot release: id 0 | task 9043 | stop processing: n_tokens = 543, truncated = 0 1.05.011.947 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 64887074 1.05.012.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.05.072.254 I slot launch_slot_: id 0 | task 9119 | processing task, is_child = 0 1.05.771.823 I slot print_timing: id 0 | task 9119 | prompt eval time = 155.13 ms / 606 tokens ( 0.26 ms per token, 3906.48 tokens per second) 1.05.771.828 I slot print_timing: id 0 | task 9119 | eval time = 544.42 ms / 100 tokens ( 5.50 ms per token, 181.84 tokens per second) 1.05.771.829 I slot print_timing: id 0 | task 9119 | total time = 699.55 ms / 706 tokens 1.05.771.830 I slot print_timing: id 0 | task 9119 | graphs reused = 8795 1.05.771.831 I slot print_timing: id 0 | task 9119 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.771.867 I slot release: id 0 | task 9119 | stop processing: n_tokens = 737, truncated = 0 1.05.795.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 65671699 1.05.795.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.05.808.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.731 MiB) 1.05.876.101 I slot launch_slot_: id 0 | task 9223 | processing task, is_child = 0 1.06.239.478 I slot print_timing: id 0 | task 9223 | prompt eval time = 135.23 ms / 477 tokens ( 0.28 ms per token, 3527.25 tokens per second) 1.06.239.485 I slot print_timing: id 0 | task 9223 | eval time = 228.12 ms / 41 tokens ( 5.70 ms per token, 175.34 tokens per second) 1.06.239.486 I slot print_timing: id 0 | task 9223 | total time = 363.36 ms / 518 tokens 1.06.239.488 I slot print_timing: id 0 | task 9223 | graphs reused = 8833 1.06.239.488 I slot print_timing: id 0 | task 9223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.239.524 I slot release: id 0 | task 9223 | stop processing: n_tokens = 549, truncated = 0 1.06.266.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 66139356 1.06.266.061 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.06.326.117 I slot launch_slot_: id 0 | task 9267 | processing task, is_child = 0 1.06.842.435 I slot print_timing: id 0 | task 9267 | prompt eval time = 187.88 ms / 845 tokens ( 0.22 ms per token, 4497.60 tokens per second) 1.06.842.441 I slot print_timing: id 0 | task 9267 | eval time = 328.42 ms / 60 tokens ( 5.57 ms per token, 179.65 tokens per second) 1.06.842.442 I slot print_timing: id 0 | task 9267 | total time = 516.30 ms / 905 tokens 1.06.842.443 I slot print_timing: id 0 | task 9267 | graphs reused = 8891 1.06.842.444 I slot print_timing: id 0 | task 9267 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.842.489 I slot release: id 0 | task 9267 | stop processing: n_tokens = 936, truncated = 0 1.06.858.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 66742321 1.06.858.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.06.871.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.06.945.249 I slot launch_slot_: id 0 | task 9331 | processing task, is_child = 0 1.07.406.266 I slot print_timing: id 0 | task 9331 | prompt eval time = 134.13 ms / 459 tokens ( 0.29 ms per token, 3422.08 tokens per second) 1.07.406.272 I slot print_timing: id 0 | task 9331 | eval time = 326.87 ms / 59 tokens ( 5.64 ms per token, 177.44 tokens per second) 1.07.406.273 I slot print_timing: id 0 | task 9331 | total time = 461.00 ms / 518 tokens 1.07.406.274 I slot print_timing: id 0 | task 9331 | graphs reused = 8947 1.07.406.275 I slot print_timing: id 0 | task 9331 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.406.305 I slot release: id 0 | task 9331 | stop processing: n_tokens = 549, truncated = 0 1.07.424.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 67306138 1.07.424.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.07.484.321 I slot launch_slot_: id 0 | task 9393 | processing task, is_child = 0 1.08.642.895 I slot print_timing: id 0 | task 9393 | prompt eval time = 161.29 ms / 670 tokens ( 0.24 ms per token, 4153.93 tokens per second) 1.08.642.901 I slot print_timing: id 0 | task 9393 | eval time = 997.26 ms / 182 tokens ( 5.51 ms per token, 181.50 tokens per second) 1.08.642.902 I slot print_timing: id 0 | task 9393 | total time = 1158.55 ms / 852 tokens 1.08.642.902 I slot print_timing: id 0 | task 9393 | graphs reused = 9126 1.08.642.903 I slot print_timing: id 0 | task 9393 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.642.942 I slot release: id 0 | task 9393 | stop processing: n_tokens = 883, truncated = 0 1.08.661.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 68542774 1.08.661.183 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.08.674.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.512 MiB) 1.08.742.529 I slot launch_slot_: id 0 | task 9579 | processing task, is_child = 0 1.09.304.278 I slot print_timing: id 0 | task 9579 | prompt eval time = 182.89 ms / 775 tokens ( 0.24 ms per token, 4237.59 tokens per second) 1.09.304.284 I slot print_timing: id 0 | task 9579 | eval time = 378.84 ms / 63 tokens ( 6.11 ms per token, 163.66 tokens per second) 1.09.304.286 I slot print_timing: id 0 | task 9579 | total time = 561.73 ms / 838 tokens 1.09.304.287 I slot print_timing: id 0 | task 9579 | graphs reused = 9187 1.09.304.288 I slot print_timing: id 0 | task 9579 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.304.336 I slot release: id 0 | task 9579 | stop processing: n_tokens = 869, truncated = 0 1.09.328.882 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 69204169 1.09.328.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.09.342.199 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.09.416.732 I slot launch_slot_: id 0 | task 9646 | processing task, is_child = 0 1.09.956.015 I slot print_timing: id 0 | task 9646 | prompt eval time = 151.70 ms / 573 tokens ( 0.26 ms per token, 3777.12 tokens per second) 1.09.956.021 I slot print_timing: id 0 | task 9646 | eval time = 387.56 ms / 71 tokens ( 5.54 ms per token, 180.62 tokens per second) 1.09.956.022 I slot print_timing: id 0 | task 9646 | total time = 539.26 ms / 644 tokens 1.09.956.023 I slot print_timing: id 0 | task 9646 | graphs reused = 9256 1.09.956.023 I slot print_timing: id 0 | task 9646 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.956.059 I slot release: id 0 | task 9646 | stop processing: n_tokens = 675, truncated = 0 1.09.970.918 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 69855892 1.09.970.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 1.09.984.434 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.887 MiB) 1.10.052.775 I slot launch_slot_: id 0 | task 9721 | processing task, is_child = 0 1.10.524.819 I slot print_timing: id 0 | task 9721 | prompt eval time = 135.04 ms / 461 tokens ( 0.29 ms per token, 3413.90 tokens per second) 1.10.524.825 I slot print_timing: id 0 | task 9721 | eval time = 336.99 ms / 61 tokens ( 5.62 ms per token, 178.05 tokens per second) 1.10.524.826 I slot print_timing: id 0 | task 9721 | total time = 472.02 ms / 522 tokens 1.10.524.827 I slot print_timing: id 0 | task 9721 | graphs reused = 9314 1.10.524.828 I slot print_timing: id 0 | task 9721 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.524.860 I slot release: id 0 | task 9721 | stop processing: n_tokens = 553, truncated = 0 1.10.546.414 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 553, t_last = 70424692 1.10.546.465 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.10.614.506 I slot launch_slot_: id 0 | task 9785 | processing task, is_child = 0 1.12.045.867 I slot print_timing: id 0 | task 9785 | prompt eval time = 151.00 ms / 609 tokens ( 0.25 ms per token, 4033.17 tokens per second) 1.12.045.873 I slot print_timing: id 0 | task 9785 | eval time = 1280.34 ms / 230 tokens ( 5.59 ms per token, 178.86 tokens per second) 1.12.045.874 I slot print_timing: id 0 | task 9785 | total time = 1431.34 ms / 839 tokens 1.12.045.875 I slot print_timing: id 0 | task 9785 | graphs reused = 9541 1.12.045.875 I slot print_timing: id 0 | task 9785 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.045.912 I slot release: id 0 | task 9785 | stop processing: n_tokens = 870, truncated = 0 1.12.074.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 870, t_last = 71945744 1.12.074.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.12.087.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.12.156.388 I slot launch_slot_: id 0 | task 10019 | processing task, is_child = 0 1.12.675.323 I slot print_timing: id 0 | task 10019 | prompt eval time = 185.15 ms / 791 tokens ( 0.23 ms per token, 4272.21 tokens per second) 1.12.675.328 I slot print_timing: id 0 | task 10019 | eval time = 333.76 ms / 61 tokens ( 5.56 ms per token, 179.77 tokens per second) 1.12.675.330 I slot print_timing: id 0 | task 10019 | total time = 518.91 ms / 852 tokens 1.12.675.330 I slot print_timing: id 0 | task 10019 | graphs reused = 9600 1.12.675.331 I slot print_timing: id 0 | task 10019 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.675.374 I slot release: id 0 | task 10019 | stop processing: n_tokens = 883, truncated = 0 1.12.702.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 72575206 1.12.702.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 275.708 MiB) 1.12.806.835 I slot launch_slot_: id 0 | task 10084 | processing task, is_child = 0 1.13.254.442 I slot print_timing: id 0 | task 10084 | prompt eval time = 142.78 ms / 533 tokens ( 0.27 ms per token, 3732.94 tokens per second) 1.13.254.448 I slot print_timing: id 0 | task 10084 | eval time = 304.80 ms / 56 tokens ( 5.54 ms per token, 180.45 tokens per second) 1.13.254.449 I slot print_timing: id 0 | task 10084 | total time = 447.59 ms / 589 tokens 1.13.254.450 I slot print_timing: id 0 | task 10084 | graphs reused = 9654 1.13.254.450 I slot print_timing: id 0 | task 10084 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.254.487 I slot release: id 0 | task 10084 | stop processing: n_tokens = 677, truncated = 0 1.13.268.624 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 73154319 1.13.268.687 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 1.13.351.573 I slot launch_slot_: id 0 | task 10144 | processing task, is_child = 0 1.13.783.866 I slot print_timing: id 0 | task 10144 | prompt eval time = 154.24 ms / 566 tokens ( 0.27 ms per token, 3669.61 tokens per second) 1.13.783.873 I slot print_timing: id 0 | task 10144 | eval time = 278.03 ms / 46 tokens ( 6.18 ms per token, 161.85 tokens per second) 1.13.783.875 I slot print_timing: id 0 | task 10144 | total time = 432.27 ms / 612 tokens 1.13.783.875 I slot print_timing: id 0 | task 10144 | graphs reused = 9698 1.13.783.876 I slot print_timing: id 0 | task 10144 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.783.912 I slot release: id 0 | task 10144 | stop processing: n_tokens = 643, truncated = 0 1.13.799.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 73683744 1.13.799.401 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 1.13.870.534 I slot launch_slot_: id 0 | task 10194 | processing task, is_child = 0 1.14.246.727 I slot print_timing: id 0 | task 10194 | prompt eval time = 136.92 ms / 443 tokens ( 0.31 ms per token, 3235.47 tokens per second) 1.14.246.733 I slot print_timing: id 0 | task 10194 | eval time = 239.25 ms / 43 tokens ( 5.70 ms per token, 175.55 tokens per second) 1.14.246.734 I slot print_timing: id 0 | task 10194 | total time = 376.17 ms / 486 tokens 1.14.246.735 I slot print_timing: id 0 | task 10194 | graphs reused = 9738 1.14.246.736 I slot print_timing: id 0 | task 10194 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.246.770 I slot release: id 0 | task 10194 | stop processing: n_tokens = 517, truncated = 0 1.14.263.225 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 74146603 1.14.263.278 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.14.334.855 I slot launch_slot_: id 0 | task 10240 | processing task, is_child = 0 1.14.822.247 I slot print_timing: id 0 | task 10240 | prompt eval time = 132.67 ms / 487 tokens ( 0.27 ms per token, 3670.79 tokens per second) 1.14.822.252 I slot print_timing: id 0 | task 10240 | eval time = 354.70 ms / 65 tokens ( 5.54 ms per token, 180.43 tokens per second) 1.14.822.253 I slot print_timing: id 0 | task 10240 | total time = 487.37 ms / 552 tokens 1.14.822.254 I slot print_timing: id 0 | task 10240 | graphs reused = 9801 1.14.822.255 I slot print_timing: id 0 | task 10240 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.822.288 I slot release: id 0 | task 10240 | stop processing: n_tokens = 583, truncated = 0 1.14.842.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 74722120 1.14.842.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.141 MiB) 1.14.856.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.14.921.828 I slot launch_slot_: id 0 | task 10308 | processing task, is_child = 0 1.15.315.535 I slot print_timing: id 0 | task 10308 | prompt eval time = 137.89 ms / 507 tokens ( 0.27 ms per token, 3676.95 tokens per second) 1.15.315.542 I slot print_timing: id 0 | task 10308 | eval time = 255.80 ms / 47 tokens ( 5.56 ms per token, 179.83 tokens per second) 1.15.315.543 I slot print_timing: id 0 | task 10308 | total time = 393.69 ms / 554 tokens 1.15.315.544 I slot print_timing: id 0 | task 10308 | graphs reused = 9846 1.15.315.545 I slot print_timing: id 0 | task 10308 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.315.583 I slot release: id 0 | task 10308 | stop processing: n_tokens = 585, truncated = 0 1.15.343.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 75215415 1.15.343.