$ /Users/minipro/quantdiff/llama.cpp/llama-b11770/llama-server -m /Users/minipro/quantdiff/models/campaign/2de73110cb25/Qwen3.8-27B-UD-Q5_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 0.00.044.633 I srv llama_server: initializing ... 0.00.044.639 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.045.170 I srv init_listene: The UI is disabled 0.00.045.171 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.045.218 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) 0.00.046.879 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/2de73110cb25/Qwen3.8-27B-UD-Q5_K_M.gguf' 0.00.556.101 W model has unused tensor blk.64.attn_norm.weight (size = 20480 bytes) -- ignoring 0.00.556.108 W model has unused tensor blk.64.post_attention_norm.weight (size = 20480 bytes) -- ignoring 0.00.556.115 W model has unused tensor blk.64.attn_q.weight (size = 51609600 bytes) -- ignoring 0.00.556.117 W model has unused tensor blk.64.attn_k.weight (size = 5570560 bytes) -- ignoring 0.00.556.120 W model has unused tensor blk.64.attn_v.weight (size = 5570560 bytes) -- ignoring 0.00.556.128 W model has unused tensor blk.64.attn_output.weight (size = 25804800 bytes) -- ignoring 0.00.556.130 W model has unused tensor blk.64.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.556.132 W model has unused tensor blk.64.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.556.134 W model has unused tensor blk.64.ffn_gate.weight (size = 73113600 bytes) -- ignoring 0.00.556.136 W model has unused tensor blk.64.ffn_down.weight (size = 73113600 bytes) -- ignoring 0.00.556.138 W model has unused tensor blk.64.ffn_up.weight (size = 73113600 bytes) -- ignoring 0.00.556.141 W model has unused tensor blk.64.nextn.eh_proj.weight (size = 43008000 bytes) -- ignoring 0.00.556.144 W model has unused tensor blk.64.nextn.enorm.weight (size = 20480 bytes) -- ignoring 0.00.556.146 W model has unused tensor blk.64.nextn.hnorm.weight (size = 20480 bytes) -- ignoring 0.00.556.153 W model has unused tensor blk.64.nextn.shared_head_norm.weight (size = 20480 bytes) -- ignoring 0.01.441.309 I cmn init: llama threadpool init, n_threads = 8 0.02.136.289 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.02.141.520 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.02.141.627 I srv llama_server: model loaded 0.02.141.632 I srv llama_server: listening on http://127.0.0.1:8089 0.04.033.829 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.04.034.321 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.08.245.875 I slot print_timing: id 0 | task 0 | prompt processing, n_tokens = 364, progress = 0.99, t = 4.21 s / 86.43 tokens per second 0.15.725.806 I slot print_timing: id 0 | task 0 | prompt eval time = 4875.33 ms / 368 tokens ( 13.25 ms per token, 75.48 tokens per second) 0.15.725.820 I slot print_timing: id 0 | task 0 | eval time = 6816.10 ms / 53 tokens ( 131.08 ms per token, 7.63 tokens per second) 0.15.725.823 I slot print_timing: id 0 | task 0 | total time = 11691.43 ms / 421 tokens 0.15.725.826 I slot print_timing: id 0 | task 0 | graphs reused = 52 0.15.725.828 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.15.725.936 I slot release: id 0 | task 0 | stop processing: n_tokens = 420, truncated = 0 0.15.735.702 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 99019477377 0.15.789.567 I slot launch_slot_: id 0 | task 56 | processing task, is_child = 0 0.19.568.372 I slot print_timing: id 0 | task 56 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.78 s / 84.15 tokens per second 0.25.542.251 I slot print_timing: id 0 | task 56 | prompt eval time = 4425.14 ms / 322 tokens ( 13.74 ms per token, 72.77 tokens per second) 0.25.542.263 I slot print_timing: id 0 | task 56 | eval time = 5327.50 ms / 42 tokens ( 129.94 ms per token, 7.70 tokens per second) 0.25.542.266 I slot print_timing: id 0 | task 56 | total time = 9752.64 ms / 364 tokens 0.25.542.268 I slot print_timing: id 0 | task 56 | graphs reused = 92 0.25.542.270 I slot print_timing: id 0 | task 56 | graph reallocs = 0 / 0 (same size) / (changed size) 0.25.542.375 I slot release: id 0 | task 56 | stop processing: n_tokens = 363, truncated = 0 0.25.553.720 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 99029293816 0.25.610.369 I slot launch_slot_: id 0 | task 101 | processing task, is_child = 0 0.29.793.664 I slot print_timing: id 0 | task 101 | prompt processing, n_tokens = 361, progress = 0.99, t = 4.18 s / 86.30 tokens per second 0.35.850.752 I slot print_timing: id 0 | task 101 | prompt eval time = 4848.96 ms / 365 tokens ( 13.28 ms per token, 75.27 tokens per second) 0.35.850.757 I slot print_timing: id 0 | task 101 | eval time = 5391.41 ms / 42 tokens ( 131.50 ms per token, 7.60 tokens per second) 0.35.850.758 I slot print_timing: id 0 | task 101 | total time = 10240.36 ms / 407 tokens 0.35.850.759 I slot print_timing: id 0 | task 101 | graphs reused = 132 0.35.850.760 I slot print_timing: id 0 | task 101 | graph reallocs = 0 / 0 (same size) / (changed size) 0.35.850.816 I slot release: id 0 | task 101 | stop processing: n_tokens = 406, truncated = 0 0.35.856.610 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 99039602257 0.35.895.046 I slot launch_slot_: id 0 | task 146 | processing task, is_child = 0 0.40.424.855 I slot print_timing: id 0 | task 146 | prompt processing, n_tokens = 393, progress = 0.99, t = 4.53 s / 86.76 tokens per second 0.46.615.292 I slot print_timing: id 0 | task 146 | prompt eval time = 5196.17 ms / 397 tokens ( 13.09 ms per token, 76.40 tokens per second) 0.46.615.298 I slot print_timing: id 0 | task 146 | eval time = 5524.06 ms / 43 tokens ( 131.53 ms per token, 7.60 tokens per second) 0.46.615.299 I slot print_timing: id 0 | task 146 | total time = 10720.23 ms / 440 tokens 0.46.615.300 I slot print_timing: id 0 | task 146 | graphs reused = 173 0.46.615.301 I slot print_timing: id 0 | task 146 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.615.364 I slot release: id 0 | task 146 | stop processing: n_tokens = 439, truncated = 0 0.46.628.012 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 0.46.687.291 I slot launch_slot_: id 0 | task 192 | processing task, is_child = 0 0.50.863.115 I slot print_timing: id 0 | task 192 | prompt processing, n_tokens = 379, progress = 0.99, t = 4.18 s / 90.76 tokens per second 0.58.725.751 I slot print_timing: id 0 | task 192 | prompt eval time = 5175.35 ms / 383 tokens ( 13.51 ms per token, 74.00 tokens per second) 0.58.725.767 I slot print_timing: id 0 | task 192 | eval time = 6863.05 ms / 55 tokens ( 127.09 ms per token, 7.87 tokens per second) 0.58.725.770 I slot print_timing: id 0 | task 192 | total time = 12038.40 ms / 438 tokens 0.58.725.772 I slot print_timing: id 0 | task 192 | graphs reused = 226 0.58.725.774 I slot print_timing: id 0 | task 192 | graph reallocs = 0 / 0 (same size) / (changed size) 0.58.725.892 I slot release: id 0 | task 192 | stop processing: n_tokens = 437, truncated = 0 0.58.738.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 99062477334 0.58.795.687 I slot launch_slot_: id 0 | task 250 | processing task, is_child = 0 1.02.983.898 I slot print_timing: id 0 | task 250 | prompt processing, n_tokens = 368, progress = 0.99, t = 4.19 s / 87.87 tokens per second 1.10.702.629 I slot print_timing: id 0 | task 250 | prompt eval time = 4835.71 ms / 372 tokens ( 13.00 ms per token, 76.93 tokens per second) 1.10.702.661 I slot print_timing: id 0 | task 250 | eval time = 7071.20 ms / 55 tokens ( 130.95 ms per token, 7.64 tokens per second) 1.10.702.670 I slot print_timing: id 0 | task 250 | total time = 11906.91 ms / 427 tokens 1.10.702.672 I slot print_timing: id 0 | task 250 | graphs reused = 279 1.10.702.674 I slot print_timing: id 0 | task 250 | graph reallocs = 0 / 0 (same size) / (changed size) 1.10.702.769 I slot release: id 0 | task 250 | stop processing: n_tokens = 426, truncated = 0 1.10.715.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 99074454211 1.10.775.102 I slot launch_slot_: id 0 | task 308 | processing task, is_child = 0 1.15.675.105 I slot print_timing: id 0 | task 308 | prompt processing, n_tokens = 418, progress = 0.99, t = 4.90 s / 85.31 tokens per second 1.23.077.631 I slot print_timing: id 0 | task 308 | prompt eval time = 5552.84 ms / 422 tokens ( 13.16 ms per token, 76.00 tokens per second) 1.23.077.656 I slot print_timing: id 0 | task 308 | eval time = 6749.65 ms / 55 tokens ( 124.99 ms per token, 8.00 tokens per second) 1.23.077.658 I slot print_timing: id 0 | task 308 | total time = 12302.49 ms / 477 tokens 1.23.077.660 I slot print_timing: id 0 | task 308 | graphs reused = 332 1.23.077.663 I slot print_timing: id 0 | task 308 | graph reallocs = 0 / 0 (same size) / (changed size) 1.23.077.817 I slot release: id 0 | task 308 | stop processing: n_tokens = 476, truncated = 0 1.23.090.611 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 99086829258 1.23.173.314 I slot launch_slot_: id 0 | task 366 | processing task, is_child = 0 1.28.462.187 I slot print_timing: id 0 | task 366 | prompt processing, n_tokens = 466, progress = 0.99, t = 5.29 s / 88.11 tokens per second 1.38.628.434 I slot print_timing: id 0 | task 366 | prompt eval time = 6287.00 ms / 470 tokens ( 13.38 ms per token, 74.76 tokens per second) 1.38.628.444 I slot print_timing: id 0 | task 366 | eval time = 9168.08 ms / 72 tokens ( 129.13 ms per token, 7.74 tokens per second) 1.38.628.446 I slot print_timing: id 0 | task 366 | total time = 15455.08 ms / 542 tokens 1.38.628.458 I slot print_timing: id 0 | task 366 | graphs reused = 401 1.38.628.461 I slot print_timing: id 0 | task 366 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.628.646 I slot release: id 0 | task 366 | stop processing: n_tokens = 541, truncated = 0 1.38.640.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 99102380087 1.38.762.807 I slot launch_slot_: id 0 | task 441 | processing task, is_child = 0 1.42.568.810 I slot print_timing: id 0 | task 441 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.81 s / 89.60 tokens per second 1.49.176.305 I slot print_timing: id 0 | task 441 | prompt eval time = 4458.59 ms / 345 tokens ( 12.92 ms per token, 77.38 tokens per second) 1.49.176.332 I slot print_timing: id 0 | task 441 | eval time = 5954.87 ms / 47 tokens ( 129.45 ms per token, 7.72 tokens per second) 1.49.176.334 I slot print_timing: id 0 | task 441 | total time = 10413.46 ms / 392 tokens 1.49.176.336 I slot print_timing: id 0 | task 441 | graphs reused = 446 1.49.176.338 I slot print_timing: id 0 | task 441 | graph reallocs = 0 / 0 (same size) / (changed size) 1.49.176.451 I slot release: id 0 | task 441 | stop processing: n_tokens = 391, truncated = 0 1.49.189.205 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 99112927892 1.49.301.897 I slot launch_slot_: id 0 | task 491 | processing task, is_child = 0 1.53.496.283 I slot print_timing: id 0 | task 491 | prompt processing, n_tokens = 360, progress = 0.99, t = 4.19 s / 85.83 tokens per second 1.59.742.709 I slot print_timing: id 0 | task 491 | prompt eval time = 5200.28 ms / 364 tokens ( 14.29 ms per token, 70.00 tokens per second) 1.59.742.729 I slot print_timing: id 0 | task 491 | eval time = 5240.44 ms / 41 tokens ( 131.01 ms per token, 7.63 tokens per second) 1.59.742.733 I slot print_timing: id 0 | task 491 | total time = 10440.72 ms / 405 tokens 1.59.742.738 I slot print_timing: id 0 | task 491 | graphs reused = 485 1.59.742.740 I slot print_timing: id 0 | task 491 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.742.866 I slot release: id 0 | task 491 | stop processing: n_tokens = 404, truncated = 0 1.59.752.709 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 99123494307 1.59.829.150 I slot launch_slot_: id 0 | task 535 | processing task, is_child = 0 2.04.013.496 I slot print_timing: id 0 | task 535 | prompt processing, n_tokens = 372, progress = 0.99, t = 4.18 s / 88.90 tokens per second 2.12.704.204 I slot print_timing: id 0 | task 535 | prompt eval time = 4844.67 ms / 376 tokens ( 12.88 ms per token, 77.61 tokens per second) 2.12.704.215 I slot print_timing: id 0 | task 535 | eval time = 8030.34 ms / 62 tokens ( 131.64 ms per token, 7.60 tokens per second) 2.12.704.218 I slot print_timing: id 0 | task 535 | total time = 12875.01 ms / 438 tokens 2.12.704.221 I slot print_timing: id 0 | task 535 | graphs reused = 545 2.12.704.223 I slot print_timing: id 0 | task 535 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.704.354 I slot release: id 0 | task 535 | stop processing: n_tokens = 437, truncated = 0 2.12.716.675 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 99136455796 2.12.798.974 I slot launch_slot_: id 0 | task 600 | processing task, is_child = 0 2.17.366.809 I slot print_timing: id 0 | task 600 | prompt processing, n_tokens = 408, progress = 0.99, t = 4.57 s / 89.32 tokens per second 2.24.076.621 I slot print_timing: id 0 | task 600 | prompt eval time = 5234.97 ms / 412 tokens ( 12.71 ms per token, 78.70 tokens per second) 2.24.076.701 I slot print_timing: id 0 | task 600 | eval time = 6042.64 ms / 47 tokens ( 131.36 ms per token, 7.61 tokens per second) 2.24.076.703 I slot print_timing: id 0 | task 600 | total time = 11277.61 ms / 459 tokens 2.24.076.705 I slot print_timing: id 0 | task 600 | graphs reused = 590 2.24.076.707 I slot print_timing: id 0 | task 600 | graph reallocs = 0 / 0 (same size) / (changed size) 2.24.076.844 I slot release: id 0 | task 600 | stop processing: n_tokens = 458, truncated = 0 2.24.090.238 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 99147828285 2.24.167.625 I slot launch_slot_: id 0 | task 650 | processing task, is_child = 0 2.28.368.866 I slot print_timing: id 0 | task 650 | prompt processing, n_tokens = 372, progress = 0.99, t = 4.20 s / 88.55 tokens per second 2.37.401.513 I slot print_timing: id 0 | task 650 | prompt eval time = 5214.94 ms / 376 tokens ( 13.87 ms per token, 72.10 tokens per second) 2.37.401.524 I slot print_timing: id 0 | task 650 | eval time = 8018.91 ms / 62 tokens ( 131.46 ms per token, 7.61 tokens per second) 2.37.401.527 I slot print_timing: id 0 | task 650 | total time = 13233.85 ms / 438 tokens 2.37.401.529 I slot print_timing: id 0 | task 650 | graphs reused = 650 2.37.401.531 I slot print_timing: id 0 | task 650 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.401.648 I slot release: id 0 | task 650 | stop processing: n_tokens = 437, truncated = 0 2.37.414.199 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 99161153089 2.37.494.957 I slot launch_slot_: id 0 | task 715 | processing task, is_child = 0 2.41.708.665 I slot print_timing: id 0 | task 715 | prompt processing, n_tokens = 374, progress = 0.99, t = 4.21 s / 88.76 tokens per second 2.49.094.930 I slot print_timing: id 0 | task 715 | prompt eval time = 4875.52 ms / 378 tokens ( 12.90 ms per token, 77.53 tokens per second) 2.49.094.940 I slot print_timing: id 0 | task 715 | eval time = 6724.41 ms / 52 tokens ( 131.85 ms per token, 7.58 tokens per second) 2.49.094.943 I slot print_timing: id 0 | task 715 | total time = 11599.94 ms / 430 tokens 2.49.094.945 I slot print_timing: id 0 | task 715 | graphs reused = 700 2.49.094.947 I slot print_timing: id 0 | task 715 | graph reallocs = 0 / 0 (same size) / (changed size) 2.49.095.097 I slot release: id 0 | task 715 | stop processing: n_tokens = 429, truncated = 0 2.49.108.926 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 99172846538 2.49.187.441 I slot launch_slot_: id 0 | task 770 | processing task, is_child = 0 2.53.379.790 I slot print_timing: id 0 | task 770 | prompt processing, n_tokens = 363, progress = 0.99, t = 4.19 s / 86.59 tokens per second 3.01.547.919 I slot print_timing: id 0 | task 770 | prompt eval time = 4840.79 ms / 367 tokens ( 13.19 ms per token, 75.81 tokens per second) 3.01.547.925 I slot print_timing: id 0 | task 770 | eval time = 7519.66 ms / 58 tokens ( 131.92 ms per token, 7.58 tokens per second) 3.01.547.926 I slot print_timing: id 0 | task 770 | total time = 12360.45 ms / 425 tokens 3.01.547.928 I slot print_timing: id 0 | task 770 | graphs reused = 756 3.01.547.929 I slot print_timing: id 0 | task 770 | graph reallocs = 0 / 0 (same size) / (changed size) 3.01.548.002 I slot release: id 0 | task 770 | stop processing: n_tokens = 424, truncated = 0 3.01.559.117 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 99185299443 3.01.695.740 I slot launch_slot_: id 0 | task 831 | processing task, is_child = 0 3.05.503.664 I slot print_timing: id 0 | task 831 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.81 s / 90.08 tokens per second 3.12.362.165 I slot print_timing: id 0 | task 831 | prompt eval time = 4460.66 ms / 347 tokens ( 12.85 ms per token, 77.79 tokens per second) 3.12.362.169 I slot print_timing: id 0 | task 831 | eval time = 6205.74 ms / 51 tokens ( 124.11 ms per token, 8.06 tokens per second) 3.12.362.170 I slot print_timing: id 0 | task 831 | total time = 10666.40 ms / 398 tokens 3.12.362.170 I slot print_timing: id 0 | task 831 | graphs reused = 805 3.12.362.171 I slot print_timing: id 0 | task 831 | graph reallocs = 0 / 0 (same size) / (changed size) 3.12.362.269 I slot release: id 0 | task 831 | stop processing: n_tokens = 397, truncated = 0 3.12.366.936 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 99196113711 3.12.626.436 I slot launch_slot_: id 0 | task 885 | processing task, is_child = 0 3.16.831.416 I slot print_timing: id 0 | task 885 | prompt processing, n_tokens = 365, progress = 0.99, t = 4.20 s / 86.80 tokens per second 3.22.778.685 I slot print_timing: id 0 | task 885 | prompt eval time = 4873.69 ms / 369 tokens ( 13.21 ms per token, 75.71 tokens per second) 3.22.778.701 I slot print_timing: id 0 | task 885 | eval time = 5278.52 ms / 41 tokens ( 131.96 ms per token, 7.58 tokens per second) 3.22.778.704 I slot print_timing: id 0 | task 885 | total time = 10152.21 ms / 410 tokens 3.22.778.707 I slot print_timing: id 0 | task 885 | graphs reused = 844 3.22.778.709 I slot print_timing: id 0 | task 885 | graph reallocs = 0 / 0 (same size) / (changed size) 3.22.779.843 I slot release: id 0 | task 885 | stop processing: n_tokens = 409, truncated = 0 3.22.802.425 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 99206531288 3.22.906.813 I slot launch_slot_: id 0 | task 929 | processing task, is_child = 0 3.27.081.557 I slot print_timing: id 0 | task 929 | prompt processing, n_tokens = 348, progress = 0.99, t = 4.17 s / 83.36 tokens per second 3.32.944.173 I slot print_timing: id 0 | task 929 | prompt eval time = 4821.88 ms / 352 tokens ( 13.70 ms per token, 73.00 tokens per second) 3.32.944.188 I slot print_timing: id 0 | task 929 | eval time = 5215.43 ms / 41 tokens ( 130.39 ms per token, 7.67 tokens per second) 3.32.944.190 I slot print_timing: id 0 | task 929 | total time = 10037.32 ms / 393 tokens 3.32.944.193 I slot print_timing: id 0 | task 929 | graphs reused = 883 3.32.944.195 I slot print_timing: id 0 | task 929 | graph reallocs = 0 / 0 (same size) / (changed size) 3.32.944.642 I slot release: id 0 | task 929 | stop processing: n_tokens = 392, truncated = 0 3.32.957.549 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 99216696083 3.32.957.614 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.138 MiB) 3.33.096.323 I slot launch_slot_: id 0 | task 973 | processing task, is_child = 0 3.37.267.417 I slot print_timing: id 0 | task 973 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.17 s / 82.71 tokens per second 3.43.010.064 I slot print_timing: id 0 | task 973 | prompt eval time = 4817.99 ms / 349 tokens ( 13.81 ms per token, 72.44 tokens per second) 3.43.010.116 I slot print_timing: id 0 | task 973 | eval time = 5095.71 ms / 40 tokens ( 130.66 ms per token, 7.65 tokens per second) 3.43.010.128 I slot print_timing: id 0 | task 973 | total time = 9913.70 ms / 389 tokens 3.43.010.130 I slot print_timing: id 0 | task 973 | graphs reused = 921 3.43.010.132 I slot print_timing: id 0 | task 973 | graph reallocs = 0 / 0 (same size) / (changed size) 3.43.010.369 I slot release: id 0 | task 973 | stop processing: n_tokens = 388, truncated = 0 3.43.023.911 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 99226761811 3.43.023.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 471.575 MiB) 3.43.187.228 I slot launch_slot_: id 0 | task 1016 | processing task, is_child = 0 3.47.398.766 I slot print_timing: id 0 | task 1016 | prompt processing, n_tokens = 380, progress = 0.99, t = 4.21 s / 90.23 tokens per second 3.56.613.558 I slot print_timing: id 0 | task 1016 | prompt eval time = 5222.72 ms / 384 tokens ( 13.60 ms per token, 73.52 tokens per second) 3.56.613.568 I slot print_timing: id 0 | task 1016 | eval time = 8203.56 ms / 63 tokens ( 132.32 ms per token, 7.56 tokens per second) 3.56.613.571 I slot print_timing: id 0 | task 1016 | total time = 13426.28 ms / 447 tokens 3.56.613.585 I slot print_timing: id 0 | task 1016 | graphs reused = 982 3.56.613.587 I slot print_timing: id 0 | task 1016 | graph reallocs = 0 / 0 (same size) / (changed size) 3.56.613.953 I slot release: id 0 | task 1016 | stop processing: n_tokens = 446, truncated = 0 3.56.625.934 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 99240365395 3.56.626.043 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.263 MiB) 3.56.803.225 I slot launch_slot_: id 0 | task 1082 | processing task, is_child = 0 4.00.602.312 I slot print_timing: id 0 | task 1082 | prompt processing, n_tokens = 352, progress = 0.99, t = 3.80 s / 92.65 tokens per second 4.08.010.769 I slot print_timing: id 0 | task 1082 | prompt eval time = 4451.12 ms / 356 tokens ( 12.50 ms per token, 79.98 tokens per second) 4.08.010.780 I slot print_timing: id 0 | task 1082 | eval time = 6756.38 ms / 54 tokens ( 127.48 ms per token, 7.84 tokens per second) 4.08.010.782 I slot print_timing: id 0 | task 1082 | total time = 11207.50 ms / 410 tokens 4.08.010.784 I slot print_timing: id 0 | task 1082 | graphs reused = 1034 4.08.010.786 I slot print_timing: id 0 | task 1082 | graph reallocs = 0 / 0 (same size) / (changed size) 4.08.011.096 I slot release: id 0 | task 1082 | stop processing: n_tokens = 409, truncated = 0 4.08.023.692 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 99251762537 4.08.023.765 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.326 MiB) 4.08.171.209 I slot launch_slot_: id 0 | task 1139 | processing task, is_child = 0 4.12.710.118 I slot print_timing: id 0 | task 1139 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.54 s / 89.45 tokens per second 4.22.254.191 I slot print_timing: id 0 | task 1139 | prompt eval time = 5533.14 ms / 410 tokens ( 13.50 ms per token, 74.10 tokens per second) 4.22.254.205 I slot print_timing: id 0 | task 1139 | eval time = 8549.82 ms / 70 tokens ( 123.91 ms per token, 8.07 tokens per second) 4.22.254.207 I slot print_timing: id 0 | task 1139 | total time = 14082.95 ms / 480 tokens 4.22.254.209 I slot print_timing: id 0 | task 1139 | graphs reused = 1102 4.22.254.210 I slot print_timing: id 0 | task 1139 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.254.357 I slot release: id 0 | task 1139 | stop processing: n_tokens = 479, truncated = 0 4.22.266.052 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 99266005798 4.22.266.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 4.22.437.581 I slot launch_slot_: id 0 | task 1212 | processing task, is_child = 0 4.26.965.111 I slot print_timing: id 0 | task 1212 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.53 s / 84.15 tokens per second 4.34.968.143 I slot print_timing: id 0 | task 1212 | prompt eval time = 5178.47 ms / 385 tokens ( 13.45 ms per token, 74.35 tokens per second) 4.34.968.156 I slot print_timing: id 0 | task 1212 | eval time = 7352.06 ms / 58 tokens ( 128.98 ms per token, 7.75 tokens per second) 4.34.968.159 I slot print_timing: id 0 | task 1212 | total time = 12530.53 ms / 443 tokens 4.34.968.161 I slot print_timing: id 0 | task 1212 | graphs reused = 1158 4.34.968.163 I slot print_timing: id 0 | task 1212 | graph reallocs = 0 / 0 (same size) / (changed size) 4.34.968.407 I slot release: id 0 | task 1212 | stop processing: n_tokens = 442, truncated = 0 4.34.981.666 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 99278719849 4.34.981.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.514 MiB) 4.35.137.812 I slot launch_slot_: id 0 | task 1273 | processing task, is_child = 0 4.39.345.140 I slot print_timing: id 0 | task 1273 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.21 s / 92.93 tokens per second 4.49.510.429 I slot print_timing: id 0 | task 1273 | prompt eval time = 5209.26 ms / 395 tokens ( 13.19 ms per token, 75.83 tokens per second) 4.49.510.439 I slot print_timing: id 0 | task 1273 | eval time = 9163.32 ms / 71 tokens ( 130.90 ms per token, 7.64 tokens per second) 4.49.510.443 I slot print_timing: id 0 | task 1273 | total time = 14372.58 ms / 466 tokens 4.49.510.445 I slot print_timing: id 0 | task 1273 | graphs reused = 1227 4.49.510.447 I slot print_timing: id 0 | task 1273 | graph reallocs = 0 / 0 (same size) / (changed size) 4.49.510.942 I slot release: id 0 | task 1273 | stop processing: n_tokens = 465, truncated = 0 4.49.527.100 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 99293262383 4.49.527.173 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.640 MiB) 4.50.829.430 I slot launch_slot_: id 0 | task 1347 | processing task, is_child = 0 4.55.401.609 I slot print_timing: id 0 | task 1347 | prompt processing, n_tokens = 426, progress = 0.99, t = 4.57 s / 93.17 tokens per second 5.04.382.778 I slot print_timing: id 0 | task 1347 | prompt eval time = 5572.81 ms / 430 tokens ( 12.96 ms per token, 77.16 tokens per second) 5.04.382.791 I slot print_timing: id 0 | task 1347 | eval time = 7980.49 ms / 62 tokens ( 130.83 ms per token, 7.64 tokens per second) 5.04.382.795 I slot print_timing: id 0 | task 1347 | total time = 13553.31 ms / 492 tokens 5.04.382.798 I slot print_timing: id 0 | task 1347 | graphs reused = 1287 5.04.382.799 I slot print_timing: id 0 | task 1347 | graph reallocs = 0 / 0 (same size) / (changed size) 5.04.383.288 I slot release: id 0 | task 1347 | stop processing: n_tokens = 491, truncated = 0 5.04.396.334 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 99308134730 5.04.396.410 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 482.704 MiB) 5.05.086.480 I slot launch_slot_: id 0 | task 1412 | processing task, is_child = 0 5.09.281.269 I slot print_timing: id 0 | task 1412 | prompt processing, n_tokens = 388, progress = 0.99, t = 4.19 s / 92.50 tokens per second 5.18.130.171 I slot print_timing: id 0 | task 1412 | prompt eval time = 5197.23 ms / 392 tokens ( 13.26 ms per token, 75.42 tokens per second) 5.18.130.194 I slot print_timing: id 0 | task 1412 | eval time = 7846.41 ms / 62 tokens ( 128.63 ms per token, 7.77 tokens per second) 5.18.130.197 I slot print_timing: id 0 | task 1412 | total time = 13043.64 ms / 454 tokens 5.18.130.199 I slot print_timing: id 0 | task 1412 | graphs reused = 1347 5.18.130.201 I slot print_timing: id 0 | task 1412 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.130.484 I slot release: id 0 | task 1412 | stop processing: n_tokens = 453, truncated = 0 5.18.144.723 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 99321881926 5.18.144.794 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.325 MiB) 5.18.280.579 I slot launch_slot_: id 0 | task 1477 | processing task, is_child = 0 5.22.450.360 I slot print_timing: id 0 | task 1477 | prompt processing, n_tokens = 346, progress = 0.99, t = 4.17 s / 82.98 tokens per second 5.29.042.358 I slot print_timing: id 0 | task 1477 | prompt eval time = 4814.33 ms / 350 tokens ( 13.76 ms per token, 72.70 tokens per second) 5.29.042.364 I slot print_timing: id 0 | task 1477 | eval time = 5947.43 ms / 49 tokens ( 123.90 ms per token, 8.07 tokens per second) 5.29.042.364 I slot print_timing: id 0 | task 1477 | total time = 10761.76 ms / 399 tokens 5.29.042.365 I slot print_timing: id 0 | task 1477 | graphs reused = 1394 5.29.042.365 I slot print_timing: id 0 | task 1477 | graph reallocs = 0 / 0 (same size) / (changed size) 5.29.042.410 I slot release: id 0 | task 1477 | stop processing: n_tokens = 398, truncated = 0 5.29.047.819 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 99332793851 5.29.047.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.138 MiB) 5.29.134.775 I slot launch_slot_: id 0 | task 1529 | processing task, is_child = 0 5.33.326.757 I slot print_timing: id 0 | task 1529 | prompt processing, n_tokens = 376, progress = 0.99, t = 4.19 s / 89.70 tokens per second 5.41.845.091 I slot print_timing: id 0 | task 1529 | prompt eval time = 4843.25 ms / 380 tokens ( 12.75 ms per token, 78.46 tokens per second) 5.41.845.110 I slot print_timing: id 0 | task 1529 | eval time = 7867.04 ms / 61 tokens ( 131.12 ms per token, 7.63 tokens per second) 5.41.845.113 I slot print_timing: id 0 | task 1529 | total time = 12710.29 ms / 441 tokens 5.41.845.115 I slot print_timing: id 0 | task 1529 | graphs reused = 1453 5.41.845.117 I slot print_timing: id 0 | task 1529 | graph reallocs = 0 / 0 (same size) / (changed size) 5.41.845.383 I slot release: id 0 | task 1529 | stop processing: n_tokens = 440, truncated = 0 5.41.858.