$ C:\quantdiff\llama.cpp\bin\llama-server.exe -m C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-IQ4_XS.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.096.842 I srv llama_server: initializing ... 0.00.096.848 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.096.993 I srv init_listene: The UI is disabled 0.00.096.996 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.097.088 W srv llama_server: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.108.239 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-IQ4_XS.gguf' 0.00.915.880 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.00.915.895 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.00.915.920 W model has unused tensor blk.32.attn_q.weight (size = 35651584 bytes) -- ignoring 0.00.915.929 W model has unused tensor blk.32.attn_k.weight (size = 4456448 bytes) -- ignoring 0.00.915.938 W model has unused tensor blk.32.attn_v.weight (size = 4456448 bytes) -- ignoring 0.00.915.971 W model has unused tensor blk.32.attn_output.weight (size = 17825792 bytes) -- ignoring 0.00.915.981 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.915.990 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.915.999 W model has unused tensor blk.32.ffn_gate.weight (size = 53477376 bytes) -- ignoring 0.00.916.008 W model has unused tensor blk.32.ffn_down.weight (size = 53477376 bytes) -- ignoring 0.00.916.016 W model has unused tensor blk.32.ffn_up.weight (size = 53477376 bytes) -- ignoring 0.00.916.026 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring 0.00.916.036 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.00.916.045 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.00.916.073 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.02.503.848 I cmn init: llama threadpool init, n_threads = 8 0.02.587.549 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.592.174 I srv llama_server: model loaded 0.02.592.180 I srv llama_server: listening on http://127.0.0.1:8089 0.04.555.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.556.176 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.247.158 I slot print_timing: id 0 | task 0 | prompt eval time = 203.82 ms / 368 tokens ( 0.55 ms per token, 1805.55 tokens per second) 0.05.247.164 I slot print_timing: id 0 | task 0 | eval time = 487.15 ms / 53 tokens ( 9.37 ms per token, 106.74 tokens per second) 0.05.247.165 I slot print_timing: id 0 | task 0 | total time = 690.97 ms / 421 tokens 0.05.247.172 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.05.247.173 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.247.202 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.05.275.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 5152307 0.05.299.414 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.05.791.981 I slot print_timing: id 0 | task 56 | prompt eval time = 109.93 ms / 322 tokens ( 0.34 ms per token, 2929.11 tokens per second) 0.05.791.985 I slot print_timing: id 0 | task 56 | eval time = 382.62 ms / 42 tokens ( 9.33 ms per token, 107.16 tokens per second) 0.05.791.986 I slot print_timing: id 0 | task 56 | total time = 492.55 ms / 364 tokens 0.05.791.987 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.05.791.988 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.792.014 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.05.817.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5697119 0.05.841.461 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.06.336.489 I slot print_timing: id 0 | task 101 | prompt eval time = 111.86 ms / 365 tokens ( 0.31 ms per token, 3262.92 tokens per second) 0.06.336.496 I slot print_timing: id 0 | task 101 | eval time = 383.15 ms / 42 tokens ( 9.35 ms per token, 107.01 tokens per second) 0.06.336.497 I slot print_timing: id 0 | task 101 | total time = 495.01 ms / 407 tokens 0.06.336.498 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.06.336.498 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.336.526 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.06.364.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6241631 0.06.388.717 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.06.896.380 I slot print_timing: id 0 | task 146 | prompt eval time = 116.31 ms / 397 tokens ( 0.29 ms per token, 3413.15 tokens per second) 0.06.896.386 I slot print_timing: id 0 | task 146 | eval time = 391.33 ms / 43 tokens ( 9.32 ms per token, 107.33 tokens per second) 0.06.896.387 I slot print_timing: id 0 | task 146 | total time = 507.64 ms / 440 tokens 0.06.896.387 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.06.896.388 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.896.417 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.06.911.522 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 0.06.935.791 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.07.550.793 I slot print_timing: id 0 | task 192 | prompt eval time = 112.90 ms / 383 tokens ( 0.29 ms per token, 3392.44 tokens per second) 0.07.550.799 I slot print_timing: id 0 | task 192 | eval time = 502.08 ms / 55 tokens ( 9.30 ms per token, 107.55 tokens per second) 0.07.550.800 I slot print_timing: id 0 | task 192 | total time = 614.98 ms / 438 tokens 0.07.550.801 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.07.550.801 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.550.828 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.07.565.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7455934 0.07.590.225 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 0.08.206.873 I slot print_timing: id 0 | task 250 | prompt eval time = 114.85 ms / 372 tokens ( 0.31 ms per token, 3238.92 tokens per second) 0.08.206.879 I slot print_timing: id 0 | task 250 | eval time = 501.77 ms / 55 tokens ( 9.29 ms per token, 107.62 tokens per second) 0.08.206.880 I slot print_timing: id 0 | task 250 | total time = 616.63 ms / 427 tokens 0.08.206.881 I slot print_timing: id 0 | task 250 | graphs reused = 279 0.08.206.882 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.206.910 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 0.08.222.341 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8112015 0.08.246.879 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 0.08.880.587 I slot print_timing: id 0 | task 308 | prompt eval time = 129.65 ms / 422 tokens ( 0.31 ms per token, 3254.92 tokens per second) 0.08.880.592 I slot print_timing: id 0 | task 308 | eval time = 504.04 ms / 55 tokens ( 9.33 ms per token, 107.13 tokens per second) 0.08.880.593 I slot print_timing: id 0 | task 308 | total time = 633.69 ms / 477 tokens 0.08.880.595 I slot print_timing: id 0 | task 308 | graphs reused = 332 0.08.880.596 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.880.624 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 0.08.895.840 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 8785730 0.08.924.663 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 0.09.726.476 I slot print_timing: id 0 | task 366 | prompt eval time = 132.07 ms / 470 tokens ( 0.28 ms per token, 3558.69 tokens per second) 0.09.726.482 I slot print_timing: id 0 | task 366 | eval time = 669.72 ms / 72 tokens ( 9.43 ms per token, 106.01 tokens per second) 0.09.726.483 I slot print_timing: id 0 | task 366 | total time = 801.79 ms / 542 tokens 0.09.726.484 I slot print_timing: id 0 | task 366 | graphs reused = 401 0.09.726.485 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.726.515 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 0.09.749.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 9631620 0.09.776.315 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 0.10.314.517 I slot print_timing: id 0 | task 441 | prompt eval time = 110.13 ms / 345 tokens ( 0.32 ms per token, 3132.63 tokens per second) 0.10.314.522 I slot print_timing: id 0 | task 441 | eval time = 428.05 ms / 47 tokens ( 9.31 ms per token, 107.46 tokens per second) 0.10.314.523 I slot print_timing: id 0 | task 441 | total time = 538.18 ms / 392 tokens 0.10.314.524 I slot print_timing: id 0 | task 441 | graphs reused = 446 0.10.314.525 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.314.551 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 0.10.342.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 10219656 0.10.367.246 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 0.10.851.271 I slot print_timing: id 0 | task 491 | prompt eval time = 110.47 ms / 364 tokens ( 0.30 ms per token, 3295.01 tokens per second) 0.10.851.277 I slot print_timing: id 0 | task 491 | eval time = 373.54 ms / 41 tokens ( 9.34 ms per token, 107.09 tokens per second) 0.10.851.279 I slot print_timing: id 0 | task 491 | total time = 484.00 ms / 405 tokens 0.10.851.279 I slot print_timing: id 0 | task 491 | graphs reused = 485 0.10.851.280 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.851.307 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 0.10.876.055 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 10756412 0.10.900.948 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 0.11.614.555 I slot print_timing: id 0 | task 535 | prompt eval time = 114.73 ms / 376 tokens ( 0.31 ms per token, 3277.23 tokens per second) 0.11.614.560 I slot print_timing: id 0 | task 535 | eval time = 598.86 ms / 62 tokens ( 9.82 ms per token, 101.86 tokens per second) 0.11.614.561 I slot print_timing: id 0 | task 535 | total time = 713.59 ms / 438 tokens 0.11.614.562 I slot print_timing: id 0 | task 535 | graphs reused = 545 0.11.614.563 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.614.589 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 0.11.637.595 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 11519694 0.11.662.835 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 0.12.208.383 I slot print_timing: id 0 | task 600 | prompt eval time = 117.33 ms / 412 tokens ( 0.28 ms per token, 3511.31 tokens per second) 0.12.208.388 I slot print_timing: id 0 | task 600 | eval time = 428.19 ms / 47 tokens ( 9.31 ms per token, 107.43 tokens per second) 0.12.208.389 I slot print_timing: id 0 | task 600 | total time = 545.52 ms / 459 tokens 0.12.208.390 I slot print_timing: id 0 | task 600 | graphs reused = 590 0.12.208.391 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.208.420 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 0.12.230.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 12113525 0.12.256.740 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 0.12.935.572 I slot print_timing: id 0 | task 650 | prompt eval time = 112.26 ms / 376 tokens ( 0.30 ms per token, 3349.28 tokens per second) 0.12.935.577 I slot print_timing: id 0 | task 650 | eval time = 566.55 ms / 62 tokens ( 9.29 ms per token, 107.67 tokens per second) 0.12.935.579 I slot print_timing: id 0 | task 650 | total time = 678.81 ms / 438 tokens 0.12.935.580 I slot print_timing: id 0 | task 650 | graphs reused = 650 0.12.935.580 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.935.608 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 0.12.952.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12840713 0.12.977.152 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 0.13.568.376 I slot print_timing: id 0 | task 715 | prompt eval time = 115.40 ms / 378 tokens ( 0.31 ms per token, 3275.53 tokens per second) 0.13.568.382 I slot print_timing: id 0 | task 715 | eval time = 475.80 ms / 52 tokens ( 9.33 ms per token, 107.19 tokens per second) 0.13.568.383 I slot print_timing: id 0 | task 715 | total time = 591.20 ms / 430 tokens 0.13.568.383 I slot print_timing: id 0 | task 715 | graphs reused = 700 0.13.568.384 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.568.411 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 0.13.595.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 13473516 0.13.620.136 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 0.14.294.878 I slot print_timing: id 0 | task 770 | prompt eval time = 115.00 ms / 367 tokens ( 0.31 ms per token, 3191.36 tokens per second) 0.14.294.884 I slot print_timing: id 0 | task 770 | eval time = 559.72 ms / 58 tokens ( 9.82 ms per token, 101.84 tokens per second) 0.14.294.885 I slot print_timing: id 0 | task 770 | total time = 674.72 ms / 425 tokens 0.14.294.886 I slot print_timing: id 0 | task 770 | graphs reused = 756 0.14.294.886 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.294.914 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 0.14.314.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 14200019 0.14.339.948 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 0.14.916.960 I slot print_timing: id 0 | task 831 | prompt eval time = 110.29 ms / 347 tokens ( 0.32 ms per token, 3146.34 tokens per second) 0.14.916.966 I slot print_timing: id 0 | task 831 | eval time = 466.70 ms / 51 tokens ( 9.33 ms per token, 107.13 tokens per second) 0.14.916.967 I slot print_timing: id 0 | task 831 | total time = 576.99 ms / 398 tokens 0.14.916.968 I slot print_timing: id 0 | task 831 | graphs reused = 805 0.14.916.969 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.916.996 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 0.14.937.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 14822101 0.14.971.879 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 0.15.457.093 I slot print_timing: id 0 | task 885 | prompt eval time = 111.09 ms / 369 tokens ( 0.30 ms per token, 3321.51 tokens per second) 0.15.457.099 I slot print_timing: id 0 | task 885 | eval time = 374.10 ms / 41 tokens ( 9.35 ms per token, 106.92 tokens per second) 0.15.457.100 I slot print_timing: id 0 | task 885 | total time = 485.19 ms / 410 tokens 0.15.457.100 I slot print_timing: id 0 | task 885 | graphs reused = 844 0.15.457.101 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.457.127 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 0.15.483.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 15362232 0.15.507.979 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 0.15.990.778 I slot print_timing: id 0 | task 929 | prompt eval time = 109.21 ms / 352 tokens ( 0.31 ms per token, 3223.18 tokens per second) 0.15.990.784 I slot print_timing: id 0 | task 929 | eval time = 373.57 ms / 41 tokens ( 9.34 ms per token, 107.08 tokens per second) 0.15.990.785 I slot print_timing: id 0 | task 929 | total time = 482.78 ms / 393 tokens 0.15.990.786 I slot print_timing: id 0 | task 929 | graphs reused = 883 0.15.990.788 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.990.815 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 0.16.013.806 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 15895920 0.16.038.459 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 0.16.512.514 I slot print_timing: id 0 | task 973 | prompt eval time = 109.10 ms / 349 tokens ( 0.31 ms per token, 3198.99 tokens per second) 0.16.512.520 I slot print_timing: id 0 | task 973 | eval time = 364.94 ms / 40 tokens ( 9.36 ms per token, 106.87 tokens per second) 0.16.512.521 I slot print_timing: id 0 | task 973 | total time = 474.03 ms / 389 tokens 0.16.512.521 I slot print_timing: id 0 | task 973 | graphs reused = 921 0.16.512.522 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.512.548 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 0.16.529.735 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 16417654 0.16.561.408 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 0.17.292.599 I slot print_timing: id 0 | task 1016 | prompt eval time = 116.46 ms / 384 tokens ( 0.30 ms per token, 3297.24 tokens per second) 0.17.292.605 I slot print_timing: id 0 | task 1016 | eval time = 614.71 ms / 63 tokens ( 9.91 ms per token, 100.86 tokens per second) 0.17.292.606 I slot print_timing: id 0 | task 1016 | total time = 731.17 ms / 447 tokens 0.17.292.607 I slot print_timing: id 0 | task 1016 | graphs reused = 982 0.17.292.608 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.292.637 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 0.17.310.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 17197743 0.17.335.909 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 0.17.960.964 I slot print_timing: id 0 | task 1082 | prompt eval time = 114.24 ms / 356 tokens ( 0.32 ms per token, 3116.16 tokens per second) 0.17.960.970 I slot print_timing: id 0 | task 1082 | eval time = 510.79 ms / 54 tokens ( 9.64 ms per token, 103.76 tokens per second) 0.17.960.971 I slot print_timing: id 0 | task 1082 | total time = 625.03 ms / 410 tokens 0.17.960.972 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 0.17.960.973 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.961.004 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 0.17.975.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 17866109 0.18.002.386 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 0.18.763.183 I slot print_timing: id 0 | task 1139 | prompt eval time = 120.01 ms / 410 tokens ( 0.29 ms per token, 3416.27 tokens per second) 0.18.763.189 I slot print_timing: id 0 | task 1139 | eval time = 640.76 ms / 70 tokens ( 9.29 ms per token, 107.68 tokens per second) 0.18.763.190 I slot print_timing: id 0 | task 1139 | total time = 760.77 ms / 480 tokens 0.18.763.191 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 0.18.763.191 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.763.219 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 0.18.781.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 18668324 0.18.808.523 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 0.19.457.212 I slot print_timing: id 0 | task 1212 | prompt eval time = 117.55 ms / 385 tokens ( 0.31 ms per token, 3275.29 tokens per second) 0.19.457.218 I slot print_timing: id 0 | task 1212 | eval time = 531.12 ms / 58 tokens ( 9.32 ms per token, 107.32 tokens per second) 0.19.457.219 I slot print_timing: id 0 | task 1212 | total time = 648.67 ms / 443 tokens 0.19.457.220 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 0.19.457.221 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.457.247 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 0.19.486.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 19362352 0.19.511.685 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 0.20.282.490 I slot print_timing: id 0 | task 1273 | prompt eval time = 117.28 ms / 395 tokens ( 0.30 ms per token, 3368.07 tokens per second) 0.20.282.496 I slot print_timing: id 0 | task 1273 | eval time = 653.50 ms / 71 tokens ( 9.34 ms per token, 107.11 tokens per second) 0.20.282.497 I slot print_timing: id 0 | task 1273 | total time = 770.78 ms / 466 tokens 0.20.282.498 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 0.20.282.499 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.282.528 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 0.20.310.802 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 20187633 0.20.336.004 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 0.21.022.640 I slot print_timing: id 0 | task 1347 | prompt eval time = 118.89 ms / 430 tokens ( 0.28 ms per token, 3616.91 tokens per second) 0.21.022.646 I slot print_timing: id 0 | task 1347 | eval time = 567.73 ms / 62 tokens ( 9.31 ms per token, 107.45 tokens per second) 0.21.022.647 I slot print_timing: id 0 | task 1347 | total time = 686.62 ms / 492 tokens 0.21.022.647 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 0.21.022.648 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.022.676 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 0.21.041.728 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 20927781 0.21.073.960 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 0.21.761.704 I slot print_timing: id 0 | task 1412 | prompt eval time = 118.02 ms / 392 tokens ( 0.30 ms per token, 3321.50 tokens per second) 0.21.761.710 I slot print_timing: id 0 | task 1412 | eval time = 569.70 ms / 62 tokens ( 9.34 ms per token, 107.07 tokens per second) 0.21.761.711 I slot print_timing: id 0 | task 1412 | total time = 687.72 ms / 454 tokens 0.21.761.712 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 0.21.761.712 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.761.740 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 0.21.778.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 21666845 0.21.803.614 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 0.22.392.036 I slot print_timing: id 0 | task 1477 | prompt eval time = 110.59 ms / 350 tokens ( 0.32 ms per token, 3164.79 tokens per second) 0.22.392.042 I slot print_timing: id 0 | task 1477 | eval time = 477.81 ms / 52 tokens ( 9.37 ms per token, 106.74 tokens per second) 0.22.392.043 I slot print_timing: id 0 | task 1477 | total time = 588.40 ms / 402 tokens 0.22.392.044 I slot print_timing: id 0 | task 1477 | graphs reused = 1397 0.22.392.045 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.392.074 I slot release: id 0 | task 1477 | stop processing: n_tokens = 401, truncated = 0 0.22.405.605 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 22297179 0.22.430.712 I slot launch_slot_: id 0 | task 1532 | processing task, is_child = 0 0.23.109.050 I slot print_timing: id 0 | task 1532 | prompt eval time = 116.59 ms / 380 tokens ( 0.31 ms per token, 3259.40 tokens per second) 0.23.109.056 I slot print_timing: id 0 | task 1532 | eval time = 561.73 ms / 61 tokens ( 9.36 ms per token, 106.81 tokens per second) 0.23.109.057 I slot print_timing: id 0 | task 1532 | total time = 678.32 ms / 441 tokens 0.23.109.058 I slot print_timing: id 0 | task 1532 | graphs reused = 1456 0.23.109.059 I slot print_timing: id 0 | task 1532 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.109.085 I slot release: id 0 | task 1532 | stop processing: n_tokens = 440, truncated = 0 0.23.137.