$ /Users/minipro/quantdiff/work/llama-b11869/src/build/bin/llama-server -m /Users/minipro/quantdiff/models/campaign/1ba3362152b9/Sage-A1.5.i1-Q2_K.gguf --host 127.0.0.1 --port 8089 -c 4096 -np 1 -ngl 999 -fa on --jinja --seed 1234 --no-webui -a quant 0.00.044.894 I srv llama_server: initializing ... 0.00.044.901 I cmn common_param: common_params_print_info: verbosity = 3 (adjust with the `-lv N` CLI arg) 0.00.046.759 I srv init_listene: The UI is disabled 0.00.046.761 I srv init_listene: Use --ui/--no-ui (or deprecated --webui/--no-webui) to enable/disable 0.00.047.067 W srv server_setup: security: no API key is set and CORS allows all origins (see https://github.com/ggml-org/llama.cpp/pull/25655) 0.00.049.205 I srv load_model: loading model '/Users/minipro/quantdiff/models/campaign/1ba3362152b9/Sage-A1.5.i1-Q2_K.gguf' 0.00.336.925 W model has unused tensor blk.40.attn_norm.weight (size = 8192 bytes) -- ignoring 0.00.336.933 W model has unused tensor blk.40.post_attention_norm.weight (size = 8192 bytes) -- ignoring 0.00.336.940 W model has unused tensor blk.40.attn_q.weight (size = 5505024 bytes) -- ignoring 0.00.336.943 W model has unused tensor blk.40.attn_k.weight (size = 344064 bytes) -- ignoring 0.00.336.945 W model has unused tensor blk.40.attn_v.weight (size = 589824 bytes) -- ignoring 0.00.336.952 W model has unused tensor blk.40.attn_output.weight (size = 3604480 bytes) -- ignoring 0.00.336.954 W model has unused tensor blk.40.attn_q_norm.weight (size = 1024 bytes) -- ignoring 0.00.336.956 W model has unused tensor blk.40.attn_k_norm.weight (size = 1024 bytes) -- ignoring 0.00.336.959 W model has unused tensor blk.40.ffn_gate_inp.weight (size = 2097152 bytes) -- ignoring 0.00.336.961 W model has unused tensor blk.40.ffn_down_exps.weight (size = 115343360 bytes) -- ignoring 0.00.336.965 W model has unused tensor blk.40.ffn_gate_exps.weight (size = 88080384 bytes) -- ignoring 0.00.336.967 W model has unused tensor blk.40.ffn_up_exps.weight (size = 88080384 bytes) -- ignoring 0.00.336.970 W model has unused tensor blk.40.ffn_gate_inp_shexp.weight (size = 8192 bytes) -- ignoring 0.00.336.972 W model has unused tensor blk.40.ffn_gate_shexp.weight (size = 344064 bytes) -- ignoring 0.00.336.974 W model has unused tensor blk.40.ffn_up_shexp.weight (size = 344064 bytes) -- ignoring 0.00.336.977 W model has unused tensor blk.40.ffn_down_shexp.weight (size = 450560 bytes) -- ignoring 0.00.336.980 W model has unused tensor blk.40.nextn.eh_proj.weight (size = 2752512 bytes) -- ignoring 0.00.336.982 W model has unused tensor blk.40.nextn.enorm.weight (size = 8192 bytes) -- ignoring 0.00.336.984 W model has unused tensor blk.40.nextn.hnorm.weight (size = 8192 bytes) -- ignoring 0.00.336.991 W model has unused tensor blk.40.nextn.shared_head_norm.weight (size = 8192 bytes) -- ignoring 0.00.922.504 I cmn init: llama threadpool init, n_threads = 8 0.01.110.018 I srv load_model: initializing, n_slots = 1, n_ctx_slot = 4096, kv_unified = 'false' 0.01.116.805 W srv init: chat template supports preserving reasoning, it is enabled by default (may use more tokens, disable via --no-reasoning-preserve) 0.01.116.827 I srv server_run_i: model loaded 0.01.116.831 I srv server_on_li: listening on http://127.0.0.1:8089 0.02.023.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 0, t_last = -1 0.02.023.980 I slot launch_slot_: id 0 | task 0 | processing task, is_child = 0 0.03.887.881 I slot print_timing: id 0 | task 0 | prompt eval time = 1047.59 ms / 368 tokens ( 2.85 ms per token, 351.28 tokens per second) 0.03.887.884 I slot print_timing: id 0 | task 0 | eval time = 816.28 ms / 41 tokens ( 20.41 ms per token, 49.00 tokens per second) 0.03.887.885 I slot print_timing: id 0 | task 0 | total time = 1863.86 ms / 409 tokens 0.03.887.885 I slot print_timing: id 0 | task 0 | graphs reused = 40 0.03.887.886 I slot print_timing: id 0 | task 0 | graph reallocs = 0 / 0 (same size) / (changed size) 0.03.887.922 I slot release: id 0 | task 0 | stop processing: n_tokens = 408, truncated = 0 0.03.893.627 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 408, t_last = 389195149841 0.03.912.188 I slot launch_slot_: id 0 | task 44 | processing task, is_child = 0 0.05.522.078 I slot print_timing: id 0 | task 44 | prompt eval time = 772.74 ms / 322 tokens ( 2.40 ms per token, 416.70 tokens per second) 0.05.522.083 I slot print_timing: id 0 | task 44 | eval time = 837.14 ms / 42 tokens ( 20.42 ms per token, 48.98 tokens per second) 0.05.522.084 I slot print_timing: id 0 | task 44 | total time = 1609.88 ms / 364 tokens 0.05.522.085 I slot print_timing: id 0 | task 44 | graphs reused = 80 0.05.522.085 I slot print_timing: id 0 | task 44 | graph reallocs = 0 / 0 (same size) / (changed size) 0.05.522.116 I slot release: id 0 | task 44 | stop processing: n_tokens = 363, truncated = 0 0.05.526.639 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 363, t_last = 389196784035 0.05.544.667 I slot launch_slot_: id 0 | task 89 | processing task, is_child = 0 0.07.222.265 I slot print_timing: id 0 | task 89 | prompt eval time = 839.42 ms / 365 tokens ( 2.30 ms per token, 434.82 tokens per second) 0.07.222.272 I slot print_timing: id 0 | task 89 | eval time = 838.16 ms / 42 tokens ( 20.44 ms per token, 48.92 tokens per second) 0.07.222.272 I slot print_timing: id 0 | task 89 | total time = 1677.59 ms / 407 tokens 0.07.222.273 I slot print_timing: id 0 | task 89 | graphs reused = 120 0.07.222.273 I slot print_timing: id 0 | task 89 | graph reallocs = 0 / 0 (same size) / (changed size) 0.07.222.304 I slot release: id 0 | task 89 | stop processing: n_tokens = 406, truncated = 0 0.07.226.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 389198484223 0.07.244.463 I slot launch_slot_: id 0 | task 134 | processing task, is_child = 0 0.09.001.975 I slot print_timing: id 0 | task 134 | prompt eval time = 898.21 ms / 397 tokens ( 2.26 ms per token, 441.99 tokens per second) 0.09.001.980 I slot print_timing: id 0 | task 134 | eval time = 859.29 ms / 43 tokens ( 20.46 ms per token, 48.88 tokens per second) 0.09.001.981 I slot print_timing: id 0 | task 134 | total time = 1757.49 ms / 440 tokens 0.09.001.982 I slot print_timing: id 0 | task 134 | graphs reused = 161 0.09.001.982 I slot print_timing: id 0 | task 134 | graph reallocs = 0 / 0 (same size) / (changed size) 0.09.002.016 I slot release: id 0 | task 134 | stop processing: n_tokens = 439, truncated = 0 0.09.006.556 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 0.09.024.737 I slot launch_slot_: id 0 | task 180 | processing task, is_child = 0 0.10.953.418 I slot print_timing: id 0 | task 180 | prompt eval time = 840.29 ms / 383 tokens ( 2.19 ms per token, 455.80 tokens per second) 0.10.953.422 I slot print_timing: id 0 | task 180 | eval time = 1088.38 ms / 55 tokens ( 20.16 ms per token, 49.61 tokens per second) 0.10.953.422 I slot print_timing: id 0 | task 180 | total time = 1928.67 ms / 438 tokens 0.10.953.423 I slot print_timing: id 0 | task 180 | graphs reused = 214 0.10.953.423 I slot print_timing: id 0 | task 180 | graph reallocs = 0 / 0 (same size) / (changed size) 0.10.953.456 I slot release: id 0 | task 180 | stop processing: n_tokens = 437, truncated = 0 0.10.958.092 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 389202215375 0.10.975.236 I slot launch_slot_: id 0 | task 238 | processing task, is_child = 0 0.12.888.405 I slot print_timing: id 0 | task 238 | prompt eval time = 807.22 ms / 372 tokens ( 2.17 ms per token, 460.84 tokens per second) 0.12.888.412 I slot print_timing: id 0 | task 238 | eval time = 1105.94 ms / 55 tokens ( 20.48 ms per token, 48.83 tokens per second) 0.12.888.413 I slot print_timing: id 0 | task 238 | total time = 1913.16 ms / 427 tokens 0.12.888.413 I slot print_timing: id 0 | task 238 | graphs reused = 267 0.12.888.414 I slot print_timing: id 0 | task 238 | graph reallocs = 0 / 0 (same size) / (changed size) 0.12.888.442 I slot release: id 0 | task 238 | stop processing: n_tokens = 426, truncated = 0 0.12.893.176 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 389204150361 0.12.911.069 I slot launch_slot_: id 0 | task 296 | processing task, is_child = 0 0.14.941.347 I slot print_timing: id 0 | task 296 | prompt eval time = 923.79 ms / 422 tokens ( 2.19 ms per token, 456.82 tokens per second) 0.14.941.354 I slot print_timing: id 0 | task 296 | eval time = 1106.48 ms / 55 tokens ( 20.49 ms per token, 48.80 tokens per second) 0.14.941.355 I slot print_timing: id 0 | task 296 | total time = 2030.27 ms / 477 tokens 0.14.941.356 I slot print_timing: id 0 | task 296 | graphs reused = 320 0.14.941.356 I slot print_timing: id 0 | task 296 | graph reallocs = 0 / 0 (same size) / (changed size) 0.14.941.394 I slot release: id 0 | task 296 | stop processing: n_tokens = 476, truncated = 0 0.14.946.305 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 476, t_last = 389206203313 0.14.964.412 I slot launch_slot_: id 0 | task 354 | processing task, is_child = 0 0.17.378.780 I slot print_timing: id 0 | task 354 | prompt eval time = 953.20 ms / 470 tokens ( 2.03 ms per token, 493.08 tokens per second) 0.17.378.786 I slot print_timing: id 0 | task 354 | eval time = 1461.16 ms / 72 tokens ( 20.58 ms per token, 48.59 tokens per second) 0.17.378.787 I slot print_timing: id 0 | task 354 | total time = 2414.36 ms / 542 tokens 0.17.378.787 I slot print_timing: id 0 | task 354 | graphs reused = 389 0.17.378.788 I slot print_timing: id 0 | task 354 | graph reallocs = 0 / 0 (same size) / (changed size) 0.17.378.824 I slot release: id 0 | task 354 | stop processing: n_tokens = 541, truncated = 0 0.17.383.315 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 541, t_last = 389208640743 0.17.401.981 I slot launch_slot_: id 0 | task 429 | processing task, is_child = 0 0.19.155.175 I slot print_timing: id 0 | task 429 | prompt eval time = 813.21 ms / 345 tokens ( 2.36 ms per token, 424.24 tokens per second) 0.19.155.181 I slot print_timing: id 0 | task 429 | eval time = 939.97 ms / 47 tokens ( 20.43 ms per token, 48.94 tokens per second) 0.19.155.182 I slot print_timing: id 0 | task 429 | total time = 1753.18 ms / 392 tokens 0.19.155.182 I slot print_timing: id 0 | task 429 | graphs reused = 434 0.19.155.183 I slot print_timing: id 0 | task 429 | graph reallocs = 0 / 0 (same size) / (changed size) 0.19.155.213 I slot release: id 0 | task 429 | stop processing: n_tokens = 391, truncated = 0 0.19.159.646 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 391, t_last = 389210417132 0.19.177.395 I slot launch_slot_: id 0 | task 479 | processing task, is_child = 0 0.20.807.431 I slot print_timing: id 0 | task 479 | prompt eval time = 811.33 ms / 364 tokens ( 2.23 ms per token, 448.64 tokens per second) 0.20.807.437 I slot print_timing: id 0 | task 479 | eval time = 818.69 ms / 41 tokens ( 20.47 ms per token, 48.86 tokens per second) 0.20.807.437 I slot print_timing: id 0 | task 479 | total time = 1630.03 ms / 405 tokens 0.20.807.438 I slot print_timing: id 0 | task 479 | graphs reused = 473 0.20.807.438 I slot print_timing: id 0 | task 479 | graph reallocs = 0 / 0 (same size) / (changed size) 0.20.807.467 I slot release: id 0 | task 479 | stop processing: n_tokens = 404, truncated = 0 0.20.812.205 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 404, t_last = 389212069386 0.20.830.451 I slot launch_slot_: id 0 | task 523 | processing task, is_child = 0 0.22.908.748 I slot print_timing: id 0 | task 523 | prompt eval time = 808.13 ms / 376 tokens ( 2.15 ms per token, 465.27 tokens per second) 0.22.908.752 I slot print_timing: id 0 | task 523 | eval time = 1270.15 ms / 62 tokens ( 20.82 ms per token, 48.03 tokens per second) 0.22.908.752 I slot print_timing: id 0 | task 523 | total time = 2078.29 ms / 438 tokens 0.22.908.753 I slot print_timing: id 0 | task 523 | graphs reused = 533 0.22.908.754 I slot print_timing: id 0 | task 523 | graph reallocs = 0 / 0 (same size) / (changed size) 0.22.908.783 I slot release: id 0 | task 523 | stop processing: n_tokens = 437, truncated = 0 0.22.913.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 389214170702 0.22.931.410 I slot launch_slot_: id 0 | task 588 | processing task, is_child = 0 0.24.773.316 I slot print_timing: id 0 | task 588 | prompt eval time = 898.47 ms / 412 tokens ( 2.18 ms per token, 458.56 tokens per second) 0.24.773.322 I slot print_timing: id 0 | task 588 | eval time = 943.42 ms / 47 tokens ( 20.51 ms per token, 48.76 tokens per second) 0.24.773.323 I slot print_timing: id 0 | task 588 | total time = 1841.89 ms / 459 tokens 0.24.773.324 I slot print_timing: id 0 | task 588 | graphs reused = 578 0.24.773.324 I slot print_timing: id 0 | task 588 | graph reallocs = 0 / 0 (same size) / (changed size) 0.24.773.356 I slot release: id 0 | task 588 | stop processing: n_tokens = 458, truncated = 0 0.24.777.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 389216035275 0.24.796.086 I slot launch_slot_: id 0 | task 638 | processing task, is_child = 0 0.26.868.841 I slot print_timing: id 0 | task 638 | prompt eval time = 824.16 ms / 376 tokens ( 2.19 ms per token, 456.22 tokens per second) 0.26.868.850 I slot print_timing: id 0 | task 638 | eval time = 1248.59 ms / 62 tokens ( 20.47 ms per token, 48.86 tokens per second) 0.26.868.851 I slot print_timing: id 0 | task 638 | total time = 2072.74 ms / 438 tokens 0.26.868.851 I slot print_timing: id 0 | task 638 | graphs reused = 638 0.26.868.852 I slot print_timing: id 0 | task 638 | graph reallocs = 0 / 0 (same size) / (changed size) 0.26.868.878 I slot release: id 0 | task 638 | stop processing: n_tokens = 437, truncated = 0 0.26.873.426 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 437, t_last = 389218130797 0.26.890.795 I slot launch_slot_: id 0 | task 703 | processing task, is_child = 0 0.28.761.774 I slot print_timing: id 0 | task 703 | prompt eval time = 826.70 ms / 378 tokens ( 2.19 ms per token, 457.24 tokens per second) 0.28.761.780 I slot print_timing: id 0 | task 703 | eval time = 1044.27 ms / 52 tokens ( 20.48 ms per token, 48.84 tokens per second) 0.28.761.781 I slot print_timing: id 0 | task 703 | total time = 1870.97 ms / 430 tokens 0.28.761.781 I slot print_timing: id 0 | task 703 | graphs reused = 688 0.28.761.782 I slot print_timing: id 0 | task 703 | graph reallocs = 0 / 0 (same size) / (changed size) 0.28.761.810 I slot release: id 0 | task 703 | stop processing: n_tokens = 429, truncated = 0 0.28.766.403 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 389220023729 0.28.784.586 I slot launch_slot_: id 0 | task 758 | processing task, is_child = 0 0.30.787.258 I slot print_timing: id 0 | task 758 | prompt eval time = 819.21 ms / 367 tokens ( 2.23 ms per token, 447.99 tokens per second) 0.30.787.264 I slot print_timing: id 0 | task 758 | eval time = 1183.45 ms / 58 tokens ( 20.76 ms per token, 48.16 tokens per second) 0.30.787.265 I slot print_timing: id 0 | task 758 | total time = 2002.66 ms / 425 tokens 0.30.787.265 I slot print_timing: id 0 | task 758 | graphs reused = 744 0.30.787.266 I slot print_timing: id 0 | task 758 | graph reallocs = 0 / 0 (same size) / (changed size) 0.30.787.294 I slot release: id 0 | task 758 | stop processing: n_tokens = 424, truncated = 0 0.30.791.679 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 424, t_last = 389222049213 0.30.809.677 I slot launch_slot_: id 0 | task 819 | processing task, is_child = 0 0.32.648.090 I slot print_timing: id 0 | task 819 | prompt eval time = 815.34 ms / 347 tokens ( 2.35 ms per token, 425.59 tokens per second) 0.32.648.093 I slot print_timing: id 0 | task 819 | eval time = 1023.06 ms / 51 tokens ( 20.46 ms per token, 48.87 tokens per second) 0.32.648.094 I slot print_timing: id 0 | task 819 | total time = 1838.40 ms / 398 tokens 0.32.648.094 I slot print_timing: id 0 | task 819 | graphs reused = 793 0.32.648.095 I slot print_timing: id 0 | task 819 | graph reallocs = 0 / 0 (same size) / (changed size) 0.32.648.121 I slot release: id 0 | task 819 | stop processing: n_tokens = 397, truncated = 0 0.32.652.592 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 397, t_last = 389223910040 0.32.670.477 I slot launch_slot_: id 0 | task 873 | processing task, is_child = 0 0.34.610.995 I slot print_timing: id 0 | task 873 | prompt eval time = 855.97 ms / 369 tokens ( 2.32 ms per token, 431.09 tokens per second) 0.34.611.001 I slot print_timing: id 0 | task 873 | eval time = 1084.54 ms / 54 tokens ( 20.46 ms per token, 48.87 tokens per second) 0.34.611.001 I slot print_timing: id 0 | task 873 | total time = 1940.51 ms / 423 tokens 0.34.611.002 I slot print_timing: id 0 | task 873 | graphs reused = 845 0.34.611.003 I slot print_timing: id 0 | task 873 | graph reallocs = 0 / 0 (same size) / (changed size) 0.34.611.034 I slot release: id 0 | task 873 | stop processing: n_tokens = 422, truncated = 0 0.34.615.582 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 422, t_last = 389225872953 0.34.633.346 I slot launch_slot_: id 0 | task 930 | processing task, is_child = 0 0.36.267.455 I slot print_timing: id 0 | task 930 | prompt eval time = 815.21 ms / 352 tokens ( 