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.15.413.793 I slot launch_slot_: id 0 | task 10358 | processing task, is_child = 0 1.15.930.044 I slot print_timing: id 0 | task 10358 | prompt eval time = 156.52 ms / 633 tokens ( 0.25 ms per token, 4044.31 tokens per second) 1.15.930.050 I slot print_timing: id 0 | task 10358 | eval time = 359.72 ms / 66 tokens ( 5.53 ms per token, 180.70 tokens per second) 1.15.930.051 I slot print_timing: id 0 | task 10358 | total time = 516.23 ms / 699 tokens 1.15.930.052 I slot print_timing: id 0 | task 10358 | graphs reused = 9910 1.15.930.053 I slot print_timing: id 0 | task 10358 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.930.090 I slot release: id 0 | task 10358 | stop processing: n_tokens = 730, truncated = 0 1.15.950.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 75829923 1.15.951.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.16.025.730 I slot launch_slot_: id 0 | task 10428 | processing task, is_child = 0 1.16.432.057 I slot print_timing: id 0 | task 10428 | prompt eval time = 150.98 ms / 571 tokens ( 0.26 ms per token, 3782.01 tokens per second) 1.16.432.063 I slot print_timing: id 0 | task 10428 | eval time = 255.33 ms / 47 tokens ( 5.55 ms per token, 180.16 tokens per second) 1.16.432.064 I slot print_timing: id 0 | task 10428 | total time = 406.31 ms / 618 tokens 1.16.432.064 I slot print_timing: id 0 | task 10428 | graphs reused = 9955 1.16.432.065 I slot print_timing: id 0 | task 10428 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.432.100 I slot release: id 0 | task 10428 | stop processing: n_tokens = 649, truncated = 0 1.16.458.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 76331932 1.16.458.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.16.531.285 I slot launch_slot_: id 0 | task 10479 | processing task, is_child = 0 1.16.953.627 I slot print_timing: id 0 | task 10479 | prompt eval time = 182.07 ms / 798 tokens ( 0.23 ms per token, 4383.00 tokens per second) 1.16.953.632 I slot print_timing: id 0 | task 10479 | eval time = 240.25 ms / 44 tokens ( 5.59 ms per token, 178.98 tokens per second) 1.16.953.633 I slot print_timing: id 0 | task 10479 | total time = 422.32 ms / 842 tokens 1.16.953.634 I slot print_timing: id 0 | task 10479 | graphs reused = 9997 1.16.953.635 I slot print_timing: id 0 | task 10479 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.953.680 I slot release: id 0 | task 10479 | stop processing: n_tokens = 873, truncated = 0 1.16.982.540 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 76853512 1.16.982.604 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.17.003.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.238 MiB) 1.17.074.676 I slot launch_slot_: id 0 | task 10527 | processing task, is_child = 0 1.17.463.467 I slot print_timing: id 0 | task 10527 | prompt eval time = 154.73 ms / 572 tokens ( 0.27 ms per token, 3696.83 tokens per second) 1.17.463.472 I slot print_timing: id 0 | task 10527 | eval time = 234.04 ms / 43 tokens ( 5.57 ms per token, 179.45 tokens per second) 1.17.463.473 I slot print_timing: id 0 | task 10527 | total time = 388.77 ms / 615 tokens 1.17.463.474 I slot print_timing: id 0 | task 10527 | graphs reused = 10038 1.17.463.474 I slot print_timing: id 0 | task 10527 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.463.510 I slot release: id 0 | task 10527 | stop processing: n_tokens = 646, truncated = 0 1.17.482.088 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 77363342 1.17.482.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.17.552.257 I slot launch_slot_: id 0 | task 10574 | processing task, is_child = 0 1.17.976.197 I slot print_timing: id 0 | task 10574 | prompt eval time = 157.38 ms / 613 tokens ( 0.26 ms per token, 3895.03 tokens per second) 1.17.976.203 I slot print_timing: id 0 | task 10574 | eval time = 266.54 ms / 49 tokens ( 5.55 ms per token, 180.08 tokens per second) 1.17.976.204 I slot print_timing: id 0 | task 10574 | total time = 423.92 ms / 662 tokens 1.17.976.205 I slot print_timing: id 0 | task 10574 | graphs reused = 10085 1.17.976.205 I slot print_timing: id 0 | task 10574 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.976.242 I slot release: id 0 | task 10574 | stop processing: n_tokens = 693, truncated = 0 1.17.996.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 77876074 1.17.996.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.18.069.044 I slot launch_slot_: id 0 | task 10627 | processing task, is_child = 0 1.18.595.286 I slot print_timing: id 0 | task 10627 | prompt eval time = 155.35 ms / 580 tokens ( 0.27 ms per token, 3733.50 tokens per second) 1.18.595.292 I slot print_timing: id 0 | task 10627 | eval time = 370.87 ms / 68 tokens ( 5.54 ms per token, 180.66 tokens per second) 1.18.595.293 I slot print_timing: id 0 | task 10627 | total time = 526.22 ms / 648 tokens 1.18.595.293 I slot print_timing: id 0 | task 10627 | graphs reused = 10151 1.18.595.294 I slot print_timing: id 0 | task 10627 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.595.330 I slot release: id 0 | task 10627 | stop processing: n_tokens = 679, truncated = 0 1.18.623.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 78495162 1.18.623.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.18.697.546 I slot launch_slot_: id 0 | task 10699 | processing task, is_child = 0 1.19.146.450 I slot print_timing: id 0 | task 10699 | prompt eval time = 171.23 ms / 716 tokens ( 0.24 ms per token, 4181.61 tokens per second) 1.19.146.455 I slot print_timing: id 0 | task 10699 | eval time = 277.66 ms / 50 tokens ( 5.67 ms per token, 176.48 tokens per second) 1.19.146.456 I slot print_timing: id 0 | task 10699 | total time = 448.88 ms / 766 tokens 1.19.146.457 I slot print_timing: id 0 | task 10699 | graphs reused = 10198 1.19.146.458 I slot print_timing: id 0 | task 10699 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.146.498 I slot release: id 0 | task 10699 | stop processing: n_tokens = 797, truncated = 0 1.19.172.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 79046330 1.19.172.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.19.194.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 1.19.272.536 I slot launch_slot_: id 0 | task 10753 | processing task, is_child = 0 1.20.015.881 I slot print_timing: id 0 | task 10753 | prompt eval time = 185.47 ms / 799 tokens ( 0.23 ms per token, 4308.04 tokens per second) 1.20.015.887 I slot print_timing: id 0 | task 10753 | eval time = 557.86 ms / 102 tokens ( 5.52 ms per token, 181.05 tokens per second) 1.20.015.888 I slot print_timing: id 0 | task 10753 | total time = 743.32 ms / 901 tokens 1.20.015.889 I slot print_timing: id 0 | task 10753 | graphs reused = 10298 1.20.015.889 I slot print_timing: id 0 | task 10753 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.015.931 I slot release: id 0 | task 10753 | stop processing: n_tokens = 932, truncated = 0 1.20.044.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 79915763 1.20.044.221 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.485 MiB) 1.20.123.700 I slot launch_slot_: id 0 | task 10859 | processing task, is_child = 0 1.22.821.692 I slot print_timing: id 0 | task 10859 | prompt eval time = 121.83 ms / 361 tokens ( 0.34 ms per token, 2963.17 tokens per second) 1.22.821.698 I slot print_timing: id 0 | task 10859 | eval time = 2576.14 ms / 471 tokens ( 5.48 ms per token, 182.44 tokens per second) 1.22.821.699 I slot print_timing: id 0 | task 10859 | total time = 2697.97 ms / 832 tokens 1.22.821.699 I slot print_timing: id 0 | task 10859 | graphs reused = 10765 1.22.821.700 I slot print_timing: id 0 | task 10859 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.821.729 I slot release: id 0 | task 10859 | stop processing: n_tokens = 863, truncated = 0 1.22.841.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 863, t_last = 82721561 1.22.841.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.802 MiB) 1.22.921.388 I slot launch_slot_: id 0 | task 11333 | processing task, is_child = 0 1.23.758.762 I slot print_timing: id 0 | task 11333 | prompt eval time = 119.74 ms / 381 tokens ( 0.31 ms per token, 3181.79 tokens per second) 1.23.758.768 I slot print_timing: id 0 | task 11333 | eval time = 717.61 ms / 131 tokens ( 5.52 ms per token, 181.16 tokens per second) 1.23.758.769 I slot print_timing: id 0 | task 11333 | total time = 837.35 ms / 512 tokens 1.23.758.769 I slot print_timing: id 0 | task 11333 | graphs reused = 10893 1.23.758.770 I slot print_timing: id 0 | task 11333 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.758.800 I slot release: id 0 | task 11333 | stop processing: n_tokens = 543, truncated = 0 1.23.778.986 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 83658632 1.23.779.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.23.846.171 I slot launch_slot_: id 0 | task 11467 | processing task, is_child = 0 1.25.347.433 I slot print_timing: id 0 | task 11467 | prompt eval time = 117.97 ms / 365 tokens ( 0.32 ms per token, 3094.03 tokens per second) 1.25.347.439 I slot print_timing: id 0 | task 11467 | eval time = 1383.28 ms / 253 tokens ( 5.49 ms per token, 182.18 tokens per second) 1.25.347.440 I slot print_timing: id 0 | task 11467 | total time = 1501.24 ms / 618 tokens 1.25.347.441 I slot print_timing: id 0 | task 11467 | graphs reused = 11143 1.25.347.442 I slot print_timing: id 0 | task 11467 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.347.472 I slot release: id 0 | task 11467 | stop processing: n_tokens = 649, truncated = 0 1.25.351.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 85247304 1.25.351.280 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.25.418.766 I slot launch_slot_: id 0 | task 11723 | processing task, is_child = 0 1.26.117.413 I slot print_timing: id 0 | task 11723 | prompt eval time = 116.27 ms / 333 tokens ( 0.35 ms per token, 2863.95 tokens per second) 1.26.117.419 I slot print_timing: id 0 | task 11723 | eval time = 582.35 ms / 107 tokens ( 5.49 ms per token, 182.02 tokens per second) 1.26.117.420 I slot print_timing: id 0 | task 11723 | total time = 698.63 ms / 440 tokens 1.26.117.421 I slot print_timing: id 0 | task 11723 | graphs reused = 11248 1.26.117.422 I slot print_timing: id 0 | task 11723 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.117.450 I slot release: id 0 | task 11723 | stop processing: n_tokens = 471, truncated = 0 1.26.136.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 86017283 1.26.136.212 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.26.205.508 I slot launch_slot_: id 0 | task 11833 | processing task, is_child = 0 1.27.122.920 I slot print_timing: id 0 | task 11833 | prompt eval time = 126.54 ms / 403 tokens ( 0.31 ms per token, 3184.66 tokens per second) 1.27.122.925 I slot print_timing: id 0 | task 11833 | eval time = 790.85 ms / 138 tokens ( 5.77 ms per token, 173.23 tokens per second) 1.27.122.926 I slot print_timing: id 0 | task 11833 | total time = 917.39 ms / 541 tokens 1.27.122.927 I slot print_timing: id 0 | task 11833 | graphs reused = 11383 1.27.122.928 I slot print_timing: id 0 | task 11833 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.122.957 I slot release: id 0 | task 11833 | stop processing: n_tokens = 572, truncated = 0 1.27.139.343 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 87022789 1.27.139.394 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.27.213.932 I slot launch_slot_: id 0 | task 11974 | processing task, is_child = 0 1.28.417.416 I slot print_timing: id 0 | task 11974 | prompt eval time = 124.83 ms / 411 tokens ( 0.30 ms per token, 3292.58 tokens per second) 1.28.417.421 I slot print_timing: id 0 | task 11974 | eval time = 1078.64 ms / 197 tokens ( 5.50 ms per token, 181.71 tokens per second) 1.28.417.423 I slot print_timing: id 0 | task 11974 | total time = 1203.46 ms / 608 tokens 1.28.417.423 I slot print_timing: id 0 | task 11974 | graphs reused = 11577 1.28.417.424 I slot print_timing: id 0 | task 11974 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.417.454 I slot release: id 0 | task 11974 | stop processing: n_tokens = 639, truncated = 0 1.28.446.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 639, t_last = 88317286 1.28.490.535 I slot launch_slot_: id 0 | task 12174 | processing task, is_child = 0 1.29.931.352 I slot print_timing: id 0 | task 12174 | prompt eval time = 140.59 ms / 490 tokens ( 0.29 ms per token, 3485.41 tokens per second) 1.29.931.357 I slot print_timing: id 0 | task 12174 | eval time = 1300.21 ms / 238 tokens ( 5.49 ms per token, 182.28 tokens per second) 1.29.931.358 I slot print_timing: id 0 | task 12174 | total time = 1440.80 ms / 728 tokens 1.29.931.359 I slot print_timing: id 0 | task 12174 | graphs reused = 11813 1.29.931.360 I slot print_timing: id 0 | task 12174 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.931.393 I slot release: id 0 | task 12174 | stop processing: n_tokens = 759, truncated = 0 1.29.956.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 759, t_last = 89831225 1.29.956.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.30.030.496 I slot launch_slot_: id 0 | task 12415 | processing task, is_child = 0 1.32.198.641 I slot print_timing: id 0 | task 12415 | prompt eval time = 116.00 ms / 344 tokens ( 0.34 ms per token, 2965.49 tokens per second) 1.32.198.648 I slot print_timing: id 0 | task 12415 | eval time = 2052.13 ms / 376 tokens ( 5.47 ms per token, 182.74 tokens per second) 1.32.198.649 I slot print_timing: id 0 | task 12415 | total time = 2168.13 ms / 720 tokens 1.32.198.649 I slot print_timing: id 0 | task 12415 | graphs reused = 12186 1.32.198.650 I slot print_timing: id 0 | task 12415 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.198.679 I slot release: id 0 | task 12415 | stop processing: n_tokens = 751, truncated = 0 1.32.214.