$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\dl\campaign\70c112196e0b\Ornith-1.5-9B-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.106.646 I srv llama_server: initializing ... 0.00.106.659 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.106.849 I srv init_listene: The UI is disabled 0.00.106.854 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.106.981 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) 0.00.124.590 I srv load_model: loading model 'C:\quantdiff\dl\campaign\70c112196e0b\Ornith-1.5-9B-Q4_K_M.gguf' 0.01.004.458 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.01.004.473 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.01.004.498 W model has unused tensor blk.32.attn_q.weight (size = 18874368 bytes) -- ignoring 0.01.004.507 W model has unused tensor blk.32.attn_k.weight (size = 2359296 bytes) -- ignoring 0.01.004.516 W model has unused tensor blk.32.attn_v.weight (size = 3440640 bytes) -- ignoring 0.01.004.549 W model has unused tensor blk.32.attn_output.weight (size = 9437184 bytes) -- ignoring 0.01.004.560 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.01.004.569 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.01.004.578 W model has unused tensor blk.32.ffn_gate.weight (size = 28311552 bytes) -- ignoring 0.01.004.586 W model has unused tensor blk.32.ffn_down.weight (size = 41287680 bytes) -- ignoring 0.01.004.595 W model has unused tensor blk.32.ffn_up.weight (size = 28311552 bytes) -- ignoring 0.01.004.605 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 18874368 bytes) -- ignoring 0.01.004.615 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.01.004.624 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.01.004.653 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.02.809.474 I cmn init: llama threadpool init, n_threads = 8 0.02.909.154 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.922.414 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.923.639 I srv llama_server: model loaded 0.02.923.760 I srv llama_server: listening on http://127.0.0.1:8089 0.04.660.500 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.661.375 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.599.814 I slot print_timing: id 0 | task 0 | prompt eval time = 144.22 ms / 368 tokens ( 0.39 ms per token, 2551.71 tokens per second) 0.05.599.820 I slot print_timing: id 0 | task 0 | eval time = 794.21 ms / 77 tokens ( 10.45 ms per token, 95.69 tokens per second) 0.05.599.821 I slot print_timing: id 0 | task 0 | total time = 938.42 ms / 445 tokens 0.05.599.828 I slot print_timing: id 0 | task 0 | graphs reused = 76 0.05.599.828 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.599.870 I slot release: id 0 | task 0 | stop processing: n_tokens = 444, truncated = 0 0.05.623.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 5495667 0.05.648.498 I slot launch_slot_: id 0 | task 80 | processing task, is_child = 0 0.06.375.463 I slot print_timing: id 0 | task 80 | prompt eval time = 121.70 ms / 322 tokens ( 0.38 ms per token, 2645.81 tokens per second) 0.06.375.469 I slot print_timing: id 0 | task 80 | eval time = 605.24 ms / 59 tokens ( 10.44 ms per token, 95.83 tokens per second) 0.06.375.470 I slot print_timing: id 0 | task 80 | total time = 726.95 ms / 381 tokens 0.06.375.471 I slot print_timing: id 0 | task 80 | graphs reused = 133 0.06.375.472 I slot print_timing: id 0 | task 80 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.375.498 I slot release: id 0 | task 80 | stop processing: n_tokens = 380, truncated = 0 0.06.418.708 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 380, t_last = 6271296 0.06.442.629 I slot launch_slot_: id 0 | task 142 | processing task, is_child = 0 0.07.187.414 I slot print_timing: id 0 | task 142 | prompt eval time = 124.47 ms / 365 tokens ( 0.34 ms per token, 2932.43 tokens per second) 0.07.187.420 I slot print_timing: id 0 | task 142 | eval time = 620.29 ms / 60 tokens ( 10.51 ms per token, 95.12 tokens per second) 0.07.187.421 I slot print_timing: id 0 | task 142 | total time = 744.76 ms / 425 tokens 0.07.187.421 I slot print_timing: id 0 | task 142 | graphs reused = 191 0.07.187.422 I slot print_timing: id 0 | task 142 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.187.451 I slot release: id 0 | task 142 | stop processing: n_tokens = 424, truncated = 0 0.07.214.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 7083249 0.07.240.136 I slot launch_slot_: id 0 | task 205 | processing task, is_child = 0 0.07.800.534 I slot print_timing: id 0 | task 205 | prompt eval time = 130.25 ms / 397 tokens ( 0.33 ms per token, 3048.05 tokens per second) 0.07.800.541 I slot print_timing: id 0 | task 205 | eval time = 430.13 ms / 43 tokens ( 10.24 ms per token, 97.64 tokens per second) 0.07.800.542 I slot print_timing: id 0 | task 205 | total time = 560.38 ms / 440 tokens 0.07.800.543 I slot print_timing: id 0 | task 205 | graphs reused = 232 0.07.800.544 I slot print_timing: id 0 | task 205 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.800.576 I slot release: id 0 | task 205 | stop processing: n_tokens = 439, truncated = 0 0.07.837.331 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.07.861.284 I slot launch_slot_: id 0 | task 251 | processing task, is_child = 0 0.08.684.129 I slot print_timing: id 0 | task 251 | prompt eval time = 123.48 ms / 383 tokens ( 0.32 ms per token, 3101.59 tokens per second) 0.08.684.135 I slot print_timing: id 0 | task 251 | eval time = 699.34 ms / 70 tokens ( 10.14 ms per token, 98.66 tokens per second) 0.08.684.136 I slot print_timing: id 0 | task 251 | total time = 822.83 ms / 453 tokens 0.08.684.137 I slot print_timing: id 0 | task 251 | graphs reused = 300 0.08.684.138 I slot print_timing: id 0 | task 251 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.684.167 I slot release: id 0 | task 251 | stop processing: n_tokens = 452, truncated = 0 0.08.712.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 452, t_last = 8579964 0.08.737.019 I slot launch_slot_: id 0 | task 324 | processing task, is_child = 0 0.09.568.460 I slot print_timing: id 0 | task 324 | prompt eval time = 124.85 ms / 372 tokens ( 0.34 ms per token, 2979.65 tokens per second) 0.09.568.465 I slot print_timing: id 0 | task 324 | eval time = 706.58 ms / 69 tokens ( 10.39 ms per token, 96.24 tokens per second) 0.09.568.466 I slot print_timing: id 0 | task 324 | total time = 831.42 ms / 441 tokens 0.09.568.468 I slot print_timing: id 0 | task 324 | graphs reused = 367 0.09.568.469 I slot print_timing: id 0 | task 324 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.568.497 I slot release: id 0 | task 324 | stop processing: n_tokens = 440, truncated = 0 0.09.583.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 9464294 0.09.608.287 I slot launch_slot_: id 0 | task 396 | processing task, is_child = 0 0.10.467.955 I slot print_timing: id 0 | task 396 | prompt eval time = 145.08 ms / 422 tokens ( 0.34 ms per token, 2908.74 tokens per second) 0.10.467.961 I slot print_timing: id 0 | task 396 | eval time = 714.57 ms / 69 tokens ( 10.51 ms per token, 95.16 tokens per second) 0.10.467.962 I slot print_timing: id 0 | task 396 | total time = 859.65 ms / 491 tokens 0.10.467.963 I slot print_timing: id 0 | task 396 | graphs reused = 434 0.10.467.964 I slot print_timing: id 0 | task 396 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.467.996 I slot release: id 0 | task 396 | stop processing: n_tokens = 490, truncated = 0 0.10.498.123 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 490, t_last = 10363794 0.10.522.946 I slot launch_slot_: id 0 | task 468 | processing task, is_child = 0 0.11.583.826 I slot print_timing: id 0 | task 468 | prompt eval time = 150.91 ms / 470 tokens ( 0.32 ms per token, 3114.44 tokens per second) 0.11.583.831 I slot print_timing: id 0 | task 468 | eval time = 909.95 ms / 88 tokens ( 10.46 ms per token, 95.61 tokens per second) 0.11.583.832 I slot print_timing: id 0 | task 468 | total time = 1060.86 ms / 558 tokens 0.11.583.833 I slot print_timing: id 0 | task 468 | graphs reused = 519 0.11.583.833 I slot print_timing: id 0 | task 468 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.583.866 I slot release: id 0 | task 468 | stop processing: n_tokens = 557, truncated = 0 0.11.621.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 11479663 0.11.646.585 I slot launch_slot_: id 0 | task 559 | processing task, is_child = 0 0.12.234.484 I slot print_timing: id 0 | task 559 | prompt eval time = 118.99 ms / 345 tokens ( 0.34 ms per token, 2899.38 tokens per second) 0.12.234.490 I slot print_timing: id 0 | task 559 | eval time = 468.89 ms / 47 tokens ( 10.19 ms per token, 98.10 tokens per second) 0.12.234.491 I slot print_timing: id 0 | task 559 | total time = 587.88 ms / 392 tokens 0.12.234.492 I slot print_timing: id 0 | task 559 | graphs reused = 564 0.12.234.493 I slot print_timing: id 0 | task 559 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.234.520 I slot release: id 0 | task 559 | stop processing: n_tokens = 391, truncated = 0 0.12.261.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 12130317 0.12.285.849 I slot launch_slot_: id 0 | task 609 | processing task, is_child = 0 0.12.932.731 I slot print_timing: id 0 | task 609 | prompt eval time = 122.00 ms / 364 tokens ( 0.34 ms per token, 2983.58 tokens per second) 0.12.932.737 I slot print_timing: id 0 | task 609 | eval time = 524.87 ms / 53 tokens ( 10.09 ms per token, 99.07 tokens per second) 0.12.932.738 I slot print_timing: id 0 | task 609 | total time = 646.87 ms / 417 tokens 0.12.932.739 I slot print_timing: id 0 | task 609 | graphs reused = 615 0.12.932.740 I slot print_timing: id 0 | task 609 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.932.768 I slot release: id 0 | task 609 | stop processing: n_tokens = 416, truncated = 0 0.12.949.741 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 12828566 0.12.974.430 I slot launch_slot_: id 0 | task 665 | processing task, is_child = 0 0.13.739.371 I slot print_timing: id 0 | task 665 | prompt eval time = 130.26 ms / 376 tokens ( 0.35 ms per token, 2886.53 tokens per second) 0.13.739.376 I slot print_timing: id 0 | task 665 | eval time = 634.66 ms / 62 tokens ( 10.40 ms per token, 96.11 tokens per second) 0.13.739.377 I slot print_timing: id 0 | task 665 | total time = 764.92 ms / 438 tokens 0.13.739.378 I slot print_timing: id 0 | task 665 | graphs reused = 675 0.13.739.379 I slot print_timing: id 0 | task 665 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.739.408 I slot release: id 0 | task 665 | stop processing: n_tokens = 437, truncated = 0 0.13.744.772 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 13635205 0.13.769.239 I slot launch_slot_: id 0 | task 730 | processing task, is_child = 0 0.14.386.266 I slot print_timing: id 0 | task 730 | prompt eval time = 132.05 ms / 412 tokens ( 0.32 ms per token, 3120.10 tokens per second) 0.14.386.271 I slot print_timing: id 0 | task 730 | eval time = 484.96 ms / 47 tokens ( 10.54 ms per token, 94.85 tokens per second) 0.14.386.273 I slot print_timing: id 0 | task 730 | total time = 617.00 ms / 459 tokens 0.14.386.273 I slot print_timing: id 0 | task 730 | graphs reused = 720 0.14.386.274 I slot print_timing: id 0 | task 730 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.386.308 I slot release: id 0 | task 730 | stop processing: n_tokens = 458, truncated = 0 0.14.431.516 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 14282105 0.14.457.802 I slot launch_slot_: id 0 | task 780 | processing task, is_child = 0 0.15.225.523 I slot print_timing: id 0 | task 780 | prompt eval time = 127.95 ms / 376 tokens ( 0.34 ms per token, 2938.60 tokens per second) 0.15.225.529 I slot print_timing: id 0 | task 780 | eval time = 639.75 ms / 62 tokens ( 10.49 ms per token, 95.35 tokens per second) 0.15.225.530 I slot print_timing: id 0 | task 780 | total time = 767.70 ms / 438 tokens 0.15.225.531 I slot print_timing: id 0 | task 780 | graphs reused = 780 0.15.225.531 I slot print_timing: id 0 | task 780 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.225.560 I slot release: id 0 | task 780 | stop processing: n_tokens = 437, truncated = 0 0.15.244.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 15121357 0.15.268.729 I slot launch_slot_: id 0 | task 845 | processing task, is_child = 0 0.15.919.656 I slot print_timing: id 0 | task 845 | prompt eval time = 129.93 ms / 378 tokens ( 0.34 ms per token, 2909.37 tokens per second) 0.15.919.661 I slot print_timing: id 0 | task 845 | eval time = 520.99 ms / 52 tokens ( 10.22 ms per token, 97.89 tokens per second) 0.15.919.662 I slot print_timing: id 0 | task 845 | total time = 650.91 ms / 430 tokens 0.15.919.663 I slot print_timing: id 0 | task 845 | graphs reused = 830 0.15.919.664 I slot print_timing: id 0 | task 845 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.919.691 I slot release: id 0 | task 845 | stop processing: n_tokens = 429, truncated = 0 0.15.944.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 15815489 0.15.968.481 I slot launch_slot_: id 0 | task 900 | processing task, is_child = 0 0.16.671.019 I slot print_timing: id 0 | task 900 | prompt eval time = 126.42 ms / 367 tokens ( 0.34 ms per token, 2903.14 tokens per second) 0.16.671.025 I slot print_timing: id 0 | task 900 | eval time = 576.11 ms / 58 tokens ( 10.11 ms per token, 98.94 tokens per second) 0.16.671.026 I slot print_timing: id 0 | task 900 | total time = 702.52 ms / 425 tokens 0.16.671.027 I slot print_timing: id 0 | task 900 | graphs reused = 886 0.16.671.028 I slot print_timing: id 0 | task 900 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.671.056 I slot release: id 0 | task 900 | stop processing: n_tokens = 424, truncated = 0 0.16.675.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 16566854 0.16.699.878 I slot launch_slot_: id 0 | task 961 | processing task, is_child = 0 0.17.337.940 I slot print_timing: id 0 | task 961 | prompt eval time = 123.35 ms / 347 tokens ( 0.36 ms per token, 2813.16 tokens per second) 0.17.337.945 I slot print_timing: id 0 | task 961 | eval time = 514.69 ms / 51 tokens ( 10.29 ms per token, 97.15 tokens per second) 0.17.337.946 I slot print_timing: id 0 | task 961 | total time = 638.04 ms / 398 tokens 0.17.337.947 I slot print_timing: id 0 | task 961 | graphs reused = 935 0.17.337.948 I slot print_timing: id 0 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.337.976 I slot release: id 0 | task 961 | stop processing: n_tokens = 397, truncated = 0 0.17.373.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 17233774 0.17.398.469 I slot launch_slot_: id 0 | task 1015 | processing task, is_child = 0 0.17.943.551 I slot print_timing: id 0 | task 1015 | prompt eval time = 123.57 ms / 369 tokens ( 0.33 ms per token, 2986.16 tokens per second) 0.17.943.557 I slot print_timing: id 0 | task 1015 | eval time = 421.49 ms / 41 tokens ( 10.54 ms per token, 94.90 tokens per second) 0.17.943.558 I slot print_timing: id 0 | task 1015 | total time = 545.06 ms / 410 tokens 0.17.943.559 I slot print_timing: id 0 | task 1015 | graphs reused = 974 0.17.943.560 I slot print_timing: id 0 | task 1015 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.943.588 I slot release: id 0 | task 1015 | stop processing: n_tokens = 409, truncated = 0 0.17.978.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 17839385 0.18.002.904 I slot launch_slot_: id 0 | task 1059 | processing task, is_child = 0 0.18.548.898 I slot print_timing: id 0 | task 1059 | prompt eval time = 122.87 ms / 352 tokens ( 0.35 ms per token, 2864.91 tokens per second) 0.18.548.904 I slot print_timing: id 0 | task 1059 | eval time = 423.11 ms / 41 tokens ( 10.58 ms per token, 94.54 tokens per second) 0.18.548.905 I slot print_timing: id 0 | task 1059 | total time = 545.98 ms / 393 tokens 0.18.548.906 I slot print_timing: id 0 | task 1059 | graphs reused = 1013 0.18.548.908 I slot print_timing: id 0 | task 1059 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.548.937 I slot release: id 0 | task 1059 | stop processing: n_tokens = 392, truncated = 0 0.18.569.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 18444734 0.18.593.230 I slot launch_slot_: id 0 | task 1103 | processing task, is_child = 0 0.19.276.195 I slot print_timing: id 0 | task 1103 | prompt eval time = 122.76 ms / 349 tokens ( 0.35 ms per token, 2842.90 tokens per second) 0.19.276.201 I slot print_timing: id 0 | task 1103 | eval time = 560.18 ms / 54 tokens ( 10.57 ms per token, 94.61 tokens per second) 0.19.276.202 I slot print_timing: id 0 | task 1103 | total time = 682.94 ms / 403 tokens 0.19.276.203 I slot print_timing: id 0 | task 1103 | graphs reused = 1065 0.19.276.203 I slot print_timing: id 0 | task 1103 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.276.230 I slot release: id 0 | task 1103 | stop processing: n_tokens = 402, truncated = 0 0.19.316.314 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 19172028 0.19.340.356 I slot launch_slot_: id 0 | task 1160 | processing task, is_child = 0 0.20.325.322 I slot print_timing: id 0 | task 1160 | prompt eval time = 132.88 ms / 384 tokens ( 0.35 ms per token, 2889.85 tokens per second) 0.20.325.328 I slot print_timing: id 0 | task 1160 | eval time = 852.07 ms / 85 tokens ( 10.14 ms per token, 98.58 tokens per second) 0.20.325.329 I slot print_timing: id 0 | task 1160 | total time = 984.95 ms / 469 tokens 0.20.325.329 I slot print_timing: id 0 | task 1160 | graphs reused = 1148 0.20.325.330 I slot print_timing: id 0 | task 1160 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.325.359 I slot release: id 0 | task 1160 | stop processing: n_tokens = 468, truncated = 0 0.20.344.837 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 468, t_last = 20221157 0.20.369.155 I slot launch_slot_: id 0 | task 1248 | processing task, is_child = 0 0.21.188.611 I slot print_timing: id 0 | task 1248 | prompt eval time = 120.00 ms / 356 tokens ( 0.34 ms per token, 2966.72 tokens per second) 0.21.188.617 I slot print_timing: id 0 | task 1248 | eval time = 699.44 ms / 70 tokens ( 10.14 ms per token, 98.65 tokens per second) 0.21.188.618 I slot print_timing: id 0 | task 1248 | total time = 819.44 ms / 426 tokens 0.21.188.619 I slot print_timing: id 0 | task 1248 | graphs reused = 1216 0.21.188.620 I slot print_timing: id 0 | task 1248 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.188.649 I slot release: id 0 | task 1248 | stop processing: n_tokens = 425, truncated = 0 0.21.217.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 21084447 0.21.241.941 I slot launch_slot_: id 0 | task 1321 | processing task, is_child = 0 0.22.096.912 I slot print_timing: id 0 | task 1321 | prompt eval time = 133.09 ms / 410 tokens ( 0.32 ms per token, 3080.55 tokens per second) 0.22.096.917 I slot print_timing: id 0 | task 1321 | eval time = 721.86 ms / 70 tokens ( 10.46 ms per token, 95.59 tokens per second) 0.22.096.918 I slot print_timing: id 0 | task 1321 | total time = 854.95 ms / 480 tokens 0.22.096.919 I slot print_timing: id 0 | task 1321 | graphs reused = 1284 0.22.096.920 I slot print_timing: id 0 | task 1321 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.096.951 I slot release: id 0 | task 1321 | stop processing: n_tokens = 479, truncated = 0 0.22.123.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 21992748 0.22.148.899 I slot launch_slot_: id 0 | task 1394 | processing task, is_child = 0 0.22.918.015 I slot print_timing: id 0 | task 1394 | prompt eval time = 128.24 ms / 385 tokens ( 0.33 ms per token, 3002.18 tokens per second) 0.22.918.020 I slot print_timing: id 0 | task 1394 | eval time = 640.86 ms / 64 tokens ( 10.17 ms per token, 98.31 tokens per second) 0.22.918.021 I slot print_timing: id 0 | task 1394 | total time = 769.10 ms / 449 tokens 0.22.918.022 I slot print_timing: id 0 | task 1394 | graphs reused = 1346 0.22.918.023 I slot print_timing: id 0 | task 1394 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.918.051 I slot release: id 0 | task 1394 | stop processing: n_tokens = 448, truncated = 0 0.22.940.353 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 22813849 0.22.964.396 I slot launch_slot_: id 0 | task 1461 | processing task, is_child = 0 0.24.007.739 I slot print_timing: id 0 | task 1461 | prompt eval time = 129.72 ms / 395 tokens ( 0.33 ms per token, 3044.95 tokens per second) 0.24.007.745 I slot print_timing: id 0 | task 1461 | eval time = 913.60 ms / 92 tokens ( 10.04 ms per token, 99.61 tokens per second) 0.24.007.746 I slot print_timing: id 0 | task 1461 | total time = 1043.33 ms / 487 tokens 0.24.007.746 I slot print_timing: id 0 | task 1461 | graphs reused = 1436 0.24.007.747 I slot print_timing: id 0 | task 1461 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.007.775 I slot release: id 0 | task 1461 | stop processing: n_tokens = 486, truncated = 0 0.24.043.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 23903572 0.24.068.452 I slot launch_slot_: id 0 | task 1556 | processing task, is_child = 0 0.25.042.042 I slot print_timing: id 0 | task 1556 | prompt eval time = 130.88 ms / 430 tokens ( 0.30 ms per token, 3285.48 tokens per second) 0.25.042.047 I slot print_timing: id 0 | task 1556 | eval time = 842.69 ms / 84 tokens ( 10.15 ms per token, 98.49 tokens per second) 0.25.042.048 I slot print_timing: id 0 | task 1556 | total time = 973.57 ms / 514 tokens 0.25.042.049 I slot print_timing: id 0 | task 1556 | graphs reused = 1517 0.25.042.050 I slot print_timing: id 0 | task 1556 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.042.080 I slot release: id 0 | task 1556 | stop processing: n_tokens = 513, truncated = 0 0.25.047.