2.32 ms per token, 431.79 tokens per second) 0.36.267.461 I slot print_timing: id 0 | task 930 | eval time = 818.89 ms / 41 tokens ( 20.47 ms per token, 48.85 tokens per second) 0.36.267.462 I slot print_timing: id 0 | task 930 | total time = 1634.10 ms / 393 tokens 0.36.267.463 I slot print_timing: id 0 | task 930 | graphs reused = 884 0.36.267.463 I slot print_timing: id 0 | task 930 | graph reallocs = 0 / 0 (same size) / (changed size) 0.36.267.490 I slot release: id 0 | task 930 | stop processing: n_tokens = 392, truncated = 0 0.36.271.914 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 392, t_last = 389227529409 0.36.290.004 I slot launch_slot_: id 0 | task 974 | processing task, is_child = 0 0.37.891.308 I slot print_timing: id 0 | task 974 | prompt eval time = 801.88 ms / 349 tokens ( 2.30 ms per token, 435.23 tokens per second) 0.37.891.313 I slot print_timing: id 0 | task 974 | eval time = 799.42 ms / 40 tokens ( 20.50 ms per token, 48.79 tokens per second) 0.37.891.315 I slot print_timing: id 0 | task 974 | total time = 1601.30 ms / 389 tokens 0.37.891.316 I slot print_timing: id 0 | task 974 | graphs reused = 922 0.37.891.316 I slot print_timing: id 0 | task 974 | graph reallocs = 0 / 0 (same size) / (changed size) 0.37.891.345 I slot release: id 0 | task 974 | stop processing: n_tokens = 388, truncated = 0 0.37.895.959 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 388, t_last = 389229153264 0.37.913.573 I slot launch_slot_: id 0 | task 1017 | processing task, is_child = 0 0.40.033.157 I slot print_timing: id 0 | task 1017 | prompt eval time = 833.04 ms / 384 tokens ( 2.17 ms per token, 460.96 tokens per second) 0.40.033.160 I slot print_timing: id 0 | task 1017 | eval time = 1286.54 ms / 63 tokens ( 20.75 ms per token, 48.19 tokens per second) 0.40.033.161 I slot print_timing: id 0 | task 1017 | total time = 2119.58 ms / 447 tokens 0.40.033.161 I slot print_timing: id 0 | task 1017 | graphs reused = 983 0.40.033.162 I slot print_timing: id 0 | task 1017 | graph reallocs = 0 / 0 (same size) / (changed size) 0.40.033.190 I slot release: id 0 | task 1017 | stop processing: n_tokens = 446, truncated = 0 0.40.037.658 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 446, t_last = 389231295109 0.40.055.454 I slot launch_slot_: id 0 | task 1083 | processing task, is_child = 0 0.41.906.552 I slot print_timing: id 0 | task 1083 | prompt eval time = 767.09 ms / 356 tokens ( 2.15 ms per token, 464.09 tokens per second) 0.41.906.557 I slot print_timing: id 0 | task 1083 | eval time = 1083.99 ms / 54 tokens ( 20.45 ms per token, 48.89 tokens per second) 0.41.906.558 I slot print_timing: id 0 | task 1083 | total time = 1851.08 ms / 410 tokens 0.41.906.559 I slot print_timing: id 0 | task 1083 | graphs reused = 1035 0.41.906.559 I slot print_timing: id 0 | task 1083 | graph reallocs = 0 / 0 (same size) / (changed size) 0.41.906.586 I slot release: id 0 | task 1083 | stop processing: n_tokens = 409, truncated = 0 0.41.911.345 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 389233168505 0.41.928.719 I slot launch_slot_: id 0 | task 1140 | processing task, is_child = 0 0.44.207.924 I slot print_timing: id 0 | task 1140 | prompt eval time = 867.40 ms / 410 tokens ( 2.12 ms per token, 472.68 tokens per second) 0.44.207.927 I slot print_timing: id 0 | task 1140 | eval time = 1411.80 ms / 70 tokens ( 20.46 ms per token, 48.87 tokens per second) 0.44.207.928 I slot print_timing: id 0 | task 1140 | total time = 2279.20 ms / 480 tokens 0.44.207.929 I slot print_timing: id 0 | task 1140 | graphs reused = 1103 0.44.207.929 I slot print_timing: id 0 | task 1140 | graph reallocs = 0 / 0 (same size) / (changed size) 0.44.207.959 I slot release: id 0 | task 1140 | stop processing: n_tokens = 479, truncated = 0 0.44.212.469 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 479, t_last = 389235469878 0.44.230.492 I slot launch_slot_: id 0 | task 1213 | processing task, is_child = 0 0.46.265.017 I slot print_timing: id 0 | task 1213 | prompt eval time = 867.79 ms / 385 tokens ( 2.25 ms per token, 443.66 tokens per second) 0.46.265.023 I slot print_timing: id 0 | task 1213 | eval time = 1166.73 ms / 58 tokens ( 20.47 ms per token, 48.85 tokens per second) 0.46.265.023 I slot print_timing: id 0 | task 1213 | total time = 2034.52 ms / 443 tokens 0.46.265.024 I slot print_timing: id 0 | task 1213 | graphs reused = 1159 0.46.265.025 I slot print_timing: id 0 | task 1213 | graph reallocs = 0 / 0 (same size) / (changed size) 0.46.265.055 I slot release: id 0 | task 1213 | stop processing: n_tokens = 442, truncated = 0 0.46.270.106 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 442, t_last = 389237526974 0.46.288.358 I slot launch_slot_: id 0 | task 1274 | processing task, is_child = 0 0.48.571.506 I slot print_timing: id 0 | task 1274 | prompt eval time = 848.49 ms / 395 tokens ( 2.15 ms per token, 465.54 tokens per second) 0.48.571.516 I slot print_timing: id 0 | task 1274 | eval time = 1434.65 ms / 71 tokens ( 20.49 ms per token, 48.79 tokens per second) 0.48.571.516 I slot print_timing: id 0 | task 1274 | total time = 2283.13 ms / 466 tokens 0.48.571.517 I slot print_timing: id 0 | task 1274 | graphs reused = 1228 0.48.571.517 I slot print_timing: id 0 | task 1274 | graph reallocs = 0 / 0 (same size) / (changed size) 0.48.571.551 I slot release: id 0 | task 1274 | stop processing: n_tokens = 465, truncated = 0 0.48.576.287 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 389239833470 0.48.594.404 I slot launch_slot_: id 0 | task 1348 | processing task, is_child = 0 0.50.735.693 I slot print_timing: id 0 | task 1348 | prompt eval time = 890.65 ms / 430 tokens ( 2.07 ms per token, 482.80 tokens per second) 0.50.735.703 I slot print_timing: id 0 | task 1348 | eval time = 1250.63 ms / 62 tokens ( 20.50 ms per token, 48.78 tokens per second) 0.50.735.703 I slot print_timing: id 0 | task 1348 | total time = 2141.28 ms / 492 tokens 0.50.735.704 I slot print_timing: id 0 | task 1348 | graphs reused = 1288 0.50.735.704 I slot print_timing: id 0 | task 1348 | graph reallocs = 0 / 0 (same size) / (changed size) 0.50.735.735 I slot release: id 0 | task 1348 | stop processing: n_tokens = 491, truncated = 0 0.50.740.332 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 389241997654 0.50.758.113 I slot launch_slot_: id 0 | task 1413 | processing task, is_child = 0 0.52.851.309 I slot print_timing: id 0 | task 1413 | prompt eval time = 843.86 ms / 392 tokens ( 2.15 ms per token, 464.53 tokens per second) 0.52.851.313 I slot print_timing: id 0 | task 1413 | eval time = 1249.33 ms / 62 tokens ( 20.48 ms per token, 48.83 tokens per second) 0.52.851.313 I slot print_timing: id 0 | task 1413 | total time = 2093.19 ms / 454 tokens 0.52.851.314 I slot print_timing: id 0 | task 1413 | graphs reused = 1348 0.52.851.314 I slot print_timing: id 0 | task 1413 | graph reallocs = 0 / 0 (same size) / (changed size) 0.52.851.343 I slot release: id 0 | task 1413 | stop processing: n_tokens = 453, truncated = 0 0.52.855.896 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 453, t_last = 389244113262 0.52.873.406 I slot launch_slot_: id 0 | task 1478 | processing task, is_child = 0 0.54.668.388 I slot print_timing: id 0 | task 1478 | prompt eval time = 812.31 ms / 350 tokens ( 2.32 ms per token, 430.87 tokens per second) 0.54.668.394 I slot print_timing: id 0 | task 1478 | eval time = 982.67 ms / 49 tokens ( 20.47 ms per token, 48.85 tokens per second) 0.54.668.395 I slot print_timing: id 0 | task 1478 | total time = 1794.97 ms / 399 tokens 0.54.668.395 I slot print_timing: id 0 | task 1478 | graphs reused = 1395 0.54.668.396 I slot print_timing: id 0 | task 1478 | graph reallocs = 0 / 0 (same size) / (changed size) 0.54.668.423 I slot release: id 0 | task 1478 | stop processing: n_tokens = 398, truncated = 0 0.54.672.984 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 398, t_last = 389245930342 0.54.691.179 I slot launch_slot_: id 0 | task 1530 | processing task, is_child = 0 0.56.716.848 I slot print_timing: id 0 | task 1530 | prompt eval time = 796.92 ms / 380 tokens ( 2.10 ms per token, 476.83 tokens per second) 0.56.716.854 I slot print_timing: id 0 | task 1530 | eval time = 1228.73 ms / 61 tokens ( 20.48 ms per token, 48.83 tokens per second) 0.56.716.855 I slot print_timing: id 0 | task 1530 | total time = 2025.66 ms / 441 tokens 0.56.716.855 I slot print_timing: id 0 | task 1530 | graphs reused = 1454 0.56.716.856 I slot print_timing: id 0 | task 1530 | graph reallocs = 0 / 0 (same size) / (changed size) 0.56.716.883 I slot release: id 0 | task 1530 | stop processing: n_tokens = 440, truncated = 0 0.56.721.641 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 440, t_last = 389247978802 0.56.739.496 I slot launch_slot_: id 0 | task 1594 | processing task, is_child = 0 0.59.250.978 I slot print_timing: id 0 | task 1594 | prompt eval time = 875.36 ms / 410 tokens ( 2.14 ms per token, 468.38 tokens per second) 0.59.250.985 I slot print_timing: id 0 | task 1594 | eval time = 1636.11 ms / 80 tokens ( 20.71 ms per token, 48.29 tokens per second) 0.59.250.985 I slot print_timing: id 0 | task 1594 | total time = 2511.47 ms / 490 tokens 0.59.250.986 I slot print_timing: id 0 | task 1594 | graphs reused = 1532 0.59.250.986 I slot print_timing: id 0 | task 1594 | graph reallocs = 0 / 0 (same size) / (changed size) 0.59.251.017 I slot release: id 0 | task 1594 | stop processing: n_tokens = 489, truncated = 0 0.59.255.563 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 489, t_last = 389250512936 0.59.273.998 I slot launch_slot_: id 0 | task 1677 | processing task, is_child = 0 1.01.522.281 I slot print_timing: id 0 | task 1677 | prompt eval time = 875.29 ms / 387 tokens ( 2.26 ms per token, 442.14 tokens per second) 1.01.522.287 I slot print_timing: id 0 | task 1677 | eval time = 1372.98 ms / 68 tokens ( 20.49 ms per token, 48.80 tokens per second) 1.01.522.288 I slot print_timing: id 0 | task 1677 | total time = 2248.27 ms / 455 tokens 1.01.522.289 I slot print_timing: id 0 | task 1677 | graphs reused = 1598 1.01.522.289 I slot print_timing: id 0 | task 1677 | graph reallocs = 0 / 0 (same size) / (changed size) 1.01.522.317 I slot release: id 0 | task 1677 | stop processing: n_tokens = 454, truncated = 0 1.01.526.945 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 454, t_last = 389252784236 1.01.545.056 I slot launch_slot_: id 0 | task 1748 | processing task, is_child = 0 1.03.549.778 I slot print_timing: id 0 | task 1748 | prompt eval time = 817.53 ms / 358 tokens ( 2.28 ms per token, 437.90 tokens per second) 1.03.549.783 I slot print_timing: id 0 | task 1748 | eval time = 1187.17 ms / 59 tokens ( 20.47 ms per token, 48.86 tokens per second) 1.03.549.784 I slot print_timing: id 0 | task 1748 | total time = 2004.71 ms / 417 tokens 1.03.549.784 I slot print_timing: id 0 | task 1748 | graphs reused = 1655 1.03.549.785 I slot print_timing: id 0 | task 1748 | graph reallocs = 0 / 0 (same size) / (changed size) 1.03.549.812 I slot release: id 0 | task 1748 | stop processing: n_tokens = 416, truncated = 0 1.03.554.363 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 389254811731 1.03.571.774 I slot launch_slot_: id 0 | task 1810 | processing task, is_child = 0 1.05.477.222 I slot print_timing: id 0 | task 1810 | prompt eval time = 802.77 ms / 359 tokens ( 2.24 ms per token, 447.20 tokens per second) 1.05.477.228 I slot print_timing: id 0 | task 1810 | eval time = 1102.67 ms / 54 tokens ( 20.81 ms per token, 48.07 tokens per second) 1.05.477.229 I slot print_timing: id 0 | task 1810 | total time = 1905.44 ms / 413 tokens 1.05.477.230 I slot print_timing: id 0 | task 1810 | graphs reused = 1707 1.05.477.230 I slot print_timing: id 0 | task 1810 | graph reallocs = 0 / 0 (same size) / (changed size) 1.05.477.260 I slot release: id 0 | task 1810 | stop processing: n_tokens = 412, truncated = 0 1.05.481.711 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 389256739179 1.05.500.724 I slot launch_slot_: id 0 | task 1867 | processing task, is_child = 0 1.07.588.552 I slot print_timing: id 0 | task 1867 | prompt eval time = 857.96 ms / 387 tokens ( 2.22 ms per token, 451.07 tokens per second) 1.07.588.562 I slot print_timing: id 0 | task 1867 | eval time = 1229.86 ms / 61 tokens ( 20.50 ms per token, 48.79 tokens per second) 1.07.588.562 I slot print_timing: id 0 | task 1867 | total time = 2087.82 ms / 448 tokens 1.07.588.563 I slot print_timing: id 0 | task 1867 | graphs reused = 1766 1.07.588.564 I slot print_timing: id 0 | task 1867 | graph reallocs = 0 / 0 (same size) / (changed size) 1.07.588.592 I slot release: id 0 | task 1867 | stop processing: n_tokens = 447, truncated = 0 1.07.593.218 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 389258850511 1.07.616.909 I slot launch_slot_: id 0 | task 1931 | processing task, is_child = 0 1.09.440.285 I slot print_timing: id 0 | task 1931 | prompt eval time = 842.71 ms / 410 tokens ( 2.06 ms per token, 486.53 tokens per second) 1.09.440.291 I slot print_timing: id 0 | task 1931 | eval time = 980.66 ms / 48 tokens ( 20.87 ms per token, 47.93 tokens per second) 1.09.440.291 I slot print_timing: id 0 | task 1931 | total time = 1823.36 ms / 458 tokens 1.09.440.292 I slot print_timing: id 0 | task 1931 | graphs reused = 1812 1.09.440.293 I slot print_timing: id 0 | task 1931 | graph reallocs = 0 / 0 (same size) / (changed size) 1.09.440.322 I slot release: id 0 | task 1931 | stop processing: n_tokens = 457, truncated = 0 1.09.444.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 457, t_last = 389260702241 1.09.468.427 I slot launch_slot_: id 0 | task 1982 | processing task, is_child = 0 1.11.273.149 I slot print_timing: id 0 | task 1982 | prompt eval time = 799.90 ms / 351 tokens ( 2.28 ms per token, 438.80 tokens per second) 1.11.273.155 I slot print_timing: id 0 | task 1982 | eval time = 1004.80 ms / 50 tokens ( 20.51 ms per token, 48.77 tokens per second) 1.11.273.156 I slot print_timing: id 0 | task 1982 | total time = 1804.71 ms / 401 tokens 1.11.273.157 I slot print_timing: id 0 | task 1982 | graphs reused = 1860 1.11.273.157 I slot print_timing: id 0 | task 1982 | graph reallocs = 0 / 0 (same size) / (changed size) 1.11.273.185 I slot release: id 0 | task 1982 | stop processing: n_tokens = 400, truncated = 0 1.11.278.036 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 389262535104 1.11.302.653 I slot launch_slot_: id 0 | task 2035 | processing task, is_child = 0 1.13.281.391 I slot print_timing: id 0 | task 2035 | prompt eval time = 852.18 ms / 393 tokens ( 2.17 ms per token, 461.17 tokens per second) 1.13.281.397 I slot print_timing: id 0 | task 2035 | eval time = 1126.54 ms / 56 tokens ( 20.48 ms per token, 48.82 tokens per second) 1.13.281.398 I slot print_timing: id 0 | task 2035 | total time = 1978.72 ms / 449 tokens 1.13.281.398 I slot print_timing: id 0 | task 2035 | graphs reused = 1914 1.13.281.399 I slot print_timing: id 0 | task 2035 | graph reallocs = 0 / 0 (same size) / (changed size) 1.13.281.430 I slot release: id 0 | task 2035 | stop processing: n_tokens = 448, truncated = 0 1.13.285.707 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 389264543349 1.13.310.335 I slot launch_slot_: id 0 | task 2094 | processing task, is_child = 0 1.14.652.881 I slot print_timing: id 0 | task 2094 | prompt eval time = 747.68 ms / 321 tokens ( 2.33 ms per token, 429.33 tokens per second) 1.14.652.887 I slot print_timing: id 0 | task 2094 | eval time = 594.85 ms / 30 tokens ( 20.51 ms per token, 48.75 tokens per second) 1.14.652.888 I slot print_timing: id 0 | task 2094 | total time = 1342.54 ms / 351 tokens 1.14.652.888 I slot print_timing: id 0 | task 2094 | graphs reused = 1942 1.14.652.889 I slot print_timing: id 0 | task 2094 | graph reallocs = 0 / 0 (same size) / (changed size) 1.14.652.915 I slot release: id 0 | task 2094 | stop processing: n_tokens = 350, truncated = 0 1.14.657.