$ 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-Q4_K_M.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.102.079 I srv llama_server: initializing ... 0.00.102.085 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.102.199 I srv init_listene: The UI is disabled 0.00.102.201 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.102.279 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) 0.00.115.250 I srv load_model: loading model 'C:\quantdiff\hf-cache\models--bartowski--Qwen_Qwen3.5-9B-GGUF\snapshots\182be2fd6c7bc44887d88a91cb03ff009cc9f549\Qwen_Qwen3.5-9B-Q4_K_M.gguf' 0.01.057.374 W model has unused tensor blk.32.attn_norm.weight (size = 16384 bytes) -- ignoring 0.01.057.389 W model has unused tensor blk.32.post_attention_norm.weight (size = 16384 bytes) -- ignoring 0.01.057.415 W model has unused tensor blk.32.attn_q.weight (size = 35651584 bytes) -- ignoring 0.01.057.426 W model has unused tensor blk.32.attn_k.weight (size = 4456448 bytes) -- ignoring 0.01.057.435 W model has unused tensor blk.32.attn_v.weight (size = 4456448 bytes) -- ignoring 0.01.057.468 W model has unused tensor blk.32.attn_output.weight (size = 17825792 bytes) -- ignoring 0.01.057.479 W model has unused tensor blk.32.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.01.057.488 W model has unused tensor blk.32.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.01.057.497 W model has unused tensor blk.32.ffn_gate.weight (size = 53477376 bytes) -- ignoring 0.01.057.506 W model has unused tensor blk.32.ffn_down.weight (size = 53477376 bytes) -- ignoring 0.01.057.516 W model has unused tensor blk.32.ffn_up.weight (size = 53477376 bytes) -- ignoring 0.01.057.526 W model has unused tensor blk.32.nextn.eh_proj.weight (size = 35651584 bytes) -- ignoring 0.01.057.536 W model has unused tensor blk.32.nextn.enorm.weight (size = 16384 bytes) -- ignoring 0.01.057.547 W model has unused tensor blk.32.nextn.hnorm.weight (size = 16384 bytes) -- ignoring 0.01.057.577 W model has unused tensor blk.32.nextn.shared_head_norm.weight (size = 16384 bytes) -- ignoring 0.02.975.488 I cmn init: llama threadpool init, n_threads = 8 0.03.062.413 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.03.067.299 I srv llama_server: model loaded 0.03.067.306 I srv llama_server: listening on http://127.0.0.1:8089 0.04.557.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.557.744 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.05.219.742 I slot print_timing: id 0 | task 0 | prompt eval time = 232.14 ms / 368 tokens ( 0.63 ms per token, 1585.23 tokens per second) 0.05.219.748 I slot print_timing: id 0 | task 0 | eval time = 429.84 ms / 41 tokens ( 10.75 ms per token, 93.06 tokens per second) 0.05.219.749 I slot print_timing: id 0 | task 0 | total time = 661.98 ms / 409 tokens 0.05.219.756 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.05.219.757 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.219.790 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.05.241.188 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 5119813 0.05.277.334 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.05.839.550 I slot print_timing: id 0 | task 44 | prompt eval time = 125.40 ms / 322 tokens ( 0.39 ms per token, 2567.80 tokens per second) 0.05.839.556 I slot print_timing: id 0 | task 44 | eval time = 436.79 ms / 42 tokens ( 10.65 ms per token, 93.87 tokens per second) 0.05.839.557 I slot print_timing: id 0 | task 44 | total time = 562.19 ms / 364 tokens 0.05.839.558 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.05.839.559 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.839.587 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.05.866.059 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 5739610 0.05.902.761 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.06.464.744 I slot print_timing: id 0 | task 89 | prompt eval time = 126.71 ms / 365 tokens ( 0.35 ms per token, 2880.68 tokens per second) 0.06.464.750 I slot print_timing: id 0 | task 89 | eval time = 435.26 ms / 42 tokens ( 10.62 ms per token, 94.20 tokens per second) 0.06.464.751 I slot print_timing: id 0 | task 89 | total time = 561.96 ms / 407 tokens 0.06.464.752 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.06.464.753 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.06.464.786 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.06.491.113 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 6364809 0.06.527.584 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.07.121.959 I slot print_timing: id 0 | task 134 | prompt eval time = 142.23 ms / 397 tokens ( 0.36 ms per token, 2791.23 tokens per second) 0.07.121.965 I slot print_timing: id 0 | task 134 | eval time = 452.12 ms / 43 tokens ( 10.76 ms per token, 92.90 tokens per second) 0.07.121.966 I slot print_timing: id 0 | task 134 | total time = 594.35 ms / 440 tokens 0.07.121.967 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.07.121.970 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.122.004 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.07.149.873 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.117 (> 0.100 thold), f_keep = 0.103 0.07.198.550 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.07.916.034 I slot print_timing: id 0 | task 180 | prompt eval time = 132.31 ms / 383 tokens ( 0.35 ms per token, 2894.65 tokens per second) 0.07.916.064 I slot print_timing: id 0 | task 180 | eval time = 585.10 ms / 55 tokens ( 10.84 ms per token, 92.29 tokens per second) 0.07.916.067 I slot print_timing: id 0 | task 180 | total time = 717.41 ms / 438 tokens 0.07.916.072 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.07.916.074 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.916.251 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.07.931.446 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 7816281 0.08.043.715 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.08.789.774 I slot print_timing: id 0 | task 238 | prompt eval time = 151.98 ms / 372 tokens ( 0.41 ms per token, 2447.63 tokens per second) 0.08.789.780 I slot print_timing: id 0 | task 238 | eval time = 594.01 ms / 55 tokens ( 11.00 ms per token, 90.91 tokens per second) 0.08.789.781 I slot print_timing: id 0 | task 238 | total time = 745.99 ms / 427 tokens 0.08.789.782 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.08.789.783 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.08.789.813 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.08.793.844 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 8689836 0.08.820.219 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 0.09.541.642 I slot print_timing: id 0 | task 296 | prompt eval time = 145.93 ms / 422 tokens ( 0.35 ms per token, 2891.84 tokens per second) 0.09.541.649 I slot print_timing: id 0 | task 296 | eval time = 575.47 ms / 55 tokens ( 10.66 ms per token, 93.84 tokens per second) 0.09.541.649 I slot print_timing: id 0 | task 296 | total time = 721.40 ms / 477 tokens 0.09.541.650 I slot print_timing: id 0 | task 296 | graphs reused = 320 0.09.541.651 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.541.687 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 0.09.569.181 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 9441710 0.09.608.421 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 0.10.519.375 I slot print_timing: id 0 | task 354 | prompt eval time = 150.74 ms / 470 tokens ( 0.32 ms per token, 3117.89 tokens per second) 0.10.519.382 I slot print_timing: id 0 | task 354 | eval time = 760.18 ms / 72 tokens ( 10.71 ms per token, 93.40 tokens per second) 0.10.519.383 I slot print_timing: id 0 | task 354 | total time = 910.93 ms / 542 tokens 0.10.519.386 I slot print_timing: id 0 | task 354 | graphs reused = 389 0.10.519.387 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.519.425 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 0.10.523.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 10419448 0.10.560.377 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 0.11.176.887 I slot print_timing: id 0 | task 429 | prompt eval time = 128.19 ms / 345 tokens ( 0.37 ms per token, 2691.36 tokens per second) 0.11.176.893 I slot print_timing: id 0 | task 429 | eval time = 488.30 ms / 47 tokens ( 10.62 ms per token, 94.20 tokens per second) 0.11.176.894 I slot print_timing: id 0 | task 429 | total time = 616.49 ms / 392 tokens 0.11.176.895 I slot print_timing: id 0 | task 429 | graphs reused = 434 0.11.176.896 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.176.925 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 0.11.195.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 11076948 0.11.231.925 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 0.11.790.597 I slot print_timing: id 0 | task 479 | prompt eval time = 126.34 ms / 364 tokens ( 0.35 ms per token, 2881.07 tokens per second) 0.11.790.603 I slot print_timing: id 0 | task 479 | eval time = 432.31 ms / 41 tokens ( 10.81 ms per token, 92.53 tokens per second) 0.11.790.605 I slot print_timing: id 0 | task 479 | total time = 558.65 ms / 405 tokens 0.11.790.606 I slot print_timing: id 0 | task 479 | graphs reused = 473 0.11.790.607 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.11.790.638 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 0.11.819.398 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 11690661 0.11.849.642 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 0.12.693.936 I slot print_timing: id 0 | task 523 | prompt eval time = 132.27 ms / 376 tokens ( 0.35 ms per token, 2842.73 tokens per second) 0.12.693.941 I slot print_timing: id 0 | task 523 | eval time = 712.00 ms / 62 tokens ( 11.67 ms per token, 85.67 tokens per second) 0.12.693.943 I slot print_timing: id 0 | task 523 | total time = 844.27 ms / 438 tokens 0.12.693.944 I slot print_timing: id 0 | task 523 | graphs reused = 533 0.12.693.945 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.693.982 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 0.12.721.826 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 12594005 0.12.749.836 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 0.13.398.824 I slot print_timing: id 0 | task 588 | prompt eval time = 135.28 ms / 412 tokens ( 0.33 ms per token, 3045.47 tokens per second) 0.13.398.830 I slot print_timing: id 0 | task 588 | eval time = 513.68 ms / 47 tokens ( 11.17 ms per token, 89.55 tokens per second) 0.13.398.831 I slot print_timing: id 0 | task 588 | total time = 648.96 ms / 459 tokens 0.13.398.832 I slot print_timing: id 0 | task 588 | graphs reused = 578 0.13.398.833 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.13.398.869 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 0.13.423.121 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 13298892 0.13.452.402 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 0.14.250.204 I slot print_timing: id 0 | task 638 | prompt eval time = 129.47 ms / 376 tokens ( 0.34 ms per token, 2904.10 tokens per second) 0.14.250.219 I slot print_timing: id 0 | task 638 | eval time = 668.28 ms / 62 tokens ( 10.96 ms per token, 91.28 tokens per second) 0.14.250.221 I slot print_timing: id 0 | task 638 | total time = 797.76 ms / 438 tokens 0.14.250.223 I slot print_timing: id 0 | task 638 | graphs reused = 638 0.14.250.224 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.250.274 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 0.14.275.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 14150297 0.14.305.068 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 0.15.002.734 I slot print_timing: id 0 | task 703 | prompt eval time = 135.47 ms / 378 tokens ( 0.36 ms per token, 2790.27 tokens per second) 0.15.002.740 I slot print_timing: id 0 | task 703 | eval time = 562.16 ms / 52 tokens ( 11.02 ms per token, 90.72 tokens per second) 0.15.002.741 I slot print_timing: id 0 | task 703 | total time = 697.63 ms / 430 tokens 0.15.002.742 I slot print_timing: id 0 | task 703 | graphs reused = 688 0.15.002.742 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.002.776 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 0.15.032.020 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 14902799 0.15.062.363 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 0.15.878.430 I slot print_timing: id 0 | task 758 | prompt eval time = 149.84 ms / 367 tokens ( 0.41 ms per token, 2449.30 tokens per second) 0.15.878.435 I slot print_timing: id 0 | task 758 | eval time = 666.20 ms / 58 tokens ( 11.69 ms per token, 85.56 tokens per second) 0.15.878.436 I slot print_timing: id 0 | task 758 | total time = 816.04 ms / 425 tokens 0.15.878.437 I slot print_timing: id 0 | task 758 | graphs reused = 744 0.15.878.438 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.878.468 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 0.15.882.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 15778491 0.15.912.819 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.16.588.191 I slot print_timing: id 0 | task 819 | prompt eval time = 128.50 ms / 347 tokens ( 0.37 ms per token, 2700.35 tokens per second) 0.16.588.198 I slot print_timing: id 0 | task 819 | eval time = 546.85 ms / 51 tokens ( 10.94 ms per token, 91.43 tokens per second) 0.16.588.199 I slot print_timing: id 0 | task 819 | total time = 675.35 ms / 398 tokens 0.16.588.200 I slot print_timing: id 0 | task 819 | graphs reused = 793 0.16.588.201 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.16.588.233 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 0.16.612.597 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 16488256 0.16.643.966 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 0.17.207.827 I slot print_timing: id 0 | task 873 | prompt eval time = 128.19 ms / 369 tokens ( 0.35 ms per token, 2878.47 tokens per second) 0.17.207.833 I slot print_timing: id 0 | task 873 | eval time = 435.64 ms / 41 tokens ( 10.89 ms per token, 91.82 tokens per second) 0.17.207.834 I slot print_timing: id 0 | task 873 | total time = 563.84 ms / 410 tokens 0.17.207.835 I slot print_timing: id 0 | task 873 | graphs reused = 832 0.17.207.836 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.207.868 I slot release: id 0 | task 873 | stop processing: n_tokens = 409, truncated = 0 0.17.211.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 17107891 0.17.246.565 I slot launch_slot_: id 0 | task 917 | processing task, is_child = 0 0.17.810.115 I slot print_timing: id 0 | task 917 | prompt eval time = 125.87 ms / 352 tokens ( 0.36 ms per token, 2796.60 tokens per second) 0.17.810.122 I slot print_timing: id 0 | task 917 | eval time = 437.66 ms / 41 tokens ( 10.94 ms per token, 91.40 tokens per second) 0.17.810.123 I slot print_timing: id 0 | task 917 | total time = 563.53 ms / 393 tokens 0.17.810.124 I slot print_timing: id 0 | task 917 | graphs reused = 871 0.17.810.125 I slot print_timing: id 0 | task 917 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.810.158 I slot release: id 0 | task 917 | stop processing: n_tokens = 392, truncated = 0 0.17.837.572 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 17710181 0.17.876.765 I slot launch_slot_: id 0 | task 961 | processing task, is_child = 0 0.18.423.352 I slot print_timing: id 0 | task 961 | prompt eval time = 127.82 ms / 349 tokens ( 0.37 ms per token, 2730.47 tokens per second) 0.18.423.357 I slot print_timing: id 0 | task 961 | eval time = 418.75 ms / 40 tokens ( 10.74 ms per token, 93.14 tokens per second) 0.18.423.358 I slot print_timing: id 0 | task 961 | total time = 546.56 ms / 389 tokens 0.18.423.359 I slot print_timing: id 0 | task 961 | graphs reused = 909 0.18.423.360 I slot print_timing: id 0 | task 961 | graph reallocs = 0 / 0 (same size) / (changed size) 0.18.423.393 I slot release: id 0 | task 961 | stop processing: n_tokens = 388, truncated = 0 0.18.443.972 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 18323416 0.18.485.786 I slot launch_slot_: id 0 | task 1004 | processing task, is_child = 0 0.19.333.788 I slot print_timing: id 0 | task 1004 | prompt eval time = 138.18 ms / 384 tokens ( 0.36 ms per token, 2778.96 tokens per second) 0.19.333.794 I slot print_timing: id 0 | task 1004 | eval time = 709.80 ms / 63 tokens ( 11.45 ms per token, 87.35 tokens per second) 0.19.333.796 I slot print_timing: id 0 | task 1004 | total time = 847.98 ms / 447 tokens 0.19.333.797 I slot print_timing: id 0 | task 1004 | graphs reused = 970 0.19.333.798 I slot print_timing: id 0 | task 1004 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.333.833 I slot release: id 0 | task 1004 | stop processing: n_tokens = 446, truncated = 0 0.19.359.875 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 19233856 0.19.395.484 I slot launch_slot_: id 0 | task 1070 | processing task, is_child = 0 0.20.098.960 I slot print_timing: id 0 | task 1070 | prompt eval time = 126.25 ms / 356 tokens ( 0.35 ms per token, 2819.89 tokens per second) 0.20.098.967 I slot print_timing: id 0 | task 1070 | eval time = 577.21 ms / 54 tokens ( 10.89 ms per token, 91.82 tokens per second) 0.20.098.968 I slot print_timing: id 0 | task 1070 | total time = 703.45 ms / 410 tokens 0.20.098.970 I slot print_timing: id 0 | task 1070 | graphs reused = 1022 0.20.098.971 I slot print_timing: id 0 | task 1070 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.099.005 I slot release: id 0 | task 1070 | stop processing: n_tokens = 409, truncated = 0 0.20.120.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 19999028 0.20.159.297 I slot launch_slot_: id 0 | task 1127 | processing task, is_child = 0 0.21.045.971 I slot print_timing: id 0 | task 1127 | prompt eval time = 136.61 ms / 410 tokens ( 0.33 ms per token, 3001.33 tokens per second) 0.21.045.977 I slot print_timing: id 0 | task 1127 | eval time = 750.04 ms / 70 tokens ( 10.87 ms per token, 91.99 tokens per second) 0.21.045.978 I slot print_timing: id 0 | task 1127 | total time = 886.65 ms / 480 tokens 0.21.045.980 I slot print_timing: id 0 | task 1127 | graphs reused = 1090 0.21.045.981 I slot print_timing: id 0 | task 1127 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.046.013 I slot release: id 0 | task 1127 | stop processing: n_tokens = 479, truncated = 0 0.21.060.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 20946036 0.21.104.020 I slot launch_slot_: id 0 | task 1200 | processing task, is_child = 0 0.21.865.013 I slot print_timing: id 0 | task 1200 | prompt eval time = 136.31 ms / 385 tokens ( 0.35 ms per token, 2824.49 tokens per second) 0.21.865.023 I slot print_timing: id 0 | task 1200 | eval time = 624.66 ms / 58 tokens ( 10.96 ms per token, 91.25 tokens per second) 0.21.865.024 I slot print_timing: id 0 | task 1200 | total time = 760.97 ms / 443 tokens 0.21.865.025 I slot print_timing: id 0 | task 1200 | graphs reused = 1146 0.21.865.026 I slot print_timing: id 0 | task 1200 | graph reallocs = 0 / 0 (same size) / (changed size) 0.21.865.060 I slot release: id 0 | task 1200 | stop processing: n_tokens = 442, truncated = 0 0.21.869.103 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 21765083 0.21.917.030 I slot launch_slot_: id 0 | task 1261 | processing task, is_child = 0 0.22.812.353 I slot print_timing: id 0 | task 1261 | prompt eval time = 135.39 ms / 395 tokens ( 0.34 ms per token, 2917.48 tokens per second) 0.22.812.359 I slot print_timing: id 0 | task 1261 | eval time = 759.90 ms / 71 tokens ( 10.86 ms per token, 92.12 tokens per second) 0.22.812.361 I slot print_timing: id 0 | task 1261 | total time = 895.30 ms / 466 tokens 0.22.812.361 I slot print_timing: id 0 | task 1261 | graphs reused = 1215 0.22.812.362 I slot print_timing: id 0 | task 1261 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.812.394 I slot release: id 0 | task 1261 | stop processing: n_tokens = 465, truncated = 0 0.22.817.276 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 22712416 0.22.853.897 I slot launch_slot_: id 0 | task 1335 | processing task, is_child = 0 0.23.653.124 I slot print_timing: id 0 | task 1335 | prompt eval time = 138.37 ms / 430 tokens ( 0.32 ms per token, 3107.70 tokens per second) 0.23.653.130 I slot print_timing: id 0 | task 1335 | eval time = 660.84 ms / 62 tokens ( 10.83 ms per token, 92.31 tokens per second) 0.23.653.131 I slot print_timing: id 0 | task 1335 | total time = 799.20 ms / 492 tokens 0.23.653.133 I slot print_timing: id 0 | task 1335 | graphs reused = 1275 0.23.653.134 I slot print_timing: id 0 | task 1335 | graph reallocs = 0 / 0 (same size) / (changed size) 0.23.653.165 I slot release: id 0 | task 1335 | stop processing: n_tokens = 491, truncated = 0 0.23.657.135 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 23553188 0.23.697.885 I slot launch_slot_: id 0 | task 1400 | processing task, is_child = 0 0.24.495.008 I slot print_timing: id 0 | task 1400 | prompt eval time = 137.91 ms / 392 tokens ( 0.35 ms per token, 2842.33 tokens per second) 0.24.495.015 I slot print_timing: id 0 | task 1400 | eval time = 659.17 ms / 62 tokens ( 10.81 ms per token, 92.54 tokens per second) 0.24.495.016 I slot print_timing: id 0 | task 1400 | total time = 797.08 ms / 454 tokens 0.24.495.018 I slot print_timing: id 0 | task 1400 | graphs reused = 1335 0.24.495.018 I slot print_timing: id 0 | task 1400 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.495.061 I slot release: id 0 | task 1400 | stop processing: n_tokens = 453, truncated = 0 0.24.524.