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 99345596825 5.41.858.977 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 5.42.036.238 I slot launch_slot_: id 0 | task 1593 | processing task, is_child = 0 5.46.551.633 I slot print_timing: id 0 | task 1593 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.52 s / 89.91 tokens per second 5.57.920.760 I slot print_timing: id 0 | task 1593 | prompt eval time = 5520.60 ms / 410 tokens ( 13.46 ms per token, 74.27 tokens per second) 5.57.920.775 I slot print_timing: id 0 | task 1593 | eval time = 10363.89 ms / 80 tokens ( 131.19 ms per token, 7.62 tokens per second) 5.57.920.777 I slot print_timing: id 0 | task 1593 | total time = 15884.49 ms / 490 tokens 5.57.920.780 I slot print_timing: id 0 | task 1593 | graphs reused = 1531 5.57.920.782 I slot print_timing: id 0 | task 1593 | graph reallocs = 0 / 0 (same size) / (changed size) 5.57.921.037 I slot release: id 0 | task 1593 | stop processing: n_tokens = 489, truncated = 0 5.57.933.368 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 99361672478 5.57.933.441 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.514 MiB) 5.58.433.380 I slot launch_slot_: id 0 | task 1676 | processing task, is_child = 0 6.02.971.400 I slot print_timing: id 0 | task 1676 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.54 s / 84.40 tokens per second 6.12.429.873 I slot print_timing: id 0 | task 1676 | prompt eval time = 5203.62 ms / 387 tokens ( 13.45 ms per token, 74.37 tokens per second) 6.12.429.883 I slot print_timing: id 0 | task 1676 | eval time = 8792.84 ms / 68 tokens ( 131.24 ms per token, 7.62 tokens per second) 6.12.429.886 I slot print_timing: id 0 | task 1676 | total time = 13996.46 ms / 455 tokens 6.12.429.889 I slot print_timing: id 0 | task 1676 | graphs reused = 1597 6.12.429.892 I slot print_timing: id 0 | task 1676 | graph reallocs = 0 / 0 (same size) / (changed size) 6.12.430.089 I slot release: id 0 | task 1676 | stop processing: n_tokens = 454, truncated = 0 6.12.444.016 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 99376181531 6.12.444.096 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.201 MiB) 6.13.054.753 I slot launch_slot_: id 0 | task 1747 | processing task, is_child = 0 6.17.239.545 I slot print_timing: id 0 | task 1747 | prompt processing, n_tokens = 354, progress = 0.99, t = 4.18 s / 84.59 tokens per second 6.25.361.098 I slot print_timing: id 0 | task 1747 | prompt eval time = 4831.27 ms / 358 tokens ( 13.50 ms per token, 74.10 tokens per second) 6.25.361.113 I slot print_timing: id 0 | task 1747 | eval time = 7475.04 ms / 59 tokens ( 128.88 ms per token, 7.76 tokens per second) 6.25.361.116 I slot print_timing: id 0 | task 1747 | total time = 12306.31 ms / 417 tokens 6.25.361.118 I slot print_timing: id 0 | task 1747 | graphs reused = 1654 6.25.361.120 I slot print_timing: id 0 | task 1747 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.361.371 I slot release: id 0 | task 1747 | stop processing: n_tokens = 416, truncated = 0 6.25.374.235 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 99389112813 6.25.374.304 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.701 MiB) 6.25.964.968 I slot launch_slot_: id 0 | task 1809 | processing task, is_child = 0 6.30.144.969 I slot print_timing: id 0 | task 1809 | prompt processing, n_tokens = 355, progress = 0.99, t = 4.18 s / 84.93 tokens per second 6.37.702.889 I slot print_timing: id 0 | task 1809 | prompt eval time = 4825.32 ms / 359 tokens ( 13.44 ms per token, 74.40 tokens per second) 6.37.702.901 I slot print_timing: id 0 | task 1809 | eval time = 6912.55 ms / 56 tokens ( 125.68 ms per token, 7.96 tokens per second) 6.37.702.904 I slot print_timing: id 0 | task 1809 | total time = 11737.87 ms / 415 tokens 6.37.702.906 I slot print_timing: id 0 | task 1809 | graphs reused = 1708 6.37.702.909 I slot print_timing: id 0 | task 1809 | graph reallocs = 0 / 0 (same size) / (changed size) 6.37.703.145 I slot release: id 0 | task 1809 | stop processing: n_tokens = 414, truncated = 0 6.37.716.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 99401454587 6.37.716.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 475.388 MiB) 6.38.368.171 I slot launch_slot_: id 0 | task 1868 | processing task, is_child = 0 6.42.903.227 I slot print_timing: id 0 | task 1868 | prompt processing, n_tokens = 383, progress = 0.99, t = 4.54 s / 84.45 tokens per second 6.51.403.664 I slot print_timing: id 0 | task 1868 | prompt eval time = 5180.76 ms / 387 tokens ( 13.39 ms per token, 74.70 tokens per second) 6.51.403.678 I slot print_timing: id 0 | task 1868 | eval time = 7854.70 ms / 61 tokens ( 130.91 ms per token, 7.64 tokens per second) 6.51.403.681 I slot print_timing: id 0 | task 1868 | total time = 13035.45 ms / 448 tokens 6.51.403.683 I slot print_timing: id 0 | task 1868 | graphs reused = 1767 6.51.403.686 I slot print_timing: id 0 | task 1868 | graph reallocs = 0 / 0 (same size) / (changed size) 6.51.404.124 I slot release: id 0 | task 1868 | stop processing: n_tokens = 447, truncated = 0 6.51.420.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 99415155565 6.51.420.719 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.700 MiB) 6.51.581.925 I slot launch_slot_: id 0 | task 1932 | processing task, is_child = 0 6.56.118.646 I slot print_timing: id 0 | task 1932 | prompt processing, n_tokens = 406, progress = 0.99, t = 4.54 s / 89.49 tokens per second 7.04.494.262 I slot print_timing: id 0 | task 1932 | prompt eval time = 5187.80 ms / 410 tokens ( 12.65 ms per token, 79.03 tokens per second) 7.04.494.273 I slot print_timing: id 0 | task 1932 | eval time = 7724.50 ms / 61 tokens ( 128.74 ms per token, 7.77 tokens per second) 7.04.494.277 I slot print_timing: id 0 | task 1932 | total time = 12912.30 ms / 471 tokens 7.04.494.279 I slot print_timing: id 0 | task 1932 | graphs reused = 1826 7.04.494.282 I slot print_timing: id 0 | task 1932 | graph reallocs = 0 / 0 (same size) / (changed size) 7.04.496.214 I slot release: id 0 | task 1932 | stop processing: n_tokens = 470, truncated = 0 7.04.515.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 99428247659 7.04.515.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 7.04.635.182 I slot launch_slot_: id 0 | task 1996 | processing task, is_child = 0 7.08.818.518 I slot print_timing: id 0 | task 1996 | prompt processing, n_tokens = 347, progress = 0.99, t = 4.18 s / 82.95 tokens per second 7.15.626.439 I slot print_timing: id 0 | task 1996 | prompt eval time = 4828.08 ms / 351 tokens ( 13.76 ms per token, 72.70 tokens per second) 7.15.626.456 I slot print_timing: id 0 | task 1996 | eval time = 6163.12 ms / 50 tokens ( 125.78 ms per token, 7.95 tokens per second) 7.15.626.458 I slot print_timing: id 0 | task 1996 | total time = 10991.21 ms / 401 tokens 7.15.626.461 I slot print_timing: id 0 | task 1996 | graphs reused = 1874 7.15.626.463 I slot print_timing: id 0 | task 1996 | graph reallocs = 0 / 0 (same size) / (changed size) 7.15.628.263 I slot release: id 0 | task 1996 | stop processing: n_tokens = 400, truncated = 0 7.15.648.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 99439379709 7.15.648.945 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.388 MiB) 7.15.778.239 I slot launch_slot_: id 0 | task 2049 | processing task, is_child = 0 7.20.311.775 I slot print_timing: id 0 | task 2049 | prompt processing, n_tokens = 389, progress = 0.99, t = 4.53 s / 85.81 tokens per second 7.33.649.639 I slot print_timing: id 0 | task 2049 | n_gen = 100, tg = 7.80 t/s, tg_3s = 7.88 t/s 7.36.678.837 I slot print_timing: id 0 | task 2049 | n_gen = 123, tg = 7.76 t/s, tg_3s = 7.59 t/s 7.39.685.788 I slot print_timing: id 0 | task 2049 | n_gen = 146, tg = 7.74 t/s, tg_3s = 7.65 t/s 7.42.706.307 I slot print_timing: id 0 | task 2049 | n_gen = 169, tg = 7.72 t/s, tg_3s = 7.61 t/s 7.45.731.084 I slot print_timing: id 0 | task 2049 | n_gen = 192, tg = 7.71 t/s, tg_3s = 7.60 t/s 7.48.758.230 I slot print_timing: id 0 | task 2049 | n_gen = 215, tg = 7.70 t/s, tg_3s = 7.60 t/s 7.49.943.113 I slot print_timing: id 0 | task 2049 | prompt eval time = 5180.31 ms / 393 tokens ( 13.18 ms per token, 75.86 tokens per second) 7.49.943.128 I slot print_timing: id 0 | task 2049 | eval time = 28984.51 ms / 224 tokens ( 129.98 ms per token, 7.69 tokens per second) 7.49.943.130 I slot print_timing: id 0 | task 2049 | total time = 34164.83 ms / 617 tokens 7.49.943.133 I slot print_timing: id 0 | task 2049 | graphs reused = 2095 7.49.943.135 I slot print_timing: id 0 | task 2049 | graph reallocs = 0 / 0 (same size) / (changed size) 7.49.943.511 I slot release: id 0 | task 2049 | stop processing: n_tokens = 616, truncated = 0 7.49.960.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 99473694952 7.49.960.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.138 MiB) 7.50.108.611 I slot launch_slot_: id 0 | task 2276 | processing task, is_child = 0 7.53.908.169 I slot print_timing: id 0 | task 2276 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.80 s / 83.43 tokens per second 7.58.589.244 I slot print_timing: id 0 | task 2276 | prompt eval time = 4446.95 ms / 321 tokens ( 13.85 ms per token, 72.18 tokens per second) 7.58.589.259 I slot print_timing: id 0 | task 2276 | eval time = 4033.64 ms / 32 tokens ( 130.12 ms per token, 7.69 tokens per second) 7.58.589.262 I slot print_timing: id 0 | task 2276 | total time = 8480.59 ms / 353 tokens 7.58.589.264 I slot print_timing: id 0 | task 2276 | graphs reused = 2125 7.58.589.266 I slot print_timing: id 0 | task 2276 | graph reallocs = 0 / 0 (same size) / (changed size) 7.58.589.371 I slot release: id 0 | task 2276 | stop processing: n_tokens = 352, truncated = 0 7.58.605.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 99482340812 7.58.605.368 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.764 MiB) 7.58.736.693 I slot launch_slot_: id 0 | task 2311 | processing task, is_child = 0 8.02.562.936 I slot print_timing: id 0 | task 2311 | prompt processing, n_tokens = 326, progress = 0.99, t = 3.83 s / 85.20 tokens per second 8.12.818.605 I slot print_timing: id 0 | task 2311 | prompt eval time = 4487.67 ms / 330 tokens ( 13.60 ms per token, 73.53 tokens per second) 8.12.818.617 I slot print_timing: id 0 | task 2311 | eval time = 9594.17 ms / 74 tokens ( 131.43 ms per token, 7.61 tokens per second) 8.12.818.620 I slot print_timing: id 0 | task 2311 | total time = 14081.84 ms / 404 tokens 8.12.818.623 I slot print_timing: id 0 | task 2311 | graphs reused = 2197 8.12.818.626 I slot print_timing: id 0 | task 2311 | graph reallocs = 0 / 0 (same size) / (changed size) 8.12.818.735 I slot release: id 0 | task 2311 | stop processing: n_tokens = 403, truncated = 0 8.12.834.261 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 99496570176 8.12.834.330 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.451 MiB) 8.12.984.272 I slot launch_slot_: id 0 | task 2388 | processing task, is_child = 0 8.16.795.074 I slot print_timing: id 0 | task 2388 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.81 s / 88.43 tokens per second 8.21.284.711 I slot print_timing: id 0 | task 2388 | prompt eval time = 4457.56 ms / 341 tokens ( 13.07 ms per token, 76.50 tokens per second) 8.21.284.714 I slot print_timing: id 0 | task 2388 | eval time = 3842.86 ms / 32 tokens ( 123.96 ms per token, 8.07 tokens per second) 8.21.284.715 I slot print_timing: id 0 | task 2388 | total time = 8300.42 ms / 373 tokens 8.21.284.715 I slot print_timing: id 0 | task 2388 | graphs reused = 2227 8.21.284.716 I slot print_timing: id 0 | task 2388 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.286.032 I slot release: id 0 | task 2388 | stop processing: n_tokens = 372, truncated = 0 8.21.292.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 99505037474 8.21.292.802 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.827 MiB) 8.21.384.889 I slot launch_slot_: id 0 | task 2423 | processing task, is_child = 0 8.25.508.115 I slot print_timing: id 0 | task 2423 | prompt processing, n_tokens = 334, progress = 0.99, t = 4.12 s / 81.01 tokens per second 8.31.950.005 I slot print_timing: id 0 | task 2423 | prompt eval time = 4737.29 ms / 338 tokens ( 14.02 ms per token, 71.35 tokens per second) 8.31.950.009 I slot print_timing: id 0 | task 2423 | eval time = 5827.80 ms / 48 tokens ( 124.00 ms per token, 8.06 tokens per second) 8.31.950.009 I slot print_timing: id 0 | task 2423 | total time = 10565.09 ms / 386 tokens 8.31.950.010 I slot print_timing: id 0 | task 2423 | graphs reused = 2273 8.31.950.010 I slot print_timing: id 0 | task 2423 | graph reallocs = 0 / 0 (same size) / (changed size) 8.31.951.394 I slot release: id 0 | task 2423 | stop processing: n_tokens = 385, truncated = 0 8.31.959.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 99515702836 8.31.959.244 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.514 MiB) 8.32.054.106 I slot launch_slot_: id 0 | task 2474 | processing task, is_child = 0 8.36.242.884 I slot print_timing: id 0 | task 2474 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.19 s / 93.35 tokens per second 8.44.283.256 I slot print_timing: id 0 | task 2474 | prompt eval time = 5187.50 ms / 395 tokens ( 13.13 ms per token, 76.14 tokens per second) 8.44.283.263 I slot print_timing: id 0 | task 2474 | eval time = 7041.63 ms / 56 tokens ( 128.03 ms per token, 7.81 tokens per second) 8.44.283.265 I slot print_timing: id 0 | task 2474 | total time = 12229.13 ms / 451 tokens 8.44.283.266 I slot print_timing: id 0 | task 2474 | graphs reused = 2327 8.44.283.266 I slot print_timing: id 0 | task 2474 | graph reallocs = 0 / 0 (same size) / (changed size) 8.44.283.342 I slot release: id 0 | task 2474 | stop processing: n_tokens = 450, truncated = 0 8.44.300.396 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 99528034783 8.44.300.463 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.952 MiB) 8.44.449.206 I slot launch_slot_: id 0 | task 2533 | processing task, is_child = 0 8.50.526.377 I slot print_timing: id 0 | task 2533 | prompt processing, n_tokens = 524, progress = 0.99, t = 6.08 s / 86.22 tokens per second 9.02.353.825 I slot print_timing: id 0 | task 2533 | prompt eval time = 7120.79 ms / 528 tokens ( 13.49 ms per token, 74.15 tokens per second) 9.02.353.838 I slot print_timing: id 0 | task 2533 | eval time = 10783.79 ms / 83 tokens ( 131.51 ms per token, 7.60 tokens per second) 9.02.353.840 I slot print_timing: id 0 | task 2533 | total time = 17904.58 ms / 611 tokens 9.02.353.843 I slot print_timing: id 0 | task 2533 | graphs reused = 2408 9.02.353.845 I slot print_timing: id 0 | task 2533 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.356.499 I slot release: id 0 | task 2533 | stop processing: n_tokens = 610, truncated = 0 9.02.368.546 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 99546107943 9.02.368.630 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.578 MiB) 9.02.368.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.202 MiB) 9.02.582.569 I slot launch_slot_: id 0 | task 2620 | processing task, is_child = 0 9.06.410.718 I slot print_timing: id 0 | task 2620 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.83 s / 85.42 tokens per second 9.12.863.044 I slot print_timing: id 0 | task 2620 | prompt eval time = 4492.55 ms / 331 tokens ( 13.57 ms per token, 73.68 tokens per second) 9.12.863.058 I slot print_timing: id 0 | task 2620 | eval time = 5787.90 ms / 45 tokens ( 131.54 ms per token, 7.60 tokens per second) 9.12.863.074 I slot print_timing: id 0 | task 2620 | total time = 10280.44 ms / 376 tokens 9.12.863.084 I slot print_timing: id 0 | task 2620 | graphs reused = 2451 9.12.863.086 I slot print_timing: id 0 | task 2620 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.863.345 I slot release: id 0 | task 2620 | stop processing: n_tokens = 387, truncated = 0 9.12.880.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 99556614786 9.12.880.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.763 MiB) 9.13.041.136 I slot launch_slot_: id 0 | task 2668 | processing task, is_child = 0 9.17.222.829 I slot print_timing: id 0 | task 2668 | prompt processing, n_tokens = 358, progress = 0.99, t = 4.18 s / 85.61 tokens per second 9.24.632.670 I slot print_timing: id 0 | task 2668 | prompt eval time = 4829.24 ms / 362 tokens ( 13.34 ms per token, 74.96 tokens per second) 9.24.632.702 I slot print_timing: id 0 | task 2668 | eval time = 6762.19 ms / 53 tokens ( 130.04 ms per token, 7.69 tokens per second) 9.24.632.704 I slot print_timing: id 0 | task 2668 | total time = 11591.44 ms / 415 tokens 9.24.632.707 I slot print_timing: id 0 | task 2668 | graphs reused = 2502 9.24.632.709 I slot print_timing: id 0 | task 2668 | graph reallocs = 0 / 0 (same size) / (changed size) 9.24.635.858 I slot release: id 0 | task 2668 | stop processing: n_tokens = 426, truncated = 0 9.24.649.252 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 99568387303 9.24.649.313 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.389 MiB) 9.24.788.868 I slot launch_slot_: id 0 | task 2724 | processing task, is_child = 0 9.29.352.201 I slot print_timing: id 0 | task 2724 | prompt processing, n_tokens = 415, progress = 0.99, t = 4.56 s / 90.94 tokens per second 9.39.293.812 I slot print_timing: id 0 | task 2724 | prompt eval time = 5572.54 ms / 419 tokens ( 13.30 ms per token, 75.19 tokens per second) 9.39.293.837 I slot print_timing: id 0 | task 2724 | eval time = 8932.36 ms / 69 tokens ( 131.36 ms per token, 7.61 tokens per second) 9.39.293.845 I slot print_timing: id 0 | task 2724 | total time = 14504.90 ms / 488 tokens 9.39.293.847 I slot print_timing: id 0 | task 2724 | graphs reused = 2569 9.39.293.849 I slot print_timing: id 0 | task 2724 | graph reallocs = 0 / 0 (same size) / (changed size) 9.39.295.877 I slot release: id 0 | task 2724 | stop processing: n_tokens = 499, truncated = 0 9.39.313.463 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 99583047320 9.39.313.528 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 479.452 MiB) 9.39.313.551 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.264 MiB) 9.39.514.891 I slot launch_slot_: id 0 | task 2796 | processing task, is_child = 0 9.44.444.921 I slot print_timing: id 0 | task 2796 | prompt processing, n_tokens = 419, progress = 0.99, t = 4.93 s / 84.99 tokens per second 9.57.381.089 I slot print_timing: id 0 | task 2796 | prompt eval time = 5582.36 ms / 423 tokens ( 13.20 ms per token, 75.77 tokens per second) 9.57.381.114 I slot print_timing: id 0 | task 2796 | eval time = 12283.80 ms / 95 tokens ( 130.68 ms per token, 7.65 tokens per second) 9.57.381.117 I slot print_timing: id 0 | task 2796 | total time = 17866.16 ms / 518 tokens 9.57.381.123 I slot print_timing: id 0 | task 2796 | graphs reused = 2661 9.57.381.126 I slot print_timing: id 0 | task 2796 | graph reallocs = 0 / 0 (same size) / (changed size) 9.57.382.036 I slot release: id 0 | task 2796 | stop processing: n_tokens = 529, truncated = 0 9.57.394.375 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 99601133482 9.57.394.450 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.888 MiB) 9.57.548.074 I slot launch_slot_: id 0 | task 2894 | processing task, is_child = 0 10.01.354.007 I slot print_timing: id 0 | task 2894 | prompt processing, n_tokens = 337, progress = 0.99, t = 3.81 s / 88.55 tokens per second 10.07.516.103 I slot print_timing: id 0 | task 2894 | prompt eval time = 4453.70 ms / 341 tokens ( 13.06 ms per token, 76.57 tokens per second) 10.07.516.116 I slot print_timing: id 0 | task 2894 | eval time = 5514.29 ms / 43 tokens ( 131.29 ms per token, 7.62 tokens per second) 10.07.516.129 I slot print_timing: id 0 | task 2894 | total time = 9967.99 ms / 384 tokens 10.07.516.138 I slot print_timing: id 0 | task 2894 | graphs reused = 2702 10.07.516.140 I slot print_timing: id 0 | task 2894 | graph reallocs = 0 / 0 (same size) / (changed size) 10.07.516.334 I slot release: id 0 | task 2894 | stop processing: n_tokens = 395, truncated = 0 10.07.529.061 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 99611267775 10.07.529.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.763 MiB) 10.07.656.192 I slot launch_slot_: id 0 | task 2940 | processing task, is_child = 0 10.11.853.022 I slot print_timing: id 0 | task 2940 | prompt processing, n_tokens = 352, progress = 0.99, t = 4.20 s / 83.87 tokens per second 10.18.204.767 I slot print_timing: id 0 | task 2940 | prompt eval time = 4844.40 ms / 356 tokens ( 13.61 ms per token, 73.49 tokens per second) 10.18.204.770 I slot print_timing: id 0 | task 2940 | eval time = 5704.16 ms / 47 tokens ( 124.00 ms per token, 8.06 tokens per second) 10.18.204.770 I slot print_timing: id 0 | task 2940 | total time = 10548.56 ms / 403 tokens 10.18.204.771 I slot print_timing: id 0 | task 2940 | graphs reused = 2747 10.18.204.771 I slot print_timing: id 0 | task 2940 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.204.810 I slot release: id 0 | task 2940 | stop processing: n_tokens = 414, truncated = 0 10.18.211.247 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 99621956251 10.18.211.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 476.826 MiB) 10.18.211.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 478.265 MiB) 10.18.301.831 I slot launch_slot_: id 0 | task 2990 | processing task, is_child = 0 10.22.500.622 I slot print_timing: id 0 | task 2990 | prompt processing, n_tokens = 358, progress = 0.99, t = 4.20 s / 85.26 tokens per second 10.28.828.164 I slot print_timing: id 0 | task 2990 | prompt eval time = 4858.79 ms / 362 tokens ( 13.42 ms per token, 74.50 tokens per second) 10.28.828.183 I slot print_timing: id 0 | task 2990 | eval time = 5667.51 ms / 44 tokens ( 131.80 ms per token, 7.59 tokens per second) 10.28.828.185 I slot print_timing: id 0 | task 2990 | total time = 10526.30 ms / 406 tokens 10.28.828.187 I slot print_timing: id 0 | task 2990 | graphs reused = 2789 10.28.828.190 I slot print_timing: id 0 | task 2990 | graph reallocs = 0 / 0 (same size) / (changed size) 10.28.830.026 I slot release: id 0 | task 2990 | stop processing: n_tokens = 417, truncated = 0 10.28.847.277 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 99632581469 10.28.847.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 473.888 MiB) 10.28.998.023 I slot launch_slot_: id 0 | task 3037 | processing task, is_child = 0 10.33.524.523 I slot print_timing: id 0 | task 3037 | prompt processing, n_tokens = 387, progress = 0.99, t = 4.53 s / 85.50 tokens per second 10.42.943.719 I slot print_timing: id 0 | task 3037 | prompt eval time = 5179.81 ms / 391 tokens ( 13.25 ms per token, 75.49 tokens per second) 10.42.943.730 I slot print_timing: id 0 | task 3037 | eval time = 8765.79 ms / 68 tokens ( 130.83 ms per token, 7.64 tokens per second) 10.42.943.754 I slot print_timing: id 0 | task 3037 | total time = 13945.61 ms / 459 tokens 10.42.943.766 I slot print_timing: id 0 | task 3037 | graphs reused = 2855 10.42.943.777 I slot print_timing: id 0 | task 3037 | graph reallocs = 0 / 0 (same size) / (changed size) 10.42.944.040 I slot release: id 0 | task 3037 | stop processing: n_tokens = 470, truncated = 0 10.42.959.273 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 99646695482 10.42.959.343 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 487.393 MiB) 10.43.102.781 I slot launch_slot_: id 0 | task 3108 | processing task, is_child = 0 10.46.923.480 I slot print_timing: id 0 | task 3108 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.82 s / 88.73 tokens per second 10.54.247.212 I slot print_timing: id 0 | task 3108 | prompt eval time = 4469.60 ms / 343 tokens ( 13.03 ms per token, 76.74 tokens per second) 10.54.247.227 I slot print_timing: id 0 | task 3108 | eval time = 6674.74 ms / 54 tokens ( 125.94 ms per token, 7.94 tokens per second) 10.54.247.237 I slot print_timing: id 0 | task 3108 | total time = 11144.34 ms / 397 tokens 10.54.247.239 I slot print_timing: id 0 | task 3108 | graphs reused = 2907 10.54.247.242 I slot print_timing: id 0 | task 3108 | graph reallocs = 0 / 0 (same size) / (changed size) 10.54.247.373 I slot release: id 0 | task 3108 | stop processing: n_tokens = 408, truncated = 0 10.54.261.021 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 99657998814 10.54.261.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 470.887 MiB) 10.54.466.090 I slot launch_slot_: id 0 | task 3165 | processing task, is_child = 0 10.59.026.196 I slot print_timing: id 0 | task 3165 | prompt processing, n_tokens = 397, progress = 0.99, t = 4.56 s / 87.06 tokens per second 11.05.609.111 I slot print_timing: id 0 | task 3165 | prompt eval time = 5226.22 ms / 401 tokens ( 13.03 ms per token, 76.73 tokens per second) 11.05.609.124 I slot print_timing: id 0 | task 3165 | eval time = 5916.76 ms / 46 tokens ( 131.48 ms per token, 7.61 tokens per second) 11.05.609.127 I slot print_timing: id 0 | task 3165 | total time = 11142.98 ms / 447 tokens 11.05.609.129 I slot print_timing: id 0 | task 3165 | graphs reused = 2951 11.05.609.131 I slot print_timing: id 0 | task 3165 | graph reallocs = 0 / 0 (same size) / (changed size) 11.05.609.416 I slot release: id 0 | task 3165 | stop processing: n_tokens = 458, truncated = 0 11.05.625.136 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 99669360857 11.05.625.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 474.075 MiB) 11.05.625.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.137 MiB) 11.05.810.594 I slot launch_slot_: id 0 | task 3214 | processing task, is_child = 0 11.09.997.063 I slot print_timing: id 0 | task 3214 | prompt processing, n_tokens = 351, progress = 0.99, t = 4.19 s / 83.84 tokens per second 11.19.448.251 I slot print_timing: id 0 | task 3214 | prompt eval time = 4833.46 ms / 355 tokens ( 13.62 ms per token, 73.45 tokens per second) 11.19.448.264 I slot print_timing: id 0 | task 3214 | eval time = 8804.15 ms / 68 tokens ( 131.41 ms per token, 7.61 tokens per second) 11.19.448.266 I slot print_timing: id 0 | task 3214 | total time = 13637.61 ms / 423 tokens 11.19.448.269 I slot print_timing: id 0 | task 3214 | graphs reused = 3017 11.19.448.271 I slot print_timing: id 0 | task 3214 | graph reallocs = 0 / 0 (same size) / (changed size) 11.19.448.522 I slot release: id 0 | task 3214 | stop processing: n_tokens = 434, truncated = 0 11.19.464.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 99683199963 11.19.464.268 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 472.950 MiB) 11.19.606.015 I slot launch_slot_: id 0 | task 3285 | processing task, is_child = 0 11.23.786.623 I slot print_timing: id 0 | task 3285 | prompt processing, n_tokens = 347, progress = 0.99, t = 4.18 s / 83.00 tokens per second 11.31.709.779 I slot print_timing: id 0 | task 3285 | prompt eval time = 4829.95 ms / 351 tokens ( 13.76 ms per token, 72.67 tokens per second) 11.31.709.790 I slot print_timing: id 0 | task 3285 | eval time = 7273.78 ms / 57 tokens ( 129.89 ms per token, 7.70 tokens per second) 11.31.709.791 I slot print_timing: id 0 | task 3285 | total time = 12103.74 ms / 408 tokens 11.31.709.794 I slot print_timing: id 0 | task 3285 | graphs reused = 3072 11.31.709.799 I slot print_timing: id 0 | task 3285 | graph reallocs = 0 / 0 (same size) / (changed size) 11.31.709.957 I slot release: id 0 | task 3285 | stop processing: n_tokens = 419, truncated = 0 11.31.725.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 99695461398 11.31.725.383 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 477.014 MiB) 11.31.921.781 I slot launch_slot_: id 0 | task 3345 | processing task, is_child = 0 11.37.235.422 I slot print_timing: id 0 | task 3345 | prompt processing, n_tokens = 471, progress = 0.99, t = 5.31 s / 88.64 tokens per second 11.50.318.668 I slot print_timing: id 0 | task 3345 | prompt eval time = 6311.48 ms / 475 tokens ( 13.29 ms per token, 75.26 tokens per second) 11.50.318.684 I slot print_timing: id 0 | task 3345 | eval time = 12085.37 ms / 93 tokens ( 131.36 ms per token, 7.61 tokens per second) 11.50.318.687 I slot print_timing: id 0 | task 3345 | total time = 18396.85 ms / 568 tokens 11.50.318.689 I slot print_timing: id 0 | task 3345 | graphs reused = 3162 11.50.318.691 I slot print_timing: id 0 | task 3345 | graph reallocs = 0 / 0 (same size) / (changed size) 11.50.319.035 I slot release: id 0 | task 3345 | stop processing: n_tokens = 579, truncated = 0 11.50.336.174 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 99714070477 11.50.336.252 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 636.644 MiB) 11.50.511.462 I slot launch_slot_: id 0 | task 3441 | processing task, is_child = 0 11.55.449.427 I slot print_timing: id 0 | task 3441 | prompt processing, n_tokens = 436, progress = 0.99, t = 4.94 s / 88.30 tokens per second 12.09.286.228 I slot print_timing: id 0 | task 3441 | n_gen = 100, tg = 7.71 t/s, tg_3s = 7.79 t/s 12.10.073.505 I slot print_timing: id 0 | task 3441 | prompt eval time = 5933.14 ms / 440 tokens ( 13.48 ms per token, 74.16 tokens per second) 12.10.073.515 I slot print_timing: id 0 | task 3441 | eval time = 13628.86 ms / 106 tokens ( 129.80 ms per token, 7.70 tokens per second) 12.10.073.518 I slot print_timing: id 0 | task 3441 | total time = 19561.99 ms / 546 tokens 12.10.073.520 I slot print_timing: id 0 | task 3441 | graphs reused = 3265 12.10.073.556 I slot print_timing: id 0 | task 3441 | graph reallocs = 0 / 0 (same size) / (changed size) 12.10.073.826 I slot release: id 0 | task 3441 | stop processing: n_tokens = 557, truncated = 0 12.10.087.440 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 99733825267 12.10.087.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 622.701 MiB) 12.10.278.125 I slot launch_slot_: id 0 | task 3550 | processing task, is_child = 0 12.14.094.428 I slot print_timing: id 0 | task 3550 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.82 s / 89.35 tokens per second 12.21.754.767 I slot print_timing: id 0 | task 3550 | prompt eval time = 4463.56 ms / 345 tokens ( 12.94 ms per token, 77.29 tokens per second) 12.21.754.778 I slot print_timing: id 0 | task 3550 | eval time = 7013.04 ms / 55 tokens ( 129.87 ms per token, 7.70 tokens per second) 12.21.754.781 I slot print_timing: id 0 | task 3550 | total time = 11476.60 ms / 400 tokens 12.21.754.784 I slot print_timing: id 0 | task 3550 | graphs reused = 3318 12.21.754.786 I slot print_timing: id 0 | task 3550 | graph reallocs = 0 / 0 (same size) / (changed size) 12.21.754.953 I slot release: id 0 | task 3550 | stop processing: n_tokens = 411, truncated = 0 12.21.773.185 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 99745506394 12.21.773.251 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.140 MiB) 12.21.938.349 I slot launch_slot_: id 0 | task 3608 | processing task, is_child = 0 12.26.467.233 I slot print_timing: id 0 | task 3608 | prompt processing, n_tokens = 378, progress = 0.99, t = 4.53 s / 83.46 tokens per second 12.34.055.775 I slot print_timing: id 0 | task 3608 | prompt eval time = 5177.05 ms / 382 tokens ( 13.55 ms per token, 73.79 tokens per second) 12.34.055.786 I slot print_timing: id 0 | task 3608 | eval time = 6940.30 ms / 55 tokens ( 128.52 ms per token, 7.78 tokens per second) 12.34.055.788 I slot print_timing: id 0 | task 3608 | total time = 12117.35 ms / 437 tokens 12.34.055.791 I slot print_timing: id 0 | task 3608 | graphs reused = 3371 12.34.055.793 I slot print_timing: id 0 | task 3608 | graph reallocs = 0 / 0 (same size) / (changed size) 12.34.058.613 I slot release: id 0 | task 3608 | stop processing: n_tokens = 448, truncated = 0 12.34.083.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 99757810058 12.34.083.680 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 629.704 MiB) 12.35.859.065 I slot launch_slot_: id 0 | task 3666 | processing task, is_child = 0 12.39.703.614 I slot print_timing: id 0 | task 3666 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.84 s / 86.62 tokens per second 12.45.938.807 I slot print_timing: id 0 | task 3666 | prompt eval time = 4490.33 ms / 337 tokens ( 13.32 ms per token, 75.05 tokens per second) 12.45.938.824 I slot print_timing: id 0 | task 3666 | eval time = 5589.36 ms / 45 tokens ( 127.03 ms per token, 7.87 tokens per second) 12.45.938.827 I slot print_timing: id 0 | task 3666 | total time = 10079.70 ms / 382 tokens 12.45.938.829 I slot print_timing: id 0 | task 3666 | graphs reused = 3414 12.45.938.832 I slot print_timing: id 0 | task 3666 | graph reallocs = 0 / 0 (same size) / (changed size) 12.45.941.643 I slot release: id 0 | task 3666 | stop processing: n_tokens = 393, truncated = 0 12.45.963.830 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 99769693089 12.45.963.