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 23014190 0.23.162.689 I slot launch_slot_: id 0 | task 1596 | processing task, is_child = 0 0.24.046.176 I slot print_timing: id 0 | task 1596 | prompt eval time = 120.05 ms / 410 tokens ( 0.29 ms per token, 3415.33 tokens per second) 0.24.046.182 I slot print_timing: id 0 | task 1596 | eval time = 763.42 ms / 80 tokens ( 9.66 ms per token, 103.48 tokens per second) 0.24.046.183 I slot print_timing: id 0 | task 1596 | total time = 883.47 ms / 490 tokens 0.24.046.184 I slot print_timing: id 0 | task 1596 | graphs reused = 1534 0.24.046.185 I slot print_timing: id 0 | task 1596 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.046.214 I slot release: id 0 | task 1596 | stop processing: n_tokens = 489, truncated = 0 0.24.072.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 23951319 0.24.098.420 I slot launch_slot_: id 0 | task 1679 | processing task, is_child = 0 0.24.835.797 I slot print_timing: id 0 | task 1679 | prompt eval time = 114.59 ms / 387 tokens ( 0.30 ms per token, 3377.38 tokens per second) 0.24.835.802 I slot print_timing: id 0 | task 1679 | eval time = 622.77 ms / 68 tokens ( 9.30 ms per token, 107.58 tokens per second) 0.24.835.803 I slot print_timing: id 0 | task 1679 | total time = 737.36 ms / 455 tokens 0.24.835.805 I slot print_timing: id 0 | task 1679 | graphs reused = 1600 0.24.835.806 I slot print_timing: id 0 | task 1679 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.835.833 I slot release: id 0 | task 1679 | stop processing: n_tokens = 454, truncated = 0 0.24.864.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 24740938 0.24.889.199 I slot launch_slot_: id 0 | task 1750 | processing task, is_child = 0 0.25.538.869 I slot print_timing: id 0 | task 1750 | prompt eval time = 110.22 ms / 358 tokens ( 0.31 ms per token, 3247.90 tokens per second) 0.25.538.874 I slot print_timing: id 0 | task 1750 | eval time = 539.42 ms / 59 tokens ( 9.30 ms per token, 107.52 tokens per second) 0.25.538.876 I slot print_timing: id 0 | task 1750 | total time = 649.65 ms / 417 tokens 0.25.538.877 I slot print_timing: id 0 | task 1750 | graphs reused = 1657 0.25.538.878 I slot print_timing: id 0 | task 1750 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.538.905 I slot release: id 0 | task 1750 | stop processing: n_tokens = 416, truncated = 0 0.25.564.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 25444011 0.25.589.050 I slot launch_slot_: id 0 | task 1812 | processing task, is_child = 0 0.26.241.075 I slot print_timing: id 0 | task 1812 | prompt eval time = 109.66 ms / 359 tokens ( 0.31 ms per token, 3273.79 tokens per second) 0.26.241.081 I slot print_timing: id 0 | task 1812 | eval time = 542.35 ms / 56 tokens ( 9.86 ms per token, 101.41 tokens per second) 0.26.241.081 I slot print_timing: id 0 | task 1812 | total time = 652.00 ms / 415 tokens 0.26.241.082 I slot print_timing: id 0 | task 1812 | graphs reused = 1711 0.26.241.083 I slot print_timing: id 0 | task 1812 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.241.109 I slot release: id 0 | task 1812 | stop processing: n_tokens = 414, truncated = 0 0.26.266.953 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 26146214 0.26.291.758 I slot launch_slot_: id 0 | task 1871 | processing task, is_child = 0 0.26.964.968 I slot print_timing: id 0 | task 1871 | prompt eval time = 114.65 ms / 387 tokens ( 0.30 ms per token, 3375.61 tokens per second) 0.26.964.974 I slot print_timing: id 0 | task 1871 | eval time = 558.54 ms / 61 tokens ( 9.31 ms per token, 107.42 tokens per second) 0.26.964.975 I slot print_timing: id 0 | task 1871 | total time = 673.19 ms / 448 tokens 0.26.964.975 I slot print_timing: id 0 | task 1871 | graphs reused = 1770 0.26.964.976 I slot print_timing: id 0 | task 1871 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.965.003 I slot release: id 0 | task 1871 | stop processing: n_tokens = 447, truncated = 0 0.26.982.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 26870108 0.27.007.290 I slot launch_slot_: id 0 | task 1935 | processing task, is_child = 0 0.27.709.427 I slot print_timing: id 0 | task 1935 | prompt eval time = 117.64 ms / 410 tokens ( 0.29 ms per token, 3485.21 tokens per second) 0.27.709.433 I slot print_timing: id 0 | task 1935 | eval time = 584.48 ms / 61 tokens ( 9.74 ms per token, 102.66 tokens per second) 0.27.709.434 I slot print_timing: id 0 | task 1935 | total time = 702.12 ms / 471 tokens 0.27.709.435 I slot print_timing: id 0 | task 1935 | graphs reused = 1829 0.27.709.435 I slot print_timing: id 0 | task 1935 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.709.465 I slot release: id 0 | task 1935 | stop processing: n_tokens = 470, truncated = 0 0.27.713.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 27614570 0.27.752.498 I slot launch_slot_: id 0 | task 1999 | processing task, is_child = 0 0.28.318.951 I slot print_timing: id 0 | task 1999 | prompt eval time = 109.44 ms / 351 tokens ( 0.31 ms per token, 3207.12 tokens per second) 0.28.318.957 I slot print_timing: id 0 | task 1999 | eval time = 456.99 ms / 50 tokens ( 9.33 ms per token, 107.22 tokens per second) 0.28.318.958 I slot print_timing: id 0 | task 1999 | total time = 566.43 ms / 401 tokens 0.28.318.959 I slot print_timing: id 0 | task 1999 | graphs reused = 1877 0.28.318.959 I slot print_timing: id 0 | task 1999 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.318.986 I slot release: id 0 | task 1999 | stop processing: n_tokens = 400, truncated = 0 0.28.337.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 28224091 0.28.362.613 I slot launch_slot_: id 0 | task 2052 | processing task, is_child = 0 0.30.545.631 I slot print_timing: id 0 | task 2052 | prompt eval time = 115.33 ms / 393 tokens ( 0.29 ms per token, 3407.73 tokens per second) 0.30.545.636 I slot print_timing: id 0 | task 2052 | eval time = 2067.67 ms / 224 tokens ( 9.27 ms per token, 107.85 tokens per second) 0.30.545.638 I slot print_timing: id 0 | task 2052 | total time = 2183.00 ms / 617 tokens 0.30.545.638 I slot print_timing: id 0 | task 2052 | graphs reused = 2098 0.30.545.639 I slot print_timing: id 0 | task 2052 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.545.667 I slot release: id 0 | task 2052 | stop processing: n_tokens = 616, truncated = 0 0.30.559.788 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 30450773 0.30.585.827 I slot launch_slot_: id 0 | task 2279 | processing task, is_child = 0 0.30.965.440 I slot print_timing: id 0 | task 2279 | prompt eval time = 107.88 ms / 321 tokens ( 0.34 ms per token, 2975.47 tokens per second) 0.30.965.446 I slot print_timing: id 0 | task 2279 | eval time = 271.71 ms / 30 tokens ( 9.37 ms per token, 106.73 tokens per second) 0.30.965.447 I slot print_timing: id 0 | task 2279 | total time = 379.59 ms / 351 tokens 0.30.965.448 I slot print_timing: id 0 | task 2279 | graphs reused = 2126 0.30.965.448 I slot print_timing: id 0 | task 2279 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.965.474 I slot release: id 0 | task 2279 | stop processing: n_tokens = 350, truncated = 0 0.30.978.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 30870579 0.31.003.373 I slot launch_slot_: id 0 | task 2312 | processing task, is_child = 0 0.31.595.407 I slot print_timing: id 0 | task 2312 | prompt eval time = 108.54 ms / 330 tokens ( 0.33 ms per token, 3040.30 tokens per second) 0.31.595.413 I slot print_timing: id 0 | task 2312 | eval time = 483.47 ms / 53 tokens ( 9.30 ms per token, 107.56 tokens per second) 0.31.595.414 I slot print_timing: id 0 | task 2312 | total time = 592.01 ms / 383 tokens 0.31.595.415 I slot print_timing: id 0 | task 2312 | graphs reused = 2177 0.31.595.416 I slot print_timing: id 0 | task 2312 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.595.442 I slot release: id 0 | task 2312 | stop processing: n_tokens = 382, truncated = 0 0.31.619.757 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 382, t_last = 31500547 0.31.644.165 I slot launch_slot_: id 0 | task 2368 | processing task, is_child = 0 0.32.043.287 I slot print_timing: id 0 | task 2368 | prompt eval time = 108.78 ms / 341 tokens ( 0.32 ms per token, 3134.80 tokens per second) 0.32.043.293 I slot print_timing: id 0 | task 2368 | eval time = 290.32 ms / 32 tokens ( 9.37 ms per token, 106.78 tokens per second) 0.32.043.294 I slot print_timing: id 0 | task 2368 | total time = 399.10 ms / 373 tokens 0.32.043.295 I slot print_timing: id 0 | task 2368 | graphs reused = 2207 0.32.043.296 I slot print_timing: id 0 | task 2368 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.043.323 I slot release: id 0 | task 2368 | stop processing: n_tokens = 372, truncated = 0 0.32.071.213 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 31948428 0.32.096.416 I slot launch_slot_: id 0 | task 2403 | processing task, is_child = 0 0.32.657.452 I slot print_timing: id 0 | task 2403 | prompt eval time = 111.69 ms / 338 tokens ( 0.33 ms per token, 3026.31 tokens per second) 0.32.657.457 I slot print_timing: id 0 | task 2403 | eval time = 449.33 ms / 48 tokens ( 9.56 ms per token, 104.60 tokens per second) 0.32.657.459 I slot print_timing: id 0 | task 2403 | total time = 561.01 ms / 386 tokens 0.32.657.459 I slot print_timing: id 0 | task 2403 | graphs reused = 2253 0.32.657.460 I slot print_timing: id 0 | task 2403 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.657.489 I slot release: id 0 | task 2403 | stop processing: n_tokens = 385, truncated = 0 0.32.661.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 32562594 0.32.686.945 I slot launch_slot_: id 0 | task 2454 | processing task, is_child = 0 0.33.316.945 I slot print_timing: id 0 | task 2454 | prompt eval time = 117.68 ms / 395 tokens ( 0.30 ms per token, 3356.45 tokens per second) 0.33.316.951 I slot print_timing: id 0 | task 2454 | eval time = 512.30 ms / 56 tokens ( 9.31 ms per token, 107.36 tokens per second) 0.33.316.952 I slot print_timing: id 0 | task 2454 | total time = 629.98 ms / 451 tokens 0.33.316.953 I slot print_timing: id 0 | task 2454 | graphs reused = 2307 0.33.316.953 I slot print_timing: id 0 | task 2454 | graph reallocs = 0 / 0 (same size) / (changed size) 0.33.316.983 I slot release: id 0 | task 2454 | stop processing: n_tokens = 450, truncated = 0 0.33.331.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 33222088 0.33.357.104 I slot launch_slot_: id 0 | task 2513 | processing task, is_child = 0 0.34.283.459 I slot print_timing: id 0 | task 2513 | prompt eval time = 165.76 ms / 528 tokens ( 0.31 ms per token, 3185.31 tokens per second) 0.34.283.464 I slot print_timing: id 0 | task 2513 | eval time = 760.57 ms / 83 tokens ( 9.28 ms per token, 107.81 tokens per second) 0.34.283.465 I slot print_timing: id 0 | task 2513 | total time = 926.33 ms / 611 tokens 0.34.283.466 I slot print_timing: id 0 | task 2513 | graphs reused = 2388 0.34.283.467 I slot print_timing: id 0 | task 2513 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.283.499 I slot release: id 0 | task 2513 | stop processing: n_tokens = 610, truncated = 0 0.34.309.458 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 34188604 0.34.341.473 I slot launch_slot_: id 0 | task 2600 | processing task, is_child = 0 0.34.878.611 I slot print_timing: id 0 | task 2600 | prompt eval time = 127.45 ms / 331 tokens ( 0.39 ms per token, 2597.00 tokens per second) 0.34.878.616 I slot print_timing: id 0 | task 2600 | eval time = 409.66 ms / 45 tokens ( 9.31 ms per token, 107.41 tokens per second) 0.34.878.617 I slot print_timing: id 0 | task 2600 | total time = 537.12 ms / 376 tokens 0.34.878.618 I slot print_timing: id 0 | task 2600 | graphs reused = 2431 0.34.878.619 I slot print_timing: id 0 | task 2600 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.878.645 I slot release: id 0 | task 2600 | stop processing: n_tokens = 387, truncated = 0 0.34.900.422 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 34783750 0.34.931.161 I slot launch_slot_: id 0 | task 2648 | processing task, is_child = 0 0.35.548.439 I slot print_timing: id 0 | task 2648 | prompt eval time = 133.74 ms / 362 tokens ( 0.37 ms per token, 2706.78 tokens per second) 0.35.548.445 I slot print_timing: id 0 | task 2648 | eval time = 483.52 ms / 53 tokens ( 9.30 ms per token, 107.54 tokens per second) 0.35.548.446 I slot print_timing: id 0 | task 2648 | total time = 617.26 ms / 415 tokens 0.35.548.448 I slot print_timing: id 0 | task 2648 | graphs reused = 2482 0.35.548.449 I slot print_timing: id 0 | task 2648 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.548.476 I slot release: id 0 | task 2648 | stop processing: n_tokens = 426, truncated = 0 0.35.569.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 35453581 0.35.600.116 I slot launch_slot_: id 0 | task 2704 | processing task, is_child = 0 0.36.368.079 I slot print_timing: id 0 | task 2704 | prompt eval time = 137.19 ms / 419 tokens ( 0.33 ms per token, 3054.27 tokens per second) 0.36.368.085 I slot print_timing: id 0 | task 2704 | eval time = 630.76 ms / 69 tokens ( 9.28 ms per token, 107.81 tokens per second) 0.36.368.086 I slot print_timing: id 0 | task 2704 | total time = 767.94 ms / 488 tokens 0.36.368.087 I slot print_timing: id 0 | task 2704 | graphs reused = 2549 0.36.368.088 I slot print_timing: id 0 | task 2704 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.368.119 I slot release: id 0 | task 2704 | stop processing: n_tokens = 499, truncated = 0 0.36.383.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 36273224 0.36.415.078 I slot launch_slot_: id 0 | task 2776 | processing task, is_child = 0 0.36.964.731 I slot print_timing: id 0 | task 2776 | prompt eval time = 149.18 ms / 423 tokens ( 0.35 ms per token, 2835.58 tokens per second) 0.36.964.737 I slot print_timing: id 0 | task 2776 | eval time = 400.46 ms / 44 tokens ( 9.31 ms per token, 107.38 tokens per second) 0.36.964.738 I slot print_timing: id 0 | task 2776 | total time = 549.63 ms / 467 tokens 0.36.964.739 I slot print_timing: id 0 | task 2776 | graphs reused = 2591 0.36.964.739 I slot print_timing: id 0 | task 2776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.964.773 I slot release: id 0 | task 2776 | stop processing: n_tokens = 478, truncated = 0 0.36.992.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 36869878 0.37.024.173 I slot launch_slot_: id 0 | task 2823 | processing task, is_child = 0 0.37.543.739 I slot print_timing: id 0 | task 2823 | prompt eval time = 128.21 ms / 341 tokens ( 0.38 ms per token, 2659.68 tokens per second) 0.37.543.745 I slot print_timing: id 0 | task 2823 | eval time = 391.34 ms / 43 tokens ( 9.32 ms per token, 107.32 tokens per second) 0.37.543.746 I slot print_timing: id 0 | task 2823 | total time = 519.55 ms / 384 tokens 0.37.543.747 I slot print_timing: id 0 | task 2823 | graphs reused = 2632 0.37.543.747 I slot print_timing: id 0 | task 2823 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.543.774 I slot release: id 0 | task 2823 | stop processing: n_tokens = 395, truncated = 0 0.37.570.866 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 37448879 0.37.602.079 I slot launch_slot_: id 0 | task 2869 | processing task, is_child = 0 0.38.159.671 I slot print_timing: id 0 | task 2869 | prompt eval time = 129.80 ms / 356 tokens ( 0.36 ms per token, 2742.66 tokens per second) 0.38.159.678 I slot print_timing: id 0 | task 2869 | eval time = 427.77 ms / 47 tokens ( 9.30 ms per token, 107.54 tokens per second) 0.38.159.679 I slot print_timing: id 0 | task 2869 | total time = 557.57 ms / 403 tokens 0.38.159.681 I slot print_timing: id 0 | task 2869 | graphs reused = 2677 0.38.159.682 I slot print_timing: id 0 | task 2869 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.159.710 I slot release: id 0 | task 2869 | stop processing: n_tokens = 414, truncated = 0 0.38.176.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 38064815 0.38.176.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.887 MiB) 0.38.213.558 I slot launch_slot_: id 0 | task 2919 | processing task, is_child = 0 0.38.748.749 I slot print_timing: id 0 | task 2919 | prompt eval time = 134.74 ms / 362 tokens ( 0.37 ms per token, 2686.60 tokens per second) 0.38.748.755 I slot print_timing: id 0 | task 2919 | eval time = 400.43 ms / 44 tokens ( 9.31 ms per token, 107.38 tokens per second) 0.38.748.756 I slot print_timing: id 0 | task 2919 | total time = 535.17 ms / 406 tokens 0.38.748.757 I slot print_timing: id 0 | task 2919 | graphs reused = 2719 0.38.748.758 I slot print_timing: id 0 | task 2919 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.748.786 I slot release: id 0 | task 2919 | stop processing: n_tokens = 417, truncated = 0 0.38.752.736 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 38653891 0.38.752.784 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.38.789.803 I slot launch_slot_: id 0 | task 2966 | processing task, is_child = 0 0.39.547.901 I slot print_timing: id 0 | task 2966 | prompt eval time = 136.24 ms / 391 tokens ( 0.35 ms per token, 2869.96 tokens per second) 0.39.547.907 I slot print_timing: id 0 | task 2966 | eval time = 621.84 ms / 68 tokens ( 9.28 ms per token, 107.74 tokens per second) 0.39.547.908 I slot print_timing: id 0 | task 2966 | total time = 758.08 ms / 459 tokens 0.39.547.909 I slot print_timing: id 0 | task 2966 | graphs reused = 2785 0.39.547.909 I slot print_timing: id 0 | task 2966 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.547.940 I slot release: id 0 | task 2966 | stop processing: n_tokens = 470, truncated = 0 0.39.561.924 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 39453045 0.39.561.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.39.600.228 I slot launch_slot_: id 0 | task 3037 | processing task, is_child = 0 0.40.222.225 I slot print_timing: id 0 | task 3037 | prompt eval time = 129.87 ms / 343 tokens ( 0.38 ms per token, 2641.08 tokens per second) 0.40.222.231 I slot print_timing: id 0 | task 3037 | eval time = 492.11 ms / 54 tokens ( 9.29 ms per token, 107.70 tokens per second) 0.40.222.232 I slot print_timing: id 0 | task 3037 | total time = 621.98 ms / 397 tokens 0.40.222.233 I slot print_timing: id 0 | task 3037 | graphs reused = 2837 0.40.222.234 I slot print_timing: id 0 | task 3037 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.222.259 I slot release: id 0 | task 3037 | stop processing: n_tokens = 408, truncated = 0 0.40.250.076 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 40127364 0.40.250.125 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.40.254.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.40.294.159 I slot launch_slot_: id 0 | task 3094 | processing task, is_child = 0 0.40.849.754 I slot print_timing: id 0 | task 3094 | prompt eval time = 135.45 ms / 401 tokens ( 0.34 ms per token, 2960.46 tokens per second) 0.40.849.761 I slot print_timing: id 0 | task 3094 | eval time = 420.12 ms / 46 tokens ( 9.34 ms per token, 107.11 tokens per second) 0.40.849.762 I slot print_timing: id 0 | task 3094 | total time = 555.57 ms / 447 tokens 0.40.849.763 I slot print_timing: id 0 | task 3094 | graphs reused = 2881 0.40.849.764 I slot print_timing: id 0 | task 3094 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.849.798 I slot release: id 0 | task 3094 | stop processing: n_tokens = 458, truncated = 0 0.40.867.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 40754903 0.40.867.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.40.908.411 I slot launch_slot_: id 0 | task 3143 | processing task, is_child = 0 0.41.663.947 I slot print_timing: id 0 | task 3143 | prompt eval time = 132.63 ms / 355 tokens ( 0.37 ms per token, 2676.54 tokens per second) 0.41.663.952 I slot print_timing: id 0 | task 3143 | eval time = 622.87 ms / 68 tokens ( 9.30 ms per token, 107.57 tokens per second) 0.41.663.954 I slot print_timing: id 0 | task 3143 | total time = 755.50 ms / 423 tokens 0.41.663.954 I slot print_timing: id 0 | task 3143 | graphs reused = 2947 0.41.663.955 I slot print_timing: id 0 | task 3143 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.663.984 I slot release: id 0 | task 3143 | stop processing: n_tokens = 434, truncated = 0 0.41.682.676 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 41569089 0.41.682.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.41.722.213 I slot launch_slot_: id 0 | task 3214 | processing task, is_child = 0 0.42.402.855 I slot print_timing: id 0 | task 3214 | prompt eval time = 128.68 ms / 351 tokens ( 0.37 ms per token, 2727.72 tokens per second) 0.42.402.861 I slot print_timing: id 0 | task 3214 | eval time = 551.95 ms / 57 tokens ( 9.86 ms per token, 101.46 tokens per second) 0.42.402.862 I slot print_timing: id 0 | task 3214 | total time = 680.62 ms / 408 tokens 0.42.402.863 I slot print_timing: id 0 | task 3214 | graphs reused = 3002 0.42.402.864 I slot print_timing: id 0 | task 3214 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.402.892 I slot release: id 0 | task 3214 | stop processing: n_tokens = 419, truncated = 0 0.42.431.326 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 42307997 0.42.431.