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 24395083 0.24.556.961 I slot launch_slot_: id 0 | task 1465 | processing task, is_child = 0 0.25.203.928 I slot print_timing: id 0 | task 1465 | prompt eval time = 125.89 ms / 350 tokens ( 0.36 ms per token, 2780.27 tokens per second) 0.25.203.934 I slot print_timing: id 0 | task 1465 | eval time = 521.06 ms / 49 tokens ( 10.86 ms per token, 92.12 tokens per second) 0.25.203.935 I slot print_timing: id 0 | task 1465 | total time = 646.94 ms / 399 tokens 0.25.203.936 I slot print_timing: id 0 | task 1465 | graphs reused = 1382 0.25.203.938 I slot print_timing: id 0 | task 1465 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.203.971 I slot release: id 0 | task 1465 | stop processing: n_tokens = 398, truncated = 0 0.25.208.350 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 25103994 0.25.252.229 I slot launch_slot_: id 0 | task 1517 | processing task, is_child = 0 0.26.036.295 I slot print_timing: id 0 | task 1517 | prompt eval time = 135.92 ms / 380 tokens ( 0.36 ms per token, 2795.68 tokens per second) 0.26.036.300 I slot print_timing: id 0 | task 1517 | eval time = 648.12 ms / 61 tokens ( 10.80 ms per token, 92.58 tokens per second) 0.26.036.302 I slot print_timing: id 0 | task 1517 | total time = 784.04 ms / 441 tokens 0.26.036.304 I slot print_timing: id 0 | task 1517 | graphs reused = 1441 0.26.036.305 I slot print_timing: id 0 | task 1517 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.036.337 I slot release: id 0 | task 1517 | stop processing: n_tokens = 440, truncated = 0 0.26.050.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 25936360 0.26.090.522 I slot launch_slot_: id 0 | task 1581 | processing task, is_child = 0 0.27.133.467 I slot print_timing: id 0 | task 1581 | prompt eval time = 151.31 ms / 410 tokens ( 0.37 ms per token, 2709.58 tokens per second) 0.27.133.474 I slot print_timing: id 0 | task 1581 | eval time = 891.60 ms / 80 tokens ( 11.29 ms per token, 88.60 tokens per second) 0.27.133.475 I slot print_timing: id 0 | task 1581 | total time = 1042.92 ms / 490 tokens 0.27.133.476 I slot print_timing: id 0 | task 1581 | graphs reused = 1519 0.27.133.478 I slot print_timing: id 0 | task 1581 | graph reallocs = 0 / 0 (same size) / (changed size) 0.27.133.515 I slot release: id 0 | task 1581 | stop processing: n_tokens = 489, truncated = 0 0.27.160.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 27033538 0.27.194.438 I slot launch_slot_: id 0 | task 1664 | processing task, is_child = 0 0.28.053.582 I slot print_timing: id 0 | task 1664 | prompt eval time = 136.53 ms / 387 tokens ( 0.35 ms per token, 2834.58 tokens per second) 0.28.053.588 I slot print_timing: id 0 | task 1664 | eval time = 722.59 ms / 68 tokens ( 10.78 ms per token, 92.72 tokens per second) 0.28.053.589 I slot print_timing: id 0 | task 1664 | total time = 859.12 ms / 455 tokens 0.28.053.590 I slot print_timing: id 0 | task 1664 | graphs reused = 1585 0.28.053.591 I slot print_timing: id 0 | task 1664 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.053.623 I slot release: id 0 | task 1664 | stop processing: n_tokens = 454, truncated = 0 0.28.081.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 27953646 0.28.120.915 I slot launch_slot_: id 0 | task 1735 | processing task, is_child = 0 0.28.878.052 I slot print_timing: id 0 | task 1735 | prompt eval time = 128.06 ms / 358 tokens ( 0.36 ms per token, 2795.59 tokens per second) 0.28.878.058 I slot print_timing: id 0 | task 1735 | eval time = 629.05 ms / 59 tokens ( 10.85 ms per token, 92.20 tokens per second) 0.28.878.060 I slot print_timing: id 0 | task 1735 | total time = 757.11 ms / 417 tokens 0.28.878.061 I slot print_timing: id 0 | task 1735 | graphs reused = 1642 0.28.878.062 I slot print_timing: id 0 | task 1735 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.878.106 I slot release: id 0 | task 1735 | stop processing: n_tokens = 416, truncated = 0 0.28.892.683 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 28778129 0.28.931.611 I slot launch_slot_: id 0 | task 1797 | processing task, is_child = 0 0.29.717.589 I slot print_timing: id 0 | task 1797 | prompt eval time = 132.62 ms / 359 tokens ( 0.37 ms per token, 2706.92 tokens per second) 0.29.717.595 I slot print_timing: id 0 | task 1797 | eval time = 653.33 ms / 56 tokens ( 11.88 ms per token, 84.18 tokens per second) 0.29.717.596 I slot print_timing: id 0 | task 1797 | total time = 785.95 ms / 415 tokens 0.29.717.597 I slot print_timing: id 0 | task 1797 | graphs reused = 1696 0.29.717.598 I slot print_timing: id 0 | task 1797 | graph reallocs = 0 / 0 (same size) / (changed size) 0.29.717.634 I slot release: id 0 | task 1797 | stop processing: n_tokens = 414, truncated = 0 0.29.746.282 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 29617657 0.29.783.924 I slot launch_slot_: id 0 | task 1856 | processing task, is_child = 0 0.30.567.227 I slot print_timing: id 0 | task 1856 | prompt eval time = 137.23 ms / 387 tokens ( 0.35 ms per token, 2820.14 tokens per second) 0.30.567.233 I slot print_timing: id 0 | task 1856 | eval time = 646.05 ms / 61 tokens ( 10.77 ms per token, 92.87 tokens per second) 0.30.567.235 I slot print_timing: id 0 | task 1856 | total time = 783.28 ms / 448 tokens 0.30.567.236 I slot print_timing: id 0 | task 1856 | graphs reused = 1755 0.30.567.237 I slot print_timing: id 0 | task 1856 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.567.281 I slot release: id 0 | task 1856 | stop processing: n_tokens = 447, truncated = 0 0.30.587.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 30467304 0.30.625.769 I slot launch_slot_: id 0 | task 1920 | processing task, is_child = 0 0.31.411.886 I slot print_timing: id 0 | task 1920 | prompt eval time = 136.00 ms / 410 tokens ( 0.33 ms per token, 3014.64 tokens per second) 0.31.411.892 I slot print_timing: id 0 | task 1920 | eval time = 650.09 ms / 61 tokens ( 10.83 ms per token, 92.30 tokens per second) 0.31.411.893 I slot print_timing: id 0 | task 1920 | total time = 786.09 ms / 471 tokens 0.31.411.894 I slot print_timing: id 0 | task 1920 | graphs reused = 1814 0.31.411.895 I slot print_timing: id 0 | task 1920 | graph reallocs = 0 / 0 (same size) / (changed size) 0.31.411.932 I slot release: id 0 | task 1920 | stop processing: n_tokens = 470, truncated = 0 0.31.437.090 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 31311955 0.31.490.702 I slot launch_slot_: id 0 | task 1984 | processing task, is_child = 0 0.32.163.421 I slot print_timing: id 0 | task 1984 | prompt eval time = 136.73 ms / 351 tokens ( 0.39 ms per token, 2567.12 tokens per second) 0.32.163.427 I slot print_timing: id 0 | task 1984 | eval time = 535.97 ms / 50 tokens ( 10.94 ms per token, 91.42 tokens per second) 0.32.163.428 I slot print_timing: id 0 | task 1984 | total time = 672.70 ms / 401 tokens 0.32.163.429 I slot print_timing: id 0 | task 1984 | graphs reused = 1862 0.32.163.431 I slot print_timing: id 0 | task 1984 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.163.469 I slot release: id 0 | task 1984 | stop processing: n_tokens = 400, truncated = 0 0.32.179.457 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 32063492 0.32.229.405 I slot launch_slot_: id 0 | task 2037 | processing task, is_child = 0 0.34.772.737 I slot print_timing: id 0 | task 2037 | prompt eval time = 139.19 ms / 393 tokens ( 0.35 ms per token, 2823.54 tokens per second) 0.34.772.743 I slot print_timing: id 0 | task 2037 | eval time = 2404.12 ms / 224 tokens ( 10.78 ms per token, 92.76 tokens per second) 0.34.772.744 I slot print_timing: id 0 | task 2037 | total time = 2543.30 ms / 617 tokens 0.34.772.745 I slot print_timing: id 0 | task 2037 | graphs reused = 2083 0.34.772.746 I slot print_timing: id 0 | task 2037 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.772.781 I slot release: id 0 | task 2037 | stop processing: n_tokens = 616, truncated = 0 0.34.795.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 34672804 0.34.838.368 I slot launch_slot_: id 0 | task 2264 | processing task, is_child = 0 0.35.304.120 I slot print_timing: id 0 | task 2264 | prompt eval time = 127.65 ms / 321 tokens ( 0.40 ms per token, 2514.73 tokens per second) 0.35.304.128 I slot print_timing: id 0 | task 2264 | eval time = 338.08 ms / 32 tokens ( 10.91 ms per token, 91.70 tokens per second) 0.35.304.129 I slot print_timing: id 0 | task 2264 | total time = 465.72 ms / 353 tokens 0.35.304.130 I slot print_timing: id 0 | task 2264 | graphs reused = 2113 0.35.304.131 I slot print_timing: id 0 | task 2264 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.304.178 I slot release: id 0 | task 2264 | stop processing: n_tokens = 352, truncated = 0 0.35.327.313 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 35204201 0.35.362.701 I slot launch_slot_: id 0 | task 2299 | processing task, is_child = 0 0.36.316.822 I slot print_timing: id 0 | task 2299 | prompt eval time = 135.62 ms / 330 tokens ( 0.41 ms per token, 2433.22 tokens per second) 0.36.316.828 I slot print_timing: id 0 | task 2299 | eval time = 818.48 ms / 77 tokens ( 10.77 ms per token, 92.86 tokens per second) 0.36.316.829 I slot print_timing: id 0 | task 2299 | total time = 954.10 ms / 407 tokens 0.36.316.829 I slot print_timing: id 0 | task 2299 | graphs reused = 2188 0.36.316.830 I slot print_timing: id 0 | task 2299 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.316.858 I slot release: id 0 | task 2299 | stop processing: n_tokens = 406, truncated = 0 0.36.338.301 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 36216881 0.36.378.757 I slot launch_slot_: id 0 | task 2379 | processing task, is_child = 0 0.36.846.075 I slot print_timing: id 0 | task 2379 | prompt eval time = 130.99 ms / 341 tokens ( 0.38 ms per token, 2603.17 tokens per second) 0.36.846.082 I slot print_timing: id 0 | task 2379 | eval time = 336.30 ms / 32 tokens ( 10.85 ms per token, 92.18 tokens per second) 0.36.846.083 I slot print_timing: id 0 | task 2379 | total time = 467.29 ms / 373 tokens 0.36.846.084 I slot print_timing: id 0 | task 2379 | graphs reused = 2218 0.36.846.085 I slot print_timing: id 0 | task 2379 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.846.115 I slot release: id 0 | task 2379 | stop processing: n_tokens = 372, truncated = 0 0.36.868.640 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 36746138 0.36.913.285 I slot launch_slot_: id 0 | task 2414 | processing task, is_child = 0 0.37.556.244 I slot print_timing: id 0 | task 2414 | prompt eval time = 136.09 ms / 338 tokens ( 0.40 ms per token, 2483.56 tokens per second) 0.37.556.250 I slot print_timing: id 0 | task 2414 | eval time = 506.84 ms / 48 tokens ( 10.78 ms per token, 92.73 tokens per second) 0.37.556.251 I slot print_timing: id 0 | task 2414 | total time = 642.93 ms / 386 tokens 0.37.556.253 I slot print_timing: id 0 | task 2414 | graphs reused = 2264 0.37.556.254 I slot print_timing: id 0 | task 2414 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.556.289 I slot release: id 0 | task 2414 | stop processing: n_tokens = 385, truncated = 0 0.37.560.208 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 37456312 0.37.601.784 I slot launch_slot_: id 0 | task 2465 | processing task, is_child = 0 0.38.338.394 I slot print_timing: id 0 | task 2465 | prompt eval time = 142.71 ms / 395 tokens ( 0.36 ms per token, 2767.81 tokens per second) 0.38.338.400 I slot print_timing: id 0 | task 2465 | eval time = 593.87 ms / 56 tokens ( 10.80 ms per token, 92.61 tokens per second) 0.38.338.402 I slot print_timing: id 0 | task 2465 | total time = 736.59 ms / 451 tokens 0.38.338.403 I slot print_timing: id 0 | task 2465 | graphs reused = 2318 0.38.338.404 I slot print_timing: id 0 | task 2465 | graph reallocs = 0 / 0 (same size) / (changed size) 0.38.338.439 I slot release: id 0 | task 2465 | stop processing: n_tokens = 450, truncated = 0 0.38.363.043 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 38238462 0.38.403.394 I slot launch_slot_: id 0 | task 2524 | processing task, is_child = 0 0.39.487.662 I slot print_timing: id 0 | task 2524 | prompt eval time = 200.79 ms / 528 tokens ( 0.38 ms per token, 2629.55 tokens per second) 0.39.487.668 I slot print_timing: id 0 | task 2524 | eval time = 883.45 ms / 83 tokens ( 10.77 ms per token, 92.82 tokens per second) 0.39.487.669 I slot print_timing: id 0 | task 2524 | total time = 1084.25 ms / 611 tokens 0.39.487.670 I slot print_timing: id 0 | task 2524 | graphs reused = 2399 0.39.487.671 I slot print_timing: id 0 | task 2524 | graph reallocs = 0 / 0 (same size) / (changed size) 0.39.487.704 I slot release: id 0 | task 2524 | stop processing: n_tokens = 610, truncated = 0 0.39.509.903 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 39387727 0.39.558.128 I slot launch_slot_: id 0 | task 2611 | processing task, is_child = 0 0.40.189.040 I slot print_timing: id 0 | task 2611 | prompt eval time = 153.12 ms / 331 tokens ( 0.46 ms per token, 2161.63 tokens per second) 0.40.189.047 I slot print_timing: id 0 | task 2611 | eval time = 477.74 ms / 45 tokens ( 10.86 ms per token, 92.10 tokens per second) 0.40.189.048 I slot print_timing: id 0 | task 2611 | total time = 630.87 ms / 376 tokens 0.40.189.049 I slot print_timing: id 0 | task 2611 | graphs reused = 2442 0.40.189.049 I slot print_timing: id 0 | task 2611 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.189.079 I slot release: id 0 | task 2611 | stop processing: n_tokens = 387, truncated = 0 0.40.212.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 40089102 0.40.263.935 I slot launch_slot_: id 0 | task 2659 | processing task, is_child = 0 0.40.983.151 I slot print_timing: id 0 | task 2659 | prompt eval time = 159.38 ms / 362 tokens ( 0.44 ms per token, 2271.33 tokens per second) 0.40.983.158 I slot print_timing: id 0 | task 2659 | eval time = 559.81 ms / 53 tokens ( 10.77 ms per token, 92.89 tokens per second) 0.40.983.160 I slot print_timing: id 0 | task 2659 | total time = 719.19 ms / 415 tokens 0.40.983.161 I slot print_timing: id 0 | task 2659 | graphs reused = 2493 0.40.983.162 I slot print_timing: id 0 | task 2659 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.983.205 I slot release: id 0 | task 2659 | stop processing: n_tokens = 426, truncated = 0 0.40.987.186 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 40883228 0.41.035.183 I slot launch_slot_: id 0 | task 2715 | processing task, is_child = 0 0.41.931.889 I slot print_timing: id 0 | task 2715 | prompt eval time = 164.48 ms / 419 tokens ( 0.39 ms per token, 2547.44 tokens per second) 0.41.931.895 I slot print_timing: id 0 | task 2715 | eval time = 732.20 ms / 69 tokens ( 10.77 ms per token, 92.87 tokens per second) 0.41.931.896 I slot print_timing: id 0 | task 2715 | total time = 896.68 ms / 488 tokens 0.41.931.898 I slot print_timing: id 0 | task 2715 | graphs reused = 2560 0.41.931.900 I slot print_timing: id 0 | task 2715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.931.944 I slot release: id 0 | task 2715 | stop processing: n_tokens = 499, truncated = 0 0.41.936.253 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 41831967 0.41.988.635 I slot launch_slot_: id 0 | task 2787 | processing task, is_child = 0 0.42.636.732 I slot print_timing: id 0 | task 2787 | prompt eval time = 183.36 ms / 423 tokens ( 0.43 ms per token, 2306.97 tokens per second) 0.42.636.739 I slot print_timing: id 0 | task 2787 | eval time = 464.71 ms / 44 tokens ( 10.81 ms per token, 92.53 tokens per second) 0.42.636.740 I slot print_timing: id 0 | task 2787 | total time = 648.07 ms / 467 tokens 0.42.636.742 I slot print_timing: id 0 | task 2787 | graphs reused = 2602 0.42.636.743 I slot print_timing: id 0 | task 2787 | graph reallocs = 0 / 0 (same size) / (changed size) 0.42.636.783 I slot release: id 0 | task 2787 | stop processing: n_tokens = 478, truncated = 0 0.42.658.974 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 42536806 0.42.707.662 I slot launch_slot_: id 0 | task 2834 | processing task, is_child = 0 0.43.318.661 I slot print_timing: id 0 | task 2834 | prompt eval time = 152.79 ms / 341 tokens ( 0.45 ms per token, 2231.78 tokens per second) 0.43.318.669 I slot print_timing: id 0 | task 2834 | eval time = 458.18 ms / 43 tokens ( 10.91 ms per token, 91.67 tokens per second) 0.43.318.671 I slot print_timing: id 0 | task 2834 | total time = 610.97 ms / 384 tokens 0.43.318.672 I slot print_timing: id 0 | task 2834 | graphs reused = 2643 0.43.318.673 I slot print_timing: id 0 | task 2834 | graph reallocs = 0 / 0 (same size) / (changed size) 0.43.318.726 I slot release: id 0 | task 2834 | stop processing: n_tokens = 395, truncated = 0 0.43.343.768 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 43218749 0.43.391.502 I slot launch_slot_: id 0 | task 2880 | processing task, is_child = 0 0.44.060.230 I slot print_timing: id 0 | task 2880 | prompt eval time = 155.07 ms / 356 tokens ( 0.44 ms per token, 2295.68 tokens per second) 0.44.060.235 I slot print_timing: id 0 | task 2880 | eval time = 513.63 ms / 47 tokens ( 11.17 ms per token, 89.56 tokens per second) 0.44.060.237 I slot print_timing: id 0 | task 2880 | total time = 668.70 ms / 403 tokens 0.44.060.237 I slot print_timing: id 0 | task 2880 | graphs reused = 2688 0.44.060.238 I slot print_timing: id 0 | task 2880 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.060.324 I slot release: id 0 | task 2880 | stop processing: n_tokens = 414, truncated = 0 0.44.064.447 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 43960348 0.44.064.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.511 MiB) 0.44.118.767 I slot launch_slot_: id 0 | task 2930 | processing task, is_child = 0 0.44.770.471 I slot print_timing: id 0 | task 2930 | prompt eval time = 161.98 ms / 362 tokens ( 0.45 ms per token, 2234.87 tokens per second) 0.44.770.478 I slot print_timing: id 0 | task 2930 | eval time = 489.70 ms / 46 tokens ( 10.88 ms per token, 91.89 tokens per second) 0.44.770.479 I slot print_timing: id 0 | task 2930 | total time = 651.68 ms / 408 tokens 0.44.770.481 I slot print_timing: id 0 | task 2930 | graphs reused = 2732 0.44.770.482 I slot print_timing: id 0 | task 2930 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.770.520 I slot release: id 0 | task 2930 | stop processing: n_tokens = 419, truncated = 0 0.44.786.521 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 44670543 0.44.786.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.104 MiB) 0.44.836.980 I slot launch_slot_: id 0 | task 2979 | processing task, is_child = 0 0.45.722.932 I slot print_timing: id 0 | task 2979 | prompt eval time = 162.68 ms / 391 tokens ( 0.42 ms per token, 2403.57 tokens per second) 0.45.722.939 I slot print_timing: id 0 | task 2979 | eval time = 723.25 ms / 68 tokens ( 10.79 ms per token, 92.64 tokens per second) 0.45.722.940 I slot print_timing: id 0 | task 2979 | total time = 885.93 ms / 459 tokens 0.45.722.941 I slot print_timing: id 0 | task 2979 | graphs reused = 2798 0.45.722.942 I slot print_timing: id 0 | task 2979 | graph reallocs = 0 / 0 (same size) / (changed size) 0.45.722.977 I slot release: id 0 | task 2979 | stop processing: n_tokens = 470, truncated = 0 0.45.738.620 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 45623000 0.45.738.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 0.45.811.131 I slot launch_slot_: id 0 | task 3050 | processing task, is_child = 0 0.46.542.455 I slot print_timing: id 0 | task 3050 | prompt eval time = 155.40 ms / 343 tokens ( 0.45 ms per token, 2207.24 tokens per second) 0.46.542.463 I slot print_timing: id 0 | task 3050 | eval time = 575.90 ms / 54 tokens ( 10.87 ms per token, 92.03 tokens per second) 0.46.542.464 I slot print_timing: id 0 | task 3050 | total time = 731.30 ms / 397 tokens 0.46.542.465 I slot print_timing: id 0 | task 3050 | graphs reused = 2850 0.46.542.466 I slot print_timing: id 0 | task 3050 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.542.500 I slot release: id 0 | task 3050 | stop processing: n_tokens = 408, truncated = 0 0.46.546.569 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 46442522 0.46.546.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.481 MiB) 0.46.554.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.46.605.171 I slot launch_slot_: id 0 | task 3107 | processing task, is_child = 0 0.47.253.063 I slot print_timing: id 0 | task 3107 | prompt eval time = 163.16 ms / 401 tokens ( 0.41 ms per token, 2457.70 tokens per second) 0.47.253.070 I slot print_timing: id 0 | task 3107 | eval time = 484.70 ms / 46 tokens ( 10.77 ms per token, 92.84 tokens per second) 0.47.253.071 I slot print_timing: id 0 | task 3107 | total time = 647.86 ms / 447 tokens 0.47.253.072 I slot print_timing: id 0 | task 3107 | graphs reused = 2894 0.47.253.073 I slot print_timing: id 0 | task 3107 | graph reallocs = 0 / 0 (same size) / (changed size) 0.47.253.108 I slot release: id 0 | task 3107 | stop processing: n_tokens = 458, truncated = 0 0.47.278.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 47153131 0.47.278.566 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.074 MiB) 0.47.340.618 I slot launch_slot_: id 0 | task 3156 | processing task, is_child = 0 0.48.210.006 I slot print_timing: id 0 | task 3156 | prompt eval time = 148.41 ms / 355 tokens ( 0.42 ms per token, 2391.96 tokens per second) 0.48.210.012 I slot print_timing: id 0 | task 3156 | eval time = 720.95 ms / 68 tokens ( 10.76 ms per token, 92.93 tokens per second) 0.48.210.013 I slot print_timing: id 0 | task 3156 | total time = 869.37 ms / 423 tokens 0.48.210.015 I slot print_timing: id 0 | task 3156 | graphs reused = 2960 0.48.210.016 I slot print_timing: id 0 | task 3156 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.210.050 I slot release: id 0 | task 3156 | stop processing: n_tokens = 434, truncated = 0 0.48.229.993 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 48110073 0.48.230.