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 631.579 MiB) 12.46.461.193 I slot launch_slot_: id 0 | task 3714 | processing task, is_child = 0 12.51.007.278 I slot print_timing: id 0 | task 3714 | prompt processing, n_tokens = 398, progress = 0.99, t = 4.55 s / 87.55 tokens per second 13.00.672.172 I slot print_timing: id 0 | task 3714 | prompt eval time = 5199.22 ms / 402 tokens ( 12.93 ms per token, 77.32 tokens per second) 13.00.672.189 I slot print_timing: id 0 | task 3714 | eval time = 9011.72 ms / 70 tokens ( 130.60 ms per token, 7.66 tokens per second) 13.00.672.207 I slot print_timing: id 0 | task 3714 | total time = 14210.94 ms / 472 tokens 13.00.672.215 I slot print_timing: id 0 | task 3714 | graphs reused = 3482 13.00.672.217 I slot print_timing: id 0 | task 3714 | graph reallocs = 0 / 0 (same size) / (changed size) 13.00.674.212 I slot release: id 0 | task 3714 | stop processing: n_tokens = 483, truncated = 0 13.00.690.889 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 99784425657 13.00.690.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.201 MiB) 13.01.520.508 I slot launch_slot_: id 0 | task 3787 | processing task, is_child = 0 13.08.013.514 I slot print_timing: id 0 | task 3787 | prompt processing, n_tokens = 545, progress = 0.99, t = 6.49 s / 83.94 tokens per second 13.16.285.290 I slot print_timing: id 0 | task 3787 | prompt eval time = 7505.05 ms / 549 tokens ( 13.67 ms per token, 73.15 tokens per second) 13.16.285.311 I slot print_timing: id 0 | task 3787 | eval time = 7259.70 ms / 57 tokens ( 129.64 ms per token, 7.71 tokens per second) 13.16.285.314 I slot print_timing: id 0 | task 3787 | total time = 14764.75 ms / 606 tokens 13.16.285.316 I slot print_timing: id 0 | task 3787 | graphs reused = 3537 13.16.285.318 I slot print_timing: id 0 | task 3787 | graph reallocs = 0 / 0 (same size) / (changed size) 13.16.287.665 I slot release: id 0 | task 3787 | stop processing: n_tokens = 617, truncated = 0 13.16.306.618 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 99800039110 13.16.306.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.389 MiB) 13.16.306.716 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.577 MiB) 13.16.478.397 I slot launch_slot_: id 0 | task 3848 | processing task, is_child = 0 13.23.700.294 I slot print_timing: id 0 | task 3848 | prompt processing, n_tokens = 612, progress = 0.99, t = 7.22 s / 84.74 tokens per second 13.32.228.852 I slot print_timing: id 0 | task 3848 | prompt eval time = 8244.82 ms / 616 tokens ( 13.38 ms per token, 74.71 tokens per second) 13.32.228.865 I slot print_timing: id 0 | task 3848 | eval time = 7505.60 ms / 58 tokens ( 131.68 ms per token, 7.59 tokens per second) 13.32.228.871 I slot print_timing: id 0 | task 3848 | total time = 15750.42 ms / 674 tokens 13.32.228.873 I slot print_timing: id 0 | task 3848 | graphs reused = 3593 13.32.228.875 I slot print_timing: id 0 | task 3848 | graph reallocs = 0 / 0 (same size) / (changed size) 13.32.229.251 I slot release: id 0 | task 3848 | stop processing: n_tokens = 685, truncated = 0 13.32.252.513 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 99815980693 13.32.252.601 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.891 MiB) 13.32.434.937 I slot launch_slot_: id 0 | task 3910 | processing task, is_child = 0 13.40.081.774 I slot print_timing: id 0 | task 3910 | prompt processing, n_tokens = 661, progress = 0.99, t = 7.65 s / 86.44 tokens per second 13.48.998.048 I slot print_timing: id 0 | task 3910 | prompt eval time = 8669.49 ms / 665 tokens ( 13.04 ms per token, 76.71 tokens per second) 13.48.998.056 I slot print_timing: id 0 | task 3910 | eval time = 7893.58 ms / 61 tokens ( 131.56 ms per token, 7.60 tokens per second) 13.48.998.058 I slot print_timing: id 0 | task 3910 | total time = 16563.07 ms / 726 tokens 13.48.998.060 I slot print_timing: id 0 | task 3910 | graphs reused = 3652 13.48.998.062 I slot print_timing: id 0 | task 3910 | graph reallocs = 0 / 0 (same size) / (changed size) 13.49.000.424 I slot release: id 0 | task 3910 | stop processing: n_tokens = 737, truncated = 0 13.49.016.506 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 99832751868 13.49.016.589 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.014 MiB) 13.49.260.695 I slot launch_slot_: id 0 | task 3975 | processing task, is_child = 0 13.57.230.641 I slot print_timing: id 0 | task 3975 | prompt processing, n_tokens = 641, progress = 0.99, t = 7.97 s / 80.43 tokens per second 14.05.021.749 I slot print_timing: id 0 | task 3975 | prompt eval time = 8637.49 ms / 645 tokens ( 13.39 ms per token, 74.67 tokens per second) 14.05.021.772 I slot print_timing: id 0 | task 3975 | eval time = 7123.53 ms / 55 tokens ( 131.92 ms per token, 7.58 tokens per second) 14.05.021.774 I slot print_timing: id 0 | task 3975 | total time = 15761.03 ms / 700 tokens 14.05.021.776 I slot print_timing: id 0 | task 3975 | graphs reused = 3705 14.05.021.779 I slot print_timing: id 0 | task 3975 | graph reallocs = 0 / 0 (same size) / (changed size) 14.05.022.189 I slot release: id 0 | task 3975 | stop processing: n_tokens = 711, truncated = 0 14.05.040.066 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 99848773631 14.05.040.161 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 627.140 MiB) 14.05.282.790 I slot launch_slot_: id 0 | task 4034 | processing task, is_child = 0 14.10.600.423 I slot print_timing: id 0 | task 4034 | prompt processing, n_tokens = 470, progress = 0.99, t = 5.32 s / 88.39 tokens per second 14.17.577.226 I slot print_timing: id 0 | task 4034 | prompt eval time = 5971.75 ms / 474 tokens ( 12.60 ms per token, 79.37 tokens per second) 14.17.577.231 I slot print_timing: id 0 | task 4034 | eval time = 6322.67 ms / 52 tokens ( 123.97 ms per token, 8.07 tokens per second) 14.17.577.232 I slot print_timing: id 0 | task 4034 | total time = 12294.42 ms / 526 tokens 14.17.577.233 I slot print_timing: id 0 | task 4034 | graphs reused = 3754 14.17.577.233 I slot print_timing: id 0 | task 4034 | graph reallocs = 0 / 0 (same size) / (changed size) 14.17.578.376 I slot release: id 0 | task 4034 | stop processing: n_tokens = 537, truncated = 0 14.17.585.087 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 99861329817 14.17.585.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 625.640 MiB) 14.17.708.560 I slot launch_slot_: id 0 | task 4089 | processing task, is_child = 0 14.25.321.767 I slot print_timing: id 0 | task 4089 | prompt processing, n_tokens = 613, progress = 0.99, t = 7.61 s / 80.52 tokens per second 14.31.380.776 I slot print_timing: id 0 | task 4089 | prompt eval time = 8281.11 ms / 617 tokens ( 13.42 ms per token, 74.51 tokens per second) 14.31.380.791 I slot print_timing: id 0 | task 4089 | eval time = 5391.08 ms / 42 tokens ( 131.49 ms per token, 7.61 tokens per second) 14.31.380.793 I slot print_timing: id 0 | task 4089 | total time = 13672.19 ms / 659 tokens 14.31.380.795 I slot print_timing: id 0 | task 4089 | graphs reused = 3794 14.31.380.797 I slot print_timing: id 0 | task 4089 | graph reallocs = 0 / 0 (same size) / (changed size) 14.31.381.267 I slot release: id 0 | task 4089 | stop processing: n_tokens = 670, truncated = 0 14.31.400.793 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 670, t_last = 99875132712 14.31.400.865 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.702 MiB) 14.31.400.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 634.706 MiB) 14.31.624.818 I slot launch_slot_: id 0 | task 4135 | processing task, is_child = 0 14.38.893.654 I slot print_timing: id 0 | task 4135 | prompt processing, n_tokens = 597, progress = 0.99, t = 7.27 s / 82.13 tokens per second 14.45.742.058 I slot print_timing: id 0 | task 4135 | prompt eval time = 7938.58 ms / 601 tokens ( 13.21 ms per token, 75.71 tokens per second) 14.45.742.073 I slot print_timing: id 0 | task 4135 | eval time = 6178.62 ms / 48 tokens ( 131.46 ms per token, 7.61 tokens per second) 14.45.742.076 I slot print_timing: id 0 | task 4135 | total time = 14117.21 ms / 649 tokens 14.45.742.078 I slot print_timing: id 0 | task 4135 | graphs reused = 3840 14.45.742.080 I slot print_timing: id 0 | task 4135 | graph reallocs = 0 / 0 (same size) / (changed size) 14.45.742.538 I slot release: id 0 | task 4135 | stop processing: n_tokens = 660, truncated = 0 14.45.761.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 99889493979 14.45.761.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 633.330 MiB) 14.45.931.235 I slot launch_slot_: id 0 | task 4187 | processing task, is_child = 0 14.52.474.720 I slot print_timing: id 0 | task 4187 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.54 s / 80.84 tokens per second 14.59.170.005 I slot print_timing: id 0 | task 4187 | prompt eval time = 7208.67 ms / 533 tokens ( 13.52 ms per token, 73.94 tokens per second) 14.59.170.017 I slot print_timing: id 0 | task 4187 | eval time = 6030.07 ms / 47 tokens ( 131.09 ms per token, 7.63 tokens per second) 14.59.170.020 I slot print_timing: id 0 | task 4187 | total time = 13238.74 ms / 580 tokens 14.59.170.025 I slot print_timing: id 0 | task 4187 | graphs reused = 3885 14.59.170.028 I slot print_timing: id 0 | task 4187 | graph reallocs = 0 / 0 (same size) / (changed size) 14.59.170.282 I slot release: id 0 | task 4187 | stop processing: n_tokens = 591, truncated = 0 14.59.187.475 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 99902921723 14.59.187.562 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 624.202 MiB) 14.59.371.598 I slot launch_slot_: id 0 | task 4238 | processing task, is_child = 0 15.05.045.834 I slot print_timing: id 0 | task 4238 | prompt processing, n_tokens = 476, progress = 0.99, t = 5.67 s / 83.89 tokens per second 15.12.397.100 I slot print_timing: id 0 | task 4238 | prompt eval time = 6320.42 ms / 480 tokens ( 13.17 ms per token, 75.94 tokens per second) 15.12.397.117 I slot print_timing: id 0 | task 4238 | eval time = 6703.42 ms / 52 tokens ( 131.44 ms per token, 7.61 tokens per second) 15.12.397.120 I slot print_timing: id 0 | task 4238 | total time = 13023.84 ms / 532 tokens 15.12.397.123 I slot print_timing: id 0 | task 4238 | graphs reused = 3934 15.12.397.125 I slot print_timing: id 0 | task 4238 | graph reallocs = 0 / 0 (same size) / (changed size) 15.12.397.315 I slot release: id 0 | task 4238 | stop processing: n_tokens = 560, truncated = 0 15.12.414.206 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 99916148756 15.12.414.288 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 626.515 MiB) 15.12.414.297 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 623.076 MiB) 15.12.812.788 I slot launch_slot_: id 0 | task 4293 | processing task, is_child = 0 15.19.726.027 I slot print_timing: id 0 | task 4293 | prompt processing, n_tokens = 563, progress = 0.99, t = 6.91 s / 81.44 tokens per second 15.25.529.543 I slot print_timing: id 0 | task 4293 | prompt eval time = 7559.40 ms / 567 tokens ( 13.33 ms per token, 75.01 tokens per second) 15.25.529.548 I slot print_timing: id 0 | task 4293 | eval time = 5157.33 ms / 42 tokens ( 125.79 ms per token, 7.95 tokens per second) 15.25.529.549 I slot print_timing: id 0 | task 4293 | total time = 12716.73 ms / 609 tokens 15.25.529.550 I slot print_timing: id 0 | task 4293 | graphs reused = 3974 15.25.529.551 I slot print_timing: id 0 | task 4293 | graph reallocs = 0 / 0 (same size) / (changed size) 15.25.531.198 I slot release: id 0 | task 4293 | stop processing: n_tokens = 637, truncated = 0 15.25.547.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 99929282644 15.25.547.855 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 628.703 MiB) 15.25.726.587 I slot launch_slot_: id 0 | task 4339 | processing task, is_child = 0 15.31.424.633 I slot print_timing: id 0 | task 4339 | prompt processing, n_tokens = 502, progress = 0.99, t = 5.70 s / 88.10 tokens per second 15.40.049.396 I slot print_timing: id 0 | task 4339 | prompt eval time = 6351.80 ms / 506 tokens ( 12.55 ms per token, 79.66 tokens per second) 15.40.049.409 I slot print_timing: id 0 | task 4339 | eval time = 7970.96 ms / 63 tokens ( 128.56 ms per token, 7.78 tokens per second) 15.40.049.420 I slot print_timing: id 0 | task 4339 | total time = 14322.76 ms / 569 tokens 15.40.049.423 I slot print_timing: id 0 | task 4339 | graphs reused = 4035 15.40.049.431 I slot print_timing: id 0 | task 4339 | graph reallocs = 0 / 0 (same size) / (changed size) 15.40.049.784 I slot release: id 0 | task 4339 | stop processing: n_tokens = 597, truncated = 0 15.40.064.880 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 597, t_last = 99943801225 15.40.064.960 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 786.708 MiB) 15.40.236.982 I slot launch_slot_: id 0 | task 4405 | processing task, is_child = 0 15.45.180.564 I slot print_timing: id 0 | task 4405 | prompt processing, n_tokens = 432, progress = 0.99, t = 4.94 s / 87.39 tokens per second 15.50.917.962 I slot print_timing: id 0 | task 4405 | prompt eval time = 5589.03 ms / 436 tokens ( 12.82 ms per token, 78.01 tokens per second) 15.50.917.971 I slot print_timing: id 0 | task 4405 | eval time = 5091.93 ms / 40 tokens ( 130.56 ms per token, 7.66 tokens per second) 15.50.917.972 I slot print_timing: id 0 | task 4405 | total time = 10680.96 ms / 476 tokens 15.50.917.973 I slot print_timing: id 0 | task 4405 | graphs reused = 4073 15.50.917.974 I slot print_timing: id 0 | task 4405 | graph reallocs = 0 / 0 (same size) / (changed size) 15.50.918.075 I slot release: id 0 | task 4405 | stop processing: n_tokens = 504, truncated = 0 15.50.936.846 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 99954669517 15.50.936.917 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.959 MiB) 15.51.119.338 I slot launch_slot_: id 0 | task 4448 | processing task, is_child = 0 15.57.375.693 I slot print_timing: id 0 | task 4448 | prompt processing, n_tokens = 515, progress = 0.99, t = 6.26 s / 82.32 tokens per second 16.05.988.142 I slot print_timing: id 0 | task 4448 | prompt eval time = 6908.41 ms / 519 tokens ( 13.31 ms per token, 75.13 tokens per second) 16.05.988.152 I slot print_timing: id 0 | task 4448 | eval time = 7960.35 ms / 62 tokens ( 130.50 ms per token, 7.66 tokens per second) 16.05.988.155 I slot print_timing: id 0 | task 4448 | total time = 14868.76 ms / 581 tokens 16.05.988.164 I slot print_timing: id 0 | task 4448 | graphs reused = 4133 16.05.988.166 I slot print_timing: id 0 | task 4448 | graph reallocs = 0 / 0 (same size) / (changed size) 16.05.990.448 I slot release: id 0 | task 4448 | stop processing: n_tokens = 609, truncated = 0 16.06.003.194 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 99969741894 16.06.003.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 794.210 MiB) 16.06.291.569 I slot launch_slot_: id 0 | task 4514 | processing task, is_child = 0 16.11.617.406 I slot print_timing: id 0 | task 4514 | prompt processing, n_tokens = 461, progress = 0.99, t = 5.33 s / 86.56 tokens per second 16.18.225.066 I slot print_timing: id 0 | task 4514 | prompt eval time = 5985.99 ms / 465 tokens ( 12.87 ms per token, 77.68 tokens per second) 16.18.225.076 I slot print_timing: id 0 | task 4514 | eval time = 5947.48 ms / 46 tokens ( 132.17 ms per token, 7.57 tokens per second) 16.18.225.079 I slot print_timing: id 0 | task 4514 | total time = 11933.47 ms / 511 tokens 16.18.225.081 I slot print_timing: id 0 | task 4514 | graphs reused = 4176 16.18.225.083 I slot print_timing: id 0 | task 4514 | graph reallocs = 0 / 0 (same size) / (changed size) 16.18.225.526 I slot release: id 0 | task 4514 | stop processing: n_tokens = 542, truncated = 0 16.18.240.507 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 99981976968 16.18.240.587 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 792.585 MiB) 16.18.514.380 I slot launch_slot_: id 0 | task 4563 | processing task, is_child = 0 16.23.453.315 I slot print_timing: id 0 | task 4563 | prompt processing, n_tokens = 427, progress = 0.99, t = 4.94 s / 86.46 tokens per second 16.29.059.902 I slot print_timing: id 0 | task 4563 | prompt eval time = 5587.90 ms / 431 tokens ( 12.96 ms per token, 77.13 tokens per second) 16.29.059.905 I slot print_timing: id 0 | task 4563 | eval time = 4957.61 ms / 41 tokens ( 123.94 ms per token, 8.07 tokens per second) 16.29.059.905 I slot print_timing: id 0 | task 4563 | total time = 10545.51 ms / 472 tokens 16.29.059.912 I slot print_timing: id 0 | task 4563 | graphs reused = 4215 16.29.059.914 I slot print_timing: id 0 | task 4563 | graph reallocs = 0 / 0 (same size) / (changed size) 16.29.060.058 I slot release: id 0 | task 4563 | stop processing: n_tokens = 503, truncated = 0 16.29.066.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 99992811500 16.29.066.998 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 632.080 MiB) 16.29.067.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 790.021 MiB) 16.29.229.703 I slot launch_slot_: id 0 | task 4607 | processing task, is_child = 0 16.34.527.409 I slot print_timing: id 0 | task 4607 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.30 s / 85.51 tokens per second 16.40.761.022 I slot print_timing: id 0 | task 4607 | prompt eval time = 5946.43 ms / 457 tokens ( 13.01 ms per token, 76.85 tokens per second) 16.40.761.044 I slot print_timing: id 0 | task 4607 | eval time = 5584.85 ms / 44 tokens ( 129.88 ms per token, 7.70 tokens per second) 16.40.761.047 I slot print_timing: id 0 | task 4607 | total time = 11531.27 ms / 501 tokens 16.40.761.049 I slot print_timing: id 0 | task 4607 | graphs reused = 4256 16.40.761.051 I slot print_timing: id 0 | task 4607 | graph reallocs = 0 / 0 (same size) / (changed size) 16.40.762.950 I slot release: id 0 | task 4607 | stop processing: n_tokens = 532, truncated = 0 16.40.776.496 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 100004514393 16.40.776.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 789.396 MiB) 16.40.990.704 I slot launch_slot_: id 0 | task 4654 | processing task, is_child = 0 16.45.931.012 I slot print_timing: id 0 | task 4654 | prompt processing, n_tokens = 435, progress = 0.99, t = 4.94 s / 88.05 tokens per second 16.51.662.741 I slot print_timing: id 0 | task 4654 | prompt eval time = 5590.25 ms / 439 tokens ( 12.73 ms per token, 78.53 tokens per second) 16.51.662.747 I slot print_timing: id 0 | task 4654 | eval time = 5081.77 ms / 42 tokens ( 123.95 ms per token, 8.07 tokens per second) 16.51.662.747 I slot print_timing: id 0 | task 4654 | total time = 10672.02 ms / 481 tokens 16.51.662.748 I slot print_timing: id 0 | task 4654 | graphs reused = 4296 16.51.662.748 I slot print_timing: id 0 | task 4654 | graph reallocs = 0 / 0 (same size) / (changed size) 16.51.662.817 I slot release: id 0 | task 4654 | stop processing: n_tokens = 512, truncated = 0 16.51.670.601 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 100015414258 16.51.670.633 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.082 MiB) 16.51.970.093 I slot launch_slot_: id 0 | task 4699 | processing task, is_child = 0 16.58.875.638 I slot print_timing: id 0 | task 4699 | prompt processing, n_tokens = 602, progress = 0.99, t = 6.91 s / 87.18 tokens per second 17.07.066.768 I slot print_timing: id 0 | task 4699 | prompt eval time = 7909.56 ms / 606 tokens ( 13.05 ms per token, 76.62 tokens per second) 17.07.066.779 I slot print_timing: id 0 | task 4699 | eval time = 7187.07 ms / 56 tokens ( 130.67 ms per token, 7.65 tokens per second) 17.07.066.788 I slot print_timing: id 0 | task 4699 | total time = 15096.62 ms / 662 tokens 17.07.066.790 I slot print_timing: id 0 | task 4699 | graphs reused = 4350 17.07.066.792 I slot print_timing: id 0 | task 4699 | graph reallocs = 0 / 0 (same size) / (changed size) 17.07.068.811 I slot release: id 0 | task 4699 | stop processing: n_tokens = 693, truncated = 0 17.07.083.954 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 100030820255 17.07.084.039 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 783.144 MiB) 17.07.084.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 17.07.407.905 I slot launch_slot_: id 0 | task 4759 | processing task, is_child = 0 17.12.769.413 I slot print_timing: id 0 | task 4759 | prompt processing, n_tokens = 473, progress = 0.99, t = 5.36 s / 88.22 tokens per second 17.19.044.166 I slot print_timing: id 0 | task 4759 | prompt eval time = 6368.17 ms / 477 tokens ( 13.35 ms per token, 74.90 tokens per second) 17.19.044.177 I slot print_timing: id 0 | task 4759 | eval time = 5268.06 ms / 41 tokens ( 131.70 ms per token, 7.59 tokens per second) 17.19.044.183 I slot print_timing: id 0 | task 4759 | total time = 11636.23 ms / 518 tokens 17.19.044.185 I slot print_timing: id 0 | task 4759 | graphs reused = 4388 17.19.044.188 I slot print_timing: id 0 | task 4759 | graph reallocs = 0 / 0 (same size) / (changed size) 17.19.045.958 I slot release: id 0 | task 4759 | stop processing: n_tokens = 549, truncated = 0 17.19.065.573 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 100042797404 17.19.065.645 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 785.457 MiB) 17.19.265.300 I slot launch_slot_: id 0 | task 4803 | processing task, is_child = 0 17.23.452.320 I slot print_timing: id 0 | task 4803 | prompt processing, n_tokens = 782, progress = 0.93, t = 4.19 s / 186.77 tokens per second 17.29.119.932 I slot print_timing: id 0 | task 4803 | prompt processing, n_tokens = 841, progress = 1.00, t = 9.85 s / 85.34 tokens per second 17.37.836.851 I slot print_timing: id 0 | task 4803 | prompt eval time = 10873.41 ms / 845 tokens ( 12.87 ms per token, 77.71 tokens per second) 17.37.836.866 I slot print_timing: id 0 | task 4803 | eval time = 7698.10 ms / 60 tokens ( 130.48 ms per token, 7.66 tokens per second) 17.37.836.869 I slot print_timing: id 0 | task 4803 | total time = 18571.50 ms / 905 tokens 17.37.836.872 I slot print_timing: id 0 | task 4803 | graphs reused = 4446 17.37.836.875 I slot print_timing: id 0 | task 4803 | graph reallocs = 0 / 0 (same size) / (changed size) 17.37.839.745 I slot release: id 0 | task 4803 | stop processing: n_tokens = 936, truncated = 0 17.37.852.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 100061591191 17.37.852.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 779.643 MiB) 17.38.218.637 I slot launch_slot_: id 0 | task 4867 | processing task, is_child = 0 17.43.518.571 I slot print_timing: id 0 | task 4867 | prompt processing, n_tokens = 455, progress = 0.99, t = 5.30 s / 85.85 tokens per second 17.49.972.461 I slot print_timing: id 0 | task 4867 | prompt eval time = 6293.36 ms / 459 tokens ( 13.71 ms per token, 72.93 tokens per second) 17.49.972.474 I slot print_timing: id 0 | task 4867 | eval time = 5460.43 ms / 43 tokens ( 130.01 ms per token, 7.69 tokens per second) 17.49.972.477 I slot print_timing: id 0 | task 4867 | total time = 11753.79 ms / 502 tokens 17.49.972.479 I slot print_timing: id 0 | task 4867 | graphs reused = 4486 17.49.972.526 I slot print_timing: id 0 | task 4867 | graph reallocs = 0 / 0 (same size) / (changed size) 17.49.974.328 I slot release: id 0 | task 4867 | stop processing: n_tokens = 533, truncated = 0 17.49.990.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 533, t_last = 100073725773 17.49.990.714 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.834 MiB) 17.50.214.887 I slot launch_slot_: id 0 | task 4913 | processing task, is_child = 0 17.57.855.297 I slot print_timing: id 0 | task 4913 | prompt processing, n_tokens = 666, progress = 0.99, t = 7.64 s / 87.17 tokens per second 18.04.845.396 I slot print_timing: id 0 | task 4913 | prompt eval time = 8641.02 ms / 670 tokens ( 12.90 ms per token, 77.54 tokens per second) 18.04.845.413 I slot print_timing: id 0 | task 4913 | eval time = 5989.43 ms / 47 tokens ( 130.20 ms per token, 7.68 tokens per second) 18.04.845.416 I slot print_timing: id 0 | task 4913 | total time = 14630.45 ms / 717 tokens 18.04.845.418 I slot print_timing: id 0 | task 4913 | graphs reused = 4531 18.04.845.421 I slot print_timing: id 0 | task 4913 | graph reallocs = 0 / 0 (same size) / (changed size) 18.04.845.973 I slot release: id 0 | task 4913 | stop processing: n_tokens = 748, truncated = 0 18.04.864.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 100088597418 18.04.864.471 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.645 MiB) 18.05.174.680 I slot launch_slot_: id 0 | task 4964 | processing task, is_child = 0 18.08.605.984 I slot print_timing: id 0 | task 4964 | prompt processing, n_tokens = 731, progress = 0.95, t = 3.43 s / 213.04 tokens per second 18.14.304.867 I slot print_timing: id 0 | task 4964 | prompt processing, n_tokens = 771, progress = 1.00, t = 9.13 s / 84.45 tokens per second 18.23.526.733 I slot print_timing: id 0 | task 4964 | prompt eval time = 10145.17 ms / 775 tokens ( 13.09 ms per token, 76.39 tokens per second) 18.23.526.749 I slot print_timing: id 0 | task 4964 | eval time = 8206.85 ms / 63 tokens ( 132.37 ms per token, 7.55 tokens per second) 18.23.526.751 I slot print_timing: id 0 | task 4964 | total time = 18352.02 ms / 838 tokens 18.23.526.754 I slot print_timing: id 0 | task 4964 | graphs reused = 4592 18.23.526.756 I slot print_timing: id 0 | task 4964 | graph reallocs = 0 / 0 (same size) / (changed size) 18.23.529.859 I slot release: id 0 | task 4964 | stop processing: n_tokens = 869, truncated = 0 18.23.545.301 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 100107281304 18.23.545.402 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.206 MiB) 18.23.810.262 I slot launch_slot_: id 0 | task 5031 | processing task, is_child = 0 18.30.329.173 I slot print_timing: id 0 | task 5031 | prompt processing, n_tokens = 569, progress = 0.99, t = 6.52 s / 87.28 tokens per second 18.40.422.729 I slot print_timing: id 0 | task 5031 | prompt eval time = 7517.10 ms / 573 tokens ( 13.12 ms per token, 76.23 tokens per second) 18.40.422.747 I slot print_timing: id 0 | task 5031 | eval time = 9095.32 ms / 71 tokens ( 129.93 ms per token, 7.70 tokens per second) 18.40.422.755 I slot print_timing: id 0 | task 5031 | total time = 16612.41 ms / 644 tokens 18.40.422.758 I slot print_timing: id 0 | task 5031 | graphs reused = 4661 18.40.422.760 I slot print_timing: id 0 | task 5031 | graph reallocs = 0 / 0 (same size) / (changed size) 18.40.425.586 I slot release: id 0 | task 5031 | stop processing: n_tokens = 675, truncated = 0 18.40.442.719 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 100124177032 18.40.442.803 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.019 MiB) 18.40.442.843 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.769 MiB) 18.40.689.316 I slot launch_slot_: id 0 | task 5106 | processing task, is_child = 0 18.46.025.829 I slot print_timing: id 0 | task 5106 | prompt processing, n_tokens = 457, progress = 0.99, t = 5.34 s / 85.64 tokens per second 18.54.830.803 I slot print_timing: id 0 | task 5106 | prompt eval time = 6330.96 ms / 461 tokens ( 13.73 ms per token, 72.82 tokens per second) 18.54.830.807 I slot print_timing: id 0 | task 5106 | eval time = 7810.51 ms / 64 tokens ( 123.98 ms per token, 8.07 tokens per second) 18.54.830.807 I slot print_timing: id 0 | task 5106 | total time = 14141.46 ms / 525 tokens 18.54.830.808 I slot print_timing: id 0 | task 5106 | graphs reused = 4722 18.54.830.808 I slot print_timing: id 0 | task 5106 | graph reallocs = 0 / 0 (same size) / (changed size) 18.54.831.966 I slot release: id 0 | task 5106 | stop processing: n_tokens = 556, truncated = 0 18.54.842.856 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 100138583408 18.54.842.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 18.54.988.812 I slot launch_slot_: id 0 | task 5173 | processing task, is_child = 0 19.02.240.553 I slot print_timing: id 0 | task 5173 | prompt processing, n_tokens = 605, progress = 0.99, t = 7.25 s / 83.43 tokens per second 19.15.628.702 I slot print_timing: id 0 | task 5173 | n_gen = 100, tg = 7.77 t/s, tg_3s = 7.85 t/s 19.18.650.045 I slot print_timing: id 0 | task 5173 | n_gen = 123, tg = 7.74 t/s, tg_3s = 7.61 t/s 19.20.896.862 I slot print_timing: id 0 | task 5173 | prompt eval time = 7904.20 ms / 609 tokens ( 12.98 ms per token, 77.05 tokens per second) 19.20.896.870 I slot print_timing: id 0 | task 5173 | eval time = 18003.82 ms / 140 tokens ( 129.52 ms per token, 7.72 tokens per second) 19.20.896.872 I slot print_timing: id 0 | task 5173 | total time = 25908.02 ms / 749 tokens 19.20.896.873 I slot print_timing: id 0 | task 5173 | graphs reused = 4859 19.20.896.874 I slot print_timing: id 0 | task 5173 | graph reallocs = 0 / 0 (same size) / (changed size) 19.20.897.021 I slot release: id 0 | task 5173 | stop processing: n_tokens = 780, truncated = 0 19.20.915.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 780, t_last = 100164648462 19.20.915.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 19.21.155.415 I slot launch_slot_: id 0 | task 5317 | processing task, is_child = 0 19.24.608.554 I slot print_timing: id 0 | task 5317 | prompt processing, n_tokens = 758, progress = 0.96, t = 3.45 s / 219.51 tokens per second 19.30.647.875 I slot print_timing: id 0 | task 5317 | prompt processing, n_tokens = 787, progress = 1.00, t = 9.49 s / 82.91 tokens per second 19.38.841.440 I slot print_timing: id 0 | task 5317 | prompt eval time = 10147.46 ms / 791 tokens ( 12.83 ms per token, 77.95 tokens per second) 19.38.841.463 I slot print_timing: id 0 | task 5317 | eval time = 7538.53 ms / 61 tokens ( 125.64 ms per token, 7.96 tokens per second) 19.38.841.466 I slot print_timing: id 0 | task 5317 | total time = 17685.99 ms / 852 tokens 19.38.842.850 I slot print_timing: id 0 | task 5317 | graphs reused = 4918 19.38.842.861 I slot print_timing: id 0 | task 5317 | graph reallocs = 0 / 0 (same size) / (changed size) 19.38.843.948 I slot release: id 0 | task 5317 | stop processing: n_tokens = 883, truncated = 0 19.38.857.633 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 100182595393 19.38.857.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1105.905 MiB) 19.39.111.232 I slot launch_slot_: id 0 | task 5382 | processing task, is_child = 0 19.45.657.298 I slot print_timing: id 0 | task 5382 | prompt processing, n_tokens = 529, progress = 0.99, t = 6.55 s / 80.81 tokens per second 19.53.128.642 I slot print_timing: id 0 | task 5382 | prompt eval time = 7199.08 ms / 533 tokens ( 13.51 ms per token, 74.04 tokens per second) 19.53.128.645 I slot print_timing: id 0 | task 5382 | eval time = 6818.31 ms / 56 tokens ( 123.97 ms per token, 8.07 tokens per second) 19.53.128.645 I slot print_timing: id 0 | task 5382 | total time = 14017.39 ms / 589 tokens 19.53.128.646 I slot print_timing: id 0 | task 5382 | graphs reused = 4972 19.53.128.647 I slot print_timing: id 0 | task 5382 | graph reallocs = 0 / 0 (same size) / (changed size) 19.53.129.756 I slot release: id 0 | task 5382 | stop processing: n_tokens = 677, truncated = 0 19.53.138.