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 751, t_last = 92098511 1.32.214.861 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.798 MiB) 1.32.282.392 I slot launch_slot_: id 0 | task 12794 | processing task, is_child = 0 1.35.161.782 I slot print_timing: id 0 | task 12794 | prompt eval time = 119.76 ms / 347 tokens ( 0.35 ms per token, 2897.36 tokens per second) 1.35.161.787 I slot print_timing: id 0 | task 12794 | eval time = 2759.61 ms / 500 tokens ( 5.53 ms per token, 180.82 tokens per second) 1.35.161.788 I slot print_timing: id 0 | task 12794 | total time = 2879.37 ms / 847 tokens 1.35.161.789 I slot print_timing: id 0 | task 12794 | graphs reused = 12682 1.35.161.790 I slot print_timing: id 0 | task 12794 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.161.820 I slot release: id 0 | task 12794 | stop processing: n_tokens = 878, truncated = 0 1.35.188.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 878, t_last = 95061653 1.35.189.019 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.962 MiB) 1.35.259.548 I slot launch_slot_: id 0 | task 13297 | processing task, is_child = 0 1.36.133.913 I slot print_timing: id 0 | task 13297 | prompt eval time = 123.47 ms / 401 tokens ( 0.31 ms per token, 3247.65 tokens per second) 1.36.133.919 I slot print_timing: id 0 | task 13297 | eval time = 750.87 ms / 137 tokens ( 5.52 ms per token, 181.12 tokens per second) 1.36.133.920 I slot print_timing: id 0 | task 13297 | total time = 874.34 ms / 538 tokens 1.36.133.920 I slot print_timing: id 0 | task 13297 | graphs reused = 12816 1.36.133.921 I slot print_timing: id 0 | task 13297 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.133.950 I slot release: id 0 | task 13297 | stop processing: n_tokens = 569, truncated = 0 1.36.153.286 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 96033782 1.36.153.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.36.236.603 I slot launch_slot_: id 0 | task 13437 | processing task, is_child = 0 1.39.331.172 I slot print_timing: id 0 | task 13437 | prompt eval time = 136.58 ms / 456 tokens ( 0.30 ms per token, 3338.63 tokens per second) 1.39.331.178 I slot print_timing: id 0 | task 13437 | eval time = 2957.97 ms / 536 tokens ( 5.53 ms per token, 180.87 tokens per second) 1.39.331.179 I slot print_timing: id 0 | task 13437 | total time = 3094.55 ms / 992 tokens 1.39.331.180 I slot print_timing: id 0 | task 13437 | graphs reused = 13348 1.39.331.181 I slot print_timing: id 0 | task 13437 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.331.211 I slot release: id 0 | task 13437 | stop processing: n_tokens = 1023, truncated = 0 1.39.353.027 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.046 1.39.353.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.39.427.323 I slot launch_slot_: id 0 | task 13976 | processing task, is_child = 0 1.42.410.015 I slot print_timing: id 0 | task 13976 | prompt eval time = 126.12 ms / 406 tokens ( 0.31 ms per token, 3219.08 tokens per second) 1.42.410.021 I slot print_timing: id 0 | task 13976 | eval time = 2856.55 ms / 522 tokens ( 5.48 ms per token, 182.39 tokens per second) 1.42.410.022 I slot print_timing: id 0 | task 13976 | total time = 2982.67 ms / 928 tokens 1.42.410.023 I slot print_timing: id 0 | task 13976 | graphs reused = 13866 1.42.410.024 I slot print_timing: id 0 | task 13976 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.410.053 I slot release: id 0 | task 13976 | stop processing: n_tokens = 959, truncated = 0 1.42.428.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 959, t_last = 102309886 1.42.428.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.42.501.419 I slot launch_slot_: id 0 | task 14501 | processing task, is_child = 0 1.43.310.605 I slot print_timing: id 0 | task 14501 | prompt eval time = 123.88 ms / 406 tokens ( 0.31 ms per token, 3277.47 tokens per second) 1.43.310.611 I slot print_timing: id 0 | task 14501 | eval time = 685.29 ms / 125 tokens ( 5.53 ms per token, 180.95 tokens per second) 1.43.310.612 I slot print_timing: id 0 | task 14501 | total time = 809.17 ms / 531 tokens 1.43.310.613 I slot print_timing: id 0 | task 14501 | graphs reused = 13988 1.43.310.614 I slot print_timing: id 0 | task 14501 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.310.647 I slot release: id 0 | task 14501 | stop processing: n_tokens = 562, truncated = 0 1.43.324.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 103210479 1.43.367.915 I slot launch_slot_: id 0 | task 14629 | processing task, is_child = 0 1.46.501.254 I slot print_timing: id 0 | task 14629 | n_gen = 548, tg = 182.25 t/s, tg_3s = 182.59 t/s 1.49.157.380 I slot print_timing: id 0 | task 14629 | prompt eval time = 132.03 ms / 444 tokens ( 0.30 ms per token, 3363.00 tokens per second) 1.49.157.386 I slot print_timing: id 0 | task 14629 | eval time = 5657.42 ms / 1024 tokens ( 5.53 ms per token, 180.82 tokens per second) 1.49.157.387 I slot print_timing: id 0 | task 14629 | total time = 5789.45 ms / 1468 tokens 1.49.157.388 I slot print_timing: id 0 | task 14629 | graphs reused = 15006 1.49.157.389 I slot print_timing: id 0 | task 14629 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.157.422 I slot release: id 0 | task 14629 | stop processing: n_tokens = 1499, truncated = 0 1.49.182.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1499, t_last = 109057255 1.49.182.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.49.203.100 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.49.274.261 I slot launch_slot_: id 0 | task 15656 | processing task, is_child = 0 1.50.049.043 I slot print_timing: id 0 | task 15656 | prompt eval time = 122.27 ms / 372 tokens ( 0.33 ms per token, 3042.47 tokens per second) 1.50.049.049 I slot print_timing: id 0 | task 15656 | eval time = 652.49 ms / 119 tokens ( 5.53 ms per token, 180.84 tokens per second) 1.50.049.050 I slot print_timing: id 0 | task 15656 | total time = 774.76 ms / 491 tokens 1.50.049.052 I slot print_timing: id 0 | task 15656 | graphs reused = 15122 1.50.049.054 I slot print_timing: id 0 | task 15656 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.049.084 I slot release: id 0 | task 15656 | stop processing: n_tokens = 522, truncated = 0 1.50.062.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 522, t_last = 109948916 1.50.062.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.50.133.279 I slot launch_slot_: id 0 | task 15778 | processing task, is_child = 0 1.52.237.369 I slot print_timing: id 0 | task 15778 | prompt eval time = 130.88 ms / 454 tokens ( 0.29 ms per token, 3468.91 tokens per second) 1.52.237.375 I slot print_timing: id 0 | task 15778 | eval time = 1973.19 ms / 360 tokens ( 5.50 ms per token, 181.94 tokens per second) 1.52.237.376 I slot print_timing: id 0 | task 15778 | total time = 2104.07 ms / 814 tokens 1.52.237.377 I slot print_timing: id 0 | task 15778 | graphs reused = 15478 1.52.237.378 I slot print_timing: id 0 | task 15778 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.237.407 I slot release: id 0 | task 15778 | stop processing: n_tokens = 845, truncated = 0 1.52.262.038 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 845, t_last = 112137240 1.52.262.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.52.337.113 I slot launch_slot_: id 0 | task 16141 | processing task, is_child = 0 1.53.855.452 I slot print_timing: id 0 | task 16141 | prompt eval time = 119.13 ms / 354 tokens ( 0.34 ms per token, 2971.59 tokens per second) 1.53.855.458 I slot print_timing: id 0 | task 16141 | eval time = 1399.19 ms / 256 tokens ( 5.49 ms per token, 182.25 tokens per second) 1.53.855.459 I slot print_timing: id 0 | task 16141 | total time = 1518.32 ms / 610 tokens 1.53.855.460 I slot print_timing: id 0 | task 16141 | graphs reused = 15731 1.53.855.461 I slot print_timing: id 0 | task 16141 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.855.489 I slot release: id 0 | task 16141 | stop processing: n_tokens = 641, truncated = 0 1.53.870.099 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 641, t_last = 113755322 1.53.918.847 I slot launch_slot_: id 0 | task 16400 | processing task, is_child = 0 1.54.969.352 I slot print_timing: id 0 | task 16400 | prompt eval time = 116.42 ms / 334 tokens ( 0.35 ms per token, 2868.85 tokens per second) 1.54.969.357 I slot print_timing: id 0 | task 16400 | eval time = 934.06 ms / 168 tokens ( 5.59 ms per token, 178.79 tokens per second) 1.54.969.359 I slot print_timing: id 0 | task 16400 | total time = 1050.49 ms / 502 tokens 1.54.969.359 I slot print_timing: id 0 | task 16400 | graphs reused = 15896 1.54.969.360 I slot print_timing: id 0 | task 16400 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.969.387 I slot release: id 0 | task 16400 | stop processing: n_tokens = 533, truncated = 0 1.54.995.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 114869219 1.54.995.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.55.065.519 I slot launch_slot_: id 0 | task 16571 | processing task, is_child = 0 1.57.212.289 I slot print_timing: id 0 | task 16571 | prompt eval time = 128.54 ms / 426 tokens ( 0.30 ms per token, 3314.07 tokens per second) 1.57.212.295 I slot print_timing: id 0 | task 16571 | eval time = 2018.21 ms / 365 tokens ( 5.54 ms per token, 180.36 tokens per second) 1.57.212.296 I slot print_timing: id 0 | task 16571 | total time = 2146.75 ms / 791 tokens 1.57.212.297 I slot print_timing: id 0 | task 16571 | graphs reused = 16257 1.57.212.298 I slot print_timing: id 0 | task 16571 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.212.331 I slot release: id 0 | task 16571 | stop processing: n_tokens = 822, truncated = 0 1.57.236.395 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 822, t_last = 117112163 1.57.236.457 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.57.304.385 I slot launch_slot_: id 0 | task 16939 | processing task, is_child = 0 1.59.409.887 I slot print_timing: id 0 | task 16939 | prompt eval time = 119.14 ms / 366 tokens ( 0.33 ms per token, 3071.99 tokens per second) 1.59.409.892 I slot print_timing: id 0 | task 16939 | eval time = 1986.34 ms / 359 tokens ( 5.55 ms per token, 180.23 tokens per second) 1.59.409.893 I slot print_timing: id 0 | task 16939 | total time = 2105.48 ms / 725 tokens 1.59.409.894 I slot print_timing: id 0 | task 16939 | graphs reused = 16613 1.59.409.895 I slot print_timing: id 0 | task 16939 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.409.925 I slot release: id 0 | task 16939 | stop processing: n_tokens = 756, truncated = 0 1.59.429.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 756, t_last = 119309757 1.59.429.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.59.499.205 I slot launch_slot_: id 0 | task 17301 | processing task, is_child = 0 2.01.584.560 I slot print_timing: id 0 | task 17301 | prompt eval time = 133.16 ms / 462 tokens ( 0.29 ms per token, 3469.59 tokens per second) 2.01.584.568 I slot print_timing: id 0 | task 17301 | eval time = 1952.18 ms / 356 tokens ( 5.50 ms per token, 181.85 tokens per second) 2.01.584.569 I slot print_timing: id 0 | task 17301 | total time = 2085.34 ms / 818 tokens 2.01.584.570 I slot print_timing: id 0 | task 17301 | graphs reused = 16965 2.01.584.572 I slot print_timing: id 0 | task 17301 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.584.611 I slot release: id 0 | task 17301 | stop processing: n_tokens = 849, truncated = 0 2.01.600.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 121484443 2.01.600.766 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.01.672.622 I slot launch_slot_: id 0 | task 17660 | processing task, is_child = 0 2.03.343.172 I slot print_timing: id 0 | task 17660 | prompt eval time = 123.95 ms / 396 tokens ( 0.31 ms per token, 3194.79 tokens per second) 2.03.343.178 I slot print_timing: id 0 | task 17660 | eval time = 1546.58 ms / 283 tokens ( 5.48 ms per token, 182.34 tokens per second) 2.03.343.179 I slot print_timing: id 0 | task 17660 | total time = 1670.53 ms / 679 tokens 2.03.343.180 I slot print_timing: id 0 | task 17660 | graphs reused = 17245 2.03.343.180 I slot print_timing: id 0 | task 17660 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.343.212 I slot release: id 0 | task 17660 | stop processing: n_tokens = 710, truncated = 0 2.03.359.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 710, t_last = 123243044 2.03.359.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.989 MiB) 2.03.436.113 I slot launch_slot_: id 0 | task 17946 | processing task, is_child = 0 2.04.528.128 I slot print_timing: id 0 | task 17946 | prompt eval time = 132.09 ms / 458 tokens ( 0.29 ms per token, 3467.31 tokens per second) 2.04.528.134 I slot print_timing: id 0 | task 17946 | eval time = 959.90 ms / 175 tokens ( 5.52 ms per token, 181.27 tokens per second) 2.04.528.135 I slot print_timing: id 0 | task 17946 | total time = 1092.00 ms / 633 tokens 2.04.528.136 I slot print_timing: id 0 | task 17946 | graphs reused = 17417 2.04.528.137 I slot print_timing: id 0 | task 17946 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.528.168 I slot release: id 0 | task 17946 | stop processing: n_tokens = 664, truncated = 0 2.04.548.266 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 664, t_last = 124428000 2.04.548.