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.638 MiB) 0.48.279.281 I slot launch_slot_: id 0 | task 3227 | processing task, is_child = 0 0.49.081.381 I slot print_timing: id 0 | task 3227 | prompt eval time = 153.68 ms / 351 tokens ( 0.44 ms per token, 2283.92 tokens per second) 0.49.081.387 I slot print_timing: id 0 | task 3227 | eval time = 648.39 ms / 57 tokens ( 11.58 ms per token, 86.37 tokens per second) 0.49.081.388 I slot print_timing: id 0 | task 3227 | total time = 802.08 ms / 408 tokens 0.49.081.389 I slot print_timing: id 0 | task 3227 | graphs reused = 3015 0.49.081.390 I slot print_timing: id 0 | task 3227 | graph reallocs = 0 / 0 (same size) / (changed size) 0.49.081.424 I slot release: id 0 | task 3227 | stop processing: n_tokens = 419, truncated = 0 0.49.109.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 48981447 0.49.109.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 167.671 MiB) 0.49.117.210 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.980 MiB) 0.49.168.604 I slot launch_slot_: id 0 | task 3287 | processing task, is_child = 0 0.50.348.667 I slot print_timing: id 0 | task 3287 | prompt eval time = 181.67 ms / 475 tokens ( 0.38 ms per token, 2614.57 tokens per second) 0.50.348.674 I slot print_timing: id 0 | task 3287 | eval time = 998.36 ms / 93 tokens ( 10.85 ms per token, 92.15 tokens per second) 0.50.348.676 I slot print_timing: id 0 | task 3287 | total time = 1180.04 ms / 568 tokens 0.50.348.677 I slot print_timing: id 0 | task 3287 | graphs reused = 3105 0.50.348.678 I slot print_timing: id 0 | task 3287 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.348.725 I slot release: id 0 | task 3287 | stop processing: n_tokens = 579, truncated = 0 0.50.353.431 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 50248748 0.50.353.503 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.386 MiB) 0.50.406.149 I slot launch_slot_: id 0 | task 3383 | processing task, is_child = 0 0.51.571.656 I slot print_timing: id 0 | task 3383 | prompt eval time = 180.96 ms / 440 tokens ( 0.41 ms per token, 2431.53 tokens per second) 0.51.571.663 I slot print_timing: id 0 | task 3383 | eval time = 984.52 ms / 92 tokens ( 10.82 ms per token, 92.43 tokens per second) 0.51.571.664 I slot print_timing: id 0 | task 3383 | total time = 1165.47 ms / 532 tokens 0.51.571.665 I slot print_timing: id 0 | task 3383 | graphs reused = 3194 0.51.571.666 I slot print_timing: id 0 | task 3383 | graph reallocs = 0 / 0 (same size) / (changed size) 0.51.571.716 I slot release: id 0 | task 3383 | stop processing: n_tokens = 543, truncated = 0 0.51.598.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 51471739 0.51.599.026 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.51.645.455 I slot launch_slot_: id 0 | task 3478 | processing task, is_child = 0 0.52.381.496 I slot print_timing: id 0 | task 3478 | prompt eval time = 150.92 ms / 345 tokens ( 0.44 ms per token, 2286.04 tokens per second) 0.52.381.505 I slot print_timing: id 0 | task 3478 | eval time = 585.10 ms / 55 tokens ( 10.84 ms per token, 92.29 tokens per second) 0.52.381.506 I slot print_timing: id 0 | task 3478 | total time = 736.02 ms / 400 tokens 0.52.381.509 I slot print_timing: id 0 | task 3478 | graphs reused = 3247 0.52.381.510 I slot print_timing: id 0 | task 3478 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.381.555 I slot release: id 0 | task 3478 | stop processing: n_tokens = 411, truncated = 0 0.52.385.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 52281578 0.52.386.012 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.075 MiB) 0.52.390.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.418 MiB) 0.52.437.699 I slot launch_slot_: id 0 | task 3536 | processing task, is_child = 0 0.53.187.232 I slot print_timing: id 0 | task 3536 | prompt eval time = 166.31 ms / 382 tokens ( 0.44 ms per token, 2296.98 tokens per second) 0.53.187.238 I slot print_timing: id 0 | task 3536 | eval time = 583.20 ms / 55 tokens ( 10.80 ms per token, 92.59 tokens per second) 0.53.187.239 I slot print_timing: id 0 | task 3536 | total time = 749.51 ms / 437 tokens 0.53.187.241 I slot print_timing: id 0 | task 3536 | graphs reused = 3300 0.53.187.242 I slot print_timing: id 0 | task 3536 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.187.284 I slot release: id 0 | task 3536 | stop processing: n_tokens = 448, truncated = 0 0.53.191.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 53087307 0.53.191.069 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.168 MiB) 0.53.234.902 I slot launch_slot_: id 0 | task 3594 | processing task, is_child = 0 0.53.867.570 I slot print_timing: id 0 | task 3594 | prompt eval time = 156.25 ms / 337 tokens ( 0.46 ms per token, 2156.77 tokens per second) 0.53.867.576 I slot print_timing: id 0 | task 3594 | eval time = 476.39 ms / 45 tokens ( 10.83 ms per token, 92.36 tokens per second) 0.53.867.577 I slot print_timing: id 0 | task 3594 | total time = 632.64 ms / 382 tokens 0.53.867.578 I slot print_timing: id 0 | task 3594 | graphs reused = 3343 0.53.867.579 I slot print_timing: id 0 | task 3594 | graph reallocs = 0 / 0 (same size) / (changed size) 0.53.867.618 I slot release: id 0 | task 3594 | stop processing: n_tokens = 393, truncated = 0 0.53.895.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 53767641 0.53.895.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.012 MiB) 0.53.941.433 I slot launch_slot_: id 0 | task 3642 | processing task, is_child = 0 0.54.896.545 I slot print_timing: id 0 | task 3642 | prompt eval time = 157.45 ms / 402 tokens ( 0.39 ms per token, 2553.18 tokens per second) 0.54.896.552 I slot print_timing: id 0 | task 3642 | eval time = 797.64 ms / 70 tokens ( 11.56 ms per token, 86.51 tokens per second) 0.54.896.553 I slot print_timing: id 0 | task 3642 | total time = 955.09 ms / 472 tokens 0.54.896.554 I slot print_timing: id 0 | task 3642 | graphs reused = 3411 0.54.896.555 I slot print_timing: id 0 | task 3642 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.896.591 I slot release: id 0 | task 3642 | stop processing: n_tokens = 483, truncated = 0 0.54.923.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 54796614 0.54.923.095 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.167 MiB) 0.54.928.391 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.54.975.254 I slot launch_slot_: id 0 | task 3715 | processing task, is_child = 0 0.55.776.588 I slot print_timing: id 0 | task 3715 | prompt eval time = 197.74 ms / 549 tokens ( 0.36 ms per token, 2776.33 tokens per second) 0.55.776.594 I slot print_timing: id 0 | task 3715 | eval time = 603.45 ms / 57 tokens ( 10.78 ms per token, 92.80 tokens per second) 0.55.776.595 I slot print_timing: id 0 | task 3715 | total time = 801.19 ms / 606 tokens 0.55.776.596 I slot print_timing: id 0 | task 3715 | graphs reused = 3466 0.55.776.597 I slot print_timing: id 0 | task 3715 | graph reallocs = 0 / 0 (same size) / (changed size) 0.55.776.650 I slot release: id 0 | task 3715 | stop processing: n_tokens = 617, truncated = 0 0.55.781.527 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 55676673 0.55.781.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.011 MiB) 0.55.843.195 I slot launch_slot_: id 0 | task 3776 | processing task, is_child = 0 0.56.679.747 I slot print_timing: id 0 | task 3776 | prompt eval time = 215.76 ms / 616 tokens ( 0.35 ms per token, 2854.96 tokens per second) 0.56.679.755 I slot print_timing: id 0 | task 3776 | eval time = 620.76 ms / 58 tokens ( 10.89 ms per token, 91.82 tokens per second) 0.56.679.756 I slot print_timing: id 0 | task 3776 | total time = 836.52 ms / 674 tokens 0.56.679.757 I slot print_timing: id 0 | task 3776 | graphs reused = 3522 0.56.679.758 I slot print_timing: id 0 | task 3776 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.679.811 I slot release: id 0 | task 3776 | stop processing: n_tokens = 685, truncated = 0 0.56.686.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 56579834 0.56.686.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.886 MiB) 0.56.692.390 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.700 MiB) 0.56.754.815 I slot launch_slot_: id 0 | task 3838 | processing task, is_child = 0 0.57.653.357 I slot print_timing: id 0 | task 3838 | prompt eval time = 235.42 ms / 665 tokens ( 0.35 ms per token, 2824.70 tokens per second) 0.57.653.363 I slot print_timing: id 0 | task 3838 | eval time = 663.09 ms / 62 tokens ( 10.87 ms per token, 91.99 tokens per second) 0.57.653.364 I slot print_timing: id 0 | task 3838 | total time = 898.52 ms / 727 tokens 0.57.653.365 I slot print_timing: id 0 | task 3838 | graphs reused = 3582 0.57.653.366 I slot print_timing: id 0 | task 3838 | graph reallocs = 0 / 0 (same size) / (changed size) 0.57.653.409 I slot release: id 0 | task 3838 | stop processing: n_tokens = 738, truncated = 0 0.57.671.644 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 738, t_last = 57553432 0.57.671.708 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.543 MiB) 0.57.677.399 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.732 MiB) 0.57.741.744 I slot launch_slot_: id 0 | task 3904 | processing task, is_child = 0 0.58.553.302 I slot print_timing: id 0 | task 3904 | prompt eval time = 226.15 ms / 645 tokens ( 0.35 ms per token, 2852.08 tokens per second) 0.58.553.311 I slot print_timing: id 0 | task 3904 | eval time = 585.38 ms / 55 tokens ( 10.84 ms per token, 92.25 tokens per second) 0.58.553.313 I slot print_timing: id 0 | task 3904 | total time = 811.53 ms / 700 tokens 0.58.553.314 I slot print_timing: id 0 | task 3904 | graphs reused = 3635 0.58.553.316 I slot print_timing: id 0 | task 3904 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.553.372 I slot release: id 0 | task 3904 | stop processing: n_tokens = 711, truncated = 0 0.58.574.784 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 58453394 0.58.574.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.575 MiB) 0.58.636.689 I slot launch_slot_: id 0 | task 3963 | processing task, is_child = 0 0.59.376.281 I slot print_timing: id 0 | task 3963 | prompt eval time = 183.16 ms / 474 tokens ( 0.39 ms per token, 2587.94 tokens per second) 0.59.376.288 I slot print_timing: id 0 | task 3963 | eval time = 556.41 ms / 52 tokens ( 10.91 ms per token, 91.66 tokens per second) 0.59.376.289 I slot print_timing: id 0 | task 3963 | total time = 739.56 ms / 526 tokens 0.59.376.291 I slot print_timing: id 0 | task 3963 | graphs reused = 3684 0.59.376.292 I slot print_timing: id 0 | task 3963 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.376.332 I slot release: id 0 | task 3963 | stop processing: n_tokens = 537, truncated = 0 0.59.400.539 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 59276354 0.59.400.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.294 MiB) 0.59.409.074 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.107 MiB) 0.59.464.667 I slot launch_slot_: id 0 | task 4018 | processing task, is_child = 0 1.00.121.494 I slot print_timing: id 0 | task 4018 | prompt eval time = 211.89 ms / 617 tokens ( 0.34 ms per token, 2911.83 tokens per second) 1.00.121.502 I slot print_timing: id 0 | task 4018 | eval time = 444.91 ms / 42 tokens ( 10.85 ms per token, 92.15 tokens per second) 1.00.121.504 I slot print_timing: id 0 | task 4018 | total time = 656.80 ms / 659 tokens 1.00.121.505 I slot print_timing: id 0 | task 4018 | graphs reused = 3724 1.00.121.505 I slot print_timing: id 0 | task 4018 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.121.552 I slot release: id 0 | task 4018 | stop processing: n_tokens = 670, truncated = 0 1.00.138.257 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 60021575 1.00.138.317 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.919 MiB) 1.00.214.362 I slot launch_slot_: id 0 | task 4064 | processing task, is_child = 0 1.00.941.036 I slot print_timing: id 0 | task 4064 | prompt eval time = 216.08 ms / 601 tokens ( 0.36 ms per token, 2781.43 tokens per second) 1.00.941.043 I slot print_timing: id 0 | task 4064 | eval time = 510.57 ms / 48 tokens ( 10.86 ms per token, 92.05 tokens per second) 1.00.941.045 I slot print_timing: id 0 | task 4064 | total time = 726.65 ms / 649 tokens 1.00.941.046 I slot print_timing: id 0 | task 4064 | graphs reused = 3770 1.00.941.047 I slot print_timing: id 0 | task 4064 | graph reallocs = 0 / 0 (same size) / (changed size) 1.00.941.100 I slot release: id 0 | task 4064 | stop processing: n_tokens = 660, truncated = 0 1.00.966.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 60841122 1.00.966.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.199 MiB) 1.00.976.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.512 MiB) 1.01.046.733 I slot launch_slot_: id 0 | task 4116 | processing task, is_child = 0 1.01.743.379 I slot print_timing: id 0 | task 4116 | prompt eval time = 200.57 ms / 533 tokens ( 0.38 ms per token, 2657.48 tokens per second) 1.01.743.385 I slot print_timing: id 0 | task 4116 | eval time = 496.06 ms / 47 tokens ( 10.78 ms per token, 92.73 tokens per second) 1.01.743.386 I slot print_timing: id 0 | task 4116 | total time = 696.62 ms / 580 tokens 1.01.743.388 I slot print_timing: id 0 | task 4116 | graphs reused = 3815 1.01.743.389 I slot print_timing: id 0 | task 4116 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.743.423 I slot release: id 0 | task 4116 | stop processing: n_tokens = 591, truncated = 0 1.01.759.970 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 61643446 1.01.760.027 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 166.044 MiB) 1.01.840.707 I slot launch_slot_: id 0 | task 4167 | processing task, is_child = 0 1.02.586.428 I slot print_timing: id 0 | task 4167 | prompt eval time = 188.19 ms / 480 tokens ( 0.39 ms per token, 2550.64 tokens per second) 1.02.586.434 I slot print_timing: id 0 | task 4167 | eval time = 557.51 ms / 52 tokens ( 10.93 ms per token, 91.48 tokens per second) 1.02.586.435 I slot print_timing: id 0 | task 4167 | total time = 745.70 ms / 532 tokens 1.02.586.436 I slot print_timing: id 0 | task 4167 | graphs reused = 3864 1.02.586.437 I slot print_timing: id 0 | task 4167 | graph reallocs = 0 / 0 (same size) / (changed size) 1.02.586.472 I slot release: id 0 | task 4167 | stop processing: n_tokens = 560, truncated = 0 1.02.603.670 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 62486494 1.02.603.725 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.950 MiB) 1.02.615.944 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.761 MiB) 1.02.703.416 I slot launch_slot_: id 0 | task 4222 | processing task, is_child = 0 1.03.354.365 I slot print_timing: id 0 | task 4222 | prompt eval time = 206.95 ms / 567 tokens ( 0.36 ms per token, 2739.79 tokens per second) 1.03.354.370 I slot print_timing: id 0 | task 4222 | eval time = 443.97 ms / 42 tokens ( 10.83 ms per token, 92.35 tokens per second) 1.03.354.371 I slot print_timing: id 0 | task 4222 | total time = 650.92 ms / 609 tokens 1.03.354.372 I slot print_timing: id 0 | task 4222 | graphs reused = 3904 1.03.354.373 I slot print_timing: id 0 | task 4222 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.354.411 I slot release: id 0 | task 4222 | stop processing: n_tokens = 637, truncated = 0 1.03.383.082 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 63254434 1.03.383.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.699 MiB) 1.03.393.083 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.731 MiB) 1.03.477.498 I slot launch_slot_: id 0 | task 4268 | processing task, is_child = 0 1.04.351.771 I slot print_timing: id 0 | task 4268 | prompt eval time = 203.83 ms / 506 tokens ( 0.40 ms per token, 2482.45 tokens per second) 1.04.351.777 I slot print_timing: id 0 | task 4268 | eval time = 670.42 ms / 63 tokens ( 10.81 ms per token, 92.48 tokens per second) 1.04.351.779 I slot print_timing: id 0 | task 4268 | total time = 874.25 ms / 569 tokens 1.04.351.780 I slot print_timing: id 0 | task 4268 | graphs reused = 3965 1.04.351.781 I slot print_timing: id 0 | task 4268 | graph reallocs = 0 / 0 (same size) / (changed size) 1.04.351.818 I slot release: id 0 | task 4268 | stop processing: n_tokens = 597, truncated = 0 1.04.356.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 64251841 1.04.356.502 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 165.450 MiB) 1.04.366.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.261 MiB) 1.04.456.483 I slot launch_slot_: id 0 | task 4334 | processing task, is_child = 0 1.05.060.877 I slot print_timing: id 0 | task 4334 | prompt eval time = 175.01 ms / 436 tokens ( 0.40 ms per token, 2491.24 tokens per second) 1.05.060.885 I slot print_timing: id 0 | task 4334 | eval time = 429.35 ms / 40 tokens ( 11.01 ms per token, 90.83 tokens per second) 1.05.060.887 I slot print_timing: id 0 | task 4334 | total time = 604.37 ms / 476 tokens 1.05.060.890 I slot print_timing: id 0 | task 4334 | graphs reused = 4003 1.05.060.891 I slot print_timing: id 0 | task 4334 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.060.939 I slot release: id 0 | task 4334 | stop processing: n_tokens = 504, truncated = 0 1.05.066.525 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 64960965 1.05.066.594 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 170.016 MiB) 1.05.154.091 I slot launch_slot_: id 0 | task 4377 | processing task, is_child = 0 1.06.011.035 I slot print_timing: id 0 | task 4377 | prompt eval time = 199.81 ms / 519 tokens ( 0.38 ms per token, 2597.53 tokens per second) 1.06.011.043 I slot print_timing: id 0 | task 4377 | eval time = 657.11 ms / 62 tokens ( 10.77 ms per token, 92.83 tokens per second) 1.06.011.044 I slot print_timing: id 0 | task 4377 | total time = 856.92 ms / 581 tokens 1.06.011.045 I slot print_timing: id 0 | task 4377 | graphs reused = 4063 1.06.011.045 I slot print_timing: id 0 | task 4377 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.011.085 I slot release: id 0 | task 4377 | stop processing: n_tokens = 609, truncated = 0 1.06.030.748 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 65911108 1.06.030.814 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 161.760 MiB) 1.06.040.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 163.449 MiB) 1.06.119.901 I slot launch_slot_: id 0 | task 4443 | processing task, is_child = 0 1.06.793.323 I slot print_timing: id 0 | task 4443 | prompt eval time = 178.94 ms / 465 tokens ( 0.38 ms per token, 2598.68 tokens per second) 1.06.793.331 I slot print_timing: id 0 | task 4443 | eval time = 494.46 ms / 46 tokens ( 10.99 ms per token, 91.01 tokens per second) 1.06.793.333 I slot print_timing: id 0 | task 4443 | total time = 673.40 ms / 511 tokens 1.06.793.334 I slot print_timing: id 0 | task 4443 | graphs reused = 4106 1.06.793.335 I slot print_timing: id 0 | task 4443 | graph reallocs = 0 / 0 (same size) / (changed size) 1.06.793.384 I slot release: id 0 | task 4443 | stop processing: n_tokens = 542, truncated = 0 1.06.797.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 66693406 1.06.797.932 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.385 MiB) 1.06.809.517 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 162.792 MiB) 1.06.897.168 I slot launch_slot_: id 0 | task 4492 | processing task, is_child = 0 1.07.516.120 I slot print_timing: id 0 | task 4492 | prompt eval time = 184.38 ms / 431 tokens ( 0.43 ms per token, 2337.58 tokens per second) 1.07.516.126 I slot print_timing: id 0 | task 4492 | eval time = 434.55 ms / 41 tokens ( 10.86 ms per token, 92.05 tokens per second) 1.07.516.127 I slot print_timing: id 0 | task 4492 | total time = 618.92 ms / 472 tokens 1.07.516.127 I slot print_timing: id 0 | task 4492 | graphs reused = 4145 1.07.516.128 I slot print_timing: id 0 | task 4492 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.516.164 I slot release: id 0 | task 4492 | stop processing: n_tokens = 503, truncated = 0 1.07.544.000 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 67416187 1.07.544.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 164.825 MiB) 1.07.554.643 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 220.079 MiB) 1.07.632.611 I slot launch_slot_: id 0 | task 4536 | processing task, is_child = 0 1.08.288.250 I slot print_timing: id 0 | task 4536 | prompt eval time = 181.73 ms / 457 tokens ( 0.40 ms per token, 2514.69 tokens per second) 1.08.288.256 I slot print_timing: id 0 | task 4536 | eval time = 473.88 ms / 44 tokens ( 11.02 ms per token, 90.74 tokens per second) 1.08.288.257 I slot print_timing: id 0 | task 4536 | total time = 655.61 ms / 501 tokens 1.08.288.258 I slot print_timing: id 0 | task 4536 | graphs reused = 4186 1.08.288.259 I slot print_timing: id 0 | task 4536 | graph reallocs = 0 / 0 (same size) / (changed size) 1.08.288.300 I slot release: id 0 | task 4536 | stop processing: n_tokens = 532, truncated = 0 1.08.306.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 68188323 1.08.306.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.105 MiB) 1.08.378.297 I slot launch_slot_: id 0 | task 4583 | processing task, is_child = 0 1.09.000.152 I slot print_timing: id 0 | task 4583 | prompt eval time = 177.89 ms / 439 tokens ( 0.41 ms per token, 2467.80 tokens per second) 1.09.000.161 I slot print_timing: id 0 | task 4583 | eval time = 443.94 ms / 42 tokens ( 10.83 ms per token, 92.36 tokens per second) 1.09.000.162 I slot print_timing: id 0 | task 4583 | total time = 621.83 ms / 481 tokens 1.09.000.163 I slot print_timing: id 0 | task 4583 | graphs reused = 4226 1.09.000.164 I slot print_timing: id 0 | task 4583 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.000.204 I slot release: id 0 | task 4583 | stop processing: n_tokens = 512, truncated = 0 1.09.026.673 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 68900227 1.09.026.