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 350, t_last = 389265914834 1.14.680.908 I slot launch_slot_: id 0 | task 2127 | processing task, is_child = 0 1.17.123.461 I slot print_timing: id 0 | task 2127 | prompt eval time = 766.60 ms / 330 tokens ( 2.32 ms per token, 430.47 tokens per second) 1.17.123.467 I slot print_timing: id 0 | task 2127 | eval time = 1675.94 ms / 83 tokens ( 20.44 ms per token, 48.93 tokens per second) 1.17.123.467 I slot print_timing: id 0 | task 2127 | total time = 2442.54 ms / 413 tokens 1.17.123.468 I slot print_timing: id 0 | task 2127 | graphs reused = 2023 1.17.123.468 I slot print_timing: id 0 | task 2127 | graph reallocs = 0 / 0 (same size) / (changed size) 1.17.123.495 I slot release: id 0 | task 2127 | stop processing: n_tokens = 412, truncated = 0 1.17.127.904 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 389268385414 1.17.150.513 I slot launch_slot_: id 0 | task 2213 | processing task, is_child = 0 1.18.549.406 I slot print_timing: id 0 | task 2213 | prompt eval time = 762.38 ms / 341 tokens ( 2.24 ms per token, 447.29 tokens per second) 1.18.549.412 I slot print_timing: id 0 | task 2213 | eval time = 636.51 ms / 32 tokens ( 20.53 ms per token, 48.70 tokens per second) 1.18.549.413 I slot print_timing: id 0 | task 2213 | total time = 1398.88 ms / 373 tokens 1.18.549.414 I slot print_timing: id 0 | task 2213 | graphs reused = 2053 1.18.549.414 I slot print_timing: id 0 | task 2213 | graph reallocs = 0 / 0 (same size) / (changed size) 1.18.549.441 I slot release: id 0 | task 2213 | stop processing: n_tokens = 372, truncated = 0 1.18.553.905 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 372, t_last = 389269811360 1.18.578.850 I slot launch_slot_: id 0 | task 2248 | processing task, is_child = 0 1.20.554.023 I slot print_timing: id 0 | task 2248 | prompt eval time = 1015.35 ms / 338 tokens ( 3.00 ms per token, 332.89 tokens per second) 1.20.554.029 I slot print_timing: id 0 | task 2248 | eval time = 959.81 ms / 48 tokens ( 20.42 ms per token, 48.97 tokens per second) 1.20.554.029 I slot print_timing: id 0 | task 2248 | total time = 1975.16 ms / 386 tokens 1.20.554.030 I slot print_timing: id 0 | task 2248 | graphs reused = 2099 1.20.554.031 I slot print_timing: id 0 | task 2248 | graph reallocs = 0 / 0 (same size) / (changed size) 1.20.554.066 I slot release: id 0 | task 2248 | stop processing: n_tokens = 385, truncated = 0 1.20.558.729 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 385, t_last = 389271815985 1.20.582.213 I slot launch_slot_: id 0 | task 2299 | processing task, is_child = 0 1.22.546.856 I slot print_timing: id 0 | task 2299 | prompt eval time = 840.71 ms / 395 tokens ( 2.13 ms per token, 469.84 tokens per second) 1.22.546.863 I slot print_timing: id 0 | task 2299 | eval time = 1123.92 ms / 56 tokens ( 20.43 ms per token, 48.94 tokens per second) 1.22.546.864 I slot print_timing: id 0 | task 2299 | total time = 1964.63 ms / 451 tokens 1.22.546.865 I slot print_timing: id 0 | task 2299 | graphs reused = 2153 1.22.546.865 I slot print_timing: id 0 | task 2299 | graph reallocs = 0 / 0 (same size) / (changed size) 1.22.546.898 I slot release: id 0 | task 2299 | stop processing: n_tokens = 450, truncated = 0 1.22.551.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 450, t_last = 389273808817 1.22.570.931 I slot launch_slot_: id 0 | task 2358 | processing task, is_child = 0 1.25.364.648 I slot print_timing: id 0 | task 2358 | prompt eval time = 1110.35 ms / 528 tokens ( 2.10 ms per token, 475.53 tokens per second) 1.25.364.654 I slot print_timing: id 0 | task 2358 | eval time = 1683.36 ms / 83 tokens ( 20.53 ms per token, 48.71 tokens per second) 1.25.364.655 I slot print_timing: id 0 | task 2358 | total time = 2793.71 ms / 611 tokens 1.25.364.655 I slot print_timing: id 0 | task 2358 | graphs reused = 2234 1.25.364.656 I slot print_timing: id 0 | task 2358 | graph reallocs = 0 / 0 (same size) / (changed size) 1.25.364.690 I slot release: id 0 | task 2358 | stop processing: n_tokens = 610, truncated = 0 1.25.369.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 610, t_last = 389276626609 1.25.369.185 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.418 MiB) 1.25.386.668 I slot launch_slot_: id 0 | task 2445 | processing task, is_child = 0 1.27.066.049 I slot print_timing: id 0 | task 2445 | prompt eval time = 776.73 ms / 331 tokens ( 2.35 ms per token, 426.15 tokens per second) 1.27.066.055 I slot print_timing: id 0 | task 2445 | eval time = 902.65 ms / 45 tokens ( 20.51 ms per token, 48.75 tokens per second) 1.27.066.056 I slot print_timing: id 0 | task 2445 | total time = 1679.37 ms / 376 tokens 1.27.066.056 I slot print_timing: id 0 | task 2445 | graphs reused = 2277 1.27.066.057 I slot print_timing: id 0 | task 2445 | graph reallocs = 0 / 0 (same size) / (changed size) 1.27.066.088 I slot release: id 0 | task 2445 | stop processing: n_tokens = 387, truncated = 0 1.27.070.612 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 387, t_last = 389278328007 1.27.070.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.538 MiB) 1.27.070.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.379 MiB) 1.27.077.090 I slot launch_slot_: id 0 | task 2493 | processing task, is_child = 0 1.28.951.013 I slot print_timing: id 0 | task 2493 | prompt eval time = 807.98 ms / 362 tokens ( 2.23 ms per token, 448.03 tokens per second) 1.28.951.017 I slot print_timing: id 0 | task 2493 | eval time = 1065.93 ms / 53 tokens ( 20.50 ms per token, 48.78 tokens per second) 1.28.951.017 I slot print_timing: id 0 | task 2493 | total time = 1873.91 ms / 415 tokens 1.28.951.018 I slot print_timing: id 0 | task 2493 | graphs reused = 2328 1.28.951.018 I slot print_timing: id 0 | task 2493 | graph reallocs = 0 / 0 (same size) / (changed size) 1.28.951.049 I slot release: id 0 | task 2493 | stop processing: n_tokens = 426, truncated = 0 1.28.955.965 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 426, t_last = 389280212968 1.28.956.000 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.024 MiB) 1.28.962.546 I slot launch_slot_: id 0 | task 2549 | processing task, is_child = 0 1.31.235.684 I slot print_timing: id 0 | task 2549 | prompt eval time = 881.06 ms / 419 tokens ( 2.10 ms per token, 475.57 tokens per second) 1.31.235.687 I slot print_timing: id 0 | task 2549 | eval time = 1392.07 ms / 69 tokens ( 20.47 ms per token, 48.85 tokens per second) 1.31.235.688 I slot print_timing: id 0 | task 2549 | total time = 2273.12 ms / 488 tokens 1.31.235.688 I slot print_timing: id 0 | task 2549 | graphs reused = 2395 1.31.235.689 I slot print_timing: id 0 | task 2549 | graph reallocs = 0 / 0 (same size) / (changed size) 1.31.235.721 I slot release: id 0 | task 2549 | stop processing: n_tokens = 499, truncated = 0 1.31.240.256 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 499, t_last = 389282497641 1.31.240.293 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.31.256.212 I slot launch_slot_: id 0 | task 2621 | processing task, is_child = 0 1.33.066.037 I slot print_timing: id 0 | task 2621 | prompt eval time = 927.36 ms / 423 tokens ( 2.19 ms per token, 456.14 tokens per second) 1.33.066.043 I slot print_timing: id 0 | task 2621 | eval time = 882.46 ms / 44 tokens ( 20.52 ms per token, 48.73 tokens per second) 1.33.066.043 I slot print_timing: id 0 | task 2621 | total time = 1809.82 ms / 467 tokens 1.33.066.044 I slot print_timing: id 0 | task 2621 | graphs reused = 2437 1.33.066.044 I slot print_timing: id 0 | task 2621 | graph reallocs = 0 / 0 (same size) / (changed size) 1.33.066.078 I slot release: id 0 | task 2621 | stop processing: n_tokens = 478, truncated = 0 1.33.070.482 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 478, t_last = 389284327997 1.33.070.520 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.770 MiB) 1.33.070.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.748 MiB) 1.33.087.278 I slot launch_slot_: id 0 | task 2668 | processing task, is_child = 0 1.34.708.002 I slot print_timing: id 0 | task 2668 | prompt eval time = 760.27 ms / 341 tokens ( 2.23 ms per token, 448.52 tokens per second) 1.34.708.007 I slot print_timing: id 0 | task 2668 | eval time = 860.44 ms / 43 tokens ( 20.49 ms per token, 48.81 tokens per second) 1.34.708.008 I slot print_timing: id 0 | task 2668 | total time = 1620.71 ms / 384 tokens 1.34.708.009 I slot print_timing: id 0 | task 2668 | graphs reused = 2478 1.34.708.009 I slot print_timing: id 0 | task 2668 | graph reallocs = 0 / 0 (same size) / (changed size) 1.34.708.037 I slot release: id 0 | task 2668 | stop processing: n_tokens = 395, truncated = 0 1.34.712.436 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 395, t_last = 389285969956 1.34.712.467 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 199.019 MiB) 1.34.719.025 I slot launch_slot_: id 0 | task 2714 | processing task, is_child = 0 1.36.486.769 I slot print_timing: id 0 | task 2714 | prompt eval time = 824.66 ms / 356 tokens ( 2.32 ms per token, 431.69 tokens per second) 1.36.486.775 I slot print_timing: id 0 | task 2714 | eval time = 943.07 ms / 47 tokens ( 20.50 ms per token, 48.78 tokens per second) 1.36.486.776 I slot print_timing: id 0 | task 2714 | total time = 1767.73 ms / 403 tokens 1.36.486.776 I slot print_timing: id 0 | task 2714 | graphs reused = 2523 1.36.486.777 I slot print_timing: id 0 | task 2714 | graph reallocs = 0 / 0 (same size) / (changed size) 1.36.486.807 I slot release: id 0 | task 2714 | stop processing: n_tokens = 414, truncated = 0 1.36.491.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 389287748726 1.36.491.306 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.086 MiB) 1.36.497.792 I slot launch_slot_: id 0 | task 2764 | processing task, is_child = 0 1.38.232.436 I slot print_timing: id 0 | task 2764 | prompt eval time = 812.36 ms / 362 tokens ( 2.24 ms per token, 445.61 tokens per second) 1.38.232.442 I slot print_timing: id 0 | task 2764 | eval time = 922.27 ms / 46 tokens ( 20.49 ms per token, 48.79 tokens per second) 1.38.232.442 I slot print_timing: id 0 | task 2764 | total time = 1734.63 ms / 408 tokens 1.38.232.443 I slot print_timing: id 0 | task 2764 | graphs reused = 2567 1.38.232.444 I slot print_timing: id 0 | task 2764 | graph reallocs = 0 / 0 (same size) / (changed size) 1.38.232.478 I slot release: id 0 | task 2764 | stop processing: n_tokens = 419, truncated = 0 1.38.237.381 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 389289494397 1.38.237.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.340 MiB) 1.38.244.260 I slot launch_slot_: id 0 | task 2813 | processing task, is_child = 0 1.40.509.271 I slot print_timing: id 0 | task 2813 | prompt eval time = 893.80 ms / 391 tokens ( 2.29 ms per token, 437.46 tokens per second) 1.40.509.277 I slot print_timing: id 0 | task 2813 | eval time = 1371.20 ms / 68 tokens ( 20.47 ms per token, 48.86 tokens per second) 1.40.509.278 I slot print_timing: id 0 | task 2813 | total time = 2265.00 ms / 459 tokens 1.40.509.279 I slot print_timing: id 0 | task 2813 | graphs reused = 2633 1.40.509.279 I slot print_timing: id 0 | task 2813 | graph reallocs = 0 / 0 (same size) / (changed size) 1.40.509.309 I slot release: id 0 | task 2813 | stop processing: n_tokens = 470, truncated = 0 1.40.513.609 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 470, t_last = 389291771228 1.40.513.644 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.40.513.647 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.396 MiB) 1.40.520.106 I slot launch_slot_: id 0 | task 2884 | processing task, is_child = 0 1.42.426.378 I slot print_timing: id 0 | task 2884 | prompt eval time = 783.97 ms / 343 tokens ( 2.29 ms per token, 437.52 tokens per second) 1.42.426.384 I slot print_timing: id 0 | task 2884 | eval time = 1122.29 ms / 55 tokens ( 20.78 ms per token, 48.12 tokens per second) 1.42.426.385 I slot print_timing: id 0 | task 2884 | total time = 1906.26 ms / 398 tokens 1.42.426.385 I slot print_timing: id 0 | task 2884 | graphs reused = 2686 1.42.426.386 I slot print_timing: id 0 | task 2884 | graph reallocs = 0 / 0 (same size) / (changed size) 1.42.426.413 I slot release: id 0 | task 2884 | stop processing: n_tokens = 409, truncated = 0 1.42.431.094 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 409, t_last = 389293688332 1.42.431.127 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.985 MiB) 1.42.437.691 I slot launch_slot_: id 0 | task 2942 | processing task, is_child = 0 1.44.250.314 I slot print_timing: id 0 | task 2942 | prompt eval time = 888.94 ms / 401 tokens ( 2.22 ms per token, 451.10 tokens per second) 1.44.250.320 I slot print_timing: id 0 | task 2942 | eval time = 923.67 ms / 46 tokens ( 20.53 ms per token, 48.72 tokens per second) 1.44.250.321 I slot print_timing: id 0 | task 2942 | total time = 1812.61 ms / 447 tokens 1.44.250.321 I slot print_timing: id 0 | task 2942 | graphs reused = 2730 1.44.250.322 I slot print_timing: id 0 | task 2942 | graph reallocs = 0 / 0 (same size) / (changed size) 1.44.250.353 I slot release: id 0 | task 2942 | stop processing: n_tokens = 458, truncated = 0 1.44.255.171 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 458, t_last = 389295512272 1.44.255.208 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.829 MiB) 1.44.262.276 I slot launch_slot_: id 0 | task 2991 | processing task, is_child = 0 1.46.425.088 I slot print_timing: id 0 | task 2991 | prompt eval time = 792.18 ms / 355 tokens ( 2.23 ms per token, 448.13 tokens per second) 1.46.425.095 I slot print_timing: id 0 | task 2991 | eval time = 1370.62 ms / 68 tokens ( 20.46 ms per token, 48.88 tokens per second) 1.46.425.096 I slot print_timing: id 0 | task 2991 | total time = 2162.80 ms / 423 tokens 1.46.425.096 I slot print_timing: id 0 | task 2991 | graphs reused = 2796 1.46.425.097 I slot print_timing: id 0 | task 2991 | graph reallocs = 0 / 0 (same size) / (changed size) 1.46.425.124 I slot release: id 0 | task 2991 | stop processing: n_tokens = 434, truncated = 0 1.46.429.750 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 434, t_last = 389297687043 1.46.429.785 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.731 MiB) 1.46.429.788 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.203 MiB) 1.46.436.287 I slot launch_slot_: id 0 | task 3062 | processing task, is_child = 0 1.48.420.817 I slot print_timing: id 0 | task 3062 | prompt eval time = 820.07 ms / 351 tokens ( 2.34 ms per token, 428.01 tokens per second) 1.48.420.823 I slot print_timing: id 0 | task 3062 | eval time = 1164.45 ms / 57 tokens ( 20.79 ms per token, 48.09 tokens per second) 1.48.420.824 I slot print_timing: id 0 | task 3062 | total time = 1984.52 ms / 408 tokens 1.48.420.825 I slot print_timing: id 0 | task 3062 | graphs reused = 2851 1.48.420.825 I slot print_timing: id 0 | task 3062 | graph reallocs = 0 / 0 (same size) / (changed size) 1.48.420.857 I slot release: id 0 | task 3062 | stop processing: n_tokens = 419, truncated = 0 1.48.425.870 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 389299682776 1.48.425.905 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.692 MiB) 1.48.432.384 I slot launch_slot_: id 0 | task 3122 | processing task, is_child = 0 1.51.278.486 I slot print_timing: id 0 | task 3122 | prompt eval time = 954.37 ms / 475 tokens ( 2.01 ms per token, 497.71 tokens per second) 1.51.278.492 I slot print_timing: id 0 | task 3122 | eval time = 1891.72 ms / 93 tokens ( 20.56 ms per token, 48.63 tokens per second) 1.51.278.493 I slot print_timing: id 0 | task 3122 | total time = 2846.09 ms / 568 tokens 1.51.278.493 I slot print_timing: id 0 | task 3122 | graphs reused = 2941 1.51.278.494 I slot print_timing: id 0 | task 3122 | graph reallocs = 0 / 0 (same size) / (changed size) 1.51.278.527 I slot release: id 0 | task 3122 | stop processing: n_tokens = 579, truncated = 0 1.51.283.450 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 389302540446 1.51.283.492 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.105 MiB) 1.51.300.886 I slot launch_slot_: id 0 | task 3218 | processing task, is_child = 0 1.54.082.458 I slot print_timing: id 0 | task 3218 | prompt eval time = 911.57 ms / 440 tokens ( 2.07 ms per token, 482.68 tokens per second) 1.54.082.461 I slot print_timing: id 0 | task 3218 | eval time = 1869.99 ms / 92 tokens ( 20.55 ms per token, 48.66 tokens per second) 1.54.082.462 I slot print_timing: id 0 | task 3218 | total time = 2781.56 ms / 532 tokens 1.54.082.462 I slot print_timing: id 0 | task 3218 | graphs reused = 3030 1.54.082.463 I slot print_timing: id 0 | task 3218 | graph reallocs = 0 / 0 (same size) / (changed size) 1.54.082.494 I slot release: id 0 | task 3218 | stop processing: n_tokens = 543, truncated = 0 1.54.087.080 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 543, t_last = 389305344413 1.54.087.120 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.027 MiB) 1.54.087.123 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.161 MiB) 1.54.105.240 I slot launch_slot_: id 0 | task 3313 | processing task, is_child = 0 1.56.041.112 I slot print_timing: id 0 | task 3313 | prompt eval time = 790.10 ms / 345 tokens ( 2.29 ms per token, 436.66 tokens per second) 1.56.041.120 I slot print_timing: id 0 | task 3313 | eval time = 1145.77 ms / 57 tokens ( 20.46 ms per token, 48.88 tokens per second) 1.56.041.120 I slot print_timing: id 0 | task 3313 | total time = 1935.86 ms / 402 tokens 1.56.041.121 I slot print_timing: id 0 | task 3313 | graphs reused = 3085 1.56.041.121 I slot print_timing: id 0 | task 3313 | graph reallocs = 0 / 0 (same size) / (changed size) 1.56.041.149 I slot release: id 0 | task 3313 | stop processing: n_tokens = 413, truncated = 0 1.56.045.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 413, t_last = 389307303068 1.56.045.