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.42.441.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.42.503.640 I slot launch_slot_: id 0 | task 3274 | processing task, is_child = 0 0.43.515.599 I slot print_timing: id 0 | task 3274 | prompt eval time = 150.41 ms / 475 tokens ( 0.32 ms per token, 3157.99 tokens per second) 0.43.515.605 I slot print_timing: id 0 | task 3274 | eval time = 861.53 ms / 93 tokens ( 9.36 ms per token, 106.79 tokens per second) 0.43.515.606 I slot print_timing: id 0 | task 3274 | total time = 1011.94 ms / 568 tokens 0.43.515.606 I slot print_timing: id 0 | task 3274 | graphs reused = 3092 0.43.515.607 I slot print_timing: id 0 | task 3274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.515.640 I slot release: id 0 | task 3274 | stop processing: n_tokens = 579, truncated = 0 0.43.543.783 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 43420746 0.43.543.830 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.43.601.890 I slot launch_slot_: id 0 | task 3370 | processing task, is_child = 0 0.44.731.230 I slot print_timing: id 0 | task 3370 | prompt eval time = 148.60 ms / 440 tokens ( 0.34 ms per token, 2960.91 tokens per second) 0.44.731.236 I slot print_timing: id 0 | task 3370 | eval time = 980.72 ms / 106 tokens ( 9.34 ms per token, 107.06 tokens per second) 0.44.731.237 I slot print_timing: id 0 | task 3370 | total time = 1129.32 ms / 546 tokens 0.44.731.238 I slot print_timing: id 0 | task 3370 | graphs reused = 3195 0.44.731.238 I slot print_timing: id 0 | task 3370 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.731.269 I slot release: id 0 | task 3370 | stop processing: n_tokens = 557, truncated = 0 0.44.745.973 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 44636374 0.44.746.028 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.44.798.795 I slot launch_slot_: id 0 | task 3479 | processing task, is_child = 0 0.45.429.003 I slot print_timing: id 0 | task 3479 | prompt eval time = 127.64 ms / 345 tokens ( 0.37 ms per token, 2702.81 tokens per second) 0.45.429.009 I slot print_timing: id 0 | task 3479 | eval time = 502.55 ms / 55 tokens ( 9.31 ms per token, 107.45 tokens per second) 0.45.429.010 I slot print_timing: id 0 | task 3479 | total time = 630.19 ms / 400 tokens 0.45.429.010 I slot print_timing: id 0 | task 3479 | graphs reused = 3248 0.45.429.011 I slot print_timing: id 0 | task 3479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.429.039 I slot release: id 0 | task 3479 | stop processing: n_tokens = 411, truncated = 0 0.45.445.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 45334144 0.45.445.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.45.456.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.45.512.148 I slot launch_slot_: id 0 | task 3537 | processing task, is_child = 0 0.46.148.315 I slot print_timing: id 0 | task 3537 | prompt eval time = 134.42 ms / 382 tokens ( 0.35 ms per token, 2841.86 tokens per second) 0.46.148.321 I slot print_timing: id 0 | task 3537 | eval time = 501.73 ms / 55 tokens ( 9.29 ms per token, 107.63 tokens per second) 0.46.148.322 I slot print_timing: id 0 | task 3537 | total time = 636.15 ms / 437 tokens 0.46.148.322 I slot print_timing: id 0 | task 3537 | graphs reused = 3301 0.46.148.323 I slot print_timing: id 0 | task 3537 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.148.352 I slot release: id 0 | task 3537 | stop processing: n_tokens = 448, truncated = 0 0.46.163.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 46053457 0.46.163.782 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.46.212.078 I slot launch_slot_: id 0 | task 3595 | processing task, is_child = 0 0.46.749.886 I slot print_timing: id 0 | task 3595 | prompt eval time = 128.04 ms / 337 tokens ( 0.38 ms per token, 2632.07 tokens per second) 0.46.749.892 I slot print_timing: id 0 | task 3595 | eval time = 409.75 ms / 45 tokens ( 9.31 ms per token, 107.38 tokens per second) 0.46.749.893 I slot print_timing: id 0 | task 3595 | total time = 537.79 ms / 382 tokens 0.46.749.894 I slot print_timing: id 0 | task 3595 | graphs reused = 3344 0.46.749.895 I slot print_timing: id 0 | task 3595 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.749.923 I slot release: id 0 | task 3595 | stop processing: n_tokens = 393, truncated = 0 0.46.776.170 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 46655028 0.46.776.219 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.46.827.589 I slot launch_slot_: id 0 | task 3643 | processing task, is_child = 0 0.47.633.161 I slot print_timing: id 0 | task 3643 | prompt eval time = 135.65 ms / 402 tokens ( 0.34 ms per token, 2963.62 tokens per second) 0.47.633.167 I slot print_timing: id 0 | task 3643 | eval time = 669.91 ms / 70 tokens ( 9.71 ms per token, 103.00 tokens per second) 0.47.633.169 I slot print_timing: id 0 | task 3643 | total time = 805.55 ms / 472 tokens 0.47.633.169 I slot print_timing: id 0 | task 3643 | graphs reused = 3412 0.47.633.170 I slot print_timing: id 0 | task 3643 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.633.200 I slot release: id 0 | task 3643 | stop processing: n_tokens = 483, truncated = 0 0.47.662.192 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 47538305 0.47.662.243 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.47.672.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.47.727.998 I slot launch_slot_: id 0 | task 3716 | processing task, is_child = 0 0.48.416.812 I slot print_timing: id 0 | task 3716 | prompt eval time = 167.80 ms / 549 tokens ( 0.31 ms per token, 3271.69 tokens per second) 0.48.416.817 I slot print_timing: id 0 | task 3716 | eval time = 520.99 ms / 57 tokens ( 9.30 ms per token, 107.49 tokens per second) 0.48.416.818 I slot print_timing: id 0 | task 3716 | total time = 688.79 ms / 606 tokens 0.48.416.819 I slot print_timing: id 0 | task 3716 | graphs reused = 3467 0.48.416.819 I slot print_timing: id 0 | task 3716 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.416.852 I slot release: id 0 | task 3716 | stop processing: n_tokens = 617, truncated = 0 0.48.441.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 48321957 0.48.441.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.48.506.568 I slot launch_slot_: id 0 | task 3777 | processing task, is_child = 0 0.49.226.604 I slot print_timing: id 0 | task 3777 | prompt eval time = 189.12 ms / 616 tokens ( 0.31 ms per token, 3257.23 tokens per second) 0.49.226.609 I slot print_timing: id 0 | task 3777 | eval time = 530.90 ms / 58 tokens ( 9.31 ms per token, 107.37 tokens per second) 0.49.226.610 I slot print_timing: id 0 | task 3777 | total time = 720.02 ms / 674 tokens 0.49.226.611 I slot print_timing: id 0 | task 3777 | graphs reused = 3523 0.49.226.612 I slot print_timing: id 0 | task 3777 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.226.646 I slot release: id 0 | task 3777 | stop processing: n_tokens = 685, truncated = 0 0.49.250.549 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 49131751 0.49.250.612 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.49.260.440 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.49.329.968 I slot launch_slot_: id 0 | task 3839 | processing task, is_child = 0 0.50.092.586 I slot print_timing: id 0 | task 3839 | prompt eval time = 194.72 ms / 665 tokens ( 0.29 ms per token, 3415.09 tokens per second) 0.50.092.591 I slot print_timing: id 0 | task 3839 | eval time = 567.87 ms / 62 tokens ( 9.31 ms per token, 107.42 tokens per second) 0.50.092.593 I slot print_timing: id 0 | task 3839 | total time = 762.60 ms / 727 tokens 0.50.092.594 I slot print_timing: id 0 | task 3839 | graphs reused = 3583 0.50.092.594 I slot print_timing: id 0 | task 3839 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.092.632 I slot release: id 0 | task 3839 | stop processing: n_tokens = 738, truncated = 0 0.50.122.239 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 49997737 0.50.122.296 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.50.132.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.50.201.737 I slot launch_slot_: id 0 | task 3905 | processing task, is_child = 0 0.50.897.420 I slot print_timing: id 0 | task 3905 | prompt eval time = 192.42 ms / 645 tokens ( 0.30 ms per token, 3352.09 tokens per second) 0.50.897.426 I slot print_timing: id 0 | task 3905 | eval time = 503.25 ms / 55 tokens ( 9.32 ms per token, 107.30 tokens per second) 0.50.897.427 I slot print_timing: id 0 | task 3905 | total time = 695.66 ms / 700 tokens 0.50.897.428 I slot print_timing: id 0 | task 3905 | graphs reused = 3636 0.50.897.428 I slot print_timing: id 0 | task 3905 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.897.465 I slot release: id 0 | task 3905 | stop processing: n_tokens = 711, truncated = 0 0.50.901.614 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 50802570 0.50.901.675 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.50.967.546 I slot launch_slot_: id 0 | task 3964 | processing task, is_child = 0 0.51.599.153 I slot print_timing: id 0 | task 3964 | prompt eval time = 151.97 ms / 474 tokens ( 0.32 ms per token, 3119.10 tokens per second) 0.51.599.158 I slot print_timing: id 0 | task 3964 | eval time = 479.62 ms / 52 tokens ( 9.40 ms per token, 106.33 tokens per second) 0.51.599.160 I slot print_timing: id 0 | task 3964 | total time = 631.59 ms / 526 tokens 0.51.599.161 I slot print_timing: id 0 | task 3964 | graphs reused = 3685 0.51.599.162 I slot print_timing: id 0 | task 3964 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.599.196 I slot release: id 0 | task 3964 | stop processing: n_tokens = 537, truncated = 0 0.51.603.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 51504301 0.51.603.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.51.616.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.51.665.065 I slot launch_slot_: id 0 | task 4019 | processing task, is_child = 0 0.52.230.258 I slot print_timing: id 0 | task 4019 | prompt eval time = 181.72 ms / 617 tokens ( 0.29 ms per token, 3395.41 tokens per second) 0.52.230.263 I slot print_timing: id 0 | task 4019 | eval time = 383.46 ms / 42 tokens ( 9.35 ms per token, 106.92 tokens per second) 0.52.230.264 I slot print_timing: id 0 | task 4019 | total time = 565.17 ms / 659 tokens 0.52.230.265 I slot print_timing: id 0 | task 4019 | graphs reused = 3725 0.52.230.266 I slot print_timing: id 0 | task 4019 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.230.300 I slot release: id 0 | task 4019 | stop processing: n_tokens = 670, truncated = 0 0.52.254.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 52135405 0.52.254.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 0.52.314.197 I slot launch_slot_: id 0 | task 4065 | processing task, is_child = 0 0.52.932.126 I slot print_timing: id 0 | task 4065 | prompt eval time = 179.55 ms / 601 tokens ( 0.30 ms per token, 3347.33 tokens per second) 0.52.932.132 I slot print_timing: id 0 | task 4065 | eval time = 438.36 ms / 48 tokens ( 9.33 ms per token, 107.22 tokens per second) 0.52.932.133 I slot print_timing: id 0 | task 4065 | total time = 617.91 ms / 649 tokens 0.52.932.134 I slot print_timing: id 0 | task 4065 | graphs reused = 3771 0.52.932.134 I slot print_timing: id 0 | task 4065 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.932.169 I slot release: id 0 | task 4065 | stop processing: n_tokens = 660, truncated = 0 0.52.936.576 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 52837274 0.52.936.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.292 MiB) 0.52.946.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 0.53.018.792 I slot launch_slot_: id 0 | task 4117 | processing task, is_child = 0 0.53.618.844 I slot print_timing: id 0 | task 4117 | prompt eval time = 169.75 ms / 533 tokens ( 0.32 ms per token, 3140.00 tokens per second) 0.53.618.849 I slot print_timing: id 0 | task 4117 | eval time = 430.28 ms / 47 tokens ( 9.35 ms per token, 106.91 tokens per second) 0.53.618.850 I slot print_timing: id 0 | task 4117 | total time = 600.03 ms / 580 tokens 0.53.618.851 I slot print_timing: id 0 | task 4117 | graphs reused = 3816 0.53.618.852 I slot print_timing: id 0 | task 4117 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.618.886 I slot release: id 0 | task 4117 | stop processing: n_tokens = 591, truncated = 0 0.53.646.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 53523991 0.53.646.979 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 0.53.711.876 I slot launch_slot_: id 0 | task 4168 | processing task, is_child = 0 0.54.348.246 I slot print_timing: id 0 | task 4168 | prompt eval time = 155.41 ms / 480 tokens ( 0.32 ms per token, 3088.50 tokens per second) 0.54.348.252 I slot print_timing: id 0 | task 4168 | eval time = 480.93 ms / 52 tokens ( 9.43 ms per token, 106.04 tokens per second) 0.54.348.253 I slot print_timing: id 0 | task 4168 | total time = 636.35 ms / 532 tokens 0.54.348.254 I slot print_timing: id 0 | task 4168 | graphs reused = 3865 0.54.348.255 I slot print_timing: id 0 | task 4168 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.348.285 I slot release: id 0 | task 4168 | stop processing: n_tokens = 560, truncated = 0 0.54.375.085 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 54253390 0.54.375.135 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 0.54.385.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 0.54.457.939 I slot launch_slot_: id 0 | task 4223 | processing task, is_child = 0 0.55.014.805 I slot print_timing: id 0 | task 4223 | prompt eval time = 171.98 ms / 567 tokens ( 0.30 ms per token, 3296.82 tokens per second) 0.55.014.810 I slot print_timing: id 0 | task 4223 | eval time = 384.86 ms / 42 tokens ( 9.39 ms per token, 106.53 tokens per second) 0.55.014.811 I slot print_timing: id 0 | task 4223 | total time = 556.85 ms / 609 tokens 0.55.014.812 I slot print_timing: id 0 | task 4223 | graphs reused = 3905 0.55.014.813 I slot print_timing: id 0 | task 4223 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.014.847 I slot release: id 0 | task 4223 | stop processing: n_tokens = 637, truncated = 0 0.55.032.579 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 54919952 0.55.032.639 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 0.55.042.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 0.55.124.915 I slot launch_slot_: id 0 | task 4269 | processing task, is_child = 0 0.55.866.701 I slot print_timing: id 0 | task 4269 | prompt eval time = 163.15 ms / 506 tokens ( 0.32 ms per token, 3101.50 tokens per second) 0.55.866.708 I slot print_timing: id 0 | task 4269 | eval time = 578.62 ms / 63 tokens ( 9.33 ms per token, 107.15 tokens per second) 0.55.866.709 I slot print_timing: id 0 | task 4269 | total time = 741.77 ms / 569 tokens 0.55.866.709 I slot print_timing: id 0 | task 4269 | graphs reused = 3966 0.55.866.710 I slot print_timing: id 0 | task 4269 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.866.742 I slot release: id 0 | task 4269 | stop processing: n_tokens = 597, truncated = 0 0.55.885.998 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 55771847 0.55.886.056 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 0.55.896.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 0.55.973.966 I slot launch_slot_: id 0 | task 4335 | processing task, is_child = 0 0.56.489.292 I slot print_timing: id 0 | task 4335 | prompt eval time = 150.27 ms / 436 tokens ( 0.34 ms per token, 2901.50 tokens per second) 0.56.489.297 I slot print_timing: id 0 | task 4335 | eval time = 365.04 ms / 40 tokens ( 9.36 ms per token, 106.84 tokens per second) 0.56.489.298 I slot print_timing: id 0 | task 4335 | total time = 515.31 ms / 476 tokens 0.56.489.299 I slot print_timing: id 0 | task 4335 | graphs reused = 4004 0.56.489.300 I slot print_timing: id 0 | task 4335 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.489.330 I slot release: id 0 | task 4335 | stop processing: n_tokens = 504, truncated = 0 0.56.507.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 56394435 0.56.507.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 0.56.575.275 I slot launch_slot_: id 0 | task 4378 | processing task, is_child = 0 0.57.309.360 I slot print_timing: id 0 | task 4378 | prompt eval time = 166.05 ms / 519 tokens ( 0.32 ms per token, 3125.60 tokens per second) 0.57.309.366 I slot print_timing: id 0 | task 4378 | eval time = 568.02 ms / 62 tokens ( 9.31 ms per token, 107.39 tokens per second) 0.57.309.367 I slot print_timing: id 0 | task 4378 | total time = 734.07 ms / 581 tokens 0.57.309.368 I slot print_timing: id 0 | task 4378 | graphs reused = 4064 0.57.309.368 I slot print_timing: id 0 | task 4378 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.309.401 I slot release: id 0 | task 4378 | stop processing: n_tokens = 609, truncated = 0 0.57.330.815 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 57214506 0.57.330.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.697 MiB) 0.57.340.637 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.698 MiB) 0.57.420.886 I slot launch_slot_: id 0 | task 4444 | processing task, is_child = 0 0.57.999.801 I slot print_timing: id 0 | task 4444 | prompt eval time = 152.94 ms / 465 tokens ( 0.33 ms per token, 3040.51 tokens per second) 0.57.999.807 I slot print_timing: id 0 | task 4444 | eval time = 425.96 ms / 46 tokens ( 9.47 ms per token, 105.64 tokens per second) 0.57.999.808 I slot print_timing: id 0 | task 4444 | total time = 578.90 ms / 511 tokens 0.57.999.808 I slot print_timing: id 0 | task 4444 | graphs reused = 4107 0.57.999.809 I slot print_timing: id 0 | task 4444 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.999.842 I slot release: id 0 | task 4444 | stop processing: n_tokens = 542, truncated = 0 0.58.016.550 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 57904947 0.58.016.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 0.58.026.300 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 0.58.116.724 I slot launch_slot_: id 0 | task 4493 | processing task, is_child = 0 0.58.643.221 I slot print_timing: id 0 | task 4493 | prompt eval time = 152.25 ms / 431 tokens ( 0.35 ms per token, 2830.91 tokens per second) 0.58.643.227 I slot print_timing: id 0 | task 4493 | eval time = 374.23 ms / 41 tokens ( 9.36 ms per token, 106.89 tokens per second) 0.58.643.228 I slot print_timing: id 0 | task 4493 | total time = 526.48 ms / 472 tokens 0.58.643.229 I slot print_timing: id 0 | task 4493 | graphs reused = 4146 0.58.643.230 I slot print_timing: id 0 | task 4493 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.643.261 I slot release: id 0 | task 4493 | stop processing: n_tokens = 503, truncated = 0 0.58.665.373 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 58548366 0.58.665.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 0.58.675.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 0.58.765.090 I slot launch_slot_: id 0 | task 4537 | processing task, is_child = 0 0.59.326.452 I slot print_timing: id 0 | task 4537 | prompt eval time = 154.62 ms / 457 tokens ( 0.34 ms per token, 2955.63 tokens per second) 0.59.326.458 I slot print_timing: id 0 | task 4537 | eval time = 406.72 ms / 44 tokens ( 9.46 ms per token, 105.72 tokens per second) 0.59.326.459 I slot print_timing: id 0 | task 4537 | total time = 561.34 ms / 501 tokens 0.59.326.460 I slot print_timing: id 0 | task 4537 | graphs reused = 4187 0.59.326.461 I slot print_timing: id 0 | task 4537 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.326.493 I slot release: id 0 | task 4537 | stop processing: n_tokens = 532, truncated = 0 0.59.350.541 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 59231599 0.59.350.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 0.59.428.049 I slot launch_slot_: id 0 | task 4584 | processing task, is_child = 0 1.00.423.284 I slot print_timing: id 0 | task 4584 | prompt eval time = 153.97 ms / 439 tokens ( 0.35 ms per token, 2851.30 tokens per second) 1.00.423.289 I slot print_timing: id 0 | task 4584 | eval time = 841.25 ms / 91 tokens ( 9.35 ms per token, 106.98 tokens per second) 1.00.423.290 I slot print_timing: id 0 | task 4584 | total time = 995.22 ms / 530 tokens 1.00.423.291 I slot print_timing: id 0 | task 4584 | graphs reused = 4275 1.00.423.292 I slot print_timing: id 0 | task 4584 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.423.324 I slot release: id 0 | task 4584 | stop processing: n_tokens = 561, truncated = 0 1.00.452.565 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 561, t_last = 60328430 1.00.452.618 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.00.465.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.00.548.682 I slot launch_slot_: id 0 | task 4678 | processing task, is_child = 0 1.01.245.449 I slot print_timing: id 0 | task 4678 | prompt eval time = 182.02 ms / 606 tokens ( 0.30 ms per token, 3329.34 tokens per second) 1.01.245.456 I slot print_timing: id 0 | task 4678 | eval time = 514.73 ms / 56 tokens ( 9.36 ms per token, 106.85 tokens per second) 1.01.245.457 I slot print_timing: id 0 | task 4678 | total time = 696.75 ms / 662 tokens 1.01.245.459 I slot print_timing: id 0 | task 4678 | graphs reused = 4329 1.01.245.459 I slot print_timing: id 0 | task 4678 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.245.495 I slot release: id 0 | task 4678 | stop processing: n_tokens = 693, truncated = 0 1.01.260.