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.325 MiB) 1.09.038.228 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.608 MiB) 1.09.108.839 I slot launch_slot_: id 0 | task 4628 | processing task, is_child = 0 1.09.916.862 I slot print_timing: id 0 | task 4628 | prompt eval time = 213.85 ms / 606 tokens ( 0.35 ms per token, 2833.71 tokens per second) 1.09.916.868 I slot print_timing: id 0 | task 4628 | eval time = 594.15 ms / 56 tokens ( 10.80 ms per token, 92.57 tokens per second) 1.09.916.869 I slot print_timing: id 0 | task 4628 | total time = 808.00 ms / 662 tokens 1.09.916.870 I slot print_timing: id 0 | task 4628 | graphs reused = 4280 1.09.916.871 I slot print_timing: id 0 | task 4628 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.916.909 I slot release: id 0 | task 4628 | stop processing: n_tokens = 693, truncated = 0 1.09.921.429 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 69816932 1.09.921.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.951 MiB) 1.09.933.588 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.355 MiB) 1.10.018.871 I slot launch_slot_: id 0 | task 4688 | processing task, is_child = 0 1.10.640.655 I slot print_timing: id 0 | task 4688 | prompt eval time = 180.75 ms / 477 tokens ( 0.38 ms per token, 2639.02 tokens per second) 1.10.640.662 I slot print_timing: id 0 | task 4688 | eval time = 441.01 ms / 41 tokens ( 11.03 ms per token, 90.70 tokens per second) 1.10.640.663 I slot print_timing: id 0 | task 4688 | total time = 621.76 ms / 518 tokens 1.10.640.664 I slot print_timing: id 0 | task 4688 | graphs reused = 4318 1.10.640.665 I slot print_timing: id 0 | task 4688 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.640.702 I slot release: id 0 | task 4688 | stop processing: n_tokens = 549, truncated = 0 1.10.668.746 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 70540725 1.10.668.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.949 MiB) 1.10.751.628 I slot launch_slot_: id 0 | task 4732 | processing task, is_child = 0 1.11.653.961 I slot print_timing: id 0 | task 4732 | prompt eval time = 263.92 ms / 845 tokens ( 0.31 ms per token, 3201.78 tokens per second) 1.11.653.968 I slot print_timing: id 0 | task 4732 | eval time = 638.39 ms / 60 tokens ( 10.82 ms per token, 92.42 tokens per second) 1.11.653.970 I slot print_timing: id 0 | task 4732 | total time = 902.31 ms / 905 tokens 1.11.653.971 I slot print_timing: id 0 | task 4732 | graphs reused = 4376 1.11.653.971 I slot print_timing: id 0 | task 4732 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.654.026 I slot release: id 0 | task 4732 | stop processing: n_tokens = 936, truncated = 0 1.11.679.781 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 71554049 1.11.679.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.11.692.139 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.701 MiB) 1.11.787.187 I slot launch_slot_: id 0 | task 4796 | processing task, is_child = 0 1.12.425.437 I slot print_timing: id 0 | task 4796 | prompt eval time = 176.59 ms / 459 tokens ( 0.38 ms per token, 2599.21 tokens per second) 1.12.425.443 I slot print_timing: id 0 | task 4796 | eval time = 461.63 ms / 43 tokens ( 10.99 ms per token, 90.98 tokens per second) 1.12.425.444 I slot print_timing: id 0 | task 4796 | total time = 638.22 ms / 502 tokens 1.12.425.445 I slot print_timing: id 0 | task 4796 | graphs reused = 4416 1.12.425.446 I slot print_timing: id 0 | task 4796 | graph reallocs = 0 / 0 (same size) / (changed size) 1.12.425.485 I slot release: id 0 | task 4796 | stop processing: n_tokens = 533, truncated = 0 1.12.455.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 72325508 1.12.455.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.762 MiB) 1.12.522.163 I slot launch_slot_: id 0 | task 4842 | processing task, is_child = 0 1.13.238.670 I slot print_timing: id 0 | task 4842 | prompt eval time = 219.14 ms / 670 tokens ( 0.33 ms per token, 3057.36 tokens per second) 1.13.238.678 I slot print_timing: id 0 | task 4842 | eval time = 497.33 ms / 47 tokens ( 10.81 ms per token, 92.49 tokens per second) 1.13.238.680 I slot print_timing: id 0 | task 4842 | total time = 716.48 ms / 717 tokens 1.13.238.681 I slot print_timing: id 0 | task 4842 | graphs reused = 4461 1.13.238.682 I slot print_timing: id 0 | task 4842 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.238.757 I slot release: id 0 | task 4842 | stop processing: n_tokens = 748, truncated = 0 1.13.244.306 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 73138782 1.13.244.363 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.325 MiB) 1.13.257.928 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.575 MiB) 1.13.349.255 I slot launch_slot_: id 0 | task 4893 | processing task, is_child = 0 1.14.306.850 I slot print_timing: id 0 | task 4893 | prompt eval time = 250.00 ms / 775 tokens ( 0.32 ms per token, 3100.04 tokens per second) 1.14.306.858 I slot print_timing: id 0 | task 4893 | eval time = 707.57 ms / 63 tokens ( 11.41 ms per token, 87.62 tokens per second) 1.14.306.859 I slot print_timing: id 0 | task 4893 | total time = 957.56 ms / 838 tokens 1.14.306.861 I slot print_timing: id 0 | task 4893 | graphs reused = 4522 1.14.306.862 I slot print_timing: id 0 | task 4893 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.306.921 I slot release: id 0 | task 4893 | stop processing: n_tokens = 869, truncated = 0 1.14.312.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 74206944 1.14.312.088 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 214.106 MiB) 1.14.323.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 219.110 MiB) 1.14.403.509 I slot launch_slot_: id 0 | task 4960 | processing task, is_child = 0 1.15.375.038 I slot print_timing: id 0 | task 4960 | prompt eval time = 207.68 ms / 573 tokens ( 0.36 ms per token, 2759.07 tokens per second) 1.15.375.045 I slot print_timing: id 0 | task 4960 | eval time = 763.83 ms / 71 tokens ( 10.91 ms per token, 91.64 tokens per second) 1.15.375.046 I slot print_timing: id 0 | task 4960 | total time = 971.50 ms / 644 tokens 1.15.375.048 I slot print_timing: id 0 | task 4960 | graphs reused = 4591 1.15.375.049 I slot print_timing: id 0 | task 4960 | graph reallocs = 0 / 0 (same size) / (changed size) 1.15.375.091 I slot release: id 0 | task 4960 | stop processing: n_tokens = 675, truncated = 0 1.15.390.886 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 75275113 1.15.390.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.984 MiB) 1.15.399.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.856 MiB) 1.15.475.887 I slot launch_slot_: id 0 | task 5035 | processing task, is_child = 0 1.16.343.186 I slot print_timing: id 0 | task 5035 | prompt eval time = 181.71 ms / 461 tokens ( 0.39 ms per token, 2537.08 tokens per second) 1.16.343.191 I slot print_timing: id 0 | task 5035 | eval time = 685.57 ms / 64 tokens ( 10.88 ms per token, 91.89 tokens per second) 1.16.343.192 I slot print_timing: id 0 | task 5035 | total time = 867.27 ms / 525 tokens 1.16.343.193 I slot print_timing: id 0 | task 5035 | graphs reused = 4652 1.16.343.194 I slot print_timing: id 0 | task 5035 | graph reallocs = 0 / 0 (same size) / (changed size) 1.16.343.230 I slot release: id 0 | task 5035 | stop processing: n_tokens = 556, truncated = 0 1.16.359.742 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 76243253 1.16.359.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 215.013 MiB) 1.16.430.576 I slot launch_slot_: id 0 | task 5102 | processing task, is_child = 0 1.17.132.126 I slot print_timing: id 0 | task 5102 | prompt eval time = 204.26 ms / 609 tokens ( 0.34 ms per token, 2981.48 tokens per second) 1.17.132.131 I slot print_timing: id 0 | task 5102 | eval time = 497.27 ms / 43 tokens ( 11.84 ms per token, 84.46 tokens per second) 1.17.132.132 I slot print_timing: id 0 | task 5102 | total time = 701.53 ms / 652 tokens 1.17.132.133 I slot print_timing: id 0 | task 5102 | graphs reused = 4693 1.17.132.134 I slot print_timing: id 0 | task 5102 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.132.174 I slot release: id 0 | task 5102 | stop processing: n_tokens = 683, truncated = 0 1.17.157.509 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 77032197 1.17.157.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 213.293 MiB) 1.17.169.285 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 216.107 MiB) 1.17.234.215 I slot launch_slot_: id 0 | task 5149 | processing task, is_child = 0 1.18.137.447 I slot print_timing: id 0 | task 5149 | prompt eval time = 251.64 ms / 791 tokens ( 0.32 ms per token, 3143.42 tokens per second) 1.18.137.453 I slot print_timing: id 0 | task 5149 | eval time = 651.49 ms / 61 tokens ( 10.86 ms per token, 92.10 tokens per second) 1.18.137.454 I slot print_timing: id 0 | task 5149 | total time = 903.12 ms / 852 tokens 1.18.137.455 I slot print_timing: id 0 | task 5149 | graphs reused = 4752 1.18.137.456 I slot print_timing: id 0 | task 5149 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.137.509 I slot release: id 0 | task 5149 | stop processing: n_tokens = 883, truncated = 0 1.18.154.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 78037531 1.18.154.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 270.548 MiB) 1.18.296.414 I slot launch_slot_: id 0 | task 5214 | processing task, is_child = 0 1.19.087.929 I slot print_timing: id 0 | task 5214 | prompt eval time = 198.21 ms / 533 tokens ( 0.37 ms per token, 2689.08 tokens per second) 1.19.087.937 I slot print_timing: id 0 | task 5214 | eval time = 593.27 ms / 56 tokens ( 10.79 ms per token, 92.71 tokens per second) 1.19.087.939 I slot print_timing: id 0 | task 5214 | total time = 791.47 ms / 589 tokens 1.19.087.940 I slot print_timing: id 0 | task 5214 | graphs reused = 4806 1.19.087.941 I slot print_timing: id 0 | task 5214 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.087.994 I slot release: id 0 | task 5214 | stop processing: n_tokens = 677, truncated = 0 1.19.093.412 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 78988016 1.19.093.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.675 MiB) 1.19.187.600 I slot launch_slot_: id 0 | task 5274 | processing task, is_child = 0 1.19.930.554 I slot print_timing: id 0 | task 5274 | prompt eval time = 214.28 ms / 566 tokens ( 0.38 ms per token, 2641.38 tokens per second) 1.19.930.560 I slot print_timing: id 0 | task 5274 | eval time = 528.65 ms / 46 tokens ( 11.75 ms per token, 85.12 tokens per second) 1.19.930.561 I slot print_timing: id 0 | task 5274 | total time = 742.93 ms / 612 tokens 1.19.930.562 I slot print_timing: id 0 | task 5274 | graphs reused = 4850 1.19.930.563 I slot print_timing: id 0 | task 5274 | graph reallocs = 0 / 0 (same size) / (changed size) 1.19.930.606 I slot release: id 0 | task 5274 | stop processing: n_tokens = 643, truncated = 0 1.19.951.027 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 79830629 1.19.951.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 274.332 MiB) 1.20.047.949 I slot launch_slot_: id 0 | task 5324 | processing task, is_child = 0 1.20.686.089 I slot print_timing: id 0 | task 5324 | prompt eval time = 173.53 ms / 443 tokens ( 0.39 ms per token, 2552.93 tokens per second) 1.20.686.095 I slot print_timing: id 0 | task 5324 | eval time = 464.59 ms / 43 tokens ( 11.06 ms per token, 90.40 tokens per second) 1.20.686.096 I slot print_timing: id 0 | task 5324 | total time = 638.12 ms / 486 tokens 1.20.686.097 I slot print_timing: id 0 | task 5324 | graphs reused = 4890 1.20.686.098 I slot print_timing: id 0 | task 5324 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.686.136 I slot release: id 0 | task 5324 | stop processing: n_tokens = 517, truncated = 0 1.20.703.667 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 80586159 1.20.703.721 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 273.488 MiB) 1.20.781.211 I slot launch_slot_: id 0 | task 5370 | processing task, is_child = 0 1.21.655.033 I slot print_timing: id 0 | task 5370 | prompt eval time = 179.00 ms / 487 tokens ( 0.37 ms per token, 2720.66 tokens per second) 1.21.655.039 I slot print_timing: id 0 | task 5370 | eval time = 694.80 ms / 65 tokens ( 10.86 ms per token, 92.11 tokens per second) 1.21.655.041 I slot print_timing: id 0 | task 5370 | total time = 873.80 ms / 552 tokens 1.21.655.041 I slot print_timing: id 0 | task 5370 | graphs reused = 4953 1.21.655.042 I slot print_timing: id 0 | task 5370 | graph reallocs = 0 / 0 (same size) / (changed size) 1.21.655.078 I slot release: id 0 | task 5370 | stop processing: n_tokens = 583, truncated = 0 1.21.680.944 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 81555101 1.21.681.005 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 217.796 MiB) 1.21.760.321 I slot launch_slot_: id 0 | task 5438 | processing task, is_child = 0 1.22.452.110 I slot print_timing: id 0 | task 5438 | prompt eval time = 187.45 ms / 507 tokens ( 0.37 ms per token, 2704.72 tokens per second) 1.22.452.116 I slot print_timing: id 0 | task 5438 | eval time = 504.31 ms / 47 tokens ( 10.96 ms per token, 91.21 tokens per second) 1.22.452.117 I slot print_timing: id 0 | task 5438 | total time = 691.76 ms / 554 tokens 1.22.452.118 I slot print_timing: id 0 | task 5438 | graphs reused = 4998 1.22.452.119 I slot print_timing: id 0 | task 5438 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.452.156 I slot release: id 0 | task 5438 | stop processing: n_tokens = 585, truncated = 0 1.22.456.982 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 82352179 1.22.457.038 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 272.206 MiB) 1.22.473.908 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 271.893 MiB) 1.22.554.009 I slot launch_slot_: id 0 | task 5488 | processing task, is_child = 0 1.23.472.049 I slot print_timing: id 0 | task 5488 | prompt eval time = 212.74 ms / 633 tokens ( 0.34 ms per token, 2975.53 tokens per second) 1.23.472.055 I slot print_timing: id 0 | task 5488 | eval time = 705.28 ms / 66 tokens ( 10.85 ms per token, 92.16 tokens per second) 1.23.472.056 I slot print_timing: id 0 | task 5488 | total time = 918.02 ms / 699 tokens 1.23.472.057 I slot print_timing: id 0 | task 5488 | graphs reused = 5062 1.23.472.058 I slot print_timing: id 0 | task 5488 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.472.097 I slot release: id 0 | task 5488 | stop processing: n_tokens = 730, truncated = 0 1.23.490.525 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 83372120 1.23.490.595 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.735 MiB) 1.23.612.134 I slot launch_slot_: id 0 | task 5558 | processing task, is_child = 0 1.24.320.518 I slot print_timing: id 0 | task 5558 | prompt eval time = 204.84 ms / 571 tokens ( 0.36 ms per token, 2787.47 tokens per second) 1.24.320.523 I slot print_timing: id 0 | task 5558 | eval time = 503.51 ms / 47 tokens ( 10.95 ms per token, 91.36 tokens per second) 1.24.320.525 I slot print_timing: id 0 | task 5558 | total time = 708.36 ms / 618 tokens 1.24.320.527 I slot print_timing: id 0 | task 5558 | graphs reused = 5107 1.24.320.527 I slot print_timing: id 0 | task 5558 | graph reallocs = 0 / 0 (same size) / (changed size) 1.24.320.566 I slot release: id 0 | task 5558 | stop processing: n_tokens = 649, truncated = 0 1.24.326.548 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 84220589 1.24.326.600 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 268.766 MiB) 1.24.444.460 I slot launch_slot_: id 0 | task 5609 | processing task, is_child = 0 1.25.172.624 I slot print_timing: id 0 | task 5609 | prompt eval time = 252.67 ms / 798 tokens ( 0.32 ms per token, 3158.31 tokens per second) 1.25.172.631 I slot print_timing: id 0 | task 5609 | eval time = 475.46 ms / 44 tokens ( 11.06 ms per token, 90.44 tokens per second) 1.25.172.633 I slot print_timing: id 0 | task 5609 | total time = 728.13 ms / 842 tokens 1.25.172.634 I slot print_timing: id 0 | task 5609 | graphs reused = 5149 1.25.172.635 I slot print_timing: id 0 | task 5609 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.172.703 I slot release: id 0 | task 5609 | stop processing: n_tokens = 873, truncated = 0 1.25.178.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 85072727 1.25.178.226 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 1.25.201.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 269.923 MiB) 1.25.303.494 I slot launch_slot_: id 0 | task 5657 | processing task, is_child = 0 1.25.988.772 I slot print_timing: id 0 | task 5657 | prompt eval time = 215.63 ms / 572 tokens ( 0.38 ms per token, 2652.69 tokens per second) 1.25.988.778 I slot print_timing: id 0 | task 5657 | eval time = 469.62 ms / 43 tokens ( 11.18 ms per token, 89.43 tokens per second) 1.25.988.779 I slot print_timing: id 0 | task 5657 | total time = 685.25 ms / 615 tokens 1.25.988.780 I slot print_timing: id 0 | task 5657 | graphs reused = 5190 1.25.988.781 I slot print_timing: id 0 | task 5657 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.988.827 I slot release: id 0 | task 5657 | stop processing: n_tokens = 646, truncated = 0 1.25.993.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 85888849 1.25.993.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 267.015 MiB) 1.26.109.041 I slot launch_slot_: id 0 | task 5704 | processing task, is_child = 0 1.26.836.830 I slot print_timing: id 0 | task 5704 | prompt eval time = 209.97 ms / 613 tokens ( 0.34 ms per token, 2919.48 tokens per second) 1.26.836.836 I slot print_timing: id 0 | task 5704 | eval time = 517.79 ms / 49 tokens ( 10.79 ms per token, 92.70 tokens per second) 1.26.836.837 I slot print_timing: id 0 | task 5704 | total time = 727.76 ms / 662 tokens 1.26.836.838 I slot print_timing: id 0 | task 5704 | graphs reused = 5237 1.26.836.838 I slot print_timing: id 0 | task 5704 | graph reallocs = 0 / 0 (same size) / (changed size) 1.26.836.884 I slot release: id 0 | task 5704 | stop processing: n_tokens = 693, truncated = 0 1.26.856.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 86736907 1.26.856.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.549 MiB) 1.26.972.894 I slot launch_slot_: id 0 | task 5757 | processing task, is_child = 0 1.28.007.590 I slot print_timing: id 0 | task 5757 | prompt eval time = 209.44 ms / 580 tokens ( 0.36 ms per token, 2769.30 tokens per second) 1.28.007.596 I slot print_timing: id 0 | task 5757 | eval time = 825.23 ms / 76 tokens ( 11.00 ms per token, 90.88 tokens per second) 1.28.007.597 I slot print_timing: id 0 | task 5757 | total time = 1034.67 ms / 656 tokens 1.28.007.598 I slot print_timing: id 0 | task 5757 | graphs reused = 5311 1.28.007.599 I slot print_timing: id 0 | task 5757 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.007.641 I slot release: id 0 | task 5757 | stop processing: n_tokens = 687, truncated = 0 1.28.028.207 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 87907663 1.28.028.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.454 MiB) 1.28.135.194 I slot launch_slot_: id 0 | task 5837 | processing task, is_child = 0 1.28.923.642 I slot print_timing: id 0 | task 5837 | prompt eval time = 239.61 ms / 716 tokens ( 0.33 ms per token, 2988.18 tokens per second) 1.28.923.650 I slot print_timing: id 0 | task 5837 | eval time = 548.81 ms / 50 tokens ( 11.20 ms per token, 89.28 tokens per second) 1.28.923.652 I slot print_timing: id 0 | task 5837 | total time = 788.42 ms / 766 tokens 1.28.923.654 I slot print_timing: id 0 | task 5837 | graphs reused = 5358 1.28.923.655 I slot print_timing: id 0 | task 5837 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.923.733 I slot release: id 0 | task 5837 | stop processing: n_tokens = 797, truncated = 0 1.28.932.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 88823757 1.28.932.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.234 MiB) 1.28.962.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.141 MiB) 1.29.058.100 I slot launch_slot_: id 0 | task 5891 | processing task, is_child = 0 1.30.413.946 I slot print_timing: id 0 | task 5891 | prompt eval time = 263.15 ms / 799 tokens ( 0.33 ms per token, 3036.23 tokens per second) 1.30.413.954 I slot print_timing: id 0 | task 5891 | eval time = 1092.67 ms / 102 tokens ( 10.82 ms per token, 92.43 tokens per second) 1.30.413.956 I slot print_timing: id 0 | task 5891 | total time = 1355.82 ms / 901 tokens 1.30.413.958 I slot print_timing: id 0 | task 5891 | graphs reused = 5458 1.30.413.959 I slot print_timing: id 0 | task 5891 | graph reallocs = 0 / 0 (same size) / (changed size) 1.30.414.024 I slot release: id 0 | task 5891 | stop processing: n_tokens = 932, truncated = 0 1.30.434.691 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 90314049 1.30.434.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.515 MiB) 1.30.516.191 I slot launch_slot_: id 0 | task 5997 | processing task, is_child = 0 1.31.861.329 I slot print_timing: id 0 | task 5997 | prompt eval time = 152.99 ms / 361 tokens ( 0.42 ms per token, 2359.62 tokens per second) 1.31.861.336 I slot print_timing: id 0 | task 5997 | eval time = 1192.12 ms / 112 tokens ( 10.74 ms per token, 93.11 tokens per second) 1.31.861.337 I slot print_timing: id 0 | task 5997 | total time = 1345.12 ms / 473 tokens 1.31.861.338 I slot print_timing: id 0 | task 5997 | graphs reused = 5568 1.31.861.339 I slot print_timing: id 0 | task 5997 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.861.375 I slot release: id 0 | task 5997 | stop processing: n_tokens = 504, truncated = 0 1.31.882.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 91761398 1.31.882.184 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 1.31.968.128 I slot launch_slot_: id 0 | task 6112 | processing task, is_child = 0 1.33.277.907 I slot print_timing: id 0 | task 6112 | prompt eval time = 157.86 ms / 381 tokens ( 0.41 ms per token, 2413.50 tokens per second) 1.33.277.915 I slot print_timing: id 0 | task 6112 | eval time = 1151.89 ms / 108 tokens ( 10.77 ms per token, 92.89 tokens per second) 1.33.277.917 I slot print_timing: id 0 | task 6112 | total time = 1309.75 ms / 489 tokens 1.33.277.918 I slot print_timing: id 0 | task 6112 | graphs reused = 5673 1.33.277.919 I slot print_timing: id 0 | task 6112 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.277.968 I slot release: id 0 | task 6112 | stop processing: n_tokens = 520, truncated = 0 1.33.296.