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 513, t_last = 24937878 0.25.072.331 I slot launch_slot_: id 0 | task 1643 | processing task, is_child = 0 0.25.819.161 I slot print_timing: id 0 | task 1643 | prompt eval time = 129.44 ms / 392 tokens ( 0.33 ms per token, 3028.31 tokens per second) 0.25.819.166 I slot print_timing: id 0 | task 1643 | eval time = 617.37 ms / 62 tokens ( 10.12 ms per token, 98.81 tokens per second) 0.25.819.168 I slot print_timing: id 0 | task 1643 | total time = 746.81 ms / 454 tokens 0.25.819.169 I slot print_timing: id 0 | task 1643 | graphs reused = 1577 0.25.819.170 I slot print_timing: id 0 | task 1643 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.819.197 I slot release: id 0 | task 1643 | stop processing: n_tokens = 453, truncated = 0 0.25.840.596 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 25714995 0.25.868.257 I slot launch_slot_: id 0 | task 1708 | processing task, is_child = 0 0.26.684.414 I slot print_timing: id 0 | task 1708 | prompt eval time = 118.75 ms / 350 tokens ( 0.34 ms per token, 2947.29 tokens per second) 0.26.684.420 I slot print_timing: id 0 | task 1708 | eval time = 697.39 ms / 70 tokens ( 10.11 ms per token, 98.94 tokens per second) 0.26.684.421 I slot print_timing: id 0 | task 1708 | total time = 816.14 ms / 420 tokens 0.26.684.422 I slot print_timing: id 0 | task 1708 | graphs reused = 1645 0.26.684.423 I slot print_timing: id 0 | task 1708 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.684.450 I slot release: id 0 | task 1708 | stop processing: n_tokens = 419, truncated = 0 0.26.726.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 26580247 0.26.750.689 I slot launch_slot_: id 0 | task 1781 | processing task, is_child = 0 0.27.740.168 I slot print_timing: id 0 | task 1781 | prompt eval time = 126.86 ms / 380 tokens ( 0.33 ms per token, 2995.40 tokens per second) 0.27.740.174 I slot print_timing: id 0 | task 1781 | eval time = 862.60 ms / 87 tokens ( 10.03 ms per token, 99.70 tokens per second) 0.27.740.175 I slot print_timing: id 0 | task 1781 | total time = 989.46 ms / 467 tokens 0.27.740.176 I slot print_timing: id 0 | task 1781 | graphs reused = 1730 0.27.740.177 I slot print_timing: id 0 | task 1781 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.740.205 I slot release: id 0 | task 1781 | stop processing: n_tokens = 466, truncated = 0 0.27.754.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 27636002 0.27.780.301 I slot launch_slot_: id 0 | task 1871 | processing task, is_child = 0 0.28.899.533 I slot print_timing: id 0 | task 1871 | prompt eval time = 131.06 ms / 410 tokens ( 0.32 ms per token, 3128.24 tokens per second) 0.28.899.539 I slot print_timing: id 0 | task 1871 | eval time = 988.15 ms / 99 tokens ( 10.08 ms per token, 99.18 tokens per second) 0.28.899.540 I slot print_timing: id 0 | task 1871 | total time = 1119.21 ms / 509 tokens 0.28.899.541 I slot print_timing: id 0 | task 1871 | graphs reused = 1827 0.28.899.541 I slot print_timing: id 0 | task 1871 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.899.570 I slot release: id 0 | task 1871 | stop processing: n_tokens = 508, truncated = 0 0.28.936.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 508, t_last = 28795368 0.28.961.146 I slot launch_slot_: id 0 | task 1973 | processing task, is_child = 0 0.29.765.390 I slot print_timing: id 0 | task 1973 | prompt eval time = 127.45 ms / 387 tokens ( 0.33 ms per token, 3036.58 tokens per second) 0.29.765.396 I slot print_timing: id 0 | task 1973 | eval time = 676.78 ms / 68 tokens ( 10.10 ms per token, 99.00 tokens per second) 0.29.765.396 I slot print_timing: id 0 | task 1973 | total time = 804.22 ms / 455 tokens 0.29.765.397 I slot print_timing: id 0 | task 1973 | graphs reused = 1893 0.29.765.398 I slot print_timing: id 0 | task 1973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.765.428 I slot release: id 0 | task 1973 | stop processing: n_tokens = 454, truncated = 0 0.29.805.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 29661226 0.29.829.848 I slot launch_slot_: id 0 | task 2044 | processing task, is_child = 0 0.30.734.071 I slot print_timing: id 0 | task 2044 | prompt eval time = 119.28 ms / 358 tokens ( 0.33 ms per token, 3001.37 tokens per second) 0.30.734.076 I slot print_timing: id 0 | task 2044 | eval time = 784.93 ms / 79 tokens ( 10.06 ms per token, 99.37 tokens per second) 0.30.734.077 I slot print_timing: id 0 | task 2044 | total time = 904.21 ms / 437 tokens 0.30.734.078 I slot print_timing: id 0 | task 2044 | graphs reused = 1970 0.30.734.079 I slot print_timing: id 0 | task 2044 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.734.108 I slot release: id 0 | task 2044 | stop processing: n_tokens = 436, truncated = 0 0.30.774.137 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 30629905 0.30.798.416 I slot launch_slot_: id 0 | task 2126 | processing task, is_child = 0 0.31.632.090 I slot print_timing: id 0 | task 2126 | prompt eval time = 119.31 ms / 359 tokens ( 0.33 ms per token, 3009.02 tokens per second) 0.31.632.096 I slot print_timing: id 0 | task 2126 | eval time = 714.35 ms / 72 tokens ( 10.06 ms per token, 99.39 tokens per second) 0.31.632.097 I slot print_timing: id 0 | task 2126 | total time = 833.66 ms / 431 tokens 0.31.632.098 I slot print_timing: id 0 | task 2126 | graphs reused = 2040 0.31.632.098 I slot print_timing: id 0 | task 2126 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.632.126 I slot release: id 0 | task 2126 | stop processing: n_tokens = 430, truncated = 0 0.31.676.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 31527924 0.31.701.524 I slot launch_slot_: id 0 | task 2201 | processing task, is_child = 0 0.32.433.987 I slot print_timing: id 0 | task 2201 | prompt eval time = 126.55 ms / 387 tokens ( 0.33 ms per token, 3058.08 tokens per second) 0.32.433.992 I slot print_timing: id 0 | task 2201 | eval time = 605.89 ms / 61 tokens ( 10.10 ms per token, 99.03 tokens per second) 0.32.433.993 I slot print_timing: id 0 | task 2201 | total time = 732.44 ms / 448 tokens 0.32.433.994 I slot print_timing: id 0 | task 2201 | graphs reused = 2099 0.32.433.995 I slot print_timing: id 0 | task 2201 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.434.025 I slot release: id 0 | task 2201 | stop processing: n_tokens = 447, truncated = 0 0.32.462.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 32329823 0.32.486.955 I slot launch_slot_: id 0 | task 2265 | processing task, is_child = 0 0.33.218.370 I slot print_timing: id 0 | task 2265 | prompt eval time = 128.50 ms / 410 tokens ( 0.31 ms per token, 3190.56 tokens per second) 0.33.218.376 I slot print_timing: id 0 | task 2265 | eval time = 602.89 ms / 61 tokens ( 10.05 ms per token, 99.52 tokens per second) 0.33.218.377 I slot print_timing: id 0 | task 2265 | total time = 731.39 ms / 471 tokens 0.33.218.378 I slot print_timing: id 0 | task 2265 | graphs reused = 2158 0.33.218.379 I slot print_timing: id 0 | task 2265 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.218.409 I slot release: id 0 | task 2265 | stop processing: n_tokens = 470, truncated = 0 0.33.242.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 33114207 0.33.267.456 I slot launch_slot_: id 0 | task 2329 | processing task, is_child = 0 0.33.882.133 I slot print_timing: id 0 | task 2329 | prompt eval time = 119.23 ms / 351 tokens ( 0.34 ms per token, 2943.96 tokens per second) 0.33.882.139 I slot print_timing: id 0 | task 2329 | eval time = 495.43 ms / 50 tokens ( 10.11 ms per token, 98.90 tokens per second) 0.33.882.140 I slot print_timing: id 0 | task 2329 | total time = 614.66 ms / 401 tokens 0.33.882.141 I slot print_timing: id 0 | task 2329 | graphs reused = 2206 0.33.882.142 I slot print_timing: id 0 | task 2329 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.882.170 I slot release: id 0 | task 2329 | stop processing: n_tokens = 400, truncated = 0 0.33.898.474 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 33777968 0.33.922.957 I slot launch_slot_: id 0 | task 2382 | processing task, is_child = 0 0.36.296.403 I slot print_timing: id 0 | task 2382 | prompt eval time = 126.13 ms / 393 tokens ( 0.32 ms per token, 3115.81 tokens per second) 0.36.296.409 I slot print_timing: id 0 | task 2382 | eval time = 2247.29 ms / 224 tokens ( 10.08 ms per token, 99.23 tokens per second) 0.36.296.410 I slot print_timing: id 0 | task 2382 | total time = 2373.42 ms / 617 tokens 0.36.296.411 I slot print_timing: id 0 | task 2382 | graphs reused = 2427 0.36.296.411 I slot print_timing: id 0 | task 2382 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.296.442 I slot release: id 0 | task 2382 | stop processing: n_tokens = 616, truncated = 0 0.36.310.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 36192239 0.36.335.464 I slot launch_slot_: id 0 | task 2609 | processing task, is_child = 0 0.36.763.850 I slot print_timing: id 0 | task 2609 | prompt eval time = 117.80 ms / 321 tokens ( 0.37 ms per token, 2725.07 tokens per second) 0.36.763.856 I slot print_timing: id 0 | task 2609 | eval time = 310.57 ms / 31 tokens ( 10.35 ms per token, 96.60 tokens per second) 0.36.763.857 I slot print_timing: id 0 | task 2609 | total time = 428.36 ms / 352 tokens 0.36.763.858 I slot print_timing: id 0 | task 2609 | graphs reused = 2456 0.36.763.859 I slot print_timing: id 0 | task 2609 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.763.887 I slot release: id 0 | task 2609 | stop processing: n_tokens = 351, truncated = 0 0.36.768.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 351, t_last = 36659684 0.36.792.197 I slot launch_slot_: id 0 | task 2643 | processing task, is_child = 0 0.37.874.136 I slot print_timing: id 0 | task 2643 | prompt eval time = 118.95 ms / 330 tokens ( 0.36 ms per token, 2774.23 tokens per second) 0.37.874.141 I slot print_timing: id 0 | task 2643 | eval time = 962.97 ms / 93 tokens ( 10.47 ms per token, 95.54 tokens per second) 0.37.874.142 I slot print_timing: id 0 | task 2643 | total time = 1081.92 ms / 423 tokens 0.37.874.143 I slot print_timing: id 0 | task 2643 | graphs reused = 2547 0.37.874.144 I slot print_timing: id 0 | task 2643 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.874.170 I slot release: id 0 | task 2643 | stop processing: n_tokens = 422, truncated = 0 0.37.914.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 37769968 0.37.939.943 I slot launch_slot_: id 0 | task 2739 | processing task, is_child = 0 0.38.528.213 I slot print_timing: id 0 | task 2739 | prompt eval time = 122.26 ms / 341 tokens ( 0.36 ms per token, 2789.09 tokens per second) 0.38.528.219 I slot print_timing: id 0 | task 2739 | eval time = 465.99 ms / 45 tokens ( 10.59 ms per token, 94.42 tokens per second) 0.38.528.220 I slot print_timing: id 0 | task 2739 | total time = 588.25 ms / 386 tokens 0.38.528.221 I slot print_timing: id 0 | task 2739 | graphs reused = 2590 0.38.528.222 I slot print_timing: id 0 | task 2739 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.528.251 I slot release: id 0 | task 2739 | stop processing: n_tokens = 385, truncated = 0 0.38.534.152 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 38424049 0.38.562.979 I slot launch_slot_: id 0 | task 2787 | processing task, is_child = 0 0.39.169.230 I slot print_timing: id 0 | task 2787 | prompt eval time = 121.72 ms / 338 tokens ( 0.36 ms per token, 2776.75 tokens per second) 0.39.169.236 I slot print_timing: id 0 | task 2787 | eval time = 484.49 ms / 48 tokens ( 10.31 ms per token, 97.01 tokens per second) 0.39.169.237 I slot print_timing: id 0 | task 2787 | total time = 606.22 ms / 386 tokens 0.39.169.238 I slot print_timing: id 0 | task 2787 | graphs reused = 2636 0.39.169.239 I slot print_timing: id 0 | task 2787 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.169.268 I slot release: id 0 | task 2787 | stop processing: n_tokens = 385, truncated = 0 0.39.200.127 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 39065066 0.39.223.469 I slot launch_slot_: id 0 | task 2838 | processing task, is_child = 0 0.39.908.204 I slot print_timing: id 0 | task 2838 | prompt eval time = 130.22 ms / 395 tokens ( 0.33 ms per token, 3033.24 tokens per second) 0.39.908.210 I slot print_timing: id 0 | task 2838 | eval time = 554.50 ms / 56 tokens ( 10.08 ms per token, 99.19 tokens per second) 0.39.908.211 I slot print_timing: id 0 | task 2838 | total time = 684.72 ms / 451 tokens 0.39.908.212 I slot print_timing: id 0 | task 2838 | graphs reused = 2690 0.39.908.213 I slot print_timing: id 0 | task 2838 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.908.241 I slot release: id 0 | task 2838 | stop processing: n_tokens = 450, truncated = 0 0.39.952.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 39804038 0.39.976.946 I slot launch_slot_: id 0 | task 2897 | processing task, is_child = 0 0.41.018.952 I slot print_timing: id 0 | task 2897 | prompt eval time = 180.84 ms / 528 tokens ( 0.34 ms per token, 2919.72 tokens per second) 0.41.018.957 I slot print_timing: id 0 | task 2897 | eval time = 861.15 ms / 83 tokens ( 10.50 ms per token, 95.22 tokens per second) 0.41.018.958 I slot print_timing: id 0 | task 2897 | total time = 1041.99 ms / 611 tokens 0.41.018.959 I slot print_timing: id 0 | task 2897 | graphs reused = 2771 0.41.018.960 I slot print_timing: id 0 | task 2897 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.019.000 I slot release: id 0 | task 2897 | stop processing: n_tokens = 610, truncated = 0 0.41.055.831 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 40914798 0.41.086.642 I slot launch_slot_: id 0 | task 2984 | processing task, is_child = 0 0.41.869.585 I slot print_timing: id 0 | task 2984 | prompt eval time = 143.82 ms / 331 tokens ( 0.43 ms per token, 2301.44 tokens per second) 0.41.869.591 I slot print_timing: id 0 | task 2984 | eval time = 639.10 ms / 62 tokens ( 10.48 ms per token, 95.45 tokens per second) 0.41.869.592 I slot print_timing: id 0 | task 2984 | total time = 782.92 ms / 393 tokens 0.41.869.593 I slot print_timing: id 0 | task 2984 | graphs reused = 2831 0.41.869.594 I slot print_timing: id 0 | task 2984 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.869.621 I slot release: id 0 | task 2984 | stop processing: n_tokens = 404, truncated = 0 0.41.896.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 41765419 0.41.926.000 I slot launch_slot_: id 0 | task 3049 | processing task, is_child = 0 0.42.854.670 I slot print_timing: id 0 | task 3049 | prompt eval time = 149.00 ms / 362 tokens ( 0.41 ms per token, 2429.48 tokens per second) 0.42.854.676 I slot print_timing: id 0 | task 3049 | eval time = 779.65 ms / 76 tokens ( 10.40 ms per token, 96.20 tokens per second) 0.42.854.678 I slot print_timing: id 0 | task 3049 | total time = 928.65 ms / 438 tokens 0.42.854.678 I slot print_timing: id 0 | task 3049 | graphs reused = 2905 0.42.854.679 I slot print_timing: id 0 | task 3049 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.854.708 I slot release: id 0 | task 3049 | stop processing: n_tokens = 449, truncated = 0 0.42.871.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 42750505 0.42.901.455 I slot launch_slot_: id 0 | task 3128 | processing task, is_child = 0 0.43.843.549 I slot print_timing: id 0 | task 3128 | prompt eval time = 148.48 ms / 419 tokens ( 0.35 ms per token, 2821.93 tokens per second) 0.43.843.555 I slot print_timing: id 0 | task 3128 | eval time = 793.60 ms / 80 tokens ( 10.05 ms per token, 99.55 tokens per second) 0.43.843.556 I slot print_timing: id 0 | task 3128 | total time = 942.08 ms / 499 tokens 0.43.843.557 I slot print_timing: id 0 | task 3128 | graphs reused = 2983 0.43.843.558 I slot print_timing: id 0 | task 3128 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.843.589 I slot release: id 0 | task 3128 | stop processing: n_tokens = 510, truncated = 0 0.43.884.251 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 510, t_last = 43739387 0.43.914.654 I slot launch_slot_: id 0 | task 3211 | processing task, is_child = 0 0.44.518.935 I slot print_timing: id 0 | task 3211 | prompt eval time = 160.63 ms / 423 tokens ( 0.38 ms per token, 2633.30 tokens per second) 0.44.518.941 I slot print_timing: id 0 | task 3211 | eval time = 443.62 ms / 44 tokens ( 10.32 ms per token, 96.93 tokens per second) 0.44.518.942 I slot print_timing: id 0 | task 3211 | total time = 604.26 ms / 467 tokens 0.44.518.943 I slot print_timing: id 0 | task 3211 | graphs reused = 3025 0.44.518.944 I slot print_timing: id 0 | task 3211 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.518.979 I slot release: id 0 | task 3211 | stop processing: n_tokens = 478, truncated = 0 0.44.543.961 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 44414776 0.44.577.040 I slot launch_slot_: id 0 | task 3258 | processing task, is_child = 0 0.45.163.933 I slot print_timing: id 0 | task 3258 | prompt eval time = 142.53 ms / 341 tokens ( 0.42 ms per token, 2392.45 tokens per second) 0.45.163.938 I slot print_timing: id 0 | task 3258 | eval time = 444.34 ms / 43 tokens ( 10.58 ms per token, 94.52 tokens per second) 0.45.163.939 I slot print_timing: id 0 | task 3258 | total time = 586.87 ms / 384 tokens 0.45.163.940 I slot print_timing: id 0 | task 3258 | graphs reused = 3066 0.45.163.941 I slot print_timing: id 0 | task 3258 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.163.971 I slot release: id 0 | task 3258 | stop processing: n_tokens = 395, truncated = 0 0.45.168.747 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 45059769 0.45.197.960 I slot launch_slot_: id 0 | task 3304 | processing task, is_child = 0 0.46.021.058 I slot print_timing: id 0 | task 3304 | prompt eval time = 141.69 ms / 356 tokens ( 0.40 ms per token, 2512.47 tokens per second) 0.46.021.064 I slot print_timing: id 0 | task 3304 | eval time = 681.38 ms / 66 tokens ( 10.48 ms per token, 95.39 tokens per second) 0.46.021.065 I slot print_timing: id 0 | task 3304 | total time = 823.08 ms / 422 tokens 0.46.021.066 I slot print_timing: id 0 | task 3304 | graphs reused = 3130 0.46.021.067 I slot print_timing: id 0 | task 3304 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.021.096 I slot release: id 0 | task 3304 | stop processing: n_tokens = 433, truncated = 0 0.46.058.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 45916893 0.46.058.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.637 MiB) 0.46.092.695 I slot launch_slot_: id 0 | task 3373 | processing task, is_child = 0 0.46.865.502 I slot print_timing: id 0 | task 3373 | prompt eval time = 156.42 ms / 362 tokens ( 0.43 ms per token, 2314.33 tokens per second) 0.46.865.509 I slot print_timing: id 0 | task 3373 | eval time = 616.37 ms / 60 tokens ( 10.45 ms per token, 95.72 tokens per second) 0.46.865.509 I slot print_timing: id 0 | task 3373 | total time = 772.78 ms / 422 tokens 0.46.865.510 I slot print_timing: id 0 | task 3373 | graphs reused = 3188 0.46.865.511 I slot print_timing: id 0 | task 3373 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.865.543 I slot release: id 0 | task 3373 | stop processing: n_tokens = 433, truncated = 0 0.46.897.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 433, t_last = 46761340 0.46.897.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.636 MiB) 0.46.929.688 I slot launch_slot_: id 0 | task 3436 | processing task, is_child = 0 0.47.748.962 I slot print_timing: id 0 | task 3436 | prompt eval time = 146.36 ms / 391 tokens ( 0.37 ms per token, 2671.49 tokens per second) 0.47.748.967 I slot print_timing: id 0 | task 3436 | eval time = 672.89 ms / 68 tokens ( 10.04 ms per token, 99.57 tokens per second) 0.47.748.969 I slot print_timing: id 0 | task 3436 | total time = 819.25 ms / 459 tokens 0.47.748.970 I slot print_timing: id 0 | task 3436 | graphs reused = 3254 0.47.748.970 I slot print_timing: id 0 | task 3436 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.749.000 I slot release: id 0 | task 3436 | stop processing: n_tokens = 470, truncated = 0 0.47.773.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 47644798 0.47.773.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.47.776.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.47.809.797 I slot launch_slot_: id 0 | task 3507 | processing task, is_child = 0 0.48.657.925 I slot print_timing: id 0 | task 3507 | prompt eval time = 137.89 ms / 343 tokens ( 0.40 ms per token, 2487.49 tokens per second) 0.48.657.930 I slot print_timing: id 0 | task 3507 | eval time = 710.22 ms / 70 tokens ( 10.29 ms per token, 97.15 tokens per second) 0.48.657.931 I slot print_timing: id 0 | task 3507 | total time = 848.11 ms / 413 tokens 0.48.657.933 I slot print_timing: id 0 | task 3507 | graphs reused = 3322 0.48.657.934 I slot print_timing: id 0 | task 3507 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.657.963 I slot release: id 0 | task 3507 | stop processing: n_tokens = 424, truncated = 0 0.48.677.141 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 48553760 0.48.677.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.887 MiB) 0.48.710.838 I slot launch_slot_: id 0 | task 3580 | processing task, is_child = 0 0.49.524.472 I slot print_timing: id 0 | task 3580 | prompt eval time = 151.15 ms / 401 tokens ( 0.38 ms per token, 2652.92 tokens per second) 0.49.524.478 I slot print_timing: id 0 | task 3580 | eval time = 662.45 ms / 64 tokens ( 10.52 ms per token, 95.10 tokens per second) 0.49.524.479 I slot print_timing: id 0 | task 3580 | total time = 813.61 ms / 465 tokens 0.49.524.480 I slot print_timing: id 0 | task 3580 | graphs reused = 3384 0.49.524.481 I slot print_timing: id 0 | task 3580 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.524.512 I slot release: id 0 | task 3580 | stop processing: n_tokens = 476, truncated = 0 0.49.564.655 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 49420310 0.49.564.