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 61150600 1.01.260.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.01.273.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.01.374.927 I slot launch_slot_: id 0 | task 4738 | processing task, is_child = 0 1.01.916.757 I slot print_timing: id 0 | task 4738 | prompt eval time = 159.39 ms / 477 tokens ( 0.33 ms per token, 2992.72 tokens per second) 1.01.916.763 I slot print_timing: id 0 | task 4738 | eval time = 382.42 ms / 41 tokens ( 9.56 ms per token, 104.60 tokens per second) 1.01.916.764 I slot print_timing: id 0 | task 4738 | total time = 541.81 ms / 518 tokens 1.01.916.765 I slot print_timing: id 0 | task 4738 | graphs reused = 4367 1.01.916.766 I slot print_timing: id 0 | task 4738 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.916.797 I slot release: id 0 | task 4738 | stop processing: n_tokens = 549, truncated = 0 1.01.944.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 61821902 1.01.944.059 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.01.997.677 I slot launch_slot_: id 0 | task 4782 | processing task, is_child = 0 1.02.773.252 I slot print_timing: id 0 | task 4782 | prompt eval time = 223.67 ms / 845 tokens ( 0.26 ms per token, 3777.92 tokens per second) 1.02.773.257 I slot print_timing: id 0 | task 4782 | eval time = 551.89 ms / 60 tokens ( 9.35 ms per token, 106.91 tokens per second) 1.02.773.258 I slot print_timing: id 0 | task 4782 | total time = 775.55 ms / 905 tokens 1.02.773.259 I slot print_timing: id 0 | task 4782 | graphs reused = 4425 1.02.773.260 I slot print_timing: id 0 | task 4782 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.773.305 I slot release: id 0 | task 4782 | stop processing: n_tokens = 936, truncated = 0 1.02.790.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 62678410 1.02.790.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.043 MiB) 1.02.799.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.02.864.301 I slot launch_slot_: id 0 | task 4846 | processing task, is_child = 0 1.03.422.782 I slot print_timing: id 0 | task 4846 | prompt eval time = 160.99 ms / 459 tokens ( 0.35 ms per token, 2851.16 tokens per second) 1.03.422.787 I slot print_timing: id 0 | task 4846 | eval time = 397.48 ms / 43 tokens ( 9.46 ms per token, 105.67 tokens per second) 1.03.422.788 I slot print_timing: id 0 | task 4846 | total time = 558.46 ms / 502 tokens 1.03.422.789 I slot print_timing: id 0 | task 4846 | graphs reused = 4465 1.03.422.790 I slot print_timing: id 0 | task 4846 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.422.821 I slot release: id 0 | task 4846 | stop processing: n_tokens = 533, truncated = 0 1.03.443.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 63327926 1.03.443.724 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.03.496.836 I slot launch_slot_: id 0 | task 4892 | processing task, is_child = 0 1.04.120.557 I slot print_timing: id 0 | task 4892 | prompt eval time = 193.67 ms / 670 tokens ( 0.29 ms per token, 3459.51 tokens per second) 1.04.120.563 I slot print_timing: id 0 | task 4892 | eval time = 430.03 ms / 47 tokens ( 9.35 ms per token, 106.97 tokens per second) 1.04.120.564 I slot print_timing: id 0 | task 4892 | total time = 623.70 ms / 717 tokens 1.04.120.565 I slot print_timing: id 0 | task 4892 | graphs reused = 4510 1.04.120.566 I slot print_timing: id 0 | task 4892 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.120.610 I slot release: id 0 | task 4892 | stop processing: n_tokens = 748, truncated = 0 1.04.141.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 64025715 1.04.141.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.04.147.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.04.211.915 I slot launch_slot_: id 0 | task 4943 | processing task, is_child = 0 1.05.039.162 I slot print_timing: id 0 | task 4943 | prompt eval time = 217.38 ms / 775 tokens ( 0.28 ms per token, 3565.25 tokens per second) 1.05.039.168 I slot print_timing: id 0 | task 4943 | eval time = 609.85 ms / 63 tokens ( 9.84 ms per token, 101.66 tokens per second) 1.05.039.169 I slot print_timing: id 0 | task 4943 | total time = 827.23 ms / 838 tokens 1.05.039.170 I slot print_timing: id 0 | task 4943 | graphs reused = 4571 1.05.039.170 I slot print_timing: id 0 | task 4943 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.039.213 I slot release: id 0 | task 4943 | stop processing: n_tokens = 869, truncated = 0 1.05.054.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 64944319 1.05.054.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.05.067.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.05.165.673 I slot launch_slot_: id 0 | task 5010 | processing task, is_child = 0 1.05.997.382 I slot print_timing: id 0 | task 5010 | prompt eval time = 179.26 ms / 573 tokens ( 0.31 ms per token, 3196.55 tokens per second) 1.05.997.389 I slot print_timing: id 0 | task 5010 | eval time = 652.43 ms / 71 tokens ( 9.32 ms per token, 107.29 tokens per second) 1.05.997.390 I slot print_timing: id 0 | task 5010 | total time = 831.69 ms / 644 tokens 1.05.997.391 I slot print_timing: id 0 | task 5010 | graphs reused = 4640 1.05.997.392 I slot print_timing: id 0 | task 5010 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.997.444 I slot release: id 0 | task 5010 | stop processing: n_tokens = 675, truncated = 0 1.06.014.890 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 65902549 1.06.014.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 218.422 MiB) 1.06.028.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.06.124.194 I slot launch_slot_: id 0 | task 5085 | processing task, is_child = 0 1.06.877.635 I slot print_timing: id 0 | task 5085 | prompt eval time = 160.20 ms / 461 tokens ( 0.35 ms per token, 2877.67 tokens per second) 1.06.877.640 I slot print_timing: id 0 | task 5085 | eval time = 593.22 ms / 64 tokens ( 9.42 ms per token, 106.20 tokens per second) 1.06.877.642 I slot print_timing: id 0 | task 5085 | total time = 753.42 ms / 525 tokens 1.06.877.642 I slot print_timing: id 0 | task 5085 | graphs reused = 4701 1.06.877.643 I slot print_timing: id 0 | task 5085 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.877.679 I slot release: id 0 | task 5085 | stop processing: n_tokens = 556, truncated = 0 1.06.882.294 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 66782784 1.06.882.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.06.962.299 I slot launch_slot_: id 0 | task 5152 | processing task, is_child = 0 1.09.079.681 I slot print_timing: id 0 | task 5152 | prompt eval time = 181.08 ms / 609 tokens ( 0.30 ms per token, 3363.19 tokens per second) 1.09.079.687 I slot print_timing: id 0 | task 5152 | eval time = 1936.29 ms / 209 tokens ( 9.31 ms per token, 107.42 tokens per second) 1.09.079.688 I slot print_timing: id 0 | task 5152 | total time = 2117.36 ms / 818 tokens 1.09.079.689 I slot print_timing: id 0 | task 5152 | graphs reused = 4907 1.09.079.690 I slot print_timing: id 0 | task 5152 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.079.729 I slot release: id 0 | task 5152 | stop processing: n_tokens = 849, truncated = 0 1.09.095.391 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 849, t_last = 68984834 1.09.095.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.09.108.089 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.09.205.317 I slot launch_slot_: id 0 | task 5365 | processing task, is_child = 0 1.10.001.332 I slot print_timing: id 0 | task 5365 | prompt eval time = 218.58 ms / 791 tokens ( 0.28 ms per token, 3618.88 tokens per second) 1.10.001.338 I slot print_timing: id 0 | task 5365 | eval time = 577.42 ms / 61 tokens ( 9.62 ms per token, 103.91 tokens per second) 1.10.001.339 I slot print_timing: id 0 | task 5365 | total time = 796.00 ms / 852 tokens 1.10.001.340 I slot print_timing: id 0 | task 5365 | graphs reused = 4966 1.10.001.341 I slot print_timing: id 0 | task 5365 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.001.383 I slot release: id 0 | task 5365 | stop processing: n_tokens = 883, truncated = 0 1.10.024.511 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 69906488 1.10.024.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.10.156.341 I slot launch_slot_: id 0 | task 5430 | processing task, is_child = 0 1.10.846.721 I slot print_timing: id 0 | task 5430 | prompt eval time = 173.21 ms / 533 tokens ( 0.32 ms per token, 3077.17 tokens per second) 1.10.846.727 I slot print_timing: id 0 | task 5430 | eval time = 517.15 ms / 56 tokens ( 9.40 ms per token, 106.35 tokens per second) 1.10.846.728 I slot print_timing: id 0 | task 5430 | total time = 690.36 ms / 589 tokens 1.10.846.728 I slot print_timing: id 0 | task 5430 | graphs reused = 5020 1.10.846.729 I slot print_timing: id 0 | task 5430 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.846.766 I slot release: id 0 | task 5430 | stop processing: n_tokens = 677, truncated = 0 1.10.873.068 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 70751871 1.10.873.131 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.10.966.000 I slot launch_slot_: id 0 | task 5490 | processing task, is_child = 0 1.11.596.266 I slot print_timing: id 0 | task 5490 | prompt eval time = 178.74 ms / 566 tokens ( 0.32 ms per token, 3166.56 tokens per second) 1.11.596.272 I slot print_timing: id 0 | task 5490 | eval time = 451.50 ms / 46 tokens ( 10.03 ms per token, 99.67 tokens per second) 1.11.596.273 I slot print_timing: id 0 | task 5490 | total time = 630.25 ms / 612 tokens 1.11.596.274 I slot print_timing: id 0 | task 5490 | graphs reused = 5064 1.11.596.275 I slot print_timing: id 0 | task 5490 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.596.310 I slot release: id 0 | task 5490 | stop processing: n_tokens = 643, truncated = 0 1.11.618.979 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 71501415 1.11.619.053 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.11.694.470 I slot launch_slot_: id 0 | task 5540 | processing task, is_child = 0 1.12.247.527 I slot print_timing: id 0 | task 5540 | prompt eval time = 153.68 ms / 443 tokens ( 0.35 ms per token, 2882.61 tokens per second) 1.12.247.533 I slot print_timing: id 0 | task 5540 | eval time = 399.36 ms / 43 tokens ( 9.51 ms per token, 105.17 tokens per second) 1.12.247.534 I slot print_timing: id 0 | task 5540 | total time = 553.04 ms / 486 tokens 1.12.247.535 I slot print_timing: id 0 | task 5540 | graphs reused = 5104 1.12.247.536 I slot print_timing: id 0 | task 5540 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.247.566 I slot release: id 0 | task 5540 | stop processing: n_tokens = 517, truncated = 0 1.12.251.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 72152671 1.12.252.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.12.332.605 I slot launch_slot_: id 0 | task 5586 | processing task, is_child = 0 1.13.088.718 I slot print_timing: id 0 | task 5586 | prompt eval time = 153.66 ms / 487 tokens ( 0.32 ms per token, 3169.44 tokens per second) 1.13.088.724 I slot print_timing: id 0 | task 5586 | eval time = 602.44 ms / 65 tokens ( 9.41 ms per token, 106.23 tokens per second) 1.13.088.725 I slot print_timing: id 0 | task 5586 | total time = 756.09 ms / 552 tokens 1.13.088.726 I slot print_timing: id 0 | task 5586 | graphs reused = 5167 1.13.088.727 I slot print_timing: id 0 | task 5586 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.088.760 I slot release: id 0 | task 5586 | stop processing: n_tokens = 583, truncated = 0 1.13.104.833 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 72993865 1.13.104.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.13.182.740 I slot launch_slot_: id 0 | task 5654 | processing task, is_child = 0 1.13.773.942 I slot print_timing: id 0 | task 5654 | prompt eval time = 158.86 ms / 507 tokens ( 0.31 ms per token, 3191.43 tokens per second) 1.13.773.948 I slot print_timing: id 0 | task 5654 | eval time = 432.32 ms / 47 tokens ( 9.40 ms per token, 106.40 tokens per second) 1.13.773.949 I slot print_timing: id 0 | task 5654 | total time = 591.18 ms / 554 tokens 1.13.773.950 I slot print_timing: id 0 | task 5654 | graphs reused = 5212 1.13.773.951 I slot print_timing: id 0 | task 5654 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.773.984 I slot release: id 0 | task 5654 | stop processing: n_tokens = 585, truncated = 0 1.13.802.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 73679090 1.13.802.720 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.13.819.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.13.913.244 I slot launch_slot_: id 0 | task 5704 | processing task, is_child = 0 1.14.704.589 I slot print_timing: id 0 | task 5704 | prompt eval time = 183.63 ms / 633 tokens ( 0.29 ms per token, 3447.21 tokens per second) 1.14.704.595 I slot print_timing: id 0 | task 5704 | eval time = 607.70 ms / 66 tokens ( 9.35 ms per token, 106.96 tokens per second) 1.14.704.596 I slot print_timing: id 0 | task 5704 | total time = 791.33 ms / 699 tokens 1.14.704.597 I slot print_timing: id 0 | task 5704 | graphs reused = 5276 1.14.704.597 I slot print_timing: id 0 | task 5704 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.704.634 I slot release: id 0 | task 5704 | stop processing: n_tokens = 730, truncated = 0 1.14.721.310 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 74609739 1.14.721.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.14.806.994 I slot launch_slot_: id 0 | task 5774 | processing task, is_child = 0 1.15.416.620 I slot print_timing: id 0 | task 5774 | prompt eval time = 177.69 ms / 571 tokens ( 0.31 ms per token, 3213.48 tokens per second) 1.15.416.626 I slot print_timing: id 0 | task 5774 | eval time = 431.92 ms / 47 tokens ( 9.39 ms per token, 106.50 tokens per second) 1.15.416.627 I slot print_timing: id 0 | task 5774 | total time = 609.61 ms / 618 tokens 1.15.416.628 I slot print_timing: id 0 | task 5774 | graphs reused = 5321 1.15.416.629 I slot print_timing: id 0 | task 5774 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.416.664 I slot release: id 0 | task 5774 | stop processing: n_tokens = 649, truncated = 0 1.15.437.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 75321769 1.15.437.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.15.554.650 I slot launch_slot_: id 0 | task 5825 | processing task, is_child = 0 1.16.180.826 I slot print_timing: id 0 | task 5825 | prompt eval time = 221.49 ms / 798 tokens ( 0.28 ms per token, 3602.86 tokens per second) 1.16.180.831 I slot print_timing: id 0 | task 5825 | eval time = 404.67 ms / 44 tokens ( 9.41 ms per token, 106.26 tokens per second) 1.16.180.832 I slot print_timing: id 0 | task 5825 | total time = 626.16 ms / 842 tokens 1.16.180.833 I slot print_timing: id 0 | task 5825 | graphs reused = 5363 1.16.180.834 I slot print_timing: id 0 | task 5825 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.180.877 I slot release: id 0 | task 5825 | stop processing: n_tokens = 873, truncated = 0 1.16.209.505 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 76085982 1.16.209.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.16.229.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.16.333.507 I slot launch_slot_: id 0 | task 5873 | processing task, is_child = 0 1.16.904.761 I slot print_timing: id 0 | task 5873 | prompt eval time = 176.44 ms / 572 tokens ( 0.31 ms per token, 3241.86 tokens per second) 1.16.904.767 I slot print_timing: id 0 | task 5873 | eval time = 394.79 ms / 43 tokens ( 9.40 ms per token, 106.39 tokens per second) 1.16.904.769 I slot print_timing: id 0 | task 5873 | total time = 571.23 ms / 615 tokens 1.16.904.770 I slot print_timing: id 0 | task 5873 | graphs reused = 5404 1.16.904.771 I slot print_timing: id 0 | task 5873 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.904.809 I slot release: id 0 | task 5873 | stop processing: n_tokens = 646, truncated = 0 1.16.926.400 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 76809915 1.16.926.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.17.010.465 I slot launch_slot_: id 0 | task 5920 | processing task, is_child = 0 1.17.650.068 I slot print_timing: id 0 | task 5920 | prompt eval time = 184.81 ms / 613 tokens ( 0.30 ms per token, 3316.97 tokens per second) 1.17.650.075 I slot print_timing: id 0 | task 5920 | eval time = 454.77 ms / 49 tokens ( 9.47 ms per token, 105.55 tokens per second) 1.17.650.076 I slot print_timing: id 0 | task 5920 | total time = 639.58 ms / 662 tokens 1.17.650.077 I slot print_timing: id 0 | task 5920 | graphs reused = 5451 1.17.650.078 I slot print_timing: id 0 | task 5920 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.650.123 I slot release: id 0 | task 5920 | stop processing: n_tokens = 693, truncated = 0 1.17.655.145 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 77555228 1.17.655.200 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.17.766.277 I slot launch_slot_: id 0 | task 5973 | processing task, is_child = 0 1.18.643.164 I slot print_timing: id 0 | task 5973 | prompt eval time = 177.48 ms / 580 tokens ( 0.31 ms per token, 3267.90 tokens per second) 1.18.643.170 I slot print_timing: id 0 | task 5973 | eval time = 699.38 ms / 76 tokens ( 9.33 ms per token, 107.24 tokens per second) 1.18.643.171 I slot print_timing: id 0 | task 5973 | total time = 876.87 ms / 656 tokens 1.18.643.172 I slot print_timing: id 0 | task 5973 | graphs reused = 5525 1.18.643.173 I slot print_timing: id 0 | task 5973 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.643.210 I slot release: id 0 | task 5973 | stop processing: n_tokens = 687, truncated = 0 1.18.667.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 78548315 1.18.667.987 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.18.781.565 I slot launch_slot_: id 0 | task 6053 | processing task, is_child = 0 1.19.449.326 I slot print_timing: id 0 | task 6053 | prompt eval time = 203.93 ms / 716 tokens ( 0.28 ms per token, 3511.08 tokens per second) 1.19.449.331 I slot print_timing: id 0 | task 6053 | eval time = 463.82 ms / 50 tokens ( 9.47 ms per token, 105.65 tokens per second) 1.19.449.332 I slot print_timing: id 0 | task 6053 | total time = 667.74 ms / 766 tokens 1.19.449.333 I slot print_timing: id 0 | task 6053 | graphs reused = 5572 1.19.449.334 I slot print_timing: id 0 | task 6053 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.449.374 I slot release: id 0 | task 6053 | stop processing: n_tokens = 797, truncated = 0 1.19.474.161 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 79354479 1.19.474.215 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.19.493.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.19.596.710 I slot launch_slot_: id 0 | task 6107 | processing task, is_child = 0 1.20.751.366 I slot print_timing: id 0 | task 6107 | prompt eval time = 215.54 ms / 799 tokens ( 0.27 ms per token, 3706.90 tokens per second) 1.20.751.372 I slot print_timing: id 0 | task 6107 | eval time = 939.09 ms / 102 tokens ( 9.30 ms per token, 107.55 tokens per second) 1.20.751.373 I slot print_timing: id 0 | task 6107 | total time = 1154.64 ms / 901 tokens 1.20.751.374 I slot print_timing: id 0 | task 6107 | graphs reused = 5672 1.20.751.375 I slot print_timing: id 0 | task 6107 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.751.417 I slot release: id 0 | task 6107 | stop processing: n_tokens = 932, truncated = 0 1.20.765.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 80656522 1.20.765.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.048 MiB) 1.20.861.772 I slot launch_slot_: id 0 | task 6213 | processing task, is_child = 0 1.22.023.735 I slot print_timing: id 0 | task 6213 | prompt eval time = 133.75 ms / 361 tokens ( 0.37 ms per token, 2699.17 tokens per second) 1.22.023.742 I slot print_timing: id 0 | task 6213 | eval time = 1028.20 ms / 112 tokens ( 9.26 ms per token, 107.96 tokens per second) 1.22.023.743 I slot print_timing: id 0 | task 6213 | total time = 1161.94 ms / 473 tokens 1.22.023.744 I slot print_timing: id 0 | task 6213 | graphs reused = 5782 1.22.023.745 I slot print_timing: id 0 | task 6213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.023.778 I slot release: id 0 | task 6213 | stop processing: n_tokens = 504, truncated = 0 1.22.042.386 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 81928883 1.22.042.436 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.22.132.811 I slot launch_slot_: id 0 | task 6328 | processing task, is_child = 0 1.23.263.995 I slot print_timing: id 0 | task 6328 | prompt eval time = 133.26 ms / 381 tokens ( 0.35 ms per token, 2859.14 tokens per second) 1.23.264.001 I slot print_timing: id 0 | task 6328 | eval time = 997.91 ms / 108 tokens ( 9.33 ms per token, 107.22 tokens per second) 1.23.264.002 I slot print_timing: id 0 | task 6328 | total time = 1131.16 ms / 489 tokens 1.23.264.002 I slot print_timing: id 0 | task 6328 | graphs reused = 5887 1.23.264.003 I slot print_timing: id 0 | task 6328 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.264.035 I slot release: id 0 | task 6328 | stop processing: n_tokens = 520, truncated = 0 1.23.291.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 83169140 1.23.291.