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.438 MiB) 1.56.052.309 I slot launch_slot_: id 0 | task 3373 | processing task, is_child = 0 1.58.018.299 I slot print_timing: id 0 | task 3373 | prompt eval time = 860.29 ms / 382 tokens ( 2.25 ms per token, 444.04 tokens per second) 1.58.018.303 I slot print_timing: id 0 | task 3373 | eval time = 1105.70 ms / 55 tokens ( 20.48 ms per token, 48.84 tokens per second) 1.58.018.303 I slot print_timing: id 0 | task 3373 | total time = 1965.98 ms / 437 tokens 1.58.018.304 I slot print_timing: id 0 | task 3373 | graphs reused = 3138 1.58.018.304 I slot print_timing: id 0 | task 3373 | graph reallocs = 0 / 0 (same size) / (changed size) 1.58.018.340 I slot release: id 0 | task 3373 | stop processing: n_tokens = 448, truncated = 0 1.58.022.971 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 448, t_last = 389309280259 1.58.023.009 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.806 MiB) 1.58.030.179 I slot launch_slot_: id 0 | task 3431 | processing task, is_child = 0 1.59.708.081 I slot print_timing: id 0 | task 3431 | prompt eval time = 776.89 ms / 337 tokens ( 2.31 ms per token, 433.78 tokens per second) 1.59.708.084 I slot print_timing: id 0 | task 3431 | eval time = 901.00 ms / 45 tokens ( 20.48 ms per token, 48.83 tokens per second) 1.59.708.085 I slot print_timing: id 0 | task 3431 | total time = 1677.89 ms / 382 tokens 1.59.708.085 I slot print_timing: id 0 | task 3431 | graphs reused = 3181 1.59.708.086 I slot print_timing: id 0 | task 3431 | graph reallocs = 0 / 0 (same size) / (changed size) 1.59.708.115 I slot release: id 0 | task 3431 | stop processing: n_tokens = 393, truncated = 0 1.59.712.920 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 393, t_last = 389310970034 1.59.712.954 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.083 MiB) 1.59.712.957 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.533 MiB) 1.59.719.494 I slot launch_slot_: id 0 | task 3479 | processing task, is_child = 0 2.01.992.424 I slot print_timing: id 0 | task 3479 | prompt eval time = 843.72 ms / 402 tokens ( 2.10 ms per token, 476.46 tokens per second) 2.01.992.428 I slot print_timing: id 0 | task 3479 | eval time = 1429.20 ms / 70 tokens ( 20.71 ms per token, 48.28 tokens per second) 2.01.992.429 I slot print_timing: id 0 | task 3479 | total time = 2272.91 ms / 472 tokens 2.01.992.430 I slot print_timing: id 0 | task 3479 | graphs reused = 3249 2.01.992.430 I slot print_timing: id 0 | task 3479 | graph reallocs = 0 / 0 (same size) / (changed size) 2.01.992.469 I slot release: id 0 | task 3479 | stop processing: n_tokens = 483, truncated = 0 2.01.997.647 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 483, t_last = 389313254388 2.01.997.684 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.041 MiB) 2.02.004.186 I slot launch_slot_: id 0 | task 3552 | processing task, is_child = 0 2.04.336.249 I slot print_timing: id 0 | task 3552 | prompt eval time = 1180.96 ms / 549 tokens ( 2.15 ms per token, 464.88 tokens per second) 2.04.336.256 I slot print_timing: id 0 | task 3552 | eval time = 1151.09 ms / 57 tokens ( 20.56 ms per token, 48.65 tokens per second) 2.04.336.256 I slot print_timing: id 0 | task 3552 | total time = 2332.05 ms / 606 tokens 2.04.336.257 I slot print_timing: id 0 | task 3552 | graphs reused = 3304 2.04.336.257 I slot print_timing: id 0 | task 3552 | graph reallocs = 0 / 0 (same size) / (changed size) 2.04.336.292 I slot release: id 0 | task 3552 | stop processing: n_tokens = 617, truncated = 0 2.04.341.687 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 617, t_last = 389315598212 2.04.341.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.298 MiB) 2.04.341.734 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.222 MiB) 2.04.358.876 I slot launch_slot_: id 0 | task 3613 | processing task, is_child = 0 2.06.847.804 I slot print_timing: id 0 | task 3613 | prompt eval time = 1315.94 ms / 616 tokens ( 2.14 ms per token, 468.11 tokens per second) 2.06.847.810 I slot print_timing: id 0 | task 3613 | eval time = 1172.97 ms / 58 tokens ( 20.58 ms per token, 48.59 tokens per second) 2.06.847.811 I slot print_timing: id 0 | task 3613 | total time = 2488.91 ms / 674 tokens 2.06.847.811 I slot print_timing: id 0 | task 3613 | graphs reused = 3360 2.06.847.812 I slot print_timing: id 0 | task 3613 | graph reallocs = 0 / 0 (same size) / (changed size) 2.06.847.847 I slot release: id 0 | task 3613 | stop processing: n_tokens = 685, truncated = 0 2.06.853.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 685, t_last = 389318109767 2.06.853.727 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.044 MiB) 2.06.872.724 I slot launch_slot_: id 0 | task 3675 | processing task, is_child = 0 2.09.473.898 I slot print_timing: id 0 | task 3675 | prompt eval time = 1365.36 ms / 665 tokens ( 2.05 ms per token, 487.05 tokens per second) 2.09.473.904 I slot print_timing: id 0 | task 3675 | eval time = 1235.81 ms / 61 tokens ( 20.60 ms per token, 48.55 tokens per second) 2.09.473.905 I slot print_timing: id 0 | task 3675 | total time = 2601.16 ms / 726 tokens 2.09.473.906 I slot print_timing: id 0 | task 3675 | graphs reused = 3419 2.09.473.906 I slot print_timing: id 0 | task 3675 | graph reallocs = 0 / 0 (same size) / (changed size) 2.09.473.946 I slot release: id 0 | task 3675 | stop processing: n_tokens = 737, truncated = 0 2.09.479.439 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 737, t_last = 389320735865 2.09.479.488 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 198.002 MiB) 2.09.479.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.317 MiB) 2.09.498.106 I slot launch_slot_: id 0 | task 3740 | processing task, is_child = 0 2.12.004.802 I slot print_timing: id 0 | task 3740 | prompt eval time = 1395.74 ms / 645 tokens ( 2.16 ms per token, 462.12 tokens per second) 2.12.004.809 I slot print_timing: id 0 | task 3740 | eval time = 1110.94 ms / 55 tokens ( 20.57 ms per token, 48.61 tokens per second) 2.12.004.810 I slot print_timing: id 0 | task 3740 | total time = 2506.69 ms / 700 tokens 2.12.004.810 I slot print_timing: id 0 | task 3740 | graphs reused = 3472 2.12.004.811 I slot print_timing: id 0 | task 3740 | graph reallocs = 0 / 0 (same size) / (changed size) 2.12.004.851 I slot release: id 0 | task 3740 | stop processing: n_tokens = 711, truncated = 0 2.12.009.964 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 711, t_last = 389323266770 2.12.010.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.574 MiB) 2.12.010.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.496 MiB) 2.12.033.071 I slot launch_slot_: id 0 | task 3799 | processing task, is_child = 0 2.14.071.738 I slot print_timing: id 0 | task 3799 | prompt eval time = 987.06 ms / 474 tokens ( 2.08 ms per token, 480.21 tokens per second) 2.14.071.744 I slot print_timing: id 0 | task 3799 | eval time = 1051.59 ms / 52 tokens ( 20.62 ms per token, 48.50 tokens per second) 2.14.071.745 I slot print_timing: id 0 | task 3799 | total time = 2038.66 ms / 526 tokens 2.14.071.745 I slot print_timing: id 0 | task 3799 | graphs reused = 3521 2.14.071.746 I slot print_timing: id 0 | task 3799 | graph reallocs = 0 / 0 (same size) / (changed size) 2.14.071.781 I slot release: id 0 | task 3799 | stop processing: n_tokens = 537, truncated = 0 2.14.077.139 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 537, t_last = 389325333700 2.14.077.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.181 MiB) 2.14.099.277 I slot launch_slot_: id 0 | task 3854 | processing task, is_child = 0 2.16.637.736 I slot print_timing: id 0 | task 3854 | prompt eval time = 1343.34 ms / 617 tokens ( 2.18 ms per token, 459.30 tokens per second) 2.16.637.744 I slot print_timing: id 0 | task 3854 | eval time = 1195.11 ms / 59 tokens ( 20.61 ms per token, 48.53 tokens per second) 2.16.637.744 I slot print_timing: id 0 | task 3854 | total time = 2538.45 ms / 676 tokens 2.16.637.745 I slot print_timing: id 0 | task 3854 | graphs reused = 3578 2.16.637.745 I slot print_timing: id 0 | task 3854 | graph reallocs = 0 / 0 (same size) / (changed size) 2.16.637.783 I slot release: id 0 | task 3854 | stop processing: n_tokens = 687, truncated = 0 2.16.643.002 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 687, t_last = 389327899702 2.16.643.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.376 MiB) 2.16.643.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.262 MiB) 2.16.671.442 I slot launch_slot_: id 0 | task 3917 | processing task, is_child = 0 2.18.956.672 I slot print_timing: id 0 | task 3917 | prompt eval time = 1318.74 ms / 601 tokens ( 2.19 ms per token, 455.74 tokens per second) 2.18.956.678 I slot print_timing: id 0 | task 3917 | eval time = 966.48 ms / 48 tokens ( 20.56 ms per token, 48.63 tokens per second) 2.18.956.679 I slot print_timing: id 0 | task 3917 | total time = 2285.22 ms / 649 tokens 2.18.956.679 I slot print_timing: id 0 | task 3917 | graphs reused = 3624 2.18.956.680 I slot print_timing: id 0 | task 3917 | graph reallocs = 0 / 0 (same size) / (changed size) 2.18.956.719 I slot release: id 0 | task 3917 | stop processing: n_tokens = 660, truncated = 0 2.18.961.809 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 660, t_last = 389330218638 2.18.961.850 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.200 MiB) 2.18.986.576 I slot launch_slot_: id 0 | task 3969 | processing task, is_child = 0 2.21.100.116 I slot print_timing: id 0 | task 3969 | prompt eval time = 1167.54 ms / 533 tokens ( 2.19 ms per token, 456.51 tokens per second) 2.21.100.122 I slot print_timing: id 0 | task 3969 | eval time = 945.98 ms / 47 tokens ( 20.56 ms per token, 48.63 tokens per second) 2.21.100.123 I slot print_timing: id 0 | task 3969 | total time = 2113.53 ms / 580 tokens 2.21.100.124 I slot print_timing: id 0 | task 3969 | graphs reused = 3669 2.21.100.124 I slot print_timing: id 0 | task 3969 | graph reallocs = 0 / 0 (same size) / (changed size) 2.21.100.158 I slot release: id 0 | task 3969 | stop processing: n_tokens = 591, truncated = 0 2.21.105.674 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 591, t_last = 389332362077 2.21.105.726 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.284 MiB) 2.21.105.729 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 196.496 MiB) 2.21.135.856 I slot launch_slot_: id 0 | task 4020 | processing task, is_child = 0 2.23.170.553 I slot print_timing: id 0 | task 4020 | prompt eval time = 984.26 ms / 480 tokens ( 2.05 ms per token, 487.68 tokens per second) 2.23.170.559 I slot print_timing: id 0 | task 4020 | eval time = 1050.43 ms / 52 tokens ( 20.60 ms per token, 48.55 tokens per second) 2.23.170.560 I slot print_timing: id 0 | task 4020 | total time = 2034.69 ms / 532 tokens 2.23.170.561 I slot print_timing: id 0 | task 4020 | graphs reused = 3718 2.23.170.561 I slot print_timing: id 0 | task 4020 | graph reallocs = 0 / 0 (same size) / (changed size) 2.23.170.594 I slot release: id 0 | task 4020 | stop processing: n_tokens = 560, truncated = 0 2.23.175.941 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 389334432513 2.23.175.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.714 MiB) 2.23.175.984 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 195.968 MiB) 2.23.204.719 I slot launch_slot_: id 0 | task 4075 | processing task, is_child = 0 2.25.260.848 I slot print_timing: id 0 | task 4075 | prompt eval time = 1212.45 ms / 567 tokens ( 2.14 ms per token, 467.65 tokens per second) 2.25.260.854 I slot print_timing: id 0 | task 4075 | eval time = 843.66 ms / 42 tokens ( 20.58 ms per token, 48.60 tokens per second) 2.25.260.855 I slot print_timing: id 0 | task 4075 | total time = 2056.11 ms / 609 tokens 2.25.260.855 I slot print_timing: id 0 | task 4075 | graphs reused = 3758 2.25.260.856 I slot print_timing: id 0 | task 4075 | graph reallocs = 0 / 0 (same size) / (changed size) 2.25.260.895 I slot release: id 0 | task 4075 | stop processing: n_tokens = 637, truncated = 0 2.25.266.047 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 389336522814 2.25.266.091 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 197.239 MiB) 2.25.266.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 263.181 MiB) 2.25.291.837 I slot launch_slot_: id 0 | task 4121 | processing task, is_child = 0 2.27.613.582 I slot print_timing: id 0 | task 4121 | prompt eval time = 1006.40 ms / 506 tokens ( 1.99 ms per token, 502.78 tokens per second) 2.27.613.586 I slot print_timing: id 0 | task 4121 | eval time = 1315.33 ms / 65 tokens ( 20.55 ms per token, 48.66 tokens per second) 2.27.613.587 I slot print_timing: id 0 | task 4121 | total time = 2321.72 ms / 571 tokens 2.27.613.588 I slot print_timing: id 0 | task 4121 | graphs reused = 3821 2.27.613.588 I slot print_timing: id 0 | task 4121 | graph reallocs = 0 / 0 (same size) / (changed size) 2.27.613.621 I slot release: id 0 | task 4121 | stop processing: n_tokens = 599, truncated = 0 2.27.618.480 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 599, t_last = 389338875540 2.27.618.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.821 MiB) 2.27.626.630 I slot launch_slot_: id 0 | task 4189 | processing task, is_child = 0 2.29.326.119 I slot print_timing: id 0 | task 4189 | prompt eval time = 899.07 ms / 436 tokens ( 2.06 ms per token, 484.94 tokens per second) 2.29.326.125 I slot print_timing: id 0 | task 4189 | eval time = 800.40 ms / 40 tokens ( 20.52 ms per token, 48.73 tokens per second) 2.29.326.126 I slot print_timing: id 0 | task 4189 | total time = 1699.48 ms / 476 tokens 2.29.326.127 I slot print_timing: id 0 | task 4189 | graphs reused = 3859 2.29.326.127 I slot print_timing: id 0 | task 4189 | graph reallocs = 0 / 0 (same size) / (changed size) 2.29.326.158 I slot release: id 0 | task 4189 | stop processing: n_tokens = 504, truncated = 0 2.29.331.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 389340588078 2.29.331.287 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.583 MiB) 2.29.349.331 I slot launch_slot_: id 0 | task 4232 | processing task, is_child = 0 2.31.675.275 I slot print_timing: id 0 | task 4232 | prompt eval time = 1072.40 ms / 519 tokens ( 2.07 ms per token, 483.96 tokens per second) 2.31.675.279 I slot print_timing: id 0 | task 4232 | eval time = 1253.54 ms / 62 tokens ( 20.55 ms per token, 48.66 tokens per second) 2.31.675.280 I slot print_timing: id 0 | task 4232 | total time = 2325.93 ms / 581 tokens 2.31.675.280 I slot print_timing: id 0 | task 4232 | graphs reused = 3919 2.31.675.281 I slot print_timing: id 0 | task 4232 | graph reallocs = 0 / 0 (same size) / (changed size) 2.31.675.314 I slot release: id 0 | task 4232 | stop processing: n_tokens = 609, truncated = 0 2.31.680.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 609, t_last = 389342937233 2.31.680.354 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.011 MiB) 2.31.680.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.600 MiB) 2.31.699.792 I slot launch_slot_: id 0 | task 4298 | processing task, is_child = 0 2.33.569.815 I slot print_timing: id 0 | task 4298 | prompt eval time = 939.82 ms / 465 tokens ( 2.02 ms per token, 494.78 tokens per second) 2.33.569.819 I slot print_timing: id 0 | task 4298 | eval time = 930.20 ms / 46 tokens ( 20.67 ms per token, 48.38 tokens per second) 2.33.569.820 I slot print_timing: id 0 | task 4298 | total time = 1870.02 ms / 511 tokens 2.33.569.821 I slot print_timing: id 0 | task 4298 | graphs reused = 3962 2.33.569.821 I slot print_timing: id 0 | task 4298 | graph reallocs = 0 / 0 (same size) / (changed size) 2.33.569.856 I slot release: id 0 | task 4298 | stop processing: n_tokens = 542, truncated = 0 2.33.574.865 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 389344831775 2.33.574.904 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.977 MiB) 2.33.594.610 I slot launch_slot_: id 0 | task 4347 | processing task, is_child = 0 2.35.331.419 I slot print_timing: id 0 | task 4347 | prompt eval time = 914.46 ms / 431 tokens ( 2.12 ms per token, 471.32 tokens per second) 2.35.331.425 I slot print_timing: id 0 | task 4347 | eval time = 822.34 ms / 41 tokens ( 20.56 ms per token, 48.64 tokens per second) 2.35.331.426 I slot print_timing: id 0 | task 4347 | total time = 1736.80 ms / 472 tokens 2.35.331.427 I slot print_timing: id 0 | task 4347 | graphs reused = 4001 2.35.331.427 I slot print_timing: id 0 | task 4347 | graph reallocs = 0 / 0 (same size) / (changed size) 2.35.331.462 I slot release: id 0 | task 4347 | stop processing: n_tokens = 503, truncated = 0 2.35.336.448 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 503, t_last = 389346593381 2.35.336.485 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.349 MiB) 2.35.336.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.35.356.498 I slot launch_slot_: id 0 | task 4391 | processing task, is_child = 0 2.37.182.363 I slot print_timing: id 0 | task 4391 | prompt eval time = 938.20 ms / 457 tokens ( 2.05 ms per token, 487.10 tokens per second) 2.37.182.369 I slot print_timing: id 0 | task 4391 | eval time = 887.65 ms / 44 tokens ( 20.64 ms per token, 48.44 tokens per second) 2.37.182.369 I slot print_timing: id 0 | task 4391 | total time = 1825.85 ms / 501 tokens 2.37.182.370 I slot print_timing: id 0 | task 4391 | graphs reused = 4042 2.37.182.370 I slot print_timing: id 0 | task 4391 | graph reallocs = 0 / 0 (same size) / (changed size) 2.37.182.403 I slot release: id 0 | task 4391 | stop processing: n_tokens = 532, truncated = 0 2.37.187.371 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 532, t_last = 389348444322 2.37.187.