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.49.600.980 I slot launch_slot_: id 0 | task 3647 | processing task, is_child = 0 0.50.587.365 I slot print_timing: id 0 | task 3647 | prompt eval time = 141.71 ms / 355 tokens ( 0.40 ms per token, 2505.17 tokens per second) 0.50.587.371 I slot print_timing: id 0 | task 3647 | eval time = 844.66 ms / 82 tokens ( 10.43 ms per token, 95.90 tokens per second) 0.50.587.372 I slot print_timing: id 0 | task 3647 | total time = 986.37 ms / 437 tokens 0.50.587.372 I slot print_timing: id 0 | task 3647 | graphs reused = 3464 0.50.587.373 I slot print_timing: id 0 | task 3647 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.587.403 I slot release: id 0 | task 3647 | stop processing: n_tokens = 448, truncated = 0 0.50.610.857 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 50483200 0.50.610.914 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.076 MiB) 0.50.647.705 I slot launch_slot_: id 0 | task 3732 | processing task, is_child = 0 0.51.589.546 I slot print_timing: id 0 | task 3732 | prompt eval time = 142.64 ms / 351 tokens ( 0.41 ms per token, 2460.72 tokens per second) 0.51.589.552 I slot print_timing: id 0 | task 3732 | eval time = 799.18 ms / 74 tokens ( 10.95 ms per token, 91.34 tokens per second) 0.51.589.553 I slot print_timing: id 0 | task 3732 | total time = 941.82 ms / 425 tokens 0.51.589.554 I slot print_timing: id 0 | task 3732 | graphs reused = 3536 0.51.589.555 I slot print_timing: id 0 | task 3732 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.589.583 I slot release: id 0 | task 3732 | stop processing: n_tokens = 436, truncated = 0 0.51.631.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 436, t_last = 51485380 0.51.631.565 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 168.171 MiB) 0.51.634.448 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.51.669.206 I slot launch_slot_: id 0 | task 3809 | processing task, is_child = 0 0.52.782.670 I slot print_timing: id 0 | task 3809 | prompt eval time = 163.54 ms / 475 tokens ( 0.34 ms per token, 2904.42 tokens per second) 0.52.782.676 I slot print_timing: id 0 | task 3809 | eval time = 949.90 ms / 93 tokens ( 10.32 ms per token, 96.85 tokens per second) 0.52.782.677 I slot print_timing: id 0 | task 3809 | total time = 1113.44 ms / 568 tokens 0.52.782.678 I slot print_timing: id 0 | task 3809 | graphs reused = 3626 0.52.782.678 I slot print_timing: id 0 | task 3809 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.782.712 I slot release: id 0 | task 3809 | stop processing: n_tokens = 579, truncated = 0 0.52.799.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 52678509 0.52.799.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.52.834.653 I slot launch_slot_: id 0 | task 3905 | processing task, is_child = 0 0.54.257.260 I slot print_timing: id 0 | task 3905 | prompt eval time = 162.49 ms / 440 tokens ( 0.37 ms per token, 2707.79 tokens per second) 0.54.257.265 I slot print_timing: id 0 | task 3905 | eval time = 1260.09 ms / 121 tokens ( 10.50 ms per token, 95.23 tokens per second) 0.54.257.266 I slot print_timing: id 0 | task 3905 | total time = 1422.59 ms / 561 tokens 0.54.257.267 I slot print_timing: id 0 | task 3905 | graphs reused = 3744 0.54.257.267 I slot print_timing: id 0 | task 3905 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.257.300 I slot release: id 0 | task 3905 | stop processing: n_tokens = 572, truncated = 0 0.54.281.204 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 54153097 0.54.281.255 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.54.314.505 I slot launch_slot_: id 0 | task 4029 | processing task, is_child = 0 0.55.025.192 I slot print_timing: id 0 | task 4029 | prompt eval time = 140.45 ms / 345 tokens ( 0.41 ms per token, 2456.46 tokens per second) 0.55.025.198 I slot print_timing: id 0 | task 4029 | eval time = 570.22 ms / 55 tokens ( 10.56 ms per token, 94.70 tokens per second) 0.55.025.199 I slot print_timing: id 0 | task 4029 | total time = 710.67 ms / 400 tokens 0.55.025.200 I slot print_timing: id 0 | task 4029 | graphs reused = 3797 0.55.025.201 I slot print_timing: id 0 | task 4029 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.025.232 I slot release: id 0 | task 4029 | stop processing: n_tokens = 411, truncated = 0 0.55.046.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 54921030 0.55.046.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.55.049.029 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.55.084.913 I slot launch_slot_: id 0 | task 4087 | processing task, is_child = 0 0.55.803.646 I slot print_timing: id 0 | task 4087 | prompt eval time = 158.79 ms / 382 tokens ( 0.42 ms per token, 2405.68 tokens per second) 0.55.803.652 I slot print_timing: id 0 | task 4087 | eval time = 559.92 ms / 55 tokens ( 10.37 ms per token, 96.44 tokens per second) 0.55.803.653 I slot print_timing: id 0 | task 4087 | total time = 718.71 ms / 437 tokens 0.55.803.655 I slot print_timing: id 0 | task 4087 | graphs reused = 3850 0.55.803.656 I slot print_timing: id 0 | task 4087 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.803.687 I slot release: id 0 | task 4087 | stop processing: n_tokens = 448, truncated = 0 0.55.824.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 55699484 0.55.824.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.55.859.143 I slot launch_slot_: id 0 | task 4145 | processing task, is_child = 0 0.56.441.011 I slot print_timing: id 0 | task 4145 | prompt eval time = 136.52 ms / 337 tokens ( 0.41 ms per token, 2468.54 tokens per second) 0.56.441.016 I slot print_timing: id 0 | task 4145 | eval time = 445.33 ms / 45 tokens ( 10.12 ms per token, 98.80 tokens per second) 0.56.441.017 I slot print_timing: id 0 | task 4145 | total time = 581.85 ms / 382 tokens 0.56.441.018 I slot print_timing: id 0 | task 4145 | graphs reused = 3893 0.56.441.019 I slot print_timing: id 0 | task 4145 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.441.046 I slot release: id 0 | task 4145 | stop processing: n_tokens = 393, truncated = 0 0.56.445.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 56336844 0.56.445.970 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.56.478.706 I slot launch_slot_: id 0 | task 4193 | processing task, is_child = 0 0.57.352.812 I slot print_timing: id 0 | task 4193 | prompt eval time = 146.05 ms / 402 tokens ( 0.36 ms per token, 2752.56 tokens per second) 0.57.352.817 I slot print_timing: id 0 | task 4193 | eval time = 728.04 ms / 70 tokens ( 10.55 ms per token, 94.78 tokens per second) 0.57.352.819 I slot print_timing: id 0 | task 4193 | total time = 874.09 ms / 472 tokens 0.57.352.819 I slot print_timing: id 0 | task 4193 | graphs reused = 3961 0.57.352.821 I slot print_timing: id 0 | task 4193 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.352.852 I slot release: id 0 | task 4193 | stop processing: n_tokens = 483, truncated = 0 0.57.357.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 57248649 0.57.357.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.57.360.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.57.395.542 I slot launch_slot_: id 0 | task 4266 | processing task, is_child = 0 0.58.171.838 I slot print_timing: id 0 | task 4266 | prompt eval time = 190.12 ms / 549 tokens ( 0.35 ms per token, 2887.67 tokens per second) 0.58.171.844 I slot print_timing: id 0 | task 4266 | eval time = 586.16 ms / 57 tokens ( 10.47 ms per token, 95.54 tokens per second) 0.58.171.845 I slot print_timing: id 0 | task 4266 | total time = 776.27 ms / 606 tokens 0.58.171.846 I slot print_timing: id 0 | task 4266 | graphs reused = 4016 0.58.171.847 I slot print_timing: id 0 | task 4266 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.171.880 I slot release: id 0 | task 4266 | stop processing: n_tokens = 617, truncated = 0 0.58.177.271 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 58067678 0.58.177.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.58.217.738 I slot launch_slot_: id 0 | task 4327 | processing task, is_child = 0 0.59.178.873 I slot print_timing: id 0 | task 4327 | prompt eval time = 206.25 ms / 616 tokens ( 0.33 ms per token, 2986.65 tokens per second) 0.59.178.879 I slot print_timing: id 0 | task 4327 | eval time = 754.86 ms / 73 tokens ( 10.48 ms per token, 95.38 tokens per second) 0.59.178.880 I slot print_timing: id 0 | task 4327 | total time = 961.11 ms / 689 tokens 0.59.178.881 I slot print_timing: id 0 | task 4327 | graphs reused = 4087 0.59.178.882 I slot print_timing: id 0 | task 4327 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.178.917 I slot release: id 0 | task 4327 | stop processing: n_tokens = 700, truncated = 0 0.59.213.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 700, t_last = 59074714 0.59.213.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.324 MiB) 0.59.216.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.388 MiB) 0.59.259.206 I slot launch_slot_: id 0 | task 4404 | processing task, is_child = 0 1.00.089.346 I slot print_timing: id 0 | task 4404 | prompt eval time = 216.02 ms / 665 tokens ( 0.32 ms per token, 3078.39 tokens per second) 1.00.089.352 I slot print_timing: id 0 | task 4404 | eval time = 614.10 ms / 61 tokens ( 10.23 ms per token, 97.70 tokens per second) 1.00.089.353 I slot print_timing: id 0 | task 4404 | total time = 830.12 ms / 726 tokens 1.00.089.354 I slot print_timing: id 0 | task 4404 | graphs reused = 4146 1.00.089.355 I slot print_timing: id 0 | task 4404 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.089.393 I slot release: id 0 | task 4404 | stop processing: n_tokens = 737, truncated = 0 1.00.119.988 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 59985190 1.00.120.055 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.043 MiB) 1.00.122.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 1.00.166.651 I slot launch_slot_: id 0 | task 4469 | processing task, is_child = 0 1.01.141.051 I slot print_timing: id 0 | task 4469 | prompt eval time = 207.77 ms / 645 tokens ( 0.32 ms per token, 3104.44 tokens per second) 1.01.141.057 I slot print_timing: id 0 | task 4469 | eval time = 766.61 ms / 77 tokens ( 10.09 ms per token, 99.14 tokens per second) 1.01.141.058 I slot print_timing: id 0 | task 4469 | total time = 974.38 ms / 722 tokens 1.01.141.059 I slot print_timing: id 0 | task 4469 | graphs reused = 4221 1.01.141.060 I slot print_timing: id 0 | task 4469 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.141.094 I slot release: id 0 | task 4469 | stop processing: n_tokens = 733, truncated = 0 1.01.146.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 733, t_last = 61036892 1.01.146.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.762 MiB) 1.01.187.569 I slot launch_slot_: id 0 | task 4550 | processing task, is_child = 0 1.02.176.114 I slot print_timing: id 0 | task 4550 | prompt eval time = 168.18 ms / 474 tokens ( 0.35 ms per token, 2818.49 tokens per second) 1.02.176.120 I slot print_timing: id 0 | task 4550 | eval time = 820.35 ms / 79 tokens ( 10.52 ms per token, 95.08 tokens per second) 1.02.176.121 I slot print_timing: id 0 | task 4550 | total time = 988.53 ms / 553 tokens 1.02.176.122 I slot print_timing: id 0 | task 4550 | graphs reused = 4297 1.02.176.122 I slot print_timing: id 0 | task 4550 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.176.154 I slot release: id 0 | task 4550 | stop processing: n_tokens = 564, truncated = 0 1.02.182.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 62071952 1.02.182.112 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.951 MiB) 1.02.185.115 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.795 MiB) 1.02.221.136 I slot launch_slot_: id 0 | task 4632 | processing task, is_child = 0 1.03.094.823 I slot print_timing: id 0 | task 4632 | prompt eval time = 203.71 ms / 617 tokens ( 0.33 ms per token, 3028.83 tokens per second) 1.03.094.829 I slot print_timing: id 0 | task 4632 | eval time = 669.96 ms / 65 tokens ( 10.47 ms per token, 95.53 tokens per second) 1.03.094.830 I slot print_timing: id 0 | task 4632 | total time = 873.66 ms / 682 tokens 1.03.094.831 I slot print_timing: id 0 | task 4632 | graphs reused = 4360 1.03.094.832 I slot print_timing: id 0 | task 4632 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.094.868 I slot release: id 0 | task 4632 | stop processing: n_tokens = 693, truncated = 0 1.03.133.825 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 62990665 1.03.133.878 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.03.173.261 I slot launch_slot_: id 0 | task 4701 | processing task, is_child = 0 1.04.121.471 I slot print_timing: id 0 | task 4701 | prompt eval time = 203.39 ms / 601 tokens ( 0.34 ms per token, 2954.97 tokens per second) 1.04.121.478 I slot print_timing: id 0 | task 4701 | eval time = 744.80 ms / 73 tokens ( 10.34 ms per token, 96.67 tokens per second) 1.04.121.479 I slot print_timing: id 0 | task 4701 | total time = 948.19 ms / 674 tokens 1.04.121.480 I slot print_timing: id 0 | task 4701 | graphs reused = 4431 1.04.121.481 I slot print_timing: id 0 | task 4701 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.121.523 I slot release: id 0 | task 4701 | stop processing: n_tokens = 685, truncated = 0 1.04.142.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 64017321 1.04.142.424 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.855 MiB) 1.04.145.103 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.325 MiB) 1.04.187.232 I slot launch_slot_: id 0 | task 4778 | processing task, is_child = 0 1.04.987.705 I slot print_timing: id 0 | task 4778 | prompt eval time = 188.56 ms / 533 tokens ( 0.35 ms per token, 2826.70 tokens per second) 1.04.987.711 I slot print_timing: id 0 | task 4778 | eval time = 611.89 ms / 61 tokens ( 10.20 ms per token, 98.06 tokens per second) 1.04.987.712 I slot print_timing: id 0 | task 4778 | total time = 800.45 ms / 594 tokens 1.04.987.713 I slot print_timing: id 0 | task 4778 | graphs reused = 4490 1.04.987.714 I slot print_timing: id 0 | task 4778 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.987.749 I slot release: id 0 | task 4778 | stop processing: n_tokens = 605, truncated = 0 1.05.002.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 605, t_last = 64883547 1.05.002.479 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.639 MiB) 1.05.005.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.05.049.662 I slot launch_slot_: id 0 | task 4843 | processing task, is_child = 0 1.05.762.257 I slot print_timing: id 0 | task 4843 | prompt eval time = 173.24 ms / 480 tokens ( 0.36 ms per token, 2770.67 tokens per second) 1.05.762.262 I slot print_timing: id 0 | task 4843 | eval time = 539.33 ms / 52 tokens ( 10.58 ms per token, 94.56 tokens per second) 1.05.762.263 I slot print_timing: id 0 | task 4843 | total time = 712.58 ms / 532 tokens 1.05.762.264 I slot print_timing: id 0 | task 4843 | graphs reused = 4539 1.05.762.265 I slot print_timing: id 0 | task 4843 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.762.295 I slot release: id 0 | task 4843 | stop processing: n_tokens = 560, truncated = 0 1.05.781.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 65658093 1.05.781.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.387 MiB) 1.05.822.580 I slot launch_slot_: id 0 | task 4898 | processing task, is_child = 0 1.06.444.897 I slot print_timing: id 0 | task 4898 | prompt eval time = 192.36 ms / 567 tokens ( 0.34 ms per token, 2947.55 tokens per second) 1.06.444.903 I slot print_timing: id 0 | task 4898 | eval time = 429.93 ms / 42 tokens ( 10.49 ms per token, 95.36 tokens per second) 1.06.444.904 I slot print_timing: id 0 | task 4898 | total time = 622.30 ms / 609 tokens 1.06.444.905 I slot print_timing: id 0 | task 4898 | graphs reused = 4579 1.06.444.906 I slot print_timing: id 0 | task 4898 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.444.941 I slot release: id 0 | task 4898 | stop processing: n_tokens = 637, truncated = 0 1.06.475.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 66340738 1.06.475.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.199 MiB) 1.06.478.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.06.525.474 I slot launch_slot_: id 0 | task 4944 | processing task, is_child = 0 1.07.362.668 I slot print_timing: id 0 | task 4944 | prompt eval time = 177.30 ms / 506 tokens ( 0.35 ms per token, 2853.86 tokens per second) 1.07.362.674 I slot print_timing: id 0 | task 4944 | eval time = 659.87 ms / 64 tokens ( 10.47 ms per token, 95.47 tokens per second) 1.07.362.675 I slot print_timing: id 0 | task 4944 | total time = 837.17 ms / 570 tokens 1.07.362.676 I slot print_timing: id 0 | task 4944 | graphs reused = 4641 1.07.362.677 I slot print_timing: id 0 | task 4944 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.362.709 I slot release: id 0 | task 4944 | stop processing: n_tokens = 598, truncated = 0 1.07.390.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 67258507 1.07.390.427 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.07.393.247 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.07.433.900 I slot launch_slot_: id 0 | task 5011 | processing task, is_child = 0 1.08.004.925 I slot print_timing: id 0 | task 5011 | prompt eval time = 165.08 ms / 436 tokens ( 0.38 ms per token, 2641.14 tokens per second) 1.08.004.931 I slot print_timing: id 0 | task 5011 | eval time = 405.93 ms / 40 tokens ( 10.41 ms per token, 96.08 tokens per second) 1.08.004.932 I slot print_timing: id 0 | task 5011 | total time = 571.00 ms / 476 tokens 1.08.004.932 I slot print_timing: id 0 | task 5011 | graphs reused = 4679 1.08.004.933 I slot print_timing: id 0 | task 5011 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.004.963 I slot release: id 0 | task 5011 | stop processing: n_tokens = 504, truncated = 0 1.08.045.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 67900761 1.08.045.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.08.085.292 I slot launch_slot_: id 0 | task 5054 | processing task, is_child = 0 1.09.066.707 I slot print_timing: id 0 | task 5054 | prompt eval time = 185.52 ms / 519 tokens ( 0.36 ms per token, 2797.60 tokens per second) 1.09.066.713 I slot print_timing: id 0 | task 5054 | eval time = 795.88 ms / 80 tokens ( 10.07 ms per token, 99.26 tokens per second) 1.09.066.714 I slot print_timing: id 0 | task 5054 | total time = 981.39 ms / 599 tokens 1.09.066.715 I slot print_timing: id 0 | task 5054 | graphs reused = 4757 1.09.066.715 I slot print_timing: id 0 | task 5054 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.066.747 I slot release: id 0 | task 5054 | stop processing: n_tokens = 627, truncated = 0 1.09.071.606 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 68962545 1.09.071.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.729 MiB) 1.09.074.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.949 MiB) 1.09.130.882 I slot launch_slot_: id 0 | task 5138 | processing task, is_child = 0 1.09.765.599 I slot print_timing: id 0 | task 5138 | prompt eval time = 161.93 ms / 465 tokens ( 0.35 ms per token, 2871.65 tokens per second) 1.09.765.605 I slot print_timing: id 0 | task 5138 | eval time = 472.77 ms / 46 tokens ( 10.51 ms per token, 95.18 tokens per second) 1.09.765.606 I slot print_timing: id 0 | task 5138 | total time = 634.70 ms / 511 tokens 1.09.765.607 I slot print_timing: id 0 | task 5138 | graphs reused = 4800 1.09.765.608 I slot print_timing: id 0 | task 5138 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.765.639 I slot release: id 0 | task 5138 | stop processing: n_tokens = 542, truncated = 0 1.09.799.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 69661437 1.09.800.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.09.802.677 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.09.847.743 I slot launch_slot_: id 0 | task 5187 | processing task, is_child = 0 1.10.638.525 I slot print_timing: id 0 | task 5187 | prompt eval time = 165.63 ms / 431 tokens ( 0.38 ms per token, 2602.19 tokens per second) 1.10.638.531 I slot print_timing: id 0 | task 5187 | eval time = 625.13 ms / 60 tokens ( 10.60 ms per token, 94.38 tokens per second) 1.10.638.532 I slot print_timing: id 0 | task 5187 | total time = 790.76 ms / 491 tokens 1.10.638.532 I slot print_timing: id 0 | task 5187 | graphs reused = 4857 1.10.638.534 I slot print_timing: id 0 | task 5187 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.638.567 I slot release: id 0 | task 5187 | stop processing: n_tokens = 522, truncated = 0 1.10.661.586 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 522, t_last = 70534364 1.10.661.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.10.664.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.10.711.651 I slot launch_slot_: id 0 | task 5250 | processing task, is_child = 0 1.11.562.793 I slot print_timing: id 0 | task 5250 | prompt eval time = 165.20 ms / 457 tokens ( 0.36 ms per token, 2766.31 tokens per second) 1.11.562.798 I slot print_timing: id 0 | task 5250 | eval time = 685.92 ms / 66 tokens ( 10.55 ms per token, 94.76 tokens per second) 1.11.562.799 I slot print_timing: id 0 | task 5250 | total time = 851.12 ms / 523 tokens 1.11.562.800 I slot print_timing: id 0 | task 5250 | graphs reused = 4920 1.11.562.801 I slot print_timing: id 0 | task 5250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.562.832 I slot release: id 0 | task 5250 | stop processing: n_tokens = 554, truncated = 0 1.11.567.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 554, t_last = 71458630 1.11.567.705 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.637 MiB) 1.11.571.324 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.044 MiB) 1.11.617.281 I slot launch_slot_: id 0 | task 5319 | processing task, is_child = 0 1.12.206.363 I slot print_timing: id 0 | task 5319 | prompt eval time = 165.88 ms / 439 tokens ( 0.38 ms per token, 2646.49 tokens per second) 1.12.206.369 I slot print_timing: id 0 | task 5319 | eval time = 423.18 ms / 42 tokens ( 10.32 ms per token, 96.89 tokens per second) 1.12.206.369 I slot print_timing: id 0 | task 5319 | total time = 589.06 ms / 481 tokens 1.12.206.370 I slot print_timing: id 0 | task 5319 | graphs reused = 4960 1.12.206.371 I slot print_timing: id 0 | task 5319 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.206.403 I slot release: id 0 | task 5319 | stop processing: n_tokens = 512, truncated = 0 1.12.223.