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.23.352.057 I slot launch_slot_: id 0 | task 6439 | processing task, is_child = 0 1.24.632.466 I slot print_timing: id 0 | task 6439 | prompt eval time = 129.89 ms / 365 tokens ( 0.36 ms per token, 2810.16 tokens per second) 1.24.632.471 I slot print_timing: id 0 | task 6439 | eval time = 1150.50 ms / 124 tokens ( 9.35 ms per token, 106.91 tokens per second) 1.24.632.472 I slot print_timing: id 0 | task 6439 | total time = 1280.39 ms / 489 tokens 1.24.632.473 I slot print_timing: id 0 | task 6439 | graphs reused = 6008 1.24.632.474 I slot print_timing: id 0 | task 6439 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.632.504 I slot release: id 0 | task 6439 | stop processing: n_tokens = 520, truncated = 0 1.24.658.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 84537609 1.24.658.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.24.717.211 I slot launch_slot_: id 0 | task 6566 | processing task, is_child = 0 1.25.830.624 I slot print_timing: id 0 | task 6566 | prompt eval time = 128.47 ms / 333 tokens ( 0.39 ms per token, 2592.07 tokens per second) 1.25.830.630 I slot print_timing: id 0 | task 6566 | eval time = 984.93 ms / 107 tokens ( 9.29 ms per token, 107.62 tokens per second) 1.25.830.631 I slot print_timing: id 0 | task 6566 | total time = 1113.39 ms / 440 tokens 1.25.830.632 I slot print_timing: id 0 | task 6566 | graphs reused = 6113 1.25.830.633 I slot print_timing: id 0 | task 6566 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.830.662 I slot release: id 0 | task 6566 | stop processing: n_tokens = 471, truncated = 0 1.25.851.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 85735767 1.25.898.455 I slot launch_slot_: id 0 | task 6676 | processing task, is_child = 0 1.27.314.738 I slot print_timing: id 0 | task 6676 | prompt eval time = 136.06 ms / 403 tokens ( 0.34 ms per token, 2962.02 tokens per second) 1.27.314.743 I slot print_timing: id 0 | task 6676 | eval time = 1280.21 ms / 138 tokens ( 9.34 ms per token, 107.01 tokens per second) 1.27.314.744 I slot print_timing: id 0 | task 6676 | total time = 1416.26 ms / 541 tokens 1.27.314.745 I slot print_timing: id 0 | task 6676 | graphs reused = 6248 1.27.314.746 I slot print_timing: id 0 | task 6676 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.314.775 I slot release: id 0 | task 6676 | stop processing: n_tokens = 572, truncated = 0 1.27.335.498 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 87219880 1.27.335.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.27.397.031 I slot launch_slot_: id 0 | task 6817 | processing task, is_child = 0 1.29.247.420 I slot print_timing: id 0 | task 6817 | prompt eval time = 135.99 ms / 411 tokens ( 0.33 ms per token, 3022.30 tokens per second) 1.29.247.425 I slot print_timing: id 0 | task 6817 | eval time = 1714.38 ms / 185 tokens ( 9.32 ms per token, 107.33 tokens per second) 1.29.247.426 I slot print_timing: id 0 | task 6817 | total time = 1850.37 ms / 596 tokens 1.29.247.427 I slot print_timing: id 0 | task 6817 | graphs reused = 6430 1.29.247.428 I slot print_timing: id 0 | task 6817 | graph reallocs = 0 / 0 (same size) / (changed size) 1.29.247.458 I slot release: id 0 | task 6817 | stop processing: n_tokens = 627, truncated = 0 1.29.270.799 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 89152563 1.29.270.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.29.329.588 I slot launch_slot_: id 0 | task 7005 | processing task, is_child = 0 1.31.560.426 I slot print_timing: id 0 | task 7005 | prompt eval time = 158.62 ms / 490 tokens ( 0.32 ms per token, 3089.12 tokens per second) 1.31.560.432 I slot print_timing: id 0 | task 7005 | eval time = 2072.20 ms / 225 tokens ( 9.25 ms per token, 108.10 tokens per second) 1.31.560.433 I slot print_timing: id 0 | task 7005 | total time = 2230.82 ms / 715 tokens 1.31.560.434 I slot print_timing: id 0 | task 7005 | graphs reused = 6653 1.31.560.434 I slot print_timing: id 0 | task 7005 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.560.467 I slot release: id 0 | task 7005 | stop processing: n_tokens = 746, truncated = 0 1.31.575.044 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 91465572 1.31.575.108 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.31.662.462 I slot launch_slot_: id 0 | task 7233 | processing task, is_child = 0 1.33.379.806 I slot print_timing: id 0 | task 7233 | prompt eval time = 128.28 ms / 344 tokens ( 0.37 ms per token, 2681.65 tokens per second) 1.33.379.812 I slot print_timing: id 0 | task 7233 | eval time = 1589.04 ms / 171 tokens ( 9.35 ms per token, 106.98 tokens per second) 1.33.379.813 I slot print_timing: id 0 | task 7233 | total time = 1717.32 ms / 515 tokens 1.33.379.814 I slot print_timing: id 0 | task 7233 | graphs reused = 6821 1.33.379.815 I slot print_timing: id 0 | task 7233 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.379.855 I slot release: id 0 | task 7233 | stop processing: n_tokens = 546, truncated = 0 1.33.396.497 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 93284960 1.33.396.547 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.33.492.201 I slot launch_slot_: id 0 | task 7407 | processing task, is_child = 0 1.35.212.715 I slot print_timing: id 0 | task 7407 | prompt eval time = 132.69 ms / 347 tokens ( 0.38 ms per token, 2615.12 tokens per second) 1.35.212.722 I slot print_timing: id 0 | task 7407 | eval time = 1587.80 ms / 171 tokens ( 9.34 ms per token, 107.07 tokens per second) 1.35.212.723 I slot print_timing: id 0 | task 7407 | total time = 1720.49 ms / 518 tokens 1.35.212.724 I slot print_timing: id 0 | task 7407 | graphs reused = 6989 1.35.212.725 I slot print_timing: id 0 | task 7407 | graph reallocs = 0 / 0 (same size) / (changed size) 1.35.212.757 I slot release: id 0 | task 7407 | stop processing: n_tokens = 549, truncated = 0 1.35.216.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 95117862 1.35.216.872 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.305 MiB) 1.35.314.790 I slot launch_slot_: id 0 | task 7581 | processing task, is_child = 0 1.36.627.825 I slot print_timing: id 0 | task 7581 | prompt eval time = 140.57 ms / 401 tokens ( 0.35 ms per token, 2852.73 tokens per second) 1.36.627.831 I slot print_timing: id 0 | task 7581 | eval time = 1172.45 ms / 126 tokens ( 9.38 ms per token, 106.61 tokens per second) 1.36.627.832 I slot print_timing: id 0 | task 7581 | total time = 1313.02 ms / 527 tokens 1.36.627.832 I slot print_timing: id 0 | task 7581 | graphs reused = 7112 1.36.627.833 I slot print_timing: id 0 | task 7581 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.627.864 I slot release: id 0 | task 7581 | stop processing: n_tokens = 558, truncated = 0 1.36.654.379 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 96532970 1.36.654.429 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.36.759.274 I slot launch_slot_: id 0 | task 7710 | processing task, is_child = 0 1.38.006.682 I slot print_timing: id 0 | task 7710 | prompt eval time = 148.95 ms / 456 tokens ( 0.33 ms per token, 3061.49 tokens per second) 1.38.006.687 I slot print_timing: id 0 | task 7710 | eval time = 1098.44 ms / 115 tokens ( 9.64 ms per token, 103.78 tokens per second) 1.38.006.688 I slot print_timing: id 0 | task 7710 | total time = 1247.39 ms / 571 tokens 1.38.006.689 I slot print_timing: id 0 | task 7710 | graphs reused = 7224 1.38.006.690 I slot print_timing: id 0 | task 7710 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.006.720 I slot release: id 0 | task 7710 | stop processing: n_tokens = 602, truncated = 0 1.38.034.725 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.107 (> 0.100 thold), f_keep = 0.078 1.38.034.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.38.127.461 I slot launch_slot_: id 0 | task 7828 | processing task, is_child = 0 1.39.305.546 I slot print_timing: id 0 | task 7828 | prompt eval time = 142.12 ms / 406 tokens ( 0.35 ms per token, 2856.66 tokens per second) 1.39.305.552 I slot print_timing: id 0 | task 7828 | eval time = 1035.94 ms / 112 tokens ( 9.33 ms per token, 107.15 tokens per second) 1.39.305.553 I slot print_timing: id 0 | task 7828 | total time = 1178.07 ms / 518 tokens 1.39.305.554 I slot print_timing: id 0 | task 7828 | graphs reused = 7333 1.39.305.555 I slot print_timing: id 0 | task 7828 | graph reallocs = 0 / 0 (same size) / (changed size) 1.39.305.585 I slot release: id 0 | task 7828 | stop processing: n_tokens = 549, truncated = 0 1.39.321.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 99210690 1.39.377.060 I slot launch_slot_: id 0 | task 7943 | processing task, is_child = 0 1.41.171.422 I slot print_timing: id 0 | task 7943 | prompt eval time = 137.50 ms / 406 tokens ( 0.34 ms per token, 2952.73 tokens per second) 1.41.171.428 I slot print_timing: id 0 | task 7943 | eval time = 1656.84 ms / 179 tokens ( 9.31 ms per token, 107.43 tokens per second) 1.41.171.429 I slot print_timing: id 0 | task 7943 | total time = 1794.34 ms / 585 tokens 1.41.171.430 I slot print_timing: id 0 | task 7943 | graphs reused = 7509 1.41.171.431 I slot print_timing: id 0 | task 7943 | graph reallocs = 0 / 0 (same size) / (changed size) 1.41.171.461 I slot release: id 0 | task 7943 | stop processing: n_tokens = 616, truncated = 0 1.41.191.433 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 101076566 1.41.191.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.41.288.544 I slot launch_slot_: id 0 | task 8125 | processing task, is_child = 0 1.42.764.043 I slot print_timing: id 0 | task 8125 | prompt eval time = 144.06 ms / 444 tokens ( 0.32 ms per token, 3082.09 tokens per second) 1.42.764.049 I slot print_timing: id 0 | task 8125 | eval time = 1331.42 ms / 144 tokens ( 9.31 ms per token, 107.40 tokens per second) 1.42.764.050 I slot print_timing: id 0 | task 8125 | total time = 1475.48 ms / 588 tokens 1.42.764.051 I slot print_timing: id 0 | task 8125 | graphs reused = 7650 1.42.764.053 I slot print_timing: id 0 | task 8125 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.764.087 I slot release: id 0 | task 8125 | stop processing: n_tokens = 619, truncated = 0 1.42.767.751 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 102669192 1.42.767.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.42.854.923 I slot launch_slot_: id 0 | task 8272 | processing task, is_child = 0 1.43.938.724 I slot print_timing: id 0 | task 8272 | prompt eval time = 135.85 ms / 372 tokens ( 0.37 ms per token, 2738.25 tokens per second) 1.43.938.730 I slot print_timing: id 0 | task 8272 | eval time = 947.93 ms / 103 tokens ( 9.29 ms per token, 107.60 tokens per second) 1.43.938.731 I slot print_timing: id 0 | task 8272 | total time = 1083.78 ms / 475 tokens 1.43.938.732 I slot print_timing: id 0 | task 8272 | graphs reused = 7751 1.43.938.733 I slot print_timing: id 0 | task 8272 | graph reallocs = 0 / 0 (same size) / (changed size) 1.43.938.766 I slot release: id 0 | task 8272 | stop processing: n_tokens = 506, truncated = 0 1.43.958.322 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 103843871 1.43.958.366 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.44.027.728 I slot launch_slot_: id 0 | task 8378 | processing task, is_child = 0 1.46.305.200 I slot print_timing: id 0 | task 8378 | prompt eval time = 143.98 ms / 454 tokens ( 0.32 ms per token, 3153.15 tokens per second) 1.46.305.206 I slot print_timing: id 0 | task 8378 | eval time = 2133.47 ms / 230 tokens ( 9.32 ms per token, 107.34 tokens per second) 1.46.305.207 I slot print_timing: id 0 | task 8378 | total time = 2277.45 ms / 684 tokens 1.46.305.208 I slot print_timing: id 0 | task 8378 | graphs reused = 7978 1.46.305.208 I slot print_timing: id 0 | task 8378 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.305.239 I slot release: id 0 | task 8378 | stop processing: n_tokens = 715, truncated = 0 1.46.325.733 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 106210344 1.46.325.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.46.428.186 I slot launch_slot_: id 0 | task 8611 | processing task, is_child = 0 1.48.655.539 I slot print_timing: id 0 | task 8611 | prompt eval time = 132.87 ms / 354 tokens ( 0.38 ms per token, 2664.30 tokens per second) 1.48.655.545 I slot print_timing: id 0 | task 8611 | eval time = 2094.47 ms / 226 tokens ( 9.31 ms per token, 107.43 tokens per second) 1.48.655.546 I slot print_timing: id 0 | task 8611 | total time = 2227.33 ms / 580 tokens 1.48.655.547 I slot print_timing: id 0 | task 8611 | graphs reused = 8201 1.48.655.548 I slot print_timing: id 0 | task 8611 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.655.578 I slot release: id 0 | task 8611 | stop processing: n_tokens = 611, truncated = 0 1.48.670.237 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 108560683 1.48.670.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 1.48.784.753 I slot launch_slot_: id 0 | task 8840 | processing task, is_child = 0 1.50.210.064 I slot print_timing: id 0 | task 8840 | prompt eval time = 133.53 ms / 334 tokens ( 0.40 ms per token, 2501.31 tokens per second) 1.50.210.070 I slot print_timing: id 0 | task 8840 | eval time = 1291.76 ms / 140 tokens ( 9.29 ms per token, 107.61 tokens per second) 1.50.210.071 I slot print_timing: id 0 | task 8840 | total time = 1425.29 ms / 474 tokens 1.50.210.072 I slot print_timing: id 0 | task 8840 | graphs reused = 8339 1.50.210.073 I slot print_timing: id 0 | task 8840 | graph reallocs = 0 / 0 (same size) / (changed size) 1.50.210.102 I slot release: id 0 | task 8840 | stop processing: n_tokens = 505, truncated = 0 1.50.214.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 110115207 1.50.214.249 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 1.50.309.950 I slot launch_slot_: id 0 | task 8983 | processing task, is_child = 0 1.52.076.421 I slot print_timing: id 0 | task 8983 | prompt eval time = 145.94 ms / 426 tokens ( 0.34 ms per token, 2918.97 tokens per second) 1.52.076.428 I slot print_timing: id 0 | task 8983 | eval time = 1620.51 ms / 175 tokens ( 9.31 ms per token, 107.37 tokens per second) 1.52.076.429 I slot print_timing: id 0 | task 8983 | total time = 1766.45 ms / 601 tokens 1.52.076.429 I slot print_timing: id 0 | task 8983 | graphs reused = 8511 1.52.076.430 I slot print_timing: id 0 | task 8983 | graph reallocs = 0 / 0 (same size) / (changed size) 1.52.076.463 I slot release: id 0 | task 8983 | stop processing: n_tokens = 632, truncated = 0 1.52.093.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 111981568 1.52.093.816 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 1.52.191.897 I slot launch_slot_: id 0 | task 9161 | processing task, is_child = 0 1.53.408.493 I slot print_timing: id 0 | task 9161 | prompt eval time = 134.19 ms / 366 tokens ( 0.37 ms per token, 2727.46 tokens per second) 1.53.408.498 I slot print_timing: id 0 | task 9161 | eval time = 1082.38 ms / 117 tokens ( 9.33 ms per token, 107.17 tokens per second) 1.53.408.499 I slot print_timing: id 0 | task 9161 | total time = 1216.57 ms / 483 tokens 1.53.408.500 I slot print_timing: id 0 | task 9161 | graphs reused = 8625 1.53.408.501 I slot print_timing: id 0 | task 9161 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.408.531 I slot release: id 0 | task 9161 | stop processing: n_tokens = 514, truncated = 0 1.53.425.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 113313636 1.53.425.567 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 1.53.536.186 I slot launch_slot_: id 0 | task 9281 | processing task, is_child = 0 1.56.693.003 I slot print_timing: id 0 | task 9281 | n_gen = 321, tg = 106.49 t/s, tg_3s = 106.82 t/s 1.56.741.246 I slot print_timing: id 0 | task 9281 | prompt eval time = 151.77 ms / 462 tokens ( 0.33 ms per token, 3044.04 tokens per second) 1.56.741.252 I slot print_timing: id 0 | task 9281 | eval time = 3053.27 ms / 326 tokens ( 9.39 ms per token, 106.44 tokens per second) 1.56.741.253 I slot print_timing: id 0 | task 9281 | total time = 3205.04 ms / 788 tokens 1.56.741.253 I slot print_timing: id 0 | task 9281 | graphs reused = 8947 1.56.741.254 I slot print_timing: id 0 | task 9281 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.741.287 I slot release: id 0 | task 9281 | stop processing: n_tokens = 819, truncated = 0 1.56.767.051 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 116646392 1.56.767.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.56.868.117 I slot launch_slot_: id 0 | task 9610 | processing task, is_child = 0 1.58.294.606 I slot print_timing: id 0 | task 9610 | prompt eval time = 137.61 ms / 396 tokens ( 0.35 ms per token, 2877.72 tokens per second) 1.58.294.611 I slot print_timing: id 0 | task 9610 | eval time = 1288.86 ms / 139 tokens ( 9.34 ms per token, 107.07 tokens per second) 1.58.294.612 I slot print_timing: id 0 | task 9610 | total time = 1426.47 ms / 535 tokens 1.58.294.613 I slot print_timing: id 0 | task 9610 | graphs reused = 9083 1.58.294.614 I slot print_timing: id 0 | task 9610 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.294.642 I slot release: id 0 | task 9610 | stop processing: n_tokens = 566, truncated = 0 1.58.320.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 118199747 1.58.384.905 I slot launch_slot_: id 0 | task 9752 | processing task, is_child = 0 2.00.027.637 I slot print_timing: id 0 | task 9752 | prompt eval time = 150.06 ms / 458 tokens ( 0.33 ms per token, 3052.05 tokens per second) 2.00.027.643 I slot print_timing: id 0 | task 9752 | eval time = 1492.65 ms / 161 tokens ( 9.33 ms per token, 107.19 tokens per second) 2.00.027.644 I slot print_timing: id 0 | task 9752 | total time = 1642.71 ms / 619 tokens 2.00.027.646 I slot print_timing: id 0 | task 9752 | graphs reused = 9241 2.00.027.646 I slot print_timing: id 0 | task 9752 | graph reallocs = 0 / 0 (same size) / (changed size) 2.00.027.678 I slot release: id 0 | task 9752 | stop processing: n_tokens = 650, truncated = 0 2.00.031.556 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 119932783 2.00.031.613 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.00.128.718 I slot launch_slot_: id 0 | task 9916 | processing task, is_child = 0 2.01.689.123 I slot print_timing: id 0 | task 9916 | prompt eval time = 152.84 ms / 458 tokens ( 0.33 ms per token, 2996.66 tokens per second) 2.01.689.129 I slot print_timing: id 0 | task 9916 | eval time = 1407.55 ms / 152 tokens ( 9.32 ms per token, 107.28 tokens per second) 2.01.689.131 I slot print_timing: id 0 | task 9916 | total time = 1560.39 ms / 610 tokens 2.01.689.131 I slot print_timing: id 0 | task 9916 | graphs reused = 9390 2.01.689.132 I slot print_timing: id 0 | task 9916 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.689.163 I slot release: id 0 | task 9916 | stop processing: n_tokens = 641, truncated = 0 2.01.707.752 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 641, t_last = 121594268 2.01.707.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.01.805.372 I slot launch_slot_: id 0 | task 10071 | processing task, is_child = 0 2.03.909.314 I slot print_timing: id 0 | task 10071 | prompt eval time = 148.61 ms / 452 tokens ( 0.33 ms per token, 3041.48 tokens per second) 2.03.909.320 I slot print_timing: id 0 | task 10071 | eval time = 1955.31 ms / 210 tokens ( 9.36 ms per token, 106.89 tokens per second) 2.03.909.321 I slot print_timing: id 0 | task 10071 | total time = 2103.92 ms / 662 tokens 2.03.909.322 I slot print_timing: id 0 | task 10071 | graphs reused = 9597 2.03.909.323 I slot print_timing: id 0 | task 10071 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.909.357 I slot release: id 0 | task 10071 | stop processing: n_tokens = 693, truncated = 0 2.03.937.888 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 123814462 2.03.937.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.04.034.554 I slot launch_slot_: id 0 | task 10284 | processing task, is_child = 0 2.05.292.152 I slot print_timing: id 0 | task 10284 | prompt eval time = 145.60 ms / 404 tokens ( 0.36 ms per token, 2774.65 tokens per second) 2.05.292.160 I slot print_timing: id 0 | task 10284 | eval time = 1111.97 ms / 120 tokens ( 9.34 ms per token, 107.02 tokens per second) 2.05.292.161 I slot print_timing: id 0 | task 10284 | total time = 1257.58 ms / 524 tokens 2.05.292.161 I slot print_timing: id 0 | task 10284 | graphs reused = 9714 2.05.292.162 I slot print_timing: id 0 | task 10284 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.292.191 I slot release: id 0 | task 10284 | stop processing: n_tokens = 555, truncated = 0 2.05.318.417 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 125197297 2.05.318.