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.444 MiB) 2.37.196.736 I slot launch_slot_: id 0 | task 4438 | processing task, is_child = 0 2.38.962.016 I slot print_timing: id 0 | task 4438 | prompt eval time = 924.95 ms / 439 tokens ( 2.11 ms per token, 474.62 tokens per second) 2.38.962.020 I slot print_timing: id 0 | task 4438 | eval time = 840.32 ms / 42 tokens ( 20.50 ms per token, 48.79 tokens per second) 2.38.962.020 I slot print_timing: id 0 | task 4438 | total time = 1765.27 ms / 481 tokens 2.38.962.021 I slot print_timing: id 0 | task 4438 | graphs reused = 4082 2.38.962.022 I slot print_timing: id 0 | task 4438 | graph reallocs = 0 / 0 (same size) / (changed size) 2.38.962.053 I slot release: id 0 | task 4438 | stop processing: n_tokens = 512, truncated = 0 2.38.967.389 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 512, t_last = 389350223972 2.38.967.430 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.251 MiB) 2.38.967.433 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.209 MiB) 2.38.987.040 I slot launch_slot_: id 0 | task 4483 | processing task, is_child = 0 2.41.393.188 I slot print_timing: id 0 | task 4483 | prompt eval time = 1274.09 ms / 606 tokens ( 2.10 ms per token, 475.63 tokens per second) 2.41.393.194 I slot print_timing: id 0 | task 4483 | eval time = 1132.04 ms / 56 tokens ( 20.58 ms per token, 48.58 tokens per second) 2.41.393.194 I slot print_timing: id 0 | task 4483 | total time = 2406.13 ms / 662 tokens 2.41.393.195 I slot print_timing: id 0 | task 4483 | graphs reused = 4136 2.41.393.195 I slot print_timing: id 0 | task 4483 | graph reallocs = 0 / 0 (same size) / (changed size) 2.41.393.233 I slot release: id 0 | task 4483 | stop processing: n_tokens = 693, truncated = 0 2.41.398.449 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 389352655152 2.41.398.495 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.740 MiB) 2.41.419.179 I slot launch_slot_: id 0 | task 4543 | processing task, is_child = 0 2.43.198.831 I slot print_timing: id 0 | task 4543 | prompt eval time = 953.78 ms / 477 tokens ( 2.00 ms per token, 500.11 tokens per second) 2.43.198.834 I slot print_timing: id 0 | task 4543 | eval time = 825.86 ms / 41 tokens ( 20.65 ms per token, 48.43 tokens per second) 2.43.198.834 I slot print_timing: id 0 | task 4543 | total time = 1779.64 ms / 518 tokens 2.43.198.835 I slot print_timing: id 0 | task 4543 | graphs reused = 4174 2.43.198.836 I slot print_timing: id 0 | task 4543 | graph reallocs = 0 / 0 (same size) / (changed size) 2.43.198.869 I slot release: id 0 | task 4543 | stop processing: n_tokens = 549, truncated = 0 2.43.205.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 389354460788 2.43.205.098 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.446 MiB) 2.43.205.102 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 262.575 MiB) 2.43.214.966 I slot launch_slot_: id 0 | task 4587 | processing task, is_child = 0 2.46.077.030 I slot print_timing: id 0 | task 4587 | prompt eval time = 1646.36 ms / 845 tokens ( 1.95 ms per token, 513.25 tokens per second) 2.46.077.035 I slot print_timing: id 0 | task 4587 | eval time = 1215.70 ms / 60 tokens ( 20.61 ms per token, 48.53 tokens per second) 2.46.077.036 I slot print_timing: id 0 | task 4587 | total time = 2862.05 ms / 905 tokens 2.46.077.037 I slot print_timing: id 0 | task 4587 | graphs reused = 4232 2.46.077.037 I slot print_timing: id 0 | task 4587 | graph reallocs = 0 / 0 (same size) / (changed size) 2.46.077.084 I slot release: id 0 | task 4587 | stop processing: n_tokens = 936, truncated = 0 2.46.082.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 936, t_last = 389357339003 2.46.082.213 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.871 MiB) 2.46.105.051 I slot launch_slot_: id 0 | task 4651 | processing task, is_child = 0 2.48.167.924 I slot print_timing: id 0 | task 4651 | prompt eval time = 948.65 ms / 459 tokens ( 2.07 ms per token, 483.84 tokens per second) 2.48.167.930 I slot print_timing: id 0 | task 4651 | eval time = 1114.21 ms / 55 tokens ( 20.63 ms per token, 48.46 tokens per second) 2.48.167.931 I slot print_timing: id 0 | task 4651 | total time = 2062.86 ms / 514 tokens 2.48.167.932 I slot print_timing: id 0 | task 4651 | graphs reused = 4284 2.48.167.932 I slot print_timing: id 0 | task 4651 | graph reallocs = 0 / 0 (same size) / (changed size) 2.48.167.965 I slot release: id 0 | task 4651 | stop processing: n_tokens = 545, truncated = 0 2.48.173.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 545, t_last = 389359429884 2.48.173.542 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 259.329 MiB) 2.48.173.546 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.013 MiB) 2.48.193.670 I slot launch_slot_: id 0 | task 4709 | processing task, is_child = 0 2.50.517.498 I slot print_timing: id 0 | task 4709 | prompt eval time = 1375.70 ms / 670 tokens ( 2.05 ms per token, 487.02 tokens per second) 2.50.517.504 I slot print_timing: id 0 | task 4709 | eval time = 948.11 ms / 47 tokens ( 20.61 ms per token, 48.52 tokens per second) 2.50.517.505 I slot print_timing: id 0 | task 4709 | total time = 2323.82 ms / 717 tokens 2.50.517.506 I slot print_timing: id 0 | task 4709 | graphs reused = 4329 2.50.517.506 I slot print_timing: id 0 | task 4709 | graph reallocs = 0 / 0 (same size) / (changed size) 2.50.517.549 I slot release: id 0 | task 4709 | stop processing: n_tokens = 748, truncated = 0 2.50.523.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 748, t_last = 389361779468 2.50.523.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 258.938 MiB) 2.50.523.826 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 260.698 MiB) 2.50.546.505 I slot launch_slot_: id 0 | task 4760 | processing task, is_child = 0 2.53.371.453 I slot print_timing: id 0 | task 4760 | prompt eval time = 1529.59 ms / 775 tokens ( 1.97 ms per token, 506.67 tokens per second) 2.53.371.457 I slot print_timing: id 0 | task 4760 | eval time = 1295.35 ms / 63 tokens ( 20.89 ms per token, 47.86 tokens per second) 2.53.371.457 I slot print_timing: id 0 | task 4760 | total time = 2824.93 ms / 838 tokens 2.53.371.458 I slot print_timing: id 0 | task 4760 | graphs reused = 4390 2.53.371.458 I slot print_timing: id 0 | task 4760 | graph reallocs = 0 / 0 (same size) / (changed size) 2.53.371.503 I slot release: id 0 | task 4760 | stop processing: n_tokens = 869, truncated = 0 2.53.377.133 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 869, t_last = 389364633422 2.53.377.186 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.131 MiB) 2.53.399.959 I slot launch_slot_: id 0 | task 4827 | processing task, is_child = 0 2.56.051.088 I slot print_timing: id 0 | task 4827 | prompt eval time = 1211.07 ms / 573 tokens ( 2.11 ms per token, 473.13 tokens per second) 2.56.051.095 I slot print_timing: id 0 | task 4827 | eval time = 1440.05 ms / 71 tokens ( 20.57 ms per token, 48.61 tokens per second) 2.56.051.096 I slot print_timing: id 0 | task 4827 | total time = 2651.12 ms / 644 tokens 2.56.051.096 I slot print_timing: id 0 | task 4827 | graphs reused = 4459 2.56.051.097 I slot print_timing: id 0 | task 4827 | graph reallocs = 0 / 0 (same size) / (changed size) 2.56.051.134 I slot release: id 0 | task 4827 | stop processing: n_tokens = 675, truncated = 0 2.56.056.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 675, t_last = 389367313053 2.56.056.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.461 MiB) 2.56.056.191 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 328.478 MiB) 2.56.067.558 I slot launch_slot_: id 0 | task 4902 | processing task, is_child = 0 2.58.307.000 I slot print_timing: id 0 | task 4902 | prompt eval time = 941.84 ms / 461 tokens ( 2.04 ms per token, 489.47 tokens per second) 2.58.307.006 I slot print_timing: id 0 | task 4902 | eval time = 1297.59 ms / 64 tokens ( 20.60 ms per token, 48.55 tokens per second) 2.58.307.006 I slot print_timing: id 0 | task 4902 | total time = 2239.43 ms / 525 tokens 2.58.307.007 I slot print_timing: id 0 | task 4902 | graphs reused = 4520 2.58.307.008 I slot print_timing: id 0 | task 4902 | graph reallocs = 0 / 0 (same size) / (changed size) 2.58.307.043 I slot release: id 0 | task 4902 | stop processing: n_tokens = 556, truncated = 0 2.58.312.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 556, t_last = 389369568962 2.58.312.580 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.969 MiB) 2.58.322.199 I slot launch_slot_: id 0 | task 4969 | processing task, is_child = 0 3.00.500.600 I slot print_timing: id 0 | task 4969 | prompt eval time = 1294.43 ms / 609 tokens ( 2.13 ms per token, 470.48 tokens per second) 3.00.500.605 I slot print_timing: id 0 | task 4969 | eval time = 883.97 ms / 43 tokens ( 21.05 ms per token, 47.51 tokens per second) 3.00.500.606 I slot print_timing: id 0 | task 4969 | total time = 2178.39 ms / 652 tokens 3.00.500.607 I slot print_timing: id 0 | task 4969 | graphs reused = 4561 3.00.500.607 I slot print_timing: id 0 | task 4969 | graph reallocs = 0 / 0 (same size) / (changed size) 3.00.500.650 I slot release: id 0 | task 4969 | stop processing: n_tokens = 683, truncated = 0 3.00.506.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 683, t_last = 389371762569 3.00.506.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 261.754 MiB) 3.00.517.350 I slot launch_slot_: id 0 | task 5016 | processing task, is_child = 0 3.03.339.235 I slot print_timing: id 0 | task 5016 | prompt eval time = 1586.38 ms / 791 tokens ( 2.01 ms per token, 498.62 tokens per second) 3.03.339.238 I slot print_timing: id 0 | task 5016 | eval time = 1235.49 ms / 61 tokens ( 20.59 ms per token, 48.56 tokens per second) 3.03.339.238 I slot print_timing: id 0 | task 5016 | total time = 2821.87 ms / 852 tokens 3.03.339.239 I slot print_timing: id 0 | task 5016 | graphs reused = 4620 3.03.339.240 I slot print_timing: id 0 | task 5016 | graph reallocs = 0 / 0 (same size) / (changed size) 3.03.339.288 I slot release: id 0 | task 5016 | stop processing: n_tokens = 883, truncated = 0 3.03.344.777 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 883, t_last = 389374601207 3.03.344.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 327.500 MiB) 3.03.344.841 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 326.972 MiB) 3.03.369.408 I slot launch_slot_: id 0 | task 5081 | processing task, is_child = 0 3.05.676.841 I slot print_timing: id 0 | task 5081 | prompt eval time = 1174.98 ms / 533 tokens ( 2.20 ms per token, 453.62 tokens per second) 3.05.676.844 I slot print_timing: id 0 | task 5081 | eval time = 1132.44 ms / 56 tokens ( 20.59 ms per token, 48.57 tokens per second) 3.05.676.845 I slot print_timing: id 0 | task 5081 | total time = 2307.42 ms / 589 tokens 3.05.676.845 I slot print_timing: id 0 | task 5081 | graphs reused = 4674 3.05.676.846 I slot print_timing: id 0 | task 5081 | graph reallocs = 0 / 0 (same size) / (changed size) 3.05.676.889 I slot release: id 0 | task 5081 | stop processing: n_tokens = 677, truncated = 0 3.05.682.347 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 677, t_last = 389376938808 3.05.694.516 I slot launch_slot_: id 0 | task 5141 | processing task, is_child = 0 3.07.851.197 I slot print_timing: id 0 | task 5141 | prompt eval time = 1211.47 ms / 566 tokens ( 2.14 ms per token, 467.20 tokens per second) 3.07.851.203 I slot print_timing: id 0 | task 5141 | eval time = 945.20 ms / 46 tokens ( 21.00 ms per token, 47.61 tokens per second) 3.07.851.203 I slot print_timing: id 0 | task 5141 | total time = 2156.67 ms / 612 tokens 3.07.851.204 I slot print_timing: id 0 | task 5141 | graphs reused = 4718 3.07.851.204 I slot print_timing: id 0 | task 5141 | graph reallocs = 0 / 0 (same size) / (changed size) 3.07.851.244 I slot release: id 0 | task 5141 | stop processing: n_tokens = 643, truncated = 0 3.07.856.010 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 643, t_last = 389379113163 3.07.856.054 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.623 MiB) 3.07.866.984 I slot launch_slot_: id 0 | task 5191 | processing task, is_child = 0 3.09.661.442 I slot print_timing: id 0 | task 5191 | prompt eval time = 926.61 ms / 443 tokens ( 2.09 ms per token, 478.09 tokens per second) 3.09.661.448 I slot print_timing: id 0 | task 5191 | eval time = 867.84 ms / 43 tokens ( 20.66 ms per token, 48.40 tokens per second) 3.09.661.448 I slot print_timing: id 0 | task 5191 | total time = 1794.45 ms / 486 tokens 3.09.661.449 I slot print_timing: id 0 | task 5191 | graphs reused = 4758 3.09.661.450 I slot print_timing: id 0 | task 5191 | graph reallocs = 0 / 0 (same size) / (changed size) 3.09.661.484 I slot release: id 0 | task 5191 | stop processing: n_tokens = 517, truncated = 0 3.09.666.409 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 517, t_last = 389380923403 3.09.666.449 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.017 MiB) 3.09.666.453 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 3.09.676.038 I slot launch_slot_: id 0 | task 5237 | processing task, is_child = 0 3.11.965.783 I slot print_timing: id 0 | task 5237 | prompt eval time = 972.66 ms / 487 tokens ( 2.00 ms per token, 500.69 tokens per second) 3.11.965.786 I slot print_timing: id 0 | task 5237 | eval time = 1317.07 ms / 65 tokens ( 20.58 ms per token, 48.59 tokens per second) 3.11.965.788 I slot print_timing: id 0 | task 5237 | total time = 2289.73 ms / 552 tokens 3.11.965.789 I slot print_timing: id 0 | task 5237 | graphs reused = 4821 3.11.965.789 I slot print_timing: id 0 | task 5237 | graph reallocs = 0 / 0 (same size) / (changed size) 3.11.965.828 I slot release: id 0 | task 5237 | stop processing: n_tokens = 583, truncated = 0 3.11.971.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 583, t_last = 389383227747 3.11.971.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 325.779 MiB) 3.11.981.694 I slot launch_slot_: id 0 | task 5305 | processing task, is_child = 0 3.13.953.286 I slot print_timing: id 0 | task 5305 | prompt eval time = 1024.33 ms / 507 tokens ( 2.02 ms per token, 494.96 tokens per second) 3.13.953.289 I slot print_timing: id 0 | task 5305 | eval time = 947.25 ms / 47 tokens ( 20.59 ms per token, 48.56 tokens per second) 3.13.953.289 I slot print_timing: id 0 | task 5305 | total time = 1971.58 ms / 554 tokens 3.13.953.290 I slot print_timing: id 0 | task 5305 | graphs reused = 4866 3.13.953.291 I slot print_timing: id 0 | task 5305 | graph reallocs = 0 / 0 (same size) / (changed size) 3.13.953.335 I slot release: id 0 | task 5305 | stop processing: n_tokens = 585, truncated = 0 3.13.958.940 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 585, t_last = 389385215254 3.13.958.981 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 323.922 MiB) 3.13.968.201 I slot launch_slot_: id 0 | task 5355 | processing task, is_child = 0 3.16.638.480 I slot print_timing: id 0 | task 5355 | prompt eval time = 1331.66 ms / 633 tokens ( 2.10 ms per token, 475.35 tokens per second) 3.16.638.482 I slot print_timing: id 0 | task 5355 | eval time = 1338.61 ms / 66 tokens ( 20.59 ms per token, 48.56 tokens per second) 3.16.638.483 I slot print_timing: id 0 | task 5355 | total time = 2670.27 ms / 699 tokens 3.16.638.484 I slot print_timing: id 0 | task 5355 | graphs reused = 4930 3.16.638.484 I slot print_timing: id 0 | task 5355 | graph reallocs = 0 / 0 (same size) / (changed size) 3.16.638.525 I slot release: id 0 | task 5355 | stop processing: n_tokens = 730, truncated = 0 3.16.643.894 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 730, t_last = 389387900444 3.16.643.943 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.788 MiB) 3.16.655.438 I slot launch_slot_: id 0 | task 5425 | processing task, is_child = 0 3.19.088.943 I slot print_timing: id 0 | task 5425 | prompt eval time = 1240.43 ms / 571 tokens ( 2.17 ms per token, 460.32 tokens per second) 3.19.088.950 I slot print_timing: id 0 | task 5425 | eval time = 1193.07 ms / 59 tokens ( 20.57 ms per token, 48.61 tokens per second) 3.19.088.951 I slot print_timing: id 0 | task 5425 | total time = 2433.49 ms / 630 tokens 3.19.088.952 I slot print_timing: id 0 | task 5425 | graphs reused = 4987 3.19.088.952 I slot print_timing: id 0 | task 5425 | graph reallocs = 0 / 0 (same size) / (changed size) 3.19.088.989 I slot release: id 0 | task 5425 | stop processing: n_tokens = 661, truncated = 0 3.19.095.093 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 661, t_last = 389390350908 3.19.095.137 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.478 MiB) 3.19.106.183 I slot launch_slot_: id 0 | task 5488 | processing task, is_child = 0 3.21.546.125 I slot print_timing: id 0 | task 5488 | prompt eval time = 1552.84 ms / 798 tokens ( 1.95 ms per token, 513.90 tokens per second) 3.21.546.130 I slot print_timing: id 0 | task 5488 | eval time = 887.10 ms / 44 tokens ( 20.63 ms per token, 48.47 tokens per second) 3.21.546.130 I slot print_timing: id 0 | task 5488 | total time = 2439.93 ms / 842 tokens 3.21.546.131 I slot print_timing: id 0 | task 5488 | graphs reused = 5029 3.21.546.132 I slot print_timing: id 0 | task 5488 | graph reallocs = 0 / 0 (same size) / (changed size) 3.21.546.177 I slot release: id 0 | task 5488 | stop processing: n_tokens = 873, truncated = 0 3.21.551.547 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 873, t_last = 389392808096 3.21.551.598 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.715 MiB) 3.21.575.584 I slot launch_slot_: id 0 | task 5536 | processing task, is_child = 0 3.23.696.851 I slot print_timing: id 0 | task 5536 | prompt eval time = 1254.98 ms / 572 tokens ( 2.19 ms per token, 455.78 tokens per second) 3.23.696.856 I slot print_timing: id 0 | task 5536 | eval time = 866.27 ms / 43 tokens ( 20.63 ms per token, 48.48 tokens per second) 3.23.696.857 I slot print_timing: id 0 | task 5536 | total time = 2121.25 ms / 615 tokens 3.23.696.858 I slot print_timing: id 0 | task 5536 | graphs reused = 5070 3.23.696.858 I slot print_timing: id 0 | task 5536 | graph reallocs = 0 / 0 (same size) / (changed size) 3.23.696.895 I slot release: id 0 | task 5536 | stop processing: n_tokens = 646, truncated = 0 3.23.702.318 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 646, t_last = 389394958814 3.23.702.