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 100196881198 19.53.398.488 I slot launch_slot_: id 0 | task 5442 | processing task, is_child = 0 19.59.934.513 I slot print_timing: id 0 | task 5442 | prompt processing, n_tokens = 562, progress = 0.99, t = 6.54 s / 85.99 tokens per second 20.06.590.154 I slot print_timing: id 0 | task 5442 | prompt eval time = 7530.81 ms / 566 tokens ( 13.31 ms per token, 75.16 tokens per second) 20.06.590.166 I slot print_timing: id 0 | task 5442 | eval time = 5660.82 ms / 46 tokens ( 125.80 ms per token, 7.95 tokens per second) 20.06.590.169 I slot print_timing: id 0 | task 5442 | total time = 13191.63 ms / 612 tokens 20.06.590.171 I slot print_timing: id 0 | task 5442 | graphs reused = 5016 20.06.590.173 I slot print_timing: id 0 | task 5442 | graph reallocs = 0 / 0 (same size) / (changed size) 20.06.592.534 I slot release: id 0 | task 5442 | stop processing: n_tokens = 643, truncated = 0 20.06.608.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 100210343977 20.06.608.963 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.082 MiB) 20.06.898.341 I slot launch_slot_: id 0 | task 5492 | processing task, is_child = 0 20.12.212.341 I slot print_timing: id 0 | task 5492 | prompt processing, n_tokens = 439, progress = 0.99, t = 5.31 s / 82.61 tokens per second 20.18.244.649 I slot print_timing: id 0 | task 5492 | prompt eval time = 5960.22 ms / 443 tokens ( 13.45 ms per token, 74.33 tokens per second) 20.18.244.657 I slot print_timing: id 0 | task 5492 | eval time = 5386.06 ms / 43 tokens ( 128.24 ms per token, 7.80 tokens per second) 20.18.244.659 I slot print_timing: id 0 | task 5492 | total time = 11346.28 ms / 486 tokens 20.18.244.660 I slot print_timing: id 0 | task 5492 | graphs reused = 5056 20.18.244.661 I slot print_timing: id 0 | task 5492 | graph reallocs = 0 / 0 (same size) / (changed size) 20.18.245.265 I slot release: id 0 | task 5492 | stop processing: n_tokens = 517, truncated = 0 20.18.260.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 100221996709 20.18.260.454 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1094.150 MiB) 20.18.499.416 I slot launch_slot_: id 0 | task 5538 | processing task, is_child = 0 20.23.811.934 I slot print_timing: id 0 | task 5538 | prompt processing, n_tokens = 483, progress = 0.99, t = 5.31 s / 90.92 tokens per second 20.33.117.806 I slot print_timing: id 0 | task 5538 | prompt eval time = 6310.89 ms / 487 tokens ( 12.96 ms per token, 77.17 tokens per second) 20.33.117.822 I slot print_timing: id 0 | task 5538 | eval time = 8307.44 ms / 65 tokens ( 129.80 ms per token, 7.70 tokens per second) 20.33.117.825 I slot print_timing: id 0 | task 5538 | total time = 14618.33 ms / 552 tokens 20.33.117.827 I slot print_timing: id 0 | task 5538 | graphs reused = 5119 20.33.117.830 I slot print_timing: id 0 | task 5538 | graph reallocs = 0 / 0 (same size) / (changed size) 20.33.120.435 I slot release: id 0 | task 5538 | stop processing: n_tokens = 583, truncated = 0 20.33.138.721 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 100236871881 20.33.138.798 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.716 MiB) 20.33.383.596 I slot launch_slot_: id 0 | task 5606 | processing task, is_child = 0 20.39.086.734 I slot print_timing: id 0 | task 5606 | prompt processing, n_tokens = 503, progress = 0.99, t = 5.70 s / 88.20 tokens per second 20.45.829.028 I slot print_timing: id 0 | task 5606 | prompt eval time = 6377.87 ms / 507 tokens ( 12.58 ms per token, 79.49 tokens per second) 20.45.829.046 I slot print_timing: id 0 | task 5606 | eval time = 6067.52 ms / 47 tokens ( 131.90 ms per token, 7.58 tokens per second) 20.45.829.049 I slot print_timing: id 0 | task 5606 | total time = 12445.39 ms / 554 tokens 20.45.829.051 I slot print_timing: id 0 | task 5606 | graphs reused = 5164 20.45.829.054 I slot print_timing: id 0 | task 5606 | graph reallocs = 0 / 0 (same size) / (changed size) 20.45.829.413 I slot release: id 0 | task 5606 | stop processing: n_tokens = 585, truncated = 0 20.45.848.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 100249580855 20.45.848.564 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.520 MiB) 20.46.063.216 I slot launch_slot_: id 0 | task 5656 | processing task, is_child = 0 20.53.668.203 I slot print_timing: id 0 | task 5656 | prompt processing, n_tokens = 629, progress = 0.99, t = 7.60 s / 82.71 tokens per second 21.02.395.940 I slot print_timing: id 0 | task 5656 | prompt eval time = 8259.84 ms / 633 tokens ( 13.05 ms per token, 76.64 tokens per second) 21.02.395.948 I slot print_timing: id 0 | task 5656 | eval time = 8072.87 ms / 66 tokens ( 124.20 ms per token, 8.05 tokens per second) 21.02.395.949 I slot print_timing: id 0 | task 5656 | total time = 16332.71 ms / 699 tokens 21.02.395.949 I slot print_timing: id 0 | task 5656 | graphs reused = 5228 21.02.395.950 I slot print_timing: id 0 | task 5656 | graph reallocs = 0 / 0 (same size) / (changed size) 21.02.396.414 I slot release: id 0 | task 5656 | stop processing: n_tokens = 730, truncated = 0 21.02.402.296 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 100266147856 21.02.402.337 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.151 MiB) 21.02.650.823 I slot launch_slot_: id 0 | task 5726 | processing task, is_child = 0 21.09.524.037 I slot print_timing: id 0 | task 5726 | prompt processing, n_tokens = 567, progress = 0.99, t = 6.87 s / 82.49 tokens per second 21.15.881.202 I slot print_timing: id 0 | task 5726 | prompt eval time = 7522.96 ms / 571 tokens ( 13.18 ms per token, 75.90 tokens per second) 21.15.881.209 I slot print_timing: id 0 | task 5726 | eval time = 5707.40 ms / 47 tokens ( 124.07 ms per token, 8.06 tokens per second) 21.15.881.210 I slot print_timing: id 0 | task 5726 | total time = 13230.36 ms / 618 tokens 21.15.881.210 I slot print_timing: id 0 | task 5726 | graphs reused = 5273 21.15.881.211 I slot print_timing: id 0 | task 5726 | graph reallocs = 0 / 0 (same size) / (changed size) 21.15.881.301 I slot release: id 0 | task 5726 | stop processing: n_tokens = 649, truncated = 0 21.15.890.029 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 649, t_last = 100279632742 21.15.890.077 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1102.591 MiB) 21.16.169.511 I slot launch_slot_: id 0 | task 5777 | processing task, is_child = 0 21.19.619.900 I slot print_timing: id 0 | task 5777 | prompt processing, n_tokens = 775, progress = 0.97, t = 3.45 s / 224.61 tokens per second 21.25.670.789 I slot print_timing: id 0 | task 5777 | prompt processing, n_tokens = 794, progress = 1.00, t = 9.50 s / 83.57 tokens per second 21.31.665.398 I slot print_timing: id 0 | task 5777 | prompt eval time = 10151.83 ms / 798 tokens ( 12.72 ms per token, 78.61 tokens per second) 21.31.665.401 I slot print_timing: id 0 | task 5777 | eval time = 5344.05 ms / 44 tokens ( 124.28 ms per token, 8.05 tokens per second) 21.31.665.401 I slot print_timing: id 0 | task 5777 | total time = 15495.87 ms / 842 tokens 21.31.665.402 I slot print_timing: id 0 | task 5777 | graphs reused = 5315 21.31.665.402 I slot print_timing: id 0 | task 5777 | graph reallocs = 0 / 0 (same size) / (changed size) 21.31.665.515 I slot release: id 0 | task 5777 | stop processing: n_tokens = 873, truncated = 0 21.31.671.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 100295416957 21.31.671.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1239.337 MiB) 21.31.915.607 I slot launch_slot_: id 0 | task 5825 | processing task, is_child = 0 21.38.792.440 I slot print_timing: id 0 | task 5825 | prompt processing, n_tokens = 568, progress = 0.99, t = 6.88 s / 82.60 tokens per second 21.44.653.537 I slot print_timing: id 0 | task 5825 | prompt eval time = 7527.92 ms / 572 tokens ( 13.16 ms per token, 75.98 tokens per second) 21.44.653.540 I slot print_timing: id 0 | task 5825 | eval time = 5209.99 ms / 43 tokens ( 124.05 ms per token, 8.06 tokens per second) 21.44.653.541 I slot print_timing: id 0 | task 5825 | total time = 12737.91 ms / 615 tokens 21.44.653.541 I slot print_timing: id 0 | task 5825 | graphs reused = 5356 21.44.653.542 I slot print_timing: id 0 | task 5825 | graph reallocs = 0 / 0 (same size) / (changed size) 21.44.653.654 I slot release: id 0 | task 5825 | stop processing: n_tokens = 646, truncated = 0 21.44.661.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 100308405096 21.44.661.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.585 MiB) 21.44.873.139 I slot launch_slot_: id 0 | task 5872 | processing task, is_child = 0 21.52.457.788 I slot print_timing: id 0 | task 5872 | prompt processing, n_tokens = 609, progress = 0.99, t = 7.58 s / 80.29 tokens per second 21.59.442.362 I slot print_timing: id 0 | task 5872 | prompt eval time = 8251.63 ms / 613 tokens ( 13.46 ms per token, 74.29 tokens per second) 21.59.442.373 I slot print_timing: id 0 | task 5872 | eval time = 6317.56 ms / 49 tokens ( 131.62 ms per token, 7.60 tokens per second) 21.59.442.375 I slot print_timing: id 0 | task 5872 | total time = 14569.19 ms / 662 tokens 21.59.442.378 I slot print_timing: id 0 | task 5872 | graphs reused = 5403 21.59.442.380 I slot print_timing: id 0 | task 5872 | graph reallocs = 0 / 0 (same size) / (changed size) 21.59.444.254 I slot release: id 0 | task 5872 | stop processing: n_tokens = 693, truncated = 0 21.59.459.410 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 100323195701 21.59.459.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.081 MiB) 21.59.708.289 I slot launch_slot_: id 0 | task 5925 | processing task, is_child = 0 22.06.574.959 I slot print_timing: id 0 | task 5925 | prompt processing, n_tokens = 576, progress = 0.99, t = 6.87 s / 83.88 tokens per second 22.15.203.578 I slot print_timing: id 0 | task 5925 | prompt eval time = 7516.19 ms / 580 tokens ( 12.96 ms per token, 77.17 tokens per second) 22.15.203.582 I slot print_timing: id 0 | task 5925 | eval time = 7979.07 ms / 64 tokens ( 126.65 ms per token, 7.90 tokens per second) 22.15.203.582 I slot print_timing: id 0 | task 5925 | total time = 15495.26 ms / 644 tokens 22.15.203.583 I slot print_timing: id 0 | task 5925 | graphs reused = 5465 22.15.203.583 I slot print_timing: id 0 | task 5925 | graph reallocs = 0 / 0 (same size) / (changed size) 22.15.208.650 I slot release: id 0 | task 5925 | stop processing: n_tokens = 675, truncated = 0 22.15.233.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 100338960093 22.15.233.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.208 MiB) 22.17.903.189 I slot launch_slot_: id 0 | task 5993 | processing task, is_child = 0 22.26.776.279 I slot print_timing: id 0 | task 5993 | prompt processing, n_tokens = 712, progress = 0.99, t = 8.87 s / 80.24 tokens per second 22.33.527.326 I slot print_timing: id 0 | task 5993 | prompt eval time = 9524.03 ms / 716 tokens ( 13.30 ms per token, 75.18 tokens per second) 22.33.527.331 I slot print_timing: id 0 | task 5993 | eval time = 6100.09 ms / 50 tokens ( 124.49 ms per token, 8.03 tokens per second) 22.33.527.332 I slot print_timing: id 0 | task 5993 | total time = 15624.12 ms / 766 tokens 22.33.527.332 I slot print_timing: id 0 | task 5993 | graphs reused = 5512 22.33.527.333 I slot print_timing: id 0 | task 5993 | graph reallocs = 0 / 0 (same size) / (changed size) 22.33.531.578 I slot release: id 0 | task 5993 | stop processing: n_tokens = 797, truncated = 0 22.33.552.274 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 100357283023 22.33.552.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.333 MiB) 22.35.269.738 I slot launch_slot_: id 0 | task 6047 | processing task, is_child = 0 22.38.737.783 I slot print_timing: id 0 | task 6047 | prompt processing, n_tokens = 755, progress = 0.95, t = 3.47 s / 217.70 tokens per second 22.44.421.006 I slot print_timing: id 0 | task 6047 | prompt processing, n_tokens = 795, progress = 1.00, t = 9.15 s / 86.87 tokens per second 22.57.723.986 I slot print_timing: id 0 | task 6047 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 22.57.972.472 I slot print_timing: id 0 | task 6047 | prompt eval time = 10152.04 ms / 799 tokens ( 12.71 ms per token, 78.70 tokens per second) 22.57.972.480 I slot print_timing: id 0 | task 6047 | eval time = 12550.68 ms / 102 tokens ( 124.26 ms per token, 8.05 tokens per second) 22.57.972.481 I slot print_timing: id 0 | task 6047 | total time = 22702.72 ms / 901 tokens 22.57.972.481 I slot print_timing: id 0 | task 6047 | graphs reused = 5612 22.57.972.482 I slot print_timing: id 0 | task 6047 | graph reallocs = 0 / 0 (same size) / (changed size) 22.57.974.515 I slot release: id 0 | task 6047 | stop processing: n_tokens = 932, truncated = 0 22.57.982.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 932, t_last = 100381725956 22.57.982.655 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.025 MiB) 22.58.186.780 I slot launch_slot_: id 0 | task 6153 | processing task, is_child = 0 23.02.006.155 I slot print_timing: id 0 | task 6153 | prompt processing, n_tokens = 357, progress = 0.99, t = 3.82 s / 93.47 tokens per second 23.15.278.312 I slot print_timing: id 0 | task 6153 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 23.16.766.086 I slot print_timing: id 0 | task 6153 | prompt eval time = 4815.89 ms / 361 tokens ( 13.34 ms per token, 74.96 tokens per second) 23.16.766.092 I slot print_timing: id 0 | task 6153 | eval time = 13763.40 ms / 112 tokens ( 123.99 ms per token, 8.06 tokens per second) 23.16.766.092 I slot print_timing: id 0 | task 6153 | total time = 18579.29 ms / 473 tokens 23.16.766.093 I slot print_timing: id 0 | task 6153 | graphs reused = 5722 23.16.766.093 I slot print_timing: id 0 | task 6153 | graph reallocs = 0 / 0 (same size) / (changed size) 23.16.766.156 I slot release: id 0 | task 6153 | stop processing: n_tokens = 504, truncated = 0 23.16.773.454 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 100400517598 23.16.773.482 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.961 MiB) 23.16.915.253 I slot launch_slot_: id 0 | task 6268 | processing task, is_child = 0 23.21.103.961 I slot print_timing: id 0 | task 6268 | prompt processing, n_tokens = 377, progress = 0.99, t = 4.19 s / 90.00 tokens per second 23.34.384.354 I slot print_timing: id 0 | task 6268 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 23.35.378.872 I slot print_timing: id 0 | task 6268 | prompt eval time = 5190.98 ms / 381 tokens ( 13.62 ms per token, 73.40 tokens per second) 23.35.378.877 I slot print_timing: id 0 | task 6268 | eval time = 13272.63 ms / 108 tokens ( 124.04 ms per token, 8.06 tokens per second) 23.35.378.878 I slot print_timing: id 0 | task 6268 | total time = 18463.61 ms / 489 tokens 23.35.378.878 I slot print_timing: id 0 | task 6268 | graphs reused = 5827 23.35.378.879 I slot print_timing: id 0 | task 6268 | graph reallocs = 0 / 0 (same size) / (changed size) 23.35.379.424 I slot release: id 0 | task 6268 | stop processing: n_tokens = 520, truncated = 0 23.35.386.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 100419130866 23.35.386.901 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.966 MiB) 23.35.519.379 I slot launch_slot_: id 0 | task 6379 | processing task, is_child = 0 23.39.329.300 I slot print_timing: id 0 | task 6379 | prompt processing, n_tokens = 361, progress = 0.99, t = 3.81 s / 94.75 tokens per second 23.52.603.991 I slot print_timing: id 0 | task 6379 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 23.55.581.735 I slot print_timing: id 0 | task 6379 | prompt eval time = 4809.69 ms / 365 tokens ( 13.18 ms per token, 75.89 tokens per second) 23.55.581.740 I slot print_timing: id 0 | task 6379 | eval time = 15252.65 ms / 124 tokens ( 124.01 ms per token, 8.06 tokens per second) 23.55.581.740 I slot print_timing: id 0 | task 6379 | total time = 20062.34 ms / 489 tokens 23.55.581.741 I slot print_timing: id 0 | task 6379 | graphs reused = 5948 23.55.581.741 I slot print_timing: id 0 | task 6379 | graph reallocs = 0 / 0 (same size) / (changed size) 23.55.582.921 I slot release: id 0 | task 6379 | stop processing: n_tokens = 520, truncated = 0 23.55.589.319 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 100439334363 23.55.589.346 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1087.773 MiB) 23.55.744.769 I slot launch_slot_: id 0 | task 6506 | processing task, is_child = 0 23.59.543.460 I slot print_timing: id 0 | task 6506 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.80 s / 86.61 tokens per second 24.12.824.800 I slot print_timing: id 0 | task 6506 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 24.13.692.482 I slot print_timing: id 0 | task 6506 | prompt eval time = 4794.64 ms / 333 tokens ( 14.40 ms per token, 69.45 tokens per second) 24.13.692.486 I slot print_timing: id 0 | task 6506 | eval time = 13153.06 ms / 107 tokens ( 124.09 ms per token, 8.06 tokens per second) 24.13.692.487 I slot print_timing: id 0 | task 6506 | total time = 17947.69 ms / 440 tokens 24.13.692.487 I slot print_timing: id 0 | task 6506 | graphs reused = 6053 24.13.692.487 I slot print_timing: id 0 | task 6506 | graph reallocs = 0 / 0 (same size) / (changed size) 24.13.692.537 I slot release: id 0 | task 6506 | stop processing: n_tokens = 471, truncated = 0 24.13.698.654 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 100457443978 24.13.805.940 I slot launch_slot_: id 0 | task 6616 | processing task, is_child = 0 24.18.346.801 I slot print_timing: id 0 | task 6616 | prompt processing, n_tokens = 399, progress = 0.99, t = 4.54 s / 87.87 tokens per second 24.31.629.912 I slot print_timing: id 0 | task 6616 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 24.34.729.989 I slot print_timing: id 0 | task 6616 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 24.37.829.579 I slot print_timing: id 0 | task 6616 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.07 t/s 24.40.928.498 I slot print_timing: id 0 | task 6616 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.07 t/s 24.41.300.499 I slot print_timing: id 0 | task 6616 | prompt eval time = 5534.53 ms / 403 tokens ( 13.73 ms per token, 72.82 tokens per second) 24.41.300.504 I slot print_timing: id 0 | task 6616 | eval time = 21960.01 ms / 178 tokens ( 124.07 ms per token, 8.06 tokens per second) 24.41.300.504 I slot print_timing: id 0 | task 6616 | total time = 27494.55 ms / 581 tokens 24.41.300.504 I slot print_timing: id 0 | task 6616 | graphs reused = 6228 24.41.300.505 I slot print_timing: id 0 | task 6616 | graph reallocs = 0 / 0 (same size) / (changed size) 24.41.300.542 I slot release: id 0 | task 6616 | stop processing: n_tokens = 612, truncated = 0 24.41.306.864 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 612, t_last = 100485051983 24.41.306.900 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1090.712 MiB) 24.41.474.886 I slot launch_slot_: id 0 | task 6797 | processing task, is_child = 0 24.45.658.672 I slot print_timing: id 0 | task 6797 | prompt processing, n_tokens = 407, progress = 0.99, t = 4.18 s / 97.28 tokens per second 24.59.326.182 I slot print_timing: id 0 | task 6797 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 25.02.424.668 I slot print_timing: id 0 | task 6797 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 25.05.523.908 I slot print_timing: id 0 | task 6797 | n_gen = 150, tg = 8.07 t/s, tg_3s = 8.07 t/s 25.08.623.165 I slot print_timing: id 0 | task 6797 | n_gen = 175, tg = 8.07 t/s, tg_3s = 8.07 t/s 25.09.863.024 I slot print_timing: id 0 | task 6797 | prompt eval time = 5576.24 ms / 411 tokens ( 13.57 ms per token, 73.71 tokens per second) 25.09.863.029 I slot print_timing: id 0 | task 6797 | eval time = 22811.89 ms / 185 tokens ( 123.98 ms per token, 8.07 tokens per second) 25.09.863.029 I slot print_timing: id 0 | task 6797 | total time = 28388.13 ms / 596 tokens 25.09.863.030 I slot print_timing: id 0 | task 6797 | graphs reused = 6410 25.09.863.030 I slot print_timing: id 0 | task 6797 | graph reallocs = 0 / 0 (same size) / (changed size) 25.09.863.064 I slot release: id 0 | task 6797 | stop processing: n_tokens = 627, truncated = 0 25.09.869.558 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 100513614505 25.09.869.596 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1089.586 MiB) 25.10.036.104 I slot launch_slot_: id 0 | task 6985 | processing task, is_child = 0 25.14.942.668 I slot print_timing: id 0 | task 6985 | prompt processing, n_tokens = 486, progress = 0.99, t = 4.91 s / 99.05 tokens per second 25.28.954.717 I slot print_timing: id 0 | task 6985 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 25.32.055.091 I slot print_timing: id 0 | task 6985 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 25.35.157.993 I slot print_timing: id 0 | task 6985 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 25.38.260.470 I slot print_timing: id 0 | task 6985 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.06 t/s 25.41.361.825 I slot print_timing: id 0 | task 6985 | n_gen = 200, tg = 8.06 t/s, tg_3s = 8.06 t/s 25.44.465.216 I slot print_timing: id 0 | task 6985 | prompt eval time = 6641.87 ms / 490 tokens ( 13.55 ms per token, 73.77 tokens per second) 25.44.465.221 I slot print_timing: id 0 | task 6985 | eval time = 27787.23 ms / 225 tokens ( 124.05 ms per token, 8.06 tokens per second) 25.44.465.221 I slot print_timing: id 0 | task 6985 | total time = 34429.10 ms / 715 tokens 25.44.465.222 I slot print_timing: id 0 | task 6985 | graphs reused = 6633 25.44.465.222 I slot print_timing: id 0 | task 6985 | graph reallocs = 0 / 0 (same size) / (changed size) 25.44.465.263 I slot release: id 0 | task 6985 | stop processing: n_tokens = 746, truncated = 0 25.44.471.689 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 100548216704 25.44.471.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.214 MiB) 25.44.527.300 I slot launch_slot_: id 0 | task 7213 | processing task, is_child = 0 25.47.961.340 I slot print_timing: id 0 | task 7213 | prompt processing, n_tokens = 340, progress = 0.99, t = 3.43 s / 99.01 tokens per second 25.54.425.591 I slot print_timing: id 0 | task 7213 | prompt eval time = 4815.35 ms / 344 tokens ( 14.00 ms per token, 71.44 tokens per second) 25.54.425.596 I slot print_timing: id 0 | task 7213 | eval time = 5082.93 ms / 42 tokens ( 123.97 ms per token, 8.07 tokens per second) 25.54.425.596 I slot print_timing: id 0 | task 7213 | total time = 9898.28 ms / 386 tokens 25.54.425.597 I slot print_timing: id 0 | task 7213 | graphs reused = 6673 25.54.425.597 I slot print_timing: id 0 | task 7213 | graph reallocs = 0 / 0 (same size) / (changed size) 25.54.425.633 I slot release: id 0 | task 7213 | stop processing: n_tokens = 417, truncated = 0 25.54.430.564 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 100558177074 25.54.430.608 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1105.655 MiB) 25.54.549.662 I slot launch_slot_: id 0 | task 7258 | processing task, is_child = 0 25.57.985.915 I slot print_timing: id 0 | task 7258 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.44 s / 99.82 tokens per second 26.11.644.945 I slot print_timing: id 0 | task 7258 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 26.14.742.381 I slot print_timing: id 0 | task 7258 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 26.17.842.797 I slot print_timing: id 0 | task 7258 | n_gen = 150, tg = 8.07 t/s, tg_3s = 8.06 t/s 26.20.445.315 I slot print_timing: id 0 | task 7258 | prompt eval time = 4824.98 ms / 347 tokens ( 13.90 ms per token, 71.92 tokens per second) 26.20.445.320 I slot print_timing: id 0 | task 7258 | eval time = 21070.67 ms / 171 tokens ( 123.95 ms per token, 8.07 tokens per second) 26.20.445.321 I slot print_timing: id 0 | task 7258 | total time = 25895.64 ms / 518 tokens 26.20.445.321 I slot print_timing: id 0 | task 7258 | graphs reused = 6841 26.20.445.322 I slot print_timing: id 0 | task 7258 | graph reallocs = 0 / 0 (same size) / (changed size) 26.20.445.348 I slot release: id 0 | task 7258 | stop processing: n_tokens = 549, truncated = 0 26.20.452.071 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 100584196789 26.20.452.101 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.269 MiB) 26.20.590.759 I slot launch_slot_: id 0 | task 7432 | processing task, is_child = 0 26.24.404.798 I slot print_timing: id 0 | task 7432 | prompt processing, n_tokens = 397, progress = 0.99, t = 3.81 s / 104.09 tokens per second 26.38.077.110 I slot print_timing: id 0 | task 7432 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 26.41.176.012 I slot print_timing: id 0 | task 7432 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 26.41.299.921 I slot print_timing: id 0 | task 7432 | prompt eval time = 5213.43 ms / 401 tokens ( 13.00 ms per token, 76.92 tokens per second) 26.41.299.926 I slot print_timing: id 0 | task 7432 | eval time = 15495.73 ms / 126 tokens ( 123.97 ms per token, 8.07 tokens per second) 26.41.299.927 I slot print_timing: id 0 | task 7432 | total time = 20709.15 ms / 527 tokens 26.41.299.927 I slot print_timing: id 0 | task 7432 | graphs reused = 6964 26.41.299.928 I slot print_timing: id 0 | task 7432 | graph reallocs = 0 / 0 (same size) / (changed size) 26.41.299.980 I slot release: id 0 | task 7432 | stop processing: n_tokens = 558, truncated = 0 26.41.307.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 100605051421 26.41.307.267 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 26.41.342.409 I slot launch_slot_: id 0 | task 7561 | processing task, is_child = 0 26.45.530.518 I slot print_timing: id 0 | task 7561 | prompt processing, n_tokens = 452, progress = 0.99, t = 4.19 s / 107.92 tokens per second 26.59.581.033 I slot print_timing: id 0 | task 7561 | n_gen = 100, tg = 8.04 t/s, tg_3s = 8.12 t/s 27.01.440.509 I slot print_timing: id 0 | task 7561 | prompt eval time = 5927.28 ms / 456 tokens ( 13.00 ms per token, 76.93 tokens per second) 27.01.440.515 I slot print_timing: id 0 | task 7561 | eval time = 14170.81 ms / 115 tokens ( 124.31 ms per token, 8.04 tokens per second) 27.01.440.515 I slot print_timing: id 0 | task 7561 | total time = 20098.09 ms / 571 tokens 27.01.440.516 I slot print_timing: id 0 | task 7561 | graphs reused = 7076 27.01.440.516 I slot print_timing: id 0 | task 7561 | graph reallocs = 0 / 0 (same size) / (changed size) 27.01.440.558 I slot release: id 0 | task 7561 | stop processing: n_tokens = 602, truncated = 0 27.01.447.344 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 27.01.447.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 27.01.484.179 I slot launch_slot_: id 0 | task 7679 | processing task, is_child = 0 27.05.278.507 I slot print_timing: id 0 | task 7679 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.79 s / 105.95 tokens per second 27.19.287.798 I slot print_timing: id 0 | task 7679 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 27.20.775.138 I slot print_timing: id 0 | task 7679 | prompt eval time = 5524.25 ms / 406 tokens ( 13.61 ms per token, 73.49 tokens per second) 27.20.775.141 I slot print_timing: id 0 | task 7679 | eval time = 13766.70 ms / 112 tokens ( 124.02 ms per token, 8.06 tokens per second) 27.20.775.142 I slot print_timing: id 0 | task 7679 | total time = 19290.94 ms / 518 tokens 27.20.775.143 I slot print_timing: id 0 | task 7679 | graphs reused = 7185 27.20.775.143 I slot print_timing: id 0 | task 7679 | graph reallocs = 0 / 0 (same size) / (changed size) 27.20.775.187 I slot release: id 0 | task 7679 | stop processing: n_tokens = 549, truncated = 0 27.20.781.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 100644526628 27.20.781.646 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.205 MiB) 27.20.857.414 I slot launch_slot_: id 0 | task 7794 | processing task, is_child = 0 27.24.678.803 I slot print_timing: id 0 | task 7794 | prompt processing, n_tokens = 402, progress = 0.99, t = 3.82 s / 105.20 tokens per second 27.38.360.290 I slot print_timing: id 0 | task 7794 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 27.41.460.379 I slot print_timing: id 0 | task 7794 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 27.44.560.033 I slot print_timing: id 0 | task 7794 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.07 t/s 27.47.658.299 I slot print_timing: id 0 | task 7794 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.07 t/s 27.48.153.790 I slot print_timing: id 0 | task 7794 | prompt eval time = 5220.40 ms / 406 tokens ( 12.86 ms per token, 77.77 tokens per second) 27.48.153.793 I slot print_timing: id 0 | task 7794 | eval time = 22075.96 ms / 179 tokens ( 124.02 ms per token, 8.06 tokens per second) 27.48.153.794 I slot print_timing: id 0 | task 7794 | total time = 27296.36 ms / 585 tokens 27.48.153.794 I slot print_timing: id 0 | task 7794 | graphs reused = 7361 27.48.153.795 I slot print_timing: id 0 | task 7794 | graph reallocs = 0 / 0 (same size) / (changed size) 27.48.153.840 I slot release: id 0 | task 7794 | stop processing: n_tokens = 616, truncated = 0 27.48.160.591 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 616, t_last = 100671905281 27.48.160.624 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.021 MiB) 27.48.201.464 I slot launch_slot_: id 0 | task 7976 | processing task, is_child = 0 27.52.376.225 I slot print_timing: id 0 | task 7976 | prompt processing, n_tokens = 440, progress = 0.99, t = 4.17 s / 105.40 tokens per second 28.02.930.560 I slot print_timing: id 0 | task 7976 | prompt eval time = 5923.93 ms / 444 tokens ( 13.34 ms per token, 74.95 tokens per second) 28.02.930.565 I slot print_timing: id 0 | task 7976 | eval time = 8805.16 ms / 72 tokens ( 124.02 ms per token, 8.06 tokens per second) 28.02.930.566 I slot print_timing: id 0 | task 7976 | total time = 14729.09 ms / 516 tokens 28.02.930.566 I slot print_timing: id 0 | task 7976 | graphs reused = 7430 28.02.930.567 I slot print_timing: id 0 | task 7976 | graph reallocs = 0 / 0 (same size) / (changed size) 28.02.931.745 I slot release: id 0 | task 7976 | stop processing: n_tokens = 547, truncated = 0 28.02.937.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 547, t_last = 100686683187 28.02.937.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.959 MiB) 28.02.979.279 I slot launch_slot_: id 0 | task 8051 | processing task, is_child = 0 28.06.775.655 I slot print_timing: id 0 | task 8051 | prompt processing, n_tokens = 368, progress = 0.99, t = 3.80 s / 96.93 tokens per second 28.20.425.041 I slot print_timing: id 0 | task 8051 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 28.20.797.068 I slot print_timing: id 0 | task 8051 | prompt eval time = 5176.24 ms / 372 tokens ( 13.91 ms per token, 71.87 tokens per second) 28.20.797.073 I slot print_timing: id 0 | task 8051 | eval time = 12641.54 ms / 103 tokens ( 123.94 ms per token, 8.07 tokens per second) 28.20.797.074 I slot print_timing: id 0 | task 8051 | total time = 17817.78 ms / 475 tokens 28.20.797.074 I slot print_timing: id 0 | task 8051 | graphs reused = 7531 28.20.797.075 I slot print_timing: id 0 | task 8051 | graph reallocs = 0 / 0 (same size) / (changed size) 28.20.797.106 I slot release: id 0 | task 8051 | stop processing: n_tokens = 506, truncated = 0 28.20.804.