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.05.414.610 I slot launch_slot_: id 0 | task 10407 | processing task, is_child = 0 2.06.522.365 I slot print_timing: id 0 | task 10407 | prompt eval time = 131.70 ms / 345 tokens ( 0.38 ms per token, 2619.55 tokens per second) 2.06.522.370 I slot print_timing: id 0 | task 10407 | eval time = 976.03 ms / 106 tokens ( 9.30 ms per token, 107.58 tokens per second) 2.06.522.372 I slot print_timing: id 0 | task 10407 | total time = 1107.74 ms / 451 tokens 2.06.522.372 I slot print_timing: id 0 | task 10407 | graphs reused = 9818 2.06.522.373 I slot print_timing: id 0 | task 10407 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.522.401 I slot release: id 0 | task 10407 | stop processing: n_tokens = 482, truncated = 0 2.06.545.848 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 126427507 2.06.545.892 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.06.608.114 I slot launch_slot_: id 0 | task 10516 | processing task, is_child = 0 2.07.730.528 I slot print_timing: id 0 | task 10516 | prompt eval time = 150.53 ms / 430 tokens ( 0.35 ms per token, 2856.61 tokens per second) 2.07.730.534 I slot print_timing: id 0 | task 10516 | eval time = 971.87 ms / 105 tokens ( 9.34 ms per token, 107.01 tokens per second) 2.07.730.535 I slot print_timing: id 0 | task 10516 | total time = 1122.39 ms / 535 tokens 2.07.730.535 I slot print_timing: id 0 | task 10516 | graphs reused = 9920 2.07.730.536 I slot print_timing: id 0 | task 10516 | graph reallocs = 0 / 0 (same size) / (changed size) 2.07.730.567 I slot release: id 0 | task 10516 | stop processing: n_tokens = 566, truncated = 0 2.07.758.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 127635672 2.07.759.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.07.814.722 I slot launch_slot_: id 0 | task 10624 | processing task, is_child = 0 2.08.752.948 I slot print_timing: id 0 | task 10624 | prompt eval time = 124.91 ms / 316 tokens ( 0.40 ms per token, 2529.86 tokens per second) 2.08.752.954 I slot print_timing: id 0 | task 10624 | eval time = 813.30 ms / 85 tokens ( 9.68 ms per token, 103.28 tokens per second) 2.08.752.955 I slot print_timing: id 0 | task 10624 | total time = 938.21 ms / 401 tokens 2.08.752.956 I slot print_timing: id 0 | task 10624 | graphs reused = 10003 2.08.752.956 I slot print_timing: id 0 | task 10624 | graph reallocs = 0 / 0 (same size) / (changed size) 2.08.752.986 I slot release: id 0 | task 10624 | stop processing: n_tokens = 432, truncated = 0 2.08.773.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 128658091 2.08.773.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.08.869.840 I slot launch_slot_: id 0 | task 10712 | processing task, is_child = 0 2.09.995.503 I slot print_timing: id 0 | task 10712 | prompt eval time = 135.70 ms / 354 tokens ( 0.38 ms per token, 2608.64 tokens per second) 2.09.995.509 I slot print_timing: id 0 | task 10712 | eval time = 989.94 ms / 107 tokens ( 9.34 ms per token, 107.08 tokens per second) 2.09.995.510 I slot print_timing: id 0 | task 10712 | total time = 1125.64 ms / 461 tokens 2.09.995.511 I slot print_timing: id 0 | task 10712 | graphs reused = 10108 2.09.995.511 I slot print_timing: id 0 | task 10712 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.995.544 I slot release: id 0 | task 10712 | stop processing: n_tokens = 492, truncated = 0 2.10.014.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 129900649 2.10.014.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.10.075.557 I slot launch_slot_: id 0 | task 10822 | processing task, is_child = 0 2.11.135.264 I slot print_timing: id 0 | task 10822 | prompt eval time = 152.43 ms / 438 tokens ( 0.35 ms per token, 2873.47 tokens per second) 2.11.135.270 I slot print_timing: id 0 | task 10822 | eval time = 907.26 ms / 98 tokens ( 9.35 ms per token, 106.92 tokens per second) 2.11.135.271 I slot print_timing: id 0 | task 10822 | total time = 1059.69 ms / 536 tokens 2.11.135.272 I slot print_timing: id 0 | task 10822 | graphs reused = 10203 2.11.135.272 I slot print_timing: id 0 | task 10822 | graph reallocs = 0 / 0 (same size) / (changed size) 2.11.135.303 I slot release: id 0 | task 10822 | stop processing: n_tokens = 567, truncated = 0 2.11.151.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 131040408 2.11.151.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.11.207.714 I slot launch_slot_: id 0 | task 10923 | processing task, is_child = 0 2.12.009.600 I slot print_timing: id 0 | task 10923 | prompt eval time = 153.09 ms / 457 tokens ( 0.33 ms per token, 2985.21 tokens per second) 2.12.009.605 I slot print_timing: id 0 | task 10923 | eval time = 648.78 ms / 70 tokens ( 9.40 ms per token, 106.35 tokens per second) 2.12.009.606 I slot print_timing: id 0 | task 10923 | total time = 801.87 ms / 527 tokens 2.12.009.607 I slot print_timing: id 0 | task 10923 | graphs reused = 10270 2.12.009.608 I slot print_timing: id 0 | task 10923 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.009.638 I slot release: id 0 | task 10923 | stop processing: n_tokens = 558, truncated = 0 2.12.032.178 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 131914743 2.12.032.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.12.124.242 I slot launch_slot_: id 0 | task 10996 | processing task, is_child = 0 2.13.191.838 I slot print_timing: id 0 | task 10996 | prompt eval time = 156.80 ms / 473 tokens ( 0.33 ms per token, 3016.58 tokens per second) 2.13.191.844 I slot print_timing: id 0 | task 10996 | eval time = 910.78 ms / 98 tokens ( 9.39 ms per token, 106.50 tokens per second) 2.13.191.845 I slot print_timing: id 0 | task 10996 | total time = 1067.58 ms / 571 tokens 2.13.191.846 I slot print_timing: id 0 | task 10996 | graphs reused = 10365 2.13.191.846 I slot print_timing: id 0 | task 10996 | graph reallocs = 0 / 0 (same size) / (changed size) 2.13.191.878 I slot release: id 0 | task 10996 | stop processing: n_tokens = 602, truncated = 0 2.13.214.803 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 133096983 2.13.214.859 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.13.312.619 I slot launch_slot_: id 0 | task 11097 | processing task, is_child = 0 2.14.106.250 I slot print_timing: id 0 | task 11097 | prompt eval time = 153.33 ms / 476 tokens ( 0.32 ms per token, 3104.44 tokens per second) 2.14.106.256 I slot print_timing: id 0 | task 11097 | eval time = 640.28 ms / 69 tokens ( 9.42 ms per token, 106.20 tokens per second) 2.14.106.257 I slot print_timing: id 0 | task 11097 | total time = 793.61 ms / 545 tokens 2.14.106.258 I slot print_timing: id 0 | task 11097 | graphs reused = 10431 2.14.106.258 I slot print_timing: id 0 | task 11097 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.106.291 I slot release: id 0 | task 11097 | stop processing: n_tokens = 576, truncated = 0 2.14.130.488 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 576, t_last = 134011397 2.14.130.544 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.14.222.000 I slot launch_slot_: id 0 | task 11169 | processing task, is_child = 0 2.15.370.467 I slot print_timing: id 0 | task 11169 | prompt eval time = 157.64 ms / 466 tokens ( 0.34 ms per token, 2956.16 tokens per second) 2.15.370.473 I slot print_timing: id 0 | task 11169 | eval time = 990.81 ms / 107 tokens ( 9.35 ms per token, 106.98 tokens per second) 2.15.370.474 I slot print_timing: id 0 | task 11169 | total time = 1148.45 ms / 573 tokens 2.15.370.475 I slot print_timing: id 0 | task 11169 | graphs reused = 10535 2.15.370.476 I slot print_timing: id 0 | task 11169 | graph reallocs = 0 / 0 (same size) / (changed size) 2.15.370.507 I slot release: id 0 | task 11169 | stop processing: n_tokens = 604, truncated = 0 2.15.392.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 135275612 2.15.392.549 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.15.487.291 I slot launch_slot_: id 0 | task 11279 | processing task, is_child = 0 2.16.349.457 I slot print_timing: id 0 | task 11279 | prompt eval time = 139.50 ms / 415 tokens ( 0.34 ms per token, 2974.97 tokens per second) 2.16.349.463 I slot print_timing: id 0 | task 11279 | eval time = 722.65 ms / 78 tokens ( 9.39 ms per token, 106.55 tokens per second) 2.16.349.463 I slot print_timing: id 0 | task 11279 | total time = 862.15 ms / 493 tokens 2.16.349.464 I slot print_timing: id 0 | task 11279 | graphs reused = 10610 2.16.349.465 I slot print_timing: id 0 | task 11279 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.349.496 I slot release: id 0 | task 11279 | stop processing: n_tokens = 524, truncated = 0 2.16.353.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 136254601 2.16.353.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.16.443.443 I slot launch_slot_: id 0 | task 11360 | processing task, is_child = 0 2.17.162.460 I slot print_timing: id 0 | task 11360 | prompt eval time = 131.51 ms / 352 tokens ( 0.37 ms per token, 2676.68 tokens per second) 2.17.162.466 I slot print_timing: id 0 | task 11360 | eval time = 587.49 ms / 64 tokens ( 9.33 ms per token, 107.24 tokens per second) 2.17.162.467 I slot print_timing: id 0 | task 11360 | total time = 719.00 ms / 416 tokens 2.17.162.467 I slot print_timing: id 0 | task 11360 | graphs reused = 10672 2.17.162.468 I slot print_timing: id 0 | task 11360 | graph reallocs = 0 / 0 (same size) / (changed size) 2.17.162.497 I slot release: id 0 | task 11360 | stop processing: n_tokens = 447, truncated = 0 2.17.180.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 137067602 2.17.180.529 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.17.270.333 I slot launch_slot_: id 0 | task 11427 | processing task, is_child = 0 2.18.672.011 I slot print_timing: id 0 | task 11427 | prompt eval time = 174.97 ms / 550 tokens ( 0.32 ms per token, 3143.38 tokens per second) 2.18.672.016 I slot print_timing: id 0 | task 11427 | eval time = 1226.69 ms / 133 tokens ( 9.29 ms per token, 107.61 tokens per second) 2.18.672.017 I slot print_timing: id 0 | task 11427 | total time = 1401.66 ms / 683 tokens 2.18.672.018 I slot print_timing: id 0 | task 11427 | graphs reused = 10803 2.18.672.019 I slot print_timing: id 0 | task 11427 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.672.054 I slot release: id 0 | task 11427 | stop processing: n_tokens = 714, truncated = 0 2.18.677.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 138577159 2.18.677.150 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.18.781.489 I slot launch_slot_: id 0 | task 11564 | processing task, is_child = 0 2.21.093.657 I slot print_timing: id 0 | task 11564 | prompt eval time = 209.86 ms / 772 tokens ( 0.27 ms per token, 3678.68 tokens per second) 2.21.093.663 I slot print_timing: id 0 | task 11564 | eval time = 2102.29 ms / 226 tokens ( 9.34 ms per token, 107.03 tokens per second) 2.21.093.664 I slot print_timing: id 0 | task 11564 | total time = 2312.15 ms / 998 tokens 2.21.093.665 I slot print_timing: id 0 | task 11564 | graphs reused = 11026 2.21.093.666 I slot print_timing: id 0 | task 11564 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.093.707 I slot release: id 0 | task 11564 | stop processing: n_tokens = 1029, truncated = 0 2.21.098.378 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 140998812 2.21.098.442 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.21.208.935 I slot launch_slot_: id 0 | task 11794 | processing task, is_child = 0 2.23.094.156 I slot print_timing: id 0 | task 11794 | prompt eval time = 204.25 ms / 683 tokens ( 0.30 ms per token, 3343.88 tokens per second) 2.23.094.162 I slot print_timing: id 0 | task 11794 | eval time = 1680.94 ms / 181 tokens ( 9.34 ms per token, 107.08 tokens per second) 2.23.094.163 I slot print_timing: id 0 | task 11794 | total time = 1885.20 ms / 864 tokens 2.23.094.164 I slot print_timing: id 0 | task 11794 | graphs reused = 11204 2.23.094.165 I slot print_timing: id 0 | task 11794 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.094.202 I slot release: id 0 | task 11794 | stop processing: n_tokens = 895, truncated = 0 2.23.113.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 142999307 2.23.113.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.23.196.197 I slot launch_slot_: id 0 | task 11979 | processing task, is_child = 0 2.25.400.836 I slot print_timing: id 0 | task 11979 | prompt eval time = 183.89 ms / 579 tokens ( 0.32 ms per token, 3148.69 tokens per second) 2.25.400.842 I slot print_timing: id 0 | task 11979 | eval time = 2020.73 ms / 218 tokens ( 9.31 ms per token, 107.39 tokens per second) 2.25.400.843 I slot print_timing: id 0 | task 11979 | total time = 2204.62 ms / 797 tokens 2.25.400.843 I slot print_timing: id 0 | task 11979 | graphs reused = 11419 2.25.400.844 I slot print_timing: id 0 | task 11979 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.400.880 I slot release: id 0 | task 11979 | stop processing: n_tokens = 828, truncated = 0 2.25.420.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 145305985 2.25.420.975 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.25.440.641 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.25.544.819 I slot launch_slot_: id 0 | task 12201 | processing task, is_child = 0 2.26.687.315 I slot print_timing: id 0 | task 12201 | prompt eval time = 165.82 ms / 500 tokens ( 0.33 ms per token, 3015.25 tokens per second) 2.26.687.321 I slot print_timing: id 0 | task 12201 | eval time = 976.65 ms / 106 tokens ( 9.30 ms per token, 107.51 tokens per second) 2.26.687.322 I slot print_timing: id 0 | task 12201 | total time = 1142.48 ms / 606 tokens 2.26.687.323 I slot print_timing: id 0 | task 12201 | graphs reused = 11523 2.26.687.323 I slot print_timing: id 0 | task 12201 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.687.356 I slot release: id 0 | task 12201 | stop processing: n_tokens = 637, truncated = 0 2.26.710.060 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 146592461 2.26.710.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.26.780.494 I slot launch_slot_: id 0 | task 12310 | processing task, is_child = 0 2.28.926.375 I slot print_timing: id 0 | task 12310 | prompt eval time = 210.55 ms / 776 tokens ( 0.27 ms per token, 3685.55 tokens per second) 2.28.926.380 I slot print_timing: id 0 | task 12310 | eval time = 1935.31 ms / 209 tokens ( 9.30 ms per token, 107.48 tokens per second) 2.28.926.381 I slot print_timing: id 0 | task 12310 | total time = 2145.86 ms / 985 tokens 2.28.926.382 I slot print_timing: id 0 | task 12310 | graphs reused = 11730 2.28.926.383 I slot print_timing: id 0 | task 12310 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.926.422 I slot release: id 0 | task 12310 | stop processing: n_tokens = 1016, truncated = 0 2.28.949.008 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 148831527 2.28.949.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.29.042.754 I slot launch_slot_: id 0 | task 12523 | processing task, is_child = 0 2.31.024.213 I slot print_timing: id 0 | task 12523 | prompt eval time = 164.24 ms / 504 tokens ( 0.33 ms per token, 3068.74 tokens per second) 2.31.024.219 I slot print_timing: id 0 | task 12523 | eval time = 1817.20 ms / 197 tokens ( 9.27 ms per token, 107.86 tokens per second) 2.31.024.220 I slot print_timing: id 0 | task 12523 | total time = 1981.44 ms / 701 tokens 2.31.024.220 I slot print_timing: id 0 | task 12523 | graphs reused = 11925 2.31.024.221 I slot print_timing: id 0 | task 12523 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.024.254 I slot release: id 0 | task 12523 | stop processing: n_tokens = 732, truncated = 0 2.31.051.307 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 150929360 2.31.051.375 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.31.137.406 I slot launch_slot_: id 0 | task 12723 | processing task, is_child = 0 2.33.246.874 I slot print_timing: id 0 | task 12723 | prompt eval time = 188.01 ms / 633 tokens ( 0.30 ms per token, 3366.82 tokens per second) 2.33.246.880 I slot print_timing: id 0 | task 12723 | eval time = 1921.44 ms / 207 tokens ( 9.33 ms per token, 107.21 tokens per second) 2.33.246.881 I slot print_timing: id 0 | task 12723 | total time = 2109.45 ms / 840 tokens 2.33.246.882 I slot print_timing: id 0 | task 12723 | graphs reused = 12129 2.33.246.883 I slot print_timing: id 0 | task 12723 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.246.921 I slot release: id 0 | task 12723 | stop processing: n_tokens = 871, truncated = 0 2.33.275.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 153152026 2.33.275.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.116 MiB) 2.33.390.673 I slot launch_slot_: id 0 | task 12934 | processing task, is_child = 0 2.34.777.532 I slot print_timing: id 0 | task 12934 | prompt eval time = 146.61 ms / 395 tokens ( 0.37 ms per token, 2694.15 tokens per second) 2.34.777.538 I slot print_timing: id 0 | task 12934 | eval time = 1240.22 ms / 134 tokens ( 9.32 ms per token, 107.24 tokens per second) 2.34.777.539 I slot print_timing: id 0 | task 12934 | total time = 1386.84 ms / 529 tokens 2.34.777.540 I slot print_timing: id 0 | task 12934 | graphs reused = 12260 2.34.777.541 I slot print_timing: id 0 | task 12934 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.777.573 I slot release: id 0 | task 12934 | stop processing: n_tokens = 560, truncated = 0 2.34.807.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 154682678 2.34.807.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.34.911.547 I slot launch_slot_: id 0 | task 13071 | processing task, is_child = 0 2.37.031.829 I slot print_timing: id 0 | task 13071 | prompt eval time = 179.83 ms / 584 tokens ( 0.31 ms per token, 3247.49 tokens per second) 2.37.031.835 I slot print_timing: id 0 | task 13071 | eval time = 1940.43 ms / 209 tokens ( 9.33 ms per token, 107.19 tokens per second) 2.37.031.836 I slot print_timing: id 0 | task 13071 | total time = 2120.26 ms / 793 tokens 2.37.031.837 I slot print_timing: id 0 | task 13071 | graphs reused = 12466 2.37.031.838 I slot print_timing: id 0 | task 13071 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.031.876 I slot release: id 0 | task 13071 | stop processing: n_tokens = 824, truncated = 0 2.37.052.209 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 156936981 2.37.052.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.37.157.888 I slot launch_slot_: id 0 | task 13284 | processing task, is_child = 0 2.39.493.138 I slot print_timing: id 0 | task 13284 | prompt eval time = 200.91 ms / 695 tokens ( 0.29 ms per token, 3459.19 tokens per second) 2.39.493.143 I slot print_timing: id 0 | task 13284 | eval time = 2134.32 ms / 230 tokens ( 9.32 ms per token, 107.29 tokens per second) 2.39.493.144 I slot print_timing: id 0 | task 13284 | total time = 2335.23 ms / 925 tokens 2.39.493.145 I slot print_timing: id 0 | task 13284 | graphs reused = 12693 2.39.493.146 I slot print_timing: id 0 | task 13284 | graph reallocs = 0 / 0 (same size) / (changed size) 2.39.493.184 I slot release: id 0 | task 13284 | stop processing: n_tokens = 956, truncated = 0 2.39.521.717 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 159398289 2.39.521.780 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.550 MiB) 2.39.630.362 I slot launch_slot_: id 0 | task 13518 | processing task, is_child = 0 2.41.639.063 I slot print_timing: id 0 | task 13518 | prompt eval time = 220.70 ms / 769 tokens ( 0.29 ms per token, 3484.43 tokens per second) 2.41.639.070 I slot print_timing: id 0 | task 13518 | eval time = 1787.98 ms / 191 tokens ( 9.41 ms per token, 106.26 tokens per second) 2.41.639.071 I slot print_timing: id 0 | task 13518 | total time = 2008.68 ms / 960 tokens 2.41.639.073 I slot print_timing: id 0 | task 13518 | graphs reused = 12882 2.41.639.074 I slot print_timing: id 0 | task 13518 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.639.122 I slot release: id 0 | task 13518 | stop processing: n_tokens = 991, truncated = 0 2.41.661.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 161544227 2.41.661.851 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 2.41.681.952 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 2.41.786.373 I slot launch_slot_: id 0 | task 13713 | processing task, is_child = 0 2.43.123.642 I slot print_timing: id 0 | task 13713 | prompt eval time = 181.45 ms / 576 tokens ( 0.32 ms per token, 3174.48 tokens per second) 2.43.123.648 I slot print_timing: id 0 | task 13713 | eval time = 1155.80 ms / 124 tokens ( 9.40 ms per token, 106.42 tokens per second) 2.43.123.649 I slot print_timing: id 0 | task 13713 | total time = 1337.25 ms / 700 tokens 2.43.123.650 I slot print_timing: id 0 | task 13713 | graphs reused = 13004 2.43.123.651 I slot print_timing: id 0 | task 13713 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.123.687 I slot release: id 0 | task 13713 | stop processing: n_tokens = 731, truncated = 0 2.43.144.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 163028792 2.43.144.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 2.43.218.187 I slot launch_slot_: id 0 | task 13841 | processing task, is_child = 0 2.45.966.941 I slot print_timing: id 0 | task 13841 | prompt eval time = 196.52 ms / 655 tokens ( 0.30 ms per token, 3333.06 tokens per second) 2.45.966.947 I slot print_timing: id 0 | task 13841 | eval time = 2552.22 ms / 275 tokens ( 9.31 ms per token, 107.36 tokens per second) 2.45.966.948 I slot print_timing: id 0 | task 13841 | total time = 2748.73 ms / 930 tokens 2.45.966.948 I slot print_timing: id 0 | task 13841 | graphs reused = 13276 2.45.966.949 I slot print_timing: id 0 | task 13841 | graph reallocs = 0 / 0 (same size) / (changed size) 2.45.966.991 I slot release: id 0 | task 13841 | stop processing: n_tokens = 961, truncated = 0 2.45.987.486 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 165872097 2.45.987.