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 93177990 1.33.296.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 1.33.373.567 I slot launch_slot_: id 0 | task 6223 | processing task, is_child = 0 1.34.853.534 I slot print_timing: id 0 | task 6223 | prompt eval time = 164.34 ms / 365 tokens ( 0.45 ms per token, 2221.06 tokens per second) 1.34.853.540 I slot print_timing: id 0 | task 6223 | eval time = 1315.60 ms / 124 tokens ( 10.70 ms per token, 93.49 tokens per second) 1.34.853.541 I slot print_timing: id 0 | task 6223 | total time = 1479.94 ms / 489 tokens 1.34.853.542 I slot print_timing: id 0 | task 6223 | graphs reused = 5794 1.34.853.543 I slot print_timing: id 0 | task 6223 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.853.577 I slot release: id 0 | task 6223 | stop processing: n_tokens = 520, truncated = 0 1.34.880.465 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 94753600 1.34.880.522 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.026 MiB) 1.34.963.660 I slot launch_slot_: id 0 | task 6350 | processing task, is_child = 0 1.36.268.060 I slot print_timing: id 0 | task 6350 | prompt eval time = 167.02 ms / 333 tokens ( 0.50 ms per token, 1993.73 tokens per second) 1.36.268.066 I slot print_timing: id 0 | task 6350 | eval time = 1137.35 ms / 107 tokens ( 10.73 ms per token, 93.20 tokens per second) 1.36.268.067 I slot print_timing: id 0 | task 6350 | total time = 1304.38 ms / 440 tokens 1.36.268.068 I slot print_timing: id 0 | task 6350 | graphs reused = 5899 1.36.268.069 I slot print_timing: id 0 | task 6350 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.268.101 I slot release: id 0 | task 6350 | stop processing: n_tokens = 471, truncated = 0 1.36.282.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 96168123 1.36.328.038 I slot launch_slot_: id 0 | task 6460 | processing task, is_child = 0 1.37.929.126 I slot print_timing: id 0 | task 6460 | prompt eval time = 155.45 ms / 403 tokens ( 0.39 ms per token, 2592.52 tokens per second) 1.37.929.132 I slot print_timing: id 0 | task 6460 | eval time = 1445.62 ms / 138 tokens ( 10.55 ms per token, 94.77 tokens per second) 1.37.929.133 I slot print_timing: id 0 | task 6460 | total time = 1601.07 ms / 541 tokens 1.37.929.133 I slot print_timing: id 0 | task 6460 | graphs reused = 6034 1.37.929.134 I slot print_timing: id 0 | task 6460 | graph reallocs = 0 / 0 (same size) / (changed size) 1.37.929.165 I slot release: id 0 | task 6460 | stop processing: n_tokens = 572, truncated = 0 1.37.956.712 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 97829188 1.37.956.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.172 MiB) 1.38.013.545 I slot launch_slot_: id 0 | task 6601 | processing task, is_child = 0 1.40.107.209 I slot print_timing: id 0 | task 6601 | prompt eval time = 150.83 ms / 411 tokens ( 0.37 ms per token, 2724.92 tokens per second) 1.40.107.215 I slot print_timing: id 0 | task 6601 | eval time = 1942.81 ms / 185 tokens ( 10.56 ms per token, 94.71 tokens per second) 1.40.107.216 I slot print_timing: id 0 | task 6601 | total time = 2093.64 ms / 596 tokens 1.40.107.217 I slot print_timing: id 0 | task 6601 | graphs reused = 6216 1.40.107.218 I slot print_timing: id 0 | task 6601 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.107.248 I slot release: id 0 | task 6601 | stop processing: n_tokens = 627, truncated = 0 1.40.130.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 100007271 1.40.130.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.146 MiB) 1.40.199.522 I slot launch_slot_: id 0 | task 6789 | processing task, is_child = 0 1.42.747.743 I slot print_timing: id 0 | task 6789 | prompt eval time = 188.77 ms / 490 tokens ( 0.39 ms per token, 2595.81 tokens per second) 1.42.747.749 I slot print_timing: id 0 | task 6789 | eval time = 2359.42 ms / 225 tokens ( 10.53 ms per token, 94.94 tokens per second) 1.42.747.750 I slot print_timing: id 0 | task 6789 | total time = 2548.19 ms / 715 tokens 1.42.747.751 I slot print_timing: id 0 | task 6789 | graphs reused = 6439 1.42.747.751 I slot print_timing: id 0 | task 6789 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.747.784 I slot release: id 0 | task 6789 | stop processing: n_tokens = 746, truncated = 0 1.42.751.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 102647806 1.42.751.616 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.930 MiB) 1.42.818.313 I slot launch_slot_: id 0 | task 7017 | processing task, is_child = 0 1.44.781.802 I slot print_timing: id 0 | task 7017 | prompt eval time = 144.71 ms / 344 tokens ( 0.42 ms per token, 2377.12 tokens per second) 1.44.781.807 I slot print_timing: id 0 | task 7017 | eval time = 1818.74 ms / 171 tokens ( 10.70 ms per token, 93.47 tokens per second) 1.44.781.808 I slot print_timing: id 0 | task 7017 | total time = 1963.45 ms / 515 tokens 1.44.781.809 I slot print_timing: id 0 | task 7017 | graphs reused = 6607 1.44.781.810 I slot print_timing: id 0 | task 7017 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.781.839 I slot release: id 0 | task 7017 | stop processing: n_tokens = 546, truncated = 0 1.44.810.798 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 104681862 1.44.810.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.891 MiB) 1.44.866.417 I slot launch_slot_: id 0 | task 7191 | processing task, is_child = 0 1.46.812.419 I slot print_timing: id 0 | task 7191 | prompt eval time = 143.24 ms / 347 tokens ( 0.41 ms per token, 2422.59 tokens per second) 1.46.812.425 I slot print_timing: id 0 | task 7191 | eval time = 1802.73 ms / 171 tokens ( 10.60 ms per token, 94.30 tokens per second) 1.46.812.426 I slot print_timing: id 0 | task 7191 | total time = 1945.97 ms / 518 tokens 1.46.812.428 I slot print_timing: id 0 | task 7191 | graphs reused = 6775 1.46.812.429 I slot print_timing: id 0 | task 7191 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.812.466 I slot release: id 0 | task 7191 | stop processing: n_tokens = 549, truncated = 0 1.46.820.278 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 106712489 1.46.820.352 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.114 MiB) 1.46.890.547 I slot launch_slot_: id 0 | task 7365 | processing task, is_child = 0 1.48.375.227 I slot print_timing: id 0 | task 7365 | prompt eval time = 155.72 ms / 401 tokens ( 0.39 ms per token, 2575.17 tokens per second) 1.48.375.233 I slot print_timing: id 0 | task 7365 | eval time = 1328.94 ms / 126 tokens ( 10.63 ms per token, 94.06 tokens per second) 1.48.375.234 I slot print_timing: id 0 | task 7365 | total time = 1484.66 ms / 527 tokens 1.48.375.235 I slot print_timing: id 0 | task 7365 | graphs reused = 6898 1.48.375.236 I slot print_timing: id 0 | task 7365 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.375.267 I slot release: id 0 | task 7365 | stop processing: n_tokens = 558, truncated = 0 1.48.402.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 108275290 1.48.402.825 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.368 MiB) 1.48.466.192 I slot launch_slot_: id 0 | task 7494 | processing task, is_child = 0 1.49.864.681 I slot print_timing: id 0 | task 7494 | prompt eval time = 169.43 ms / 456 tokens ( 0.37 ms per token, 2691.31 tokens per second) 1.49.864.686 I slot print_timing: id 0 | task 7494 | eval time = 1229.02 ms / 115 tokens ( 10.78 ms per token, 92.76 tokens per second) 1.49.864.687 I slot print_timing: id 0 | task 7494 | total time = 1398.45 ms / 571 tokens 1.49.864.688 I slot print_timing: id 0 | task 7494 | graphs reused = 7010 1.49.864.689 I slot print_timing: id 0 | task 7494 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.864.721 I slot release: id 0 | task 7494 | stop processing: n_tokens = 602, truncated = 0 1.49.893.048 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 1.49.893.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 423.177 MiB) 1.49.959.717 I slot launch_slot_: id 0 | task 7612 | processing task, is_child = 0 1.51.283.169 I slot print_timing: id 0 | task 7612 | prompt eval time = 156.86 ms / 406 tokens ( 0.39 ms per token, 2588.23 tokens per second) 1.51.283.174 I slot print_timing: id 0 | task 7612 | eval time = 1166.56 ms / 112 tokens ( 10.51 ms per token, 95.15 tokens per second) 1.51.283.175 I slot print_timing: id 0 | task 7612 | total time = 1323.42 ms / 518 tokens 1.51.283.176 I slot print_timing: id 0 | task 7612 | graphs reused = 7119 1.51.283.177 I slot print_timing: id 0 | task 7612 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.283.206 I slot release: id 0 | task 7612 | stop processing: n_tokens = 549, truncated = 0 1.51.299.869 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 111183229 1.51.340.862 I slot launch_slot_: id 0 | task 7727 | processing task, is_child = 0 1.53.364.326 I slot print_timing: id 0 | task 7727 | prompt eval time = 155.42 ms / 406 tokens ( 0.38 ms per token, 2612.34 tokens per second) 1.53.364.332 I slot print_timing: id 0 | task 7727 | eval time = 1868.03 ms / 179 tokens ( 10.49 ms per token, 95.29 tokens per second) 1.53.364.333 I slot print_timing: id 0 | task 7727 | total time = 2023.45 ms / 585 tokens 1.53.364.334 I slot print_timing: id 0 | task 7727 | graphs reused = 7295 1.53.364.335 I slot print_timing: id 0 | task 7727 | graph reallocs = 0 / 0 (same size) / (changed size) 1.53.364.365 I slot release: id 0 | task 7727 | stop processing: n_tokens = 616, truncated = 0 1.53.386.504 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 113264388 1.53.386.555 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.863 MiB) 1.53.448.499 I slot launch_slot_: id 0 | task 7909 | processing task, is_child = 0 1.55.132.920 I slot print_timing: id 0 | task 7909 | prompt eval time = 168.43 ms / 444 tokens ( 0.38 ms per token, 2636.16 tokens per second) 1.55.132.926 I slot print_timing: id 0 | task 7909 | eval time = 1515.96 ms / 144 tokens ( 10.60 ms per token, 94.33 tokens per second) 1.55.132.927 I slot print_timing: id 0 | task 7909 | total time = 1684.39 ms / 588 tokens 1.55.132.928 I slot print_timing: id 0 | task 7909 | graphs reused = 7436 1.55.132.929 I slot print_timing: id 0 | task 7909 | graph reallocs = 0 / 0 (same size) / (changed size) 1.55.132.960 I slot release: id 0 | task 7909 | stop processing: n_tokens = 619, truncated = 0 1.55.150.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 115032983 1.55.150.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.672 MiB) 1.55.209.758 I slot launch_slot_: id 0 | task 8056 | processing task, is_child = 0 1.56.445.233 I slot print_timing: id 0 | task 8056 | prompt eval time = 155.30 ms / 372 tokens ( 0.42 ms per token, 2395.35 tokens per second) 1.56.445.239 I slot print_timing: id 0 | task 8056 | eval time = 1080.14 ms / 103 tokens ( 10.59 ms per token, 94.43 tokens per second) 1.56.445.240 I slot print_timing: id 0 | task 8056 | total time = 1235.44 ms / 475 tokens 1.56.445.241 I slot print_timing: id 0 | task 8056 | graphs reused = 7537 1.56.445.242 I slot print_timing: id 0 | task 8056 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.445.273 I slot release: id 0 | task 8056 | stop processing: n_tokens = 506, truncated = 0 1.56.468.901 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 116345296 1.56.468.949 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.736 MiB) 1.56.525.721 I slot launch_slot_: id 0 | task 8162 | processing task, is_child = 0 1.59.095.488 I slot print_timing: id 0 | task 8162 | prompt eval time = 162.74 ms / 454 tokens ( 0.36 ms per token, 2789.78 tokens per second) 1.59.095.494 I slot print_timing: id 0 | task 8162 | eval time = 2407.00 ms / 230 tokens ( 10.51 ms per token, 95.14 tokens per second) 1.59.095.495 I slot print_timing: id 0 | task 8162 | total time = 2569.73 ms / 684 tokens 1.59.095.495 I slot print_timing: id 0 | task 8162 | graphs reused = 7764 1.59.095.496 I slot print_timing: id 0 | task 8162 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.095.527 I slot release: id 0 | task 8162 | stop processing: n_tokens = 715, truncated = 0 1.59.112.418 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 118995550 1.59.112.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.798 MiB) 1.59.170.211 I slot launch_slot_: id 0 | task 8395 | processing task, is_child = 0 2.01.683.641 I slot print_timing: id 0 | task 8395 | prompt eval time = 150.02 ms / 354 tokens ( 0.42 ms per token, 2359.64 tokens per second) 2.01.683.647 I slot print_timing: id 0 | task 8395 | eval time = 2363.39 ms / 226 tokens ( 10.50 ms per token, 95.20 tokens per second) 2.01.683.648 I slot print_timing: id 0 | task 8395 | total time = 2513.41 ms / 580 tokens 2.01.683.650 I slot print_timing: id 0 | task 8395 | graphs reused = 7987 2.01.683.651 I slot print_timing: id 0 | task 8395 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.683.680 I slot release: id 0 | task 8395 | stop processing: n_tokens = 611, truncated = 0 2.01.713.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 121583703 2.01.713.067 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.583 MiB) 2.01.780.122 I slot launch_slot_: id 0 | task 8624 | processing task, is_child = 0 2.03.383.180 I slot print_timing: id 0 | task 8624 | prompt eval time = 144.76 ms / 334 tokens ( 0.43 ms per token, 2307.25 tokens per second) 2.03.383.186 I slot print_timing: id 0 | task 8624 | eval time = 1458.26 ms / 140 tokens ( 10.49 ms per token, 95.32 tokens per second) 2.03.383.187 I slot print_timing: id 0 | task 8624 | total time = 1603.02 ms / 474 tokens 2.03.383.188 I slot print_timing: id 0 | task 8624 | graphs reused = 8125 2.03.383.189 I slot print_timing: id 0 | task 8624 | graph reallocs = 0 / 0 (same size) / (changed size) 2.03.383.222 I slot release: id 0 | task 8624 | stop processing: n_tokens = 505, truncated = 0 2.03.387.248 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 123283244 2.03.387.291 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 372.050 MiB) 2.03.460.462 I slot launch_slot_: id 0 | task 8767 | processing task, is_child = 0 2.05.457.368 I slot print_timing: id 0 | task 8767 | prompt eval time = 158.90 ms / 426 tokens ( 0.37 ms per token, 2680.98 tokens per second) 2.05.457.374 I slot print_timing: id 0 | task 8767 | eval time = 1837.97 ms / 175 tokens ( 10.56 ms per token, 94.67 tokens per second) 2.05.457.375 I slot print_timing: id 0 | task 8767 | total time = 1996.87 ms / 601 tokens 2.05.457.375 I slot print_timing: id 0 | task 8767 | graphs reused = 8297 2.05.457.376 I slot print_timing: id 0 | task 8767 | graph reallocs = 0 / 0 (same size) / (changed size) 2.05.457.409 I slot release: id 0 | task 8767 | stop processing: n_tokens = 632, truncated = 0 2.05.476.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 125357432 2.05.476.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.055 MiB) 2.05.548.911 I slot launch_slot_: id 0 | task 8945 | processing task, is_child = 0 2.06.920.067 I slot print_timing: id 0 | task 8945 | prompt eval time = 148.18 ms / 366 tokens ( 0.40 ms per token, 2469.95 tokens per second) 2.06.920.072 I slot print_timing: id 0 | task 8945 | eval time = 1222.96 ms / 117 tokens ( 10.54 ms per token, 94.85 tokens per second) 2.06.920.073 I slot print_timing: id 0 | task 8945 | total time = 1371.14 ms / 483 tokens 2.06.920.074 I slot print_timing: id 0 | task 8945 | graphs reused = 8411 2.06.920.075 I slot print_timing: id 0 | task 8945 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.920.103 I slot release: id 0 | task 8945 | stop processing: n_tokens = 514, truncated = 0 2.06.934.272 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 126820126 2.06.934.322 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 371.957 MiB) 2.07.012.389 I slot launch_slot_: id 0 | task 9065 | processing task, is_child = 0 2.10.190.295 I slot print_timing: id 0 | task 9065 | n_gen = 287, tg = 95.05 t/s, tg_3s = 95.39 t/s 2.10.598.737 I slot print_timing: id 0 | task 9065 | prompt eval time = 169.08 ms / 462 tokens ( 0.37 ms per token, 2732.43 tokens per second) 2.10.598.743 I slot print_timing: id 0 | task 9065 | eval time = 3417.25 ms / 326 tokens ( 10.51 ms per token, 95.11 tokens per second) 2.10.598.744 I slot print_timing: id 0 | task 9065 | total time = 3586.33 ms / 788 tokens 2.10.598.745 I slot print_timing: id 0 | task 9065 | graphs reused = 8733 2.10.598.746 I slot print_timing: id 0 | task 9065 | graph reallocs = 0 / 0 (same size) / (changed size) 2.10.598.777 I slot release: id 0 | task 9065 | stop processing: n_tokens = 819, truncated = 0 2.10.622.421 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 819, t_last = 130498800 2.10.622.487 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.426 MiB) 2.10.697.525 I slot launch_slot_: id 0 | task 9394 | processing task, is_child = 0 2.12.302.393 I slot print_timing: id 0 | task 9394 | prompt eval time = 154.29 ms / 396 tokens ( 0.39 ms per token, 2566.60 tokens per second) 2.12.302.399 I slot print_timing: id 0 | task 9394 | eval time = 1450.56 ms / 139 tokens ( 10.51 ms per token, 95.14 tokens per second) 2.12.302.401 I slot print_timing: id 0 | task 9394 | total time = 1604.85 ms / 535 tokens 2.12.302.401 I slot print_timing: id 0 | task 9394 | graphs reused = 8869 2.12.302.402 I slot print_timing: id 0 | task 9394 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.302.435 I slot release: id 0 | task 9394 | stop processing: n_tokens = 566, truncated = 0 2.12.327.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 132202458 2.12.370.813 I slot launch_slot_: id 0 | task 9536 | processing task, is_child = 0 2.14.221.788 I slot print_timing: id 0 | task 9536 | prompt eval time = 166.73 ms / 458 tokens ( 0.36 ms per token, 2747.02 tokens per second) 2.14.221.794 I slot print_timing: id 0 | task 9536 | eval time = 1684.23 ms / 161 tokens ( 10.53 ms per token, 95.00 tokens per second) 2.14.221.795 I slot print_timing: id 0 | task 9536 | total time = 1850.95 ms / 619 tokens 2.14.221.796 I slot print_timing: id 0 | task 9536 | graphs reused = 9027 2.14.221.796 I slot print_timing: id 0 | task 9536 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.221.829 I slot release: id 0 | task 9536 | stop processing: n_tokens = 650, truncated = 0 2.14.239.816 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 134121852 2.14.239.871 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 373.239 MiB) 2.14.323.791 I slot launch_slot_: id 0 | task 9700 | processing task, is_child = 0 2.16.361.858 I slot print_timing: id 0 | task 9700 | prompt eval time = 167.74 ms / 458 tokens ( 0.37 ms per token, 2730.38 tokens per second) 2.16.361.864 I slot print_timing: id 0 | task 9700 | eval time = 1870.30 ms / 176 tokens ( 10.69 ms per token, 93.57 tokens per second) 2.16.361.865 I slot print_timing: id 0 | task 9700 | total time = 2038.05 ms / 634 tokens 2.16.361.866 I slot print_timing: id 0 | task 9700 | graphs reused = 9200 2.16.361.867 I slot print_timing: id 0 | task 9700 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.361.902 I slot release: id 0 | task 9700 | stop processing: n_tokens = 665, truncated = 0 2.16.380.231 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 665, t_last = 136261925 2.16.380.281 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.679 MiB) 2.16.449.760 I slot launch_slot_: id 0 | task 9879 | processing task, is_child = 0 2.18.808.678 I slot print_timing: id 0 | task 9879 | prompt eval time = 163.95 ms / 452 tokens ( 0.36 ms per token, 2757.01 tokens per second) 2.18.808.684 I slot print_timing: id 0 | task 9879 | eval time = 2194.95 ms / 210 tokens ( 10.50 ms per token, 95.22 tokens per second) 2.18.808.686 I slot print_timing: id 0 | task 9879 | total time = 2358.90 ms / 662 tokens 2.18.808.686 I slot print_timing: id 0 | task 9879 | graphs reused = 9407 2.18.808.688 I slot print_timing: id 0 | task 9879 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.808.722 I slot release: id 0 | task 9879 | stop processing: n_tokens = 693, truncated = 0 2.18.824.216 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 138708745 2.18.824.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 380.901 MiB) 2.18.891.489 I slot launch_slot_: id 0 | task 10092 | processing task, is_child = 0 2.20.302.966 I slot print_timing: id 0 | task 10092 | prompt eval time = 156.44 ms / 404 tokens ( 0.39 ms per token, 2582.49 tokens per second) 2.20.302.972 I slot print_timing: id 0 | task 10092 | eval time = 1255.02 ms / 120 tokens ( 10.55 ms per token, 94.82 tokens per second) 2.20.302.973 I slot print_timing: id 0 | task 10092 | total time = 1411.46 ms / 524 tokens 2.20.302.975 I slot print_timing: id 0 | task 10092 | graphs reused = 9524 2.20.302.976 I slot print_timing: id 0 | task 10092 | graph reallocs = 0 / 0 (same size) / (changed size) 2.20.303.006 I slot release: id 0 | task 10092 | stop processing: n_tokens = 555, truncated = 0 2.20.328.195 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 140203028 2.20.328.250 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.265 MiB) 2.20.392.998 I slot launch_slot_: id 0 | task 10215 | processing task, is_child = 0 2.21.644.362 I slot print_timing: id 0 | task 10215 | prompt eval time = 147.26 ms / 345 tokens ( 0.43 ms per token, 2342.72 tokens per second) 2.21.644.368 I slot print_timing: id 0 | task 10215 | eval time = 1104.08 ms / 106 tokens ( 10.52 ms per token, 95.10 tokens per second) 2.21.644.369 I slot print_timing: id 0 | task 10215 | total time = 1251.34 ms / 451 tokens 2.21.644.370 I slot print_timing: id 0 | task 10215 | graphs reused = 9628 2.21.644.371 I slot print_timing: id 0 | task 10215 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.644.399 I slot release: id 0 | task 10215 | stop processing: n_tokens = 482, truncated = 0 2.21.666.