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 100704548547 28.20.804.980 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.399 MiB) 28.20.827.869 I slot launch_slot_: id 0 | task 8157 | processing task, is_child = 0 28.25.000.988 I slot print_timing: id 0 | task 8157 | prompt processing, n_tokens = 450, progress = 0.99, t = 4.17 s / 107.83 tokens per second 28.39.038.060 I slot print_timing: id 0 | task 8157 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 28.42.136.757 I slot print_timing: id 0 | task 8157 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 28.45.234.577 I slot print_timing: id 0 | task 8157 | n_gen = 150, tg = 8.07 t/s, tg_3s = 8.07 t/s 28.48.334.338 I slot print_timing: id 0 | task 8157 | n_gen = 175, tg = 8.07 t/s, tg_3s = 8.07 t/s 28.51.435.346 I slot print_timing: id 0 | task 8157 | n_gen = 200, tg = 8.07 t/s, tg_3s = 8.06 t/s 28.54.536.415 I slot print_timing: id 0 | task 8157 | n_gen = 225, tg = 8.07 t/s, tg_3s = 8.06 t/s 28.55.156.471 I slot print_timing: id 0 | task 8157 | prompt eval time = 5934.76 ms / 454 tokens ( 13.07 ms per token, 76.50 tokens per second) 28.55.156.473 I slot print_timing: id 0 | task 8157 | eval time = 28393.82 ms / 230 tokens ( 123.99 ms per token, 8.07 tokens per second) 28.55.156.473 I slot print_timing: id 0 | task 8157 | total time = 34328.59 ms / 684 tokens 28.55.156.474 I slot print_timing: id 0 | task 8157 | graphs reused = 7758 28.55.156.474 I slot print_timing: id 0 | task 8157 | graph reallocs = 0 / 0 (same size) / (changed size) 28.55.156.520 I slot release: id 0 | task 8157 | stop processing: n_tokens = 715, truncated = 0 28.55.160.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 100738907961 28.55.161.006 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.829 MiB) 28.55.183.404 I slot launch_slot_: id 0 | task 8390 | processing task, is_child = 0 28.58.978.185 I slot print_timing: id 0 | task 8390 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.79 s / 92.23 tokens per second 29.12.260.239 I slot print_timing: id 0 | task 8390 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 29.15.358.363 I slot print_timing: id 0 | task 8390 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 29.18.461.922 I slot print_timing: id 0 | task 8390 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 29.21.560.329 I slot print_timing: id 0 | task 8390 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.07 t/s 29.24.658.223 I slot print_timing: id 0 | task 8390 | n_gen = 200, tg = 8.07 t/s, tg_3s = 8.07 t/s 29.27.756.673 I slot print_timing: id 0 | task 8390 | n_gen = 225, tg = 8.07 t/s, tg_3s = 8.07 t/s 29.30.607.750 I slot print_timing: id 0 | task 8390 | prompt eval time = 4800.81 ms / 354 tokens ( 13.56 ms per token, 73.74 tokens per second) 29.30.607.755 I slot print_timing: id 0 | task 8390 | eval time = 30623.53 ms / 248 tokens ( 123.98 ms per token, 8.07 tokens per second) 29.30.607.757 I slot print_timing: id 0 | task 8390 | total time = 35424.33 ms / 602 tokens 29.30.607.757 I slot print_timing: id 0 | task 8390 | graphs reused = 8003 29.30.607.758 I slot print_timing: id 0 | task 8390 | graph reallocs = 0 / 0 (same size) / (changed size) 29.30.607.804 I slot release: id 0 | task 8390 | stop processing: n_tokens = 633, truncated = 0 29.30.612.834 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 633, t_last = 100774359245 29.30.612.874 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 29.30.635.395 I slot launch_slot_: id 0 | task 8641 | processing task, is_child = 0 29.34.424.415 I slot print_timing: id 0 | task 8641 | prompt processing, n_tokens = 330, progress = 0.99, t = 3.79 s / 87.09 tokens per second 29.47.687.548 I slot print_timing: id 0 | task 8641 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 29.50.785.145 I slot print_timing: id 0 | task 8641 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 29.53.887.803 I slot print_timing: id 0 | task 8641 | n_gen = 150, tg = 8.07 t/s, tg_3s = 8.06 t/s 29.54.878.714 I slot print_timing: id 0 | task 8641 | prompt eval time = 4780.56 ms / 334 tokens ( 14.31 ms per token, 69.87 tokens per second) 29.54.878.720 I slot print_timing: id 0 | task 8641 | eval time = 19462.75 ms / 158 tokens ( 123.97 ms per token, 8.07 tokens per second) 29.54.878.721 I slot print_timing: id 0 | task 8641 | total time = 24243.31 ms / 492 tokens 29.54.878.721 I slot print_timing: id 0 | task 8641 | graphs reused = 8158 29.54.878.722 I slot print_timing: id 0 | task 8641 | graph reallocs = 0 / 0 (same size) / (changed size) 29.54.878.746 I slot release: id 0 | task 8641 | stop processing: n_tokens = 523, truncated = 0 29.54.886.035 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 523, t_last = 100798630187 29.54.886.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 29.54.910.646 I slot launch_slot_: id 0 | task 8802 | processing task, is_child = 0 29.59.099.332 I slot print_timing: id 0 | task 8802 | prompt processing, n_tokens = 422, progress = 0.99, t = 4.19 s / 100.75 tokens per second 30.12.775.098 I slot print_timing: id 0 | task 8802 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 30.15.873.687 I slot print_timing: id 0 | task 8802 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.07 t/s 30.18.974.629 I slot print_timing: id 0 | task 8802 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 30.22.074.624 I slot print_timing: id 0 | task 8802 | prompt eval time = 5581.72 ms / 426 tokens ( 13.10 ms per token, 76.32 tokens per second) 30.22.074.629 I slot print_timing: id 0 | task 8802 | eval time = 21582.24 ms / 175 tokens ( 124.04 ms per token, 8.06 tokens per second) 30.22.074.630 I slot print_timing: id 0 | task 8802 | total time = 27163.96 ms / 601 tokens 30.22.074.630 I slot print_timing: id 0 | task 8802 | graphs reused = 8330 30.22.074.631 I slot print_timing: id 0 | task 8802 | graph reallocs = 0 / 0 (same size) / (changed size) 30.22.074.671 I slot release: id 0 | task 8802 | stop processing: n_tokens = 632, truncated = 0 30.22.083.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 100825826113 30.22.083.947 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 30.22.107.708 I slot launch_slot_: id 0 | task 8980 | processing task, is_child = 0 30.25.910.582 I slot print_timing: id 0 | task 8980 | prompt processing, n_tokens = 362, progress = 0.99, t = 3.80 s / 95.19 tokens per second 30.39.197.016 I slot print_timing: id 0 | task 8980 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 30.41.307.143 I slot print_timing: id 0 | task 8980 | prompt eval time = 4810.07 ms / 366 tokens ( 13.14 ms per token, 76.09 tokens per second) 30.41.307.147 I slot print_timing: id 0 | task 8980 | eval time = 14389.35 ms / 117 tokens ( 124.05 ms per token, 8.06 tokens per second) 30.41.307.147 I slot print_timing: id 0 | task 8980 | total time = 19199.42 ms / 483 tokens 30.41.307.148 I slot print_timing: id 0 | task 8980 | graphs reused = 8444 30.41.307.148 I slot print_timing: id 0 | task 8980 | graph reallocs = 0 / 0 (same size) / (changed size) 30.41.307.193 I slot release: id 0 | task 8980 | stop processing: n_tokens = 514, truncated = 0 30.41.312.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 100845058634 30.41.312.275 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.082 MiB) 30.41.339.586 I slot launch_slot_: id 0 | task 9100 | processing task, is_child = 0 30.45.152.605 I slot print_timing: id 0 | task 9100 | prompt processing, n_tokens = 458, progress = 0.99, t = 3.81 s / 120.12 tokens per second 30.57.812.278 I slot print_timing: id 0 | task 9100 | prompt eval time = 5933.21 ms / 462 tokens ( 12.84 ms per token, 77.87 tokens per second) 30.57.812.284 I slot print_timing: id 0 | task 9100 | eval time = 10539.47 ms / 86 tokens ( 123.99 ms per token, 8.06 tokens per second) 30.57.812.284 I slot print_timing: id 0 | task 9100 | total time = 16472.68 ms / 548 tokens 30.57.812.285 I slot print_timing: id 0 | task 9100 | graphs reused = 8527 30.57.812.285 I slot print_timing: id 0 | task 9100 | graph reallocs = 0 / 0 (same size) / (changed size) 30.57.813.827 I slot release: id 0 | task 9100 | stop processing: n_tokens = 579, truncated = 0 30.57.819.820 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 100861565269 30.57.819.867 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.271 MiB) 30.57.843.063 I slot launch_slot_: id 0 | task 9189 | processing task, is_child = 0 31.01.283.364 I slot print_timing: id 0 | task 9189 | prompt processing, n_tokens = 392, progress = 0.99, t = 3.44 s / 113.94 tokens per second 31.15.308.131 I slot print_timing: id 0 | task 9189 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 31.18.407.569 I slot print_timing: id 0 | task 9189 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.07 t/s 31.21.506.448 I slot print_timing: id 0 | task 9189 | prompt eval time = 5186.82 ms / 396 tokens ( 13.10 ms per token, 76.35 tokens per second) 31.21.506.453 I slot print_timing: id 0 | task 9189 | eval time = 18476.55 ms / 150 tokens ( 124.00 ms per token, 8.06 tokens per second) 31.21.506.453 I slot print_timing: id 0 | task 9189 | total time = 23663.37 ms / 546 tokens 31.21.506.454 I slot print_timing: id 0 | task 9189 | graphs reused = 8674 31.21.506.454 I slot print_timing: id 0 | task 9189 | graph reallocs = 0 / 0 (same size) / (changed size) 31.21.506.489 I slot release: id 0 | task 9189 | stop processing: n_tokens = 577, truncated = 0 31.21.511.776 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 577, t_last = 100885257930 31.21.511.817 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.957 MiB) 31.21.533.786 I slot launch_slot_: id 0 | task 9342 | processing task, is_child = 0 31.26.052.965 I slot print_timing: id 0 | task 9342 | prompt processing, n_tokens = 454, progress = 0.99, t = 4.52 s / 100.46 tokens per second 31.40.066.319 I slot print_timing: id 0 | task 9342 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 31.43.165.000 I slot print_timing: id 0 | task 9342 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.07 t/s 31.46.265.645 I slot print_timing: id 0 | task 9342 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 31.47.629.447 I slot print_timing: id 0 | task 9342 | prompt eval time = 6251.79 ms / 458 tokens ( 13.65 ms per token, 73.26 tokens per second) 31.47.629.452 I slot print_timing: id 0 | task 9342 | eval time = 19843.85 ms / 161 tokens ( 124.02 ms per token, 8.06 tokens per second) 31.47.629.453 I slot print_timing: id 0 | task 9342 | total time = 26095.64 ms / 619 tokens 31.47.629.453 I slot print_timing: id 0 | task 9342 | graphs reused = 8832 31.47.629.454 I slot print_timing: id 0 | task 9342 | graph reallocs = 0 / 0 (same size) / (changed size) 31.47.629.496 I slot release: id 0 | task 9342 | stop processing: n_tokens = 650, truncated = 0 31.47.634.424 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 100911380937 31.47.634.461 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.394 MiB) 31.47.667.808 I slot launch_slot_: id 0 | task 9506 | processing task, is_child = 0 31.51.464.809 I slot print_timing: id 0 | task 9506 | prompt processing, n_tokens = 454, progress = 0.99, t = 3.80 s / 119.57 tokens per second 32.02.167.304 I slot print_timing: id 0 | task 9506 | prompt eval time = 5925.99 ms / 458 tokens ( 12.94 ms per token, 77.29 tokens per second) 32.02.167.309 I slot print_timing: id 0 | task 9506 | eval time = 8573.49 ms / 70 tokens ( 124.25 ms per token, 8.05 tokens per second) 32.02.167.310 I slot print_timing: id 0 | task 9506 | total time = 14499.49 ms / 528 tokens 32.02.167.310 I slot print_timing: id 0 | task 9506 | graphs reused = 8899 32.02.167.311 I slot print_timing: id 0 | task 9506 | graph reallocs = 0 / 0 (same size) / (changed size) 32.02.167.341 I slot release: id 0 | task 9506 | stop processing: n_tokens = 559, truncated = 0 32.02.171.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 559, t_last = 100925918782 32.02.171.827 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 942.461 MiB) 32.02.193.980 I slot launch_slot_: id 0 | task 9579 | processing task, is_child = 0 32.06.380.734 I slot print_timing: id 0 | task 9579 | prompt processing, n_tokens = 448, progress = 0.99, t = 4.19 s / 107.00 tokens per second 32.20.415.146 I slot print_timing: id 0 | task 9579 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 32.23.515.085 I slot print_timing: id 0 | task 9579 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.06 t/s 32.26.614.802 I slot print_timing: id 0 | task 9579 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.07 t/s 32.29.715.562 I slot print_timing: id 0 | task 9579 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.06 t/s 32.32.817.650 I slot print_timing: id 0 | task 9579 | n_gen = 200, tg = 8.06 t/s, tg_3s = 8.06 t/s 32.35.919.209 I slot print_timing: id 0 | task 9579 | n_gen = 225, tg = 8.06 t/s, tg_3s = 8.06 t/s 32.38.277.783 I slot print_timing: id 0 | task 9579 | prompt eval time = 5925.60 ms / 452 tokens ( 13.11 ms per token, 76.28 tokens per second) 32.38.277.789 I slot print_timing: id 0 | task 9579 | eval time = 30158.20 ms / 244 tokens ( 124.11 ms per token, 8.06 tokens per second) 32.38.277.789 I slot print_timing: id 0 | task 9579 | total time = 36083.79 ms / 696 tokens 32.38.277.790 I slot print_timing: id 0 | task 9579 | graphs reused = 9140 32.38.277.790 I slot print_timing: id 0 | task 9579 | graph reallocs = 0 / 0 (same size) / (changed size) 32.38.277.817 I slot release: id 0 | task 9579 | stop processing: n_tokens = 727, truncated = 0 32.38.282.990 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 727, t_last = 100962029258 32.38.283.032 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.334 MiB) 32.38.305.901 I slot launch_slot_: id 0 | task 9826 | processing task, is_child = 0 32.42.099.499 I slot print_timing: id 0 | task 9826 | prompt processing, n_tokens = 400, progress = 0.99, t = 3.79 s / 105.44 tokens per second 32.56.109.982 I slot print_timing: id 0 | task 9826 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 32.59.208.583 I slot print_timing: id 0 | task 9826 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 32.59.952.258 I slot print_timing: id 0 | task 9826 | prompt eval time = 5527.99 ms / 404 tokens ( 13.68 ms per token, 73.08 tokens per second) 32.59.952.260 I slot print_timing: id 0 | task 9826 | eval time = 16118.36 ms / 131 tokens ( 123.99 ms per token, 8.07 tokens per second) 32.59.952.261 I slot print_timing: id 0 | task 9826 | total time = 21646.35 ms / 535 tokens 32.59.952.262 I slot print_timing: id 0 | task 9826 | graphs reused = 9268 32.59.952.262 I slot print_timing: id 0 | task 9826 | graph reallocs = 0 / 0 (same size) / (changed size) 32.59.952.297 I slot release: id 0 | task 9826 | stop processing: n_tokens = 566, truncated = 0 32.59.956.951 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 100983703738 32.59.956.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.457 MiB) 32.59.979.825 I slot launch_slot_: id 0 | task 9960 | processing task, is_child = 0 33.03.774.525 I slot print_timing: id 0 | task 9960 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.79 s / 89.86 tokens per second 33.17.054.045 I slot print_timing: id 0 | task 9960 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 33.17.797.980 I slot print_timing: id 0 | task 9960 | prompt eval time = 4794.94 ms / 345 tokens ( 13.90 ms per token, 71.95 tokens per second) 33.17.797.983 I slot print_timing: id 0 | task 9960 | eval time = 13023.20 ms / 106 tokens ( 124.03 ms per token, 8.06 tokens per second) 33.17.797.984 I slot print_timing: id 0 | task 9960 | total time = 17818.15 ms / 451 tokens 33.17.797.984 I slot print_timing: id 0 | task 9960 | graphs reused = 9372 33.17.797.985 I slot print_timing: id 0 | task 9960 | graph reallocs = 0 / 0 (same size) / (changed size) 33.17.798.017 I slot release: id 0 | task 9960 | stop processing: n_tokens = 482, truncated = 0 33.17.803.329 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 101001549458 33.17.803.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.272 MiB) 33.17.825.460 I slot launch_slot_: id 0 | task 10069 | processing task, is_child = 0 33.21.613.422 I slot print_timing: id 0 | task 10069 | prompt processing, n_tokens = 426, progress = 0.99, t = 3.79 s / 112.46 tokens per second 33.36.010.145 I slot print_timing: id 0 | task 10069 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 33.39.108.469 I slot print_timing: id 0 | task 10069 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.07 t/s 33.39.356.332 I slot print_timing: id 0 | task 10069 | prompt eval time = 5903.73 ms / 430 tokens ( 13.73 ms per token, 72.84 tokens per second) 33.39.356.337 I slot print_timing: id 0 | task 10069 | eval time = 15627.12 ms / 127 tokens ( 124.02 ms per token, 8.06 tokens per second) 33.39.356.337 I slot print_timing: id 0 | task 10069 | total time = 21530.86 ms / 557 tokens 33.39.356.338 I slot print_timing: id 0 | task 10069 | graphs reused = 9496 33.39.356.338 I slot print_timing: id 0 | task 10069 | graph reallocs = 0 / 0 (same size) / (changed size) 33.39.356.363 I slot release: id 0 | task 10069 | stop processing: n_tokens = 588, truncated = 0 33.39.361.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 588, t_last = 101023107805 33.39.361.318 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.894 MiB) 33.39.395.068 I slot launch_slot_: id 0 | task 10199 | processing task, is_child = 0 33.42.829.971 I slot print_timing: id 0 | task 10199 | prompt processing, n_tokens = 312, progress = 0.99, t = 3.43 s / 90.83 tokens per second 33.54.256.447 I slot print_timing: id 0 | task 10199 | prompt eval time = 4434.22 ms / 316 tokens ( 14.03 ms per token, 71.26 tokens per second) 33.54.256.450 I slot print_timing: id 0 | task 10199 | eval time = 10427.15 ms / 85 tokens ( 124.13 ms per token, 8.06 tokens per second) 33.54.256.451 I slot print_timing: id 0 | task 10199 | total time = 14861.36 ms / 401 tokens 33.54.256.451 I slot print_timing: id 0 | task 10199 | graphs reused = 9579 33.54.256.452 I slot print_timing: id 0 | task 10199 | graph reallocs = 0 / 0 (same size) / (changed size) 33.54.256.475 I slot release: id 0 | task 10199 | stop processing: n_tokens = 432, truncated = 0 33.54.262.908 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 101038007916 33.54.262.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.958 MiB) 33.54.284.706 I slot launch_slot_: id 0 | task 10287 | processing task, is_child = 0 33.58.069.407 I slot print_timing: id 0 | task 10287 | prompt processing, n_tokens = 350, progress = 0.99, t = 3.78 s / 92.48 tokens per second 34.11.361.046 I slot print_timing: id 0 | task 10287 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 34.12.228.528 I slot print_timing: id 0 | task 10287 | prompt eval time = 4798.63 ms / 354 tokens ( 13.56 ms per token, 73.77 tokens per second) 34.12.228.533 I slot print_timing: id 0 | task 10287 | eval time = 13145.18 ms / 107 tokens ( 124.01 ms per token, 8.06 tokens per second) 34.12.228.534 I slot print_timing: id 0 | task 10287 | total time = 17943.81 ms / 461 tokens 34.12.228.534 I slot print_timing: id 0 | task 10287 | graphs reused = 9684 34.12.228.535 I slot print_timing: id 0 | task 10287 | graph reallocs = 0 / 0 (same size) / (changed size) 34.12.228.560 I slot release: id 0 | task 10287 | stop processing: n_tokens = 492, truncated = 0 34.12.236.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 101055980001 34.12.236.351 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.833 MiB) 34.12.259.030 I slot launch_slot_: id 0 | task 10397 | processing task, is_child = 0 34.17.170.292 I slot print_timing: id 0 | task 10397 | prompt processing, n_tokens = 434, progress = 0.99, t = 4.91 s / 88.37 tokens per second 34.30.445.198 I slot print_timing: id 0 | task 10397 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 34.32.554.340 I slot print_timing: id 0 | task 10397 | prompt eval time = 5911.24 ms / 438 tokens ( 13.50 ms per token, 74.10 tokens per second) 34.32.554.346 I slot print_timing: id 0 | task 10397 | eval time = 14384.06 ms / 117 tokens ( 124.00 ms per token, 8.06 tokens per second) 34.32.554.346 I slot print_timing: id 0 | task 10397 | total time = 20295.30 ms / 555 tokens 34.32.554.347 I slot print_timing: id 0 | task 10397 | graphs reused = 9798 34.32.554.347 I slot print_timing: id 0 | task 10397 | graph reallocs = 0 / 0 (same size) / (changed size) 34.32.554.375 I slot release: id 0 | task 10397 | stop processing: n_tokens = 586, truncated = 0 34.32.558.969 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 101076305816 34.32.559.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 938.397 MiB) 34.32.580.956 I slot launch_slot_: id 0 | task 10517 | processing task, is_child = 0 34.37.864.093 I slot print_timing: id 0 | task 10517 | prompt processing, n_tokens = 453, progress = 0.99, t = 5.28 s / 85.74 tokens per second 34.47.414.685 I slot print_timing: id 0 | task 10517 | prompt eval time = 6275.24 ms / 457 tokens ( 13.73 ms per token, 72.83 tokens per second) 34.47.414.693 I slot print_timing: id 0 | task 10517 | eval time = 8558.48 ms / 70 tokens ( 124.04 ms per token, 8.06 tokens per second) 34.47.414.694 I slot print_timing: id 0 | task 10517 | total time = 14833.72 ms / 527 tokens 34.47.414.695 I slot print_timing: id 0 | task 10517 | graphs reused = 9865 34.47.414.696 I slot print_timing: id 0 | task 10517 | graph reallocs = 0 / 0 (same size) / (changed size) 34.47.414.749 I slot release: id 0 | task 10517 | stop processing: n_tokens = 558, truncated = 0 34.47.423.724 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 101091166190 34.47.423.775 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.707 MiB) 34.47.455.155 I slot launch_slot_: id 0 | task 10590 | processing task, is_child = 0 34.52.381.145 I slot print_timing: id 0 | task 10590 | prompt processing, n_tokens = 469, progress = 0.99, t = 4.93 s / 95.21 tokens per second 35.05.795.147 I slot print_timing: id 0 | task 10590 | prompt eval time = 6309.71 ms / 473 tokens ( 13.34 ms per token, 74.96 tokens per second) 35.05.795.154 I slot print_timing: id 0 | task 10590 | eval time = 12030.26 ms / 98 tokens ( 124.02 ms per token, 8.06 tokens per second) 35.05.795.154 I slot print_timing: id 0 | task 10590 | total time = 18339.98 ms / 571 tokens 35.05.795.155 I slot print_timing: id 0 | task 10590 | graphs reused = 9960 35.05.795.155 I slot print_timing: id 0 | task 10590 | graph reallocs = 0 / 0 (same size) / (changed size) 35.05.795.196 I slot release: id 0 | task 10590 | stop processing: n_tokens = 602, truncated = 0 35.05.799.950 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 602, t_last = 101109546637 35.05.799.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 943.211 MiB) 35.05.821.943 I slot launch_slot_: id 0 | task 10691 | processing task, is_child = 0 35.11.113.626 I slot print_timing: id 0 | task 10691 | prompt processing, n_tokens = 472, progress = 0.99, t = 5.29 s / 89.20 tokens per second 35.15.349.518 I slot print_timing: id 0 | task 10691 | prompt eval time = 6295.32 ms / 476 tokens ( 13.23 ms per token, 75.61 tokens per second) 35.15.349.520 I slot print_timing: id 0 | task 10691 | eval time = 3232.24 ms / 27 tokens ( 124.32 ms per token, 8.04 tokens per second) 35.15.349.521 I slot print_timing: id 0 | task 10691 | total time = 9527.56 ms / 503 tokens 35.15.349.521 I slot print_timing: id 0 | task 10691 | graphs reused = 9984 35.15.349.522 I slot print_timing: id 0 | task 10691 | graph reallocs = 0 / 0 (same size) / (changed size) 35.15.349.573 I slot release: id 0 | task 10691 | stop processing: n_tokens = 534, truncated = 0 35.15.354.298 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 101119101014 35.15.354.332 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.145 MiB) 35.15.376.909 I slot launch_slot_: id 0 | task 10721 | processing task, is_child = 0 35.20.284.621 I slot print_timing: id 0 | task 10721 | prompt processing, n_tokens = 462, progress = 0.99, t = 4.91 s / 94.14 tokens per second 35.33.946.716 I slot print_timing: id 0 | task 10721 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 35.34.815.127 I slot print_timing: id 0 | task 10721 | prompt eval time = 6294.90 ms / 466 tokens ( 13.51 ms per token, 74.03 tokens per second) 35.34.815.130 I slot print_timing: id 0 | task 10721 | eval time = 13143.30 ms / 107 tokens ( 123.99 ms per token, 8.06 tokens per second) 35.34.815.130 I slot print_timing: id 0 | task 10721 | total time = 19438.20 ms / 573 tokens 35.34.815.131 I slot print_timing: id 0 | task 10721 | graphs reused = 10088 35.34.815.131 I slot print_timing: id 0 | task 10721 | graph reallocs = 0 / 0 (same size) / (changed size) 35.34.815.187 I slot release: id 0 | task 10721 | stop processing: n_tokens = 604, truncated = 0 35.34.821.361 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 101138566628 35.34.821.392 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.893 MiB) 35.34.844.858 I slot launch_slot_: id 0 | task 10831 | processing task, is_child = 0 35.39.381.509 I slot print_timing: id 0 | task 10831 | prompt processing, n_tokens = 411, progress = 0.99, t = 4.54 s / 90.60 tokens per second 35.49.922.511 I slot print_timing: id 0 | task 10831 | prompt eval time = 5528.24 ms / 415 tokens ( 13.32 ms per token, 75.07 tokens per second) 35.49.922.517 I slot print_timing: id 0 | task 10831 | eval time = 9549.39 ms / 78 tokens ( 124.02 ms per token, 8.06 tokens per second) 35.49.922.518 I slot print_timing: id 0 | task 10831 | total time = 15077.64 ms / 493 tokens 35.49.922.519 I slot print_timing: id 0 | task 10831 | graphs reused = 10163 35.49.922.519 I slot print_timing: id 0 | task 10831 | graph reallocs = 0 / 0 (same size) / (changed size) 35.49.922.546 I slot release: id 0 | task 10831 | stop processing: n_tokens = 524, truncated = 0 35.49.927.876 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 101153673987 35.49.927.916 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.521 MiB) 35.49.949.862 I slot launch_slot_: id 0 | task 10912 | processing task, is_child = 0 35.53.758.298 I slot print_timing: id 0 | task 10912 | prompt processing, n_tokens = 348, progress = 0.99, t = 3.81 s / 91.38 tokens per second 36.07.036.779 I slot print_timing: id 0 | task 10912 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 36.10.135.351 I slot print_timing: id 0 | task 10912 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.07 t/s 36.10.507.279 I slot print_timing: id 0 | task 10912 | prompt eval time = 4802.05 ms / 352 tokens ( 13.64 ms per token, 73.30 tokens per second) 36.10.507.288 I slot print_timing: id 0 | task 10912 | eval time = 15755.35 ms / 128 tokens ( 124.06 ms per token, 8.06 tokens per second) 36.10.507.290 I slot print_timing: id 0 | task 10912 | total time = 20557.40 ms / 480 tokens 36.10.507.290 I slot print_timing: id 0 | task 10912 | graphs reused = 10289 36.10.507.290 I slot print_timing: id 0 | task 10912 | graph reallocs = 0 / 0 (same size) / (changed size) 36.10.507.322 I slot release: id 0 | task 10912 | stop processing: n_tokens = 511, truncated = 0 36.10.514.382 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 511, t_last = 101174258763 36.10.514.412 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 924.767 MiB) 36.10.535.970 I slot launch_slot_: id 0 | task 11043 | processing task, is_child = 0 36.17.016.076 I slot print_timing: id 0 | task 11043 | prompt processing, n_tokens = 546, progress = 0.99, t = 6.48 s / 84.26 tokens per second 36.30.299.103 I slot print_timing: id 0 | task 11043 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 36.33.402.230 I slot print_timing: id 0 | task 11043 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 36.34.394.871 I slot print_timing: id 0 | task 11043 | prompt eval time = 7483.84 ms / 550 tokens ( 13.61 ms per token, 73.49 tokens per second) 36.34.394.874 I slot print_timing: id 0 | task 11043 | eval time = 16375.05 ms / 133 tokens ( 124.05 ms per token, 8.06 tokens per second) 36.34.394.874 I slot print_timing: id 0 | task 11043 | total time = 23858.89 ms / 683 tokens 36.34.394.875 I slot print_timing: id 0 | task 11043 | graphs reused = 10420 36.34.394.875 I slot print_timing: id 0 | task 11043 | graph reallocs = 0 / 0 (same size) / (changed size) 36.34.394.918 I slot release: id 0 | task 11043 | stop processing: n_tokens = 714, truncated = 0 36.34.403.571 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 101198146359 36.34.403.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.518 MiB) 36.34.429.182 I slot launch_slot_: id 0 | task 11180 | processing task, is_child = 0 36.37.469.426 I slot print_timing: id 0 | task 11180 | prompt processing, n_tokens = 586, progress = 0.77, t = 3.04 s / 192.75 tokens per second 36.41.642.074 I slot print_timing: id 0 | task 11180 | prompt processing, n_tokens = 768, progress = 1.00, t = 7.21 s / 106.48 tokens per second 36.56.443.219 I slot print_timing: id 0 | task 11180 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 36.59.548.099 I slot print_timing: id 0 | task 11180 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 37.02.653.849 I slot print_timing: id 0 | task 11180 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.05 t/s 37.05.759.201 I slot print_timing: id 0 | task 11180 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 37.08.863.753 I slot print_timing: id 0 | task 11180 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 37.11.972.544 I slot print_timing: id 0 | task 11180 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.04 t/s 37.14.830.481 I slot print_timing: id 0 | task 11180 | prompt eval time = 9719.34 ms / 772 tokens ( 12.59 ms per token, 79.43 tokens per second) 37.14.830.484 I slot print_timing: id 0 | task 11180 | eval time = 30681.95 ms / 248 tokens ( 124.22 ms per token, 8.05 tokens per second) 37.14.830.484 I slot print_timing: id 0 | task 11180 | total time = 40401.29 ms / 1020 tokens 37.14.830.485 I slot print_timing: id 0 | task 11180 | graphs reused = 10665 37.14.830.486 I slot print_timing: id 0 | task 11180 | graph reallocs = 0 / 0 (same size) / (changed size) 37.14.830.953 I slot release: id 0 | task 11180 | stop processing: n_tokens = 1051, truncated = 0 37.14.836.