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.282 MiB) 3.23.702.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.891 MiB) 3.23.723.186 I slot launch_slot_: id 0 | task 5583 | processing task, is_child = 0 3.26.048.926 I slot print_timing: id 0 | task 5583 | prompt eval time = 1336.25 ms / 613 tokens ( 2.18 ms per token, 458.75 tokens per second) 3.26.048.932 I slot print_timing: id 0 | task 5583 | eval time = 989.48 ms / 49 tokens ( 20.61 ms per token, 48.51 tokens per second) 3.26.048.933 I slot print_timing: id 0 | task 5583 | total time = 2325.73 ms / 662 tokens 3.26.048.933 I slot print_timing: id 0 | task 5583 | graphs reused = 5117 3.26.048.934 I slot print_timing: id 0 | task 5583 | graph reallocs = 0 / 0 (same size) / (changed size) 3.26.048.973 I slot release: id 0 | task 5583 | stop processing: n_tokens = 693, truncated = 0 3.26.054.485 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 389397310892 3.26.054.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 3.26.065.307 I slot launch_slot_: id 0 | task 5636 | processing task, is_child = 0 3.28.880.509 I slot print_timing: id 0 | task 5636 | prompt eval time = 1253.31 ms / 580 tokens ( 2.16 ms per token, 462.78 tokens per second) 3.28.880.516 I slot print_timing: id 0 | task 5636 | eval time = 1561.88 ms / 77 tokens ( 20.55 ms per token, 48.66 tokens per second) 3.28.880.516 I slot print_timing: id 0 | task 5636 | total time = 2815.19 ms / 657 tokens 3.28.880.517 I slot print_timing: id 0 | task 5636 | graphs reused = 5192 3.28.880.518 I slot print_timing: id 0 | task 5636 | graph reallocs = 0 / 0 (same size) / (changed size) 3.28.880.558 I slot release: id 0 | task 5636 | stop processing: n_tokens = 688, truncated = 0 3.28.886.200 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 688, t_last = 389400142477 3.28.886.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 3.28.908.480 I slot launch_slot_: id 0 | task 5717 | processing task, is_child = 0 3.31.390.391 I slot print_timing: id 0 | task 5717 | prompt eval time = 1468.99 ms / 716 tokens ( 2.05 ms per token, 487.41 tokens per second) 3.31.390.397 I slot print_timing: id 0 | task 5717 | eval time = 1012.91 ms / 50 tokens ( 20.67 ms per token, 48.38 tokens per second) 3.31.390.398 I slot print_timing: id 0 | task 5717 | total time = 2481.90 ms / 766 tokens 3.31.390.399 I slot print_timing: id 0 | task 5717 | graphs reused = 5239 3.31.390.399 I slot print_timing: id 0 | task 5717 | graph reallocs = 0 / 0 (same size) / (changed size) 3.31.390.442 I slot release: id 0 | task 5717 | stop processing: n_tokens = 797, truncated = 0 3.31.396.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 797, t_last = 389402652361 3.31.396.653 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.995 MiB) 3.31.407.652 I slot launch_slot_: id 0 | task 5771 | processing task, is_child = 0 3.35.064.001 I slot print_timing: id 0 | task 5771 | prompt eval time = 1558.22 ms / 799 tokens ( 1.95 ms per token, 512.76 tokens per second) 3.35.064.008 I slot print_timing: id 0 | task 5771 | eval time = 2098.12 ms / 103 tokens ( 20.57 ms per token, 48.62 tokens per second) 3.35.064.008 I slot print_timing: id 0 | task 5771 | total time = 3656.34 ms / 902 tokens 3.35.064.009 I slot print_timing: id 0 | task 5771 | graphs reused = 5340 3.35.064.010 I slot print_timing: id 0 | task 5771 | graph reallocs = 0 / 0 (same size) / (changed size) 3.35.064.064 I slot release: id 0 | task 5771 | stop processing: n_tokens = 933, truncated = 0 3.35.068.774 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 933, t_last = 389406325983 3.35.068.828 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.537 MiB) 3.35.092.989 I slot launch_slot_: id 0 | task 5878 | processing task, is_child = 0 3.38.170.993 I slot print_timing: id 0 | task 5878 | prompt eval time = 805.36 ms / 361 tokens ( 2.23 ms per token, 448.25 tokens per second) 3.38.170.997 I slot print_timing: id 0 | task 5878 | eval time = 2272.63 ms / 112 tokens ( 20.47 ms per token, 48.84 tokens per second) 3.38.170.997 I slot print_timing: id 0 | task 5878 | total time = 3077.99 ms / 473 tokens 3.38.170.998 I slot print_timing: id 0 | task 5878 | graphs reused = 5450 3.38.170.998 I slot print_timing: id 0 | task 5878 | graph reallocs = 0 / 0 (same size) / (changed size) 3.38.171.027 I slot release: id 0 | task 5878 | stop processing: n_tokens = 504, truncated = 0 3.38.175.798 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 504, t_last = 389409432946 3.38.175.835 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.319 MiB) 3.38.185.421 I slot launch_slot_: id 0 | task 5993 | processing task, is_child = 0 3.41.223.150 I slot print_timing: id 0 | task 5993 | prompt eval time = 842.18 ms / 381 tokens ( 2.21 ms per token, 452.40 tokens per second) 3.41.223.153 I slot print_timing: id 0 | task 5993 | eval time = 2195.54 ms / 108 tokens ( 20.52 ms per token, 48.74 tokens per second) 3.41.223.154 I slot print_timing: id 0 | task 5993 | total time = 3037.72 ms / 489 tokens 3.41.223.154 I slot print_timing: id 0 | task 5993 | graphs reused = 5555 3.41.223.155 I slot print_timing: id 0 | task 5993 | graph reallocs = 0 / 0 (same size) / (changed size) 3.41.223.186 I slot release: id 0 | task 5993 | stop processing: n_tokens = 520, truncated = 0 3.41.227.863 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 389412485106 3.41.227.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.685 MiB) 3.41.237.101 I slot launch_slot_: id 0 | task 6104 | processing task, is_child = 0 3.44.564.330 I slot print_timing: id 0 | task 6104 | prompt eval time = 804.67 ms / 365 tokens ( 2.20 ms per token, 453.60 tokens per second) 3.44.564.336 I slot print_timing: id 0 | task 6104 | eval time = 2522.55 ms / 124 tokens ( 20.51 ms per token, 48.76 tokens per second) 3.44.564.337 I slot print_timing: id 0 | task 6104 | total time = 3327.22 ms / 489 tokens 3.44.564.338 I slot print_timing: id 0 | task 6104 | graphs reused = 5676 3.44.564.338 I slot print_timing: id 0 | task 6104 | graph reallocs = 0 / 0 (same size) / (changed size) 3.44.564.370 I slot release: id 0 | task 6104 | stop processing: n_tokens = 520, truncated = 0 3.44.568.978 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 520, t_last = 389415826289 3.44.569.015 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.752 MiB) 3.44.578.407 I slot launch_slot_: id 0 | task 6231 | processing task, is_child = 0 3.47.524.925 I slot print_timing: id 0 | task 6231 | prompt eval time = 777.69 ms / 333 tokens ( 2.34 ms per token, 428.19 tokens per second) 3.47.524.927 I slot print_timing: id 0 | task 6231 | eval time = 2168.82 ms / 107 tokens ( 20.46 ms per token, 48.87 tokens per second) 3.47.524.928 I slot print_timing: id 0 | task 6231 | total time = 2946.51 ms / 440 tokens 3.47.524.928 I slot print_timing: id 0 | task 6231 | graphs reused = 5781 3.47.524.929 I slot print_timing: id 0 | task 6231 | graph reallocs = 0 / 0 (same size) / (changed size) 3.47.524.957 I slot release: id 0 | task 6231 | stop processing: n_tokens = 471, truncated = 0 3.47.529.968 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 471, t_last = 389418786876 3.47.530.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.048 MiB) 3.47.539.221 I slot launch_slot_: id 0 | task 6341 | processing task, is_child = 0 3.51.215.144 I slot print_timing: id 0 | task 6341 | prompt eval time = 865.69 ms / 403 tokens ( 2.15 ms per token, 465.52 tokens per second) 3.51.215.150 I slot print_timing: id 0 | task 6341 | eval time = 2810.22 ms / 138 tokens ( 20.51 ms per token, 48.75 tokens per second) 3.51.215.150 I slot print_timing: id 0 | task 6341 | total time = 3675.91 ms / 541 tokens 3.51.215.151 I slot print_timing: id 0 | task 6341 | graphs reused = 5916 3.51.215.152 I slot print_timing: id 0 | task 6341 | graph reallocs = 0 / 0 (same size) / (changed size) 3.51.215.186 I slot release: id 0 | task 6341 | stop processing: n_tokens = 572, truncated = 0 3.51.219.952 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 389422477105 3.51.229.241 I slot launch_slot_: id 0 | task 6482 | processing task, is_child = 0 3.55.134.179 I slot print_timing: id 0 | task 6482 | n_gen = 148, tg = 48.72 t/s, tg_3s = 49.05 t/s 3.55.892.341 I slot print_timing: id 0 | task 6482 | prompt eval time = 887.51 ms / 411 tokens ( 2.16 ms per token, 463.09 tokens per second) 3.55.892.347 I slot print_timing: id 0 | task 6482 | eval time = 3775.58 ms / 185 tokens ( 20.52 ms per token, 48.73 tokens per second) 3.55.892.347 I slot print_timing: id 0 | task 6482 | total time = 4663.09 ms / 596 tokens 3.55.892.348 I slot print_timing: id 0 | task 6482 | graphs reused = 6098 3.55.892.348 I slot print_timing: id 0 | task 6482 | graph reallocs = 0 / 0 (same size) / (changed size) 3.55.892.382 I slot release: id 0 | task 6482 | stop processing: n_tokens = 627, truncated = 0 3.55.897.648 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 627, t_last = 389427154301 3.55.897.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.959 MiB) 3.55.907.239 I slot launch_slot_: id 0 | task 6670 | processing task, is_child = 0 3.59.931.046 I slot print_timing: id 0 | task 6670 | n_gen = 148, tg = 48.71 t/s, tg_3s = 49.04 t/s 4.01.508.908 I slot print_timing: id 0 | task 6670 | prompt eval time = 1006.08 ms / 490 tokens ( 2.05 ms per token, 487.04 tokens per second) 4.01.508.912 I slot print_timing: id 0 | task 6670 | eval time = 4595.58 ms / 225 tokens ( 20.52 ms per token, 48.74 tokens per second) 4.01.508.912 I slot print_timing: id 0 | task 6670 | total time = 5601.66 ms / 715 tokens 4.01.508.913 I slot print_timing: id 0 | task 6670 | graphs reused = 6321 4.01.508.914 I slot print_timing: id 0 | task 6670 | graph reallocs = 0 / 0 (same size) / (changed size) 4.01.508.954 I slot release: id 0 | task 6670 | stop processing: n_tokens = 746, truncated = 0 4.01.513.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 746, t_last = 389432770873 4.01.513.751 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 515.744 MiB) 4.01.523.170 I slot launch_slot_: id 0 | task 6898 | processing task, is_child = 0 4.05.341.301 I slot print_timing: id 0 | task 6898 | n_gen = 148, tg = 48.81 t/s, tg_3s = 49.14 t/s 4.05.812.313 I slot print_timing: id 0 | task 6898 | prompt eval time = 806.58 ms / 344 tokens ( 2.34 ms per token, 426.49 tokens per second) 4.05.812.319 I slot print_timing: id 0 | task 6898 | eval time = 3482.55 ms / 171 tokens ( 20.49 ms per token, 48.81 tokens per second) 4.05.812.319 I slot print_timing: id 0 | task 6898 | total time = 4289.13 ms / 515 tokens 4.05.812.320 I slot print_timing: id 0 | task 6898 | graphs reused = 6489 4.05.812.321 I slot print_timing: id 0 | task 6898 | graph reallocs = 0 / 0 (same size) / (changed size) 4.05.812.349 I slot release: id 0 | task 6898 | stop processing: n_tokens = 546, truncated = 0 4.05.816.946 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 546, t_last = 389437074269 4.05.816.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.266 MiB) 4.05.826.618 I slot launch_slot_: id 0 | task 7072 | processing task, is_child = 0 4.09.651.575 I slot print_timing: id 0 | task 7072 | n_gen = 148, tg = 48.84 t/s, tg_3s = 49.17 t/s 4.10.123.513 I slot print_timing: id 0 | task 7072 | prompt eval time = 815.04 ms / 347 tokens ( 2.35 ms per token, 425.75 tokens per second) 4.10.123.519 I slot print_timing: id 0 | task 7072 | eval time = 3481.85 ms / 171 tokens ( 20.48 ms per token, 48.82 tokens per second) 4.10.123.521 I slot print_timing: id 0 | task 7072 | total time = 4296.89 ms / 518 tokens 4.10.123.521 I slot print_timing: id 0 | task 7072 | graphs reused = 6657 4.10.123.522 I slot print_timing: id 0 | task 7072 | graph reallocs = 0 / 0 (same size) / (changed size) 4.10.123.554 I slot release: id 0 | task 7072 | stop processing: n_tokens = 549, truncated = 0 4.10.128.275 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 389441385473 4.10.128.314 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.989 MiB) 4.10.137.723 I slot launch_slot_: id 0 | task 7246 | processing task, is_child = 0 4.13.620.107 I slot print_timing: id 0 | task 7246 | prompt eval time = 875.31 ms / 401 tokens ( 2.18 ms per token, 458.12 tokens per second) 4.13.620.113 I slot print_timing: id 0 | task 7246 | eval time = 2607.07 ms / 128 tokens ( 20.53 ms per token, 48.71 tokens per second) 4.13.620.113 I slot print_timing: id 0 | task 7246 | total time = 3482.37 ms / 529 tokens 4.13.620.114 I slot print_timing: id 0 | task 7246 | graphs reused = 6782 4.13.620.115 I slot print_timing: id 0 | task 7246 | graph reallocs = 0 / 0 (same size) / (changed size) 4.13.620.148 I slot release: id 0 | task 7246 | stop processing: n_tokens = 560, truncated = 0 4.13.624.949 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 560, t_last = 389444882067 4.13.624.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.280 MiB) 4.13.634.173 I slot launch_slot_: id 0 | task 7377 | processing task, is_child = 0 4.16.961.941 I slot print_timing: id 0 | task 7377 | prompt eval time = 965.21 ms / 456 tokens ( 2.12 ms per token, 472.44 tokens per second) 4.16.961.949 I slot print_timing: id 0 | task 7377 | eval time = 2362.55 ms / 115 tokens ( 20.72 ms per token, 48.25 tokens per second) 4.16.961.949 I slot print_timing: id 0 | task 7377 | total time = 3327.76 ms / 571 tokens 4.16.961.950 I slot print_timing: id 0 | task 7377 | graphs reused = 6894 4.16.961.951 I slot print_timing: id 0 | task 7377 | graph reallocs = 0 / 0 (same size) / (changed size) 4.16.961.986 I slot release: id 0 | task 7377 | stop processing: n_tokens = 602, truncated = 0 4.16.966.776 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 4.16.966.818 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.319 MiB) 4.16.976.208 I slot launch_slot_: id 0 | task 7495 | processing task, is_child = 0 4.20.161.025 I slot print_timing: id 0 | task 7495 | prompt eval time = 906.83 ms / 406 tokens ( 2.23 ms per token, 447.71 tokens per second) 4.20.161.031 I slot print_timing: id 0 | task 7495 | eval time = 2277.97 ms / 112 tokens ( 20.52 ms per token, 48.73 tokens per second) 4.20.161.032 I slot print_timing: id 0 | task 7495 | total time = 3184.81 ms / 518 tokens 4.20.161.033 I slot print_timing: id 0 | task 7495 | graphs reused = 7003 4.20.161.033 I slot print_timing: id 0 | task 7495 | graph reallocs = 0 / 0 (same size) / (changed size) 4.20.161.067 I slot release: id 0 | task 7495 | stop processing: n_tokens = 549, truncated = 0 4.20.166.005 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 549, t_last = 389451422986 4.20.166.046 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.967 MiB) 4.20.175.740 I slot launch_slot_: id 0 | task 7610 | processing task, is_child = 0 4.22.309.719 I slot print_timing: id 0 | task 7610 | prompt eval time = 860.32 ms / 406 tokens ( 2.12 ms per token, 471.92 tokens per second) 4.22.309.725 I slot print_timing: id 0 | task 7610 | eval time = 1273.65 ms / 63 tokens ( 20.54 ms per token, 48.68 tokens per second) 4.22.309.725 I slot print_timing: id 0 | task 7610 | total time = 2133.97 ms / 469 tokens 4.22.309.726 I slot print_timing: id 0 | task 7610 | graphs reused = 7064 4.22.309.726 I slot print_timing: id 0 | task 7610 | graph reallocs = 0 / 0 (same size) / (changed size) 4.22.309.756 I slot release: id 0 | task 7610 | stop processing: n_tokens = 500, truncated = 0 4.22.314.407 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 500, t_last = 389453571675 4.22.314.