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.04.623.855 I slot launch_slot_: id 0 | task 18124 | processing task, is_child = 0 2.05.821.335 I slot print_timing: id 0 | task 18124 | prompt eval time = 133.12 ms / 458 tokens ( 0.29 ms per token, 3440.63 tokens per second) 2.05.821.341 I slot print_timing: id 0 | task 18124 | eval time = 1064.35 ms / 189 tokens ( 5.66 ms per token, 176.63 tokens per second) 2.05.821.342 I slot print_timing: id 0 | task 18124 | total time = 1197.46 ms / 647 tokens 2.05.821.343 I slot print_timing: id 0 | task 18124 | graphs reused = 17603 2.05.821.343 I slot print_timing: id 0 | task 18124 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.821.376 I slot release: id 0 | task 18124 | stop processing: n_tokens = 678, truncated = 0 2.05.846.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 678, t_last = 125721208 2.05.890.099 I slot launch_slot_: id 0 | task 18316 | processing task, is_child = 0 2.07.709.515 I slot print_timing: id 0 | task 18316 | prompt eval time = 132.66 ms / 452 tokens ( 0.29 ms per token, 3407.26 tokens per second) 2.07.709.521 I slot print_timing: id 0 | task 18316 | eval time = 1686.74 ms / 307 tokens ( 5.51 ms per token, 181.42 tokens per second) 2.07.709.522 I slot print_timing: id 0 | task 18316 | total time = 1819.39 ms / 759 tokens 2.07.709.522 I slot print_timing: id 0 | task 18316 | graphs reused = 17906 2.07.709.523 I slot print_timing: id 0 | task 18316 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.709.557 I slot release: id 0 | task 18316 | stop processing: n_tokens = 790, truncated = 0 2.07.731.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 127609389 2.07.731.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.07.804.674 I slot launch_slot_: id 0 | task 18626 | processing task, is_child = 0 2.09.118.111 I slot print_timing: id 0 | task 18626 | prompt eval time = 125.83 ms / 404 tokens ( 0.31 ms per token, 3210.81 tokens per second) 2.09.118.117 I slot print_timing: id 0 | task 18626 | eval time = 1187.59 ms / 217 tokens ( 5.50 ms per token, 181.88 tokens per second) 2.09.118.118 I slot print_timing: id 0 | task 18626 | total time = 1313.42 ms / 621 tokens 2.09.118.118 I slot print_timing: id 0 | task 18626 | graphs reused = 18120 2.09.118.119 I slot print_timing: id 0 | task 18626 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.118.150 I slot release: id 0 | task 18626 | stop processing: n_tokens = 652, truncated = 0 2.09.146.260 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 652, t_last = 129017982 2.09.146.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.492 MiB) 2.09.219.263 I slot launch_slot_: id 0 | task 18846 | processing task, is_child = 0 2.10.152.102 I slot print_timing: id 0 | task 18846 | prompt eval time = 117.34 ms / 345 tokens ( 0.34 ms per token, 2940.27 tokens per second) 2.10.152.108 I slot print_timing: id 0 | task 18846 | eval time = 815.48 ms / 149 tokens ( 5.51 ms per token, 181.49 tokens per second) 2.10.152.109 I slot print_timing: id 0 | task 18846 | total time = 932.82 ms / 494 tokens 2.10.152.109 I slot print_timing: id 0 | task 18846 | graphs reused = 18266 2.10.152.110 I slot print_timing: id 0 | task 18846 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.152.139 I slot release: id 0 | task 18846 | stop processing: n_tokens = 525, truncated = 0 2.10.167.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 525, t_last = 130051971 2.10.167.623 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.485 MiB) 2.10.249.617 I slot launch_slot_: id 0 | task 18998 | processing task, is_child = 0 2.11.039.817 I slot print_timing: id 0 | task 18998 | prompt eval time = 131.83 ms / 430 tokens ( 0.31 ms per token, 3261.85 tokens per second) 2.11.039.822 I slot print_timing: id 0 | task 18998 | eval time = 658.35 ms / 120 tokens ( 5.53 ms per token, 180.75 tokens per second) 2.11.039.823 I slot print_timing: id 0 | task 18998 | total time = 790.18 ms / 550 tokens 2.11.039.824 I slot print_timing: id 0 | task 18998 | graphs reused = 18383 2.11.039.825 I slot print_timing: id 0 | task 18998 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.039.853 I slot release: id 0 | task 18998 | stop processing: n_tokens = 581, truncated = 0 2.11.063.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 581, t_last = 130939686 2.11.063.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.800 MiB) 2.11.132.749 I slot launch_slot_: id 0 | task 19121 | processing task, is_child = 0 2.11.736.147 I slot print_timing: id 0 | task 19121 | prompt eval time = 113.68 ms / 316 tokens ( 0.36 ms per token, 2779.66 tokens per second) 2.11.736.153 I slot print_timing: id 0 | task 19121 | eval time = 489.69 ms / 85 tokens ( 5.83 ms per token, 171.54 tokens per second) 2.11.736.154 I slot print_timing: id 0 | task 19121 | total time = 603.38 ms / 401 tokens 2.11.736.155 I slot print_timing: id 0 | task 19121 | graphs reused = 18466 2.11.736.156 I slot print_timing: id 0 | task 19121 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.736.182 I slot release: id 0 | task 19121 | stop processing: n_tokens = 432, truncated = 0 2.11.739.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 131636015 2.11.739.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.11.810.602 I slot launch_slot_: id 0 | task 19209 | processing task, is_child = 0 2.12.650.434 I slot print_timing: id 0 | task 19209 | prompt eval time = 120.42 ms / 354 tokens ( 0.34 ms per token, 2939.74 tokens per second) 2.12.650.440 I slot print_timing: id 0 | task 19209 | eval time = 719.39 ms / 131 tokens ( 5.53 ms per token, 180.71 tokens per second) 2.12.650.441 I slot print_timing: id 0 | task 19209 | total time = 839.81 ms / 485 tokens 2.12.650.442 I slot print_timing: id 0 | task 19209 | graphs reused = 18594 2.12.650.442 I slot print_timing: id 0 | task 19209 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.650.475 I slot release: id 0 | task 19209 | stop processing: n_tokens = 516, truncated = 0 2.12.668.855 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 516, t_last = 132550307 2.12.668.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.12.736.100 I slot launch_slot_: id 0 | task 19343 | processing task, is_child = 0 2.14.162.709 I slot print_timing: id 0 | task 19343 | prompt eval time = 131.50 ms / 438 tokens ( 0.30 ms per token, 3330.75 tokens per second) 2.14.162.716 I slot print_timing: id 0 | task 19343 | eval time = 1295.09 ms / 236 tokens ( 5.51 ms per token, 181.45 tokens per second) 2.14.162.717 I slot print_timing: id 0 | task 19343 | total time = 1426.59 ms / 674 tokens 2.14.162.717 I slot print_timing: id 0 | task 19343 | graphs reused = 18827 2.14.162.718 I slot print_timing: id 0 | task 19343 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.162.752 I slot release: id 0 | task 19343 | stop processing: n_tokens = 705, truncated = 0 2.14.188.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 705, t_last = 134062584 2.14.188.672 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.487 MiB) 2.14.256.889 I slot launch_slot_: id 0 | task 19582 | processing task, is_child = 0 2.14.944.568 I slot print_timing: id 0 | task 19582 | prompt eval time = 138.19 ms / 457 tokens ( 0.30 ms per token, 3307.02 tokens per second) 2.14.944.574 I slot print_timing: id 0 | task 19582 | eval time = 549.47 ms / 100 tokens ( 5.55 ms per token, 180.17 tokens per second) 2.14.944.575 I slot print_timing: id 0 | task 19582 | total time = 687.66 ms / 557 tokens 2.14.944.575 I slot print_timing: id 0 | task 19582 | graphs reused = 18924 2.14.944.576 I slot print_timing: id 0 | task 19582 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.944.608 I slot release: id 0 | task 19582 | stop processing: n_tokens = 588, truncated = 0 2.14.961.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 134844441 2.14.961.220 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.240 MiB) 2.15.033.237 I slot launch_slot_: id 0 | task 19685 | processing task, is_child = 0 2.17.989.833 I slot print_timing: id 0 | task 19685 | prompt eval time = 136.08 ms / 473 tokens ( 0.29 ms per token, 3475.90 tokens per second) 2.17.989.841 I slot print_timing: id 0 | task 19685 | eval time = 2820.50 ms / 515 tokens ( 5.49 ms per token, 182.24 tokens per second) 2.17.989.842 I slot print_timing: id 0 | task 19685 | total time = 2956.58 ms / 988 tokens 2.17.989.842 I slot print_timing: id 0 | task 19685 | graphs reused = 19435 2.17.989.843 I slot print_timing: id 0 | task 19685 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.989.877 I slot release: id 0 | task 19685 | stop processing: n_tokens = 1019, truncated = 0 2.17.993.878 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1019, t_last = 137889709 2.17.993.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.990 MiB) 2.18.063.541 I slot launch_slot_: id 0 | task 20203 | processing task, is_child = 0 2.18.553.234 I slot print_timing: id 0 | task 20203 | prompt eval time = 132.78 ms / 476 tokens ( 0.28 ms per token, 3584.80 tokens per second) 2.18.553.240 I slot print_timing: id 0 | task 20203 | eval time = 356.89 ms / 55 tokens ( 6.61 ms per token, 151.31 tokens per second) 2.18.553.241 I slot print_timing: id 0 | task 20203 | total time = 489.67 ms / 531 tokens 2.18.553.242 I slot print_timing: id 0 | task 20203 | graphs reused = 19487 2.18.553.243 I slot print_timing: id 0 | task 20203 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.553.280 I slot release: id 0 | task 20203 | stop processing: n_tokens = 562, truncated = 0 2.18.580.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 138453113 2.18.580.792 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.961 MiB) 2.18.648.177 I slot launch_slot_: id 0 | task 20261 | processing task, is_child = 0 2.20.294.570 I slot print_timing: id 0 | task 20261 | prompt eval time = 136.10 ms / 466 tokens ( 0.29 ms per token, 3423.88 tokens per second) 2.20.294.576 I slot print_timing: id 0 | task 20261 | eval time = 1510.27 ms / 275 tokens ( 5.51 ms per token, 181.42 tokens per second) 2.20.294.577 I slot print_timing: id 0 | task 20261 | total time = 1646.37 ms / 741 tokens 2.20.294.577 I slot print_timing: id 0 | task 20261 | graphs reused = 19758 2.20.294.578 I slot print_timing: id 0 | task 20261 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.294.609 I slot release: id 0 | task 20261 | stop processing: n_tokens = 772, truncated = 0 2.20.316.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 772, t_last = 140194441 2.20.316.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.298 MiB) 2.20.384.179 I slot launch_slot_: id 0 | task 20539 | processing task, is_child = 0 2.20.937.184 I slot print_timing: id 0 | task 20539 | prompt eval time = 123.40 ms / 415 tokens ( 0.30 ms per token, 3362.99 tokens per second) 2.20.937.190 I slot print_timing: id 0 | task 20539 | eval time = 429.58 ms / 78 tokens ( 5.58 ms per token, 179.24 tokens per second) 2.20.937.191 I slot print_timing: id 0 | task 20539 | total time = 552.99 ms / 493 tokens 2.20.937.191 I slot print_timing: id 0 | task 20539 | graphs reused = 19833 2.20.937.192 I slot print_timing: id 0 | task 20539 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.937.223 I slot release: id 0 | task 20539 | stop processing: n_tokens = 524, truncated = 0 2.20.954.004 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 140837055 2.20.954.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.496 MiB) 2.21.025.789 I slot launch_slot_: id 0 | task 20620 | processing task, is_child = 0 2.21.621.908 I slot print_timing: id 0 | task 20620 | prompt eval time = 117.33 ms / 352 tokens ( 0.33 ms per token, 3000.03 tokens per second) 2.21.621.914 I slot print_timing: id 0 | task 20620 | eval time = 478.77 ms / 88 tokens ( 5.50 ms per token, 181.72 tokens per second) 2.21.621.915 I slot print_timing: id 0 | task 20620 | total time = 596.10 ms / 440 tokens 2.21.621.916 I slot print_timing: id 0 | task 20620 | graphs reused = 19919 2.21.621.916 I slot print_timing: id 0 | task 20620 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.621.944 I slot release: id 0 | task 20620 | stop processing: n_tokens = 471, truncated = 0 2.21.641.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 141521776 2.21.641.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 331.494 MiB) 2.21.707.487 I slot launch_slot_: id 0 | task 20711 | processing task, is_child = 0 2.22.579.397 I slot print_timing: id 0 | task 20711 | prompt eval time = 146.32 ms / 550 tokens ( 0.27 ms per token, 3758.76 tokens per second) 2.22.579.402 I slot print_timing: id 0 | task 20711 | eval time = 725.56 ms / 133 tokens ( 5.50 ms per token, 181.93 tokens per second) 2.22.579.403 I slot print_timing: id 0 | task 20711 | total time = 871.89 ms / 683 tokens 2.22.579.404 I slot print_timing: id 0 | task 20711 | graphs reused = 20050 2.22.579.405 I slot print_timing: id 0 | task 20711 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.579.439 I slot release: id 0 | task 20711 | stop processing: n_tokens = 714, truncated = 0 2.22.605.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 142479271 2.22.605.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.079 MiB) 2.22.679.000 I slot launch_slot_: id 0 | task 20848 | processing task, is_child = 0 2.25.856.556 I slot print_timing: id 0 | task 20848 | n_gen = 546, tg = 181.49 t/s, tg_3s = 181.82 t/s 2.25.960.936 I slot print_timing: id 0 | task 20848 | prompt eval time = 174.61 ms / 772 tokens ( 0.23 ms per token, 4421.26 tokens per second) 2.25.960.941 I slot print_timing: id 0 | task 20848 | eval time = 3107.31 ms / 565 tokens ( 5.51 ms per token, 181.51 tokens per second) 2.25.960.942 I slot print_timing: id 0 | task 20848 | total time = 3281.92 ms / 1337 tokens 2.25.960.943 I slot print_timing: id 0 | task 20848 | graphs reused = 20611 2.25.960.944 I slot print_timing: id 0 | task 20848 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.960.980 I slot release: id 0 | task 20848 | stop processing: n_tokens = 1368, truncated = 0 2.25.976.