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1051, t_last = 101238582394 37.14.836.764 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.396 MiB) 37.14.889.667 I slot launch_slot_: id 0 | task 11432 | processing task, is_child = 0 37.22.104.967 I slot print_timing: id 0 | task 11432 | prompt processing, n_tokens = 679, progress = 0.99, t = 7.22 s / 94.11 tokens per second 37.36.140.650 I slot print_timing: id 0 | task 11432 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.14 t/s 37.39.243.351 I slot print_timing: id 0 | task 11432 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.06 t/s 37.42.345.984 I slot print_timing: id 0 | task 11432 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 37.45.453.272 I slot print_timing: id 0 | task 11432 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 37.46.197.858 I slot print_timing: id 0 | task 11432 | prompt eval time = 8959.33 ms / 683 tokens ( 13.12 ms per token, 76.23 tokens per second) 37.46.197.861 I slot print_timing: id 0 | task 11432 | eval time = 22348.85 ms / 181 tokens ( 124.16 ms per token, 8.05 tokens per second) 37.46.197.861 I slot print_timing: id 0 | task 11432 | total time = 31308.18 ms / 864 tokens 37.46.197.862 I slot print_timing: id 0 | task 11432 | graphs reused = 10843 37.46.197.862 I slot print_timing: id 0 | task 11432 | graph reallocs = 0 / 0 (same size) / (changed size) 37.46.197.894 I slot release: id 0 | task 11432 | stop processing: n_tokens = 895, truncated = 0 37.46.203.962 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 895, t_last = 101269949335 37.46.204.003 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.645 MiB) 37.46.229.698 I slot launch_slot_: id 0 | task 11617 | processing task, is_child = 0 37.51.961.525 I slot print_timing: id 0 | task 11617 | prompt processing, n_tokens = 575, progress = 0.99, t = 5.73 s / 100.32 tokens per second 38.06.007.866 I slot print_timing: id 0 | task 11617 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 38.09.116.506 I slot print_timing: id 0 | task 11617 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.04 t/s 38.12.218.765 I slot print_timing: id 0 | task 11617 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.06 t/s 38.15.324.669 I slot print_timing: id 0 | task 11617 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 38.18.427.884 I slot print_timing: id 0 | task 11617 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.06 t/s 38.21.533.624 I slot print_timing: id 0 | task 11617 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.05 t/s 38.23.520.538 I slot print_timing: id 0 | task 11617 | prompt eval time = 7490.83 ms / 579 tokens ( 12.94 ms per token, 77.29 tokens per second) 38.23.520.540 I slot print_timing: id 0 | task 11617 | eval time = 29800.00 ms / 241 tokens ( 124.17 ms per token, 8.05 tokens per second) 38.23.520.541 I slot print_timing: id 0 | task 11617 | total time = 37290.83 ms / 820 tokens 38.23.520.541 I slot print_timing: id 0 | task 11617 | graphs reused = 11081 38.23.520.542 I slot print_timing: id 0 | task 11617 | graph reallocs = 0 / 0 (same size) / (changed size) 38.23.520.574 I slot release: id 0 | task 11617 | stop processing: n_tokens = 851, truncated = 0 38.23.525.686 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 851, t_last = 101307272015 38.23.525.728 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.396 MiB) 38.24.183.567 I slot launch_slot_: id 0 | task 11862 | processing task, is_child = 0 38.29.855.639 I slot print_timing: id 0 | task 11862 | prompt processing, n_tokens = 496, progress = 0.99, t = 5.67 s / 87.45 tokens per second 38.43.134.378 I slot print_timing: id 0 | task 11862 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 38.43.878.707 I slot print_timing: id 0 | task 11862 | prompt eval time = 6676.43 ms / 500 tokens ( 13.35 ms per token, 74.89 tokens per second) 38.43.878.718 I slot print_timing: id 0 | task 11862 | eval time = 13018.70 ms / 106 tokens ( 123.99 ms per token, 8.07 tokens per second) 38.43.878.720 I slot print_timing: id 0 | task 11862 | total time = 19695.13 ms / 606 tokens 38.43.878.722 I slot print_timing: id 0 | task 11862 | graphs reused = 11185 38.43.878.724 I slot print_timing: id 0 | task 11862 | graph reallocs = 0 / 0 (same size) / (changed size) 38.43.878.756 I slot release: id 0 | task 11862 | stop processing: n_tokens = 637, truncated = 0 38.43.886.095 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 101327630197 38.43.886.128 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 931.144 MiB) 38.43.990.867 I slot launch_slot_: id 0 | task 11971 | processing task, is_child = 0 38.47.410.161 I slot print_timing: id 0 | task 11971 | prompt processing, n_tokens = 613, progress = 0.80, t = 3.42 s / 179.28 tokens per second 38.51.923.347 I slot print_timing: id 0 | task 11971 | prompt processing, n_tokens = 772, progress = 1.00, t = 7.93 s / 97.32 tokens per second 39.06.364.674 I slot print_timing: id 0 | task 11971 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 39.09.467.903 I slot print_timing: id 0 | task 11971 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.06 t/s 39.12.571.493 I slot print_timing: id 0 | task 11971 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.06 t/s 39.15.675.539 I slot print_timing: id 0 | task 11971 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 39.18.780.068 I slot print_timing: id 0 | task 11971 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 39.21.392.202 I slot print_timing: id 0 | task 11971 | prompt eval time = 10076.74 ms / 776 tokens ( 12.99 ms per token, 77.01 tokens per second) 39.21.392.207 I slot print_timing: id 0 | task 11971 | eval time = 27324.58 ms / 221 tokens ( 124.20 ms per token, 8.05 tokens per second) 39.21.392.208 I slot print_timing: id 0 | task 11971 | total time = 37401.32 ms / 997 tokens 39.21.392.208 I slot print_timing: id 0 | task 11971 | graphs reused = 11403 39.21.392.209 I slot print_timing: id 0 | task 11971 | graph reallocs = 0 / 0 (same size) / (changed size) 39.21.392.284 I slot release: id 0 | task 11971 | stop processing: n_tokens = 1028, truncated = 0 39.21.399.156 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1028, t_last = 101365143725 39.21.399.206 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.521 MiB) 39.21.399.240 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.519 MiB) 39.22.197.322 I slot launch_slot_: id 0 | task 12196 | processing task, is_child = 0 39.27.503.430 I slot print_timing: id 0 | task 12196 | prompt processing, n_tokens = 500, progress = 0.99, t = 5.31 s / 94.23 tokens per second 39.38.686.361 I slot print_timing: id 0 | task 12196 | prompt eval time = 6690.84 ms / 504 tokens ( 13.28 ms per token, 75.33 tokens per second) 39.38.686.367 I slot print_timing: id 0 | task 12196 | eval time = 9798.18 ms / 80 tokens ( 124.03 ms per token, 8.06 tokens per second) 39.38.686.367 I slot print_timing: id 0 | task 12196 | total time = 16489.02 ms / 584 tokens 39.38.686.368 I slot print_timing: id 0 | task 12196 | graphs reused = 11481 39.38.686.368 I slot print_timing: id 0 | task 12196 | graph reallocs = 0 / 0 (same size) / (changed size) 39.38.686.431 I slot release: id 0 | task 12196 | stop processing: n_tokens = 615, truncated = 0 39.38.696.280 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 101382437872 39.38.696.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.706 MiB) 39.38.843.437 I slot launch_slot_: id 0 | task 12279 | processing task, is_child = 0 39.45.315.716 I slot print_timing: id 0 | task 12279 | prompt processing, n_tokens = 629, progress = 0.99, t = 6.47 s / 97.18 tokens per second 39.59.365.892 I slot print_timing: id 0 | task 12279 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 40.02.471.910 I slot print_timing: id 0 | task 12279 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 40.05.576.328 I slot print_timing: id 0 | task 12279 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.05 t/s 40.08.680.606 I slot print_timing: id 0 | task 12279 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 40.11.784.357 I slot print_timing: id 0 | task 12279 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 40.12.653.337 I slot print_timing: id 0 | task 12279 | prompt eval time = 8227.34 ms / 633 tokens ( 13.00 ms per token, 76.94 tokens per second) 40.12.653.339 I slot print_timing: id 0 | task 12279 | eval time = 25582.55 ms / 207 tokens ( 124.19 ms per token, 8.05 tokens per second) 40.12.653.340 I slot print_timing: id 0 | task 12279 | total time = 33809.89 ms / 840 tokens 40.12.653.340 I slot print_timing: id 0 | task 12279 | graphs reused = 11685 40.12.653.341 I slot print_timing: id 0 | task 12279 | graph reallocs = 0 / 0 (same size) / (changed size) 40.12.653.397 I slot release: id 0 | task 12279 | stop processing: n_tokens = 871, truncated = 0 40.12.659.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 101416404838 40.12.659.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1092.025 MiB) 40.12.845.262 I slot launch_slot_: id 0 | task 12490 | processing task, is_child = 0 40.17.040.734 I slot print_timing: id 0 | task 12490 | prompt processing, n_tokens = 391, progress = 0.99, t = 4.20 s / 93.20 tokens per second 40.29.583.712 I slot print_timing: id 0 | task 12490 | prompt eval time = 5203.11 ms / 395 tokens ( 13.17 ms per token, 75.92 tokens per second) 40.29.583.715 I slot print_timing: id 0 | task 12490 | eval time = 11535.32 ms / 94 tokens ( 124.04 ms per token, 8.06 tokens per second) 40.29.583.716 I slot print_timing: id 0 | task 12490 | total time = 16738.44 ms / 489 tokens 40.29.583.716 I slot print_timing: id 0 | task 12490 | graphs reused = 11776 40.29.583.717 I slot print_timing: id 0 | task 12490 | graph reallocs = 0 / 0 (same size) / (changed size) 40.29.583.760 I slot release: id 0 | task 12490 | stop processing: n_tokens = 520, truncated = 0 40.29.588.881 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 101433335201 40.29.588.910 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1113.095 MiB) 40.29.730.948 I slot launch_slot_: id 0 | task 12587 | processing task, is_child = 0 40.35.860.328 I slot print_timing: id 0 | task 12587 | prompt processing, n_tokens = 580, progress = 0.99, t = 6.13 s / 94.63 tokens per second 40.49.889.605 I slot print_timing: id 0 | task 12587 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 40.52.994.007 I slot print_timing: id 0 | task 12587 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 40.56.099.692 I slot print_timing: id 0 | task 12587 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.05 t/s 40.59.206.441 I slot print_timing: id 0 | task 12587 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 41.02.310.272 I slot print_timing: id 0 | task 12587 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 41.04.918.408 I slot print_timing: id 0 | task 12587 | prompt eval time = 7863.61 ms / 584 tokens ( 13.47 ms per token, 74.27 tokens per second) 41.04.918.411 I slot print_timing: id 0 | task 12587 | eval time = 27323.83 ms / 221 tokens ( 124.20 ms per token, 8.05 tokens per second) 41.04.918.411 I slot print_timing: id 0 | task 12587 | total time = 35187.44 ms / 805 tokens 41.04.918.412 I slot print_timing: id 0 | task 12587 | graphs reused = 11994 41.04.918.412 I slot print_timing: id 0 | task 12587 | graph reallocs = 0 / 0 (same size) / (changed size) 41.04.918.475 I slot release: id 0 | task 12587 | stop processing: n_tokens = 836, truncated = 0 41.04.925.696 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 836, t_last = 101468669916 41.04.925.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1103.341 MiB) 41.05.117.713 I slot launch_slot_: id 0 | task 12812 | processing task, is_child = 0 41.11.619.140 I slot print_timing: id 0 | task 12812 | prompt processing, n_tokens = 691, progress = 0.99, t = 6.50 s / 106.28 tokens per second 41.26.413.559 I slot print_timing: id 0 | task 12812 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 41.29.518.253 I slot print_timing: id 0 | task 12812 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 41.32.621.861 I slot print_timing: id 0 | task 12812 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.06 t/s 41.35.725.372 I slot print_timing: id 0 | task 12812 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.06 t/s 41.38.829.139 I slot print_timing: id 0 | task 12812 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 41.41.934.289 I slot print_timing: id 0 | task 12812 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.05 t/s 41.45.039.271 I slot print_timing: id 0 | task 12812 | n_gen = 250, tg = 8.05 t/s, tg_3s = 8.05 t/s 41.46.032.802 I slot print_timing: id 0 | task 12812 | prompt eval time = 8999.37 ms / 695 tokens ( 12.95 ms per token, 77.23 tokens per second) 41.46.032.808 I slot print_timing: id 0 | task 12812 | eval time = 31915.71 ms / 258 tokens ( 124.19 ms per token, 8.05 tokens per second) 41.46.032.808 I slot print_timing: id 0 | task 12812 | total time = 40915.08 ms / 953 tokens 41.46.032.809 I slot print_timing: id 0 | task 12812 | graphs reused = 12249 41.46.032.809 I slot print_timing: id 0 | task 12812 | graph reallocs = 0 / 0 (same size) / (changed size) 41.46.032.861 I slot release: id 0 | task 12812 | stop processing: n_tokens = 984, truncated = 0 41.46.038.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 984, t_last = 101509784302 41.46.038.458 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.590 MiB) 41.46.198.525 I slot launch_slot_: id 0 | task 13074 | processing task, is_child = 0 41.49.251.795 I slot print_timing: id 0 | task 13074 | prompt processing, n_tokens = 640, progress = 0.84, t = 3.05 s / 209.61 tokens per second 41.54.156.352 I slot print_timing: id 0 | task 13074 | prompt processing, n_tokens = 765, progress = 1.00, t = 7.96 s / 96.13 tokens per second 42.08.225.946 I slot print_timing: id 0 | task 13074 | n_gen = 100, tg = 8.04 t/s, tg_3s = 8.13 t/s 42.11.331.463 I slot print_timing: id 0 | task 13074 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 42.14.436.710 I slot print_timing: id 0 | task 13074 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.05 t/s 42.17.547.578 I slot print_timing: id 0 | task 13074 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.04 t/s 42.19.534.966 I slot print_timing: id 0 | task 13074 | prompt eval time = 9721.29 ms / 769 tokens ( 12.64 ms per token, 79.10 tokens per second) 42.19.534.971 I slot print_timing: id 0 | task 13074 | eval time = 23615.14 ms / 191 tokens ( 124.29 ms per token, 8.05 tokens per second) 42.19.534.972 I slot print_timing: id 0 | task 13074 | total time = 33336.43 ms / 960 tokens 42.19.534.972 I slot print_timing: id 0 | task 13074 | graphs reused = 12438 42.19.534.973 I slot print_timing: id 0 | task 13074 | graph reallocs = 0 / 0 (same size) / (changed size) 42.19.535.040 I slot release: id 0 | task 13074 | stop processing: n_tokens = 991, truncated = 0 42.19.542.860 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 101543286481 42.19.542.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.584 MiB) 42.19.718.211 I slot launch_slot_: id 0 | task 13269 | processing task, is_child = 0 42.25.850.436 I slot print_timing: id 0 | task 13269 | prompt processing, n_tokens = 572, progress = 0.99, t = 6.13 s / 93.28 tokens per second 42.39.524.205 I slot print_timing: id 0 | task 13269 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 42.42.504.285 I slot print_timing: id 0 | task 13269 | prompt eval time = 7522.40 ms / 576 tokens ( 13.06 ms per token, 76.57 tokens per second) 42.42.504.290 I slot print_timing: id 0 | task 13269 | eval time = 15263.66 ms / 124 tokens ( 124.09 ms per token, 8.06 tokens per second) 42.42.504.290 I slot print_timing: id 0 | task 13269 | total time = 22786.06 ms / 700 tokens 42.42.504.291 I slot print_timing: id 0 | task 13269 | graphs reused = 12560 42.42.504.292 I slot print_timing: id 0 | task 13269 | graph reallocs = 0 / 0 (same size) / (changed size) 42.42.505.639 I slot release: id 0 | task 13269 | stop processing: n_tokens = 731, truncated = 0 42.42.511.867 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 101566257081 42.42.511.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1111.657 MiB) 42.42.600.541 I slot launch_slot_: id 0 | task 13397 | processing task, is_child = 0 42.49.067.673 I slot print_timing: id 0 | task 13397 | prompt processing, n_tokens = 651, progress = 0.99, t = 6.47 s / 100.66 tokens per second 43.02.617.325 I slot print_timing: id 0 | task 13397 | prompt eval time = 8586.83 ms / 655 tokens ( 13.11 ms per token, 76.28 tokens per second) 43.02.617.329 I slot print_timing: id 0 | task 13397 | eval time = 11429.94 ms / 93 tokens ( 124.24 ms per token, 8.05 tokens per second) 43.02.617.330 I slot print_timing: id 0 | task 13397 | total time = 20016.77 ms / 748 tokens 43.02.617.330 I slot print_timing: id 0 | task 13397 | graphs reused = 12650 43.02.617.331 I slot print_timing: id 0 | task 13397 | graph reallocs = 0 / 0 (same size) / (changed size) 43.02.617.402 I slot release: id 0 | task 13397 | stop processing: n_tokens = 779, truncated = 0 43.02.623.824 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 779, t_last = 101586368843 43.02.623.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.209 MiB) 43.02.663.744 I slot launch_slot_: id 0 | task 13494 | processing task, is_child = 0 43.09.125.093 I slot print_timing: id 0 | task 13494 | prompt processing, n_tokens = 617, progress = 0.99, t = 6.46 s / 95.49 tokens per second 43.23.155.203 I slot print_timing: id 0 | task 13494 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 43.26.261.158 I slot print_timing: id 0 | task 13494 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.05 t/s 43.27.874.855 I slot print_timing: id 0 | task 13494 | prompt eval time = 8205.49 ms / 621 tokens ( 13.21 ms per token, 75.68 tokens per second) 43.27.874.860 I slot print_timing: id 0 | task 13494 | eval time = 17005.61 ms / 138 tokens ( 124.13 ms per token, 8.06 tokens per second) 43.27.874.861 I slot print_timing: id 0 | task 13494 | total time = 25211.10 ms / 759 tokens 43.27.874.861 I slot print_timing: id 0 | task 13494 | graphs reused = 12785 43.27.874.862 I slot print_timing: id 0 | task 13494 | graph reallocs = 0 / 0 (same size) / (changed size) 43.27.874.934 I slot release: id 0 | task 13494 | stop processing: n_tokens = 790, truncated = 0 43.27.882.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 790, t_last = 101611626375 43.27.882.071 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1101.841 MiB) 43.27.921.424 I slot launch_slot_: id 0 | task 13636 | processing task, is_child = 0 43.30.971.678 I slot print_timing: id 0 | task 13636 | prompt processing, n_tokens = 633, progress = 0.83, t = 3.05 s / 207.52 tokens per second 43.35.512.668 I slot print_timing: id 0 | task 13636 | prompt processing, n_tokens = 763, progress = 0.99, t = 7.59 s / 100.51 tokens per second 43.49.926.204 I slot print_timing: id 0 | task 13636 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 43.53.031.058 I slot print_timing: id 0 | task 13636 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 43.56.153.049 I slot print_timing: id 0 | task 13636 | n_gen = 150, tg = 8.04 t/s, tg_3s = 8.01 t/s 43.59.258.844 I slot print_timing: id 0 | task 13636 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 44.02.364.151 I slot print_timing: id 0 | task 13636 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 44.03.235.362 I slot print_timing: id 0 | task 13636 | prompt eval time = 9709.76 ms / 767 tokens ( 12.66 ms per token, 78.99 tokens per second) 44.03.235.366 I slot print_timing: id 0 | task 13636 | eval time = 25604.16 ms / 207 tokens ( 124.29 ms per token, 8.05 tokens per second) 44.03.235.367 I slot print_timing: id 0 | task 13636 | total time = 35313.93 ms / 974 tokens 44.03.235.367 I slot print_timing: id 0 | task 13636 | graphs reused = 12990 44.03.235.368 I slot print_timing: id 0 | task 13636 | graph reallocs = 0 / 0 (same size) / (changed size) 44.03.235.420 I slot release: id 0 | task 13636 | stop processing: n_tokens = 1005, truncated = 0 44.03.240.955 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1005, t_last = 101646986862 44.03.241.002 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 44.03.296.740 I slot launch_slot_: id 0 | task 13847 | processing task, is_child = 0 44.07.489.730 I slot print_timing: id 0 | task 13847 | prompt processing, n_tokens = 686, progress = 0.80, t = 4.19 s / 163.61 tokens per second 44.11.674.270 I slot print_timing: id 0 | task 13847 | prompt processing, n_tokens = 860, progress = 1.00, t = 8.38 s / 102.66 tokens per second 44.26.477.535 I slot print_timing: id 0 | task 13847 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 44.29.583.274 I slot print_timing: id 0 | task 13847 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 44.32.693.261 I slot print_timing: id 0 | task 13847 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.04 t/s 44.35.814.502 I slot print_timing: id 0 | task 13847 | n_gen = 175, tg = 8.04 t/s, tg_3s = 8.01 t/s 44.38.921.845 I slot print_timing: id 0 | task 13847 | n_gen = 200, tg = 8.04 t/s, tg_3s = 8.05 t/s 44.41.531.876 I slot print_timing: id 0 | task 13847 | prompt eval time = 10879.85 ms / 864 tokens ( 12.59 ms per token, 79.41 tokens per second) 44.41.531.881 I slot print_timing: id 0 | task 13847 | eval time = 27355.27 ms / 221 tokens ( 124.34 ms per token, 8.04 tokens per second) 44.41.531.882 I slot print_timing: id 0 | task 13847 | total time = 38235.13 ms / 1085 tokens 44.41.531.883 I slot print_timing: id 0 | task 13847 | graphs reused = 13208 44.41.531.911 I slot print_timing: id 0 | task 13847 | graph reallocs = 0 / 0 (same size) / (changed size) 44.41.531.963 I slot release: id 0 | task 13847 | stop processing: n_tokens = 1116, truncated = 0 44.41.538.912 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1116, t_last = 101685283404 44.41.538.962 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1099.652 MiB) 44.41.604.959 I slot launch_slot_: id 0 | task 14072 | processing task, is_child = 0 44.48.434.828 I slot print_timing: id 0 | task 14072 | prompt processing, n_tokens = 642, progress = 0.99, t = 6.83 s / 94.00 tokens per second 45.02.478.033 I slot print_timing: id 0 | task 14072 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.14 t/s 45.05.581.655 I slot print_timing: id 0 | task 14072 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.06 t/s 45.06.078.406 I slot print_timing: id 0 | task 14072 | prompt eval time = 8581.17 ms / 646 tokens ( 13.28 ms per token, 75.28 tokens per second) 45.06.078.411 I slot print_timing: id 0 | task 14072 | eval time = 15892.27 ms / 129 tokens ( 124.16 ms per token, 8.05 tokens per second) 45.06.078.411 I slot print_timing: id 0 | task 14072 | total time = 24473.44 ms / 775 tokens 45.06.078.412 I slot print_timing: id 0 | task 14072 | graphs reused = 13334 45.06.078.412 I slot print_timing: id 0 | task 14072 | graph reallocs = 0 / 0 (same size) / (changed size) 45.06.078.459 I slot release: id 0 | task 14072 | stop processing: n_tokens = 806, truncated = 0 45.06.083.858 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 806, t_last = 101709829900 45.06.083.895 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.906 MiB) 45.06.127.911 I slot launch_slot_: id 0 | task 14205 | processing task, is_child = 0 45.13.344.639 I slot print_timing: id 0 | task 14205 | prompt processing, n_tokens = 716, progress = 0.99, t = 7.22 s / 99.21 tokens per second 45.27.763.532 I slot print_timing: id 0 | task 14205 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 45.30.883.100 I slot print_timing: id 0 | task 14205 | n_gen = 125, tg = 8.04 t/s, tg_3s = 8.01 t/s 45.33.987.823 I slot print_timing: id 0 | task 14205 | n_gen = 150, tg = 8.04 t/s, tg_3s = 8.05 t/s 45.37.104.327 I slot print_timing: id 0 | task 14205 | n_gen = 175, tg = 8.04 t/s, tg_3s = 8.02 t/s 45.40.211.244 I slot print_timing: id 0 | task 14205 | n_gen = 200, tg = 8.04 t/s, tg_3s = 8.05 t/s 45.42.944.908 I slot print_timing: id 0 | task 14205 | prompt eval time = 9338.05 ms / 720 tokens ( 12.97 ms per token, 77.10 tokens per second) 45.42.944.911 I slot print_timing: id 0 | task 14205 | eval time = 27478.93 ms / 222 tokens ( 124.34 ms per token, 8.04 tokens per second) 45.42.944.912 I slot print_timing: id 0 | task 14205 | total time = 36816.98 ms / 942 tokens 45.42.944.912 I slot print_timing: id 0 | task 14205 | graphs reused = 13553 45.42.944.913 I slot print_timing: id 0 | task 14205 | graph reallocs = 0 / 0 (same size) / (changed size) 45.42.944.950 I slot release: id 0 | task 14205 | stop processing: n_tokens = 973, truncated = 0 45.42.950.114 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 101746696391 45.42.950.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1109.343 MiB) 45.43.000.665 I slot launch_slot_: id 0 | task 14431 | processing task, is_child = 0 45.47.925.297 I slot print_timing: id 0 | task 14431 | prompt processing, n_tokens = 505, progress = 0.99, t = 4.92 s / 102.55 tokens per second 46.01.938.689 I slot print_timing: id 0 | task 14431 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 46.05.040.002 I slot print_timing: id 0 | task 14431 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.08.143.296 I slot print_timing: id 0 | task 14431 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.11.241.575 I slot print_timing: id 0 | task 14431 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.07 t/s 46.14.342.575 I slot print_timing: id 0 | task 14431 | n_gen = 200, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.16.076.949 I slot print_timing: id 0 | task 14431 | prompt eval time = 6656.19 ms / 509 tokens ( 13.08 ms per token, 76.47 tokens per second) 46.16.076.954 I slot print_timing: id 0 | task 14431 | eval time = 26420.08 ms / 214 tokens ( 124.04 ms per token, 8.06 tokens per second) 46.16.076.955 I slot print_timing: id 0 | task 14431 | total time = 33076.27 ms / 723 tokens 46.16.076.955 I slot print_timing: id 0 | task 14431 | graphs reused = 13765 46.16.076.956 I slot print_timing: id 0 | task 14431 | graph reallocs = 0 / 0 (same size) / (changed size) 46.16.076.988 I slot release: id 0 | task 14431 | stop processing: n_tokens = 754, truncated = 0 46.16.083.126 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 101779828429 46.16.083.163 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1093.087 MiB) 46.16.112.386 I slot launch_slot_: id 0 | task 14648 | processing task, is_child = 0 46.22.226.595 I slot print_timing: id 0 | task 14648 | prompt processing, n_tokens = 577, progress = 0.99, t = 6.11 s / 94.37 tokens per second 46.36.239.918 I slot print_timing: id 0 | task 14648 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 46.39.342.139 I slot print_timing: id 0 | task 14648 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.42.443.589 I slot print_timing: id 0 | task 14648 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.45.553.313 I slot print_timing: id 0 | task 14648 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.04 t/s 46.48.654.072 I slot print_timing: id 0 | task 14648 | n_gen = 200, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.51.755.821 I slot print_timing: id 0 | task 14648 | n_gen = 225, tg = 8.06 t/s, tg_3s = 8.06 t/s 46.53.865.603 I slot print_timing: id 0 | task 14648 | prompt eval time = 7850.93 ms / 581 tokens ( 13.51 ms per token, 74.00 tokens per second) 46.53.865.608 I slot print_timing: id 0 | task 14648 | eval time = 29902.27 ms / 242 tokens ( 124.08 ms per token, 8.06 tokens per second) 46.53.865.609 I slot print_timing: id 0 | task 14648 | total time = 37753.20 ms / 823 tokens 46.53.865.609 I slot print_timing: id 0 | task 14648 | graphs reused = 14004 46.53.865.610 I slot print_timing: id 0 | task 14648 | graph reallocs = 0 / 0 (same size) / (changed size) 46.53.865.655 I slot release: id 0 | task 14648 | stop processing: n_tokens = 854, truncated = 0 46.53.871.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 101817617096 46.53.871.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.089 MiB) 46.53.897.254 I slot launch_slot_: id 0 | task 14894 | processing task, is_child = 0 46.58.823.100 I slot print_timing: id 0 | task 14894 | prompt processing, n_tokens = 741, progress = 0.81, t = 4.93 s / 150.43 tokens per second 47.03.006.443 I slot print_timing: id 0 | task 14894 | prompt processing, n_tokens = 921, progress = 1.00, t = 9.11 s / 101.11 tokens per second 47.17.814.807 I slot print_timing: id 0 | task 14894 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 47.20.933.510 I slot print_timing: id 0 | task 14894 | n_gen = 125, tg = 8.04 t/s, tg_3s = 8.02 t/s 47.24.041.010 I slot print_timing: id 0 | task 14894 | n_gen = 150, tg = 8.04 t/s, tg_3s = 8.05 t/s 47.27.147.568 I slot print_timing: id 0 | task 14894 | n_gen = 175, tg = 8.04 t/s, tg_3s = 8.05 t/s 47.30.252.063 I slot print_timing: id 0 | task 14894 | n_gen = 200, tg = 8.04 t/s, tg_3s = 8.05 t/s 47.33.357.174 I slot print_timing: id 0 | task 14894 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.05 t/s 47.35.108.382 I slot print_timing: id 0 | task 14894 | prompt eval time = 11618.23 ms / 925 tokens ( 12.56 ms per token, 79.62 tokens per second) 47.35.108.384 I slot print_timing: id 0 | task 14894 | eval time = 29592.89 ms / 239 tokens ( 124.34 ms per token, 8.04 tokens per second) 47.35.108.385 I slot print_timing: id 0 | task 14894 | total time = 41211.11 ms / 1164 tokens 47.35.108.385 I slot print_timing: id 0 | task 14894 | graphs reused = 14240 47.35.108.386 I slot print_timing: id 0 | task 14894 | graph reallocs = 0 / 0 (same size) / (changed size) 47.35.109.871 I slot release: id 0 | task 14894 | stop processing: n_tokens = 1195, truncated = 0 47.35.118.252 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1195, t_last = 101858861314 47.35.118.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1096.776 MiB) 47.35.435.645 I slot launch_slot_: id 0 | task 15137 | processing task, is_child = 0 47.39.982.520 I slot print_timing: id 0 | task 15137 | prompt processing, n_tokens = 743, progress = 0.85, t = 4.55 s / 163.41 tokens per second 47.44.522.358 I slot print_timing: id 0 | task 15137 | prompt processing, n_tokens = 881, progress = 1.00, t = 9.09 s / 96.95 tokens per second 47.50.749.479 I slot print_timing: id 0 | task 15137 | prompt eval time = 11213.16 ms / 885 tokens ( 12.67 ms per token, 78.93 tokens per second) 47.50.749.482 I slot print_timing: id 0 | task 15137 | eval time = 4100.66 ms / 34 tokens ( 124.26 ms per token, 8.05 tokens per second) 47.50.749.482 I slot print_timing: id 0 | task 15137 | total time = 15313.82 ms / 919 tokens 47.50.749.483 I slot print_timing: id 0 | task 15137 | graphs reused = 14272 47.50.749.483 I slot print_timing: id 0 | task 15137 | graph reallocs = 0 / 0 (same size) / (changed size) 47.50.749.621 I slot release: id 0 | task 15137 | stop processing: n_tokens = 950, truncated = 0 47.50.757.616 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 950, t_last = 101874501063 47.50.757.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1110.219 MiB) 47.50.925.480 I slot launch_slot_: id 0 | task 15175 | processing task, is_child = 0 47.55.470.007 I slot print_timing: id 0 | task 15175 | prompt processing, n_tokens = 388, progress = 0.99, t = 4.54 s / 85.38 tokens per second 48.08.400.663 I slot print_timing: id 0 | task 15175 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 48.11.496.431 I slot print_timing: id 0 | task 15175 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.08 t/s 48.14.596.132 I slot print_timing: id 0 | task 15175 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.07 t/s 48.17.693.748 I slot print_timing: id 0 | task 15175 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.07 t/s 48.20.792.078 I slot print_timing: id 0 | task 15175 | n_gen = 200, tg = 8.07 t/s, tg_3s = 8.07 t/s 48.23.893.799 I slot print_timing: id 0 | task 15175 | n_gen = 225, tg = 8.06 t/s, tg_3s = 8.06 t/s 48.26.994.085 I slot print_timing: id 0 | task 15175 | n_gen = 250, tg = 8.06 t/s, tg_3s = 8.06 t/s 48.30.101.863 I slot print_timing: id 0 | task 15175 | n_gen = 275, tg = 8.06 t/s, tg_3s = 8.04 t/s 48.32.961.594 I slot print_timing: id 0 | task 15175 | prompt eval time = 5192.23 ms / 392 tokens ( 13.25 ms per token, 75.50 tokens per second) 48.32.961.599 I slot print_timing: id 0 | task 15175 | eval time = 36843.88 ms / 298 tokens ( 124.05 ms per token, 8.06 tokens per second) 48.32.961.600 I slot print_timing: id 0 | task 15175 | total time = 42036.10 ms / 690 tokens 48.32.961.600 I slot print_timing: id 0 | task 15175 | graphs reused = 14567 48.32.961.601 I slot print_timing: id 0 | task 15175 | graph reallocs = 0 / 0 (same size) / (changed size) 48.32.961.646 I slot release: id 0 | task 15175 | stop processing: n_tokens = 721, truncated = 0 48.32.966.608 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 721, t_last = 101916713087 48.32.966.