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 72102200 1.12.223.092 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.952 MiB) 1.12.269.045 I slot launch_slot_: id 0 | task 5364 | processing task, is_child = 0 1.13.159.428 I slot print_timing: id 0 | task 5364 | prompt eval time = 194.76 ms / 606 tokens ( 0.32 ms per token, 3111.46 tokens per second) 1.13.159.434 I slot print_timing: id 0 | task 5364 | eval time = 695.60 ms / 70 tokens ( 10.08 ms per token, 99.20 tokens per second) 1.13.159.435 I slot print_timing: id 0 | task 5364 | total time = 890.36 ms / 676 tokens 1.13.159.436 I slot print_timing: id 0 | task 5364 | graphs reused = 5028 1.13.159.437 I slot print_timing: id 0 | task 5364 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.159.475 I slot release: id 0 | task 5364 | stop processing: n_tokens = 707, truncated = 0 1.13.203.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 707, t_last = 73055273 1.13.203.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.13.206.711 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.13.258.355 I slot launch_slot_: id 0 | task 5438 | processing task, is_child = 0 1.14.117.951 I slot print_timing: id 0 | task 5438 | prompt eval time = 166.39 ms / 477 tokens ( 0.35 ms per token, 2866.74 tokens per second) 1.14.117.964 I slot print_timing: id 0 | task 5438 | eval time = 693.17 ms / 67 tokens ( 10.50 ms per token, 95.21 tokens per second) 1.14.117.966 I slot print_timing: id 0 | task 5438 | total time = 859.56 ms / 544 tokens 1.14.117.967 I slot print_timing: id 0 | task 5438 | graphs reused = 5092 1.14.117.968 I slot print_timing: id 0 | task 5438 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.118.040 I slot release: id 0 | task 5438 | stop processing: n_tokens = 575, truncated = 0 1.14.160.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 74013838 1.14.160.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.544 MiB) 1.14.206.897 I slot launch_slot_: id 0 | task 5508 | processing task, is_child = 0 1.15.204.633 I slot print_timing: id 0 | task 5508 | prompt eval time = 251.50 ms / 845 tokens ( 0.30 ms per token, 3359.79 tokens per second) 1.15.204.638 I slot print_timing: id 0 | task 5508 | eval time = 746.21 ms / 72 tokens ( 10.51 ms per token, 95.15 tokens per second) 1.15.204.639 I slot print_timing: id 0 | task 5508 | total time = 997.72 ms / 917 tokens 1.15.204.640 I slot print_timing: id 0 | task 5508 | graphs reused = 5162 1.15.204.641 I slot print_timing: id 0 | task 5508 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.204.686 I slot release: id 0 | task 5508 | stop processing: n_tokens = 948, truncated = 0 1.15.209.745 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 948, t_last = 75100484 1.15.209.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.544 MiB) 1.15.213.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.15.271.092 I slot launch_slot_: id 0 | task 5584 | processing task, is_child = 0 1.15.885.808 I slot print_timing: id 0 | task 5584 | prompt eval time = 168.78 ms / 459 tokens ( 0.37 ms per token, 2719.58 tokens per second) 1.15.885.814 I slot print_timing: id 0 | task 5584 | eval time = 445.92 ms / 43 tokens ( 10.62 ms per token, 94.19 tokens per second) 1.15.885.815 I slot print_timing: id 0 | task 5584 | total time = 614.70 ms / 502 tokens 1.15.885.816 I slot print_timing: id 0 | task 5584 | graphs reused = 5202 1.15.885.818 I slot print_timing: id 0 | task 5584 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.885.850 I slot release: id 0 | task 5584 | stop processing: n_tokens = 533, truncated = 0 1.15.925.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 75781648 1.15.925.290 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.262 MiB) 1.15.983.300 I slot launch_slot_: id 0 | task 5630 | processing task, is_child = 0 1.16.659.696 I slot print_timing: id 0 | task 5630 | prompt eval time = 211.62 ms / 670 tokens ( 0.32 ms per token, 3166.11 tokens per second) 1.16.659.702 I slot print_timing: id 0 | task 5630 | eval time = 464.76 ms / 47 tokens ( 10.10 ms per token, 98.98 tokens per second) 1.16.659.703 I slot print_timing: id 0 | task 5630 | total time = 676.38 ms / 717 tokens 1.16.659.704 I slot print_timing: id 0 | task 5630 | graphs reused = 5247 1.16.659.705 I slot print_timing: id 0 | task 5630 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.659.743 I slot release: id 0 | task 5630 | stop processing: n_tokens = 748, truncated = 0 1.16.675.813 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 76555541 1.16.675.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.888 MiB) 1.16.679.395 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.16.738.840 I slot launch_slot_: id 0 | task 5681 | processing task, is_child = 0 1.17.870.983 I slot print_timing: id 0 | task 5681 | prompt eval time = 233.62 ms / 775 tokens ( 0.30 ms per token, 3317.32 tokens per second) 1.17.870.989 I slot print_timing: id 0 | task 5681 | eval time = 898.50 ms / 86 tokens ( 10.57 ms per token, 94.60 tokens per second) 1.17.870.991 I slot print_timing: id 0 | task 5681 | total time = 1132.12 ms / 861 tokens 1.17.870.992 I slot print_timing: id 0 | task 5681 | graphs reused = 5331 1.17.870.993 I slot print_timing: id 0 | task 5681 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.871.037 I slot release: id 0 | task 5681 | stop processing: n_tokens = 892, truncated = 0 1.17.900.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 892, t_last = 77766835 1.17.900.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.637 MiB) 1.17.904.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.17.963.542 I slot launch_slot_: id 0 | task 5771 | processing task, is_child = 0 1.19.008.283 I slot print_timing: id 0 | task 5771 | prompt eval time = 200.25 ms / 573 tokens ( 0.35 ms per token, 2861.41 tokens per second) 1.19.008.289 I slot print_timing: id 0 | task 5771 | eval time = 844.47 ms / 82 tokens ( 10.43 ms per token, 95.92 tokens per second) 1.19.008.290 I slot print_timing: id 0 | task 5771 | total time = 1044.72 ms / 655 tokens 1.19.008.291 I slot print_timing: id 0 | task 5771 | graphs reused = 5411 1.19.008.292 I slot print_timing: id 0 | task 5771 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.008.331 I slot release: id 0 | task 5771 | stop processing: n_tokens = 686, truncated = 0 1.19.047.538 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 686, t_last = 78904129 1.19.047.602 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.891 MiB) 1.19.051.282 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.19.114.481 I slot launch_slot_: id 0 | task 5857 | processing task, is_child = 0 1.19.952.383 I slot print_timing: id 0 | task 5857 | prompt eval time = 172.22 ms / 461 tokens ( 0.37 ms per token, 2676.87 tokens per second) 1.19.952.389 I slot print_timing: id 0 | task 5857 | eval time = 665.64 ms / 64 tokens ( 10.57 ms per token, 94.65 tokens per second) 1.19.952.390 I slot print_timing: id 0 | task 5857 | total time = 837.86 ms / 525 tokens 1.19.952.391 I slot print_timing: id 0 | task 5857 | graphs reused = 5472 1.19.952.392 I slot print_timing: id 0 | task 5857 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.952.428 I slot release: id 0 | task 5857 | stop processing: n_tokens = 556, truncated = 0 1.19.958.074 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 79848225 1.19.958.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.20.006.554 I slot launch_slot_: id 0 | task 5924 | processing task, is_child = 0 1.20.917.328 I slot print_timing: id 0 | task 5924 | prompt eval time = 196.74 ms / 609 tokens ( 0.32 ms per token, 3095.39 tokens per second) 1.20.917.334 I slot print_timing: id 0 | task 5924 | eval time = 714.01 ms / 69 tokens ( 10.50 ms per token, 95.24 tokens per second) 1.20.917.335 I slot print_timing: id 0 | task 5924 | total time = 910.75 ms / 678 tokens 1.20.917.336 I slot print_timing: id 0 | task 5924 | graphs reused = 5539 1.20.917.336 I slot print_timing: id 0 | task 5924 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.917.374 I slot release: id 0 | task 5924 | stop processing: n_tokens = 709, truncated = 0 1.20.923.791 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 709, t_last = 80813171 1.20.923.849 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.20.927.514 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.20.984.612 I slot launch_slot_: id 0 | task 5997 | processing task, is_child = 0 1.22.049.945 I slot print_timing: id 0 | task 5997 | prompt eval time = 233.56 ms / 791 tokens ( 0.30 ms per token, 3386.64 tokens per second) 1.22.049.951 I slot print_timing: id 0 | task 5997 | eval time = 831.75 ms / 82 tokens ( 10.27 ms per token, 97.39 tokens per second) 1.22.049.952 I slot print_timing: id 0 | task 5997 | total time = 1065.31 ms / 873 tokens 1.22.049.953 I slot print_timing: id 0 | task 5997 | graphs reused = 5619 1.22.049.953 I slot print_timing: id 0 | task 5997 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.049.996 I slot release: id 0 | task 5997 | stop processing: n_tokens = 904, truncated = 0 1.22.083.682 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 904, t_last = 81945794 1.22.083.753 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.22.160.884 I slot launch_slot_: id 0 | task 6083 | processing task, is_child = 0 1.23.110.226 I slot print_timing: id 0 | task 6083 | prompt eval time = 187.11 ms / 533 tokens ( 0.35 ms per token, 2848.61 tokens per second) 1.23.110.237 I slot print_timing: id 0 | task 6083 | eval time = 762.20 ms / 74 tokens ( 10.44 ms per token, 95.78 tokens per second) 1.23.110.238 I slot print_timing: id 0 | task 6083 | total time = 949.31 ms / 607 tokens 1.23.110.240 I slot print_timing: id 0 | task 6083 | graphs reused = 5691 1.23.110.241 I slot print_timing: id 0 | task 6083 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.110.312 I slot release: id 0 | task 6083 | stop processing: n_tokens = 695, truncated = 0 1.23.119.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 695, t_last = 83006110 1.23.119.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.144 MiB) 1.23.180.957 I slot launch_slot_: id 0 | task 6161 | processing task, is_child = 0 1.23.877.303 I slot print_timing: id 0 | task 6161 | prompt eval time = 195.32 ms / 566 tokens ( 0.35 ms per token, 2897.75 tokens per second) 1.23.877.309 I slot print_timing: id 0 | task 6161 | eval time = 501.00 ms / 46 tokens ( 11.13 ms per token, 89.82 tokens per second) 1.23.877.309 I slot print_timing: id 0 | task 6161 | total time = 696.33 ms / 612 tokens 1.23.877.310 I slot print_timing: id 0 | task 6161 | graphs reused = 5735 1.23.877.311 I slot print_timing: id 0 | task 6161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.877.347 I slot release: id 0 | task 6161 | stop processing: n_tokens = 643, truncated = 0 1.23.919.331 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 83773144 1.23.919.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.301 MiB) 1.23.977.530 I slot launch_slot_: id 0 | task 6211 | processing task, is_child = 0 1.24.578.969 I slot print_timing: id 0 | task 6211 | prompt eval time = 170.36 ms / 443 tokens ( 0.38 ms per token, 2600.44 tokens per second) 1.24.578.974 I slot print_timing: id 0 | task 6211 | eval time = 431.06 ms / 43 tokens ( 10.26 ms per token, 97.43 tokens per second) 1.24.578.975 I slot print_timing: id 0 | task 6211 | total time = 601.42 ms / 486 tokens 1.24.578.976 I slot print_timing: id 0 | task 6211 | graphs reused = 5775 1.24.578.976 I slot print_timing: id 0 | task 6211 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.579.007 I slot release: id 0 | task 6211 | stop processing: n_tokens = 517, truncated = 0 1.24.601.917 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 84474804 1.24.601.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.176 MiB) 1.24.649.385 I slot launch_slot_: id 0 | task 6257 | processing task, is_child = 0 1.25.782.079 I slot print_timing: id 0 | task 6257 | prompt eval time = 164.33 ms / 487 tokens ( 0.34 ms per token, 2963.59 tokens per second) 1.25.782.085 I slot print_timing: id 0 | task 6257 | eval time = 968.35 ms / 96 tokens ( 10.19 ms per token, 98.11 tokens per second) 1.25.782.086 I slot print_timing: id 0 | task 6257 | total time = 1132.67 ms / 583 tokens 1.25.782.087 I slot print_timing: id 0 | task 6257 | graphs reused = 5869 1.25.782.088 I slot print_timing: id 0 | task 6257 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.782.124 I slot release: id 0 | task 6257 | stop processing: n_tokens = 614, truncated = 0 1.25.787.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 614, t_last = 85677922 1.25.787.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.640 MiB) 1.25.835.698 I slot launch_slot_: id 0 | task 6356 | processing task, is_child = 0 1.26.720.726 I slot print_timing: id 0 | task 6356 | prompt eval time = 176.83 ms / 507 tokens ( 0.35 ms per token, 2867.16 tokens per second) 1.26.720.733 I slot print_timing: id 0 | task 6356 | eval time = 708.17 ms / 68 tokens ( 10.57 ms per token, 94.61 tokens per second) 1.26.720.734 I slot print_timing: id 0 | task 6356 | total time = 885.00 ms / 575 tokens 1.26.720.735 I slot print_timing: id 0 | task 6356 | graphs reused = 5935 1.26.720.737 I slot print_timing: id 0 | task 6356 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.720.790 I slot release: id 0 | task 6356 | stop processing: n_tokens = 606, truncated = 0 1.26.765.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 86616588 1.26.765.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.925 MiB) 1.26.770.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.26.832.388 I slot launch_slot_: id 0 | task 6427 | processing task, is_child = 0 1.27.734.221 I slot print_timing: id 0 | task 6427 | prompt eval time = 208.99 ms / 633 tokens ( 0.33 ms per token, 3028.81 tokens per second) 1.27.734.232 I slot print_timing: id 0 | task 6427 | eval time = 692.81 ms / 66 tokens ( 10.66 ms per token, 93.82 tokens per second) 1.27.734.234 I slot print_timing: id 0 | task 6427 | total time = 901.80 ms / 699 tokens 1.27.734.235 I slot print_timing: id 0 | task 6427 | graphs reused = 5999 1.27.734.236 I slot print_timing: id 0 | task 6427 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.734.302 I slot release: id 0 | task 6427 | stop processing: n_tokens = 730, truncated = 0 1.27.740.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 87630100 1.27.740.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.173 MiB) 1.27.807.049 I slot launch_slot_: id 0 | task 6497 | processing task, is_child = 0 1.28.700.756 I slot print_timing: id 0 | task 6497 | prompt eval time = 198.95 ms / 571 tokens ( 0.35 ms per token, 2870.13 tokens per second) 1.28.700.764 I slot print_timing: id 0 | task 6497 | eval time = 694.73 ms / 67 tokens ( 10.53 ms per token, 95.00 tokens per second) 1.28.700.767 I slot print_timing: id 0 | task 6497 | total time = 893.68 ms / 638 tokens 1.28.700.767 I slot print_timing: id 0 | task 6497 | graphs reused = 6064 1.28.700.769 I slot print_timing: id 0 | task 6497 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.700.822 I slot release: id 0 | task 6497 | stop processing: n_tokens = 669, truncated = 0 1.28.727.877 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 669, t_last = 88596619 1.28.727.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.28.790.486 I slot launch_slot_: id 0 | task 6568 | processing task, is_child = 0 1.29.470.281 I slot print_timing: id 0 | task 6568 | prompt eval time = 238.83 ms / 798 tokens ( 0.30 ms per token, 3341.30 tokens per second) 1.29.470.287 I slot print_timing: id 0 | task 6568 | eval time = 440.94 ms / 44 tokens ( 10.25 ms per token, 97.52 tokens per second) 1.29.470.288 I slot print_timing: id 0 | task 6568 | total time = 679.77 ms / 842 tokens 1.29.470.288 I slot print_timing: id 0 | task 6568 | graphs reused = 6106 1.29.470.289 I slot print_timing: id 0 | task 6568 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.470.347 I slot release: id 0 | task 6568 | stop processing: n_tokens = 873, truncated = 0 1.29.508.688 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 89366145 1.29.508.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.29.514.197 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.954 MiB) 1.29.589.785 I slot launch_slot_: id 0 | task 6616 | processing task, is_child = 0 1.30.231.451 I slot print_timing: id 0 | task 6616 | prompt eval time = 193.69 ms / 572 tokens ( 0.34 ms per token, 2953.22 tokens per second) 1.30.231.458 I slot print_timing: id 0 | task 6616 | eval time = 447.95 ms / 43 tokens ( 10.67 ms per token, 93.76 tokens per second) 1.30.231.459 I slot print_timing: id 0 | task 6616 | total time = 641.64 ms / 615 tokens 1.30.231.460 I slot print_timing: id 0 | task 6616 | graphs reused = 6147 1.30.231.462 I slot print_timing: id 0 | task 6616 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.231.509 I slot release: id 0 | task 6616 | stop processing: n_tokens = 646, truncated = 0 1.30.273.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 90127307 1.30.273.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.30.333.724 I slot launch_slot_: id 0 | task 6663 | processing task, is_child = 0 1.31.431.896 I slot print_timing: id 0 | task 6663 | prompt eval time = 205.74 ms / 613 tokens ( 0.34 ms per token, 2979.47 tokens per second) 1.31.431.902 I slot print_timing: id 0 | task 6663 | eval time = 892.41 ms / 86 tokens ( 10.50 ms per token, 95.25 tokens per second) 1.31.431.903 I slot print_timing: id 0 | task 6663 | total time = 1098.15 ms / 699 tokens 1.31.431.903 I slot print_timing: id 0 | task 6663 | graphs reused = 6231 1.31.431.904 I slot print_timing: id 0 | task 6663 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.431.941 I slot release: id 0 | task 6663 | stop processing: n_tokens = 730, truncated = 0 1.31.459.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 91327739 1.31.459.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 1.31.516.517 I slot launch_slot_: id 0 | task 6753 | processing task, is_child = 0 1.32.498.330 I slot print_timing: id 0 | task 6753 | prompt eval time = 192.19 ms / 580 tokens ( 0.33 ms per token, 3017.77 tokens per second) 1.32.498.335 I slot print_timing: id 0 | task 6753 | eval time = 789.60 ms / 77 tokens ( 10.39 ms per token, 96.25 tokens per second) 1.32.498.336 I slot print_timing: id 0 | task 6753 | total time = 981.79 ms / 657 tokens 1.32.498.337 I slot print_timing: id 0 | task 6753 | graphs reused = 6306 1.32.498.338 I slot print_timing: id 0 | task 6753 | graph reallocs = 0 / 0 (same size) / (changed size) 1.32.498.373 I slot release: id 0 | task 6753 | stop processing: n_tokens = 688, truncated = 0 1.32.519.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 92394171 1.32.519.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.32.576.162 I slot launch_slot_: id 0 | task 6834 | processing task, is_child = 0 1.33.493.244 I slot print_timing: id 0 | task 6834 | prompt eval time = 216.89 ms / 716 tokens ( 0.30 ms per token, 3301.15 tokens per second) 1.33.493.250 I slot print_timing: id 0 | task 6834 | eval time = 700.17 ms / 70 tokens ( 10.15 ms per token, 98.55 tokens per second) 1.33.493.251 I slot print_timing: id 0 | task 6834 | total time = 917.06 ms / 786 tokens 1.33.493.252 I slot print_timing: id 0 | task 6834 | graphs reused = 6373 1.33.493.253 I slot print_timing: id 0 | task 6834 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.493.293 I slot release: id 0 | task 6834 | stop processing: n_tokens = 817, truncated = 0 1.33.523.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 817, t_last = 93389091 1.33.523.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.828 MiB) 1.33.529.040 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.829 MiB) 1.33.588.745 I slot launch_slot_: id 0 | task 6908 | processing task, is_child = 0 1.35.080.999 I slot print_timing: id 0 | task 6908 | prompt eval time = 234.39 ms / 799 tokens ( 0.29 ms per token, 3408.80 tokens per second) 1.35.081.005 I slot print_timing: id 0 | task 6908 | eval time = 1257.84 ms / 122 tokens ( 10.40 ms per token, 96.20 tokens per second) 1.35.081.006 I slot print_timing: id 0 | task 6908 | total time = 1492.24 ms / 921 tokens 1.35.081.007 I slot print_timing: id 0 | task 6908 | graphs reused = 6493 1.35.081.008 I slot print_timing: id 0 | task 6908 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.081.051 I slot release: id 0 | task 6908 | stop processing: n_tokens = 952, truncated = 0 1.35.100.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 952, t_last = 94976849 1.35.100.898 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.35.162.107 I slot launch_slot_: id 0 | task 7034 | processing task, is_child = 0 1.36.589.335 I slot print_timing: id 0 | task 7034 | prompt eval time = 142.72 ms / 361 tokens ( 0.40 ms per token, 2529.41 tokens per second) 1.36.589.340 I slot print_timing: id 0 | task 7034 | eval time = 1284.49 ms / 125 tokens ( 10.36 ms per token, 96.54 tokens per second) 1.36.589.341 I slot print_timing: id 0 | task 7034 | total time = 1427.21 ms / 486 tokens 1.36.589.342 I slot print_timing: id 0 | task 7034 | graphs reused = 6615 1.36.589.343 I slot print_timing: id 0 | task 7034 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.589.373 I slot release: id 0 | task 7034 | stop processing: n_tokens = 517, truncated = 0 1.36.627.833 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 96485171 1.36.627.