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1368, t_last = 145860812 2.25.976.894 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 348.382 MiB) 2.26.056.622 I slot launch_slot_: id 0 | task 21417 | processing task, is_child = 0 2.27.337.371 I slot print_timing: id 0 | task 21417 | prompt eval time = 171.52 ms / 683 tokens ( 0.25 ms per token, 3982.00 tokens per second) 2.27.337.376 I slot print_timing: id 0 | task 21417 | eval time = 1109.21 ms / 202 tokens ( 5.52 ms per token, 181.21 tokens per second) 2.27.337.378 I slot print_timing: id 0 | task 21417 | total time = 1280.73 ms / 885 tokens 2.27.337.379 I slot print_timing: id 0 | task 21417 | graphs reused = 20810 2.27.337.379 I slot print_timing: id 0 | task 21417 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.337.415 I slot release: id 0 | task 21417 | stop processing: n_tokens = 916, truncated = 0 2.27.356.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 916, t_last = 147237247 2.27.356.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.828 MiB) 2.27.376.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.929 MiB) 2.27.462.683 I slot launch_slot_: id 0 | task 21623 | processing task, is_child = 0 2.28.218.185 I slot print_timing: id 0 | task 21623 | prompt eval time = 155.29 ms / 579 tokens ( 0.27 ms per token, 3728.58 tokens per second) 2.28.218.191 I slot print_timing: id 0 | task 21623 | eval time = 600.19 ms / 110 tokens ( 5.51 ms per token, 181.61 tokens per second) 2.28.218.192 I slot print_timing: id 0 | task 21623 | total time = 755.48 ms / 689 tokens 2.28.218.193 I slot print_timing: id 0 | task 21623 | graphs reused = 20918 2.28.218.194 I slot print_timing: id 0 | task 21623 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.218.232 I slot release: id 0 | task 21623 | stop processing: n_tokens = 720, truncated = 0 2.28.245.552 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 720, t_last = 148118064 2.28.245.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.550 MiB) 2.28.328.292 I slot launch_slot_: id 0 | task 21737 | processing task, is_child = 0 2.29.177.835 I slot print_timing: id 0 | task 21737 | prompt eval time = 145.69 ms / 500 tokens ( 0.29 ms per token, 3432.04 tokens per second) 2.29.177.841 I slot print_timing: id 0 | task 21737 | eval time = 703.84 ms / 129 tokens ( 5.50 ms per token, 181.86 tokens per second) 2.29.177.842 I slot print_timing: id 0 | task 21737 | total time = 849.52 ms / 629 tokens 2.29.177.842 I slot print_timing: id 0 | task 21737 | graphs reused = 21045 2.29.177.843 I slot print_timing: id 0 | task 21737 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.177.875 I slot release: id 0 | task 21737 | stop processing: n_tokens = 660, truncated = 0 2.29.203.580 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 149077707 2.29.203.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 2.29.272.075 I slot launch_slot_: id 0 | task 21869 | processing task, is_child = 0 2.30.116.370 I slot print_timing: id 0 | task 21869 | prompt eval time = 181.20 ms / 776 tokens ( 0.23 ms per token, 4282.51 tokens per second) 2.30.116.376 I slot print_timing: id 0 | task 21869 | eval time = 663.07 ms / 121 tokens ( 5.53 ms per token, 180.98 tokens per second) 2.30.116.377 I slot print_timing: id 0 | task 21869 | total time = 844.27 ms / 897 tokens 2.30.116.378 I slot print_timing: id 0 | task 21869 | graphs reused = 21164 2.30.116.379 I slot print_timing: id 0 | task 21869 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.116.419 I slot release: id 0 | task 21869 | stop processing: n_tokens = 928, truncated = 0 2.30.144.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 928, t_last = 150016251 2.30.144.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.210 MiB) 2.30.226.858 I slot launch_slot_: id 0 | task 21994 | processing task, is_child = 0 2.31.684.779 I slot print_timing: id 0 | task 21994 | prompt eval time = 143.33 ms / 504 tokens ( 0.28 ms per token, 3516.41 tokens per second) 2.31.684.785 I slot print_timing: id 0 | task 21994 | eval time = 1314.57 ms / 240 tokens ( 5.50 ms per token, 181.81 tokens per second) 2.31.684.786 I slot print_timing: id 0 | task 21994 | total time = 1457.90 ms / 744 tokens 2.31.684.786 I slot print_timing: id 0 | task 21994 | graphs reused = 21401 2.31.684.787 I slot print_timing: id 0 | task 21994 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.684.820 I slot release: id 0 | task 21994 | stop processing: n_tokens = 775, truncated = 0 2.31.702.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 775, t_last = 151584652 2.31.702.985 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.146 MiB) 2.31.770.933 I slot launch_slot_: id 0 | task 22237 | processing task, is_child = 0 2.33.374.322 I slot print_timing: id 0 | task 22237 | prompt eval time = 160.51 ms / 633 tokens ( 0.25 ms per token, 3943.63 tokens per second) 2.33.374.328 I slot print_timing: id 0 | task 22237 | eval time = 1442.86 ms / 263 tokens ( 5.51 ms per token, 181.58 tokens per second) 2.33.374.329 I slot print_timing: id 0 | task 22237 | total time = 1603.37 ms / 896 tokens 2.33.374.329 I slot print_timing: id 0 | task 22237 | graphs reused = 21661 2.33.374.331 I slot print_timing: id 0 | task 22237 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.374.367 I slot release: id 0 | task 22237 | stop processing: n_tokens = 927, truncated = 0 2.33.393.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 927, t_last = 153274199 2.33.393.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.054 MiB) 2.33.468.844 I slot launch_slot_: id 0 | task 22504 | processing task, is_child = 0 2.36.601.620 I slot print_timing: id 0 | task 22504 | n_gen = 549, tg = 182.38 t/s, tg_3s = 182.71 t/s 2.37.615.659 I slot print_timing: id 0 | task 22504 | prompt eval time = 128.07 ms / 395 tokens ( 0.32 ms per token, 3084.20 tokens per second) 2.37.615.664 I slot print_timing: id 0 | task 22504 | eval time = 4018.72 ms / 733 tokens ( 5.49 ms per token, 182.15 tokens per second) 2.37.615.665 I slot print_timing: id 0 | task 22504 | total time = 4146.80 ms / 1128 tokens 2.37.615.666 I slot print_timing: id 0 | task 22504 | graphs reused = 22389 2.37.615.667 I slot print_timing: id 0 | task 22504 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.615.697 I slot release: id 0 | task 22504 | stop processing: n_tokens = 1159, truncated = 0 2.37.643.651 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1159, t_last = 157515529 2.37.643.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.707 MiB) 2.37.716.640 I slot launch_slot_: id 0 | task 23240 | processing task, is_child = 0 2.39.137.381 I slot print_timing: id 0 | task 23240 | prompt eval time = 151.94 ms / 584 tokens ( 0.26 ms per token, 3843.75 tokens per second) 2.39.137.387 I slot print_timing: id 0 | task 23240 | eval time = 1268.79 ms / 231 tokens ( 5.52 ms per token, 181.28 tokens per second) 2.39.137.388 I slot print_timing: id 0 | task 23240 | total time = 1420.72 ms / 815 tokens 2.39.137.388 I slot print_timing: id 0 | task 23240 | graphs reused = 22617 2.39.137.389 I slot print_timing: id 0 | task 23240 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.137.427 I slot release: id 0 | task 23240 | stop processing: n_tokens = 846, truncated = 0 2.39.156.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 846, t_last = 159037259 2.39.156.468 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.269 MiB) 2.39.232.826 I slot launch_slot_: id 0 | task 23475 | processing task, is_child = 0 2.40.825.684 I slot print_timing: id 0 | task 23475 | prompt eval time = 171.36 ms / 695 tokens ( 0.25 ms per token, 4055.72 tokens per second) 2.40.825.689 I slot print_timing: id 0 | task 23475 | eval time = 1421.48 ms / 259 tokens ( 5.51 ms per token, 181.50 tokens per second) 2.40.825.690 I slot print_timing: id 0 | task 23475 | total time = 1592.84 ms / 954 tokens 2.40.825.691 I slot print_timing: id 0 | task 23475 | graphs reused = 22873 2.40.825.692 I slot print_timing: id 0 | task 23475 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.825.731 I slot release: id 0 | task 23475 | stop processing: n_tokens = 985, truncated = 0 2.40.853.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 985, t_last = 160725563 2.40.853.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.707 MiB) 2.40.872.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.209 MiB) 2.40.951.955 I slot launch_slot_: id 0 | task 23738 | processing task, is_child = 0 2.41.694.410 I slot print_timing: id 0 | task 23738 | prompt eval time = 180.19 ms / 769 tokens ( 0.23 ms per token, 4267.79 tokens per second) 2.41.694.416 I slot print_timing: id 0 | task 23738 | eval time = 562.25 ms / 101 tokens ( 5.62 ms per token, 177.86 tokens per second) 2.41.694.417 I slot print_timing: id 0 | task 23738 | total time = 742.43 ms / 870 tokens 2.41.694.418 I slot print_timing: id 0 | task 23738 | graphs reused = 22972 2.41.694.418 I slot print_timing: id 0 | task 23738 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.694.461 I slot release: id 0 | task 23738 | stop processing: n_tokens = 901, truncated = 0 2.41.709.530 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 901, t_last = 161594293 2.41.709.592 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.894 MiB) 2.41.786.983 I slot launch_slot_: id 0 | task 23843 | processing task, is_child = 0 2.42.679.453 I slot print_timing: id 0 | task 23843 | prompt eval time = 151.14 ms / 576 tokens ( 0.26 ms per token, 3811.14 tokens per second) 2.42.679.459 I slot print_timing: id 0 | task 23843 | eval time = 741.31 ms / 131 tokens ( 5.70 ms per token, 175.36 tokens per second) 2.42.679.460 I slot print_timing: id 0 | task 23843 | total time = 892.45 ms / 707 tokens 2.42.679.461 I slot print_timing: id 0 | task 23843 | graphs reused = 23101 2.42.679.461 I slot print_timing: id 0 | task 23843 | graph reallocs = 0 / 0 (same size) / (changed size) 2.42.679.497 I slot release: id 0 | task 23843 | stop processing: n_tokens = 738, truncated = 0 2.42.707.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 162579329 2.42.707.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.922 MiB) 2.42.781.715 I slot launch_slot_: id 0 | task 23978 | processing task, is_child = 0 2.44.029.985 I slot print_timing: id 0 | task 23978 | prompt eval time = 164.53 ms / 655 tokens ( 0.25 ms per token, 3981.13 tokens per second) 2.44.029.991 I slot print_timing: id 0 | task 23978 | eval time = 1083.72 ms / 197 tokens ( 5.53 ms per token, 180.86 tokens per second) 2.44.029.992 I slot print_timing: id 0 | task 23978 | total time = 1248.25 ms / 852 tokens 2.44.029.992 I slot print_timing: id 0 | task 23978 | graphs reused = 23295 2.44.029.993 I slot print_timing: id 0 | task 23978 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.030.029 I slot release: id 0 | task 23978 | stop processing: n_tokens = 883, truncated = 0 2.44.048.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 163929861 2.44.049.017 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.673 MiB) 2.44.126.319 I slot launch_slot_: id 0 | task 24179 | processing task, is_child = 0 2.45.537.086 I slot print_timing: id 0 | task 24179 | prompt eval time = 160.55 ms / 621 tokens ( 0.26 ms per token, 3868.05 tokens per second) 2.45.537.092 I slot print_timing: id 0 | task 24179 | eval time = 1250.20 ms / 228 tokens ( 5.51 ms per token, 181.57 tokens per second) 2.45.537.093 I slot print_timing: id 0 | task 24179 | total time = 1410.75 ms / 849 tokens 2.45.537.094 I slot print_timing: id 0 | task 24179 | graphs reused = 23520 2.45.537.094 I slot print_timing: id 0 | task 24179 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.537.132 I slot release: id 0 | task 24179 | stop processing: n_tokens = 880, truncated = 0 2.45.561.209 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 880, t_last = 165436964 2.45.561.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.45.635.087 I slot launch_slot_: id 0 | task 24411 | processing task, is_child = 0 2.46.917.674 I slot print_timing: id 0 | task 24411 | prompt eval time = 177.77 ms / 767 tokens ( 0.23 ms per token, 4314.47 tokens per second) 2.46.917.680 I slot print_timing: id 0 | task 24411 | eval time = 1104.79 ms / 196 tokens ( 5.67 ms per token, 176.50 tokens per second) 2.46.917.681 I slot print_timing: id 0 | task 24411 | total time = 1282.57 ms / 963 tokens 2.46.917.682 I slot print_timing: id 0 | task 24411 | graphs reused = 23714 2.46.917.683 I slot print_timing: id 0 | task 24411 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.917.727 I slot release: id 0 | task 24411 | stop processing: n_tokens = 994, truncated = 0 2.46.945.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 994, t_last = 166817559 2.46.945.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.640 MiB) 2.47.021.515 I slot launch_slot_: id 0 | task 24611 | processing task, is_child = 0 2.48.538.698 I slot print_timing: id 0 | task 24611 | prompt eval time = 198.32 ms / 864 tokens ( 0.23 ms per token, 4356.51 tokens per second) 2.48.538.703 I slot print_timing: id 0 | task 24611 | eval time = 1318.84 ms / 234 tokens ( 5.66 ms per token, 176.67 tokens per second) 2.48.538.705 I slot print_timing: id 0 | task 24611 | total time = 1517.16 ms / 1098 tokens 2.48.538.705 I slot print_timing: id 0 | task 24611 | graphs reused = 23945 2.48.538.706 I slot print_timing: id 0 | task 24611 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.538.750 I slot release: id 0 | task 24611 | stop processing: n_tokens = 1129, truncated = 0 2.48.558.