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1117.159 MiB) 48.33.088.827 I slot launch_slot_: id 0 | task 15476 | processing task, is_child = 0 48.36.901.984 I slot print_timing: id 0 | task 15476 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.81 s / 85.76 tokens per second 48.49.814.624 I slot print_timing: id 0 | task 15476 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 48.51.427.525 I slot print_timing: id 0 | task 15476 | prompt eval time = 4422.87 ms / 331 tokens ( 13.36 ms per token, 74.84 tokens per second) 48.51.427.531 I slot print_timing: id 0 | task 15476 | eval time = 13915.81 ms / 113 tokens ( 124.25 ms per token, 8.05 tokens per second) 48.51.427.532 I slot print_timing: id 0 | task 15476 | total time = 18338.68 ms / 444 tokens 48.51.427.533 I slot print_timing: id 0 | task 15476 | graphs reused = 14678 48.51.427.533 I slot print_timing: id 0 | task 15476 | graph reallocs = 0 / 0 (same size) / (changed size) 48.51.427.581 I slot release: id 0 | task 15476 | stop processing: n_tokens = 475, truncated = 0 48.51.432.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 475, t_last = 101935179022 48.51.432.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.777 MiB) 48.51.555.579 I slot launch_slot_: id 0 | task 15592 | processing task, is_child = 0 48.55.733.200 I slot print_timing: id 0 | task 15592 | prompt processing, n_tokens = 353, progress = 0.99, t = 4.18 s / 84.50 tokens per second 49.03.100.678 I slot print_timing: id 0 | task 15592 | prompt eval time = 4830.19 ms / 357 tokens ( 13.53 ms per token, 73.91 tokens per second) 49.03.100.682 I slot print_timing: id 0 | task 15592 | eval time = 6714.89 ms / 55 tokens ( 124.35 ms per token, 8.04 tokens per second) 49.03.100.682 I slot print_timing: id 0 | task 15592 | total time = 11545.08 ms / 412 tokens 49.03.100.683 I slot print_timing: id 0 | task 15592 | graphs reused = 14731 49.03.100.683 I slot print_timing: id 0 | task 15592 | graph reallocs = 0 / 0 (same size) / (changed size) 49.03.100.712 I slot release: id 0 | task 15592 | stop processing: n_tokens = 443, truncated = 0 49.03.104.925 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 443, t_last = 101946852153 49.03.190.696 I slot launch_slot_: id 0 | task 15650 | processing task, is_child = 0 49.06.988.994 I slot print_timing: id 0 | task 15650 | prompt processing, n_tokens = 311, progress = 0.99, t = 3.80 s / 81.88 tokens per second 49.19.645.932 I slot print_timing: id 0 | task 15650 | prompt eval time = 4410.36 ms / 315 tokens ( 14.00 ms per token, 71.42 tokens per second) 49.19.645.937 I slot print_timing: id 0 | task 15650 | eval time = 12044.86 ms / 98 tokens ( 124.17 ms per token, 8.05 tokens per second) 49.19.645.938 I slot print_timing: id 0 | task 15650 | total time = 16455.22 ms / 413 tokens 49.19.645.938 I slot print_timing: id 0 | task 15650 | graphs reused = 14827 49.19.645.939 I slot print_timing: id 0 | task 15650 | graph reallocs = 0 / 0 (same size) / (changed size) 49.19.645.980 I slot release: id 0 | task 15650 | stop processing: n_tokens = 444, truncated = 0 49.19.650.606 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 101963397421 49.19.650.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1108.218 MiB) 49.19.779.975 I slot launch_slot_: id 0 | task 15751 | processing task, is_child = 0 49.23.977.258 I slot print_timing: id 0 | task 15751 | prompt processing, n_tokens = 374, progress = 0.99, t = 4.20 s / 89.11 tokens per second 49.32.289.425 I slot print_timing: id 0 | task 15751 | prompt eval time = 5194.35 ms / 378 tokens ( 13.74 ms per token, 72.77 tokens per second) 49.32.289.431 I slot print_timing: id 0 | task 15751 | eval time = 7315.09 ms / 60 tokens ( 123.98 ms per token, 8.07 tokens per second) 49.32.289.431 I slot print_timing: id 0 | task 15751 | total time = 12509.44 ms / 438 tokens 49.32.289.432 I slot print_timing: id 0 | task 15751 | graphs reused = 14885 49.32.289.432 I slot print_timing: id 0 | task 15751 | graph reallocs = 0 / 0 (same size) / (changed size) 49.32.289.474 I slot release: id 0 | task 15751 | stop processing: n_tokens = 469, truncated = 0 49.32.294.234 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 101976040915 49.32.294.264 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.899 MiB) 49.32.375.486 I slot launch_slot_: id 0 | task 15814 | processing task, is_child = 0 49.35.818.885 I slot print_timing: id 0 | task 15814 | prompt processing, n_tokens = 291, progress = 0.99, t = 3.44 s / 84.51 tokens per second 49.39.813.270 I slot print_timing: id 0 | task 15814 | prompt eval time = 4091.88 ms / 295 tokens ( 13.87 ms per token, 72.09 tokens per second) 49.39.813.275 I slot print_timing: id 0 | task 15814 | eval time = 3345.89 ms / 28 tokens ( 123.92 ms per token, 8.07 tokens per second) 49.39.813.276 I slot print_timing: id 0 | task 15814 | total time = 7437.77 ms / 323 tokens 49.39.813.276 I slot print_timing: id 0 | task 15814 | graphs reused = 14911 49.39.813.277 I slot print_timing: id 0 | task 15814 | graph reallocs = 0 / 0 (same size) / (changed size) 49.39.813.318 I slot release: id 0 | task 15814 | stop processing: n_tokens = 354, truncated = 0 49.39.817.661 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 101983564759 49.39.817.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.778 MiB) 49.39.936.328 I slot launch_slot_: id 0 | task 15845 | processing task, is_child = 0 49.43.756.505 I slot print_timing: id 0 | task 15845 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.82 s / 87.17 tokens per second 49.49.951.746 I slot print_timing: id 0 | task 15845 | prompt eval time = 4433.82 ms / 337 tokens ( 13.16 ms per token, 76.01 tokens per second) 49.49.951.750 I slot print_timing: id 0 | task 15845 | eval time = 5581.59 ms / 46 tokens ( 124.04 ms per token, 8.06 tokens per second) 49.49.951.751 I slot print_timing: id 0 | task 15845 | total time = 10015.41 ms / 383 tokens 49.49.951.751 I slot print_timing: id 0 | task 15845 | graphs reused = 14955 49.49.951.752 I slot print_timing: id 0 | task 15845 | graph reallocs = 0 / 0 (same size) / (changed size) 49.49.951.786 I slot release: id 0 | task 15845 | stop processing: n_tokens = 414, truncated = 0 49.49.956.743 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 101993703227 49.49.956.770 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1122.098 MiB) 49.50.010.459 I slot launch_slot_: id 0 | task 15894 | processing task, is_child = 0 49.53.803.367 I slot print_timing: id 0 | task 15894 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.79 s / 84.63 tokens per second 50.06.744.408 I slot print_timing: id 0 | task 15894 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.14 t/s 50.09.846.912 I slot print_timing: id 0 | task 15894 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 50.12.950.179 I slot print_timing: id 0 | task 15894 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 50.14.072.103 I slot print_timing: id 0 | task 15894 | prompt eval time = 4442.66 ms / 325 tokens ( 13.67 ms per token, 73.15 tokens per second) 50.14.072.110 I slot print_timing: id 0 | task 15894 | eval time = 19618.98 ms / 159 tokens ( 124.17 ms per token, 8.05 tokens per second) 50.14.072.112 I slot print_timing: id 0 | task 15894 | total time = 24061.63 ms / 484 tokens 50.14.072.112 I slot print_timing: id 0 | task 15894 | graphs reused = 15111 50.14.072.113 I slot print_timing: id 0 | task 15894 | graph reallocs = 0 / 0 (same size) / (changed size) 50.14.072.148 I slot release: id 0 | task 15894 | stop processing: n_tokens = 515, truncated = 0 50.14.076.722 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.062 50.14.076.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1106.780 MiB) 50.14.118.572 I slot launch_slot_: id 0 | task 16056 | processing task, is_child = 0 50.17.159.019 I slot print_timing: id 0 | task 16056 | prompt processing, n_tokens = 260, progress = 0.99, t = 3.04 s / 85.51 tokens per second 50.30.491.492 I slot print_timing: id 0 | task 16056 | n_gen = 100, tg = 7.80 t/s, tg_3s = 7.88 t/s 50.33.597.222 I slot print_timing: id 0 | task 16056 | n_gen = 125, tg = 7.85 t/s, tg_3s = 8.05 t/s 50.36.694.863 I slot print_timing: id 0 | task 16056 | n_gen = 150, tg = 7.89 t/s, tg_3s = 8.07 t/s 50.39.793.684 I slot print_timing: id 0 | task 16056 | n_gen = 175, tg = 7.91 t/s, tg_3s = 8.07 t/s 50.42.895.366 I slot print_timing: id 0 | task 16056 | n_gen = 200, tg = 7.93 t/s, tg_3s = 8.06 t/s 50.46.004.299 I slot print_timing: id 0 | task 16056 | n_gen = 225, tg = 7.94 t/s, tg_3s = 8.04 t/s 50.49.105.783 I slot print_timing: id 0 | task 16056 | n_gen = 250, tg = 7.96 t/s, tg_3s = 8.06 t/s 50.52.205.734 I slot print_timing: id 0 | task 16056 | n_gen = 275, tg = 7.97 t/s, tg_3s = 8.06 t/s 50.53.444.783 I slot print_timing: id 0 | task 16056 | prompt eval time = 3688.29 ms / 264 tokens ( 13.97 ms per token, 71.58 tokens per second) 50.53.444.788 I slot print_timing: id 0 | task 16056 | eval time = 35637.91 ms / 285 tokens ( 125.49 ms per token, 7.97 tokens per second) 50.53.444.789 I slot print_timing: id 0 | task 16056 | total time = 39326.20 ms / 549 tokens 50.53.444.789 I slot print_timing: id 0 | task 16056 | graphs reused = 15393 50.53.444.790 I slot print_timing: id 0 | task 16056 | graph reallocs = 0 / 0 (same size) / (changed size) 50.53.444.826 I slot release: id 0 | task 16056 | stop processing: n_tokens = 580, truncated = 0 50.53.449.758 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 580, t_last = 102057196268 50.53.449.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 942.836 MiB) 50.53.495.935 I slot launch_slot_: id 0 | task 16344 | processing task, is_child = 0 50.57.292.112 I slot print_timing: id 0 | task 16344 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.80 s / 86.14 tokens per second 51.04.658.409 I slot print_timing: id 0 | task 16344 | prompt eval time = 4445.88 ms / 331 tokens ( 13.43 ms per token, 74.45 tokens per second) 51.04.658.415 I slot print_timing: id 0 | task 16344 | eval time = 6716.58 ms / 55 tokens ( 124.38 ms per token, 8.04 tokens per second) 51.04.658.416 I slot print_timing: id 0 | task 16344 | total time = 11162.47 ms / 386 tokens 51.04.658.416 I slot print_timing: id 0 | task 16344 | graphs reused = 15446 51.04.658.417 I slot print_timing: id 0 | task 16344 | graph reallocs = 0 / 0 (same size) / (changed size) 51.04.658.449 I slot release: id 0 | task 16344 | stop processing: n_tokens = 417, truncated = 0 51.04.664.935 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 102068409890 51.04.664.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.456 MiB) 51.04.701.375 I slot launch_slot_: id 0 | task 16402 | processing task, is_child = 0 51.08.501.829 I slot print_timing: id 0 | task 16402 | prompt processing, n_tokens = 329, progress = 0.99, t = 3.80 s / 86.57 tokens per second 51.21.437.973 I slot print_timing: id 0 | task 16402 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 51.24.540.202 I slot print_timing: id 0 | task 16402 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 51.25.407.341 I slot print_timing: id 0 | task 16402 | prompt eval time = 4447.25 ms / 333 tokens ( 13.36 ms per token, 74.88 tokens per second) 51.25.407.350 I slot print_timing: id 0 | task 16402 | eval time = 16258.70 ms / 132 tokens ( 124.11 ms per token, 8.06 tokens per second) 51.25.407.350 I slot print_timing: id 0 | task 16402 | total time = 20705.96 ms / 465 tokens 51.25.407.351 I slot print_timing: id 0 | task 16402 | graphs reused = 15576 51.25.407.351 I slot print_timing: id 0 | task 16402 | graph reallocs = 0 / 0 (same size) / (changed size) 51.25.407.377 I slot release: id 0 | task 16402 | stop processing: n_tokens = 496, truncated = 0 51.25.412.293 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 496, t_last = 102089158818 51.25.412.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.455 MiB) 51.25.454.455 I slot launch_slot_: id 0 | task 16537 | processing task, is_child = 0 51.29.242.898 I slot print_timing: id 0 | task 16537 | prompt processing, n_tokens = 342, progress = 0.99, t = 3.79 s / 90.27 tokens per second 51.42.535.496 I slot print_timing: id 0 | task 16537 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 51.44.766.395 I slot print_timing: id 0 | task 16537 | prompt eval time = 4791.96 ms / 346 tokens ( 13.85 ms per token, 72.20 tokens per second) 51.44.766.398 I slot print_timing: id 0 | task 16537 | eval time = 14519.97 ms / 118 tokens ( 124.10 ms per token, 8.06 tokens per second) 51.44.766.399 I slot print_timing: id 0 | task 16537 | total time = 19311.93 ms / 464 tokens 51.44.766.399 I slot print_timing: id 0 | task 16537 | graphs reused = 15692 51.44.766.400 I slot print_timing: id 0 | task 16537 | graph reallocs = 0 / 0 (same size) / (changed size) 51.44.766.446 I slot release: id 0 | task 16537 | stop processing: n_tokens = 495, truncated = 0 51.44.771.339 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 495, t_last = 102108517887 51.44.771.378 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.517 MiB) 51.44.817.599 I slot launch_slot_: id 0 | task 16658 | processing task, is_child = 0 51.48.614.322 I slot print_timing: id 0 | task 16658 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.80 s / 84.55 tokens per second 51.53.445.354 I slot print_timing: id 0 | task 16658 | prompt eval time = 4411.55 ms / 325 tokens ( 13.57 ms per token, 73.67 tokens per second) 51.53.445.359 I slot print_timing: id 0 | task 16658 | eval time = 4216.19 ms / 35 tokens ( 124.01 ms per token, 8.06 tokens per second) 51.53.445.360 I slot print_timing: id 0 | task 16658 | total time = 8627.74 ms / 360 tokens 51.53.445.361 I slot print_timing: id 0 | task 16658 | graphs reused = 15725 51.53.445.361 I slot print_timing: id 0 | task 16658 | graph reallocs = 0 / 0 (same size) / (changed size) 51.53.445.409 I slot release: id 0 | task 16658 | stop processing: n_tokens = 391, truncated = 0 51.53.449.678 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 102117196850 51.53.449.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 927.080 MiB) 51.53.487.036 I slot launch_slot_: id 0 | task 16696 | processing task, is_child = 0 51.57.277.616 I slot print_timing: id 0 | task 16696 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.79 s / 83.89 tokens per second 52.10.226.489 I slot print_timing: id 0 | task 16696 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 52.13.333.206 I slot print_timing: id 0 | task 16696 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 52.16.442.354 I slot print_timing: id 0 | task 16696 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.04 t/s 52.19.550.430 I slot print_timing: id 0 | task 16696 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.04 t/s 52.22.659.790 I slot print_timing: id 0 | task 16696 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.04 t/s 52.25.763.481 I slot print_timing: id 0 | task 16696 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.05 t/s 52.28.871.548 I slot print_timing: id 0 | task 16696 | n_gen = 250, tg = 8.05 t/s, tg_3s = 8.04 t/s 52.31.974.878 I slot print_timing: id 0 | task 16696 | n_gen = 275, tg = 8.05 t/s, tg_3s = 8.06 t/s 52.35.080.510 I slot print_timing: id 0 | task 16696 | n_gen = 300, tg = 8.05 t/s, tg_3s = 8.05 t/s 52.38.187.503 I slot print_timing: id 0 | task 16696 | n_gen = 325, tg = 8.05 t/s, tg_3s = 8.05 t/s 52.38.311.424 I slot print_timing: id 0 | task 16696 | prompt eval time = 4440.07 ms / 322 tokens ( 13.79 ms per token, 72.52 tokens per second) 52.38.311.430 I slot print_timing: id 0 | task 16696 | eval time = 40384.31 ms / 326 tokens ( 124.26 ms per token, 8.05 tokens per second) 52.38.311.431 I slot print_timing: id 0 | task 16696 | total time = 44824.38 ms / 648 tokens 52.38.311.431 I slot print_timing: id 0 | task 16696 | graphs reused = 16048 52.38.311.431 I slot print_timing: id 0 | task 16696 | graph reallocs = 0 / 0 (same size) / (changed size) 52.38.311.465 I slot release: id 0 | task 16696 | stop processing: n_tokens = 679, truncated = 0 52.38.316.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 679, t_last = 102162062906 52.38.316.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 919.890 MiB) 52.38.370.671 I slot launch_slot_: id 0 | task 17025 | processing task, is_child = 0 52.42.175.808 I slot print_timing: id 0 | task 17025 | prompt processing, n_tokens = 334, progress = 0.99, t = 3.81 s / 87.78 tokens per second 52.55.122.929 I slot print_timing: id 0 | task 17025 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 52.58.229.099 I slot print_timing: id 0 | task 17025 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.05 t/s 53.01.338.761 I slot print_timing: id 0 | task 17025 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.04 t/s 53.04.444.661 I slot print_timing: id 0 | task 17025 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 53.07.545.656 I slot print_timing: id 0 | task 17025 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.06 t/s 53.10.652.697 I slot print_timing: id 0 | task 17025 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.05 t/s 53.13.760.945 I slot print_timing: id 0 | task 17025 | n_gen = 250, tg = 8.05 t/s, tg_3s = 8.04 t/s 53.16.866.049 I slot print_timing: id 0 | task 17025 | n_gen = 275, tg = 8.05 t/s, tg_3s = 8.05 t/s 53.19.972.182 I slot print_timing: id 0 | task 17025 | n_gen = 300, tg = 8.05 t/s, tg_3s = 8.05 t/s 53.23.087.757 I slot print_timing: id 0 | task 17025 | n_gen = 325, tg = 8.05 t/s, tg_3s = 8.02 t/s 53.26.200.828 I slot print_timing: id 0 | task 17025 | n_gen = 350, tg = 8.05 t/s, tg_3s = 8.03 t/s 53.29.307.345 I slot print_timing: id 0 | task 17025 | n_gen = 375, tg = 8.05 t/s, tg_3s = 8.05 t/s 53.32.423.482 I slot print_timing: id 0 | task 17025 | n_gen = 400, tg = 8.04 t/s, tg_3s = 8.02 t/s 53.35.534.957 I slot print_timing: id 0 | task 17025 | n_gen = 425, tg = 8.04 t/s, tg_3s = 8.03 t/s 53.38.649.072 I slot print_timing: id 0 | task 17025 | n_gen = 450, tg = 8.04 t/s, tg_3s = 8.03 t/s 53.41.759.448 I slot print_timing: id 0 | task 17025 | n_gen = 475, tg = 8.04 t/s, tg_3s = 8.04 t/s 53.44.868.768 I slot print_timing: id 0 | task 17025 | n_gen = 500, tg = 8.04 t/s, tg_3s = 8.04 t/s 53.47.982.143 I slot print_timing: id 0 | task 17025 | n_gen = 525, tg = 8.04 t/s, tg_3s = 8.03 t/s 53.51.089.890 I slot print_timing: id 0 | task 17025 | n_gen = 550, tg = 8.04 t/s, tg_3s = 8.04 t/s 53.54.196.446 I slot print_timing: id 0 | task 17025 | n_gen = 575, tg = 8.04 t/s, tg_3s = 8.05 t/s 53.57.309.480 I slot print_timing: id 0 | task 17025 | n_gen = 600, tg = 8.04 t/s, tg_3s = 8.03 t/s 54.00.423.433 I slot print_timing: id 0 | task 17025 | n_gen = 625, tg = 8.04 t/s, tg_3s = 8.03 t/s 54.03.530.821 I slot print_timing: id 0 | task 17025 | n_gen = 650, tg = 8.04 t/s, tg_3s = 8.05 t/s 54.06.642.946 I slot print_timing: id 0 | task 17025 | n_gen = 675, tg = 8.04 t/s, tg_3s = 8.03 t/s 54.09.753.906 I slot print_timing: id 0 | task 17025 | n_gen = 700, tg = 8.04 t/s, tg_3s = 8.04 t/s 54.12.859.272 I slot print_timing: id 0 | task 17025 | n_gen = 725, tg = 8.04 t/s, tg_3s = 8.05 t/s 54.15.970.865 I slot print_timing: id 0 | task 17025 | n_gen = 750, tg = 8.04 t/s, tg_3s = 8.03 t/s 54.19.078.753 I slot print_timing: id 0 | task 17025 | n_gen = 775, tg = 8.04 t/s, tg_3s = 8.04 t/s 54.22.187.394 I slot print_timing: id 0 | task 17025 | n_gen = 800, tg = 8.04 t/s, tg_3s = 8.04 t/s 54.22.436.043 I slot print_timing: id 0 | task 17025 | prompt eval time = 4454.35 ms / 338 tokens ( 13.18 ms per token, 75.88 tokens per second) 54.22.436.048 I slot print_timing: id 0 | task 17025 | eval time = 99611.01 ms / 802 tokens ( 124.36 ms per token, 8.04 tokens per second) 54.22.436.048 I slot print_timing: id 0 | task 17025 | total time = 104065.36 ms / 1140 tokens 54.22.436.049 I slot print_timing: id 0 | task 17025 | graphs reused = 16845 54.22.436.049 I slot print_timing: id 0 | task 17025 | graph reallocs = 0 / 0 (same size) / (changed size) 54.22.436.085 I slot release: id 0 | task 17025 | stop processing: n_tokens = 1171, truncated = 0 54.22.443.024 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1171, t_last = 102266187526 54.22.443.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.642 MiB) 54.22.478.892 I slot launch_slot_: id 0 | task 17830 | processing task, is_child = 0 54.26.292.282 I slot print_timing: id 0 | task 17830 | prompt processing, n_tokens = 343, progress = 0.99, t = 3.81 s / 89.95 tokens per second 54.39.240.726 I slot print_timing: id 0 | task 17830 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 54.42.350.966 I slot print_timing: id 0 | task 17830 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.04 t/s 54.45.465.034 I slot print_timing: id 0 | task 17830 | n_gen = 150, tg = 8.04 t/s, tg_3s = 8.03 t/s 54.48.573.548 I slot print_timing: id 0 | task 17830 | n_gen = 175, tg = 8.04 t/s, tg_3s = 8.04 t/s 54.51.680.017 I slot print_timing: id 0 | task 17830 | n_gen = 200, tg = 8.04 t/s, tg_3s = 8.05 t/s 54.54.789.847 I slot print_timing: id 0 | task 17830 | n_gen = 225, tg = 8.04 t/s, tg_3s = 8.04 t/s 54.57.890.803 I slot print_timing: id 0 | task 17830 | n_gen = 250, tg = 8.05 t/s, tg_3s = 8.06 t/s 55.01.003.882 I slot print_timing: id 0 | task 17830 | n_gen = 275, tg = 8.04 t/s, tg_3s = 8.03 t/s 55.04.104.951 I slot print_timing: id 0 | task 17830 | n_gen = 300, tg = 8.05 t/s, tg_3s = 8.06 t/s 55.07.209.941 I slot print_timing: id 0 | task 17830 | n_gen = 325, tg = 8.05 t/s, tg_3s = 8.05 t/s 55.10.312.707 I slot print_timing: id 0 | task 17830 | n_gen = 350, tg = 8.05 t/s, tg_3s = 8.06 t/s 55.13.416.098 I slot print_timing: id 0 | task 17830 | n_gen = 375, tg = 8.05 t/s, tg_3s = 8.06 t/s 55.16.521.128 I slot print_timing: id 0 | task 17830 | n_gen = 400, tg = 8.05 t/s, tg_3s = 8.05 t/s 55.19.630.297 I slot print_timing: id 0 | task 17830 | n_gen = 425, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.22.737.446 I slot print_timing: id 0 | task 17830 | n_gen = 450, tg = 8.05 t/s, tg_3s = 8.05 t/s 55.25.846.030 I slot print_timing: id 0 | task 17830 | n_gen = 475, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.28.953.908 I slot print_timing: id 0 | task 17830 | n_gen = 500, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.32.059.315 I slot print_timing: id 0 | task 17830 | n_gen = 525, tg = 8.05 t/s, tg_3s = 8.05 t/s 55.35.168.646 I slot print_timing: id 0 | task 17830 | n_gen = 550, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.38.278.454 I slot print_timing: id 0 | task 17830 | n_gen = 575, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.41.387.094 I slot print_timing: id 0 | task 17830 | n_gen = 600, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.44.492.762 I slot print_timing: id 0 | task 17830 | n_gen = 625, tg = 8.05 t/s, tg_3s = 8.05 t/s 55.47.602.740 I slot print_timing: id 0 | task 17830 | n_gen = 650, tg = 8.05 t/s, tg_3s = 8.04 t/s 55.50.461.254 I slot print_timing: id 0 | task 17830 | prompt eval time = 4462.76 ms / 347 tokens ( 12.86 ms per token, 77.75 tokens per second) 55.50.461.259 I slot print_timing: id 0 | task 17830 | eval time = 83519.59 ms / 673 tokens ( 124.29 ms per token, 8.05 tokens per second) 55.50.461.259 I slot print_timing: id 0 | task 17830 | total time = 87982.35 ms / 1020 tokens 55.50.461.260 I slot print_timing: id 0 | task 17830 | graphs reused = 17513 55.50.461.260 I slot print_timing: id 0 | task 17830 | graph reallocs = 0 / 0 (same size) / (changed size) 55.50.461.288 I slot release: id 0 | task 17830 | stop processing: n_tokens = 1051, truncated = 0 55.50.468.744 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1051, t_last = 102354212730 55.50.468.799 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.956 MiB) 55.50.517.374 I slot launch_slot_: id 0 | task 18506 | processing task, is_child = 0 55.54.314.958 I slot print_timing: id 0 | task 18506 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.80 s / 86.11 tokens per second 56.01.878.244 I slot print_timing: id 0 | task 18506 | prompt eval time = 4446.62 ms / 331 tokens ( 13.43 ms per token, 74.44 tokens per second) 56.01.878.247 I slot print_timing: id 0 | task 18506 | eval time = 6914.23 ms / 56 tokens ( 125.71 ms per token, 7.95 tokens per second) 56.01.878.248 I slot print_timing: id 0 | task 18506 | total time = 11360.85 ms / 387 tokens 56.01.878.248 I slot print_timing: id 0 | task 18506 | graphs reused = 17567 56.01.878.249 I slot print_timing: id 0 | task 18506 | graph reallocs = 0 / 0 (same size) / (changed size) 56.01.878.386 I slot release: id 0 | task 18506 | stop processing: n_tokens = 418, truncated = 0 56.01.888.512 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 418, t_last = 102365629828 56.01.888.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.020 MiB) 56.02.070.966 I slot launch_slot_: id 0 | task 18565 | processing task, is_child = 0 56.05.866.537 I slot print_timing: id 0 | task 18565 | prompt processing, n_tokens = 341, progress = 0.99, t = 3.80 s / 89.84 tokens per second 56.18.783.108 I slot print_timing: id 0 | task 18565 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 56.21.827.154 I slot print_timing: id 0 | task 18565 | n_gen = 124, tg = 8.03 t/s, tg_3s = 7.88 t/s 56.24.903.626 I slot print_timing: id 0 | task 18565 | n_gen = 147, tg = 7.94 t/s, tg_3s = 7.48 t/s 56.27.979.884 I slot print_timing: id 0 | task 18565 | n_gen = 170, tg = 7.87 t/s, tg_3s = 7.48 t/s 56.31.089.328 I slot print_timing: id 0 | task 18565 | n_gen = 193, tg = 7.81 t/s, tg_3s = 7.40 t/s 56.34.171.673 I slot print_timing: id 0 | task 18565 | n_gen = 216, tg = 7.77 t/s, tg_3s = 7.46 t/s 56.34.974.737 I slot print_timing: id 0 | task 18565 | prompt eval time = 4441.73 ms / 345 tokens ( 12.87 ms per token, 77.67 tokens per second) 56.34.974.761 I slot print_timing: id 0 | task 18565 | eval time = 28462.01 ms / 222 tokens ( 128.79 ms per token, 7.76 tokens per second) 56.34.974.763 I slot print_timing: id 0 | task 18565 | total time = 32903.74 ms / 567 tokens 56.34.974.765 I slot print_timing: id 0 | task 18565 | graphs reused = 17786 56.34.974.768 I slot print_timing: id 0 | task 18565 | graph reallocs = 0 / 0 (same size) / (changed size) 56.34.975.550 I slot release: id 0 | task 18565 | stop processing: n_tokens = 598, truncated = 0 56.34.988.570 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 598, t_last = 102398726996 56.34.988.650 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.829 MiB) 56.35.203.197 I slot launch_slot_: id 0 | task 18790 | processing task, is_child = 0 56.38.998.330 I slot print_timing: id 0 | task 18790 | prompt processing, n_tokens = 316, progress = 0.99, t = 3.80 s / 83.26 tokens per second 56.50.680.581 I slot print_timing: id 0 | task 18790 | prompt eval time = 4444.25 ms / 320 tokens ( 13.89 ms per token, 72.00 tokens per second) 56.50.680.587 I slot print_timing: id 0 | task 18790 | eval time = 11033.13 ms / 90 tokens ( 123.97 ms per token, 8.07 tokens per second) 56.50.680.588 I slot print_timing: id 0 | task 18790 | total time = 15477.37 ms / 410 tokens 56.50.680.588 I slot print_timing: id 0 | task 18790 | graphs reused = 17874 56.50.680.589 I slot print_timing: id 0 | task 18790 | graph reallocs = 0 / 0 (same size) / (changed size) 56.50.680.642 I slot release: id 0 | task 18790 | stop processing: n_tokens = 441, truncated = 0 56.50.685.177 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 441, t_last = 102414432083 56.50.685.205 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.768 MiB) 56.50.837.199 I slot launch_slot_: id 0 | task 18883 | processing task, is_child = 0 56.54.288.108 I slot print_timing: id 0 | task 18883 | prompt processing, n_tokens = 293, progress = 0.99, t = 3.45 s / 84.91 tokens per second 56.58.984.293 I slot print_timing: id 0 | task 18883 | prompt eval time = 4060.70 ms / 297 tokens ( 13.67 ms per token, 73.14 tokens per second) 56.58.984.298 I slot print_timing: id 0 | task 18883 | eval time = 4086.38 ms / 34 tokens ( 123.83 ms per token, 8.08 tokens per second) 56.58.984.299 I slot print_timing: id 0 | task 18883 | total time = 8147.08 ms / 331 tokens 56.58.984.299 I slot print_timing: id 0 | task 18883 | graphs reused = 17906 56.58.984.300 I slot print_timing: id 0 | task 18883 | graph reallocs = 0 / 0 (same size) / (changed size) 56.58.984.326 I slot release: id 0 | task 18883 | stop processing: n_tokens = 362, truncated = 0 56.58.990.325 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 362, t_last = 102422735767 56.58.990.349 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 928.706 MiB) 56.59.152.897 I slot launch_slot_: id 0 | task 18920 | processing task, is_child = 0 57.02.970.065 I slot print_timing: id 0 | task 18920 | prompt processing, n_tokens = 339, progress = 0.99, t = 3.82 s / 88.81 tokens per second 57.15.898.298 I slot print_timing: id 0 | task 18920 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 57.18.999.801 I slot print_timing: id 0 | task 18920 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 57.21.606.876 I slot print_timing: id 0 | task 18920 | prompt eval time = 4464.11 ms / 343 tokens ( 13.01 ms per token, 76.84 tokens per second) 57.21.606.879 I slot print_timing: id 0 | task 18920 | eval time = 17989.86 ms / 146 tokens ( 124.07 ms per token, 8.06 tokens per second) 57.21.606.879 I slot print_timing: id 0 | task 18920 | total time = 22453.97 ms / 489 tokens 57.21.606.880 I slot print_timing: id 0 | task 18920 | graphs reused = 18049 57.21.606.880 I slot print_timing: id 0 | task 18920 | graph reallocs = 0 / 0 (same size) / (changed size) 57.21.607.288 I slot release: id 0 | task 18920 | stop processing: n_tokens = 520, truncated = 0 57.21.613.