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 141544422 2.21.666.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.21.741.608 I slot launch_slot_: id 0 | task 10324 | processing task, is_child = 0 2.23.007.112 I slot print_timing: id 0 | task 10324 | prompt eval time = 170.12 ms / 430 tokens ( 0.40 ms per token, 2527.69 tokens per second) 2.23.007.118 I slot print_timing: id 0 | task 10324 | eval time = 1095.37 ms / 105 tokens ( 10.53 ms per token, 94.95 tokens per second) 2.23.007.119 I slot print_timing: id 0 | task 10324 | total time = 1265.48 ms / 535 tokens 2.23.007.120 I slot print_timing: id 0 | task 10324 | graphs reused = 9730 2.23.007.121 I slot print_timing: id 0 | task 10324 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.007.151 I slot release: id 0 | task 10324 | stop processing: n_tokens = 566, truncated = 0 2.23.026.354 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 142907174 2.23.026.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.766 MiB) 2.23.081.954 I slot launch_slot_: id 0 | task 10432 | processing task, is_child = 0 2.24.135.057 I slot print_timing: id 0 | task 10432 | prompt eval time = 138.69 ms / 316 tokens ( 0.44 ms per token, 2278.53 tokens per second) 2.24.135.064 I slot print_timing: id 0 | task 10432 | eval time = 914.40 ms / 85 tokens ( 10.89 ms per token, 91.86 tokens per second) 2.24.135.065 I slot print_timing: id 0 | task 10432 | total time = 1053.08 ms / 401 tokens 2.24.135.066 I slot print_timing: id 0 | task 10432 | graphs reused = 9813 2.24.135.066 I slot print_timing: id 0 | task 10432 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.135.109 I slot release: id 0 | task 10432 | stop processing: n_tokens = 432, truncated = 0 2.24.150.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 144035132 2.24.150.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.233 MiB) 2.24.212.751 I slot launch_slot_: id 0 | task 10520 | processing task, is_child = 0 2.25.472.952 I slot print_timing: id 0 | task 10520 | prompt eval time = 146.45 ms / 354 tokens ( 0.41 ms per token, 2417.16 tokens per second) 2.25.472.958 I slot print_timing: id 0 | task 10520 | eval time = 1113.73 ms / 107 tokens ( 10.51 ms per token, 95.18 tokens per second) 2.25.472.959 I slot print_timing: id 0 | task 10520 | total time = 1260.18 ms / 461 tokens 2.25.472.959 I slot print_timing: id 0 | task 10520 | graphs reused = 9918 2.25.472.961 I slot print_timing: id 0 | task 10520 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.472.991 I slot release: id 0 | task 10520 | stop processing: n_tokens = 492, truncated = 0 2.25.477.116 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 145373013 2.25.477.167 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.392 MiB) 2.25.533.068 I slot launch_slot_: id 0 | task 10630 | processing task, is_child = 0 2.26.728.195 I slot print_timing: id 0 | task 10630 | prompt eval time = 170.82 ms / 438 tokens ( 0.39 ms per token, 2564.13 tokens per second) 2.26.728.201 I slot print_timing: id 0 | task 10630 | eval time = 1024.29 ms / 98 tokens ( 10.56 ms per token, 94.70 tokens per second) 2.26.728.202 I slot print_timing: id 0 | task 10630 | total time = 1195.11 ms / 536 tokens 2.26.728.204 I slot print_timing: id 0 | task 10630 | graphs reused = 10013 2.26.728.205 I slot print_timing: id 0 | task 10630 | graph reallocs = 0 / 0 (same size) / (changed size) 2.26.728.235 I slot release: id 0 | task 10630 | stop processing: n_tokens = 567, truncated = 0 2.26.748.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 146628258 2.26.748.540 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.112 MiB) 2.26.804.339 I slot launch_slot_: id 0 | task 10731 | processing task, is_child = 0 2.27.712.800 I slot print_timing: id 0 | task 10731 | prompt eval time = 169.10 ms / 457 tokens ( 0.37 ms per token, 2702.57 tokens per second) 2.27.712.807 I slot print_timing: id 0 | task 10731 | eval time = 739.34 ms / 70 tokens ( 10.72 ms per token, 93.33 tokens per second) 2.27.712.808 I slot print_timing: id 0 | task 10731 | total time = 908.44 ms / 527 tokens 2.27.712.809 I slot print_timing: id 0 | task 10731 | graphs reused = 10080 2.27.712.810 I slot print_timing: id 0 | task 10731 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.712.847 I slot release: id 0 | task 10731 | stop processing: n_tokens = 558, truncated = 0 2.27.716.906 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 147612870 2.27.716.956 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.833 MiB) 2.27.774.477 I slot launch_slot_: id 0 | task 10804 | processing task, is_child = 0 2.28.975.622 I slot print_timing: id 0 | task 10804 | prompt eval time = 176.49 ms / 473 tokens ( 0.37 ms per token, 2680.05 tokens per second) 2.28.975.628 I slot print_timing: id 0 | task 10804 | eval time = 1024.64 ms / 98 tokens ( 10.56 ms per token, 94.67 tokens per second) 2.28.975.629 I slot print_timing: id 0 | task 10804 | total time = 1201.12 ms / 571 tokens 2.28.975.630 I slot print_timing: id 0 | task 10804 | graphs reused = 10175 2.28.975.631 I slot print_timing: id 0 | task 10804 | graph reallocs = 0 / 0 (same size) / (changed size) 2.28.975.663 I slot release: id 0 | task 10804 | stop processing: n_tokens = 602, truncated = 0 2.28.992.804 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 148875686 2.28.992.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.579 MiB) 2.29.048.129 I slot launch_slot_: id 0 | task 10905 | processing task, is_child = 0 2.31.104.375 I slot print_timing: id 0 | task 10905 | prompt eval time = 170.02 ms / 476 tokens ( 0.36 ms per token, 2799.74 tokens per second) 2.31.104.381 I slot print_timing: id 0 | task 10905 | eval time = 1886.21 ms / 177 tokens ( 10.72 ms per token, 93.31 tokens per second) 2.31.104.383 I slot print_timing: id 0 | task 10905 | total time = 2056.22 ms / 653 tokens 2.31.104.383 I slot print_timing: id 0 | task 10905 | graphs reused = 10349 2.31.104.385 I slot print_timing: id 0 | task 10905 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.104.422 I slot release: id 0 | task 10905 | stop processing: n_tokens = 684, truncated = 0 2.31.125.364 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 684, t_last = 151004445 2.31.125.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.31.182.770 I slot launch_slot_: id 0 | task 11085 | processing task, is_child = 0 2.32.476.506 I slot print_timing: id 0 | task 11085 | prompt eval time = 175.55 ms / 466 tokens ( 0.38 ms per token, 2654.51 tokens per second) 2.32.476.511 I slot print_timing: id 0 | task 11085 | eval time = 1118.16 ms / 107 tokens ( 10.55 ms per token, 94.80 tokens per second) 2.32.476.512 I slot print_timing: id 0 | task 11085 | total time = 1293.71 ms / 573 tokens 2.32.476.513 I slot print_timing: id 0 | task 11085 | graphs reused = 10453 2.32.476.514 I slot print_timing: id 0 | task 11085 | graph reallocs = 0 / 0 (same size) / (changed size) 2.32.476.545 I slot release: id 0 | task 11085 | stop processing: n_tokens = 604, truncated = 0 2.32.480.801 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 152376568 2.32.480.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 2.32.536.953 I slot launch_slot_: id 0 | task 11195 | processing task, is_child = 0 2.33.516.646 I slot print_timing: id 0 | task 11195 | prompt eval time = 154.38 ms / 415 tokens ( 0.37 ms per token, 2688.15 tokens per second) 2.33.516.653 I slot print_timing: id 0 | task 11195 | eval time = 825.29 ms / 78 tokens ( 10.72 ms per token, 93.30 tokens per second) 2.33.516.654 I slot print_timing: id 0 | task 11195 | total time = 979.67 ms / 493 tokens 2.33.516.655 I slot print_timing: id 0 | task 11195 | graphs reused = 10528 2.33.516.656 I slot print_timing: id 0 | task 11195 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.516.689 I slot release: id 0 | task 11195 | stop processing: n_tokens = 524, truncated = 0 2.33.533.981 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 153416712 2.33.534.036 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 2.33.591.684 I slot launch_slot_: id 0 | task 11276 | processing task, is_child = 0 2.34.416.535 I slot print_timing: id 0 | task 11276 | prompt eval time = 150.24 ms / 352 tokens ( 0.43 ms per token, 2342.95 tokens per second) 2.34.416.541 I slot print_timing: id 0 | task 11276 | eval time = 674.59 ms / 64 tokens ( 10.71 ms per token, 93.39 tokens per second) 2.34.416.542 I slot print_timing: id 0 | task 11276 | total time = 824.83 ms / 416 tokens 2.34.416.543 I slot print_timing: id 0 | task 11276 | graphs reused = 10590 2.34.416.543 I slot print_timing: id 0 | task 11276 | graph reallocs = 0 / 0 (same size) / (changed size) 2.34.416.571 I slot release: id 0 | task 11276 | stop processing: n_tokens = 447, truncated = 0 2.34.441.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 154316594 2.34.441.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.672 MiB) 2.34.497.779 I slot launch_slot_: id 0 | task 11343 | processing task, is_child = 0 2.36.080.973 I slot print_timing: id 0 | task 11343 | prompt eval time = 195.64 ms / 550 tokens ( 0.36 ms per token, 2811.33 tokens per second) 2.36.080.979 I slot print_timing: id 0 | task 11343 | eval time = 1387.54 ms / 133 tokens ( 10.51 ms per token, 95.13 tokens per second) 2.36.080.980 I slot print_timing: id 0 | task 11343 | total time = 1583.17 ms / 683 tokens 2.36.080.981 I slot print_timing: id 0 | task 11343 | graphs reused = 10721 2.36.080.981 I slot print_timing: id 0 | task 11343 | graph reallocs = 0 / 0 (same size) / (changed size) 2.36.081.018 I slot release: id 0 | task 11343 | stop processing: n_tokens = 714, truncated = 0 2.36.104.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 155981041 2.36.104.476 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.768 MiB) 2.36.168.075 I slot launch_slot_: id 0 | task 11480 | processing task, is_child = 0 2.38.766.877 I slot print_timing: id 0 | task 11480 | prompt eval time = 234.62 ms / 772 tokens ( 0.30 ms per token, 3290.36 tokens per second) 2.38.766.883 I slot print_timing: id 0 | task 11480 | eval time = 2364.16 ms / 226 tokens ( 10.51 ms per token, 95.17 tokens per second) 2.38.766.884 I slot print_timing: id 0 | task 11480 | total time = 2598.78 ms / 998 tokens 2.38.766.885 I slot print_timing: id 0 | task 11480 | graphs reused = 10944 2.38.766.886 I slot print_timing: id 0 | task 11480 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.766.928 I slot release: id 0 | task 11480 | stop processing: n_tokens = 1029, truncated = 0 2.38.771.634 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 158666951 2.38.771.707 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.862 MiB) 2.38.836.613 I slot launch_slot_: id 0 | task 11710 | processing task, is_child = 0 2.40.958.789 I slot print_timing: id 0 | task 11710 | prompt eval time = 229.28 ms / 683 tokens ( 0.34 ms per token, 2978.86 tokens per second) 2.40.958.795 I slot print_timing: id 0 | task 11710 | eval time = 1892.87 ms / 181 tokens ( 10.52 ms per token, 95.09 tokens per second) 2.40.958.796 I slot print_timing: id 0 | task 11710 | total time = 2122.15 ms / 864 tokens 2.40.958.797 I slot print_timing: id 0 | task 11710 | graphs reused = 11122 2.40.958.799 I slot print_timing: id 0 | task 11710 | graph reallocs = 0 / 0 (same size) / (changed size) 2.40.958.841 I slot release: id 0 | task 11710 | stop processing: n_tokens = 895, truncated = 0 2.40.976.245 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 160858864 2.40.976.315 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.328 MiB) 2.41.040.051 I slot launch_slot_: id 0 | task 11895 | processing task, is_child = 0 2.43.538.985 I slot print_timing: id 0 | task 11895 | prompt eval time = 203.41 ms / 579 tokens ( 0.35 ms per token, 2846.41 tokens per second) 2.43.538.991 I slot print_timing: id 0 | task 11895 | eval time = 2295.50 ms / 218 tokens ( 10.58 ms per token, 94.53 tokens per second) 2.43.538.992 I slot print_timing: id 0 | task 11895 | total time = 2498.91 ms / 797 tokens 2.43.538.993 I slot print_timing: id 0 | task 11895 | graphs reused = 11337 2.43.538.994 I slot print_timing: id 0 | task 11895 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.539.034 I slot release: id 0 | task 11895 | stop processing: n_tokens = 828, truncated = 0 2.43.558.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 828, t_last = 163439057 2.43.558.927 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.864 MiB) 2.43.567.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.611 MiB) 2.43.636.571 I slot launch_slot_: id 0 | task 12117 | processing task, is_child = 0 2.44.926.169 I slot print_timing: id 0 | task 12117 | prompt eval time = 184.33 ms / 500 tokens ( 0.37 ms per token, 2712.59 tokens per second) 2.44.926.174 I slot print_timing: id 0 | task 12117 | eval time = 1105.25 ms / 106 tokens ( 10.53 ms per token, 95.00 tokens per second) 2.44.926.175 I slot print_timing: id 0 | task 12117 | total time = 1289.58 ms / 606 tokens 2.44.926.177 I slot print_timing: id 0 | task 12117 | graphs reused = 11441 2.44.926.177 I slot print_timing: id 0 | task 12117 | graph reallocs = 0 / 0 (same size) / (changed size) 2.44.926.209 I slot release: id 0 | task 12117 | stop processing: n_tokens = 637, truncated = 0 2.44.948.037 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 164826231 2.44.948.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.296 MiB) 2.45.004.528 I slot launch_slot_: id 0 | task 12226 | processing task, is_child = 0 2.47.428.410 I slot print_timing: id 0 | task 12226 | prompt eval time = 236.85 ms / 776 tokens ( 0.31 ms per token, 3276.29 tokens per second) 2.47.428.416 I slot print_timing: id 0 | task 12226 | eval time = 2187.01 ms / 209 tokens ( 10.51 ms per token, 95.11 tokens per second) 2.47.428.417 I slot print_timing: id 0 | task 12226 | total time = 2423.86 ms / 985 tokens 2.47.428.417 I slot print_timing: id 0 | task 12226 | graphs reused = 11648 2.47.428.418 I slot print_timing: id 0 | task 12226 | graph reallocs = 0 / 0 (same size) / (changed size) 2.47.428.460 I slot release: id 0 | task 12226 | stop processing: n_tokens = 1016, truncated = 0 2.47.456.162 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 167328483 2.47.456.238 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.268 MiB) 2.47.521.956 I slot launch_slot_: id 0 | task 12439 | processing task, is_child = 0 2.49.753.430 I slot print_timing: id 0 | task 12439 | prompt eval time = 175.99 ms / 504 tokens ( 0.35 ms per token, 2863.88 tokens per second) 2.49.753.435 I slot print_timing: id 0 | task 12439 | eval time = 2055.47 ms / 197 tokens ( 10.49 ms per token, 95.36 tokens per second) 2.49.753.437 I slot print_timing: id 0 | task 12439 | total time = 2231.45 ms / 701 tokens 2.49.753.437 I slot print_timing: id 0 | task 12439 | graphs reused = 11843 2.49.753.438 I slot print_timing: id 0 | task 12439 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.753.472 I slot release: id 0 | task 12439 | stop processing: n_tokens = 732, truncated = 0 2.49.769.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 732, t_last = 169653495 2.49.769.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.578 MiB) 2.49.837.445 I slot launch_slot_: id 0 | task 12639 | processing task, is_child = 0 2.52.209.742 I slot print_timing: id 0 | task 12639 | prompt eval time = 208.43 ms / 633 tokens ( 0.33 ms per token, 3037.01 tokens per second) 2.52.209.748 I slot print_timing: id 0 | task 12639 | eval time = 2163.85 ms / 207 tokens ( 10.50 ms per token, 95.20 tokens per second) 2.52.209.749 I slot print_timing: id 0 | task 12639 | total time = 2372.28 ms / 840 tokens 2.52.209.751 I slot print_timing: id 0 | task 12639 | graphs reused = 12047 2.52.209.751 I slot print_timing: id 0 | task 12639 | graph reallocs = 0 / 0 (same size) / (changed size) 2.52.209.792 I slot release: id 0 | task 12639 | stop processing: n_tokens = 871, truncated = 0 2.52.226.040 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 172109815 2.52.226.107 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.116 MiB) 2.52.310.562 I slot launch_slot_: id 0 | task 12850 | processing task, is_child = 0 2.53.866.125 I slot print_timing: id 0 | task 12850 | prompt eval time = 157.21 ms / 395 tokens ( 0.40 ms per token, 2512.55 tokens per second) 2.53.866.132 I slot print_timing: id 0 | task 12850 | eval time = 1398.33 ms / 134 tokens ( 10.51 ms per token, 95.11 tokens per second) 2.53.866.133 I slot print_timing: id 0 | task 12850 | total time = 1555.54 ms / 529 tokens 2.53.866.134 I slot print_timing: id 0 | task 12850 | graphs reused = 12178 2.53.866.135 I slot print_timing: id 0 | task 12850 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.866.165 I slot release: id 0 | task 12850 | stop processing: n_tokens = 560, truncated = 0 2.53.894.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 173766187 2.53.894.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 2.53.962.216 I slot launch_slot_: id 0 | task 12987 | processing task, is_child = 0 2.56.349.316 I slot print_timing: id 0 | task 12987 | prompt eval time = 199.49 ms / 584 tokens ( 0.34 ms per token, 2927.54 tokens per second) 2.56.349.322 I slot print_timing: id 0 | task 12987 | eval time = 2187.60 ms / 209 tokens ( 10.52 ms per token, 95.08 tokens per second) 2.56.349.323 I slot print_timing: id 0 | task 12987 | total time = 2387.08 ms / 793 tokens 2.56.349.324 I slot print_timing: id 0 | task 12987 | graphs reused = 12384 2.56.349.325 I slot print_timing: id 0 | task 12987 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.349.361 I slot release: id 0 | task 12987 | stop processing: n_tokens = 824, truncated = 0 2.56.373.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 176249384 2.56.373.229 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.831 MiB) 2.56.451.838 I slot launch_slot_: id 0 | task 13200 | processing task, is_child = 0 2.59.088.840 I slot print_timing: id 0 | task 13200 | prompt eval time = 228.41 ms / 695 tokens ( 0.33 ms per token, 3042.84 tokens per second) 2.59.088.846 I slot print_timing: id 0 | task 13200 | eval time = 2408.58 ms / 230 tokens ( 10.52 ms per token, 95.08 tokens per second) 2.59.088.847 I slot print_timing: id 0 | task 13200 | total time = 2636.98 ms / 925 tokens 2.59.088.847 I slot print_timing: id 0 | task 13200 | graphs reused = 12611 2.59.088.848 I slot print_timing: id 0 | task 13200 | graph reallocs = 0 / 0 (same size) / (changed size) 2.59.088.888 I slot release: id 0 | task 13200 | stop processing: n_tokens = 956, truncated = 0 2.59.093.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 178988910 2.59.093.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.300 MiB) 2.59.165.592 I slot launch_slot_: id 0 | task 13434 | processing task, is_child = 0 3.01.400.227 I slot print_timing: id 0 | task 13434 | prompt eval time = 239.34 ms / 769 tokens ( 0.31 ms per token, 3213.00 tokens per second) 3.01.400.233 I slot print_timing: id 0 | task 13434 | eval time = 1995.28 ms / 191 tokens ( 10.50 ms per token, 95.22 tokens per second) 3.01.400.234 I slot print_timing: id 0 | task 13434 | total time = 2234.62 ms / 960 tokens 3.01.400.235 I slot print_timing: id 0 | task 13434 | graphs reused = 12800 3.01.400.236 I slot print_timing: id 0 | task 13434 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.400.279 I slot release: id 0 | task 13434 | stop processing: n_tokens = 991, truncated = 0 3.01.425.039 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 181300302 3.01.425.113 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.176 MiB) 3.01.440.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.860 MiB) 3.01.517.174 I slot launch_slot_: id 0 | task 13629 | processing task, is_child = 0 3.03.005.532 I slot print_timing: id 0 | task 13629 | prompt eval time = 197.52 ms / 576 tokens ( 0.34 ms per token, 2916.15 tokens per second) 3.03.005.538 I slot print_timing: id 0 | task 13629 | eval time = 1290.82 ms / 124 tokens ( 10.49 ms per token, 95.29 tokens per second) 3.03.005.539 I slot print_timing: id 0 | task 13629 | total time = 1488.34 ms / 700 tokens 3.03.005.540 I slot print_timing: id 0 | task 13629 | graphs reused = 12922 3.03.005.541 I slot print_timing: id 0 | task 13629 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.005.578 I slot release: id 0 | task 13629 | stop processing: n_tokens = 731, truncated = 0 3.03.032.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 182905601 3.03.032.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.577 MiB) 3.03.099.630 I slot launch_slot_: id 0 | task 13757 | processing task, is_child = 0 3.06.237.335 I slot print_timing: id 0 | task 13757 | prompt eval time = 217.22 ms / 655 tokens ( 0.33 ms per token, 3015.35 tokens per second) 3.06.237.341 I slot print_timing: id 0 | task 13757 | eval time = 2920.46 ms / 275 tokens ( 10.66 ms per token, 93.82 tokens per second) 3.06.237.342 I slot print_timing: id 0 | task 13757 | total time = 3137.68 ms / 930 tokens 3.06.237.343 I slot print_timing: id 0 | task 13757 | graphs reused = 13194 3.06.237.344 I slot print_timing: id 0 | task 13757 | graph reallocs = 0 / 0 (same size) / (changed size) 3.06.237.385 I slot release: id 0 | task 13757 | stop processing: n_tokens = 961, truncated = 0 3.06.261.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 186137408 3.06.261.