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1129, t_last = 168438582 2.48.558.986 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.551 MiB) 2.48.578.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.892 MiB) 2.48.655.387 I slot launch_slot_: id 0 | task 24849 | processing task, is_child = 0 2.49.709.884 I slot print_timing: id 0 | task 24849 | prompt eval time = 168.28 ms / 646 tokens ( 0.26 ms per token, 3838.75 tokens per second) 2.49.709.889 I slot print_timing: id 0 | task 24849 | eval time = 886.19 ms / 161 tokens ( 5.54 ms per token, 180.55 tokens per second) 2.49.709.891 I slot print_timing: id 0 | task 24849 | total time = 1054.48 ms / 807 tokens 2.49.709.892 I slot print_timing: id 0 | task 24849 | graphs reused = 24103 2.49.709.893 I slot print_timing: id 0 | task 24849 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.709.934 I slot release: id 0 | task 24849 | stop processing: n_tokens = 838, truncated = 0 2.49.730.064 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 838, t_last = 169609766 2.49.730.130 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 333.371 MiB) 2.49.808.367 I slot launch_slot_: id 0 | task 25014 | processing task, is_child = 0 2.51.811.989 I slot print_timing: id 0 | task 25014 | prompt eval time = 172.54 ms / 720 tokens ( 0.24 ms per token, 4172.95 tokens per second) 2.51.811.994 I slot print_timing: id 0 | task 25014 | eval time = 1831.06 ms / 322 tokens ( 5.70 ms per token, 175.31 tokens per second) 2.51.811.996 I slot print_timing: id 0 | task 25014 | total time = 2003.60 ms / 1042 tokens 2.51.811.997 I slot print_timing: id 0 | task 25014 | graphs reused = 24421 2.51.811.998 I slot print_timing: id 0 | task 25014 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.812.038 I slot release: id 0 | task 25014 | stop processing: n_tokens = 1073, truncated = 0 2.51.837.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1073, t_last = 171711871 2.51.837.309 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.079 MiB) 2.51.913.703 I slot launch_slot_: id 0 | task 25340 | processing task, is_child = 0 2.53.399.885 I slot print_timing: id 0 | task 25340 | prompt eval time = 142.91 ms / 509 tokens ( 0.28 ms per token, 3561.63 tokens per second) 2.53.399.891 I slot print_timing: id 0 | task 25340 | eval time = 1343.25 ms / 245 tokens ( 5.51 ms per token, 181.65 tokens per second) 2.53.399.892 I slot print_timing: id 0 | task 25340 | total time = 1486.16 ms / 754 tokens 2.53.399.892 I slot print_timing: id 0 | task 25340 | graphs reused = 24663 2.53.399.893 I slot print_timing: id 0 | task 25340 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.399.929 I slot release: id 0 | task 25340 | stop processing: n_tokens = 785, truncated = 0 2.53.423.438 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 785, t_last = 173299761 2.53.423.500 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.646 MiB) 2.53.492.216 I slot launch_slot_: id 0 | task 25588 | processing task, is_child = 0 2.55.586.243 I slot print_timing: id 0 | task 25588 | prompt eval time = 151.29 ms / 581 tokens ( 0.26 ms per token, 3840.36 tokens per second) 2.55.586.249 I slot print_timing: id 0 | task 25588 | eval time = 1942.72 ms / 355 tokens ( 5.49 ms per token, 182.22 tokens per second) 2.55.586.250 I slot print_timing: id 0 | task 25588 | total time = 2094.01 ms / 936 tokens 2.55.586.250 I slot print_timing: id 0 | task 25588 | graphs reused = 25015 2.55.586.251 I slot print_timing: id 0 | task 25588 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.586.291 I slot release: id 0 | task 25588 | stop processing: n_tokens = 967, truncated = 0 2.55.602.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 967, t_last = 175486123 2.55.603.048 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 2.55.675.893 I slot launch_slot_: id 0 | task 25947 | processing task, is_child = 0 2.57.902.301 I slot print_timing: id 0 | task 25947 | prompt eval time = 200.76 ms / 925 tokens ( 0.22 ms per token, 4607.54 tokens per second) 2.57.902.307 I slot print_timing: id 0 | task 25947 | eval time = 2025.63 ms / 363 tokens ( 5.60 ms per token, 178.71 tokens per second) 2.57.902.308 I slot print_timing: id 0 | task 25947 | total time = 2226.39 ms / 1288 tokens 2.57.902.309 I slot print_timing: id 0 | task 25947 | graphs reused = 25374 2.57.902.310 I slot print_timing: id 0 | task 25947 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.902.355 I slot release: id 0 | task 25947 | stop processing: n_tokens = 1319, truncated = 0 2.57.928.755 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1319, t_last = 177802187 2.57.928.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.58.010.411 I slot launch_slot_: id 0 | task 26314 | processing task, is_child = 0 3.00.453.350 I slot print_timing: id 0 | task 26314 | prompt eval time = 195.86 ms / 885 tokens ( 0.22 ms per token, 4518.49 tokens per second) 3.00.453.356 I slot print_timing: id 0 | task 26314 | eval time = 2247.06 ms / 402 tokens ( 5.60 ms per token, 178.46 tokens per second) 3.00.453.357 I slot print_timing: id 0 | task 26314 | total time = 2442.92 ms / 1287 tokens 3.00.453.358 I slot print_timing: id 0 | task 26314 | graphs reused = 25772 3.00.453.358 I slot print_timing: id 0 | task 26314 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.453.410 I slot release: id 0 | task 26314 | stop processing: n_tokens = 1318, truncated = 0 3.00.472.775 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1318, t_last = 180353242 3.00.472.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.00.495.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 394.536 MiB) 3.00.577.707 I slot launch_slot_: id 0 | task 26720 | processing task, is_child = 0 3.02.085.115 I slot print_timing: id 0 | task 26720 | prompt eval time = 125.54 ms / 392 tokens ( 0.32 ms per token, 3122.54 tokens per second) 3.02.085.120 I slot print_timing: id 0 | task 26720 | eval time = 1381.85 ms / 253 tokens ( 5.48 ms per token, 182.36 tokens per second) 3.02.085.121 I slot print_timing: id 0 | task 26720 | total time = 1507.39 ms / 645 tokens 3.02.085.122 I slot print_timing: id 0 | task 26720 | graphs reused = 26022 3.02.085.123 I slot print_timing: id 0 | task 26720 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.085.153 I slot release: id 0 | task 26720 | stop processing: n_tokens = 676, truncated = 0 3.02.113.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 676, t_last = 181984986 3.02.157.907 I slot launch_slot_: id 0 | task 26976 | processing task, is_child = 0 3.02.929.581 I slot print_timing: id 0 | task 26976 | prompt eval time = 114.10 ms / 331 tokens ( 0.34 ms per token, 2901.07 tokens per second) 3.02.929.587 I slot print_timing: id 0 | task 26976 | eval time = 657.56 ms / 121 tokens ( 5.48 ms per token, 182.49 tokens per second) 3.02.929.588 I slot print_timing: id 0 | task 26976 | total time = 771.65 ms / 452 tokens 3.02.929.589 I slot print_timing: id 0 | task 26976 | graphs reused = 26141 3.02.929.590 I slot print_timing: id 0 | task 26976 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.929.618 I slot release: id 0 | task 26976 | stop processing: n_tokens = 483, truncated = 0 3.02.956.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 182829450 3.02.956.224 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.400 MiB) 3.03.027.514 I slot launch_slot_: id 0 | task 27100 | processing task, is_child = 0 3.05.053.626 I slot print_timing: id 0 | task 27100 | prompt eval time = 117.23 ms / 357 tokens ( 0.33 ms per token, 3045.24 tokens per second) 3.05.053.632 I slot print_timing: id 0 | task 27100 | eval time = 1908.86 ms / 350 tokens ( 5.47 ms per token, 182.83 tokens per second) 3.05.053.633 I slot print_timing: id 0 | task 27100 | total time = 2026.09 ms / 707 tokens 3.05.053.634 I slot print_timing: id 0 | task 27100 | graphs reused = 26488 3.05.053.634 I slot print_timing: id 0 | task 27100 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.053.663 I slot release: id 0 | task 27100 | stop processing: n_tokens = 738, truncated = 0 3.05.081.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 184953495 3.05.082.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.271 MiB) 3.05.153.801 I slot launch_slot_: id 0 | task 27453 | processing task, is_child = 0 3.05.770.492 I slot print_timing: id 0 | task 27453 | prompt eval time = 116.89 ms / 315 tokens ( 0.37 ms per token, 2694.77 tokens per second) 3.05.770.497 I slot print_timing: id 0 | task 27453 | eval time = 499.78 ms / 92 tokens ( 5.49 ms per token, 182.08 tokens per second) 3.05.770.499 I slot print_timing: id 0 | task 27453 | total time = 616.67 ms / 407 tokens 3.05.770.499 I slot print_timing: id 0 | task 27453 | graphs reused = 26578 3.05.770.500 I slot print_timing: id 0 | task 27453 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.770.526 I slot release: id 0 | task 27453 | stop processing: n_tokens = 438, truncated = 0 3.05.791.163 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 438, t_last = 185670359 3.05.791.201 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.144 MiB) 3.05.856.917 I slot launch_slot_: id 0 | task 27548 | processing task, is_child = 0 3.08.978.783 I slot print_timing: id 0 | task 27548 | n_gen = 549, tg = 182.40 t/s, tg_3s = 182.73 t/s 3.09.432.744 I slot print_timing: id 0 | task 27548 | prompt eval time = 117.43 ms / 378 tokens ( 0.31 ms per token, 3218.91 tokens per second) 3.09.432.750 I slot print_timing: id 0 | task 27548 | eval time = 3458.38 ms / 631 tokens ( 5.49 ms per token, 182.17 tokens per second) 3.09.432.751 I slot print_timing: id 0 | task 27548 | total time = 3575.81 ms / 1009 tokens 3.09.432.752 I slot print_timing: id 0 | task 27548 | graphs reused = 27204 3.09.432.753 I slot print_timing: id 0 | task 27548 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.432.783 I slot release: id 0 | task 27548 | stop processing: n_tokens = 1040, truncated = 0 3.09.446.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1040, t_last = 189332615 3.09.446.380 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.775 MiB) 3.09.533.810 I slot launch_slot_: id 0 | task 28182 | processing task, is_child = 0 3.10.539.389 I slot print_timing: id 0 | task 28182 | prompt eval time = 109.86 ms / 295 tokens ( 0.37 ms per token, 2685.24 tokens per second) 3.10.539.395 I slot print_timing: id 0 | task 28182 | eval time = 895.70 ms / 165 tokens ( 5.46 ms per token, 183.10 tokens per second) 3.10.539.396 I slot print_timing: id 0 | task 28182 | total time = 1005.56 ms / 460 tokens 3.10.539.398 I slot print_timing: id 0 | task 28182 | graphs reused = 27367 3.10.539.399 I slot print_timing: id 0 | task 28182 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.539.426 I slot release: id 0 | task 28182 | stop processing: n_tokens = 491, truncated = 0 3.10.553.045 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 190439258 3.10.553.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.740 MiB) 3.10.619.243 I slot launch_slot_: id 0 | task 28350 | processing task, is_child = 0 3.11.623.663 I slot print_timing: id 0 | task 28350 | prompt eval time = 113.99 ms / 337 tokens ( 0.34 ms per token, 2956.50 tokens per second) 3.11.623.669 I slot print_timing: id 0 | task 28350 | eval time = 890.42 ms / 163 tokens ( 5.50 ms per token, 181.94 tokens per second) 3.11.623.670 I slot print_timing: id 0 | task 28350 | total time = 1004.40 ms / 500 tokens 3.11.623.671 I slot print_timing: id 0 | task 28350 | graphs reused = 27527 3.11.623.672 I slot print_timing: id 0 | task 28350 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.623.700 I slot release: id 0 | task 28350 | stop processing: n_tokens = 531, truncated = 0 3.11.637.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 191523532 3.11.637.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.744 MiB) 3.11.717.007 I slot launch_slot_: id 0 | task 28516 | processing task, is_child = 0 3.12.287.335 I slot print_timing: id 0 | task 28516 | prompt eval time = 114.31 ms / 325 tokens ( 0.35 ms per token, 2843.15 tokens per second) 3.12.287.341 I slot print_timing: id 0 | task 28516 | eval time = 456.00 ms / 84 tokens ( 5.49 ms per token, 182.02 tokens per second) 3.12.287.342 I slot print_timing: id 0 | task 28516 | total time = 570.31 ms / 409 tokens 3.12.287.343 I slot print_timing: id 0 | task 28516 | graphs reused = 27609 3.12.287.344 I slot print_timing: id 0 | task 28516 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.287.374 I slot release: id 0 | task 28516 | stop processing: n_tokens = 440, truncated = 0 3.12.308.324 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.073 3.12.308.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 337.749 MiB) 3.12.375.016 I slot launch_slot_: id 0 | task 28603 | processing task, is_child = 0 3.12.971.830 I slot print_timing: id 0 | task 28603 | prompt eval time = 102.87 ms / 264 tokens ( 0.39 ms per token, 2566.27 tokens per second) 3.12.971.835 I slot print_timing: id 0 | task 28603 | eval time = 493.92 ms / 91 tokens ( 5.49 ms per token, 182.21 tokens per second) 3.12.971.836 I slot print_timing: id 0 | task 28603 | total time = 596.80 ms / 355 tokens 3.12.971.837 I slot print_timing: id 0 | task 28603 | graphs reused = 27698 3.12.971.838 I slot print_timing: id 0 | task 28603 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.971.861 I slot release: id 0 | task 28603 | stop processing: n_tokens = 386, truncated = 0 3.12.996.822 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 386, t_last = 192871694 3.13.039.858 I slot launch_slot_: id 0 | task 28697 | processing task, is_child = 0 3.13.195.835 I slot print_timing: id 0 | task 28697 | prompt eval time = 118.12 ms / 331 tokens ( 0.36 ms per token, 2802.28 tokens per second) 3.13.195.841 I slot print_timing: id 0 | task 28697 | eval time = 37.84 ms / 7 tokens ( 6.31 ms per token, 158.57 tokens per second) 3.13.195.842 I slot print_timing: id 0 | task 28697 | total time = 155.96 ms / 338 tokens 3.13.195.843 I slot print_timing: id 0 | task 28697 | graphs reused = 27703 3.13.195.843 I slot print_timing: id 0 | task 28697 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.195.873 I slot release: id 0 | task 28697 | stop processing: n_tokens = 369, truncated = 0 3.13.214.