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.618 MiB) 4.22.323.844 I slot launch_slot_: id 0 | task 7676 | processing task, is_child = 0 4.24.655.938 I slot print_timing: id 0 | task 7676 | prompt eval time = 955.80 ms / 444 tokens ( 2.15 ms per token, 464.53 tokens per second) 4.24.655.945 I slot print_timing: id 0 | task 7676 | eval time = 1376.28 ms / 67 tokens ( 20.85 ms per token, 47.96 tokens per second) 4.24.655.945 I slot print_timing: id 0 | task 7676 | total time = 2332.08 ms / 511 tokens 4.24.655.946 I slot print_timing: id 0 | task 7676 | graphs reused = 7128 4.24.655.947 I slot print_timing: id 0 | task 7676 | graph reallocs = 0 / 0 (same size) / (changed size) 4.24.655.978 I slot release: id 0 | task 7676 | stop processing: n_tokens = 542, truncated = 0 4.24.660.367 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 542, t_last = 389455917897 4.24.674.124 I slot launch_slot_: id 0 | task 7746 | processing task, is_child = 0 4.27.604.410 I slot print_timing: id 0 | task 7746 | prompt eval time = 842.93 ms / 372 tokens ( 2.27 ms per token, 441.32 tokens per second) 4.27.604.417 I slot print_timing: id 0 | task 7746 | eval time = 2087.34 ms / 103 tokens ( 20.46 ms per token, 48.87 tokens per second) 4.27.604.418 I slot print_timing: id 0 | task 7746 | total time = 2930.27 ms / 475 tokens 4.27.604.419 I slot print_timing: id 0 | task 7746 | graphs reused = 7229 4.27.604.419 I slot print_timing: id 0 | task 7746 | graph reallocs = 0 / 0 (same size) / (changed size) 4.27.604.450 I slot release: id 0 | task 7746 | stop processing: n_tokens = 506, truncated = 0 4.27.609.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 506, t_last = 389458866369 4.27.609.323 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.764 MiB) 4.27.618.595 I slot launch_slot_: id 0 | task 7852 | processing task, is_child = 0 4.31.601.691 I slot print_timing: id 0 | task 7852 | n_gen = 148, tg = 48.67 t/s, tg_3s = 49.00 t/s 4.33.281.771 I slot print_timing: id 0 | task 7852 | prompt eval time = 962.55 ms / 454 tokens ( 2.12 ms per token, 471.67 tokens per second) 4.33.281.776 I slot print_timing: id 0 | task 7852 | eval time = 4700.62 ms / 230 tokens ( 20.53 ms per token, 48.72 tokens per second) 4.33.281.778 I slot print_timing: id 0 | task 7852 | total time = 5663.17 ms / 684 tokens 4.33.281.778 I slot print_timing: id 0 | task 7852 | graphs reused = 7456 4.33.281.779 I slot print_timing: id 0 | task 7852 | graph reallocs = 0 / 0 (same size) / (changed size) 4.33.281.814 I slot release: id 0 | task 7852 | stop processing: n_tokens = 715, truncated = 0 4.33.286.515 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 715, t_last = 389464543733 4.33.286.561 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 452.325 MiB) 4.33.296.090 I slot launch_slot_: id 0 | task 8085 | processing task, is_child = 0 4.37.112.340 I slot print_timing: id 0 | task 8085 | n_gen = 148, tg = 48.78 t/s, tg_3s = 49.11 t/s 4.38.713.095 I slot print_timing: id 0 | task 8085 | prompt eval time = 802.66 ms / 354 tokens ( 2.27 ms per token, 441.03 tokens per second) 4.38.713.101 I slot print_timing: id 0 | task 8085 | eval time = 4614.34 ms / 226 tokens ( 20.51 ms per token, 48.76 tokens per second) 4.38.713.102 I slot print_timing: id 0 | task 8085 | total time = 5417.00 ms / 580 tokens 4.38.713.103 I slot print_timing: id 0 | task 8085 | graphs reused = 7679 4.38.713.103 I slot print_timing: id 0 | task 8085 | graph reallocs = 0 / 0 (same size) / (changed size) 4.38.713.135 I slot release: id 0 | task 8085 | stop processing: n_tokens = 611, truncated = 0 4.38.717.443 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 611, t_last = 389469975054 4.38.717.484 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.244 MiB) 4.38.726.926 I slot launch_slot_: id 0 | task 8314 | processing task, is_child = 0 4.42.345.629 I slot print_timing: id 0 | task 8314 | prompt eval time = 777.15 ms / 334 tokens ( 2.33 ms per token, 429.78 tokens per second) 4.42.345.635 I slot print_timing: id 0 | task 8314 | eval time = 2841.54 ms / 140 tokens ( 20.44 ms per token, 48.92 tokens per second) 4.42.345.635 I slot print_timing: id 0 | task 8314 | total time = 3618.69 ms / 474 tokens 4.42.345.636 I slot print_timing: id 0 | task 8314 | graphs reused = 7817 4.42.345.637 I slot print_timing: id 0 | task 8314 | graph reallocs = 0 / 0 (same size) / (changed size) 4.42.345.665 I slot release: id 0 | task 8314 | stop processing: n_tokens = 505, truncated = 0 4.42.350.473 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 505, t_last = 389473607584 4.42.350.511 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.146 MiB) 4.42.359.754 I slot launch_slot_: id 0 | task 8457 | processing task, is_child = 0 4.46.288.953 I slot print_timing: id 0 | task 8457 | n_gen = 148, tg = 48.70 t/s, tg_3s = 49.03 t/s 4.46.842.020 I slot print_timing: id 0 | task 8457 | prompt eval time = 910.88 ms / 426 tokens ( 2.14 ms per token, 467.68 tokens per second) 4.46.842.024 I slot print_timing: id 0 | task 8457 | eval time = 3571.37 ms / 175 tokens ( 20.53 ms per token, 48.72 tokens per second) 4.46.842.024 I slot print_timing: id 0 | task 8457 | total time = 4482.25 ms / 601 tokens 4.46.842.025 I slot print_timing: id 0 | task 8457 | graphs reused = 7989 4.46.842.026 I slot print_timing: id 0 | task 8457 | graph reallocs = 0 / 0 (same size) / (changed size) 4.46.842.061 I slot release: id 0 | task 8457 | stop processing: n_tokens = 632, truncated = 0 4.46.847.487 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 632, t_last = 389478103980 4.46.847.535 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.277 MiB) 4.46.857.933 I slot launch_slot_: id 0 | task 8635 | processing task, is_child = 0 4.50.053.231 I slot print_timing: id 0 | task 8635 | prompt eval time = 818.00 ms / 366 tokens ( 2.23 ms per token, 447.43 tokens per second) 4.50.053.235 I slot print_timing: id 0 | task 8635 | eval time = 2377.28 ms / 117 tokens ( 20.49 ms per token, 48.80 tokens per second) 4.50.053.235 I slot print_timing: id 0 | task 8635 | total time = 3195.29 ms / 483 tokens 4.50.053.236 I slot print_timing: id 0 | task 8635 | graphs reused = 8103 4.50.053.236 I slot print_timing: id 0 | task 8635 | graph reallocs = 0 / 0 (same size) / (changed size) 4.50.053.269 I slot release: id 0 | task 8635 | stop processing: n_tokens = 514, truncated = 0 4.50.058.079 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 514, t_last = 389481315188 4.50.058.117 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.937 MiB) 4.50.067.247 I slot launch_slot_: id 0 | task 8755 | processing task, is_child = 0 4.52.778.516 I slot print_timing: id 0 | task 8755 | prompt eval time = 961.38 ms / 462 tokens ( 2.08 ms per token, 480.56 tokens per second) 4.52.778.522 I slot print_timing: id 0 | task 8755 | eval time = 1749.87 ms / 86 tokens ( 20.59 ms per token, 48.58 tokens per second) 4.52.778.523 I slot print_timing: id 0 | task 8755 | total time = 2711.25 ms / 548 tokens 4.52.778.523 I slot print_timing: id 0 | task 8755 | graphs reused = 8186 4.52.778.524 I slot print_timing: id 0 | task 8755 | graph reallocs = 0 / 0 (same size) / (changed size) 4.52.778.558 I slot release: id 0 | task 8755 | stop processing: n_tokens = 579, truncated = 0 4.52.783.197 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 579, t_last = 389484040477 4.52.792.502 I slot launch_slot_: id 0 | task 8844 | processing task, is_child = 0 4.56.501.288 I slot print_timing: id 0 | task 8844 | prompt eval time = 877.25 ms / 396 tokens ( 2.22 ms per token, 451.41 tokens per second) 4.56.501.292 I slot print_timing: id 0 | task 8844 | eval time = 2831.52 ms / 139 tokens ( 20.52 ms per token, 48.74 tokens per second) 4.56.501.293 I slot print_timing: id 0 | task 8844 | total time = 3708.77 ms / 535 tokens 4.56.501.294 I slot print_timing: id 0 | task 8844 | graphs reused = 8322 4.56.501.294 I slot print_timing: id 0 | task 8844 | graph reallocs = 0 / 0 (same size) / (changed size) 4.56.501.323 I slot release: id 0 | task 8844 | stop processing: n_tokens = 566, truncated = 0 4.56.506.150 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 566, t_last = 389487763242 4.56.506.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.735 MiB) 4.56.515.635 I slot launch_slot_: id 0 | task 8986 | processing task, is_child = 0 5.00.509.454 I slot print_timing: id 0 | task 8986 | n_gen = 148, tg = 48.68 t/s, tg_3s = 49.01 t/s 5.00.776.016 I slot print_timing: id 0 | task 8986 | prompt eval time = 974.03 ms / 458 tokens ( 2.13 ms per token, 470.21 tokens per second) 5.00.776.022 I slot print_timing: id 0 | task 8986 | eval time = 3286.35 ms / 161 tokens ( 20.54 ms per token, 48.69 tokens per second) 5.00.776.022 I slot print_timing: id 0 | task 8986 | total time = 4260.37 ms / 619 tokens 5.00.776.023 I slot print_timing: id 0 | task 8986 | graphs reused = 8480 5.00.776.023 I slot print_timing: id 0 | task 8986 | graph reallocs = 0 / 0 (same size) / (changed size) 5.00.776.058 I slot release: id 0 | task 8986 | stop processing: n_tokens = 650, truncated = 0 5.00.780.891 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 650, t_last = 389492037977 5.00.780.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 5.00.790.234 I slot launch_slot_: id 0 | task 9150 | processing task, is_child = 0 5.04.772.062 I slot print_timing: id 0 | task 9150 | n_gen = 148, tg = 48.71 t/s, tg_3s = 49.05 t/s 5.06.576.948 I slot print_timing: id 0 | task 9150 | prompt eval time = 964.24 ms / 458 tokens ( 2.11 ms per token, 474.98 tokens per second) 5.06.576.951 I slot print_timing: id 0 | task 9150 | eval time = 4822.45 ms / 236 tokens ( 20.52 ms per token, 48.73 tokens per second) 5.06.576.953 I slot print_timing: id 0 | task 9150 | total time = 5786.69 ms / 694 tokens 5.06.576.953 I slot print_timing: id 0 | task 9150 | graphs reused = 8713 5.06.576.954 I slot print_timing: id 0 | task 9150 | graph reallocs = 0 / 0 (same size) / (changed size) 5.06.576.993 I slot release: id 0 | task 9150 | stop processing: n_tokens = 725, truncated = 0 5.06.582.120 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 725, t_last = 389497838912 5.06.582.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.048 MiB) 5.06.593.525 I slot launch_slot_: id 0 | task 9389 | processing task, is_child = 0 5.10.561.769 I slot print_timing: id 0 | task 9389 | n_gen = 148, tg = 48.69 t/s, tg_3s = 49.02 t/s 5.11.831.598 I slot print_timing: id 0 | task 9389 | prompt eval time = 949.29 ms / 452 tokens ( 2.10 ms per token, 476.15 tokens per second) 5.11.831.605 I slot print_timing: id 0 | task 9389 | eval time = 4288.78 ms / 210 tokens ( 20.52 ms per token, 48.73 tokens per second) 5.11.831.606 I slot print_timing: id 0 | task 9389 | total time = 5238.07 ms / 662 tokens 5.11.831.607 I slot print_timing: id 0 | task 9389 | graphs reused = 8920 5.11.831.607 I slot print_timing: id 0 | task 9389 | graph reallocs = 0 / 0 (same size) / (changed size) 5.11.831.640 I slot release: id 0 | task 9389 | stop processing: n_tokens = 693, truncated = 0 5.11.836.489 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 693, t_last = 389503093559 5.11.836.539 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.090 MiB) 5.11.851.182 I slot launch_slot_: id 0 | task 9602 | processing task, is_child = 0 5.15.185.061 I slot print_timing: id 0 | task 9602 | prompt eval time = 892.16 ms / 404 tokens ( 2.21 ms per token, 452.83 tokens per second) 5.15.185.067 I slot print_timing: id 0 | task 9602 | eval time = 2441.69 ms / 120 tokens ( 20.52 ms per token, 48.74 tokens per second) 5.15.185.068 I slot print_timing: id 0 | task 9602 | total time = 3333.86 ms / 524 tokens 5.15.185.068 I slot print_timing: id 0 | task 9602 | graphs reused = 9037 5.15.185.069 I slot print_timing: id 0 | task 9602 | graph reallocs = 0 / 0 (same size) / (changed size) 5.15.185.103 I slot release: id 0 | task 9602 | stop processing: n_tokens = 555, truncated = 0 5.15.189.759 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 555, t_last = 389506447022 5.15.189.799 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.064 MiB) 5.15.198.983 I slot launch_slot_: id 0 | task 9725 | processing task, is_child = 0 5.18.138.613 I slot print_timing: id 0 | task 9725 | prompt eval time = 793.06 ms / 345 tokens ( 2.30 ms per token, 435.02 tokens per second) 5.18.138.620 I slot print_timing: id 0 | task 9725 | eval time = 2146.56 ms / 106 tokens ( 20.44 ms per token, 48.92 tokens per second) 5.18.138.621 I slot print_timing: id 0 | task 9725 | total time = 2939.62 ms / 451 tokens 5.18.138.621 I slot print_timing: id 0 | task 9725 | graphs reused = 9141 5.18.138.622 I slot print_timing: id 0 | task 9725 | graph reallocs = 0 / 0 (same size) / (changed size) 5.18.138.654 I slot release: id 0 | task 9725 | stop processing: n_tokens = 482, truncated = 0 5.18.143.263 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 482, t_last = 389509400573 5.18.143.299 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.140 MiB) 5.18.152.509 I slot launch_slot_: id 0 | task 9834 | processing task, is_child = 0 5.21.671.130 I slot print_timing: id 0 | task 9834 | prompt eval time = 952.69 ms / 430 tokens ( 2.22 ms per token, 451.36 tokens per second) 5.21.671.137 I slot print_timing: id 0 | task 9834 | eval time = 2565.93 ms / 126 tokens ( 20.53 ms per token, 48.72 tokens per second) 5.21.671.138 I slot print_timing: id 0 | task 9834 | total time = 3518.61 ms / 556 tokens 5.21.671.138 I slot print_timing: id 0 | task 9834 | graphs reused = 9264 5.21.671.139 I slot print_timing: id 0 | task 9834 | graph reallocs = 0 / 0 (same size) / (changed size) 5.21.671.175 I slot release: id 0 | task 9834 | stop processing: n_tokens = 587, truncated = 0 5.21.675.693 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 389512933094 5.21.675.736 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.467 MiB) 5.21.684.992 I slot launch_slot_: id 0 | task 9963 | processing task, is_child = 0 5.24.175.032 I slot print_timing: id 0 | task 9963 | prompt eval time = 754.83 ms / 316 tokens ( 2.39 ms per token, 418.64 tokens per second) 5.24.175.038 I slot print_timing: id 0 | task 9963 | eval time = 1735.19 ms / 85 tokens ( 20.66 ms per token, 48.41 tokens per second) 5.24.175.039 I slot print_timing: id 0 | task 9963 | total time = 2490.03 ms / 401 tokens 5.24.175.040 I slot print_timing: id 0 | task 9963 | graphs reused = 9347 5.24.175.040 I slot print_timing: id 0 | task 9963 | graph reallocs = 0 / 0 (same size) / (changed size) 5.24.175.067 I slot release: id 0 | task 9963 | stop processing: n_tokens = 432, truncated = 0 5.24.179.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 432, t_last = 389515436986 5.24.179.809 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.556 MiB) 5.24.189.258 I slot launch_slot_: id 0 | task 10051 | processing task, is_child = 0 5.27.166.513 I slot print_timing: id 0 | task 10051 | prompt eval time = 807.14 ms / 354 tokens ( 2.28 ms per token, 438.58 tokens per second) 5.27.166.519 I slot print_timing: id 0 | task 10051 | eval time = 2170.10 ms / 107 tokens ( 20.47 ms per token, 48.85 tokens per second) 5.27.166.520 I slot print_timing: id 0 | task 10051 | total time = 2977.25 ms / 461 tokens 5.27.166.521 I slot print_timing: id 0 | task 10051 | graphs reused = 9452 5.27.166.521 I slot print_timing: id 0 | task 10051 | graph reallocs = 0 / 0 (same size) / (changed size) 5.27.166.550 I slot release: id 0 | task 10051 | stop processing: n_tokens = 492, truncated = 0 5.27.171.460 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 492, t_last = 389518428469 5.27.171.497 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 5.27.181.516 I slot launch_slot_: id 0 | task 10161 | processing task, is_child = 0 5.30.107.416 I slot print_timing: id 0 | task 10161 | prompt eval time = 914.21 ms / 438 tokens ( 2.09 ms per token, 479.10 tokens per second) 5.30.107.422 I slot print_timing: id 0 | task 10161 | eval time = 2011.68 ms / 98 tokens ( 20.74 ms per token, 48.22 tokens per second) 5.30.107.423 I slot print_timing: id 0 | task 10161 | total time = 2925.89 ms / 536 tokens 5.30.107.423 I slot print_timing: id 0 | task 10161 | graphs reused = 9547 5.30.107.424 I slot print_timing: id 0 | task 10161 | graph reallocs = 0 / 0 (same size) / (changed size) 5.30.107.455 I slot release: id 0 | task 10161 | stop processing: n_tokens = 567, truncated = 0 5.30.112.451 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 567, t_last = 389521369374 5.30.112.491 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.830 MiB) 5.30.121.666 I slot launch_slot_: id 0 | task 10262 | processing task, is_child = 0 5.32.481.580 I slot print_timing: id 0 | task 10262 | prompt eval time = 938.20 ms / 457 tokens ( 2.05 ms per token, 487.10 tokens per second) 5.32.481.585 I slot print_timing: id 0 | task 10262 | eval time = 1421.70 ms / 70 tokens ( 20.60 ms per token, 48.53 tokens per second) 5.32.481.586 I slot print_timing: id 0 | task 10262 | total time = 2359.90 ms / 527 tokens 5.32.481.587 I slot print_timing: id 0 | task 10262 | graphs reused = 9614 5.32.481.587 I slot print_timing: id 0 | task 10262 | graph reallocs = 0 / 0 (same size) / (changed size) 5.32.481.621 I slot release: id 0 | task 10262 | stop processing: n_tokens = 558, truncated = 0 5.32.486.791 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 558, t_last = 389523743540 5.32.486.