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.204 MiB) 3.06.327.214 I slot launch_slot_: id 0 | task 14036 | processing task, is_child = 0 3.07.821.154 I slot print_timing: id 0 | task 14036 | prompt eval time = 217.71 ms / 621 tokens ( 0.35 ms per token, 2852.47 tokens per second) 3.07.821.160 I slot print_timing: id 0 | task 14036 | eval time = 1276.21 ms / 121 tokens ( 10.64 ms per token, 94.03 tokens per second) 3.07.821.161 I slot print_timing: id 0 | task 14036 | total time = 1493.92 ms / 742 tokens 3.07.821.162 I slot print_timing: id 0 | task 14036 | graphs reused = 13312 3.07.821.163 I slot print_timing: id 0 | task 14036 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.821.203 I slot release: id 0 | task 14036 | stop processing: n_tokens = 773, truncated = 0 3.07.845.884 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 187721226 3.07.845.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.014 MiB) 3.07.910.908 I slot launch_slot_: id 0 | task 14161 | processing task, is_child = 0 3.10.041.463 I slot print_timing: id 0 | task 14161 | prompt eval time = 233.38 ms / 767 tokens ( 0.30 ms per token, 3286.42 tokens per second) 3.10.041.469 I slot print_timing: id 0 | task 14161 | eval time = 1897.15 ms / 178 tokens ( 10.72 ms per token, 93.30 tokens per second) 3.10.041.470 I slot print_timing: id 0 | task 14161 | total time = 2130.54 ms / 945 tokens 3.10.041.471 I slot print_timing: id 0 | task 14161 | graphs reused = 13488 3.10.041.472 I slot print_timing: id 0 | task 14161 | graph reallocs = 0 / 0 (same size) / (changed size) 3.10.041.515 I slot release: id 0 | task 14161 | stop processing: n_tokens = 976, truncated = 0 3.10.070.340 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 976, t_last = 189941538 3.10.070.414 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.890 MiB) 3.10.134.278 I slot launch_slot_: id 0 | task 14343 | processing task, is_child = 0 3.12.574.239 I slot print_timing: id 0 | task 14343 | prompt eval time = 261.06 ms / 864 tokens ( 0.30 ms per token, 3309.57 tokens per second) 3.12.574.244 I slot print_timing: id 0 | task 14343 | eval time = 2178.88 ms / 203 tokens ( 10.79 ms per token, 92.71 tokens per second) 3.12.574.245 I slot print_timing: id 0 | task 14343 | total time = 2439.94 ms / 1067 tokens 3.12.574.246 I slot print_timing: id 0 | task 14343 | graphs reused = 13688 3.12.574.247 I slot print_timing: id 0 | task 14343 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.574.295 I slot release: id 0 | task 14343 | stop processing: n_tokens = 1098, truncated = 0 3.12.598.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 192474318 3.12.598.563 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.235 MiB) 3.12.607.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.954 MiB) 3.12.679.235 I slot launch_slot_: id 0 | task 14550 | processing task, is_child = 0 3.14.266.516 I slot print_timing: id 0 | task 14550 | prompt eval time = 224.06 ms / 646 tokens ( 0.35 ms per token, 2883.21 tokens per second) 3.14.266.522 I slot print_timing: id 0 | task 14550 | eval time = 1363.20 ms / 129 tokens ( 10.65 ms per token, 93.90 tokens per second) 3.14.266.523 I slot print_timing: id 0 | task 14550 | total time = 1587.26 ms / 775 tokens 3.14.266.524 I slot print_timing: id 0 | task 14550 | graphs reused = 13814 3.14.266.526 I slot print_timing: id 0 | task 14550 | graph reallocs = 0 / 0 (same size) / (changed size) 3.14.266.564 I slot release: id 0 | task 14550 | stop processing: n_tokens = 806, truncated = 0 3.14.290.663 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 194166587 3.14.290.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.330 MiB) 3.14.353.203 I slot launch_slot_: id 0 | task 14683 | processing task, is_child = 0 3.16.932.126 I slot print_timing: id 0 | task 14683 | prompt eval time = 222.57 ms / 720 tokens ( 0.31 ms per token, 3234.92 tokens per second) 3.16.932.132 I slot print_timing: id 0 | task 14683 | eval time = 2356.33 ms / 219 tokens ( 10.81 ms per token, 92.52 tokens per second) 3.16.932.133 I slot print_timing: id 0 | task 14683 | total time = 2578.90 ms / 939 tokens 3.16.932.134 I slot print_timing: id 0 | task 14683 | graphs reused = 14030 3.16.932.135 I slot print_timing: id 0 | task 14683 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.932.178 I slot release: id 0 | task 14683 | stop processing: n_tokens = 970, truncated = 0 3.16.948.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 970, t_last = 196832200 3.16.948.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 322.894 MiB) 3.17.011.690 I slot launch_slot_: id 0 | task 14906 | processing task, is_child = 0 3.19.428.883 I slot print_timing: id 0 | task 14906 | prompt eval time = 180.90 ms / 509 tokens ( 0.36 ms per token, 2813.79 tokens per second) 3.19.428.889 I slot print_timing: id 0 | task 14906 | eval time = 2236.28 ms / 214 tokens ( 10.50 ms per token, 95.25 tokens per second) 3.19.428.890 I slot print_timing: id 0 | task 14906 | total time = 2417.17 ms / 723 tokens 3.19.428.891 I slot print_timing: id 0 | task 14906 | graphs reused = 14242 3.19.428.892 I slot print_timing: id 0 | task 14906 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.428.927 I slot release: id 0 | task 14906 | stop processing: n_tokens = 754, truncated = 0 3.19.458.289 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 199328949 3.19.458.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 320.392 MiB) 3.19.514.823 I slot launch_slot_: id 0 | task 15123 | processing task, is_child = 0 3.22.239.808 I slot print_timing: id 0 | task 15123 | prompt eval time = 196.33 ms / 581 tokens ( 0.34 ms per token, 2959.26 tokens per second) 3.22.239.815 I slot print_timing: id 0 | task 15123 | eval time = 2528.63 ms / 242 tokens ( 10.49 ms per token, 95.31 tokens per second) 3.22.239.816 I slot print_timing: id 0 | task 15123 | total time = 2724.96 ms / 823 tokens 3.22.239.817 I slot print_timing: id 0 | task 15123 | graphs reused = 14481 3.22.239.818 I slot print_timing: id 0 | task 15123 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.239.858 I slot release: id 0 | task 15123 | stop processing: n_tokens = 854, truncated = 0 3.22.262.259 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 202139881 3.22.262.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 317.891 MiB) 3.22.326.966 I slot launch_slot_: id 0 | task 15369 | processing task, is_child = 0 3.24.898.252 I slot print_timing: id 0 | task 15369 | prompt eval time = 267.66 ms / 925 tokens ( 0.29 ms per token, 3455.88 tokens per second) 3.24.898.258 I slot print_timing: id 0 | task 15369 | eval time = 2303.61 ms / 220 tokens ( 10.52 ms per token, 95.07 tokens per second) 3.24.898.260 I slot print_timing: id 0 | task 15369 | total time = 2571.27 ms / 1145 tokens 3.24.898.260 I slot print_timing: id 0 | task 15369 | graphs reused = 14698 3.24.898.261 I slot print_timing: id 0 | task 15369 | graph reallocs = 0 / 0 (same size) / (changed size) 3.24.898.309 I slot release: id 0 | task 15369 | stop processing: n_tokens = 1176, truncated = 0 3.24.922.031 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1176, t_last = 204798333 3.24.922.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.483 MiB) 3.24.994.744 I slot launch_slot_: id 0 | task 15593 | processing task, is_child = 0 3.27.873.549 I slot print_timing: id 0 | task 15593 | prompt eval time = 256.35 ms / 885 tokens ( 0.29 ms per token, 3452.35 tokens per second) 3.27.873.554 I slot print_timing: id 0 | task 15593 | eval time = 2622.44 ms / 245 tokens ( 10.75 ms per token, 93.04 tokens per second) 3.27.873.556 I slot print_timing: id 0 | task 15593 | total time = 2878.78 ms / 1130 tokens 3.27.873.556 I slot print_timing: id 0 | task 15593 | graphs reused = 14940 3.27.873.557 I slot print_timing: id 0 | task 15593 | graph reallocs = 0 / 0 (same size) / (changed size) 3.27.873.603 I slot release: id 0 | task 15593 | stop processing: n_tokens = 1161, truncated = 0 3.27.896.740 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 207773626 3.27.896.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.083 MiB) 3.27.964.700 I slot launch_slot_: id 0 | task 15842 | processing task, is_child = 0 3.29.216.950 I slot print_timing: id 0 | task 15842 | prompt eval time = 154.59 ms / 392 tokens ( 0.39 ms per token, 2535.74 tokens per second) 3.29.216.955 I slot print_timing: id 0 | task 15842 | eval time = 1097.64 ms / 105 tokens ( 10.55 ms per token, 94.75 tokens per second) 3.29.216.956 I slot print_timing: id 0 | task 15842 | total time = 1252.23 ms / 497 tokens 3.29.216.957 I slot print_timing: id 0 | task 15842 | graphs reused = 15042 3.29.216.958 I slot print_timing: id 0 | task 15842 | graph reallocs = 0 / 0 (same size) / (changed size) 3.29.216.989 I slot release: id 0 | task 15842 | stop processing: n_tokens = 528, truncated = 0 3.29.243.975 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 528, t_last = 209117012 3.29.244.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.934 MiB) 3.29.313.936 I slot launch_slot_: id 0 | task 15950 | processing task, is_child = 0 3.30.000.279 I slot print_timing: id 0 | task 15950 | prompt eval time = 160.47 ms / 331 tokens ( 0.48 ms per token, 2062.69 tokens per second) 3.30.000.284 I slot print_timing: id 0 | task 15950 | eval time = 525.85 ms / 49 tokens ( 10.96 ms per token, 91.28 tokens per second) 3.30.000.286 I slot print_timing: id 0 | task 15950 | total time = 686.32 ms / 380 tokens 3.30.000.286 I slot print_timing: id 0 | task 15950 | graphs reused = 15089 3.30.000.287 I slot print_timing: id 0 | task 15950 | graph reallocs = 0 / 0 (same size) / (changed size) 3.30.000.317 I slot release: id 0 | task 15950 | stop processing: n_tokens = 411, truncated = 0 3.30.020.003 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 209900340 3.30.020.047 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 379.743 MiB) 3.30.085.704 I slot launch_slot_: id 0 | task 16002 | processing task, is_child = 0 3.31.899.648 I slot print_timing: id 0 | task 16002 | prompt eval time = 162.54 ms / 357 tokens ( 0.46 ms per token, 2196.33 tokens per second) 3.31.899.654 I slot print_timing: id 0 | task 16002 | eval time = 1651.36 ms / 157 tokens ( 10.59 ms per token, 94.47 tokens per second) 3.31.899.655 I slot print_timing: id 0 | task 16002 | total time = 1813.90 ms / 514 tokens 3.31.899.656 I slot print_timing: id 0 | task 16002 | graphs reused = 15243 3.31.899.657 I slot print_timing: id 0 | task 16002 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.899.688 I slot release: id 0 | task 16002 | stop processing: n_tokens = 545, truncated = 0 3.31.914.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 211799710 3.31.914.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.648 MiB) 3.31.972.613 I slot launch_slot_: id 0 | task 16162 | processing task, is_child = 0 3.32.670.945 I slot print_timing: id 0 | task 16162 | prompt eval time = 147.62 ms / 315 tokens ( 0.47 ms per token, 2133.83 tokens per second) 3.32.670.952 I slot print_timing: id 0 | task 16162 | eval time = 550.69 ms / 53 tokens ( 10.59 ms per token, 94.43 tokens per second) 3.32.670.953 I slot print_timing: id 0 | task 16162 | total time = 698.31 ms / 368 tokens 3.32.670.954 I slot print_timing: id 0 | task 16162 | graphs reused = 15294 3.32.670.955 I slot print_timing: id 0 | task 16162 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.670.986 I slot release: id 0 | task 16162 | stop processing: n_tokens = 399, truncated = 0 3.32.690.399 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 212571009 3.32.690.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.424 MiB) 3.32.744.732 I slot launch_slot_: id 0 | task 16218 | processing task, is_child = 0 3.33.741.272 I slot print_timing: id 0 | task 16218 | prompt eval time = 147.10 ms / 378 tokens ( 0.39 ms per token, 2569.61 tokens per second) 3.33.741.278 I slot print_timing: id 0 | task 16218 | eval time = 849.42 ms / 82 tokens ( 10.49 ms per token, 95.36 tokens per second) 3.33.741.279 I slot print_timing: id 0 | task 16218 | total time = 996.52 ms / 460 tokens 3.33.741.280 I slot print_timing: id 0 | task 16218 | graphs reused = 15374 3.33.741.281 I slot print_timing: id 0 | task 16218 | graph reallocs = 0 / 0 (same size) / (changed size) 3.33.741.312 I slot release: id 0 | task 16218 | stop processing: n_tokens = 491, truncated = 0 3.33.767.456 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 213641335 3.33.767.508 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.527 MiB) 3.33.827.969 I slot launch_slot_: id 0 | task 16303 | processing task, is_child = 0 3.34.252.503 I slot print_timing: id 0 | task 16303 | prompt eval time = 136.76 ms / 295 tokens ( 0.46 ms per token, 2157.08 tokens per second) 3.34.252.509 I slot print_timing: id 0 | task 16303 | eval time = 287.74 ms / 28 tokens ( 10.66 ms per token, 93.84 tokens per second) 3.34.252.510 I slot print_timing: id 0 | task 16303 | total time = 424.49 ms / 323 tokens 3.34.252.511 I slot print_timing: id 0 | task 16303 | graphs reused = 15400 3.34.252.512 I slot print_timing: id 0 | task 16303 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.252.542 I slot release: id 0 | task 16303 | stop processing: n_tokens = 354, truncated = 0 3.34.279.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 214152565 3.34.279.723 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 324.395 MiB) 3.34.345.246 I slot launch_slot_: id 0 | task 16334 | processing task, is_child = 0 3.34.941.371 I slot print_timing: id 0 | task 16334 | prompt eval time = 141.50 ms / 337 tokens ( 0.42 ms per token, 2381.56 tokens per second) 3.34.941.376 I slot print_timing: id 0 | task 16334 | eval time = 454.60 ms / 44 tokens ( 10.57 ms per token, 94.59 tokens per second) 3.34.941.377 I slot print_timing: id 0 | task 16334 | total time = 596.11 ms / 381 tokens 3.34.941.378 I slot print_timing: id 0 | task 16334 | graphs reused = 15442 3.34.941.379 I slot print_timing: id 0 | task 16334 | graph reallocs = 0 / 0 (same size) / (changed size) 3.34.941.408 I slot release: id 0 | task 16334 | stop processing: n_tokens = 412, truncated = 0 3.34.945.166 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 214841431 3.34.985.971 I slot launch_slot_: id 0 | task 16381 | processing task, is_child = 0 3.35.756.841 I slot print_timing: id 0 | task 16381 | prompt eval time = 141.52 ms / 325 tokens ( 0.44 ms per token, 2296.43 tokens per second) 3.35.756.848 I slot print_timing: id 0 | task 16381 | eval time = 629.32 ms / 60 tokens ( 10.67 ms per token, 93.75 tokens per second) 3.35.756.850 I slot print_timing: id 0 | task 16381 | total time = 770.85 ms / 385 tokens 3.35.756.850 I slot print_timing: id 0 | task 16381 | graphs reused = 15500 3.35.756.851 I slot print_timing: id 0 | task 16381 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.756.885 I slot release: id 0 | task 16381 | stop processing: n_tokens = 416, truncated = 0 3.35.778.732 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.077 3.35.778.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.993 MiB) 3.35.852.656 I slot launch_slot_: id 0 | task 16444 | processing task, is_child = 0 3.36.577.598 I slot print_timing: id 0 | task 16444 | prompt eval time = 125.18 ms / 264 tokens ( 0.47 ms per token, 2108.96 tokens per second) 3.36.577.604 I slot print_timing: id 0 | task 16444 | eval time = 599.74 ms / 57 tokens ( 10.71 ms per token, 93.37 tokens per second) 3.36.577.605 I slot print_timing: id 0 | task 16444 | total time = 724.92 ms / 321 tokens 3.36.577.606 I slot print_timing: id 0 | task 16444 | graphs reused = 15555 3.36.577.607 I slot print_timing: id 0 | task 16444 | graph reallocs = 0 / 0 (same size) / (changed size) 3.36.577.636 I slot release: id 0 | task 16444 | stop processing: n_tokens = 352, truncated = 0 3.36.604.767 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 216477659 3.36.604.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 319.016 MiB) 3.36.674.274 I slot launch_slot_: id 0 | task 16504 | processing task, is_child = 0 3.37.038.419 I slot print_timing: id 0 | task 16504 | prompt eval time = 146.75 ms / 331 tokens ( 0.44 ms per token, 2255.49 tokens per second) 3.37.038.426 I slot print_timing: id 0 | task 16504 | eval time = 217.37 ms / 21 tokens ( 10.87 ms per token, 92.01 tokens per second) 3.37.038.427 I slot print_timing: id 0 | task 16504 | total time = 364.12 ms / 352 tokens 3.37.038.428 I slot print_timing: id 0 | task 16504 | graphs reused = 15574 3.37.038.429 I slot print_timing: id 0 | task 16504 | graph reallocs = 0 / 0 (same size) / (changed size) 3.37.038.458 I slot release: id 0 | task 16504 | stop processing: n_tokens = 383, truncated = 0 3.37.059.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 383, t_last = 216938481 3.37.059.406 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 377.523 MiB) 3.37.144.736 I slot launch_slot_: id 0 | task 16528 | processing task, is_child = 0 3.38.313.731 I slot print_timing: id 0 | task 16528 | prompt eval time = 144.32 ms / 333 tokens ( 0.43 ms per token, 2307.44 tokens per second) 3.38.313.737 I slot print_timing: id 0 | task 16528 | eval time = 1024.66 ms / 98 tokens ( 10.56 ms per token, 94.67 tokens per second) 3.38.313.739 I slot print_timing: id 0 | task 16528 | total time = 1168.97 ms / 431 tokens 3.38.313.740 I slot print_timing: id 0 | task 16528 | graphs reused = 15670 3.38.313.740 I slot print_timing: id 0 | task 16528 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.313.772 I slot release: id 0 | task 16528 | stop processing: n_tokens = 462, truncated = 0 3.38.329.715 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 462, t_last = 218213795 3.38.329.756 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.651 MiB) 3.38.401.490 I slot launch_slot_: id 0 | task 16629 | processing task, is_child = 0 3.39.095.887 I slot print_timing: id 0 | task 16629 | prompt eval time = 145.46 ms / 346 tokens ( 0.42 ms per token, 2378.63 tokens per second) 3.39.095.893 I slot print_timing: id 0 | task 16629 | eval time = 548.91 ms / 53 tokens ( 10.56 ms per token, 94.73 tokens per second) 3.39.095.895 I slot print_timing: id 0 | task 16629 | total time = 694.38 ms / 399 tokens 3.39.095.896 I slot print_timing: id 0 | task 16629 | graphs reused = 15721 3.39.095.898 I slot print_timing: id 0 | task 16629 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.095.930 I slot release: id 0 | task 16629 | stop processing: n_tokens = 430, truncated = 0 3.39.113.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 430, t_last = 218995952 3.39.113.159 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.746 MiB) 3.39.173.797 I slot launch_slot_: id 0 | task 16685 | processing task, is_child = 0 3.39.863.794 I slot print_timing: id 0 | task 16685 | prompt eval time = 140.98 ms / 325 tokens ( 0.43 ms per token, 2305.29 tokens per second) 3.39.863.800 I slot print_timing: id 0 | task 16685 | eval time = 549.00 ms / 53 tokens ( 10.56 ms per token, 94.72 tokens per second) 3.39.863.801 I slot print_timing: id 0 | task 16685 | total time = 689.98 ms / 378 tokens 3.39.863.802 I slot print_timing: id 0 | task 16685 | graphs reused = 15772 3.39.863.803 I slot print_timing: id 0 | task 16685 | graph reallocs = 0 / 0 (same size) / (changed size) 3.39.863.832 I slot release: id 0 | task 16685 | stop processing: n_tokens = 409, truncated = 0 3.39.890.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 219763854 3.39.890.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 374.615 MiB) 3.39.954.097 I slot launch_slot_: id 0 | task 16741 | processing task, is_child = 0 3.43.096.887 I slot print_timing: id 0 | task 16741 | n_gen = 287, tg = 95.22 t/s, tg_3s = 95.55 t/s 3.43.128.141 I slot print_timing: id 0 | task 16741 | prompt eval time = 139.24 ms / 322 tokens ( 0.43 ms per token, 2312.59 tokens per second) 3.43.128.146 I slot print_timing: id 0 | task 16741 | eval time = 3034.79 ms / 290 tokens ( 10.50 ms per token, 95.23 tokens per second) 3.43.128.147 I slot print_timing: id 0 | task 16741 | total time = 3174.02 ms / 612 tokens 3.43.128.148 I slot print_timing: id 0 | task 16741 | graphs reused = 16059 3.43.128.149 I slot print_timing: id 0 | task 16741 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.128.177 I slot release: id 0 | task 16741 | stop processing: n_tokens = 643, truncated = 0 3.43.142.818 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 223028200 3.43.189.106 I slot launch_slot_: id 0 | task 17034 | processing task, is_child = 0 3.46.336.520 I slot print_timing: id 0 | task 17034 | n_gen = 287, tg = 95.13 t/s, tg_3s = 95.47 t/s 3.47.426.881 I slot print_timing: id 0 | task 17034 | prompt eval time = 141.06 ms / 338 tokens ( 0.42 ms per token, 2396.08 tokens per second) 3.47.426.887 I slot print_timing: id 0 | task 17034 | eval time = 4096.69 ms / 391 tokens ( 10.50 ms per token, 95.20 tokens per second) 3.47.426.888 I slot print_timing: id 0 | task 17034 | total time = 4237.76 ms / 729 tokens 3.47.426.889 I slot print_timing: id 0 | task 17034 | graphs reused = 16447 3.47.426.890 I slot print_timing: id 0 | task 17034 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.426.918 I slot release: id 0 | task 17034 | stop processing: n_tokens = 760, truncated = 0 3.47.452.722 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 760, t_last = 227326941 3.47.452.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 381.807 MiB) 3.47.514.204 I slot launch_slot_: id 0 | task 17428 | processing task, is_child = 0 3.50.664.831 I slot print_timing: id 0 | task 17428 | n_gen = 287, tg = 95.09 t/s, tg_3s = 95.42 t/s 3.51.011.589 I slot print_timing: id 0 | task 17428 | prompt eval time = 142.82 ms / 347 tokens ( 0.41 ms per token, 2429.67 tokens per second) 3.51.011.595 I slot print_timing: id 0 | task 17428 | eval time = 3354.55 ms / 320 tokens ( 10.52 ms per token, 95.09 tokens per second) 3.51.011.596 I slot print_timing: id 0 | task 17428 | total time = 3497.37 ms / 667 tokens 3.51.011.596 I slot print_timing: id 0 | task 17428 | graphs reused = 16764 3.51.011.597 I slot print_timing: id 0 | task 17428 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.011.626 I slot release: id 0 | task 17428 | stop processing: n_tokens = 698, truncated = 0 3.51.038.122 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 698, t_last = 230911648 3.51.038.