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.46.051.225 I slot launch_slot_: id 0 | task 14120 | processing task, is_child = 0 2.47.363.400 I slot print_timing: id 0 | task 14120 | prompt eval time = 189.84 ms / 621 tokens ( 0.31 ms per token, 3271.24 tokens per second) 2.47.363.406 I slot print_timing: id 0 | task 14120 | eval time = 1122.32 ms / 121 tokens ( 9.35 ms per token, 106.92 tokens per second) 2.47.363.407 I slot print_timing: id 0 | task 14120 | total time = 1312.16 ms / 742 tokens 2.47.363.408 I slot print_timing: id 0 | task 14120 | graphs reused = 13394 2.47.363.409 I slot print_timing: id 0 | task 14120 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.363.446 I slot release: id 0 | task 14120 | stop processing: n_tokens = 773, truncated = 0 2.47.389.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 167268551 2.47.389.335 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 2.47.500.552 I slot launch_slot_: id 0 | task 14245 | processing task, is_child = 0 2.49.450.466 I slot print_timing: id 0 | task 14245 | prompt eval time = 215.51 ms / 767 tokens ( 0.28 ms per token, 3559.05 tokens per second) 2.49.450.472 I slot print_timing: id 0 | task 14245 | eval time = 1734.39 ms / 184 tokens ( 9.48 ms per token, 105.51 tokens per second) 2.49.450.473 I slot print_timing: id 0 | task 14245 | total time = 1949.89 ms / 951 tokens 2.49.450.474 I slot print_timing: id 0 | task 14245 | graphs reused = 13576 2.49.450.475 I slot print_timing: id 0 | task 14245 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.450.521 I slot release: id 0 | task 14245 | stop processing: n_tokens = 982, truncated = 0 2.49.473.359 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 169355626 2.49.473.431 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 2.49.547.742 I slot launch_slot_: id 0 | task 14433 | processing task, is_child = 0 2.51.700.764 I slot print_timing: id 0 | task 14433 | prompt eval time = 234.85 ms / 864 tokens ( 0.27 ms per token, 3678.96 tokens per second) 2.51.700.770 I slot print_timing: id 0 | task 14433 | eval time = 1918.15 ms / 203 tokens ( 9.50 ms per token, 105.31 tokens per second) 2.51.700.771 I slot print_timing: id 0 | task 14433 | total time = 2153.00 ms / 1067 tokens 2.51.700.771 I slot print_timing: id 0 | task 14433 | graphs reused = 13776 2.51.700.772 I slot print_timing: id 0 | task 14433 | graph reallocs = 0 / 0 (same size) / (changed size) 2.51.700.817 I slot release: id 0 | task 14433 | stop processing: n_tokens = 1098, truncated = 0 2.51.716.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 171605922 2.51.716.974 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 2.51.727.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.51.807.162 I slot launch_slot_: id 0 | task 14640 | processing task, is_child = 0 2.53.203.093 I slot print_timing: id 0 | task 14640 | prompt eval time = 199.83 ms / 646 tokens ( 0.31 ms per token, 3232.72 tokens per second) 2.53.203.100 I slot print_timing: id 0 | task 14640 | eval time = 1196.08 ms / 129 tokens ( 9.34 ms per token, 107.02 tokens per second) 2.53.203.101 I slot print_timing: id 0 | task 14640 | total time = 1395.91 ms / 775 tokens 2.53.203.102 I slot print_timing: id 0 | task 14640 | graphs reused = 13902 2.53.203.103 I slot print_timing: id 0 | task 14640 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.203.148 I slot release: id 0 | task 14640 | stop processing: n_tokens = 806, truncated = 0 2.53.221.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 173108253 2.53.221.493 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.53.303.342 I slot launch_slot_: id 0 | task 14773 | processing task, is_child = 0 2.55.605.104 I slot print_timing: id 0 | task 14773 | prompt eval time = 203.98 ms / 720 tokens ( 0.28 ms per token, 3529.83 tokens per second) 2.55.605.110 I slot print_timing: id 0 | task 14773 | eval time = 2097.77 ms / 219 tokens ( 9.62 ms per token, 103.92 tokens per second) 2.55.605.111 I slot print_timing: id 0 | task 14773 | total time = 2301.74 ms / 939 tokens 2.55.605.111 I slot print_timing: id 0 | task 14773 | graphs reused = 14118 2.55.605.112 I slot print_timing: id 0 | task 14773 | graph reallocs = 0 / 0 (same size) / (changed size) 2.55.605.153 I slot release: id 0 | task 14773 | stop processing: n_tokens = 970, truncated = 0 2.55.609.492 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 175510258 2.55.609.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.517 MiB) 2.55.695.677 I slot launch_slot_: id 0 | task 14996 | processing task, is_child = 0 2.57.844.829 I slot print_timing: id 0 | task 14996 | prompt eval time = 168.66 ms / 509 tokens ( 0.33 ms per token, 3017.92 tokens per second) 2.57.844.836 I slot print_timing: id 0 | task 14996 | eval time = 1980.47 ms / 214 tokens ( 9.30 ms per token, 107.55 tokens per second) 2.57.844.837 I slot print_timing: id 0 | task 14996 | total time = 2149.13 ms / 723 tokens 2.57.844.839 I slot print_timing: id 0 | task 14996 | graphs reused = 14330 2.57.844.840 I slot print_timing: id 0 | task 14996 | graph reallocs = 0 / 0 (same size) / (changed size) 2.57.844.874 I slot release: id 0 | task 14996 | stop processing: n_tokens = 754, truncated = 0 2.57.863.405 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 177749980 2.57.863.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 2.57.949.434 I slot launch_slot_: id 0 | task 15213 | processing task, is_child = 0 3.00.372.204 I slot print_timing: id 0 | task 15213 | prompt eval time = 181.34 ms / 581 tokens ( 0.31 ms per token, 3203.89 tokens per second) 3.00.372.210 I slot print_timing: id 0 | task 15213 | eval time = 2241.41 ms / 242 tokens ( 9.30 ms per token, 107.52 tokens per second) 3.00.372.211 I slot print_timing: id 0 | task 15213 | total time = 2422.75 ms / 823 tokens 3.00.372.211 I slot print_timing: id 0 | task 15213 | graphs reused = 14569 3.00.372.212 I slot print_timing: id 0 | task 15213 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.372.249 I slot release: id 0 | task 15213 | stop processing: n_tokens = 854, truncated = 0 3.00.392.355 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 180277354 3.00.392.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.00.495.418 I slot launch_slot_: id 0 | task 15459 | processing task, is_child = 0 3.02.779.166 I slot print_timing: id 0 | task 15459 | prompt eval time = 241.67 ms / 925 tokens ( 0.26 ms per token, 3827.57 tokens per second) 3.02.779.171 I slot print_timing: id 0 | task 15459 | eval time = 2042.06 ms / 220 tokens ( 9.32 ms per token, 107.24 tokens per second) 3.02.779.172 I slot print_timing: id 0 | task 15459 | total time = 2283.73 ms / 1145 tokens 3.02.779.173 I slot print_timing: id 0 | task 15459 | graphs reused = 14786 3.02.779.174 I slot print_timing: id 0 | task 15459 | graph reallocs = 0 / 0 (same size) / (changed size) 3.02.779.220 I slot release: id 0 | task 15459 | stop processing: n_tokens = 1176, truncated = 0 3.02.799.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 182684325 3.02.799.376 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.02.906.141 I slot launch_slot_: id 0 | task 15683 | processing task, is_child = 0 3.05.442.762 I slot print_timing: id 0 | task 15683 | prompt eval time = 229.45 ms / 885 tokens ( 0.26 ms per token, 3857.07 tokens per second) 3.05.442.768 I slot print_timing: id 0 | task 15683 | eval time = 2307.15 ms / 245 tokens ( 9.46 ms per token, 105.76 tokens per second) 3.05.442.769 I slot print_timing: id 0 | task 15683 | total time = 2536.60 ms / 1130 tokens 3.05.442.770 I slot print_timing: id 0 | task 15683 | graphs reused = 15028 3.05.442.771 I slot print_timing: id 0 | task 15683 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.442.821 I slot release: id 0 | task 15683 | stop processing: n_tokens = 1161, truncated = 0 3.05.462.154 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 185347927 3.05.462.235 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.05.577.315 I slot launch_slot_: id 0 | task 15932 | processing task, is_child = 0 3.07.831.711 I slot print_timing: id 0 | task 15932 | prompt eval time = 147.00 ms / 392 tokens ( 0.37 ms per token, 2666.76 tokens per second) 3.07.831.717 I slot print_timing: id 0 | task 15932 | eval time = 2107.38 ms / 227 tokens ( 9.32 ms per token, 107.24 tokens per second) 3.07.831.718 I slot print_timing: id 0 | task 15932 | total time = 2254.38 ms / 619 tokens 3.07.831.719 I slot print_timing: id 0 | task 15932 | graphs reused = 15252 3.07.831.720 I slot print_timing: id 0 | task 15932 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.831.751 I slot release: id 0 | task 15932 | stop processing: n_tokens = 650, truncated = 0 3.07.845.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 187736856 3.07.845.690 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.07.940.158 I slot launch_slot_: id 0 | task 16162 | processing task, is_child = 0 3.08.528.197 I slot print_timing: id 0 | task 16162 | prompt eval time = 137.76 ms / 331 tokens ( 0.42 ms per token, 2402.68 tokens per second) 3.08.528.203 I slot print_timing: id 0 | task 16162 | eval time = 450.26 ms / 49 tokens ( 9.38 ms per token, 106.61 tokens per second) 3.08.528.204 I slot print_timing: id 0 | task 16162 | total time = 588.02 ms / 380 tokens 3.08.528.204 I slot print_timing: id 0 | task 16162 | graphs reused = 15299 3.08.528.205 I slot print_timing: id 0 | task 16162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.08.528.233 I slot release: id 0 | task 16162 | stop processing: n_tokens = 411, truncated = 0 3.08.543.851 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 188433338 3.08.543.897 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.08.631.186 I slot launch_slot_: id 0 | task 16214 | processing task, is_child = 0 3.10.264.507 I slot print_timing: id 0 | task 16214 | prompt eval time = 135.33 ms / 357 tokens ( 0.38 ms per token, 2638.00 tokens per second) 3.10.264.512 I slot print_timing: id 0 | task 16214 | eval time = 1497.97 ms / 161 tokens ( 9.36 ms per token, 106.81 tokens per second) 3.10.264.513 I slot print_timing: id 0 | task 16214 | total time = 1633.30 ms / 518 tokens 3.10.264.514 I slot print_timing: id 0 | task 16214 | graphs reused = 15457 3.10.264.515 I slot print_timing: id 0 | task 16214 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.264.543 I slot release: id 0 | task 16214 | stop processing: n_tokens = 549, truncated = 0 3.10.286.091 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 190169649 3.10.286.146 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.10.378.994 I slot launch_slot_: id 0 | task 16378 | processing task, is_child = 0 3.10.989.800 I slot print_timing: id 0 | task 16378 | prompt eval time = 135.51 ms / 315 tokens ( 0.43 ms per token, 2324.57 tokens per second) 3.10.989.806 I slot print_timing: id 0 | task 16378 | eval time = 475.28 ms / 52 tokens ( 9.32 ms per token, 107.31 tokens per second) 3.10.989.807 I slot print_timing: id 0 | task 16378 | total time = 610.79 ms / 367 tokens 3.10.989.808 I slot print_timing: id 0 | task 16378 | graphs reused = 15507 3.10.989.808 I slot print_timing: id 0 | task 16378 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.989.839 I slot release: id 0 | task 16378 | stop processing: n_tokens = 398, truncated = 0 3.11.007.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 190894944 3.11.007.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.11.094.378 I slot launch_slot_: id 0 | task 16433 | processing task, is_child = 0 3.12.073.851 I slot print_timing: id 0 | task 16433 | prompt eval time = 136.87 ms / 378 tokens ( 0.36 ms per token, 2761.83 tokens per second) 3.12.073.857 I slot print_timing: id 0 | task 16433 | eval time = 842.59 ms / 91 tokens ( 9.36 ms per token, 106.81 tokens per second) 3.12.073.858 I slot print_timing: id 0 | task 16433 | total time = 979.45 ms / 469 tokens 3.12.073.859 I slot print_timing: id 0 | task 16433 | graphs reused = 15596 3.12.073.859 I slot print_timing: id 0 | task 16433 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.073.889 I slot release: id 0 | task 16433 | stop processing: n_tokens = 500, truncated = 0 3.12.098.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 191978994 3.12.098.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.12.205.916 I slot launch_slot_: id 0 | task 16527 | processing task, is_child = 0 3.12.587.863 I slot print_timing: id 0 | task 16527 | prompt eval time = 127.11 ms / 295 tokens ( 0.43 ms per token, 2320.75 tokens per second) 3.12.587.869 I slot print_timing: id 0 | task 16527 | eval time = 254.81 ms / 28 tokens ( 9.44 ms per token, 105.96 tokens per second) 3.12.587.870 I slot print_timing: id 0 | task 16527 | total time = 381.93 ms / 323 tokens 3.12.587.871 I slot print_timing: id 0 | task 16527 | graphs reused = 15622 3.12.587.872 I slot print_timing: id 0 | task 16527 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.587.899 I slot release: id 0 | task 16527 | stop processing: n_tokens = 354, truncated = 0 3.12.610.766 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 192493004 3.12.610.805 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.12.685.193 I slot launch_slot_: id 0 | task 16558 | processing task, is_child = 0 3.14.227.200 I slot print_timing: id 0 | task 16558 | prompt eval time = 132.95 ms / 337 tokens ( 0.39 ms per token, 2534.75 tokens per second) 3.14.227.206 I slot print_timing: id 0 | task 16558 | eval time = 1409.04 ms / 152 tokens ( 9.33 ms per token, 107.17 tokens per second) 3.14.227.207 I slot print_timing: id 0 | task 16558 | total time = 1541.99 ms / 489 tokens 3.14.227.208 I slot print_timing: id 0 | task 16558 | graphs reused = 15771 3.14.227.209 I slot print_timing: id 0 | task 16558 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.227.239 I slot release: id 0 | task 16558 | stop processing: n_tokens = 520, truncated = 0 3.14.251.428 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 194132344 3.14.251.473 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.14.336.161 I slot launch_slot_: id 0 | task 16713 | processing task, is_child = 0 3.15.306.023 I slot print_timing: id 0 | task 16713 | prompt eval time = 130.60 ms / 325 tokens ( 0.40 ms per token, 2488.44 tokens per second) 3.15.306.028 I slot print_timing: id 0 | task 16713 | eval time = 839.24 ms / 91 tokens ( 9.32 ms per token, 107.24 tokens per second) 3.15.306.029 I slot print_timing: id 0 | task 16713 | total time = 969.84 ms / 416 tokens 3.15.306.030 I slot print_timing: id 0 | task 16713 | graphs reused = 15860 3.15.306.031 I slot print_timing: id 0 | task 16713 | graph reallocs = 0 / 0 (same size) / (changed size) 3.15.306.059 I slot release: id 0 | task 16713 | stop processing: n_tokens = 447, truncated = 0 3.15.309.712 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.072 3.15.361.578 I slot launch_slot_: id 0 | task 16807 | processing task, is_child = 0 3.16.355.781 I slot print_timing: id 0 | task 16807 | prompt eval time = 120.38 ms / 264 tokens ( 0.46 ms per token, 2192.98 tokens per second) 3.16.355.787 I slot print_timing: id 0 | task 16807 | eval time = 873.80 ms / 95 tokens ( 9.30 ms per token, 107.58 tokens per second) 3.16.355.788 I slot print_timing: id 0 | task 16807 | total time = 994.18 ms / 359 tokens 3.16.355.789 I slot print_timing: id 0 | task 16807 | graphs reused = 15953 3.16.355.790 I slot print_timing: id 0 | task 16807 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.355.815 I slot release: id 0 | task 16807 | stop processing: n_tokens = 390, truncated = 0 3.16.379.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 390, t_last = 196260920 3.16.379.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.16.472.428 I slot launch_slot_: id 0 | task 16905 | processing task, is_child = 0 3.16.951.088 I slot print_timing: id 0 | task 16905 | prompt eval time = 131.70 ms / 331 tokens ( 0.40 ms per token, 2513.25 tokens per second) 3.16.951.094 I slot print_timing: id 0 | task 16905 | eval time = 346.94 ms / 38 tokens ( 9.38 ms per token, 106.65 tokens per second) 3.16.951.095 I slot print_timing: id 0 | task 16905 | total time = 478.64 ms / 369 tokens 3.16.951.096 I slot print_timing: id 0 | task 16905 | graphs reused = 15989 3.16.951.096 I slot print_timing: id 0 | task 16905 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.951.125 I slot release: id 0 | task 16905 | stop processing: n_tokens = 400, truncated = 0 3.16.974.525 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 196856230 3.16.974.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.17.071.203 I slot launch_slot_: id 0 | task 16946 | processing task, is_child = 0 3.17.362.266 I slot print_timing: id 0 | task 16946 | prompt eval time = 134.69 ms / 333 tokens ( 0.40 ms per token, 2472.33 tokens per second) 3.17.362.272 I slot print_timing: id 0 | task 16946 | eval time = 156.35 ms / 17 tokens ( 9.77 ms per token, 102.33 tokens per second) 3.17.362.274 I slot print_timing: id 0 | task 16946 | total time = 291.04 ms / 350 tokens 3.17.362.274 I slot print_timing: id 0 | task 16946 | graphs reused = 16004 3.17.362.275 I slot print_timing: id 0 | task 16946 | graph reallocs = 0 / 0 (same size) / (changed size) 3.17.362.305 I slot release: id 0 | task 16946 | stop processing: n_tokens = 381, truncated = 0 3.17.380.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 381, t_last = 197267411 3.17.380.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.17.483.554 I slot launch_slot_: id 0 | task 16966 | processing task, is_child = 0 3.18.112.014 I slot print_timing: id 0 | task 16966 | prompt eval time = 136.90 ms / 346 tokens ( 0.40 ms per token, 2527.32 tokens per second) 3.18.112.019 I slot print_timing: id 0 | task 16966 | eval time = 491.54 ms / 53 tokens ( 9.45 ms per token, 105.79 tokens per second) 3.18.112.020 I slot print_timing: id 0 | task 16966 | total time = 628.44 ms / 399 tokens 3.18.112.021 I slot print_timing: id 0 | task 16966 | graphs reused = 16055 3.18.112.022 I slot print_timing: id 0 | task 16966 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.112.050 I slot release: id 0 | task 16966 | stop processing: n_tokens = 430, truncated = 0 3.18.127.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 198017156 3.18.127.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.18.216.898 I slot launch_slot_: id 0 | task 17022 | processing task, is_child = 0 3.18.893.137 I slot print_timing: id 0 | task 17022 | prompt eval time = 131.94 ms / 325 tokens ( 0.41 ms per token, 2463.24 tokens per second) 3.18.893.143 I slot print_timing: id 0 | task 17022 | eval time = 544.27 ms / 59 tokens ( 9.38 ms per token, 106.56 tokens per second) 3.18.893.144 I slot print_timing: id 0 | task 17022 | total time = 676.21 ms / 384 tokens 3.18.893.145 I slot print_timing: id 0 | task 17022 | graphs reused = 16112 3.18.893.146 I slot print_timing: id 0 | task 17022 | graph reallocs = 0 / 0 (same size) / (changed size) 3.18.893.179 I slot release: id 0 | task 17022 | stop processing: n_tokens = 415, truncated = 0 3.18.920.304 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 415, t_last = 198798284 3.18.920.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.18.986.000 I slot launch_slot_: id 0 | task 17084 | processing task, is_child = 0 3.21.827.964 I slot print_timing: id 0 | task 17084 | prompt eval time = 132.80 ms / 322 tokens ( 0.41 ms per token, 2424.74 tokens per second) 3.21.827.969 I slot print_timing: id 0 | task 17084 | eval time = 2709.14 ms / 292 tokens ( 9.31 ms per token, 107.41 tokens per second) 3.21.827.971 I slot print_timing: id 0 | task 17084 | total time = 2841.94 ms / 614 tokens 3.21.827.972 I slot print_timing: id 0 | task 17084 | graphs reused = 16401 3.21.827.973 I slot print_timing: id 0 | task 17084 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.828.005 I slot release: id 0 | task 17084 | stop processing: n_tokens = 645, truncated = 0 3.21.831.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 645, t_last = 201733110 3.21.899.327 I slot launch_slot_: id 0 | task 17379 | processing task, is_child = 0 3.24.774.359 I slot print_timing: id 0 | task 17379 | prompt eval time = 133.41 ms / 338 tokens ( 0.39 ms per token, 2533.58 tokens per second) 3.24.774.365 I slot print_timing: id 0 | task 17379 | eval time = 2741.60 ms / 296 tokens ( 9.29 ms per token, 107.60 tokens per second) 3.24.774.366 I slot print_timing: id 0 | task 17379 | total time = 2875.01 ms / 634 tokens 3.24.774.368 I slot print_timing: id 0 | task 17379 | graphs reused = 16694 3.24.774.369 I slot print_timing: id 0 | task 17379 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.774.397 I slot release: id 0 | task 17379 | stop processing: n_tokens = 665, truncated = 0 3.24.801.726 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 204679502 3.24.801.786 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.24.862.172 I slot launch_slot_: id 0 | task 17678 | processing task, is_child = 0 3.27.995.649 I slot print_timing: id 0 | task 17678 | n_gen = 324, tg = 107.59 t/s, tg_3s = 107.92 t/s 3.31.002.986 I slot print_timing: id 0 | task 17678 | n_gen = 647, tg = 107.50 t/s, tg_3s = 107.40 t/s 3.34.003.429 I slot print_timing: id 0 | task 17678 | n_gen = 968, tg = 107.33 t/s, tg_3s = 106.98 t/s 3.34.523.476 I slot print_timing: id 0 | task 17678 | prompt eval time = 131.31 ms / 347 tokens ( 0.38 ms per token, 2642.64 tokens per second) 3.34.523.482 I slot print_timing: id 0 | task 17678 | eval time = 9529.98 ms / 1024 tokens ( 9.32 ms per token, 107.35 tokens per second) 3.34.523.483 I slot print_timing: id 0 | task 17678 | total time = 9661.28 ms / 1371 tokens 3.34.523.484 I slot print_timing: id 0 | task 17678 | graphs reused = 17712 3.34.523.484 I slot print_timing: id 0 | task 17678 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.523.513 I slot release: id 0 | task 17678 | stop processing: n_tokens = 1402, truncated = 0 3.34.551.081 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 214428618 3.34.551.