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.864 MiB) 1.36.676.695 I slot launch_slot_: id 0 | task 7162 | processing task, is_child = 0 1.38.189.422 I slot print_timing: id 0 | task 7162 | prompt eval time = 142.77 ms / 381 tokens ( 0.37 ms per token, 2668.59 tokens per second) 1.38.189.428 I slot print_timing: id 0 | task 7162 | eval time = 1369.93 ms / 133 tokens ( 10.38 ms per token, 96.36 tokens per second) 1.38.189.429 I slot print_timing: id 0 | task 7162 | total time = 1512.70 ms / 514 tokens 1.38.189.430 I slot print_timing: id 0 | task 7162 | graphs reused = 6745 1.38.189.430 I slot print_timing: id 0 | task 7162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.189.461 I slot release: id 0 | task 7162 | stop processing: n_tokens = 545, truncated = 0 1.38.215.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 98085259 1.38.215.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.486 MiB) 1.38.264.149 I slot launch_slot_: id 0 | task 7298 | processing task, is_child = 0 1.39.804.116 I slot print_timing: id 0 | task 7298 | prompt eval time = 142.47 ms / 365 tokens ( 0.39 ms per token, 2561.89 tokens per second) 1.39.804.123 I slot print_timing: id 0 | task 7298 | eval time = 1397.47 ms / 135 tokens ( 10.43 ms per token, 95.89 tokens per second) 1.39.804.124 I slot print_timing: id 0 | task 7298 | total time = 1539.95 ms / 500 tokens 1.39.804.125 I slot print_timing: id 0 | task 7298 | graphs reused = 6877 1.39.804.126 I slot print_timing: id 0 | task 7298 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.804.161 I slot release: id 0 | task 7298 | stop processing: n_tokens = 531, truncated = 0 1.39.822.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 531, t_last = 99699959 1.39.822.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.401 MiB) 1.39.872.957 I slot launch_slot_: id 0 | task 7436 | processing task, is_child = 0 1.41.386.534 I slot print_timing: id 0 | task 7436 | prompt eval time = 141.28 ms / 333 tokens ( 0.42 ms per token, 2357.10 tokens per second) 1.41.386.539 I slot print_timing: id 0 | task 7436 | eval time = 1372.28 ms / 136 tokens ( 10.17 ms per token, 98.38 tokens per second) 1.41.386.540 I slot print_timing: id 0 | task 7436 | total time = 1513.56 ms / 469 tokens 1.41.386.541 I slot print_timing: id 0 | task 7436 | graphs reused = 7011 1.41.386.542 I slot print_timing: id 0 | task 7436 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.386.569 I slot release: id 0 | task 7436 | stop processing: n_tokens = 500, truncated = 0 1.41.411.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 101282367 1.41.451.446 I slot launch_slot_: id 0 | task 7575 | processing task, is_child = 0 1.43.437.369 I slot print_timing: id 0 | task 7575 | prompt eval time = 146.79 ms / 403 tokens ( 0.36 ms per token, 2745.47 tokens per second) 1.43.437.375 I slot print_timing: id 0 | task 7575 | eval time = 1839.12 ms / 179 tokens ( 10.33 ms per token, 96.79 tokens per second) 1.43.437.377 I slot print_timing: id 0 | task 7575 | total time = 1985.90 ms / 582 tokens 1.43.437.377 I slot print_timing: id 0 | task 7575 | graphs reused = 7187 1.43.437.378 I slot print_timing: id 0 | task 7575 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.437.408 I slot release: id 0 | task 7575 | stop processing: n_tokens = 613, truncated = 0 1.43.442.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 613, t_last = 103333205 1.43.442.515 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.43.492.047 I slot launch_slot_: id 0 | task 7757 | processing task, is_child = 0 1.45.631.004 I slot print_timing: id 0 | task 7757 | prompt eval time = 150.81 ms / 411 tokens ( 0.37 ms per token, 2725.34 tokens per second) 1.45.631.010 I slot print_timing: id 0 | task 7757 | eval time = 1988.13 ms / 196 tokens ( 10.20 ms per token, 98.08 tokens per second) 1.45.631.011 I slot print_timing: id 0 | task 7757 | total time = 2138.94 ms / 607 tokens 1.45.631.012 I slot print_timing: id 0 | task 7757 | graphs reused = 7380 1.45.631.013 I slot print_timing: id 0 | task 7757 | graph reallocs = 0 / 0 (same size) / (changed size) 1.45.631.043 I slot release: id 0 | task 7757 | stop processing: n_tokens = 638, truncated = 0 1.45.636.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 638, t_last = 105526841 1.45.636.196 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.45.688.642 I slot launch_slot_: id 0 | task 7956 | processing task, is_child = 0 1.48.315.810 I slot print_timing: id 0 | task 7956 | prompt eval time = 172.69 ms / 490 tokens ( 0.35 ms per token, 2837.45 tokens per second) 1.48.315.815 I slot print_timing: id 0 | task 7956 | eval time = 2454.45 ms / 236 tokens ( 10.44 ms per token, 95.74 tokens per second) 1.48.315.816 I slot print_timing: id 0 | task 7956 | total time = 2627.14 ms / 726 tokens 1.48.315.818 I slot print_timing: id 0 | task 7956 | graphs reused = 7614 1.48.315.819 I slot print_timing: id 0 | task 7956 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.315.851 I slot release: id 0 | task 7956 | stop processing: n_tokens = 757, truncated = 0 1.48.320.427 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 757, t_last = 108211649 1.48.320.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.650 MiB) 1.48.374.935 I slot launch_slot_: id 0 | task 8195 | processing task, is_child = 0 1.50.387.188 I slot print_timing: id 0 | task 8195 | prompt eval time = 142.02 ms / 344 tokens ( 0.41 ms per token, 2422.16 tokens per second) 1.50.387.194 I slot print_timing: id 0 | task 8195 | eval time = 1870.21 ms / 186 tokens ( 10.11 ms per token, 98.92 tokens per second) 1.50.387.195 I slot print_timing: id 0 | task 8195 | total time = 2012.23 ms / 530 tokens 1.50.387.196 I slot print_timing: id 0 | task 8195 | graphs reused = 7797 1.50.387.197 I slot print_timing: id 0 | task 8195 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.387.226 I slot release: id 0 | task 8195 | stop processing: n_tokens = 561, truncated = 0 1.50.402.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 110283024 1.50.402.432 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.50.452.845 I slot launch_slot_: id 0 | task 8384 | processing task, is_child = 0 1.52.517.551 I slot print_timing: id 0 | task 8384 | prompt eval time = 141.25 ms / 347 tokens ( 0.41 ms per token, 2456.60 tokens per second) 1.52.517.557 I slot print_timing: id 0 | task 8384 | eval time = 1923.43 ms / 187 tokens ( 10.34 ms per token, 96.70 tokens per second) 1.52.517.558 I slot print_timing: id 0 | task 8384 | total time = 2064.68 ms / 534 tokens 1.52.517.559 I slot print_timing: id 0 | task 8384 | graphs reused = 7981 1.52.517.560 I slot print_timing: id 0 | task 8384 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.517.591 I slot release: id 0 | task 8384 | stop processing: n_tokens = 565, truncated = 0 1.52.539.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 565, t_last = 112413388 1.52.539.700 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.927 MiB) 1.52.592.963 I slot launch_slot_: id 0 | task 8574 | processing task, is_child = 0 1.54.134.695 I slot print_timing: id 0 | task 8574 | prompt eval time = 147.45 ms / 401 tokens ( 0.37 ms per token, 2719.55 tokens per second) 1.54.134.701 I slot print_timing: id 0 | task 8574 | eval time = 1394.26 ms / 137 tokens ( 10.25 ms per token, 97.54 tokens per second) 1.54.134.702 I slot print_timing: id 0 | task 8574 | total time = 1541.71 ms / 538 tokens 1.54.134.703 I slot print_timing: id 0 | task 8574 | graphs reused = 8115 1.54.134.703 I slot print_timing: id 0 | task 8574 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.134.734 I slot release: id 0 | task 8574 | stop processing: n_tokens = 569, truncated = 0 1.54.162.525 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 569, t_last = 114030532 1.54.162.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.025 MiB) 1.54.213.728 I slot launch_slot_: id 0 | task 8714 | processing task, is_child = 0 1.55.708.385 I slot print_timing: id 0 | task 8714 | prompt eval time = 161.28 ms / 456 tokens ( 0.35 ms per token, 2827.29 tokens per second) 1.55.708.391 I slot print_timing: id 0 | task 8714 | eval time = 1333.35 ms / 131 tokens ( 10.26 ms per token, 97.50 tokens per second) 1.55.708.392 I slot print_timing: id 0 | task 8714 | total time = 1494.64 ms / 587 tokens 1.55.708.393 I slot print_timing: id 0 | task 8714 | graphs reused = 8243 1.55.708.393 I slot print_timing: id 0 | task 8714 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.708.424 I slot release: id 0 | task 8714 | stop processing: n_tokens = 618, truncated = 0 1.55.748.145 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.076 1.55.748.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.739 MiB) 1.55.810.613 I slot launch_slot_: id 0 | task 8848 | processing task, is_child = 0 1.57.276.429 I slot print_timing: id 0 | task 8848 | prompt eval time = 153.35 ms / 406 tokens ( 0.38 ms per token, 2647.61 tokens per second) 1.57.276.434 I slot print_timing: id 0 | task 8848 | eval time = 1312.45 ms / 127 tokens ( 10.42 ms per token, 96.00 tokens per second) 1.57.276.435 I slot print_timing: id 0 | task 8848 | total time = 1465.80 ms / 533 tokens 1.57.276.436 I slot print_timing: id 0 | task 8848 | graphs reused = 8367 1.57.276.436 I slot print_timing: id 0 | task 8848 | graph reallocs = 0 / 0 (same size) / (changed size) 1.57.276.466 I slot release: id 0 | task 8848 | stop processing: n_tokens = 564, truncated = 0 1.57.292.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 117172264 1.57.332.816 I slot launch_slot_: id 0 | task 8978 | processing task, is_child = 0 1.59.451.458 I slot print_timing: id 0 | task 8978 | prompt eval time = 152.14 ms / 406 tokens ( 0.37 ms per token, 2668.66 tokens per second) 1.59.451.464 I slot print_timing: id 0 | task 8978 | eval time = 1966.49 ms / 194 tokens ( 10.19 ms per token, 98.14 tokens per second) 1.59.451.465 I slot print_timing: id 0 | task 8978 | total time = 2118.62 ms / 600 tokens 1.59.451.466 I slot print_timing: id 0 | task 8978 | graphs reused = 8558 1.59.451.467 I slot print_timing: id 0 | task 8978 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.451.497 I slot release: id 0 | task 8978 | stop processing: n_tokens = 631, truncated = 0 1.59.478.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 631, t_last = 119347295 1.59.478.682 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.59.531.415 I slot launch_slot_: id 0 | task 9175 | processing task, is_child = 0 2.01.172.230 I slot print_timing: id 0 | task 9175 | prompt eval time = 153.33 ms / 444 tokens ( 0.35 ms per token, 2895.68 tokens per second) 2.01.172.236 I slot print_timing: id 0 | task 9175 | eval time = 1487.46 ms / 144 tokens ( 10.40 ms per token, 96.14 tokens per second) 2.01.172.237 I slot print_timing: id 0 | task 9175 | total time = 1640.80 ms / 588 tokens 2.01.172.238 I slot print_timing: id 0 | task 9175 | graphs reused = 8699 2.01.172.239 I slot print_timing: id 0 | task 9175 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.172.271 I slot release: id 0 | task 9175 | stop processing: n_tokens = 619, truncated = 0 2.01.210.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 121068069 2.01.210.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 2.01.259.322 I slot launch_slot_: id 0 | task 9322 | processing task, is_child = 0 2.02.643.998 I slot print_timing: id 0 | task 9322 | prompt eval time = 148.53 ms / 372 tokens ( 0.40 ms per token, 2504.60 tokens per second) 2.02.644.004 I slot print_timing: id 0 | task 9322 | eval time = 1236.13 ms / 120 tokens ( 10.39 ms per token, 96.27 tokens per second) 2.02.644.005 I slot print_timing: id 0 | task 9322 | total time = 1384.66 ms / 492 tokens 2.02.644.006 I slot print_timing: id 0 | task 9322 | graphs reused = 8816 2.02.644.007 I slot print_timing: id 0 | task 9322 | graph reallocs = 0 / 0 (same size) / (changed size) 2.02.644.036 I slot release: id 0 | task 9322 | stop processing: n_tokens = 523, truncated = 0 2.02.670.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 122539834 2.02.670.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.705 MiB) 2.02.720.156 I slot launch_slot_: id 0 | task 9445 | processing task, is_child = 0 2.05.348.937 I slot print_timing: id 0 | task 9445 | prompt eval time = 153.93 ms / 454 tokens ( 0.34 ms per token, 2949.32 tokens per second) 2.05.348.943 I slot print_timing: id 0 | task 9445 | eval time = 2474.83 ms / 243 tokens ( 10.23 ms per token, 97.78 tokens per second) 2.05.348.944 I slot print_timing: id 0 | task 9445 | total time = 2628.76 ms / 697 tokens 2.05.348.945 I slot print_timing: id 0 | task 9445 | graphs reused = 9056 2.05.348.945 I slot print_timing: id 0 | task 9445 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.348.977 I slot release: id 0 | task 9445 | stop processing: n_tokens = 728, truncated = 0 2.05.377.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 728, t_last = 125244774 2.05.377.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.455 MiB) 2.05.429.459 I slot launch_slot_: id 0 | task 9691 | processing task, is_child = 0 2.07.866.601 I slot print_timing: id 0 | task 9691 | prompt eval time = 146.73 ms / 354 tokens ( 0.41 ms per token, 2412.66 tokens per second) 2.07.866.606 I slot print_timing: id 0 | task 9691 | eval time = 2290.39 ms / 226 tokens ( 10.18 ms per token, 98.24 tokens per second) 2.07.866.607 I slot print_timing: id 0 | task 9691 | total time = 2437.12 ms / 580 tokens 2.07.866.608 I slot print_timing: id 0 | task 9691 | graphs reused = 9279 2.07.866.609 I slot print_timing: id 0 | task 9691 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.866.637 I slot release: id 0 | task 9691 | stop processing: n_tokens = 611, truncated = 0 2.07.888.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 127762435 2.07.888.959 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.07.943.088 I slot launch_slot_: id 0 | task 9920 | processing task, is_child = 0 2.09.713.817 I slot print_timing: id 0 | task 9920 | prompt eval time = 140.47 ms / 334 tokens ( 0.42 ms per token, 2377.77 tokens per second) 2.09.713.822 I slot print_timing: id 0 | task 9920 | eval time = 1630.24 ms / 158 tokens ( 10.38 ms per token, 96.30 tokens per second) 2.09.713.823 I slot print_timing: id 0 | task 9920 | total time = 1770.71 ms / 492 tokens 2.09.713.824 I slot print_timing: id 0 | task 9920 | graphs reused = 9434 2.09.713.825 I slot print_timing: id 0 | task 9920 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.713.855 I slot release: id 0 | task 9920 | stop processing: n_tokens = 523, truncated = 0 2.09.733.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 129609652 2.09.733.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.676 MiB) 2.09.784.020 I slot launch_slot_: id 0 | task 10081 | processing task, is_child = 0 2.12.059.746 I slot print_timing: id 0 | task 10081 | prompt eval time = 157.07 ms / 426 tokens ( 0.37 ms per token, 2712.11 tokens per second) 2.12.059.752 I slot print_timing: id 0 | task 10081 | eval time = 2118.64 ms / 209 tokens ( 10.19 ms per token, 98.18 tokens per second) 2.12.059.753 I slot print_timing: id 0 | task 10081 | total time = 2275.71 ms / 635 tokens 2.12.059.754 I slot print_timing: id 0 | task 10081 | graphs reused = 9640 2.12.059.754 I slot print_timing: id 0 | task 10081 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.059.785 I slot release: id 0 | task 10081 | stop processing: n_tokens = 666, truncated = 0 2.12.083.423 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 666, t_last = 131955582 2.12.083.480 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.12.144.535 I slot launch_slot_: id 0 | task 10293 | processing task, is_child = 0 2.13.782.681 I slot print_timing: id 0 | task 10293 | prompt eval time = 145.05 ms / 366 tokens ( 0.40 ms per token, 2523.34 tokens per second) 2.13.782.687 I slot print_timing: id 0 | task 10293 | eval time = 1493.08 ms / 144 tokens ( 10.44 ms per token, 95.78 tokens per second) 2.13.782.688 I slot print_timing: id 0 | task 10293 | total time = 1638.12 ms / 510 tokens 2.13.782.689 I slot print_timing: id 0 | task 10293 | graphs reused = 9781 2.13.782.690 I slot print_timing: id 0 | task 10293 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.782.723 I slot release: id 0 | task 10293 | stop processing: n_tokens = 541, truncated = 0 2.13.801.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 133678520 2.13.801.940 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.13.853.574 I slot launch_slot_: id 0 | task 10440 | processing task, is_child = 0 2.16.665.566 I slot print_timing: id 0 | task 10440 | prompt eval time = 167.61 ms / 462 tokens ( 0.36 ms per token, 2756.42 tokens per second) 2.16.665.571 I slot print_timing: id 0 | task 10440 | eval time = 2644.36 ms / 260 tokens ( 10.21 ms per token, 97.94 tokens per second) 2.16.665.572 I slot print_timing: id 0 | task 10440 | total time = 2811.97 ms / 722 tokens 2.16.665.573 I slot print_timing: id 0 | task 10440 | graphs reused = 10038 2.16.665.574 I slot print_timing: id 0 | task 10440 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.665.606 I slot release: id 0 | task 10440 | stop processing: n_tokens = 753, truncated = 0 2.16.684.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 753, t_last = 136561404 2.16.684.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.16.738.554 I slot launch_slot_: id 0 | task 10703 | processing task, is_child = 0 2.18.548.925 I slot print_timing: id 0 | task 10703 | prompt eval time = 150.41 ms / 396 tokens ( 0.38 ms per token, 2632.89 tokens per second) 2.18.548.930 I slot print_timing: id 0 | task 10703 | eval time = 1659.94 ms / 160 tokens ( 10.44 ms per token, 95.79 tokens per second) 2.18.548.931 I slot print_timing: id 0 | task 10703 | total time = 1810.35 ms / 556 tokens 2.18.548.932 I slot print_timing: id 0 | task 10703 | graphs reused = 10195 2.18.548.932 I slot print_timing: id 0 | task 10703 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.548.963 I slot release: id 0 | task 10703 | stop processing: n_tokens = 587, truncated = 0 2.18.577.169 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 138444760 2.18.617.162 I slot launch_slot_: id 0 | task 10866 | processing task, is_child = 0 2.20.402.593 I slot print_timing: id 0 | task 10866 | prompt eval time = 161.54 ms / 458 tokens ( 0.35 ms per token, 2835.12 tokens per second) 2.20.402.598 I slot print_timing: id 0 | task 10866 | eval time = 1623.87 ms / 161 tokens ( 10.15 ms per token, 98.53 tokens per second) 2.20.402.600 I slot print_timing: id 0 | task 10866 | total time = 1785.41 ms / 619 tokens 2.20.402.602 I slot print_timing: id 0 | task 10866 | graphs reused = 10353 2.20.402.603 I slot print_timing: id 0 | task 10866 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.402.635 I slot release: id 0 | task 10866 | stop processing: n_tokens = 650, truncated = 0 2.20.407.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 140298432 2.20.407.490 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.270 MiB) 2.20.457.219 I slot launch_slot_: id 0 | task 11030 | processing task, is_child = 0 2.22.679.391 I slot print_timing: id 0 | task 11030 | prompt eval time = 165.98 ms / 458 tokens ( 0.36 ms per token, 2759.37 tokens per second) 2.22.679.397 I slot print_timing: id 0 | task 11030 | eval time = 2056.17 ms / 196 tokens ( 10.54 ms per token, 94.84 tokens per second) 2.22.679.398 I slot print_timing: id 0 | task 11030 | total time = 2222.15 ms / 654 tokens 2.22.679.398 I slot print_timing: id 0 | task 11030 | graphs reused = 10546 2.22.679.399 I slot print_timing: id 0 | task 11030 | graph reallocs = 0 / 0 (same size) / (changed size) 2.22.679.430 I slot release: id 0 | task 11030 | stop processing: n_tokens = 685, truncated = 0 2.22.699.932 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 142575227 2.22.699.991 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.304 MiB) 2.22.753.801 I slot launch_slot_: id 0 | task 11229 | processing task, is_child = 0 2.25.834.296 I slot print_timing: id 0 | task 11229 | prompt eval time = 161.58 ms / 452 tokens ( 0.36 ms per token, 2797.38 tokens per second) 2.25.834.301 I slot print_timing: id 0 | task 11229 | eval time = 2918.89 ms / 284 tokens ( 10.31 ms per token, 96.95 tokens per second) 2.25.834.302 I slot print_timing: id 0 | task 11229 | total time = 3080.47 ms / 736 tokens 2.25.834.303 I slot print_timing: id 0 | task 11229 | graphs reused = 10827 2.25.834.304 I slot print_timing: id 0 | task 11229 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.834.337 I slot release: id 0 | task 11229 | stop processing: n_tokens = 767, truncated = 0 2.25.867.553 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 767, t_last = 145730134 2.25.867.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.526 MiB) 2.25.918.694 I slot launch_slot_: id 0 | task 11516 | processing task, is_child = 0 2.27.365.474 I slot print_timing: id 0 | task 11516 | prompt eval time = 153.92 ms / 404 tokens ( 0.38 ms per token, 2624.72 tokens per second) 2.27.365.480 I slot print_timing: id 0 | task 11516 | eval time = 1292.84 ms / 127 tokens ( 10.26 ms per token, 97.46 tokens per second) 2.27.365.481 I slot print_timing: id 0 | task 11516 | total time = 1446.76 ms / 531 tokens 2.27.365.482 I slot print_timing: id 0 | task 11516 | graphs reused = 10951 2.27.365.482 I slot print_timing: id 0 | task 11516 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.365.512 I slot release: id 0 | task 11516 | stop processing: n_tokens = 562, truncated = 0 2.27.384.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 147261310 2.27.384.