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 102445358730 57.21.613.606 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 922.204 MiB) 57.21.752.185 I slot launch_slot_: id 0 | task 19069 | processing task, is_child = 0 57.25.949.068 I slot print_timing: id 0 | task 19069 | prompt processing, n_tokens = 367, progress = 0.99, t = 4.20 s / 87.45 tokens per second 57.38.874.183 I slot print_timing: id 0 | task 19069 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.15 t/s 57.41.975.439 I slot print_timing: id 0 | task 19069 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 57.45.075.746 I slot print_timing: id 0 | task 19069 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 57.48.177.474 I slot print_timing: id 0 | task 19069 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.06 t/s 57.51.278.557 I slot print_timing: id 0 | task 19069 | n_gen = 200, tg = 8.06 t/s, tg_3s = 8.06 t/s 57.52.889.013 I slot print_timing: id 0 | task 19069 | prompt eval time = 4845.40 ms / 371 tokens ( 13.06 ms per token, 76.57 tokens per second) 57.52.889.018 I slot print_timing: id 0 | task 19069 | eval time = 26291.41 ms / 213 tokens ( 124.02 ms per token, 8.06 tokens per second) 57.52.889.018 I slot print_timing: id 0 | task 19069 | total time = 31136.81 ms / 584 tokens 57.52.889.019 I slot print_timing: id 0 | task 19069 | graphs reused = 18259 57.52.889.019 I slot print_timing: id 0 | task 19069 | graph reallocs = 0 / 0 (same size) / (changed size) 57.52.889.064 I slot release: id 0 | task 19069 | stop processing: n_tokens = 615, truncated = 0 57.52.893.812 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 615, t_last = 102476640505 57.52.893.848 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 940.210 MiB) 57.53.057.254 I slot launch_slot_: id 0 | task 19285 | processing task, is_child = 0 57.56.483.664 I slot print_timing: id 0 | task 19285 | prompt processing, n_tokens = 288, progress = 0.99, t = 3.43 s / 84.05 tokens per second 58.09.409.062 I slot print_timing: id 0 | task 19285 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 58.12.503.897 I slot print_timing: id 0 | task 19285 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.08 t/s 58.15.598.922 I slot print_timing: id 0 | task 19285 | n_gen = 150, tg = 8.07 t/s, tg_3s = 8.08 t/s 58.18.693.162 I slot print_timing: id 0 | task 19285 | n_gen = 175, tg = 8.07 t/s, tg_3s = 8.08 t/s 58.21.800.115 I slot print_timing: id 0 | task 19285 | n_gen = 200, tg = 8.07 t/s, tg_3s = 8.05 t/s 58.24.918.540 I slot print_timing: id 0 | task 19285 | n_gen = 225, tg = 8.06 t/s, tg_3s = 8.02 t/s 58.28.018.971 I slot print_timing: id 0 | task 19285 | n_gen = 250, tg = 8.06 t/s, tg_3s = 8.06 t/s 58.29.632.042 I slot print_timing: id 0 | task 19285 | prompt eval time = 4073.90 ms / 292 tokens ( 13.95 ms per token, 71.68 tokens per second) 58.29.632.046 I slot print_timing: id 0 | task 19285 | eval time = 32500.88 ms / 263 tokens ( 124.05 ms per token, 8.06 tokens per second) 58.29.632.047 I slot print_timing: id 0 | task 19285 | total time = 36574.78 ms / 555 tokens 58.29.632.047 I slot print_timing: id 0 | task 19285 | graphs reused = 18519 58.29.632.048 I slot print_timing: id 0 | task 19285 | graph reallocs = 0 / 0 (same size) / (changed size) 58.29.632.108 I slot release: id 0 | task 19285 | stop processing: n_tokens = 586, truncated = 0 58.29.638.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 586, t_last = 102513383549 58.29.638.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 970.971 MiB) 58.29.826.965 I slot launch_slot_: id 0 | task 19551 | processing task, is_child = 0 58.33.279.545 I slot print_timing: id 0 | task 19551 | prompt processing, n_tokens = 297, progress = 0.99, t = 3.45 s / 86.02 tokens per second 58.44.304.360 I slot print_timing: id 0 | task 19551 | prompt eval time = 4064.84 ms / 301 tokens ( 13.50 ms per token, 74.05 tokens per second) 58.44.304.364 I slot print_timing: id 0 | task 19551 | eval time = 10412.54 ms / 85 tokens ( 123.96 ms per token, 8.07 tokens per second) 58.44.304.364 I slot print_timing: id 0 | task 19551 | total time = 14477.38 ms / 386 tokens 58.44.304.365 I slot print_timing: id 0 | task 19551 | graphs reused = 18602 58.44.304.365 I slot print_timing: id 0 | task 19551 | graph reallocs = 0 / 0 (same size) / (changed size) 58.44.304.401 I slot release: id 0 | task 19551 | stop processing: n_tokens = 417, truncated = 0 58.44.310.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 417, t_last = 102528055842 58.44.310.418 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 963.469 MiB) 58.44.399.317 I slot launch_slot_: id 0 | task 19639 | processing task, is_child = 0 58.47.846.943 I slot print_timing: id 0 | task 19639 | prompt processing, n_tokens = 299, progress = 0.99, t = 3.45 s / 86.73 tokens per second 59.00.761.563 I slot print_timing: id 0 | task 19639 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 59.03.865.547 I slot print_timing: id 0 | task 19639 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.05 t/s 59.06.963.512 I slot print_timing: id 0 | task 19639 | n_gen = 150, tg = 8.07 t/s, tg_3s = 8.07 t/s 59.10.062.077 I slot print_timing: id 0 | task 19639 | n_gen = 175, tg = 8.07 t/s, tg_3s = 8.07 t/s 59.13.163.027 I slot print_timing: id 0 | task 19639 | n_gen = 200, tg = 8.07 t/s, tg_3s = 8.06 t/s 59.16.264.184 I slot print_timing: id 0 | task 19639 | n_gen = 225, tg = 8.07 t/s, tg_3s = 8.06 t/s 59.19.363.738 I slot print_timing: id 0 | task 19639 | n_gen = 250, tg = 8.07 t/s, tg_3s = 8.07 t/s 59.22.465.919 I slot print_timing: id 0 | task 19639 | n_gen = 275, tg = 8.07 t/s, tg_3s = 8.06 t/s 59.25.564.902 I slot print_timing: id 0 | task 19639 | n_gen = 300, tg = 8.07 t/s, tg_3s = 8.07 t/s 59.26.557.698 I slot print_timing: id 0 | task 19639 | prompt eval time = 4095.98 ms / 303 tokens ( 13.52 ms per token, 73.97 tokens per second) 59.26.557.703 I slot print_timing: id 0 | task 19639 | eval time = 38062.39 ms / 308 tokens ( 123.98 ms per token, 8.07 tokens per second) 59.26.557.704 I slot print_timing: id 0 | task 19639 | total time = 42158.37 ms / 611 tokens 59.26.557.704 I slot print_timing: id 0 | task 19639 | graphs reused = 18907 59.26.557.705 I slot print_timing: id 0 | task 19639 | graph reallocs = 0 / 0 (same size) / (changed size) 59.26.557.729 I slot release: id 0 | task 19639 | stop processing: n_tokens = 642, truncated = 0 59.26.562.125 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 642, t_last = 102570309170 59.26.562.157 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.892 MiB) 59.26.682.721 I slot launch_slot_: id 0 | task 19950 | processing task, is_child = 0 59.30.481.871 I slot print_timing: id 0 | task 19950 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.80 s / 83.44 tokens per second 59.43.402.226 I slot print_timing: id 0 | task 19950 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 59.44.147.529 I slot print_timing: id 0 | task 19950 | prompt eval time = 4447.02 ms / 321 tokens ( 13.85 ms per token, 72.18 tokens per second) 59.44.147.535 I slot print_timing: id 0 | task 19950 | eval time = 13017.77 ms / 106 tokens ( 123.98 ms per token, 8.07 tokens per second) 59.44.147.536 I slot print_timing: id 0 | task 19950 | total time = 17464.79 ms / 427 tokens 59.44.147.536 I slot print_timing: id 0 | task 19950 | graphs reused = 19011 59.44.147.537 I slot print_timing: id 0 | task 19950 | graph reallocs = 0 / 0 (same size) / (changed size) 59.44.147.575 I slot release: id 0 | task 19950 | stop processing: n_tokens = 458, truncated = 0 59.44.152.919 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 102587899016 59.44.152.950 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 935.146 MiB) 59.44.310.760 I slot launch_slot_: id 0 | task 20059 | processing task, is_child = 0 59.48.115.110 I slot print_timing: id 0 | task 20059 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.80 s / 83.59 tokens per second 60.01.036.140 I slot print_timing: id 0 | task 20059 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 60.01.159.962 I slot print_timing: id 0 | task 20059 | prompt eval time = 4451.35 ms / 322 tokens ( 13.82 ms per token, 72.34 tokens per second) 60.01.159.967 I slot print_timing: id 0 | task 20059 | eval time = 12397.83 ms / 101 tokens ( 123.98 ms per token, 8.07 tokens per second) 60.01.159.968 I slot print_timing: id 0 | task 20059 | total time = 16849.19 ms / 423 tokens 60.01.159.968 I slot print_timing: id 0 | task 20059 | graphs reused = 19110 60.01.159.969 I slot print_timing: id 0 | task 20059 | graph reallocs = 0 / 0 (same size) / (changed size) 60.01.160.012 I slot release: id 0 | task 20059 | stop processing: n_tokens = 454, truncated = 0 60.01.165.164 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 102604911453 60.01.165.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 925.330 MiB) 60.01.280.381 I slot launch_slot_: id 0 | task 20163 | processing task, is_child = 0 60.05.081.964 I slot print_timing: id 0 | task 20163 | prompt processing, n_tokens = 319, progress = 0.99, t = 3.80 s / 83.91 tokens per second 60.18.001.405 I slot print_timing: id 0 | task 20163 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 60.21.098.161 I slot print_timing: id 0 | task 20163 | n_gen = 125, tg = 8.07 t/s, tg_3s = 8.07 t/s 60.23.823.098 I slot print_timing: id 0 | task 20163 | prompt eval time = 4449.21 ms / 323 tokens ( 13.77 ms per token, 72.60 tokens per second) 60.23.823.100 I slot print_timing: id 0 | task 20163 | eval time = 18093.49 ms / 147 tokens ( 123.93 ms per token, 8.07 tokens per second) 60.23.823.101 I slot print_timing: id 0 | task 20163 | total time = 22542.70 ms / 470 tokens 60.23.823.101 I slot print_timing: id 0 | task 20163 | graphs reused = 19255 60.23.823.102 I slot print_timing: id 0 | task 20163 | graph reallocs = 0 / 0 (same size) / (changed size) 60.23.823.144 I slot release: id 0 | task 20163 | stop processing: n_tokens = 501, truncated = 0 60.23.828.653 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 501, t_last = 102627574585 60.23.828.692 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 920.390 MiB) 60.23.986.019 I slot launch_slot_: id 0 | task 20313 | processing task, is_child = 0 60.27.776.676 I slot print_timing: id 0 | task 20313 | prompt processing, n_tokens = 317, progress = 0.99, t = 3.79 s / 83.63 tokens per second 60.40.665.808 I slot print_timing: id 0 | task 20313 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 60.43.767.875 I slot print_timing: id 0 | task 20313 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 60.46.869.616 I slot print_timing: id 0 | task 20313 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.06 t/s 60.49.977.983 I slot print_timing: id 0 | task 20313 | n_gen = 175, tg = 8.06 t/s, tg_3s = 8.04 t/s 60.53.084.630 I slot print_timing: id 0 | task 20313 | n_gen = 200, tg = 8.06 t/s, tg_3s = 8.05 t/s 60.56.190.055 I slot print_timing: id 0 | task 20313 | n_gen = 225, tg = 8.06 t/s, tg_3s = 8.05 t/s 60.59.293.255 I slot print_timing: id 0 | task 20313 | n_gen = 250, tg = 8.06 t/s, tg_3s = 8.06 t/s 61.02.323.050 I slot print_timing: id 0 | task 20313 | n_gen = 274, tg = 8.05 t/s, tg_3s = 7.92 t/s 61.05.433.906 I slot print_timing: id 0 | task 20313 | n_gen = 299, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.08.539.334 I slot print_timing: id 0 | task 20313 | n_gen = 324, tg = 8.05 t/s, tg_3s = 8.05 t/s 61.11.645.856 I slot print_timing: id 0 | task 20313 | n_gen = 349, tg = 8.05 t/s, tg_3s = 8.05 t/s 61.14.752.542 I slot print_timing: id 0 | task 20313 | n_gen = 374, tg = 8.05 t/s, tg_3s = 8.05 t/s 61.17.859.013 I slot print_timing: id 0 | task 20313 | n_gen = 399, tg = 8.05 t/s, tg_3s = 8.05 t/s 61.20.976.598 I slot print_timing: id 0 | task 20313 | n_gen = 424, tg = 8.04 t/s, tg_3s = 8.02 t/s 61.24.081.863 I slot print_timing: id 0 | task 20313 | n_gen = 449, tg = 8.04 t/s, tg_3s = 8.05 t/s 61.27.197.640 I slot print_timing: id 0 | task 20313 | n_gen = 474, tg = 8.04 t/s, tg_3s = 8.02 t/s 61.30.305.843 I slot print_timing: id 0 | task 20313 | n_gen = 499, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.33.415.086 I slot print_timing: id 0 | task 20313 | n_gen = 524, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.36.525.178 I slot print_timing: id 0 | task 20313 | n_gen = 549, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.39.635.812 I slot print_timing: id 0 | task 20313 | n_gen = 574, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.42.747.569 I slot print_timing: id 0 | task 20313 | n_gen = 599, tg = 8.04 t/s, tg_3s = 8.03 t/s 61.45.857.547 I slot print_timing: id 0 | task 20313 | n_gen = 624, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.48.972.423 I slot print_timing: id 0 | task 20313 | n_gen = 649, tg = 8.04 t/s, tg_3s = 8.03 t/s 61.52.090.161 I slot print_timing: id 0 | task 20313 | n_gen = 674, tg = 8.04 t/s, tg_3s = 8.02 t/s 61.55.201.188 I slot print_timing: id 0 | task 20313 | n_gen = 699, tg = 8.04 t/s, tg_3s = 8.04 t/s 61.58.306.987 I slot print_timing: id 0 | task 20313 | n_gen = 724, tg = 8.04 t/s, tg_3s = 8.05 t/s 62.01.418.879 I slot print_timing: id 0 | task 20313 | n_gen = 749, tg = 8.04 t/s, tg_3s = 8.03 t/s 62.04.542.921 I slot print_timing: id 0 | task 20313 | n_gen = 774, tg = 8.04 t/s, tg_3s = 8.00 t/s 62.07.660.897 I slot print_timing: id 0 | task 20313 | n_gen = 799, tg = 8.04 t/s, tg_3s = 8.02 t/s 62.08.656.134 I slot print_timing: id 0 | task 20313 | prompt eval time = 4405.20 ms / 321 tokens ( 13.72 ms per token, 72.87 tokens per second) 62.08.656.139 I slot print_timing: id 0 | task 20313 | eval time = 100264.91 ms / 807 tokens ( 124.40 ms per token, 8.04 tokens per second) 62.08.656.140 I slot print_timing: id 0 | task 20313 | total time = 104670.10 ms / 1128 tokens 62.08.656.141 I slot print_timing: id 0 | task 20313 | graphs reused = 20057 62.08.656.141 I slot print_timing: id 0 | task 20313 | graph reallocs = 0 / 0 (same size) / (changed size) 62.08.656.224 I slot release: id 0 | task 20313 | stop processing: n_tokens = 1159, truncated = 0 62.08.663.392 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1159, t_last = 102732407665 62.08.663.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.269 MiB) 62.08.889.469 I slot launch_slot_: id 0 | task 21123 | processing task, is_child = 0 62.12.697.785 I slot print_timing: id 0 | task 21123 | prompt processing, n_tokens = 318, progress = 0.99, t = 3.81 s / 83.50 tokens per second 62.25.596.518 I slot print_timing: id 0 | task 21123 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.14 t/s 62.28.710.869 I slot print_timing: id 0 | task 21123 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.03 t/s 62.31.811.776 I slot print_timing: id 0 | task 21123 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.06 t/s 62.34.917.271 I slot print_timing: id 0 | task 21123 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.05 t/s 62.38.018.098 I slot print_timing: id 0 | task 21123 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.06 t/s 62.39.382.239 I slot print_timing: id 0 | task 21123 | prompt eval time = 4415.67 ms / 322 tokens ( 13.71 ms per token, 72.92 tokens per second) 62.39.382.242 I slot print_timing: id 0 | task 21123 | eval time = 26077.09 ms / 211 tokens ( 124.18 ms per token, 8.05 tokens per second) 62.39.382.243 I slot print_timing: id 0 | task 21123 | total time = 30492.76 ms / 533 tokens 62.39.382.243 I slot print_timing: id 0 | task 21123 | graphs reused = 20265 62.39.382.244 I slot print_timing: id 0 | task 21123 | graph reallocs = 0 / 0 (same size) / (changed size) 62.39.382.760 I slot release: id 0 | task 21123 | stop processing: n_tokens = 564, truncated = 0 62.39.393.045 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 564, t_last = 102763134201 62.39.393.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 936.209 MiB) 62.39.570.860 I slot launch_slot_: id 0 | task 21337 | processing task, is_child = 0 62.43.380.764 I slot print_timing: id 0 | task 21337 | prompt processing, n_tokens = 333, progress = 0.99, t = 3.81 s / 87.40 tokens per second 62.49.607.764 I slot print_timing: id 0 | task 21337 | prompt eval time = 4455.64 ms / 337 tokens ( 13.22 ms per token, 75.63 tokens per second) 62.49.607.767 I slot print_timing: id 0 | task 21337 | eval time = 5581.25 ms / 46 tokens ( 124.03 ms per token, 8.06 tokens per second) 62.49.607.767 I slot print_timing: id 0 | task 21337 | total time = 10036.89 ms / 383 tokens 62.49.607.768 I slot print_timing: id 0 | task 21337 | graphs reused = 20309 62.49.607.768 I slot print_timing: id 0 | task 21337 | graph reallocs = 0 / 0 (same size) / (changed size) 62.49.607.823 I slot release: id 0 | task 21337 | stop processing: n_tokens = 414, truncated = 0 62.49.614.041 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 102773359264 62.49.614.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 934.396 MiB) 62.49.844.246 I slot launch_slot_: id 0 | task 21386 | processing task, is_child = 0 62.53.651.029 I slot print_timing: id 0 | task 21386 | prompt processing, n_tokens = 321, progress = 0.99, t = 3.81 s / 84.32 tokens per second 63.00.003.902 I slot print_timing: id 0 | task 21386 | prompt eval time = 4456.15 ms / 325 tokens ( 13.71 ms per token, 72.93 tokens per second) 63.00.003.904 I slot print_timing: id 0 | task 21386 | eval time = 5703.50 ms / 47 tokens ( 123.99 ms per token, 8.07 tokens per second) 63.00.003.904 I slot print_timing: id 0 | task 21386 | total time = 10159.64 ms / 372 tokens 63.00.003.905 I slot print_timing: id 0 | task 21386 | graphs reused = 20354 63.00.003.905 I slot print_timing: id 0 | task 21386 | graph reallocs = 0 / 0 (same size) / (changed size) 63.00.003.954 I slot release: id 0 | task 21386 | stop processing: n_tokens = 403, truncated = 0 63.00.011.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 102783755395 63.00.011.435 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.829 MiB) 63.00.165.935 I slot launch_slot_: id 0 | task 21436 | processing task, is_child = 0 63.03.971.322 I slot print_timing: id 0 | task 21436 | prompt processing, n_tokens = 327, progress = 0.99, t = 3.81 s / 85.93 tokens per second 63.16.892.440 I slot print_timing: id 0 | task 21436 | n_gen = 100, tg = 8.07 t/s, tg_3s = 8.15 t/s 63.19.998.641 I slot print_timing: id 0 | task 21436 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.05 t/s 63.23.098.055 I slot print_timing: id 0 | task 21436 | n_gen = 150, tg = 8.06 t/s, tg_3s = 8.07 t/s 63.25.207.268 I slot print_timing: id 0 | task 21436 | prompt eval time = 4451.74 ms / 331 tokens ( 13.45 ms per token, 74.35 tokens per second) 63.25.207.274 I slot print_timing: id 0 | task 21436 | eval time = 20589.58 ms / 167 tokens ( 124.03 ms per token, 8.06 tokens per second) 63.25.207.274 I slot print_timing: id 0 | task 21436 | total time = 25041.32 ms / 498 tokens 63.25.207.275 I slot print_timing: id 0 | task 21436 | graphs reused = 20518 63.25.207.275 I slot print_timing: id 0 | task 21436 | graph reallocs = 0 / 0 (same size) / (changed size) 63.25.207.307 I slot release: id 0 | task 21436 | stop processing: n_tokens = 529, truncated = 0 63.25.215.574 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 529, t_last = 102808958748 63.25.215.603 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 937.897 MiB) 63.25.370.867 I slot launch_slot_: id 0 | task 21606 | processing task, is_child = 0 63.29.184.327 I slot print_timing: id 0 | task 21606 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.81 s / 87.06 tokens per second 63.42.076.631 I slot print_timing: id 0 | task 21606 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 63.44.058.552 I slot print_timing: id 0 | task 21606 | prompt eval time = 4420.03 ms / 336 tokens ( 13.15 ms per token, 76.02 tokens per second) 63.44.058.556 I slot print_timing: id 0 | task 21606 | eval time = 14267.64 ms / 116 tokens ( 124.07 ms per token, 8.06 tokens per second) 63.44.058.557 I slot print_timing: id 0 | task 21606 | total time = 18687.67 ms / 452 tokens 63.44.058.557 I slot print_timing: id 0 | task 21606 | graphs reused = 20632 63.44.058.558 I slot print_timing: id 0 | task 21606 | graph reallocs = 0 / 0 (same size) / (changed size) 63.44.058.589 I slot release: id 0 | task 21606 | stop processing: n_tokens = 483, truncated = 0 63.44.066.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 102827810030 63.44.066.237 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.393 MiB) 63.44.208.813 I slot launch_slot_: id 0 | task 21725 | processing task, is_child = 0 63.48.389.159 I slot print_timing: id 0 | task 21725 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.18 s / 82.53 tokens per second 63.52.761.983 I slot print_timing: id 0 | task 21725 | prompt eval time = 4830.39 ms / 349 tokens ( 13.84 ms per token, 72.25 tokens per second) 63.52.761.988 I slot print_timing: id 0 | task 21725 | eval time = 3722.77 ms / 31 tokens ( 124.09 ms per token, 8.06 tokens per second) 63.52.761.989 I slot print_timing: id 0 | task 21725 | total time = 8553.16 ms / 380 tokens 63.52.761.989 I slot print_timing: id 0 | task 21725 | graphs reused = 20661 63.52.761.990 I slot print_timing: id 0 | task 21725 | graph reallocs = 0 / 0 (same size) / (changed size) 63.52.762.035 I slot release: id 0 | task 21725 | stop processing: n_tokens = 411, truncated = 0 63.52.770.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 411, t_last = 102836513476 63.52.770.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.143 MiB) 63.52.892.034 I slot launch_slot_: id 0 | task 21759 | processing task, is_child = 0 63.56.713.185 I slot print_timing: id 0 | task 21759 | prompt processing, n_tokens = 332, progress = 0.99, t = 3.82 s / 86.89 tokens per second 64.09.622.213 I slot print_timing: id 0 | task 21759 | n_gen = 100, tg = 8.05 t/s, tg_3s = 8.13 t/s 64.12.725.128 I slot print_timing: id 0 | task 21759 | n_gen = 125, tg = 8.05 t/s, tg_3s = 8.06 t/s 64.15.830.549 I slot print_timing: id 0 | task 21759 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.05 t/s 64.18.931.175 I slot print_timing: id 0 | task 21759 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.06 t/s 64.22.038.481 I slot print_timing: id 0 | task 21759 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 64.25.146.923 I slot print_timing: id 0 | task 21759 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.04 t/s 64.28.250.676 I slot print_timing: id 0 | task 21759 | n_gen = 250, tg = 8.05 t/s, tg_3s = 8.06 t/s 64.31.357.709 I slot print_timing: id 0 | task 21759 | n_gen = 275, tg = 8.05 t/s, tg_3s = 8.04 t/s 64.34.469.446 I slot print_timing: id 0 | task 21759 | n_gen = 300, tg = 8.05 t/s, tg_3s = 8.03 t/s 64.37.577.385 I slot print_timing: id 0 | task 21759 | n_gen = 325, tg = 8.05 t/s, tg_3s = 8.04 t/s 64.40.686.112 I slot print_timing: id 0 | task 21759 | n_gen = 350, tg = 8.05 t/s, tg_3s = 8.04 t/s 64.43.796.757 I slot print_timing: id 0 | task 21759 | n_gen = 375, tg = 8.05 t/s, tg_3s = 8.04 t/s 64.46.899.653 I slot print_timing: id 0 | task 21759 | n_gen = 400, tg = 8.05 t/s, tg_3s = 8.06 t/s 64.50.015.384 I slot print_timing: id 0 | task 21759 | n_gen = 425, tg = 8.05 t/s, tg_3s = 8.02 t/s 64.53.118.174 I slot print_timing: id 0 | task 21759 | n_gen = 450, tg = 8.05 t/s, tg_3s = 8.06 t/s 64.56.226.938 I slot print_timing: id 0 | task 21759 | n_gen = 475, tg = 8.05 t/s, tg_3s = 8.04 t/s 64.59.332.538 I slot print_timing: id 0 | task 21759 | n_gen = 500, tg = 8.05 t/s, tg_3s = 8.05 t/s 65.02.440.755 I slot print_timing: id 0 | task 21759 | n_gen = 525, tg = 8.05 t/s, tg_3s = 8.04 t/s 65.05.549.915 I slot print_timing: id 0 | task 21759 | n_gen = 550, tg = 8.05 t/s, tg_3s = 8.04 t/s 65.08.663.457 I slot print_timing: id 0 | task 21759 | n_gen = 575, tg = 8.05 t/s, tg_3s = 8.03 t/s 65.11.774.077 I slot print_timing: id 0 | task 21759 | n_gen = 600, tg = 8.05 t/s, tg_3s = 8.04 t/s 65.14.886.530 I slot print_timing: id 0 | task 21759 | n_gen = 625, tg = 8.05 t/s, tg_3s = 8.03 t/s 65.17.998.188 I slot print_timing: id 0 | task 21759 | n_gen = 650, tg = 8.04 t/s, tg_3s = 8.03 t/s 65.21.116.780 I slot print_timing: id 0 | task 21759 | n_gen = 675, tg = 8.04 t/s, tg_3s = 8.02 t/s 65.24.226.226 I slot print_timing: id 0 | task 21759 | n_gen = 700, tg = 8.04 t/s, tg_3s = 8.04 t/s 65.27.342.033 I slot print_timing: id 0 | task 21759 | n_gen = 725, tg = 8.04 t/s, tg_3s = 8.02 t/s 65.30.450.479 I slot print_timing: id 0 | task 21759 | n_gen = 750, tg = 8.04 t/s, tg_3s = 8.04 t/s 65.33.566.218 I slot print_timing: id 0 | task 21759 | n_gen = 775, tg = 8.04 t/s, tg_3s = 8.02 t/s 65.36.687.393 I slot print_timing: id 0 | task 21759 | n_gen = 800, tg = 8.04 t/s, tg_3s = 8.01 t/s 65.39.801.035 I slot print_timing: id 0 | task 21759 | n_gen = 825, tg = 8.04 t/s, tg_3s = 8.03 t/s 65.42.915.760 I slot print_timing: id 0 | task 21759 | n_gen = 850, tg = 8.04 t/s, tg_3s = 8.03 t/s 65.43.414.932 I slot print_timing: id 0 | task 21759 | prompt eval time = 4432.36 ms / 336 tokens ( 13.19 ms per token, 75.81 tokens per second) 65.43.414.935 I slot print_timing: id 0 | task 21759 | eval time = 106090.53 ms / 854 tokens ( 124.37 ms per token, 8.04 tokens per second) 65.43.414.935 I slot print_timing: id 0 | task 21759 | total time = 110522.89 ms / 1190 tokens 65.43.414.936 I slot print_timing: id 0 | task 21759 | graphs reused = 21510 65.43.414.936 I slot print_timing: id 0 | task 21759 | graph reallocs = 0 / 0 (same size) / (changed size) 65.43.414.976 I slot release: id 0 | task 21759 | stop processing: n_tokens = 1221, truncated = 0 65.43.423.242 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1221, t_last = 102947166417 65.43.423.292 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 929.081 MiB) 65.43.628.802 I slot launch_slot_: id 0 | task 22616 | processing task, is_child = 0 65.47.814.431 I slot print_timing: id 0 | task 22616 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.19 s / 82.43 tokens per second 66.00.718.796 I slot print_timing: id 0 | task 22616 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 66.03.822.538 I slot print_timing: id 0 | task 22616 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.05 t/s 66.06.930.971 I slot print_timing: id 0 | task 22616 | n_gen = 150, tg = 8.05 t/s, tg_3s = 8.04 t/s 66.10.031.937 I slot print_timing: id 0 | task 22616 | n_gen = 175, tg = 8.05 t/s, tg_3s = 8.06 t/s 66.13.136.487 I slot print_timing: id 0 | task 22616 | n_gen = 200, tg = 8.05 t/s, tg_3s = 8.05 t/s 66.16.240.233 I slot print_timing: id 0 | task 22616 | n_gen = 225, tg = 8.05 t/s, tg_3s = 8.05 t/s 66.19.345.448 I slot print_timing: id 0 | task 22616 | n_gen = 250, tg = 8.05 t/s, tg_3s = 8.05 t/s 66.22.447.859 I slot print_timing: id 0 | task 22616 | n_gen = 275, tg = 8.05 t/s, tg_3s = 8.06 t/s 66.25.560.678 I slot print_timing: id 0 | task 22616 | n_gen = 300, tg = 8.05 t/s, tg_3s = 8.03 t/s 66.28.671.812 I slot print_timing: id 0 | task 22616 | n_gen = 325, tg = 8.05 t/s, tg_3s = 8.04 t/s 66.31.780.258 I slot print_timing: id 0 | task 22616 | n_gen = 350, tg = 8.05 t/s, tg_3s = 8.04 t/s 66.34.888.225 I slot print_timing: id 0 | task 22616 | n_gen = 375, tg = 8.05 t/s, tg_3s = 8.04 t/s 66.38.000.807 I slot print_timing: id 0 | task 22616 | n_gen = 400, tg = 8.05 t/s, tg_3s = 8.03 t/s 66.41.105.676 I slot print_timing: id 0 | task 22616 | n_gen = 425, tg = 8.05 t/s, tg_3s = 8.05 t/s 66.43.483.657 I slot print_timing: id 0 | task 22616 | prompt eval time = 4799.80 ms / 349 tokens ( 13.75 ms per token, 72.71 tokens per second) 66.43.483.660 I slot print_timing: id 0 | task 22616 | eval time = 55055.04 ms / 444 tokens ( 124.28 ms per token, 8.05 tokens per second) 66.43.483.661 I slot print_timing: id 0 | task 22616 | total time = 59854.84 ms / 793 tokens 66.43.483.661 I slot print_timing: id 0 | task 22616 | graphs reused = 21950 66.43.483.662 I slot print_timing: id 0 | task 22616 | graph reallocs = 0 / 0 (same size) / (changed size) 66.43.483.710 I slot release: id 0 | task 22616 | stop processing: n_tokens = 824, truncated = 0 66.43.491.376 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 103007235151 66.43.491.423 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 970.221 MiB) 66.43.820.936 I slot launch_slot_: id 0 | task 23063 | processing task, is_child = 0 66.47.999.966 I slot print_timing: id 0 | task 23063 | prompt processing, n_tokens = 345, progress = 0.99, t = 4.18 s / 82.56 tokens per second 67.00.894.992 I slot print_timing: id 0 | task 23063 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 67.03.995.915 I slot print_timing: id 0 | task 23063 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.06 t/s 67.05.487.758 I slot print_timing: id 0 | task 23063 | prompt eval time = 4792.16 ms / 349 tokens ( 13.73 ms per token, 72.83 tokens per second) 67.05.487.763 I slot print_timing: id 0 | task 23063 | eval time = 16874.65 ms / 137 tokens ( 124.08 ms per token, 8.06 tokens per second) 67.05.487.764 I slot print_timing: id 0 | task 23063 | total time = 21666.81 ms / 486 tokens 67.05.487.771 I slot print_timing: id 0 | task 23063 | graphs reused = 22084 67.05.487.773 I slot print_timing: id 0 | task 23063 | graph reallocs = 0 / 0 (same size) / (changed size) 67.05.487.797 I slot release: id 0 | task 23063 | stop processing: n_tokens = 517, truncated = 0 67.05.493.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 103029239238 67.05.493.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 933.020 MiB) 67.05.619.774 I slot launch_slot_: id 0 | task 23203 | processing task, is_child = 0 67.10.200.435 I slot print_timing: id 0 | task 23203 | prompt processing, n_tokens = 381, progress = 0.99, t = 4.58 s / 83.18 tokens per second 67.23.130.346 I slot print_timing: id 0 | task 23203 | n_gen = 100, tg = 8.06 t/s, tg_3s = 8.14 t/s 67.26.229.444 I slot print_timing: id 0 | task 23203 | n_gen = 125, tg = 8.06 t/s, tg_3s = 8.07 t/s 67.28.215.656 I slot print_timing: id 0 | task 23203 | prompt eval time = 5224.62 ms / 385 tokens ( 13.57 ms per token, 73.69 tokens per second) 67.28.215.661 I slot print_timing: id 0 | task 23203 | eval time = 17371.25 ms / 141 tokens ( 124.08 ms per token, 8.06 tokens per second) 67.28.215.661 I slot print_timing: id 0 | task 23203 | total time = 22595.87 ms / 526 tokens 67.28.215.662 I slot print_timing: id 0 | task 23203 | graphs reused = 22222 67.28.215.662 I slot print_timing: id 0 | task 23203 | graph reallocs = 0 / 0 (same size) / (changed size) 67.28.218.781 I slot release: id 0 | task 23203 | stop processing: n_tokens = 557, truncated = 0 67.28.230.309 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 557, t_last = 103051970223 67.28.230.347 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 923.642 MiB) 67.28.458.941 I slot launch_slot_: id 0 | task 23347 | processing task, is_child = 0 67.32.268.258 I slot print_timing: id 0 | task 23347 | prompt processing, n_tokens = 324, progress = 0.99, t = 3.81 s / 85.06 tokens per second 67.39.867.999 I slot print_timing: id 0 | task 23347 | prompt eval time = 4457.95 ms / 328 tokens ( 13.59 ms per token, 73.58 tokens per second) 67.39.868.001 I slot print_timing: id 0 | task 23347 | eval time = 6951.07 ms / 57 tokens ( 124.13 ms per token, 8.06 tokens per second) 67.39.868.003 I slot print_timing: id 0 | task 23347 | total time = 11409.02 ms / 385 tokens 67.39.868.003 I slot print_timing: id 0 | task 23347 | graphs reused = 22277 67.39.868.004 I slot print_timing: id 0 | task 23347 | graph reallocs = 0 / 0 (same size) / (changed size) 67.39.868.037 I slot release: id 0 | task 23347 | stop processing: n_tokens = 416, truncated = 0 67.40.287.427 I srv operator(): operator(): cleaning up before exit...