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 369, t_last = 193095706 3.13.214.407 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.211 MiB) 3.13.291.237 I slot launch_slot_: id 0 | task 28707 | processing task, is_child = 0 3.14.230.391 I slot print_timing: id 0 | task 28707 | prompt eval time = 118.77 ms / 333 tokens ( 0.36 ms per token, 2803.74 tokens per second) 3.14.230.396 I slot print_timing: id 0 | task 28707 | eval time = 820.36 ms / 150 tokens ( 5.51 ms per token, 181.63 tokens per second) 3.14.230.397 I slot print_timing: id 0 | task 28707 | total time = 939.13 ms / 483 tokens 3.14.230.398 I slot print_timing: id 0 | task 28707 | graphs reused = 27850 3.14.230.399 I slot print_timing: id 0 | task 28707 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.230.425 I slot release: id 0 | task 28707 | stop processing: n_tokens = 514, truncated = 0 3.14.246.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 194130257 3.14.246.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.558 MiB) 3.14.327.070 I slot launch_slot_: id 0 | task 28860 | processing task, is_child = 0 3.16.807.792 I slot print_timing: id 0 | task 28860 | prompt eval time = 118.23 ms / 346 tokens ( 0.34 ms per token, 2926.50 tokens per second) 3.16.807.798 I slot print_timing: id 0 | task 28860 | eval time = 2362.47 ms / 429 tokens ( 5.52 ms per token, 181.17 tokens per second) 3.16.807.799 I slot print_timing: id 0 | task 28860 | total time = 2480.70 ms / 775 tokens 3.16.807.800 I slot print_timing: id 0 | task 28860 | graphs reused = 28275 3.16.807.801 I slot print_timing: id 0 | task 28860 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.807.832 I slot release: id 0 | task 28860 | stop processing: n_tokens = 806, truncated = 0 3.16.828.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 196707664 3.16.828.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.931 MiB) 3.16.898.316 I slot launch_slot_: id 0 | task 29292 | processing task, is_child = 0 3.17.898.856 I slot print_timing: id 0 | task 29292 | prompt eval time = 113.62 ms / 325 tokens ( 0.35 ms per token, 2860.34 tokens per second) 3.17.898.862 I slot print_timing: id 0 | task 29292 | eval time = 886.90 ms / 162 tokens ( 5.51 ms per token, 181.53 tokens per second) 3.17.898.863 I slot print_timing: id 0 | task 29292 | total time = 1000.52 ms / 487 tokens 3.17.898.864 I slot print_timing: id 0 | task 29292 | graphs reused = 28434 3.17.898.865 I slot print_timing: id 0 | task 29292 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.898.892 I slot release: id 0 | task 29292 | stop processing: n_tokens = 518, truncated = 0 3.17.902.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 197798724 3.17.902.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.834 MiB) 3.17.972.468 I slot launch_slot_: id 0 | task 29457 | processing task, is_child = 0 3.19.343.960 I slot print_timing: id 0 | task 29457 | prompt eval time = 117.61 ms / 322 tokens ( 0.37 ms per token, 2737.84 tokens per second) 3.19.343.966 I slot print_timing: id 0 | task 29457 | eval time = 1253.86 ms / 229 tokens ( 5.50 ms per token, 181.84 tokens per second) 3.19.343.967 I slot print_timing: id 0 | task 29457 | total time = 1371.47 ms / 551 tokens 3.19.343.968 I slot print_timing: id 0 | task 29457 | graphs reused = 28660 3.19.343.969 I slot print_timing: id 0 | task 29457 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.343.996 I slot release: id 0 | task 29457 | stop processing: n_tokens = 582, truncated = 0 3.19.360.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 582, t_last = 199243828 3.19.360.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 3.19.430.340 I slot launch_slot_: id 0 | task 29689 | processing task, is_child = 0 3.21.470.175 I slot print_timing: id 0 | task 29689 | prompt eval time = 115.98 ms / 338 tokens ( 0.34 ms per token, 2914.30 tokens per second) 3.21.470.181 I slot print_timing: id 0 | task 29689 | eval time = 1923.84 ms / 352 tokens ( 5.48 ms per token, 182.45 tokens per second) 3.21.470.182 I slot print_timing: id 0 | task 29689 | total time = 2039.82 ms / 690 tokens 3.21.470.183 I slot print_timing: id 0 | task 29689 | graphs reused = 29009 3.21.470.184 I slot print_timing: id 0 | task 29689 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.470.211 I slot release: id 0 | task 29689 | stop processing: n_tokens = 721, truncated = 0 3.21.489.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 721, t_last = 201370044 3.21.489.740 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.274 MiB) 3.21.560.836 I slot launch_slot_: id 0 | task 30044 | processing task, is_child = 0 3.24.681.129 I slot print_timing: id 0 | task 30044 | n_gen = 549, tg = 182.38 t/s, tg_3s = 182.71 t/s 3.27.314.057 I slot print_timing: id 0 | task 30044 | prompt eval time = 115.52 ms / 347 tokens ( 0.33 ms per token, 3003.73 tokens per second) 3.27.314.063 I slot print_timing: id 0 | task 30044 | eval time = 5637.68 ms / 1024 tokens ( 5.51 ms per token, 181.46 tokens per second) 3.27.314.064 I slot print_timing: id 0 | task 30044 | total time = 5753.20 ms / 1371 tokens 3.27.314.065 I slot print_timing: id 0 | task 30044 | graphs reused = 30027 3.27.314.066 I slot print_timing: id 0 | task 30044 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.314.096 I slot release: id 0 | task 30044 | stop processing: n_tokens = 1402, truncated = 0 3.27.327.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 207213929 3.27.375.204 I slot launch_slot_: id 0 | task 31071 | processing task, is_child = 0 3.29.379.170 I slot print_timing: id 0 | task 31071 | prompt eval time = 118.83 ms / 331 tokens ( 0.36 ms per token, 2785.61 tokens per second) 3.29.379.179 I slot print_timing: id 0 | task 31071 | eval time = 1885.12 ms / 345 tokens ( 5.48 ms per token, 182.48 tokens per second) 3.29.379.180 I slot print_timing: id 0 | task 31071 | total time = 2003.94 ms / 676 tokens 3.29.379.181 I slot print_timing: id 0 | task 31071 | graphs reused = 30369 3.29.379.182 I slot print_timing: id 0 | task 31071 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.379.211 I slot release: id 0 | task 31071 | stop processing: n_tokens = 707, truncated = 0 3.29.392.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 209279043 3.29.392.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.839 MiB) 3.29.463.324 I slot launch_slot_: id 0 | task 31419 | processing task, is_child = 0 3.30.199.075 I slot print_timing: id 0 | task 31419 | prompt eval time = 114.93 ms / 345 tokens ( 0.33 ms per token, 3001.88 tokens per second) 3.30.199.081 I slot print_timing: id 0 | task 31419 | eval time = 620.81 ms / 114 tokens ( 5.49 ms per token, 182.02 tokens per second) 3.30.199.082 I slot print_timing: id 0 | task 31419 | total time = 735.73 ms / 459 tokens 3.30.199.083 I slot print_timing: id 0 | task 31419 | graphs reused = 30481 3.30.199.084 I slot print_timing: id 0 | task 31419 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.199.112 I slot release: id 0 | task 31419 | stop processing: n_tokens = 490, truncated = 0 3.30.216.320 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 210098944 3.30.216.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.061 MiB) 3.30.293.255 I slot launch_slot_: id 0 | task 31536 | processing task, is_child = 0 3.30.945.464 I slot print_timing: id 0 | task 31536 | prompt eval time = 120.16 ms / 320 tokens ( 0.38 ms per token, 2663.12 tokens per second) 3.30.945.470 I slot print_timing: id 0 | task 31536 | eval time = 532.03 ms / 98 tokens ( 5.48 ms per token, 182.32 tokens per second) 3.30.945.471 I slot print_timing: id 0 | task 31536 | total time = 652.19 ms / 418 tokens 3.30.945.472 I slot print_timing: id 0 | task 31536 | graphs reused = 30577 3.30.945.472 I slot print_timing: id 0 | task 31536 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.945.500 I slot release: id 0 | task 31536 | stop processing: n_tokens = 449, truncated = 0 3.30.969.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 210845332 3.30.969.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.961 MiB) 3.31.040.392 I slot launch_slot_: id 0 | task 31637 | processing task, is_child = 0 3.31.432.879 I slot print_timing: id 0 | task 31637 | prompt eval time = 109.08 ms / 297 tokens ( 0.37 ms per token, 2722.75 tokens per second) 3.31.432.885 I slot print_timing: id 0 | task 31637 | eval time = 283.39 ms / 47 tokens ( 6.16 ms per token, 162.32 tokens per second) 3.31.432.886 I slot print_timing: id 0 | task 31637 | total time = 392.47 ms / 344 tokens 3.31.432.887 I slot print_timing: id 0 | task 31637 | graphs reused = 30622 3.31.432.887 I slot print_timing: id 0 | task 31637 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.432.913 I slot release: id 0 | task 31637 | stop processing: n_tokens = 375, truncated = 0 3.31.453.526 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 211332745 3.31.453.568 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.310 MiB) 3.31.529.257 I slot launch_slot_: id 0 | task 31687 | processing task, is_child = 0 3.32.588.865 I slot print_timing: id 0 | task 31687 | prompt eval time = 114.67 ms / 343 tokens ( 0.33 ms per token, 2991.06 tokens per second) 3.32.588.871 I slot print_timing: id 0 | task 31687 | eval time = 944.91 ms / 173 tokens ( 5.49 ms per token, 182.03 tokens per second) 3.32.588.872 I slot print_timing: id 0 | task 31687 | total time = 1059.59 ms / 516 tokens 3.32.588.873 I slot print_timing: id 0 | task 31687 | graphs reused = 30792 3.32.588.874 I slot print_timing: id 0 | task 31687 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.588.900 I slot release: id 0 | task 31687 | stop processing: n_tokens = 547, truncated = 0 3.32.616.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 212488733 3.32.616.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.053 MiB) 3.32.683.638 I slot launch_slot_: id 0 | task 31863 | processing task, is_child = 0 3.33.603.331 I slot print_timing: id 0 | task 31863 | prompt eval time = 121.51 ms / 371 tokens ( 0.33 ms per token, 3053.22 tokens per second) 3.33.603.337 I slot print_timing: id 0 | task 31863 | eval time = 798.16 ms / 146 tokens ( 5.50 ms per token, 181.67 tokens per second) 3.33.603.338 I slot print_timing: id 0 | task 31863 | total time = 919.68 ms / 517 tokens 3.33.603.338 I slot print_timing: id 0 | task 31863 | graphs reused = 30935 3.33.603.339 I slot print_timing: id 0 | task 31863 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.603.366 I slot release: id 0 | task 31863 | stop processing: n_tokens = 548, truncated = 0 3.33.618.499 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 548, t_last = 213503199 3.33.618.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.995 MiB) 3.33.687.829 I slot launch_slot_: id 0 | task 32012 | processing task, is_child = 0 3.34.552.518 I slot print_timing: id 0 | task 32012 | prompt eval time = 109.41 ms / 292 tokens ( 0.37 ms per token, 2668.93 tokens per second) 3.34.552.524 I slot print_timing: id 0 | task 32012 | eval time = 755.26 ms / 139 tokens ( 5.47 ms per token, 182.72 tokens per second) 3.34.552.525 I slot print_timing: id 0 | task 32012 | total time = 864.67 ms / 431 tokens 3.34.552.526 I slot print_timing: id 0 | task 32012 | graphs reused = 31072 3.34.552.527 I slot print_timing: id 0 | task 32012 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.552.554 I slot release: id 0 | task 32012 | stop processing: n_tokens = 462, truncated = 0 3.34.570.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 214452386 3.34.613.342 I slot launch_slot_: id 0 | task 32154 | processing task, is_child = 0 3.35.526.021 I slot print_timing: id 0 | task 32154 | prompt eval time = 109.47 ms / 301 tokens ( 0.36 ms per token, 2749.66 tokens per second) 3.35.526.027 I slot print_timing: id 0 | task 32154 | eval time = 803.19 ms / 148 tokens ( 5.46 ms per token, 183.02 tokens per second) 3.35.526.028 I slot print_timing: id 0 | task 32154 | total time = 912.66 ms / 449 tokens 3.35.526.029 I slot print_timing: id 0 | task 32154 | graphs reused = 31218 3.35.526.029 I slot print_timing: id 0 | task 32154 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.526.054 I slot release: id 0 | task 32154 | stop processing: n_tokens = 480, truncated = 0 3.35.551.308 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 480, t_last = 215425886 3.35.551.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 393.003 MiB) 3.35.622.395 I slot launch_slot_: id 0 | task 32305 | processing task, is_child = 0 3.36.443.721 I slot print_timing: id 0 | task 32305 | prompt eval time = 109.73 ms / 303 tokens ( 0.36 ms per token, 2761.25 tokens per second) 3.36.443.727 I slot print_timing: id 0 | task 32305 | eval time = 711.58 ms / 131 tokens ( 5.47 ms per token, 182.69 tokens per second) 3.36.443.728 I slot print_timing: id 0 | task 32305 | total time = 821.31 ms / 434 tokens 3.36.443.730 I slot print_timing: id 0 | task 32305 | graphs reused = 31347 3.36.443.731 I slot print_timing: id 0 | task 32305 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.443.756 I slot release: id 0 | task 32305 | stop processing: n_tokens = 465, truncated = 0 3.36.458.