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 2.27.434.317 I slot launch_slot_: id 0 | task 11646 | processing task, is_child = 0 2.28.805.146 I slot print_timing: id 0 | task 11646 | prompt eval time = 139.54 ms / 345 tokens ( 0.40 ms per token, 2472.46 tokens per second) 2.28.805.151 I slot print_timing: id 0 | task 11646 | eval time = 1231.27 ms / 122 tokens ( 10.18 ms per token, 98.27 tokens per second) 2.28.805.152 I slot print_timing: id 0 | task 11646 | total time = 1370.81 ms / 467 tokens 2.28.805.153 I slot print_timing: id 0 | task 11646 | graphs reused = 11071 2.28.805.154 I slot print_timing: id 0 | task 11646 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.805.181 I slot release: id 0 | task 11646 | stop processing: n_tokens = 498, truncated = 0 2.28.809.761 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 498, t_last = 148700978 2.28.809.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.547 MiB) 2.28.858.141 I slot launch_slot_: id 0 | task 11771 | processing task, is_child = 0 2.30.243.095 I slot print_timing: id 0 | task 11771 | prompt eval time = 164.70 ms / 430 tokens ( 0.38 ms per token, 2610.81 tokens per second) 2.30.243.100 I slot print_timing: id 0 | task 11771 | eval time = 1220.23 ms / 118 tokens ( 10.43 ms per token, 95.88 tokens per second) 2.30.243.101 I slot print_timing: id 0 | task 11771 | total time = 1384.93 ms / 548 tokens 2.30.243.102 I slot print_timing: id 0 | task 11771 | graphs reused = 11186 2.30.243.102 I slot print_timing: id 0 | task 11771 | graph reallocs = 0 / 0 (same size) / (changed size) 2.30.243.133 I slot release: id 0 | task 11771 | stop processing: n_tokens = 579, truncated = 0 2.30.282.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 150138931 2.30.282.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.110 MiB) 2.30.332.399 I slot launch_slot_: id 0 | task 11892 | processing task, is_child = 0 2.31.446.176 I slot print_timing: id 0 | task 11892 | prompt eval time = 135.00 ms / 316 tokens ( 0.43 ms per token, 2340.83 tokens per second) 2.31.446.181 I slot print_timing: id 0 | task 11892 | eval time = 978.76 ms / 97 tokens ( 10.20 ms per token, 98.08 tokens per second) 2.31.446.182 I slot print_timing: id 0 | task 11892 | total time = 1113.76 ms / 413 tokens 2.31.446.183 I slot print_timing: id 0 | task 11892 | graphs reused = 11281 2.31.446.184 I slot print_timing: id 0 | task 11892 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.446.211 I slot release: id 0 | task 11892 | stop processing: n_tokens = 444, truncated = 0 2.31.450.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 151342008 2.31.450.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 2.31.495.832 I slot launch_slot_: id 0 | task 11992 | processing task, is_child = 0 2.32.995.277 I slot print_timing: id 0 | task 11992 | prompt eval time = 140.96 ms / 354 tokens ( 0.40 ms per token, 2511.35 tokens per second) 2.32.995.282 I slot print_timing: id 0 | task 11992 | eval time = 1358.46 ms / 134 tokens ( 10.21 ms per token, 97.90 tokens per second) 2.32.995.283 I slot print_timing: id 0 | task 11992 | total time = 1499.42 ms / 488 tokens 2.32.995.284 I slot print_timing: id 0 | task 11992 | graphs reused = 11412 2.32.995.285 I slot print_timing: id 0 | task 11992 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.995.315 I slot release: id 0 | task 11992 | stop processing: n_tokens = 519, truncated = 0 2.33.015.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 519, t_last = 152891112 2.33.015.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.674 MiB) 2.33.065.104 I slot launch_slot_: id 0 | task 12129 | processing task, is_child = 0 2.34.383.531 I slot print_timing: id 0 | task 12129 | prompt eval time = 166.29 ms / 438 tokens ( 0.38 ms per token, 2633.89 tokens per second) 2.34.383.538 I slot print_timing: id 0 | task 12129 | eval time = 1152.11 ms / 111 tokens ( 10.47 ms per token, 95.48 tokens per second) 2.34.383.538 I slot print_timing: id 0 | task 12129 | total time = 1318.41 ms / 549 tokens 2.34.383.539 I slot print_timing: id 0 | task 12129 | graphs reused = 11520 2.34.383.540 I slot print_timing: id 0 | task 12129 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.383.574 I slot release: id 0 | task 12129 | stop processing: n_tokens = 580, truncated = 0 2.34.401.149 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 154279371 2.34.401.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.456 MiB) 2.34.452.955 I slot launch_slot_: id 0 | task 12243 | processing task, is_child = 0 2.35.633.750 I slot print_timing: id 0 | task 12243 | prompt eval time = 166.22 ms / 457 tokens ( 0.36 ms per token, 2749.40 tokens per second) 2.35.633.756 I slot print_timing: id 0 | task 12243 | eval time = 1014.56 ms / 100 tokens ( 10.25 ms per token, 97.58 tokens per second) 2.35.633.757 I slot print_timing: id 0 | task 12243 | total time = 1180.78 ms / 557 tokens 2.35.633.757 I slot print_timing: id 0 | task 12243 | graphs reused = 11617 2.35.633.758 I slot print_timing: id 0 | task 12243 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.633.789 I slot release: id 0 | task 12243 | stop processing: n_tokens = 588, truncated = 0 2.35.648.967 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 155529587 2.35.649.020 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.177 MiB) 2.35.701.334 I slot launch_slot_: id 0 | task 12346 | processing task, is_child = 0 2.37.024.612 I slot print_timing: id 0 | task 12346 | prompt eval time = 171.05 ms / 473 tokens ( 0.36 ms per token, 2765.29 tokens per second) 2.37.024.619 I slot print_timing: id 0 | task 12346 | eval time = 1152.21 ms / 113 tokens ( 10.29 ms per token, 97.20 tokens per second) 2.37.024.620 I slot print_timing: id 0 | task 12346 | total time = 1323.26 ms / 586 tokens 2.37.024.623 I slot print_timing: id 0 | task 12346 | graphs reused = 11727 2.37.024.624 I slot print_timing: id 0 | task 12346 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.024.660 I slot release: id 0 | task 12346 | stop processing: n_tokens = 617, truncated = 0 2.37.050.514 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 156920457 2.37.050.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 2.37.101.228 I slot launch_slot_: id 0 | task 12462 | processing task, is_child = 0 2.37.849.950 I slot print_timing: id 0 | task 12462 | prompt eval time = 176.25 ms / 476 tokens ( 0.37 ms per token, 2700.74 tokens per second) 2.37.849.956 I slot print_timing: id 0 | task 12462 | eval time = 572.46 ms / 55 tokens ( 10.60 ms per token, 94.33 tokens per second) 2.37.849.957 I slot print_timing: id 0 | task 12462 | total time = 748.70 ms / 531 tokens 2.37.849.958 I slot print_timing: id 0 | task 12462 | graphs reused = 11779 2.37.849.959 I slot print_timing: id 0 | task 12462 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.849.992 I slot release: id 0 | task 12462 | stop processing: n_tokens = 562, truncated = 0 2.37.877.124 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 562, t_last = 157745790 2.37.877.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.173 MiB) 2.37.929.662 I slot launch_slot_: id 0 | task 12520 | processing task, is_child = 0 2.39.316.603 I slot print_timing: id 0 | task 12520 | prompt eval time = 172.84 ms / 466 tokens ( 0.37 ms per token, 2696.21 tokens per second) 2.39.316.609 I slot print_timing: id 0 | task 12520 | eval time = 1214.09 ms / 118 tokens ( 10.38 ms per token, 96.37 tokens per second) 2.39.316.610 I slot print_timing: id 0 | task 12520 | total time = 1386.92 ms / 584 tokens 2.39.316.611 I slot print_timing: id 0 | task 12520 | graphs reused = 11894 2.39.316.612 I slot print_timing: id 0 | task 12520 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.316.644 I slot release: id 0 | task 12520 | stop processing: n_tokens = 615, truncated = 0 2.39.343.937 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 159212441 2.39.343.992 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.298 MiB) 2.39.394.768 I slot launch_slot_: id 0 | task 12641 | processing task, is_child = 0 2.40.552.558 I slot print_timing: id 0 | task 12641 | prompt eval time = 147.26 ms / 415 tokens ( 0.35 ms per token, 2818.09 tokens per second) 2.40.552.563 I slot print_timing: id 0 | task 12641 | eval time = 1010.51 ms / 101 tokens ( 10.11 ms per token, 98.96 tokens per second) 2.40.552.564 I slot print_timing: id 0 | task 12641 | total time = 1157.77 ms / 516 tokens 2.40.552.565 I slot print_timing: id 0 | task 12641 | graphs reused = 11992 2.40.552.566 I slot print_timing: id 0 | task 12641 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.552.595 I slot release: id 0 | task 12641 | stop processing: n_tokens = 547, truncated = 0 2.40.574.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 160448393 2.40.574.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.830 MiB) 2.40.634.065 I slot launch_slot_: id 0 | task 12745 | processing task, is_child = 0 2.41.707.898 I slot print_timing: id 0 | task 12745 | prompt eval time = 142.21 ms / 352 tokens ( 0.40 ms per token, 2475.28 tokens per second) 2.41.707.904 I slot print_timing: id 0 | task 12745 | eval time = 931.61 ms / 91 tokens ( 10.35 ms per token, 96.61 tokens per second) 2.41.707.905 I slot print_timing: id 0 | task 12745 | total time = 1073.81 ms / 443 tokens 2.41.707.906 I slot print_timing: id 0 | task 12745 | graphs reused = 12081 2.41.707.906 I slot print_timing: id 0 | task 12745 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.707.934 I slot release: id 0 | task 12745 | stop processing: n_tokens = 474, truncated = 0 2.41.749.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 474, t_last = 161603731 2.41.749.671 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.142 MiB) 2.41.795.518 I slot launch_slot_: id 0 | task 12839 | processing task, is_child = 0 2.43.710.029 I slot print_timing: id 0 | task 12839 | prompt eval time = 189.73 ms / 550 tokens ( 0.34 ms per token, 2898.83 tokens per second) 2.43.710.034 I slot print_timing: id 0 | task 12839 | eval time = 1724.76 ms / 169 tokens ( 10.27 ms per token, 97.40 tokens per second) 2.43.710.035 I slot print_timing: id 0 | task 12839 | total time = 1914.49 ms / 719 tokens 2.43.710.036 I slot print_timing: id 0 | task 12839 | graphs reused = 12248 2.43.710.037 I slot print_timing: id 0 | task 12839 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.710.073 I slot release: id 0 | task 12839 | stop processing: n_tokens = 750, truncated = 0 2.43.734.153 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 750, t_last = 163605871 2.43.734.214 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.237 MiB) 2.43.791.870 I slot launch_slot_: id 0 | task 13012 | processing task, is_child = 0 2.46.579.222 I slot print_timing: id 0 | task 13012 | prompt eval time = 220.27 ms / 772 tokens ( 0.29 ms per token, 3504.77 tokens per second) 2.46.579.228 I slot print_timing: id 0 | task 13012 | eval time = 2567.06 ms / 250 tokens ( 10.31 ms per token, 97.00 tokens per second) 2.46.579.229 I slot print_timing: id 0 | task 13012 | total time = 2787.33 ms / 1022 tokens 2.46.579.229 I slot print_timing: id 0 | task 13012 | graphs reused = 12495 2.46.579.230 I slot print_timing: id 0 | task 13012 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.579.271 I slot release: id 0 | task 13012 | stop processing: n_tokens = 1053, truncated = 0 2.46.597.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1053, t_last = 166475069 2.46.597.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.46.655.020 I slot launch_slot_: id 0 | task 13266 | processing task, is_child = 0 2.48.900.729 I slot print_timing: id 0 | task 13266 | prompt eval time = 220.58 ms / 683 tokens ( 0.32 ms per token, 3096.34 tokens per second) 2.48.900.735 I slot print_timing: id 0 | task 13266 | eval time = 2025.10 ms / 200 tokens ( 10.18 ms per token, 98.27 tokens per second) 2.48.900.736 I slot print_timing: id 0 | task 13266 | total time = 2245.69 ms / 883 tokens 2.48.900.737 I slot print_timing: id 0 | task 13266 | graphs reused = 12692 2.48.900.738 I slot print_timing: id 0 | task 13266 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.900.779 I slot release: id 0 | task 13266 | stop processing: n_tokens = 914, truncated = 0 2.48.906.069 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 914, t_last = 168796577 2.48.906.143 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.859 MiB) 2.48.966.646 I slot launch_slot_: id 0 | task 13470 | processing task, is_child = 0 2.51.622.972 I slot print_timing: id 0 | task 13470 | prompt eval time = 204.11 ms / 579 tokens ( 0.35 ms per token, 2836.68 tokens per second) 2.51.622.978 I slot print_timing: id 0 | task 13470 | eval time = 2452.19 ms / 238 tokens ( 10.35 ms per token, 96.65 tokens per second) 2.51.622.979 I slot print_timing: id 0 | task 13470 | total time = 2656.31 ms / 817 tokens 2.51.622.979 I slot print_timing: id 0 | task 13470 | graphs reused = 12927 2.51.622.980 I slot print_timing: id 0 | task 13470 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.623.016 I slot release: id 0 | task 13470 | stop processing: n_tokens = 848, truncated = 0 2.51.652.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 848, t_last = 171518814 2.51.652.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.270 MiB) 2.51.658.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.51.726.735 I slot launch_slot_: id 0 | task 13712 | processing task, is_child = 0 2.53.312.330 I slot print_timing: id 0 | task 13712 | prompt eval time = 173.48 ms / 500 tokens ( 0.35 ms per token, 2882.21 tokens per second) 2.53.312.336 I slot print_timing: id 0 | task 13712 | eval time = 1412.10 ms / 140 tokens ( 10.16 ms per token, 98.44 tokens per second) 2.53.312.337 I slot print_timing: id 0 | task 13712 | total time = 1585.57 ms / 640 tokens 2.53.312.338 I slot print_timing: id 0 | task 13712 | graphs reused = 13065 2.53.312.339 I slot print_timing: id 0 | task 13712 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.312.372 I slot release: id 0 | task 13712 | stop processing: n_tokens = 671, truncated = 0 2.53.335.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 671, t_last = 173208169 2.53.335.903 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.859 MiB) 2.53.387.394 I slot launch_slot_: id 0 | task 13855 | processing task, is_child = 0 2.56.032.974 I slot print_timing: id 0 | task 13855 | prompt eval time = 237.18 ms / 776 tokens ( 0.31 ms per token, 3271.72 tokens per second) 2.56.032.980 I slot print_timing: id 0 | task 13855 | eval time = 2408.38 ms / 235 tokens ( 10.29 ms per token, 97.16 tokens per second) 2.56.032.980 I slot print_timing: id 0 | task 13855 | total time = 2645.56 ms / 1011 tokens 2.56.032.981 I slot print_timing: id 0 | task 13855 | graphs reused = 13297 2.56.032.982 I slot print_timing: id 0 | task 13855 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.033.021 I slot release: id 0 | task 13855 | stop processing: n_tokens = 1042, truncated = 0 2.56.056.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1042, t_last = 175928819 2.56.056.657 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.331 MiB) 2.56.123.940 I slot launch_slot_: id 0 | task 14094 | processing task, is_child = 0 2.58.306.921 I slot print_timing: id 0 | task 14094 | prompt eval time = 170.12 ms / 504 tokens ( 0.34 ms per token, 2962.58 tokens per second) 2.58.306.927 I slot print_timing: id 0 | task 14094 | eval time = 2012.84 ms / 197 tokens ( 10.27 ms per token, 97.37 tokens per second) 2.58.306.928 I slot print_timing: id 0 | task 14094 | total time = 2182.96 ms / 701 tokens 2.58.306.928 I slot print_timing: id 0 | task 14094 | graphs reused = 13492 2.58.306.929 I slot print_timing: id 0 | task 14094 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.306.963 I slot release: id 0 | task 14094 | stop processing: n_tokens = 732, truncated = 0 2.58.312.554 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 178202761 2.58.312.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.422 MiB) 2.58.364.104 I slot launch_slot_: id 0 | task 14294 | processing task, is_child = 0 3.00.954.149 I slot print_timing: id 0 | task 14294 | prompt eval time = 210.83 ms / 633 tokens ( 0.33 ms per token, 3002.45 tokens per second) 3.00.954.154 I slot print_timing: id 0 | task 14294 | eval time = 2379.20 ms / 235 tokens ( 10.17 ms per token, 98.35 tokens per second) 3.00.954.155 I slot print_timing: id 0 | task 14294 | total time = 2590.03 ms / 868 tokens 3.00.954.156 I slot print_timing: id 0 | task 14294 | graphs reused = 13724 3.00.954.158 I slot print_timing: id 0 | task 14294 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.954.195 I slot release: id 0 | task 14294 | stop processing: n_tokens = 899, truncated = 0 3.00.959.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 899, t_last = 180849992 3.00.959.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.052 MiB) 3.01.021.144 I slot launch_slot_: id 0 | task 14533 | processing task, is_child = 0 3.02.556.563 I slot print_timing: id 0 | task 14533 | prompt eval time = 153.78 ms / 395 tokens ( 0.39 ms per token, 2568.54 tokens per second) 3.02.556.568 I slot print_timing: id 0 | task 14533 | eval time = 1381.62 ms / 134 tokens ( 10.39 ms per token, 96.26 tokens per second) 3.02.556.569 I slot print_timing: id 0 | task 14533 | total time = 1535.40 ms / 529 tokens 3.02.556.570 I slot print_timing: id 0 | task 14533 | graphs reused = 13855 3.02.556.571 I slot print_timing: id 0 | task 14533 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.556.600 I slot release: id 0 | task 14533 | stop processing: n_tokens = 560, truncated = 0 3.02.588.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 182452397 3.02.588.779 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.861 MiB) 3.02.634.829 I slot launch_slot_: id 0 | task 14670 | processing task, is_child = 0 3.05.148.654 I slot print_timing: id 0 | task 14670 | prompt eval time = 197.28 ms / 584 tokens ( 0.34 ms per token, 2960.27 tokens per second) 3.05.148.659 I slot print_timing: id 0 | task 14670 | eval time = 2316.52 ms / 229 tokens ( 10.16 ms per token, 98.42 tokens per second) 3.05.148.660 I slot print_timing: id 0 | task 14670 | total time = 2513.80 ms / 813 tokens 3.05.148.661 I slot print_timing: id 0 | task 14670 | graphs reused = 14081 3.05.148.662 I slot print_timing: id 0 | task 14670 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.148.699 I slot release: id 0 | task 14670 | stop processing: n_tokens = 844, truncated = 0 3.05.154.258 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 844, t_last = 185044497 3.05.154.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 3.05.210.052 I slot launch_slot_: id 0 | task 14903 | processing task, is_child = 0 3.08.038.237 I slot print_timing: id 0 | task 14903 | prompt eval time = 220.62 ms / 695 tokens ( 0.32 ms per token, 3150.21 tokens per second) 3.08.038.242 I slot print_timing: id 0 | task 14903 | eval time = 2607.55 ms / 254 tokens ( 10.31 ms per token, 97.03 tokens per second) 3.08.038.243 I slot print_timing: id 0 | task 14903 | total time = 2828.16 ms / 949 tokens 3.08.038.244 I slot print_timing: id 0 | task 14903 | graphs reused = 14332 3.08.038.245 I slot print_timing: id 0 | task 14903 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.038.284 I slot release: id 0 | task 14903 | stop processing: n_tokens = 980, truncated = 0 3.08.059.928 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 980, t_last = 187934081 3.08.060.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.926 MiB) 3.08.125.978 I slot launch_slot_: id 0 | task 15161 | processing task, is_child = 0 3.10.543.023 I slot print_timing: id 0 | task 15161 | prompt eval time = 228.18 ms / 769 tokens ( 0.30 ms per token, 3370.15 tokens per second) 3.10.543.028 I slot print_timing: id 0 | task 15161 | eval time = 2188.84 ms / 214 tokens ( 10.28 ms per token, 97.31 tokens per second) 3.10.543.030 I slot print_timing: id 0 | task 15161 | total time = 2417.02 ms / 983 tokens 3.10.543.030 I slot print_timing: id 0 | task 15161 | graphs reused = 14544 3.10.543.031 I slot print_timing: id 0 | task 15161 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.543.071 I slot release: id 0 | task 15161 | stop processing: n_tokens = 1014, truncated = 0 3.10.548.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1014, t_last = 190438869 3.10.548.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.490 MiB) 3.10.554.223 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.079 MiB) 3.10.615.560 I slot launch_slot_: id 0 | task 15379 | processing task, is_child = 0 3.12.492.422 I slot print_timing: id 0 | task 15379 | prompt eval time = 192.38 ms / 576 tokens ( 0.33 ms per token, 2994.15 tokens per second) 3.12.492.428 I slot print_timing: id 0 | task 15379 | eval time = 1684.47 ms / 166 tokens ( 10.21 ms per token, 97.95 tokens per second) 3.12.492.429 I slot print_timing: id 0 | task 15379 | total time = 1876.84 ms / 742 tokens 3.12.492.429 I slot print_timing: id 0 | task 15379 | graphs reused = 14707 3.12.492.430 I slot print_timing: id 0 | task 15379 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.492.471 I slot release: id 0 | task 15379 | stop processing: n_tokens = 773, truncated = 0 3.12.513.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 192388268 3.12.513.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.078 MiB) 3.12.568.374 I slot launch_slot_: id 0 | task 15549 | processing task, is_child = 0 3.15.613.276 I slot print_timing: id 0 | task 15549 | prompt eval time = 207.35 ms / 655 tokens ( 0.32 ms per token, 3158.85 tokens per second) 3.15.613.282 I slot print_timing: id 0 | task 15549 | eval time = 2837.53 ms / 275 tokens ( 10.36 ms per token, 96.56 tokens per second) 3.15.613.283 I slot print_timing: id 0 | task 15549 | total time = 3044.88 ms / 930 tokens 3.15.613.284 I slot print_timing: id 0 | task 15549 | graphs reused = 14979 3.15.613.285 I slot print_timing: id 0 | task 15549 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.613.322 I slot release: id 0 | task 15549 | stop processing: n_tokens = 961, truncated = 0 3.15.635.