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.34.648.337 I slot launch_slot_: id 0 | task 18705 | processing task, is_child = 0 3.36.636.178 I slot print_timing: id 0 | task 18705 | prompt eval time = 132.11 ms / 331 tokens ( 0.40 ms per token, 2505.49 tokens per second) 3.36.636.183 I slot print_timing: id 0 | task 18705 | eval time = 1855.71 ms / 201 tokens ( 9.28 ms per token, 107.78 tokens per second) 3.36.636.184 I slot print_timing: id 0 | task 18705 | total time = 1987.82 ms / 532 tokens 3.36.636.185 I slot print_timing: id 0 | task 18705 | graphs reused = 17910 3.36.636.186 I slot print_timing: id 0 | task 18705 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.636.214 I slot release: id 0 | task 18705 | stop processing: n_tokens = 563, truncated = 0 3.36.661.537 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 563, t_last = 216541319 3.36.661.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.464 MiB) 3.36.725.753 I slot launch_slot_: id 0 | task 18909 | processing task, is_child = 0 3.37.822.834 I slot print_timing: id 0 | task 18909 | prompt eval time = 132.00 ms / 345 tokens ( 0.38 ms per token, 2613.58 tokens per second) 3.37.822.840 I slot print_timing: id 0 | task 18909 | eval time = 965.06 ms / 105 tokens ( 9.28 ms per token, 107.77 tokens per second) 3.37.822.841 I slot print_timing: id 0 | task 18909 | total time = 1097.06 ms / 450 tokens 3.37.822.841 I slot print_timing: id 0 | task 18909 | graphs reused = 18013 3.37.822.842 I slot print_timing: id 0 | task 18909 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.822.869 I slot release: id 0 | task 18909 | stop processing: n_tokens = 481, truncated = 0 3.37.842.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 481, t_last = 217727974 3.37.842.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.37.901.572 I slot launch_slot_: id 0 | task 19017 | processing task, is_child = 0 3.38.525.348 I slot print_timing: id 0 | task 19017 | prompt eval time = 130.63 ms / 320 tokens ( 0.41 ms per token, 2449.70 tokens per second) 3.38.525.353 I slot print_timing: id 0 | task 19017 | eval time = 493.13 ms / 54 tokens ( 9.30 ms per token, 107.48 tokens per second) 3.38.525.354 I slot print_timing: id 0 | task 19017 | total time = 623.76 ms / 374 tokens 3.38.525.355 I slot print_timing: id 0 | task 19017 | graphs reused = 18065 3.38.525.356 I slot print_timing: id 0 | task 19017 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.525.384 I slot release: id 0 | task 19017 | stop processing: n_tokens = 405, truncated = 0 3.38.542.338 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 218430489 3.38.542.382 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.38.629.613 I slot launch_slot_: id 0 | task 19074 | processing task, is_child = 0 3.39.225.740 I slot print_timing: id 0 | task 19074 | prompt eval time = 135.43 ms / 297 tokens ( 0.46 ms per token, 2193.00 tokens per second) 3.39.225.746 I slot print_timing: id 0 | task 19074 | eval time = 460.68 ms / 47 tokens ( 10.01 ms per token, 99.85 tokens per second) 3.39.225.747 I slot print_timing: id 0 | task 19074 | total time = 596.11 ms / 344 tokens 3.39.225.747 I slot print_timing: id 0 | task 19074 | graphs reused = 18110 3.39.225.748 I slot print_timing: id 0 | task 19074 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.225.775 I slot release: id 0 | task 19074 | stop processing: n_tokens = 375, truncated = 0 3.39.244.562 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 219130881 3.39.244.607 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.39.330.413 I slot launch_slot_: id 0 | task 19124 | processing task, is_child = 0 3.41.353.763 I slot print_timing: id 0 | task 19124 | prompt eval time = 131.95 ms / 343 tokens ( 0.38 ms per token, 2599.41 tokens per second) 3.41.353.769 I slot print_timing: id 0 | task 19124 | eval time = 1891.38 ms / 203 tokens ( 9.36 ms per token, 106.80 tokens per second) 3.41.353.770 I slot print_timing: id 0 | task 19124 | total time = 2023.33 ms / 546 tokens 3.41.353.772 I slot print_timing: id 0 | task 19124 | graphs reused = 18310 3.41.353.773 I slot print_timing: id 0 | task 19124 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.353.801 I slot release: id 0 | task 19124 | stop processing: n_tokens = 577, truncated = 0 3.41.370.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 221258906 3.41.433.358 I slot launch_slot_: id 0 | task 19330 | processing task, is_child = 0 3.42.804.615 I slot print_timing: id 0 | task 19330 | prompt eval time = 140.24 ms / 371 tokens ( 0.38 ms per token, 2645.43 tokens per second) 3.42.804.621 I slot print_timing: id 0 | task 19330 | eval time = 1231.00 ms / 133 tokens ( 9.33 ms per token, 107.23 tokens per second) 3.42.804.622 I slot print_timing: id 0 | task 19330 | total time = 1371.24 ms / 504 tokens 3.42.804.622 I slot print_timing: id 0 | task 19330 | graphs reused = 18440 3.42.804.623 I slot print_timing: id 0 | task 19330 | graph reallocs = 0 / 0 (same size) / (changed size) 3.42.804.654 I slot release: id 0 | task 19330 | stop processing: n_tokens = 535, truncated = 0 3.42.830.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 535, t_last = 222709759 3.42.830.591 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.42.921.820 I slot launch_slot_: id 0 | task 19466 | processing task, is_child = 0 3.44.482.824 I slot print_timing: id 0 | task 19466 | prompt eval time = 132.90 ms / 292 tokens ( 0.46 ms per token, 2197.21 tokens per second) 3.44.482.829 I slot print_timing: id 0 | task 19466 | eval time = 1428.09 ms / 155 tokens ( 9.27 ms per token, 107.84 tokens per second) 3.44.482.831 I slot print_timing: id 0 | task 19466 | total time = 1560.98 ms / 447 tokens 3.44.482.832 I slot print_timing: id 0 | task 19466 | graphs reused = 18593 3.44.482.833 I slot print_timing: id 0 | task 19466 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.482.861 I slot release: id 0 | task 19466 | stop processing: n_tokens = 478, truncated = 0 3.44.508.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 224387966 3.44.508.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 3.44.605.766 I slot launch_slot_: id 0 | task 19624 | processing task, is_child = 0 3.45.366.494 I slot print_timing: id 0 | task 19624 | prompt eval time = 127.85 ms / 301 tokens ( 0.42 ms per token, 2354.32 tokens per second) 3.45.366.500 I slot print_timing: id 0 | task 19624 | eval time = 632.86 ms / 69 tokens ( 9.31 ms per token, 107.45 tokens per second) 3.45.366.501 I slot print_timing: id 0 | task 19624 | total time = 760.71 ms / 370 tokens 3.45.366.502 I slot print_timing: id 0 | task 19624 | graphs reused = 18660 3.45.366.503 I slot print_timing: id 0 | task 19624 | graph reallocs = 0 / 0 (same size) / (changed size) 3.45.366.531 I slot release: id 0 | task 19624 | stop processing: n_tokens = 401, truncated = 0 3.45.370.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 225271636 3.45.370.051 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 3.45.464.388 I slot launch_slot_: id 0 | task 19696 | processing task, is_child = 0 3.46.649.207 I slot print_timing: id 0 | task 19696 | prompt eval time = 127.47 ms / 303 tokens ( 0.42 ms per token, 2377.01 tokens per second) 3.46.649.214 I slot print_timing: id 0 | task 19696 | eval time = 1057.33 ms / 115 tokens ( 9.27 ms per token, 107.82 tokens per second) 3.46.649.216 I slot print_timing: id 0 | task 19696 | total time = 1184.80 ms / 418 tokens 3.46.649.216 I slot print_timing: id 0 | task 19696 | graphs reused = 18773 3.46.649.217 I slot print_timing: id 0 | task 19696 | graph reallocs = 0 / 0 (same size) / (changed size) 3.46.649.252 I slot release: id 0 | task 19696 | stop processing: n_tokens = 449, truncated = 0 3.46.665.656 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 449, t_last = 226554357 3.46.665.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 3.46.757.314 I slot launch_slot_: id 0 | task 19814 | processing task, is_child = 0 3.47.374.787 I slot print_timing: id 0 | task 19814 | prompt eval time = 137.48 ms / 321 tokens ( 0.43 ms per token, 2334.94 tokens per second) 3.47.374.793 I slot print_timing: id 0 | task 19814 | eval time = 479.98 ms / 52 tokens ( 9.41 ms per token, 106.26 tokens per second) 3.47.374.794 I slot print_timing: id 0 | task 19814 | total time = 617.45 ms / 373 tokens 3.47.374.795 I slot print_timing: id 0 | task 19814 | graphs reused = 18823 3.47.374.795 I slot print_timing: id 0 | task 19814 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.374.824 I slot release: id 0 | task 19814 | stop processing: n_tokens = 404, truncated = 0 3.47.398.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 227279929 3.47.398.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 3.47.468.751 I slot launch_slot_: id 0 | task 19869 | processing task, is_child = 0 3.48.315.759 I slot print_timing: id 0 | task 19869 | prompt eval time = 132.09 ms / 322 tokens ( 0.41 ms per token, 2437.82 tokens per second) 3.48.315.766 I slot print_timing: id 0 | task 19869 | eval time = 714.90 ms / 78 tokens ( 9.28 ms per token, 107.71 tokens per second) 3.48.315.767 I slot print_timing: id 0 | task 19869 | total time = 846.99 ms / 400 tokens 3.48.315.768 I slot print_timing: id 0 | task 19869 | graphs reused = 18899 3.48.315.769 I slot print_timing: id 0 | task 19869 | graph reallocs = 0 / 0 (same size) / (changed size) 3.48.315.801 I slot release: id 0 | task 19869 | stop processing: n_tokens = 431, truncated = 0 3.48.332.442 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 431, t_last = 228220906 3.48.332.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.357 MiB) 3.48.399.878 I slot launch_slot_: id 0 | task 19950 | processing task, is_child = 0 3.49.538.155 I slot print_timing: id 0 | task 19950 | prompt eval time = 130.04 ms / 323 tokens ( 0.40 ms per token, 2483.77 tokens per second) 3.49.538.162 I slot print_timing: id 0 | task 19950 | eval time = 1008.21 ms / 109 tokens ( 9.34 ms per token, 107.12 tokens per second) 3.49.538.163 I slot print_timing: id 0 | task 19950 | total time = 1138.26 ms / 432 tokens 3.49.538.163 I slot print_timing: id 0 | task 19950 | graphs reused = 19006 3.49.538.164 I slot print_timing: id 0 | task 19950 | graph reallocs = 0 / 0 (same size) / (changed size) 3.49.538.192 I slot release: id 0 | task 19950 | stop processing: n_tokens = 463, truncated = 0 3.49.556.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 463, t_last = 229443297 3.49.556.060 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 3.49.639.959 I slot launch_slot_: id 0 | task 20062 | processing task, is_child = 0 3.52.778.506 I slot print_timing: id 0 | task 20062 | n_gen = 325, tg = 107.81 t/s, tg_3s = 108.14 t/s 3.53.333.718 I slot print_timing: id 0 | task 20062 | prompt eval time = 133.25 ms / 321 tokens ( 0.42 ms per token, 2408.92 tokens per second) 3.53.333.723 I slot print_timing: id 0 | task 20062 | eval time = 3560.48 ms / 385 tokens ( 9.27 ms per token, 107.85 tokens per second) 3.53.333.724 I slot print_timing: id 0 | task 20062 | total time = 3693.74 ms / 706 tokens 3.53.333.725 I slot print_timing: id 0 | task 20062 | graphs reused = 19388 3.53.333.726 I slot print_timing: id 0 | task 20062 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.333.754 I slot release: id 0 | task 20062 | stop processing: n_tokens = 737, truncated = 0 3.53.361.811 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 233238859 3.53.361.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.950 MiB) 3.53.441.349 I slot launch_slot_: id 0 | task 20450 | processing task, is_child = 0 3.55.873.689 I slot print_timing: id 0 | task 20450 | prompt eval time = 132.01 ms / 322 tokens ( 0.41 ms per token, 2439.26 tokens per second) 3.55.873.695 I slot print_timing: id 0 | task 20450 | eval time = 2300.31 ms / 249 tokens ( 9.28 ms per token, 107.81 tokens per second) 3.55.873.695 I slot print_timing: id 0 | task 20450 | total time = 2432.32 ms / 571 tokens 3.55.873.696 I slot print_timing: id 0 | task 20450 | graphs reused = 19634 3.55.873.697 I slot print_timing: id 0 | task 20450 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.873.726 I slot release: id 0 | task 20450 | stop processing: n_tokens = 602, truncated = 0 3.55.896.243 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 235778832 3.55.896.298 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.140 MiB) 3.55.980.799 I slot launch_slot_: id 0 | task 20702 | processing task, is_child = 0 3.56.534.410 I slot print_timing: id 0 | task 20702 | prompt eval time = 132.63 ms / 337 tokens ( 0.39 ms per token, 2540.81 tokens per second) 3.56.534.415 I slot print_timing: id 0 | task 20702 | eval time = 420.96 ms / 46 tokens ( 9.35 ms per token, 106.90 tokens per second) 3.56.534.416 I slot print_timing: id 0 | task 20702 | total time = 553.59 ms / 383 tokens 3.56.534.417 I slot print_timing: id 0 | task 20702 | graphs reused = 19678 3.56.534.418 I slot print_timing: id 0 | task 20702 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.534.447 I slot release: id 0 | task 20702 | stop processing: n_tokens = 414, truncated = 0 3.56.550.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 236439552 3.56.550.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 3.56.633.035 I slot launch_slot_: id 0 | task 20751 | processing task, is_child = 0 3.57.195.550 I slot print_timing: id 0 | task 20751 | prompt eval time = 132.57 ms / 325 tokens ( 0.41 ms per token, 2451.55 tokens per second) 3.57.195.556 I slot print_timing: id 0 | task 20751 | eval time = 429.92 ms / 47 tokens ( 9.35 ms per token, 107.00 tokens per second) 3.57.195.559 I slot print_timing: id 0 | task 20751 | total time = 562.49 ms / 372 tokens 3.57.195.561 I slot print_timing: id 0 | task 20751 | graphs reused = 19723 3.57.195.562 I slot print_timing: id 0 | task 20751 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.195.593 I slot release: id 0 | task 20751 | stop processing: n_tokens = 403, truncated = 0 3.57.219.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 237100698 3.57.219.524 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 3.57.307.449 I slot launch_slot_: id 0 | task 20801 | processing task, is_child = 0 3.58.387.451 I slot print_timing: id 0 | task 20801 | prompt eval time = 133.24 ms / 331 tokens ( 0.40 ms per token, 2484.31 tokens per second) 3.58.387.456 I slot print_timing: id 0 | task 20801 | eval time = 946.75 ms / 103 tokens ( 9.28 ms per token, 107.74 tokens per second) 3.58.387.457 I slot print_timing: id 0 | task 20801 | total time = 1079.98 ms / 434 tokens 3.58.387.460 I slot print_timing: id 0 | task 20801 | graphs reused = 19824 3.58.387.460 I slot print_timing: id 0 | task 20801 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.387.489 I slot release: id 0 | task 20801 | stop processing: n_tokens = 465, truncated = 0 3.58.409.551 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 238292594 3.58.409.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.58.498.647 I slot launch_slot_: id 0 | task 20907 | processing task, is_child = 0 3.59.476.630 I slot print_timing: id 0 | task 20907 | prompt eval time = 132.80 ms / 336 tokens ( 0.40 ms per token, 2530.12 tokens per second) 3.59.476.635 I slot print_timing: id 0 | task 20907 | eval time = 845.16 ms / 92 tokens ( 9.29 ms per token, 107.67 tokens per second) 3.59.476.636 I slot print_timing: id 0 | task 20907 | total time = 977.96 ms / 428 tokens 3.59.476.637 I slot print_timing: id 0 | task 20907 | graphs reused = 19914 3.59.476.637 I slot print_timing: id 0 | task 20907 | graph reallocs = 0 / 0 (same size) / (changed size) 3.59.476.666 I slot release: id 0 | task 20907 | stop processing: n_tokens = 459, truncated = 0 3.59.502.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 459, t_last = 239381771 3.59.502.325 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.700 MiB) 3.59.595.971 I slot launch_slot_: id 0 | task 21002 | processing task, is_child = 0 4.00.010.541 I slot print_timing: id 0 | task 21002 | prompt eval time = 133.19 ms / 349 tokens ( 0.38 ms per token, 2620.30 tokens per second) 4.00.010.547 I slot print_timing: id 0 | task 21002 | eval time = 281.36 ms / 31 tokens ( 9.38 ms per token, 106.62 tokens per second) 4.00.010.548 I slot print_timing: id 0 | task 21002 | total time = 414.55 ms / 380 tokens 4.00.010.549 I slot print_timing: id 0 | task 21002 | graphs reused = 19943 4.00.010.550 I slot print_timing: id 0 | task 21002 | graph reallocs = 0 / 0 (same size) / (changed size) 4.00.010.578 I slot release: id 0 | task 21002 | stop processing: n_tokens = 411, truncated = 0 4.00.014.397 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 239915683 4.00.014.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.013 MiB) 4.00.102.379 I slot launch_slot_: id 0 | task 21036 | processing task, is_child = 0 4.03.151.181 I slot print_timing: id 0 | task 21036 | prompt eval time = 132.42 ms / 336 tokens ( 0.39 ms per token, 2537.46 tokens per second) 4.03.151.187 I slot print_timing: id 0 | task 21036 | eval time = 2916.37 ms / 315 tokens ( 9.29 ms per token, 107.67 tokens per second) 4.03.151.188 I slot print_timing: id 0 | task 21036 | total time = 3048.78 ms / 651 tokens 4.03.151.189 I slot print_timing: id 0 | task 21036 | graphs reused = 20255 4.03.151.190 I slot print_timing: id 0 | task 21036 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.151.218 I slot release: id 0 | task 21036 | stop processing: n_tokens = 682, truncated = 0 4.03.169.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 682, t_last = 243056323 4.03.170.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.419 MiB) 4.03.272.535 I slot launch_slot_: id 0 | task 21354 | processing task, is_child = 0 4.06.410.670 I slot print_timing: id 0 | task 21354 | n_gen = 325, tg = 107.85 t/s, tg_3s = 108.18 t/s 4.08.498.928 I slot print_timing: id 0 | task 21354 | prompt eval time = 133.90 ms / 349 tokens ( 0.38 ms per token, 2606.52 tokens per second) 4.08.498.935 I slot print_timing: id 0 | task 21354 | eval time = 5092.48 ms / 550 tokens ( 9.28 ms per token, 107.81 tokens per second) 4.08.498.937 I slot print_timing: id 0 | task 21354 | total time = 5226.37 ms / 899 tokens 4.08.498.937 I slot print_timing: id 0 | task 21354 | graphs reused = 20801 4.08.498.939 I slot print_timing: id 0 | task 21354 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.498.973 I slot release: id 0 | task 21354 | stop processing: n_tokens = 930, truncated = 0 4.08.522.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 930, t_last = 248404078 4.08.522.593 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.08.621.741 I slot launch_slot_: id 0 | task 21907 | processing task, is_child = 0 4.09.543.351 I slot print_timing: id 0 | task 21907 | prompt eval time = 132.06 ms / 349 tokens ( 0.38 ms per token, 2642.66 tokens per second) 4.09.543.357 I slot print_timing: id 0 | task 21907 | eval time = 789.53 ms / 86 tokens ( 9.29 ms per token, 107.66 tokens per second) 4.09.543.358 I slot print_timing: id 0 | task 21907 | total time = 921.59 ms / 435 tokens 4.09.543.358 I slot print_timing: id 0 | task 21907 | graphs reused = 20885 4.09.543.359 I slot print_timing: id 0 | task 21907 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.543.389 I slot release: id 0 | task 21907 | stop processing: n_tokens = 466, truncated = 0 4.09.547.299 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 466, t_last = 249448494 4.09.547.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.482 MiB) 4.09.607.069 I slot launch_slot_: id 0 | task 21996 | processing task, is_child = 0 4.10.037.265 I slot print_timing: id 0 | task 21996 | prompt eval time = 139.16 ms / 385 tokens ( 0.36 ms per token, 2766.68 tokens per second) 4.10.037.270 I slot print_timing: id 0 | task 21996 | eval time = 291.02 ms / 32 tokens ( 9.39 ms per token, 106.52 tokens per second) 4.10.037.271 I slot print_timing: id 0 | task 21996 | total time = 430.18 ms / 417 tokens 4.10.037.272 I slot print_timing: id 0 | task 21996 | graphs reused = 20915 4.10.037.273 I slot print_timing: id 0 | task 21996 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.037.304 I slot release: id 0 | task 21996 | stop processing: n_tokens = 448, truncated = 0 4.10.064.567 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 249942409 4.10.064.610 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.675 MiB) 4.10.154.893 I slot launch_slot_: id 0 | task 22031 | processing task, is_child = 0 4.10.809.760 I slot print_timing: id 0 | task 22031 | prompt eval time = 132.46 ms / 328 tokens ( 0.40 ms per token, 2476.20 tokens per second) 4.10.809.768 I slot print_timing: id 0 | task 22031 | eval time = 522.39 ms / 57 tokens ( 9.33 ms per token, 107.20 tokens per second) 4.10.809.769 I slot print_timing: id 0 | task 22031 | total time = 654.85 ms / 385 tokens 4.10.809.770 I slot print_timing: id 0 | task 22031 | graphs reused = 20970 4.10.809.771 I slot print_timing: id 0 | task 22031 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.809.798 I slot release: id 0 | task 22031 | stop processing: n_tokens = 416, truncated = 0