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 375.928 MiB) 3.51.099.266 I slot launch_slot_: id 0 | task 17751 | processing task, is_child = 0 3.52.936.904 I slot print_timing: id 0 | task 17751 | prompt eval time = 141.93 ms / 331 tokens ( 0.43 ms per token, 2332.14 tokens per second) 3.52.936.909 I slot print_timing: id 0 | task 17751 | eval time = 1695.69 ms / 162 tokens ( 10.53 ms per token, 94.95 tokens per second) 3.52.936.911 I slot print_timing: id 0 | task 17751 | total time = 1837.62 ms / 493 tokens 3.52.936.912 I slot print_timing: id 0 | task 17751 | graphs reused = 16923 3.52.936.912 I slot print_timing: id 0 | task 17751 | graph reallocs = 0 / 0 (same size) / (changed size) 3.52.936.942 I slot release: id 0 | task 17751 | stop processing: n_tokens = 524, truncated = 0 3.52.955.012 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 232836964 3.52.955.057 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.277 MiB) 3.53.014.070 I slot launch_slot_: id 0 | task 17916 | processing task, is_child = 0 3.53.579.755 I slot print_timing: id 0 | task 17916 | prompt eval time = 142.53 ms / 345 tokens ( 0.41 ms per token, 2420.53 tokens per second) 3.53.579.762 I slot print_timing: id 0 | task 17916 | eval time = 423.14 ms / 41 tokens ( 10.58 ms per token, 94.53 tokens per second) 3.53.579.763 I slot print_timing: id 0 | task 17916 | total time = 565.67 ms / 386 tokens 3.53.579.763 I slot print_timing: id 0 | task 17916 | graphs reused = 16962 3.53.579.764 I slot print_timing: id 0 | task 17916 | graph reallocs = 0 / 0 (same size) / (changed size) 3.53.579.795 I slot release: id 0 | task 17916 | stop processing: n_tokens = 417, truncated = 0 3.53.597.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 233479818 3.53.597.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.092 MiB) 3.53.655.324 I slot launch_slot_: id 0 | task 17960 | processing task, is_child = 0 3.54.360.993 I slot print_timing: id 0 | task 17960 | prompt eval time = 143.92 ms / 320 tokens ( 0.45 ms per token, 2223.52 tokens per second) 3.54.360.998 I slot print_timing: id 0 | task 17960 | eval time = 561.73 ms / 54 tokens ( 10.60 ms per token, 94.35 tokens per second) 3.54.360.999 I slot print_timing: id 0 | task 17960 | total time = 705.65 ms / 374 tokens 3.54.361.000 I slot print_timing: id 0 | task 17960 | graphs reused = 17014 3.54.361.001 I slot print_timing: id 0 | task 17960 | graph reallocs = 0 / 0 (same size) / (changed size) 3.54.361.030 I slot release: id 0 | task 17960 | stop processing: n_tokens = 405, truncated = 0 3.54.377.006 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 405, t_last = 234261053 3.54.377.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 376.960 MiB) 3.54.433.571 I slot launch_slot_: id 0 | task 18017 | processing task, is_child = 0 3.55.085.548 I slot print_timing: id 0 | task 18017 | prompt eval time = 134.96 ms / 297 tokens ( 0.45 ms per token, 2200.64 tokens per second) 3.55.085.554 I slot print_timing: id 0 | task 18017 | eval time = 517.00 ms / 47 tokens ( 11.24 ms per token, 88.98 tokens per second) 3.55.085.555 I slot print_timing: id 0 | task 18017 | total time = 651.96 ms / 344 tokens 3.55.085.556 I slot print_timing: id 0 | task 18017 | graphs reused = 17059 3.55.085.556 I slot print_timing: id 0 | task 18017 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.085.584 I slot release: id 0 | task 18017 | stop processing: n_tokens = 375, truncated = 0 3.55.104.523 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 234985607 3.55.146.741 I slot launch_slot_: id 0 | task 18067 | processing task, is_child = 0 3.57.072.425 I slot print_timing: id 0 | task 18067 | prompt eval time = 143.12 ms / 343 tokens ( 0.42 ms per token, 2396.64 tokens per second) 3.57.072.431 I slot print_timing: id 0 | task 18067 | eval time = 1782.54 ms / 169 tokens ( 10.61 ms per token, 94.25 tokens per second) 3.57.072.433 I slot print_timing: id 0 | task 18067 | total time = 1925.66 ms / 512 tokens 3.57.072.433 I slot print_timing: id 0 | task 18067 | graphs reused = 17225 3.57.072.434 I slot print_timing: id 0 | task 18067 | graph reallocs = 0 / 0 (same size) / (changed size) 3.57.072.467 I slot release: id 0 | task 18067 | stop processing: n_tokens = 543, truncated = 0 3.57.100.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 236972490 3.57.100.121 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 382.089 MiB) 3.57.160.331 I slot launch_slot_: id 0 | task 18239 | processing task, is_child = 0 3.58.397.948 I slot print_timing: id 0 | task 18239 | prompt eval time = 152.90 ms / 371 tokens ( 0.41 ms per token, 2426.36 tokens per second) 3.58.397.953 I slot print_timing: id 0 | task 18239 | eval time = 1084.69 ms / 103 tokens ( 10.63 ms per token, 94.04 tokens per second) 3.58.397.954 I slot print_timing: id 0 | task 18239 | total time = 1237.60 ms / 474 tokens 3.58.397.955 I slot print_timing: id 0 | task 18239 | graphs reused = 17326 3.58.397.956 I slot print_timing: id 0 | task 18239 | graph reallocs = 0 / 0 (same size) / (changed size) 3.58.397.988 I slot release: id 0 | task 18239 | stop processing: n_tokens = 505, truncated = 0 3.58.425.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 238298011 3.58.425.746 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.083 MiB) 3.58.480.224 I slot launch_slot_: id 0 | task 18345 | processing task, is_child = 0 4.01.615.148 I slot print_timing: id 0 | task 18345 | n_gen = 286, tg = 94.98 t/s, tg_3s = 95.32 t/s 4.01.719.189 I slot print_timing: id 0 | task 18345 | prompt eval time = 134.42 ms / 292 tokens ( 0.46 ms per token, 2172.28 tokens per second) 4.01.719.194 I slot print_timing: id 0 | task 18345 | eval time = 3104.52 ms / 296 tokens ( 10.52 ms per token, 95.02 tokens per second) 4.01.719.195 I slot print_timing: id 0 | task 18345 | total time = 3238.94 ms / 588 tokens 4.01.719.196 I slot print_timing: id 0 | task 18345 | graphs reused = 17619 4.01.719.196 I slot print_timing: id 0 | task 18345 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.719.222 I slot release: id 0 | task 18345 | stop processing: n_tokens = 619, truncated = 0 4.01.732.518 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 619, t_last = 241619245 4.01.732.570 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 378.461 MiB) 4.01.790.447 I slot launch_slot_: id 0 | task 18644 | processing task, is_child = 0 4.02.106.290 I slot print_timing: id 0 | task 18644 | prompt eval time = 133.72 ms / 301 tokens ( 0.44 ms per token, 2250.96 tokens per second) 4.02.106.296 I slot print_timing: id 0 | task 18644 | eval time = 182.10 ms / 18 tokens ( 10.71 ms per token, 93.35 tokens per second) 4.02.106.297 I slot print_timing: id 0 | task 18644 | total time = 315.83 ms / 319 tokens 4.02.106.298 I slot print_timing: id 0 | task 18644 | graphs reused = 17635 4.02.106.299 I slot print_timing: id 0 | task 18644 | graph reallocs = 0 / 0 (same size) / (changed size) 4.02.106.327 I slot release: id 0 | task 18644 | stop processing: n_tokens = 350, truncated = 0 4.02.109.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 242006349 4.02.109.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.531 MiB) 4.02.167.484 I slot launch_slot_: id 0 | task 18665 | processing task, is_child = 0 4.03.248.782 I slot print_timing: id 0 | task 18665 | prompt eval time = 134.01 ms / 303 tokens ( 0.44 ms per token, 2260.99 tokens per second) 4.03.248.788 I slot print_timing: id 0 | task 18665 | eval time = 947.26 ms / 91 tokens ( 10.53 ms per token, 95.01 tokens per second) 4.03.248.789 I slot print_timing: id 0 | task 18665 | total time = 1081.28 ms / 394 tokens 4.03.248.790 I slot print_timing: id 0 | task 18665 | graphs reused = 17724 4.03.248.791 I slot print_timing: id 0 | task 18665 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.248.821 I slot release: id 0 | task 18665 | stop processing: n_tokens = 425, truncated = 0 4.03.275.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 243148844 4.03.275.642 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.062 MiB) 4.03.333.320 I slot launch_slot_: id 0 | task 18759 | processing task, is_child = 0 4.03.938.076 I slot print_timing: id 0 | task 18759 | prompt eval time = 140.04 ms / 321 tokens ( 0.44 ms per token, 2292.23 tokens per second) 4.03.938.082 I slot print_timing: id 0 | task 18759 | eval time = 464.70 ms / 45 tokens ( 10.56 ms per token, 94.69 tokens per second) 4.03.938.083 I slot print_timing: id 0 | task 18759 | total time = 604.74 ms / 366 tokens 4.03.938.084 I slot print_timing: id 0 | task 18759 | graphs reused = 17767 4.03.938.085 I slot print_timing: id 0 | task 18759 | graph reallocs = 0 / 0 (same size) / (changed size) 4.03.938.111 I slot release: id 0 | task 18759 | stop processing: n_tokens = 397, truncated = 0 4.03.964.756 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 243838134 4.03.964.801 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.016 MiB) 4.04.019.326 I slot launch_slot_: id 0 | task 18807 | processing task, is_child = 0 4.04.290.576 I slot print_timing: id 0 | task 18807 | prompt eval time = 141.07 ms / 322 tokens ( 0.44 ms per token, 2282.60 tokens per second) 4.04.290.582 I slot print_timing: id 0 | task 18807 | eval time = 130.16 ms / 13 tokens ( 10.85 ms per token, 92.19 tokens per second) 4.04.290.583 I slot print_timing: id 0 | task 18807 | total time = 271.23 ms / 335 tokens 4.04.290.584 I slot print_timing: id 0 | task 18807 | graphs reused = 17778 4.04.290.585 I slot print_timing: id 0 | task 18807 | graph reallocs = 0 / 0 (same size) / (changed size) 4.04.290.612 I slot release: id 0 | task 18807 | stop processing: n_tokens = 366, truncated = 0 4.04.307.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 366, t_last = 244190635 4.04.307.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.357 MiB) 4.04.362.059 I slot launch_slot_: id 0 | task 18823 | processing task, is_child = 0 4.05.399.155 I slot print_timing: id 0 | task 18823 | prompt eval time = 140.79 ms / 323 tokens ( 0.44 ms per token, 2294.25 tokens per second) 4.05.399.160 I slot print_timing: id 0 | task 18823 | eval time = 896.29 ms / 86 tokens ( 10.54 ms per token, 94.84 tokens per second) 4.05.399.161 I slot print_timing: id 0 | task 18823 | total time = 1037.07 ms / 409 tokens 4.05.399.162 I slot print_timing: id 0 | task 18823 | graphs reused = 17862 4.05.399.163 I slot print_timing: id 0 | task 18823 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.399.194 I slot release: id 0 | task 18823 | stop processing: n_tokens = 440, truncated = 0 4.05.425.503 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 245299217 4.05.425.545 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 318.547 MiB) 4.05.479.878 I slot launch_slot_: id 0 | task 18912 | processing task, is_child = 0 4.08.622.289 I slot print_timing: id 0 | task 18912 | n_gen = 287, tg = 95.27 t/s, tg_3s = 95.60 t/s 4.09.637.400 I slot print_timing: id 0 | task 18912 | prompt eval time = 140.42 ms / 321 tokens ( 0.44 ms per token, 2286.03 tokens per second) 4.09.637.406 I slot print_timing: id 0 | task 18912 | eval time = 4017.08 ms / 383 tokens ( 10.52 ms per token, 95.09 tokens per second) 4.09.637.408 I slot print_timing: id 0 | task 18912 | total time = 4157.50 ms / 704 tokens 4.09.637.408 I slot print_timing: id 0 | task 18912 | graphs reused = 18242 4.09.637.409 I slot print_timing: id 0 | task 18912 | graph reallocs = 0 / 0 (same size) / (changed size) 4.09.637.439 I slot release: id 0 | task 18912 | stop processing: n_tokens = 735, truncated = 0 4.09.641.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 735, t_last = 249537462 4.09.641.760 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.982 MiB) 4.09.707.275 I slot launch_slot_: id 0 | task 19298 | processing task, is_child = 0 4.10.194.812 I slot print_timing: id 0 | task 19298 | prompt eval time = 144.77 ms / 322 tokens ( 0.45 ms per token, 2224.19 tokens per second) 4.10.194.818 I slot print_timing: id 0 | task 19298 | eval time = 342.74 ms / 33 tokens ( 10.71 ms per token, 93.36 tokens per second) 4.10.194.819 I slot print_timing: id 0 | task 19298 | total time = 487.51 ms / 355 tokens 4.10.194.820 I slot print_timing: id 0 | task 19298 | graphs reused = 18273 4.10.194.821 I slot print_timing: id 0 | task 19298 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.194.848 I slot release: id 0 | task 19298 | stop processing: n_tokens = 386, truncated = 0 4.10.198.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 386, t_last = 250094870 4.10.198.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 316.859 MiB) 4.10.259.386 I slot launch_slot_: id 0 | task 19334 | processing task, is_child = 0 4.10.882.935 I slot print_timing: id 0 | task 19334 | prompt eval time = 147.95 ms / 337 tokens ( 0.44 ms per token, 2277.78 tokens per second) 4.10.882.942 I slot print_timing: id 0 | task 19334 | eval time = 475.56 ms / 46 tokens ( 10.57 ms per token, 94.62 tokens per second) 4.10.882.943 I slot print_timing: id 0 | task 19334 | total time = 623.51 ms / 383 tokens 4.10.882.944 I slot print_timing: id 0 | task 19334 | graphs reused = 18317 4.10.882.944 I slot print_timing: id 0 | task 19334 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.882.974 I slot release: id 0 | task 19334 | stop processing: n_tokens = 414, truncated = 0 4.10.900.590 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 250782997 4.10.900.636 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.574 MiB) 4.10.954.296 I slot launch_slot_: id 0 | task 19383 | processing task, is_child = 0 4.11.581.900 I slot print_timing: id 0 | task 19383 | prompt eval time = 141.75 ms / 325 tokens ( 0.44 ms per token, 2292.72 tokens per second) 4.11.581.906 I slot print_timing: id 0 | task 19383 | eval time = 485.83 ms / 47 tokens ( 10.56 ms per token, 94.68 tokens per second) 4.11.581.907 I slot print_timing: id 0 | task 19383 | total time = 627.59 ms / 372 tokens 4.11.581.908 I slot print_timing: id 0 | task 19383 | graphs reused = 18362 4.11.581.908 I slot print_timing: id 0 | task 19383 | graph reallocs = 0 / 0 (same size) / (changed size) 4.11.581.937 I slot release: id 0 | task 19383 | stop processing: n_tokens = 403, truncated = 0 4.11.599.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 251481959 4.11.599.631 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.388 MiB) 4.11.653.793 I slot launch_slot_: id 0 | task 19433 | processing task, is_child = 0 4.12.939.991 I slot print_timing: id 0 | task 19433 | prompt eval time = 143.28 ms / 331 tokens ( 0.43 ms per token, 2310.18 tokens per second) 4.12.939.997 I slot print_timing: id 0 | task 19433 | eval time = 1142.90 ms / 110 tokens ( 10.49 ms per token, 95.37 tokens per second) 4.12.939.998 I slot print_timing: id 0 | task 19433 | total time = 1286.18 ms / 441 tokens 4.12.939.999 I slot print_timing: id 0 | task 19433 | graphs reused = 18470 4.12.940.000 I slot print_timing: id 0 | task 19433 | graph reallocs = 0 / 0 (same size) / (changed size) 4.12.940.027 I slot release: id 0 | task 19433 | stop processing: n_tokens = 472, truncated = 0 4.12.954.976 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 472, t_last = 252840050 4.12.955.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.513 MiB) 4.13.020.349 I slot launch_slot_: id 0 | task 19546 | processing task, is_child = 0 4.13.564.680 I slot print_timing: id 0 | task 19546 | prompt eval time = 142.75 ms / 336 tokens ( 0.42 ms per token, 2353.78 tokens per second) 4.13.564.685 I slot print_timing: id 0 | task 19546 | eval time = 401.56 ms / 39 tokens ( 10.57 ms per token, 94.63 tokens per second) 4.13.564.686 I slot print_timing: id 0 | task 19546 | total time = 544.31 ms / 375 tokens 4.13.564.687 I slot print_timing: id 0 | task 19546 | graphs reused = 18507 4.13.564.688 I slot print_timing: id 0 | task 19546 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.564.717 I slot release: id 0 | task 19546 | stop processing: n_tokens = 406, truncated = 0 4.13.593.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 253464740 4.13.593.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 312.512 MiB) 4.13.652.933 I slot launch_slot_: id 0 | task 19588 | processing task, is_child = 0 4.13.988.797 I slot print_timing: id 0 | task 19588 | prompt eval time = 143.32 ms / 349 tokens ( 0.41 ms per token, 2435.18 tokens per second) 4.13.988.802 I slot print_timing: id 0 | task 19588 | eval time = 192.53 ms / 19 tokens ( 10.70 ms per token, 93.49 tokens per second) 4.13.988.804 I slot print_timing: id 0 | task 19588 | total time = 335.85 ms / 368 tokens 4.13.988.804 I slot print_timing: id 0 | task 19588 | graphs reused = 18524 4.13.988.805 I slot print_timing: id 0 | task 19588 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.988.833 I slot release: id 0 | task 19588 | stop processing: n_tokens = 399, truncated = 0 4.14.016.508 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 399, t_last = 253888856 4.14.016.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 313.481 MiB) 4.14.086.755 I slot launch_slot_: id 0 | task 19610 | processing task, is_child = 0 4.17.233.364 I slot print_timing: id 0 | task 19610 | n_gen = 287, tg = 95.13 t/s, tg_3s = 95.47 t/s 4.20.235.202 I slot print_timing: id 0 | task 19610 | n_gen = 573, tg = 95.20 t/s, tg_3s = 95.27 t/s 4.23.040.942 I slot print_timing: id 0 | task 19610 | prompt eval time = 140.26 ms / 336 tokens ( 0.42 ms per token, 2395.52 tokens per second) 4.23.040.948 I slot print_timing: id 0 | task 19610 | eval time = 8813.91 ms / 840 tokens ( 10.51 ms per token, 95.19 tokens per second) 4.23.040.949 I slot print_timing: id 0 | task 19610 | total time = 8954.17 ms / 1176 tokens 4.23.040.950 I slot print_timing: id 0 | task 19610 | graphs reused = 19359 4.23.040.951 I slot print_timing: id 0 | task 19610 | graph reallocs = 0 / 0 (same size) / (changed size) 4.23.040.979 I slot release: id 0 | task 19610 | stop processing: n_tokens = 1207, truncated = 0 4.23.066.989 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1207, t_last = 262941002 4.23.067.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 315.952 MiB) 4.23.140.883 I slot launch_slot_: id 0 | task 20453 | processing task, is_child = 0 4.26.293.116 I slot print_timing: id 0 | task 20453 | n_gen = 288, tg = 95.38 t/s, tg_3s = 95.71 t/s 4.28.613.743 I slot print_timing: id 0 | task 20453 | prompt eval time = 143.26 ms / 349 tokens ( 0.41 ms per token, 2436.16 tokens per second) 4.28.613.749 I slot print_timing: id 0 | task 20453 | eval time = 5329.58 ms / 507 tokens ( 10.53 ms per token, 94.94 tokens per second) 4.28.613.750 I slot print_timing: id 0 | task 20453 | total time = 5472.84 ms / 856 tokens 4.28.613.750 I slot print_timing: id 0 | task 20453 | graphs reused = 19862 4.28.613.751 I slot print_timing: id 0 | task 20453 | graph reallocs = 0 / 0 (same size) / (changed size) 4.28.613.782 I slot release: id 0 | task 20453 | stop processing: n_tokens = 887, truncated = 0 4.28.640.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 887, t_last = 268513804 4.28.640.333 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.951 MiB) 4.28.703.886 I slot launch_slot_: id 0 | task 20963 | processing task, is_child = 0 4.29.335.415 I slot print_timing: id 0 | task 20963 | prompt eval time = 143.77 ms / 349 tokens ( 0.41 ms per token, 2427.56 tokens per second) 4.29.335.422 I slot print_timing: id 0 | task 20963 | eval time = 487.74 ms / 47 tokens ( 10.60 ms per token, 94.31 tokens per second) 4.29.335.423 I slot print_timing: id 0 | task 20963 | total time = 631.51 ms / 396 tokens 4.29.335.424 I slot print_timing: id 0 | task 20963 | graphs reused = 19907 4.29.335.425 I slot print_timing: id 0 | task 20963 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.335.460 I slot release: id 0 | task 20963 | stop processing: n_tokens = 427, truncated = 0 4.29.360.623 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 427, t_last = 269235483 4.29.360.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 314.294 MiB) 4.29.421.220 I slot launch_slot_: id 0 | task 21013 | processing task, is_child = 0 4.29.920.924 I slot print_timing: id 0 | task 21013 | prompt eval time = 150.10 ms / 385 tokens ( 0.39 ms per token, 2564.87 tokens per second) 4.29.920.931 I slot print_timing: id 0 | task 21013 | eval time = 349.58 ms / 34 tokens ( 10.59 ms per token, 94.40 tokens per second) 4.29.920.932 I slot print_timing: id 0 | task 21013 | total time = 499.68 ms / 419 tokens 4.29.920.934 I slot print_timing: id 0 | task 21013 | graphs reused = 19939 4.29.920.935 I slot print_timing: id 0 | task 21013 | graph reallocs = 0 / 0 (same size) / (changed size) 4.29.920.965 I slot release: id 0 | task 21013 | stop processing: n_tokens = 450, truncated = 0 4.29.938.118 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 269820988 4.29.938.165 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 321.612 MiB) 4.30.004.956 I slot launch_slot_: id 0 | task 21050 | processing task, is_child = 0 4.30.733.936 I slot print_timing: id 0 | task 21050 | prompt eval time = 139.77 ms / 328 tokens ( 0.43 ms per token, 2346.65 tokens per second) 4.30.733.941 I slot print_timing: id 0 | task 21050 | eval time = 589.19 ms / 57 tokens ( 10.52 ms per token, 95.05 tokens per second) 4.30.733.942 I slot print_timing: id 0 | task 21050 | total time = 728.96 ms / 385 tokens 4.30.733.944 I slot print_timing: id 0 | task 21050 | graphs reused = 19994 4.30.733.944 I slot print_timing: id 0 | task 21050 | graph reallocs = 0 / 0 (same size) / (changed size) 4.30.733.970 I slot release: id 0 | task 21050 | stop processing: n_tokens = 416, truncated = 0