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 195509119 3.15.635.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.611 MiB) 3.15.692.702 I slot launch_slot_: id 0 | task 15828 | processing task, is_child = 0 3.17.349.147 I slot print_timing: id 0 | task 15828 | prompt eval time = 199.13 ms / 621 tokens ( 0.32 ms per token, 3118.57 tokens per second) 3.17.349.152 I slot print_timing: id 0 | task 15828 | eval time = 1457.30 ms / 145 tokens ( 10.12 ms per token, 98.81 tokens per second) 3.17.349.153 I slot print_timing: id 0 | task 15828 | total time = 1656.43 ms / 766 tokens 3.17.349.154 I slot print_timing: id 0 | task 15828 | graphs reused = 15121 3.17.349.155 I slot print_timing: id 0 | task 15828 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.349.193 I slot release: id 0 | task 15828 | stop processing: n_tokens = 797, truncated = 0 3.17.366.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 197244991 3.17.366.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.389 MiB) 3.17.419.173 I slot launch_slot_: id 0 | task 15977 | processing task, is_child = 0 3.19.795.252 I slot print_timing: id 0 | task 15977 | prompt eval time = 228.32 ms / 767 tokens ( 0.30 ms per token, 3359.38 tokens per second) 3.19.795.258 I slot print_timing: id 0 | task 15977 | eval time = 2147.74 ms / 208 tokens ( 10.38 ms per token, 96.38 tokens per second) 3.19.795.259 I slot print_timing: id 0 | task 15977 | total time = 2376.06 ms / 975 tokens 3.19.795.259 I slot print_timing: id 0 | task 15977 | graphs reused = 15327 3.19.795.260 I slot print_timing: id 0 | task 15977 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.795.306 I slot release: id 0 | task 15977 | stop processing: n_tokens = 1006, truncated = 0 3.19.815.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1006, t_last = 199691103 3.19.815.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.734 MiB) 3.19.873.560 I slot launch_slot_: id 0 | task 16189 | processing task, is_child = 0 3.22.372.658 I slot print_timing: id 0 | task 16189 | prompt eval time = 255.37 ms / 864 tokens ( 0.30 ms per token, 3383.31 tokens per second) 3.22.372.663 I slot print_timing: id 0 | task 16189 | eval time = 2243.71 ms / 220 tokens ( 10.25 ms per token, 97.61 tokens per second) 3.22.372.665 I slot print_timing: id 0 | task 16189 | total time = 2499.08 ms / 1084 tokens 3.22.372.665 I slot print_timing: id 0 | task 16189 | graphs reused = 15544 3.22.372.667 I slot print_timing: id 0 | task 16189 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.372.711 I slot release: id 0 | task 16189 | stop processing: n_tokens = 1115, truncated = 0 3.22.416.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1115, t_last = 202268509 3.22.416.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.642 MiB) 3.22.422.024 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.892 MiB) 3.22.488.460 I slot launch_slot_: id 0 | task 16413 | processing task, is_child = 0 3.24.253.469 I slot print_timing: id 0 | task 16413 | prompt eval time = 215.99 ms / 646 tokens ( 0.33 ms per token, 2990.85 tokens per second) 3.24.253.475 I slot print_timing: id 0 | task 16413 | eval time = 1549.00 ms / 151 tokens ( 10.33 ms per token, 96.84 tokens per second) 3.24.253.476 I slot print_timing: id 0 | task 16413 | total time = 1764.99 ms / 797 tokens 3.24.253.476 I slot print_timing: id 0 | task 16413 | graphs reused = 15692 3.24.253.477 I slot print_timing: id 0 | task 16413 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.253.514 I slot release: id 0 | task 16413 | stop processing: n_tokens = 828, truncated = 0 3.24.291.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 204149312 3.24.291.560 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.799 MiB) 3.24.348.912 I slot launch_slot_: id 0 | task 16568 | processing task, is_child = 0 3.27.050.008 I slot print_timing: id 0 | task 16568 | prompt eval time = 215.29 ms / 720 tokens ( 0.30 ms per token, 3344.37 tokens per second) 3.27.050.014 I slot print_timing: id 0 | task 16568 | eval time = 2485.79 ms / 240 tokens ( 10.40 ms per token, 96.15 tokens per second) 3.27.050.015 I slot print_timing: id 0 | task 16568 | total time = 2701.07 ms / 960 tokens 3.27.050.016 I slot print_timing: id 0 | task 16568 | graphs reused = 15929 3.27.050.017 I slot print_timing: id 0 | task 16568 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.050.060 I slot release: id 0 | task 16568 | stop processing: n_tokens = 991, truncated = 0 3.27.083.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 206945857 3.27.083.795 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.079 MiB) 3.27.148.723 I slot launch_slot_: id 0 | task 16812 | processing task, is_child = 0 3.29.483.031 I slot print_timing: id 0 | task 16812 | prompt eval time = 179.29 ms / 509 tokens ( 0.35 ms per token, 2838.99 tokens per second) 3.29.483.036 I slot print_timing: id 0 | task 16812 | eval time = 2155.00 ms / 214 tokens ( 10.12 ms per token, 98.84 tokens per second) 3.29.483.038 I slot print_timing: id 0 | task 16812 | total time = 2334.29 ms / 723 tokens 3.29.483.038 I slot print_timing: id 0 | task 16812 | graphs reused = 16141 3.29.483.039 I slot print_timing: id 0 | task 16812 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.483.073 I slot release: id 0 | task 16812 | stop processing: n_tokens = 754, truncated = 0 3.29.488.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 209378871 3.29.488.456 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.736 MiB) 3.29.540.161 I slot launch_slot_: id 0 | task 17029 | processing task, is_child = 0 3.32.540.322 I slot print_timing: id 0 | task 17029 | prompt eval time = 196.98 ms / 581 tokens ( 0.34 ms per token, 2949.60 tokens per second) 3.32.540.327 I slot print_timing: id 0 | task 17029 | eval time = 2803.16 ms / 273 tokens ( 10.31 ms per token, 97.03 tokens per second) 3.32.540.328 I slot print_timing: id 0 | task 17029 | total time = 3000.14 ms / 854 tokens 3.32.540.329 I slot print_timing: id 0 | task 17029 | graphs reused = 16411 3.32.540.330 I slot print_timing: id 0 | task 17029 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.540.367 I slot release: id 0 | task 17029 | stop processing: n_tokens = 885, truncated = 0 3.32.569.782 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 885, t_last = 212436165 3.32.569.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.610 MiB) 3.32.636.925 I slot launch_slot_: id 0 | task 17306 | processing task, is_child = 0 3.35.411.943 I slot print_timing: id 0 | task 17306 | prompt eval time = 257.67 ms / 925 tokens ( 0.28 ms per token, 3589.90 tokens per second) 3.35.411.949 I slot print_timing: id 0 | task 17306 | eval time = 2517.33 ms / 245 tokens ( 10.32 ms per token, 96.93 tokens per second) 3.35.411.950 I slot print_timing: id 0 | task 17306 | total time = 2775.00 ms / 1170 tokens 3.35.411.951 I slot print_timing: id 0 | task 17306 | graphs reused = 16653 3.35.411.952 I slot print_timing: id 0 | task 17306 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.411.998 I slot release: id 0 | task 17306 | stop processing: n_tokens = 1201, truncated = 0 3.35.429.461 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1201, t_last = 215307795 3.35.429.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.327 MiB) 3.35.488.091 I slot launch_slot_: id 0 | task 17555 | processing task, is_child = 0 3.38.502.627 I slot print_timing: id 0 | task 17555 | prompt eval time = 254.23 ms / 885 tokens ( 0.29 ms per token, 3481.11 tokens per second) 3.38.502.632 I slot print_timing: id 0 | task 17555 | eval time = 2760.29 ms / 271 tokens ( 10.22 ms per token, 97.82 tokens per second) 3.38.502.633 I slot print_timing: id 0 | task 17555 | total time = 3014.52 ms / 1156 tokens 3.38.502.634 I slot print_timing: id 0 | task 17555 | graphs reused = 16921 3.38.502.635 I slot print_timing: id 0 | task 17555 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.502.680 I slot release: id 0 | task 17555 | stop processing: n_tokens = 1187, truncated = 0 3.38.507.619 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1187, t_last = 218398477 3.38.507.701 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.209 MiB) 3.38.571.506 I slot launch_slot_: id 0 | task 17830 | processing task, is_child = 0 3.40.632.128 I slot print_timing: id 0 | task 17830 | prompt eval time = 149.72 ms / 392 tokens ( 0.38 ms per token, 2618.19 tokens per second) 3.40.632.133 I slot print_timing: id 0 | task 17830 | eval time = 1910.88 ms / 185 tokens ( 10.39 ms per token, 96.29 tokens per second) 3.40.632.134 I slot print_timing: id 0 | task 17830 | total time = 2060.61 ms / 577 tokens 3.40.632.135 I slot print_timing: id 0 | task 17830 | graphs reused = 17103 3.40.632.136 I slot print_timing: id 0 | task 17830 | graph reallocs = 0 / 0 (same size) / (changed size) 3.40.632.165 I slot release: id 0 | task 17830 | stop processing: n_tokens = 608, truncated = 0 3.40.653.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 608, t_last = 220527962 3.40.653.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.685 MiB) 3.40.703.964 I slot launch_slot_: id 0 | task 18018 | processing task, is_child = 0 3.42.836.096 I slot print_timing: id 0 | task 18018 | prompt eval time = 134.84 ms / 331 tokens ( 0.41 ms per token, 2454.76 tokens per second) 3.42.836.102 I slot print_timing: id 0 | task 18018 | eval time = 1997.27 ms / 196 tokens ( 10.24 ms per token, 97.63 tokens per second) 3.42.836.103 I slot print_timing: id 0 | task 18018 | total time = 2132.11 ms / 527 tokens 3.42.836.104 I slot print_timing: id 0 | task 18018 | graphs reused = 17296 3.42.836.105 I slot print_timing: id 0 | task 18018 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.836.135 I slot release: id 0 | task 18018 | stop processing: n_tokens = 558, truncated = 0 3.42.852.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 222731932 3.42.852.504 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.338 MiB) 3.42.903.109 I slot launch_slot_: id 0 | task 18217 | processing task, is_child = 0 3.44.943.865 I slot print_timing: id 0 | task 18217 | prompt eval time = 142.20 ms / 357 tokens ( 0.40 ms per token, 2510.53 tokens per second) 3.44.943.870 I slot print_timing: id 0 | task 18217 | eval time = 1898.53 ms / 185 tokens ( 10.32 ms per token, 96.92 tokens per second) 3.44.943.871 I slot print_timing: id 0 | task 18217 | total time = 2040.73 ms / 542 tokens 3.44.943.872 I slot print_timing: id 0 | task 18217 | graphs reused = 17478 3.44.943.873 I slot print_timing: id 0 | task 18217 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.943.901 I slot release: id 0 | task 18217 | stop processing: n_tokens = 573, truncated = 0 3.44.968.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 573, t_last = 224839699 3.44.968.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.274 MiB) 3.45.028.148 I slot launch_slot_: id 0 | task 18405 | processing task, is_child = 0 3.46.612.413 I slot print_timing: id 0 | task 18405 | prompt eval time = 138.55 ms / 315 tokens ( 0.44 ms per token, 2273.53 tokens per second) 3.46.612.420 I slot print_timing: id 0 | task 18405 | eval time = 1445.69 ms / 143 tokens ( 10.18 ms per token, 98.22 tokens per second) 3.46.612.421 I slot print_timing: id 0 | task 18405 | total time = 1584.24 ms / 458 tokens 3.46.612.422 I slot print_timing: id 0 | task 18405 | graphs reused = 17619 3.46.612.422 I slot print_timing: id 0 | task 18405 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.612.451 I slot release: id 0 | task 18405 | stop processing: n_tokens = 489, truncated = 0 3.46.632.942 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 226508248 3.46.632.989 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.488 MiB) 3.46.683.735 I slot launch_slot_: id 0 | task 18551 | processing task, is_child = 0 3.47.774.091 I slot print_timing: id 0 | task 18551 | prompt eval time = 143.76 ms / 378 tokens ( 0.38 ms per token, 2629.46 tokens per second) 3.47.774.097 I slot print_timing: id 0 | task 18551 | eval time = 946.58 ms / 92 tokens ( 10.40 ms per token, 96.14 tokens per second) 3.47.774.098 I slot print_timing: id 0 | task 18551 | total time = 1090.34 ms / 470 tokens 3.47.774.099 I slot print_timing: id 0 | task 18551 | graphs reused = 17709 3.47.774.099 I slot print_timing: id 0 | task 18551 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.774.131 I slot release: id 0 | task 18551 | stop processing: n_tokens = 501, truncated = 0 3.47.778.731 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 227669928 3.47.778.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.341 MiB) 3.47.834.849 I slot launch_slot_: id 0 | task 18646 | processing task, is_child = 0 3.48.251.702 I slot print_timing: id 0 | task 18646 | prompt eval time = 132.28 ms / 295 tokens ( 0.45 ms per token, 2230.20 tokens per second) 3.48.251.707 I slot print_timing: id 0 | task 18646 | eval time = 284.56 ms / 28 tokens ( 10.54 ms per token, 94.88 tokens per second) 3.48.251.708 I slot print_timing: id 0 | task 18646 | total time = 416.83 ms / 323 tokens 3.48.251.710 I slot print_timing: id 0 | task 18646 | graphs reused = 17735 3.48.251.710 I slot print_timing: id 0 | task 18646 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.251.736 I slot release: id 0 | task 18646 | stop processing: n_tokens = 354, truncated = 0 3.48.271.780 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 228147534 3.48.271.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.48.321.081 I slot launch_slot_: id 0 | task 18677 | processing task, is_child = 0 3.49.282.675 I slot print_timing: id 0 | task 18677 | prompt eval time = 138.19 ms / 337 tokens ( 0.41 ms per token, 2438.69 tokens per second) 3.49.282.681 I slot print_timing: id 0 | task 18677 | eval time = 823.38 ms / 82 tokens ( 10.17 ms per token, 98.37 tokens per second) 3.49.282.682 I slot print_timing: id 0 | task 18677 | total time = 961.57 ms / 419 tokens 3.49.282.682 I slot print_timing: id 0 | task 18677 | graphs reused = 17815 3.49.282.683 I slot print_timing: id 0 | task 18677 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.282.710 I slot release: id 0 | task 18677 | stop processing: n_tokens = 450, truncated = 0 3.49.287.447 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 229178508 3.49.287.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.869 MiB) 3.49.339.948 I slot launch_slot_: id 0 | task 18762 | processing task, is_child = 0 3.51.232.249 I slot print_timing: id 0 | task 18762 | prompt eval time = 135.47 ms / 325 tokens ( 0.42 ms per token, 2399.04 tokens per second) 3.51.232.255 I slot print_timing: id 0 | task 18762 | eval time = 1756.81 ms / 172 tokens ( 10.27 ms per token, 97.34 tokens per second) 3.51.232.256 I slot print_timing: id 0 | task 18762 | total time = 1892.28 ms / 497 tokens 3.51.232.257 I slot print_timing: id 0 | task 18762 | graphs reused = 17984 3.51.232.258 I slot print_timing: id 0 | task 18762 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.232.288 I slot release: id 0 | task 18762 | stop processing: n_tokens = 528, truncated = 0 3.51.262.037 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.061 3.51.301.804 I slot launch_slot_: id 0 | task 18937 | processing task, is_child = 0 3.52.011.054 I slot print_timing: id 0 | task 18937 | prompt eval time = 123.55 ms / 264 tokens ( 0.47 ms per token, 2136.79 tokens per second) 3.52.011.060 I slot print_timing: id 0 | task 18937 | eval time = 585.68 ms / 57 tokens ( 10.46 ms per token, 95.62 tokens per second) 3.52.011.061 I slot print_timing: id 0 | task 18937 | total time = 709.23 ms / 321 tokens 3.52.011.062 I slot print_timing: id 0 | task 18937 | graphs reused = 18039 3.52.011.062 I slot print_timing: id 0 | task 18937 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.011.089 I slot release: id 0 | task 18937 | stop processing: n_tokens = 352, truncated = 0 3.52.015.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 231906886 3.52.015.997 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.52.065.298 I slot launch_slot_: id 0 | task 18997 | processing task, is_child = 0 3.53.206.806 I slot print_timing: id 0 | task 18997 | prompt eval time = 137.45 ms / 331 tokens ( 0.42 ms per token, 2408.18 tokens per second) 3.53.206.812 I slot print_timing: id 0 | task 18997 | eval time = 1004.04 ms / 99 tokens ( 10.25 ms per token, 97.61 tokens per second) 3.53.206.813 I slot print_timing: id 0 | task 18997 | total time = 1141.49 ms / 430 tokens 3.53.206.814 I slot print_timing: id 0 | task 18997 | graphs reused = 18136 3.53.206.815 I slot print_timing: id 0 | task 18997 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.206.846 I slot release: id 0 | task 18997 | stop processing: n_tokens = 461, truncated = 0 3.53.242.873 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 461, t_last = 233102643 3.53.242.919 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.149 MiB) 3.53.292.037 I slot launch_slot_: id 0 | task 19099 | processing task, is_child = 0 3.55.198.554 I slot print_timing: id 0 | task 19099 | prompt eval time = 141.19 ms / 333 tokens ( 0.42 ms per token, 2358.51 tokens per second) 3.55.198.560 I slot print_timing: id 0 | task 19099 | eval time = 1765.31 ms / 173 tokens ( 10.26 ms per token, 97.43 tokens per second) 3.55.198.561 I slot print_timing: id 0 | task 19099 | total time = 1906.50 ms / 506 tokens 3.55.198.562 I slot print_timing: id 0 | task 19099 | graphs reused = 18306 3.55.198.563 I slot print_timing: id 0 | task 19099 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.198.591 I slot release: id 0 | task 19099 | stop processing: n_tokens = 537, truncated = 0 3.55.228.279 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 235094388 3.55.228.329 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.402 MiB) 3.55.281.400 I slot launch_slot_: id 0 | task 19275 | processing task, is_child = 0 3.56.352.443 I slot print_timing: id 0 | task 19275 | prompt eval time = 142.24 ms / 346 tokens ( 0.41 ms per token, 2432.47 tokens per second) 3.56.352.449 I slot print_timing: id 0 | task 19275 | eval time = 928.78 ms / 90 tokens ( 10.44 ms per token, 95.82 tokens per second) 3.56.352.450 I slot print_timing: id 0 | task 19275 | total time = 1071.02 ms / 436 tokens 3.56.352.452 I slot print_timing: id 0 | task 19275 | graphs reused = 18394 3.56.352.453 I slot print_timing: id 0 | task 19275 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.352.483 I slot release: id 0 | task 19275 | stop processing: n_tokens = 467, truncated = 0 3.56.367.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 467, t_last = 236248280 3.56.367.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.465 MiB) 3.56.421.492 I slot launch_slot_: id 0 | task 19368 | processing task, is_child = 0 3.57.657.901 I slot print_timing: id 0 | task 19368 | prompt eval time = 138.68 ms / 325 tokens ( 0.43 ms per token, 2343.56 tokens per second) 3.57.657.906 I slot print_timing: id 0 | task 19368 | eval time = 1097.71 ms / 109 tokens ( 10.16 ms per token, 98.39 tokens per second) 3.57.657.907 I slot print_timing: id 0 | task 19368 | total time = 1236.39 ms / 434 tokens 3.57.657.908 I slot print_timing: id 0 | task 19368 | graphs reused = 18501 3.57.657.909 I slot print_timing: id 0 | task 19368 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.657.936 I slot release: id 0 | task 19368 | stop processing: n_tokens = 465, truncated = 0 3.57.672.835 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 237553734 3.57.672.880 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.57.722.434 I slot launch_slot_: id 0 | task 19480 | processing task, is_child = 0 3.59.543.228 I slot print_timing: id 0 | task 19480 | prompt eval time = 135.98 ms / 322 tokens ( 0.42 ms per token, 2367.98 tokens per second) 3.59.543.233 I slot print_timing: id 0 | task 19480 | eval time = 1684.79 ms / 165 tokens ( 10.27 ms per token, 97.34 tokens per second) 3.59.543.234 I slot print_timing: id 0 | task 19480 | total time = 1820.77 ms / 487 tokens 3.59.543.235 I slot print_timing: id 0 | task 19480 | graphs reused = 18663 3.59.543.236 I slot print_timing: id 0 | task 19480 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.543.267 I slot release: id 0 | task 19480 | stop processing: n_tokens = 518, truncated = 0 3.59.548.321 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 518, t_last = 239439064 3.59.548.370 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.59.599.308 I slot launch_slot_: id 0 | task 19648 | processing task, is_child = 0 4.02.746.670 I slot print_timing: id 0 | task 19648 | n_gen = 296, tg = 98.10 t/s, tg_3s = 98.43 t/s 4.03.428.558 I slot print_timing: id 0 | task 19648 | prompt eval time = 140.23 ms / 338 tokens ( 0.41 ms per token, 2410.33 tokens per second) 4.03.428.563 I slot print_timing: id 0 | task 19648 | eval time = 3689.00 ms / 362 tokens ( 10.22 ms per token, 97.86 tokens per second) 4.03.428.564 I slot print_timing: id 0 | task 19648 | total time = 3829.23 ms / 700 tokens 4.03.428.565 I slot print_timing: id 0 | task 19648 | graphs reused = 19022 4.03.428.565 I slot print_timing: id 0 | task 19648 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.428.594 I slot release: id 0 | task 19648 | stop processing: n_tokens = 731, truncated = 0 4.03.443.477 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 243324391 4.03.484.199 I slot launch_slot_: id 0 | task 20013 | processing task, is_child = 0 4.05.956.514 I slot print_timing: id 0 | task 20013 | prompt eval time = 140.18 ms / 347 tokens ( 0.40 ms per token, 2475.42 tokens per second) 4.05.956.519 I slot print_timing: id 0 | task 20013 | eval time = 2332.12 ms / 228 tokens ( 10.27 ms per token, 97.34 tokens per second) 4.05.956.520 I slot print_timing: id 0 | task 20013 | total time = 2472.30 ms / 575 tokens 4.05.956.522 I slot print_timing: id 0 | task 20013 | graphs reused = 19247 4.05.956.522 I slot print_timing: id 0 | task 20013 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.956.551 I slot release: id 0 | task 20013 | stop processing: n_tokens = 606, truncated = 0 4.05.983.929 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 606, t_last = 245852349 4.05.983.