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 216343588 3.36.458.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 392.972 MiB) 3.36.528.178 I slot launch_slot_: id 0 | task 32439 | processing task, is_child = 0 3.36.984.078 I slot print_timing: id 0 | task 32439 | prompt eval time = 114.03 ms / 321 tokens ( 0.36 ms per token, 2815.05 tokens per second) 3.36.984.084 I slot print_timing: id 0 | task 32439 | eval time = 341.85 ms / 63 tokens ( 5.51 ms per token, 181.37 tokens per second) 3.36.984.085 I slot print_timing: id 0 | task 32439 | total time = 455.88 ms / 384 tokens 3.36.984.085 I slot print_timing: id 0 | task 32439 | graphs reused = 31408 3.36.984.087 I slot print_timing: id 0 | task 32439 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.984.114 I slot release: id 0 | task 32439 | stop processing: n_tokens = 415, truncated = 0 3.37.004.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 216883946 3.37.004.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.644 MiB) 3.37.070.789 I slot launch_slot_: id 0 | task 32505 | processing task, is_child = 0 3.37.587.848 I slot print_timing: id 0 | task 32505 | prompt eval time = 115.44 ms / 322 tokens ( 0.36 ms per token, 2789.38 tokens per second) 3.37.587.854 I slot print_timing: id 0 | task 32505 | eval time = 401.60 ms / 74 tokens ( 5.50 ms per token, 181.77 tokens per second) 3.37.587.855 I slot print_timing: id 0 | task 32505 | total time = 517.04 ms / 396 tokens 3.37.587.856 I slot print_timing: id 0 | task 32505 | graphs reused = 31480 3.37.587.856 I slot print_timing: id 0 | task 32505 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.587.885 I slot release: id 0 | task 32505 | stop processing: n_tokens = 427, truncated = 0 3.37.612.600 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 217487717 3.37.612.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.608 MiB) 3.37.678.010 I slot launch_slot_: id 0 | task 32582 | processing task, is_child = 0 3.38.706.296 I slot print_timing: id 0 | task 32582 | prompt eval time = 114.68 ms / 323 tokens ( 0.36 ms per token, 2816.53 tokens per second) 3.38.706.302 I slot print_timing: id 0 | task 32582 | eval time = 913.59 ms / 167 tokens ( 5.50 ms per token, 181.70 tokens per second) 3.38.706.303 I slot print_timing: id 0 | task 32582 | total time = 1028.27 ms / 490 tokens 3.38.706.303 I slot print_timing: id 0 | task 32582 | graphs reused = 31644 3.38.706.304 I slot print_timing: id 0 | task 32582 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.706.329 I slot release: id 0 | task 32582 | stop processing: n_tokens = 521, truncated = 0 3.38.733.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 521, t_last = 218606162 3.38.733.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.583 MiB) 3.38.799.523 I slot launch_slot_: id 0 | task 32752 | processing task, is_child = 0 3.41.915.499 I slot print_timing: id 0 | task 32752 | n_gen = 549, tg = 182.55 t/s, tg_3s = 182.88 t/s 3.43.614.238 I slot print_timing: id 0 | task 32752 | prompt eval time = 114.04 ms / 321 tokens ( 0.36 ms per token, 2814.73 tokens per second) 3.43.614.245 I slot print_timing: id 0 | task 32752 | eval time = 4700.66 ms / 858 tokens ( 5.49 ms per token, 182.31 tokens per second) 3.43.614.246 I slot print_timing: id 0 | task 32752 | total time = 4814.70 ms / 1179 tokens 3.43.614.247 I slot print_timing: id 0 | task 32752 | graphs reused = 32497 3.43.614.247 I slot print_timing: id 0 | task 32752 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.614.276 I slot release: id 0 | task 32752 | stop processing: n_tokens = 1210, truncated = 0 3.43.630.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1210, t_last = 223514108 3.43.630.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.201 MiB) 3.43.701.657 I slot launch_slot_: id 0 | task 33613 | processing task, is_child = 0 3.44.017.790 I slot print_timing: id 0 | task 33613 | prompt eval time = 114.28 ms / 322 tokens ( 0.35 ms per token, 2817.71 tokens per second) 3.44.017.795 I slot print_timing: id 0 | task 33613 | eval time = 201.84 ms / 37 tokens ( 5.61 ms per token, 178.36 tokens per second) 3.44.017.797 I slot print_timing: id 0 | task 33613 | total time = 316.12 ms / 359 tokens 3.44.017.797 I slot print_timing: id 0 | task 33613 | graphs reused = 32532 3.44.017.798 I slot print_timing: id 0 | task 33613 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.017.826 I slot release: id 0 | task 33613 | stop processing: n_tokens = 390, truncated = 0 3.44.033.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 223917658 3.44.033.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 334.027 MiB) 3.44.099.569 I slot launch_slot_: id 0 | task 33653 | processing task, is_child = 0 3.45.363.683 I slot print_timing: id 0 | task 33653 | prompt eval time = 115.99 ms / 337 tokens ( 0.34 ms per token, 2905.40 tokens per second) 3.45.363.689 I slot print_timing: id 0 | task 33653 | eval time = 1148.10 ms / 210 tokens ( 5.49 ms per token, 182.04 tokens per second) 3.45.363.690 I slot print_timing: id 0 | task 33653 | total time = 1264.10 ms / 547 tokens 3.45.363.690 I slot print_timing: id 0 | task 33653 | graphs reused = 32739 3.45.363.691 I slot print_timing: id 0 | task 33653 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.363.720 I slot release: id 0 | task 33653 | stop processing: n_tokens = 578, truncated = 0 3.45.388.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 578, t_last = 225263553 3.45.388.156 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 3.45.458.011 I slot launch_slot_: id 0 | task 33866 | processing task, is_child = 0 3.46.208.126 I slot print_timing: id 0 | task 33866 | prompt eval time = 114.66 ms / 325 tokens ( 0.35 ms per token, 2834.49 tokens per second) 3.46.208.131 I slot print_timing: id 0 | task 33866 | eval time = 635.43 ms / 117 tokens ( 5.48 ms per token, 182.55 tokens per second) 3.46.208.132 I slot print_timing: id 0 | task 33866 | total time = 750.09 ms / 442 tokens 3.46.208.133 I slot print_timing: id 0 | task 33866 | graphs reused = 32854 3.46.208.134 I slot print_timing: id 0 | task 33866 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.208.163 I slot release: id 0 | task 33866 | stop processing: n_tokens = 473, truncated = 0 3.46.230.522 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 473, t_last = 226107995 3.46.230.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.110 MiB) 3.46.298.939 I slot launch_slot_: id 0 | task 33986 | processing task, is_child = 0 3.46.783.696 I slot print_timing: id 0 | task 33986 | prompt eval time = 115.13 ms / 331 tokens ( 0.35 ms per token, 2874.99 tokens per second) 3.46.783.702 I slot print_timing: id 0 | task 33986 | eval time = 369.61 ms / 68 tokens ( 5.52 ms per token, 181.27 tokens per second) 3.46.783.703 I slot print_timing: id 0 | task 33986 | total time = 484.74 ms / 399 tokens 3.46.783.704 I slot print_timing: id 0 | task 33986 | graphs reused = 32920 3.46.783.705 I slot print_timing: id 0 | task 33986 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.783.731 I slot release: id 0 | task 33986 | stop processing: n_tokens = 430, truncated = 0 3.46.804.629 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 226683563 3.46.804.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.264 MiB) 3.46.869.801 I slot launch_slot_: id 0 | task 34057 | processing task, is_child = 0 3.47.254.833 I slot print_timing: id 0 | task 34057 | prompt eval time = 114.13 ms / 336 tokens ( 0.34 ms per token, 2944.04 tokens per second) 3.47.254.839 I slot print_timing: id 0 | task 34057 | eval time = 270.88 ms / 50 tokens ( 5.53 ms per token, 180.89 tokens per second) 3.47.254.840 I slot print_timing: id 0 | task 34057 | total time = 385.01 ms / 386 tokens 3.47.254.840 I slot print_timing: id 0 | task 34057 | graphs reused = 32968 3.47.254.841 I slot print_timing: id 0 | task 34057 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.254.879 I slot release: id 0 | task 34057 | stop processing: n_tokens = 417, truncated = 0 3.47.271.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 227154711 3.47.271.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.575 MiB) 3.47.338.954 I slot launch_slot_: id 0 | task 34110 | processing task, is_child = 0 3.47.845.385 I slot print_timing: id 0 | task 34110 | prompt eval time = 115.78 ms / 349 tokens ( 0.33 ms per token, 3014.31 tokens per second) 3.47.845.390 I slot print_timing: id 0 | task 34110 | eval time = 390.63 ms / 72 tokens ( 5.50 ms per token, 181.76 tokens per second) 3.47.845.391 I slot print_timing: id 0 | task 34110 | total time = 506.41 ms / 421 tokens 3.47.845.392 I slot print_timing: id 0 | task 34110 | graphs reused = 33038 3.47.845.393 I slot print_timing: id 0 | task 34110 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.845.420 I slot release: id 0 | task 34110 | stop processing: n_tokens = 452, truncated = 0 3.47.860.520 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 227745252 3.47.860.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.043 MiB) 3.47.925.828 I slot launch_slot_: id 0 | task 34185 | processing task, is_child = 0 3.51.041.598 I slot print_timing: id 0 | task 34185 | n_gen = 549, tg = 182.57 t/s, tg_3s = 182.90 t/s 3.53.656.706 I slot print_timing: id 0 | task 34185 | prompt eval time = 114.17 ms / 336 tokens ( 0.34 ms per token, 2942.93 tokens per second) 3.53.656.712 I slot print_timing: id 0 | task 34185 | eval time = 5616.69 ms / 1024 tokens ( 5.49 ms per token, 182.14 tokens per second) 3.53.656.713 I slot print_timing: id 0 | task 34185 | total time = 5730.86 ms / 1360 tokens 3.53.656.713 I slot print_timing: id 0 | task 34185 | graphs reused = 34056 3.53.656.714 I slot print_timing: id 0 | task 34185 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.656.745 I slot release: id 0 | task 34185 | stop processing: n_tokens = 1391, truncated = 0 3.53.678.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1391, t_last = 233556577 3.53.678.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 3.53.750.260 I slot launch_slot_: id 0 | task 35212 | processing task, is_child = 0 3.56.867.527 I slot print_timing: id 0 | task 35212 | n_gen = 545, tg = 181.19 t/s, tg_3s = 181.52 t/s 3.57.912.247 I slot print_timing: id 0 | task 35212 | prompt eval time = 114.82 ms / 349 tokens ( 0.33 ms per token, 3039.62 tokens per second) 3.57.912.253 I slot print_timing: id 0 | task 35212 | eval time = 4047.15 ms / 734 tokens ( 5.52 ms per token, 181.12 tokens per second) 3.57.912.255 I slot print_timing: id 0 | task 35212 | total time = 4161.97 ms / 1083 tokens 3.57.912.256 I slot print_timing: id 0 | task 35212 | graphs reused = 34785 3.57.912.257 I slot print_timing: id 0 | task 35212 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.912.290 I slot release: id 0 | task 35212 | stop processing: n_tokens = 1114, truncated = 0 3.57.930.628 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1114, t_last = 237812122 3.57.930.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.710 MiB) 3.58.001.098 I slot launch_slot_: id 0 | task 35949 | processing task, is_child = 0 3.58.842.345 I slot print_timing: id 0 | task 35949 | prompt eval time = 114.67 ms / 349 tokens ( 0.33 ms per token, 3043.62 tokens per second) 3.58.842.351 I slot print_timing: id 0 | task 35949 | eval time = 726.56 ms / 133 tokens ( 5.50 ms per token, 181.68 tokens per second) 3.58.842.352 I slot print_timing: id 0 | task 35949 | total time = 841.23 ms / 482 tokens 3.58.842.353 I slot print_timing: id 0 | task 35949 | graphs reused = 34915 3.58.842.354 I slot print_timing: id 0 | task 35949 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.842.382 I slot release: id 0 | task 35949 | stop processing: n_tokens = 513, truncated = 0 3.58.858.746 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 238742214 3.58.858.793 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.703 MiB) 3.58.930.712 I slot launch_slot_: id 0 | task 36085 | processing task, is_child = 0 3.59.567.894 I slot print_timing: id 0 | task 36085 | prompt eval time = 121.39 ms / 385 tokens ( 0.32 ms per token, 3171.65 tokens per second) 3.59.567.899 I slot print_timing: id 0 | task 36085 | eval time = 515.78 ms / 95 tokens ( 5.49 ms per token, 182.25 tokens per second) 3.59.567.900 I slot print_timing: id 0 | task 36085 | total time = 637.16 ms / 480 tokens 3.59.567.901 I slot print_timing: id 0 | task 36085 | graphs reused = 35008 3.59.567.902 I slot print_timing: id 0 | task 36085 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.567.932 I slot release: id 0 | task 36085 | stop processing: n_tokens = 511, truncated = 0 3.59.571.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 239467765 3.59.571.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.704 MiB) 3.59.641.739 I slot launch_slot_: id 0 | task 36183 | processing task, is_child = 0 4.00.066.620 I slot print_timing: id 0 | task 36183 | prompt eval time = 114.37 ms / 328 tokens ( 0.35 ms per token, 2867.94 tokens per second) 4.00.066.626 I slot print_timing: id 0 | task 36183 | eval time = 310.49 ms / 57 tokens ( 5.54 ms per token, 180.36 tokens per second) 4.00.066.627 I slot print_timing: id 0 | task 36183 | total time = 424.86 ms / 385 tokens 4.00.066.628 I slot print_timing: id 0 | task 36183 | graphs reused = 35063 4.00.066.628 I slot print_timing: id 0 | task 36183 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.066.655 I slot release: id 0 | task 36183 | stop processing: n_tokens = 416, truncated = 0