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 4.06.034.474 I slot launch_slot_: id 0 | task 20244 | processing task, is_child = 0 4.06.997.420 I slot print_timing: id 0 | task 20244 | prompt eval time = 137.06 ms / 331 tokens ( 0.41 ms per token, 2415.00 tokens per second) 4.06.997.425 I slot print_timing: id 0 | task 20244 | eval time = 825.87 ms / 82 tokens ( 10.20 ms per token, 98.08 tokens per second) 4.06.997.426 I slot print_timing: id 0 | task 20244 | total time = 962.93 ms / 413 tokens 4.06.997.427 I slot print_timing: id 0 | task 20244 | graphs reused = 19327 4.06.997.428 I slot print_timing: id 0 | task 20244 | graph reallocs = 0 / 0 (same size) / (changed size) 4.06.997.457 I slot release: id 0 | task 20244 | stop processing: n_tokens = 444, truncated = 0 4.07.017.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 246893255 4.07.017.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.215 MiB) 4.07.067.805 I slot launch_slot_: id 0 | task 20329 | processing task, is_child = 0 4.09.823.944 I slot print_timing: id 0 | task 20329 | prompt eval time = 140.53 ms / 345 tokens ( 0.41 ms per token, 2454.97 tokens per second) 4.09.823.950 I slot print_timing: id 0 | task 20329 | eval time = 2615.59 ms / 255 tokens ( 10.30 ms per token, 97.11 tokens per second) 4.09.823.951 I slot print_timing: id 0 | task 20329 | total time = 2756.12 ms / 600 tokens 4.09.823.952 I slot print_timing: id 0 | task 20329 | graphs reused = 19579 4.09.823.953 I slot print_timing: id 0 | task 20329 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.823.982 I slot release: id 0 | task 20329 | stop processing: n_tokens = 631, truncated = 0 4.09.856.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 631, t_last = 249719780 4.09.856.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.624 MiB) 4.09.916.586 I slot launch_slot_: id 0 | task 20587 | processing task, is_child = 0 4.11.596.759 I slot print_timing: id 0 | task 20587 | prompt eval time = 136.32 ms / 320 tokens ( 0.43 ms per token, 2347.35 tokens per second) 4.11.596.765 I slot print_timing: id 0 | task 20587 | eval time = 1543.83 ms / 152 tokens ( 10.22 ms per token, 97.81 tokens per second) 4.11.596.766 I slot print_timing: id 0 | task 20587 | total time = 1680.15 ms / 472 tokens 4.11.596.767 I slot print_timing: id 0 | task 20587 | graphs reused = 19729 4.11.596.768 I slot print_timing: id 0 | task 20587 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.596.796 I slot release: id 0 | task 20587 | stop processing: n_tokens = 503, truncated = 0 4.11.601.167 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 251492594 4.11.601.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 4.11.653.173 I slot launch_slot_: id 0 | task 20742 | processing task, is_child = 0 4.12.419.355 I slot print_timing: id 0 | task 20742 | prompt eval time = 131.39 ms / 297 tokens ( 0.44 ms per token, 2260.45 tokens per second) 4.12.419.360 I slot print_timing: id 0 | task 20742 | eval time = 634.77 ms / 59 tokens ( 10.94 ms per token, 91.37 tokens per second) 4.12.419.362 I slot print_timing: id 0 | task 20742 | total time = 766.16 ms / 356 tokens 4.12.419.362 I slot print_timing: id 0 | task 20742 | graphs reused = 19786 4.12.419.363 I slot print_timing: id 0 | task 20742 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.419.389 I slot release: id 0 | task 20742 | stop processing: n_tokens = 387, truncated = 0 4.12.453.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 252315187 4.12.453.925 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 4.12.505.077 I slot launch_slot_: id 0 | task 20804 | processing task, is_child = 0 4.14.853.833 I slot print_timing: id 0 | task 20804 | prompt eval time = 140.02 ms / 343 tokens ( 0.41 ms per token, 2449.62 tokens per second) 4.14.853.839 I slot print_timing: id 0 | task 20804 | eval time = 2208.72 ms / 219 tokens ( 10.13 ms per token, 98.70 tokens per second) 4.14.853.840 I slot print_timing: id 0 | task 20804 | total time = 2348.74 ms / 562 tokens 4.14.853.841 I slot print_timing: id 0 | task 20804 | graphs reused = 20002 4.14.853.842 I slot print_timing: id 0 | task 20804 | graph reallocs = 0 / 0 (same size) / (changed size) 4.14.853.871 I slot release: id 0 | task 20804 | stop processing: n_tokens = 593, truncated = 0 4.14.892.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 593, t_last = 254749668 4.14.932.022 I slot launch_slot_: id 0 | task 21026 | processing task, is_child = 0 4.17.023.188 I slot print_timing: id 0 | task 21026 | prompt eval time = 147.60 ms / 371 tokens ( 0.40 ms per token, 2513.60 tokens per second) 4.17.023.193 I slot print_timing: id 0 | task 21026 | eval time = 1943.55 ms / 188 tokens ( 10.39 ms per token, 96.22 tokens per second) 4.17.023.195 I slot print_timing: id 0 | task 21026 | total time = 2091.15 ms / 559 tokens 4.17.023.195 I slot print_timing: id 0 | task 21026 | graphs reused = 20187 4.17.023.196 I slot print_timing: id 0 | task 21026 | graph reallocs = 0 / 0 (same size) / (changed size) 4.17.023.227 I slot release: id 0 | task 21026 | stop processing: n_tokens = 590, truncated = 0 4.17.051.983 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 590, t_last = 256919024 4.17.052.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 4.17.103.765 I slot launch_slot_: id 0 | task 21217 | processing task, is_child = 0 4.18.610.980 I slot print_timing: id 0 | task 21217 | prompt eval time = 136.69 ms / 292 tokens ( 0.47 ms per token, 2136.28 tokens per second) 4.18.610.986 I slot print_timing: id 0 | task 21217 | eval time = 1370.49 ms / 137 tokens ( 10.08 ms per token, 99.23 tokens per second) 4.18.610.987 I slot print_timing: id 0 | task 21217 | total time = 1507.18 ms / 429 tokens 4.18.610.988 I slot print_timing: id 0 | task 21217 | graphs reused = 20322 4.18.610.989 I slot print_timing: id 0 | task 21217 | graph reallocs = 0 / 0 (same size) / (changed size) 4.18.611.017 I slot release: id 0 | task 21217 | stop processing: n_tokens = 460, truncated = 0 4.18.652.705 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 460, t_last = 258506815 4.18.652.752 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.431 MiB) 4.18.712.984 I slot launch_slot_: id 0 | task 21357 | processing task, is_child = 0 4.19.981.969 I slot print_timing: id 0 | task 21357 | prompt eval time = 130.06 ms / 301 tokens ( 0.43 ms per token, 2314.32 tokens per second) 4.19.981.975 I slot print_timing: id 0 | task 21357 | eval time = 1138.91 ms / 111 tokens ( 10.35 ms per token, 96.58 tokens per second) 4.19.981.976 I slot print_timing: id 0 | task 21357 | total time = 1268.97 ms / 412 tokens 4.19.981.976 I slot print_timing: id 0 | task 21357 | graphs reused = 20431 4.19.981.977 I slot print_timing: id 0 | task 21357 | graph reallocs = 0 / 0 (same size) / (changed size) 4.19.982.005 I slot release: id 0 | task 21357 | stop processing: n_tokens = 443, truncated = 0 4.20.024.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 259877802 4.20.024.771 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.313 MiB) 4.20.071.699 I slot launch_slot_: id 0 | task 21471 | processing task, is_child = 0 4.20.636.029 I slot print_timing: id 0 | task 21471 | prompt eval time = 132.44 ms / 303 tokens ( 0.44 ms per token, 2287.91 tokens per second) 4.20.636.035 I slot print_timing: id 0 | task 21471 | eval time = 431.88 ms / 42 tokens ( 10.53 ms per token, 94.93 tokens per second) 4.20.636.036 I slot print_timing: id 0 | task 21471 | total time = 564.31 ms / 345 tokens 4.20.636.037 I slot print_timing: id 0 | task 21471 | graphs reused = 20471 4.20.636.038 I slot print_timing: id 0 | task 21471 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.636.064 I slot release: id 0 | task 21471 | stop processing: n_tokens = 376, truncated = 0 4.20.640.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 376, t_last = 260531861 4.20.640.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.875 MiB) 4.20.693.457 I slot launch_slot_: id 0 | task 21516 | processing task, is_child = 0 4.23.083.812 I slot print_timing: id 0 | task 21516 | prompt eval time = 139.18 ms / 321 tokens ( 0.43 ms per token, 2306.40 tokens per second) 4.23.083.817 I slot print_timing: id 0 | task 21516 | eval time = 2251.16 ms / 223 tokens ( 10.14 ms per token, 98.62 tokens per second) 4.23.083.818 I slot print_timing: id 0 | task 21516 | total time = 2390.34 ms / 544 tokens 4.23.083.819 I slot print_timing: id 0 | task 21516 | graphs reused = 20691 4.23.083.820 I slot print_timing: id 0 | task 21516 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.083.849 I slot release: id 0 | task 21516 | stop processing: n_tokens = 575, truncated = 0 4.23.105.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 575, t_last = 262979646 4.23.106.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.518 MiB) 4.23.155.245 I slot launch_slot_: id 0 | task 21742 | processing task, is_child = 0 4.24.073.886 I slot print_timing: id 0 | task 21742 | prompt eval time = 137.63 ms / 322 tokens ( 0.43 ms per token, 2339.67 tokens per second) 4.24.073.892 I slot print_timing: id 0 | task 21742 | eval time = 781.00 ms / 76 tokens ( 10.41 ms per token, 96.03 tokens per second) 4.24.073.893 I slot print_timing: id 0 | task 21742 | total time = 918.62 ms / 398 tokens 4.24.073.893 I slot print_timing: id 0 | task 21742 | graphs reused = 20765 4.24.073.894 I slot print_timing: id 0 | task 21742 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.073.926 I slot release: id 0 | task 21742 | stop processing: n_tokens = 429, truncated = 0 4.24.118.357 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 263969724 4.24.118.398 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 4.24.167.746 I slot launch_slot_: id 0 | task 21821 | processing task, is_child = 0 4.25.357.241 I slot print_timing: id 0 | task 21821 | prompt eval time = 139.00 ms / 323 tokens ( 0.43 ms per token, 2323.69 tokens per second) 4.25.357.246 I slot print_timing: id 0 | task 21821 | eval time = 1050.47 ms / 102 tokens ( 10.40 ms per token, 96.15 tokens per second) 4.25.357.247 I slot print_timing: id 0 | task 21821 | total time = 1189.47 ms / 425 tokens 4.25.357.248 I slot print_timing: id 0 | task 21821 | graphs reused = 20865 4.25.357.249 I slot print_timing: id 0 | task 21821 | graph reallocs = 0 / 0 (same size) / (changed size) 4.25.357.279 I slot release: id 0 | task 21821 | stop processing: n_tokens = 456, truncated = 0 4.25.402.130 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 456, t_last = 265253077 4.25.402.182 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.423 MiB) 4.25.460.720 I slot launch_slot_: id 0 | task 21926 | processing task, is_child = 0 4.28.598.611 I slot print_timing: id 0 | task 21926 | n_gen = 295, tg = 97.90 t/s, tg_3s = 98.24 t/s 4.28.692.819 I slot print_timing: id 0 | task 21926 | prompt eval time = 134.93 ms / 321 tokens ( 0.42 ms per token, 2379.06 tokens per second) 4.28.692.824 I slot print_timing: id 0 | task 21926 | eval time = 3097.15 ms / 304 tokens ( 10.22 ms per token, 97.83 tokens per second) 4.28.692.825 I slot print_timing: id 0 | task 21926 | total time = 3232.08 ms / 625 tokens 4.28.692.826 I slot print_timing: id 0 | task 21926 | graphs reused = 21166 4.28.692.827 I slot print_timing: id 0 | task 21926 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.692.858 I slot release: id 0 | task 21926 | stop processing: n_tokens = 656, truncated = 0 4.28.721.226 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 656, t_last = 268588656 4.28.721.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.796 MiB) 4.28.772.722 I slot launch_slot_: id 0 | task 22233 | processing task, is_child = 0 4.30.254.193 I slot print_timing: id 0 | task 22233 | prompt eval time = 138.22 ms / 322 tokens ( 0.43 ms per token, 2329.70 tokens per second) 4.30.254.198 I slot print_timing: id 0 | task 22233 | eval time = 1343.24 ms / 133 tokens ( 10.18 ms per token, 98.27 tokens per second) 4.30.254.199 I slot print_timing: id 0 | task 22233 | total time = 1481.45 ms / 455 tokens 4.30.254.200 I slot print_timing: id 0 | task 22233 | graphs reused = 21297 4.30.254.201 I slot print_timing: id 0 | task 22233 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.254.229 I slot release: id 0 | task 22233 | stop processing: n_tokens = 486, truncated = 0 4.30.258.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 486, t_last = 270150027 4.30.258.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.171 MiB) 4.30.313.379 I slot launch_slot_: id 0 | task 22369 | processing task, is_child = 0 4.31.037.931 I slot print_timing: id 0 | task 22369 | prompt eval time = 140.82 ms / 337 tokens ( 0.42 ms per token, 2393.07 tokens per second) 4.31.037.936 I slot print_timing: id 0 | task 22369 | eval time = 583.71 ms / 59 tokens ( 10.06 ms per token, 99.36 tokens per second) 4.31.037.938 I slot print_timing: id 0 | task 22369 | total time = 724.53 ms / 396 tokens 4.31.037.939 I slot print_timing: id 0 | task 22369 | graphs reused = 21354 4.31.037.940 I slot print_timing: id 0 | task 22369 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.037.967 I slot release: id 0 | task 22369 | stop processing: n_tokens = 427, truncated = 0 4.31.055.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 270933765 4.31.055.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.31.107.301 I slot launch_slot_: id 0 | task 22431 | processing task, is_child = 0 4.31.964.769 I slot print_timing: id 0 | task 22431 | prompt eval time = 147.81 ms / 325 tokens ( 0.45 ms per token, 2198.69 tokens per second) 4.31.964.775 I slot print_timing: id 0 | task 22431 | eval time = 709.63 ms / 69 tokens ( 10.44 ms per token, 95.82 tokens per second) 4.31.964.776 I slot print_timing: id 0 | task 22431 | total time = 857.45 ms / 394 tokens 4.31.964.778 I slot print_timing: id 0 | task 22431 | graphs reused = 21421 4.31.964.779 I slot print_timing: id 0 | task 22431 | graph reallocs = 0 / 0 (same size) / (changed size) 4.31.964.808 I slot release: id 0 | task 22431 | stop processing: n_tokens = 425, truncated = 0 4.31.992.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 271860606 4.31.992.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.576 MiB) 4.32.044.725 I slot launch_slot_: id 0 | task 22503 | processing task, is_child = 0 4.33.768.926 I slot print_timing: id 0 | task 22503 | prompt eval time = 139.76 ms / 331 tokens ( 0.42 ms per token, 2368.31 tokens per second) 4.33.768.931 I slot print_timing: id 0 | task 22503 | eval time = 1584.42 ms / 153 tokens ( 10.42 ms per token, 95.93 tokens per second) 4.33.768.932 I slot print_timing: id 0 | task 22503 | total time = 1724.18 ms / 484 tokens 4.33.768.933 I slot print_timing: id 0 | task 22503 | graphs reused = 21571 4.33.768.934 I slot print_timing: id 0 | task 22503 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.768.962 I slot release: id 0 | task 22503 | stop processing: n_tokens = 515, truncated = 0 4.33.783.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 515, t_last = 273664759 4.33.783.939 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.016 MiB) 4.33.829.121 I slot launch_slot_: id 0 | task 22659 | processing task, is_child = 0 4.35.103.511 I slot print_timing: id 0 | task 22659 | prompt eval time = 136.10 ms / 336 tokens ( 0.41 ms per token, 2468.68 tokens per second) 4.35.103.516 I slot print_timing: id 0 | task 22659 | eval time = 1138.26 ms / 114 tokens ( 10.07 ms per token, 99.27 tokens per second) 4.35.103.518 I slot print_timing: id 0 | task 22659 | total time = 1274.37 ms / 450 tokens 4.35.103.518 I slot print_timing: id 0 | task 22659 | graphs reused = 21683 4.35.103.519 I slot print_timing: id 0 | task 22659 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.103.549 I slot release: id 0 | task 22659 | stop processing: n_tokens = 481, truncated = 0 4.35.108.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 274999347 4.35.108.166 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.512 MiB) 4.35.153.320 I slot launch_slot_: id 0 | task 22776 | processing task, is_child = 0 4.35.680.218 I slot print_timing: id 0 | task 22776 | prompt eval time = 140.69 ms / 349 tokens ( 0.40 ms per token, 2480.68 tokens per second) 4.35.680.224 I slot print_timing: id 0 | task 22776 | eval time = 386.19 ms / 38 tokens ( 10.44 ms per token, 95.81 tokens per second) 4.35.680.225 I slot print_timing: id 0 | task 22776 | total time = 526.88 ms / 387 tokens 4.35.680.225 I slot print_timing: id 0 | task 22776 | graphs reused = 21719 4.35.680.227 I slot print_timing: id 0 | task 22776 | graph reallocs = 0 / 0 (same size) / (changed size) 4.35.680.255 I slot release: id 0 | task 22776 | stop processing: n_tokens = 418, truncated = 0 4.35.717.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 275576052 4.35.717.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.920 MiB) 4.35.768.195 I slot launch_slot_: id 0 | task 22817 | processing task, is_child = 0 4.38.916.325 I slot print_timing: id 0 | task 22817 | n_gen = 294, tg = 97.38 t/s, tg_3s = 97.71 t/s 4.40.170.781 I slot print_timing: id 0 | task 22817 | prompt eval time = 139.32 ms / 336 tokens ( 0.41 ms per token, 2411.73 tokens per second) 4.40.170.787 I slot print_timing: id 0 | task 22817 | eval time = 4263.25 ms / 415 tokens ( 10.30 ms per token, 97.11 tokens per second) 4.40.170.788 I slot print_timing: id 0 | task 22817 | total time = 4402.57 ms / 751 tokens 4.40.170.789 I slot print_timing: id 0 | task 22817 | graphs reused = 22130 4.40.170.789 I slot print_timing: id 0 | task 22817 | graph reallocs = 0 / 0 (same size) / (changed size) 4.40.170.819 I slot release: id 0 | task 22817 | stop processing: n_tokens = 782, truncated = 0 4.40.187.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 782, t_last = 280066617 4.40.187.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.297 MiB) 4.40.241.632 I slot launch_slot_: id 0 | task 23235 | processing task, is_child = 0 4.43.386.125 I slot print_timing: id 0 | task 23235 | n_gen = 296, tg = 98.18 t/s, tg_3s = 98.52 t/s 4.44.172.148 I slot print_timing: id 0 | task 23235 | prompt eval time = 139.87 ms / 349 tokens ( 0.40 ms per token, 2495.17 tokens per second) 4.44.172.154 I slot print_timing: id 0 | task 23235 | eval time = 3790.63 ms / 372 tokens ( 10.22 ms per token, 97.87 tokens per second) 4.44.172.155 I slot print_timing: id 0 | task 23235 | total time = 3930.50 ms / 721 tokens 4.44.172.156 I slot print_timing: id 0 | task 23235 | graphs reused = 22499 4.44.172.158 I slot print_timing: id 0 | task 23235 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.172.189 I slot release: id 0 | task 23235 | stop processing: n_tokens = 752, truncated = 0 4.44.199.476 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 752, t_last = 284067986 4.44.199.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.108 MiB) 4.44.254.188 I slot launch_slot_: id 0 | task 23610 | processing task, is_child = 0 4.44.999.819 I slot print_timing: id 0 | task 23610 | prompt eval time = 139.89 ms / 349 tokens ( 0.40 ms per token, 2494.84 tokens per second) 4.44.999.824 I slot print_timing: id 0 | task 23610 | eval time = 605.72 ms / 59 tokens ( 10.44 ms per token, 95.75 tokens per second) 4.44.999.825 I slot print_timing: id 0 | task 23610 | total time = 745.61 ms / 408 tokens 4.44.999.826 I slot print_timing: id 0 | task 23610 | graphs reused = 22556 4.44.999.827 I slot print_timing: id 0 | task 23610 | graph reallocs = 0 / 0 (same size) / (changed size) 4.44.999.854 I slot release: id 0 | task 23610 | stop processing: n_tokens = 439, truncated = 0 4.45.025.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 284895652 4.45.025.310 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.046 MiB) 4.45.073.823 I slot launch_slot_: id 0 | task 23672 | processing task, is_child = 0 4.47.451.354 I slot print_timing: id 0 | task 23672 | prompt eval time = 147.21 ms / 385 tokens ( 0.38 ms per token, 2615.26 tokens per second) 4.47.451.359 I slot print_timing: id 0 | task 23672 | eval time = 2230.30 ms / 221 tokens ( 10.14 ms per token, 98.64 tokens per second) 4.47.451.361 I slot print_timing: id 0 | task 23672 | total time = 2377.51 ms / 606 tokens 4.47.451.361 I slot print_timing: id 0 | task 23672 | graphs reused = 22774 4.47.451.362 I slot print_timing: id 0 | task 23672 | graph reallocs = 0 / 0 (same size) / (changed size) 4.47.451.392 I slot release: id 0 | task 23672 | stop processing: n_tokens = 637, truncated = 0 4.47.469.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 287347189 4.47.469.505 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.703 MiB) 4.47.519.825 I slot launch_slot_: id 0 | task 23896 | processing task, is_child = 0 4.48.247.941 I slot print_timing: id 0 | task 23896 | prompt eval time = 139.14 ms / 328 tokens ( 0.42 ms per token, 2357.30 tokens per second) 4.48.247.947 I slot print_timing: id 0 | task 23896 | eval time = 588.95 ms / 57 tokens ( 10.52 ms per token, 95.08 tokens per second) 4.48.247.948 I slot print_timing: id 0 | task 23896 | total time = 728.10 ms / 385 tokens 4.48.247.948 I slot print_timing: id 0 | task 23896 | graphs reused = 22829 4.48.247.949 I slot print_timing: id 0 | task 23896 | graph reallocs = 0 / 0 (same size) / (changed size) 4.48.247.978 I slot release: id 0 | task 23896 | stop processing: n_tokens = 416, truncated = 0