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.651 MiB) 5.32.496.724 I slot launch_slot_: id 0 | task 10335 | processing task, is_child = 0 5.35.479.990 I slot print_timing: id 0 | task 10335 | prompt eval time = 967.39 ms / 473 tokens ( 2.05 ms per token, 488.94 tokens per second) 5.35.479.995 I slot print_timing: id 0 | task 10335 | eval time = 2015.87 ms / 99 tokens ( 20.57 ms per token, 48.61 tokens per second) 5.35.479.996 I slot print_timing: id 0 | task 10335 | total time = 2983.26 ms / 572 tokens 5.35.479.997 I slot print_timing: id 0 | task 10335 | graphs reused = 9710 5.35.479.997 I slot print_timing: id 0 | task 10335 | graph reallocs = 0 / 0 (same size) / (changed size) 5.35.480.035 I slot release: id 0 | task 10335 | stop processing: n_tokens = 603, truncated = 0 5.35.485.138 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 603, t_last = 389526741954 5.35.485.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.615 MiB) 5.35.494.525 I slot launch_slot_: id 0 | task 10437 | processing task, is_child = 0 5.36.998.262 I slot print_timing: id 0 | task 10437 | prompt eval time = 963.21 ms / 476 tokens ( 2.02 ms per token, 494.18 tokens per second) 5.36.998.269 I slot print_timing: id 0 | task 10437 | eval time = 540.51 ms / 27 tokens ( 20.79 ms per token, 48.10 tokens per second) 5.36.998.270 I slot print_timing: id 0 | task 10437 | total time = 1503.72 ms / 503 tokens 5.36.998.270 I slot print_timing: id 0 | task 10437 | graphs reused = 9734 5.36.998.271 I slot print_timing: id 0 | task 10437 | graph reallocs = 0 / 0 (same size) / (changed size) 5.36.998.307 I slot release: id 0 | task 10437 | stop processing: n_tokens = 534, truncated = 0 5.37.003.281 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 534, t_last = 389528260226 5.37.003.321 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.657 MiB) 5.37.012.645 I slot launch_slot_: id 0 | task 10467 | processing task, is_child = 0 5.40.157.900 I slot print_timing: id 0 | task 10467 | prompt eval time = 966.95 ms / 466 tokens ( 2.07 ms per token, 481.93 tokens per second) 5.40.157.907 I slot print_timing: id 0 | task 10467 | eval time = 2178.30 ms / 107 tokens ( 20.55 ms per token, 48.66 tokens per second) 5.40.157.908 I slot print_timing: id 0 | task 10467 | total time = 3145.25 ms / 573 tokens 5.40.157.908 I slot print_timing: id 0 | task 10467 | graphs reused = 9838 5.40.157.909 I slot print_timing: id 0 | task 10467 | graph reallocs = 0 / 0 (same size) / (changed size) 5.40.157.940 I slot release: id 0 | task 10467 | stop processing: n_tokens = 604, truncated = 0 5.40.162.893 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 604, t_last = 389531419859 5.40.162.937 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.478 MiB) 5.40.172.661 I slot launch_slot_: id 0 | task 10577 | processing task, is_child = 0 5.42.628.924 I slot print_timing: id 0 | task 10577 | prompt eval time = 872.69 ms / 415 tokens ( 2.10 ms per token, 475.54 tokens per second) 5.42.628.930 I slot print_timing: id 0 | task 10577 | eval time = 1583.56 ms / 78 tokens ( 20.57 ms per token, 48.62 tokens per second) 5.42.628.931 I slot print_timing: id 0 | task 10577 | total time = 2456.25 ms / 493 tokens 5.42.628.932 I slot print_timing: id 0 | task 10577 | graphs reused = 9913 5.42.628.932 I slot print_timing: id 0 | task 10577 | graph reallocs = 0 / 0 (same size) / (changed size) 5.42.628.963 I slot release: id 0 | task 10577 | stop processing: n_tokens = 524, truncated = 0 5.42.633.845 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 389533890882 5.42.633.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.774 MiB) 5.42.643.869 I slot launch_slot_: id 0 | task 10658 | processing task, is_child = 0 5.44.718.626 I slot print_timing: id 0 | task 10658 | prompt eval time = 786.08 ms / 352 tokens ( 2.23 ms per token, 447.79 tokens per second) 5.44.718.629 I slot print_timing: id 0 | task 10658 | eval time = 1288.67 ms / 64 tokens ( 20.46 ms per token, 48.89 tokens per second) 5.44.718.630 I slot print_timing: id 0 | task 10658 | total time = 2074.75 ms / 416 tokens 5.44.718.631 I slot print_timing: id 0 | task 10658 | graphs reused = 9975 5.44.718.631 I slot print_timing: id 0 | task 10658 | graph reallocs = 0 / 0 (same size) / (changed size) 5.44.718.661 I slot release: id 0 | task 10658 | stop processing: n_tokens = 447, truncated = 0 5.44.723.927 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 447, t_last = 389535980580 5.44.723.965 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.861 MiB) 5.44.733.290 I slot launch_slot_: id 0 | task 10725 | processing task, is_child = 0 5.48.631.988 I slot print_timing: id 0 | task 10725 | prompt eval time = 1189.72 ms / 550 tokens ( 2.16 ms per token, 462.29 tokens per second) 5.48.631.993 I slot print_timing: id 0 | task 10725 | eval time = 2708.96 ms / 133 tokens ( 20.52 ms per token, 48.73 tokens per second) 5.48.631.994 I slot print_timing: id 0 | task 10725 | total time = 3898.68 ms / 683 tokens 5.48.631.994 I slot print_timing: id 0 | task 10725 | graphs reused = 10106 5.48.631.995 I slot print_timing: id 0 | task 10725 | graph reallocs = 0 / 0 (same size) / (changed size) 5.48.632.031 I slot release: id 0 | task 10725 | stop processing: n_tokens = 714, truncated = 0 5.48.637.895 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 714, t_last = 389539893950 5.48.637.941 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.827 MiB) 5.48.637.946 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.754 MiB) 5.48.649.461 I slot launch_slot_: id 0 | task 10862 | processing task, is_child = 0 5.53.195.112 I slot print_timing: id 0 | task 10862 | n_gen = 147, tg = 48.66 t/s, tg_3s = 49.00 t/s 5.54.819.599 I slot print_timing: id 0 | task 10862 | prompt eval time = 1545.41 ms / 772 tokens ( 2.00 ms per token, 499.54 tokens per second) 5.54.819.605 I slot print_timing: id 0 | task 10862 | eval time = 4624.72 ms / 226 tokens ( 20.55 ms per token, 48.65 tokens per second) 5.54.819.606 I slot print_timing: id 0 | task 10862 | total time = 6170.13 ms / 998 tokens 5.54.819.606 I slot print_timing: id 0 | task 10862 | graphs reused = 10329 5.54.819.607 I slot print_timing: id 0 | task 10862 | graph reallocs = 0 / 0 (same size) / (changed size) 5.54.819.648 I slot release: id 0 | task 10862 | stop processing: n_tokens = 1029, truncated = 0 5.54.825.333 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1029, t_last = 389546081567 5.54.825.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.238 MiB) 5.54.841.980 I slot launch_slot_: id 0 | task 11092 | processing task, is_child = 0 5.59.261.904 I slot print_timing: id 0 | task 11092 | n_gen = 147, tg = 48.64 t/s, tg_3s = 48.97 t/s 5.59.979.607 I slot print_timing: id 0 | task 11092 | prompt eval time = 1418.35 ms / 683 tokens ( 2.08 ms per token, 481.55 tokens per second) 5.59.979.613 I slot print_timing: id 0 | task 11092 | eval time = 3719.27 ms / 182 tokens ( 20.55 ms per token, 48.67 tokens per second) 5.59.979.613 I slot print_timing: id 0 | task 11092 | total time = 5137.62 ms / 865 tokens 5.59.979.614 I slot print_timing: id 0 | task 11092 | graphs reused = 10508 5.59.979.614 I slot print_timing: id 0 | task 11092 | graph reallocs = 0 / 0 (same size) / (changed size) 5.59.979.653 I slot release: id 0 | task 11092 | stop processing: n_tokens = 896, truncated = 0 5.59.985.019 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 896, t_last = 389551241572 5.59.985.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.930 MiB) 6.00.000.719 I slot launch_slot_: id 0 | task 11278 | processing task, is_child = 0 6.04.283.033 I slot print_timing: id 0 | task 11278 | n_gen = 148, tg = 48.72 t/s, tg_3s = 49.05 t/s 6.06.274.292 I slot print_timing: id 0 | task 11278 | prompt eval time = 1265.07 ms / 579 tokens ( 2.18 ms per token, 457.68 tokens per second) 6.06.274.298 I slot print_timing: id 0 | task 11278 | eval time = 5008.50 ms / 245 tokens ( 20.53 ms per token, 48.72 tokens per second) 6.06.274.299 I slot print_timing: id 0 | task 11278 | total time = 6273.56 ms / 824 tokens 6.06.274.299 I slot print_timing: id 0 | task 11278 | graphs reused = 10750 6.06.274.300 I slot print_timing: id 0 | task 11278 | graph reallocs = 0 / 0 (same size) / (changed size) 6.06.274.340 I slot release: id 0 | task 11278 | stop processing: n_tokens = 855, truncated = 0 6.06.279.681 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 855, t_last = 389557536259 6.06.279.733 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.201 MiB) 6.06.291.136 I slot launch_slot_: id 0 | task 11527 | processing task, is_child = 0 6.09.453.100 I slot print_timing: id 0 | task 11527 | prompt eval time = 1004.83 ms / 500 tokens ( 2.01 ms per token, 497.60 tokens per second) 6.09.453.106 I slot print_timing: id 0 | task 11527 | eval time = 2157.12 ms / 106 tokens ( 20.54 ms per token, 48.68 tokens per second) 6.09.453.107 I slot print_timing: id 0 | task 11527 | total time = 3161.95 ms / 606 tokens 6.09.453.107 I slot print_timing: id 0 | task 11527 | graphs reused = 10854 6.09.453.108 I slot print_timing: id 0 | task 11527 | graph reallocs = 0 / 0 (same size) / (changed size) 6.09.453.140 I slot release: id 0 | task 11527 | stop processing: n_tokens = 637, truncated = 0 6.09.459.365 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 637, t_last = 389560715059 6.09.459.408 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.947 MiB) 6.09.469.119 I slot launch_slot_: id 0 | task 11636 | processing task, is_child = 0 6.14.050.843 I slot print_timing: id 0 | task 11636 | n_gen = 148, tg = 48.68 t/s, tg_3s = 49.01 t/s 6.15.302.774 I slot print_timing: id 0 | task 11636 | prompt eval time = 1562.14 ms / 776 tokens ( 2.01 ms per token, 496.75 tokens per second) 6.15.302.778 I slot print_timing: id 0 | task 11636 | eval time = 4271.51 ms / 209 tokens ( 20.54 ms per token, 48.69 tokens per second) 6.15.302.779 I slot print_timing: id 0 | task 11636 | total time = 5833.65 ms / 985 tokens 6.15.302.779 I slot print_timing: id 0 | task 11636 | graphs reused = 11061 6.15.302.780 I slot print_timing: id 0 | task 11636 | graph reallocs = 0 / 0 (same size) / (changed size) 6.15.302.823 I slot release: id 0 | task 11636 | stop processing: n_tokens = 1016, truncated = 0 6.15.308.384 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1016, t_last = 389566564742 6.15.308.444 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.590 MiB) 6.15.326.104 I slot launch_slot_: id 0 | task 11849 | processing task, is_child = 0 6.17.485.394 I slot print_timing: id 0 | task 11849 | prompt eval time = 1006.07 ms / 504 tokens ( 2.00 ms per token, 500.96 tokens per second) 6.17.485.401 I slot print_timing: id 0 | task 11849 | eval time = 1153.20 ms / 57 tokens ( 20.59 ms per token, 48.56 tokens per second) 6.17.485.402 I slot print_timing: id 0 | task 11849 | total time = 2159.28 ms / 561 tokens 6.17.485.402 I slot print_timing: id 0 | task 11849 | graphs reused = 11116 6.17.485.403 I slot print_timing: id 0 | task 11849 | graph reallocs = 0 / 0 (same size) / (changed size) 6.17.485.440 I slot release: id 0 | task 11849 | stop processing: n_tokens = 592, truncated = 0 6.17.490.770 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 592, t_last = 389568747359 6.17.490.813 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.056 MiB) 6.17.500.139 I slot launch_slot_: id 0 | task 11909 | processing task, is_child = 0 6.21.851.516 I slot print_timing: id 0 | task 11909 | n_gen = 147, tg = 48.64 t/s, tg_3s = 48.98 t/s 6.23.082.290 I slot print_timing: id 0 | task 11909 | prompt eval time = 1349.88 ms / 633 tokens ( 2.13 ms per token, 468.93 tokens per second) 6.23.082.296 I slot print_timing: id 0 | task 11909 | eval time = 4232.26 ms / 207 tokens ( 20.54 ms per token, 48.67 tokens per second) 6.23.082.297 I slot print_timing: id 0 | task 11909 | total time = 5582.14 ms / 840 tokens 6.23.082.298 I slot print_timing: id 0 | task 11909 | graphs reused = 11320 6.23.082.298 I slot print_timing: id 0 | task 11909 | graph reallocs = 0 / 0 (same size) / (changed size) 6.23.082.336 I slot release: id 0 | task 11909 | stop processing: n_tokens = 871, truncated = 0 6.23.087.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 871, t_last = 389574344255 6.23.087.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.431 MiB) 6.23.098.285 I slot launch_slot_: id 0 | task 12120 | processing task, is_child = 0 6.25.255.180 I slot print_timing: id 0 | task 12120 | prompt eval time = 846.52 ms / 395 tokens ( 2.14 ms per token, 466.62 tokens per second) 6.25.255.183 I slot print_timing: id 0 | task 12120 | eval time = 1310.36 ms / 65 tokens ( 20.47 ms per token, 48.84 tokens per second) 6.25.255.184 I slot print_timing: id 0 | task 12120 | total time = 2156.88 ms / 460 tokens 6.25.255.185 I slot print_timing: id 0 | task 12120 | graphs reused = 11383 6.25.255.185 I slot print_timing: id 0 | task 12120 | graph reallocs = 0 / 0 (same size) / (changed size) 6.25.255.217 I slot release: id 0 | task 12120 | stop processing: n_tokens = 491, truncated = 0 6.25.260.578 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 389576517136 6.25.260.617 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.732 MiB) 6.25.270.134 I slot launch_slot_: id 0 | task 12188 | processing task, is_child = 0 6.29.565.815 I slot print_timing: id 0 | task 12188 | n_gen = 148, tg = 48.73 t/s, tg_3s = 49.06 t/s 6.30.819.044 I slot print_timing: id 0 | task 12188 | prompt eval time = 1279.03 ms / 584 tokens ( 2.19 ms per token, 456.60 tokens per second) 6.30.819.048 I slot print_timing: id 0 | task 12188 | eval time = 4269.87 ms / 209 tokens ( 20.53 ms per token, 48.71 tokens per second) 6.30.819.049 I slot print_timing: id 0 | task 12188 | total time = 5548.90 ms / 793 tokens 6.30.819.050 I slot print_timing: id 0 | task 12188 | graphs reused = 11589 6.30.819.050 I slot print_timing: id 0 | task 12188 | graph reallocs = 0 / 0 (same size) / (changed size) 6.30.819.089 I slot release: id 0 | task 12188 | stop processing: n_tokens = 824, truncated = 0 6.30.824.690 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 824, t_last = 389582081008 6.30.824.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.305 MiB) 6.30.824.747 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.358 MiB) 6.30.835.487 I slot launch_slot_: id 0 | task 12401 | processing task, is_child = 0 6.35.279.474 I slot print_timing: id 0 | task 12401 | n_gen = 147, tg = 48.61 t/s, tg_3s = 48.94 t/s 6.36.981.742 I slot print_timing: id 0 | task 12401 | prompt eval time = 1440.17 ms / 695 tokens ( 2.07 ms per token, 482.58 tokens per second) 6.36.981.748 I slot print_timing: id 0 | task 12401 | eval time = 4706.07 ms / 230 tokens ( 20.55 ms per token, 48.66 tokens per second) 6.36.981.749 I slot print_timing: id 0 | task 12401 | total time = 6146.24 ms / 925 tokens 6.36.981.749 I slot print_timing: id 0 | task 12401 | graphs reused = 11816 6.36.981.750 I slot print_timing: id 0 | task 12401 | graph reallocs = 0 / 0 (same size) / (changed size) 6.36.981.794 I slot release: id 0 | task 12401 | stop processing: n_tokens = 956, truncated = 0 6.36.987.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 956, t_last = 389588243713 6.36.987.790 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.327 MiB) 6.37.006.214 I slot launch_slot_: id 0 | task 12635 | processing task, is_child = 0 6.41.537.700 I slot print_timing: id 0 | task 12635 | n_gen = 147, tg = 48.66 t/s, tg_3s = 48.99 t/s 6.42.440.160 I slot print_timing: id 0 | task 12635 | prompt eval time = 1531.14 ms / 769 tokens ( 1.99 ms per token, 502.24 tokens per second) 6.42.440.163 I slot print_timing: id 0 | task 12635 | eval time = 3902.79 ms / 191 tokens ( 20.54 ms per token, 48.68 tokens per second) 6.42.440.165 I slot print_timing: id 0 | task 12635 | total time = 5433.93 ms / 960 tokens 6.42.440.165 I slot print_timing: id 0 | task 12635 | graphs reused = 12005 6.42.440.166 I slot print_timing: id 0 | task 12635 | graph reallocs = 0 / 0 (same size) / (changed size) 6.42.440.213 I slot release: id 0 | task 12635 | stop processing: n_tokens = 991, truncated = 0 6.42.445.695 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 991, t_last = 389593702132 6.42.445.755 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.500 MiB) 6.42.463.848 I slot launch_slot_: id 0 | task 12830 | processing task, is_child = 0 6.46.235.510 I slot print_timing: id 0 | task 12830 | prompt eval time = 1230.07 ms / 576 tokens ( 2.14 ms per token, 468.27 tokens per second) 6.46.235.517 I slot print_timing: id 0 | task 12830 | eval time = 2541.58 ms / 124 tokens ( 20.66 ms per token, 48.40 tokens per second) 6.46.235.517 I slot print_timing: id 0 | task 12830 | total time = 3771.65 ms / 700 tokens 6.46.235.518 I slot print_timing: id 0 | task 12830 | graphs reused = 12127 6.46.235.518 I slot print_timing: id 0 | task 12830 | graph reallocs = 0 / 0 (same size) / (changed size) 6.46.235.555 I slot release: id 0 | task 12830 | stop processing: n_tokens = 731, truncated = 0 6.46.241.022 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 731, t_last = 389597497474 6.46.241.066 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.967 MiB) 6.46.257.768 I slot launch_slot_: id 0 | task 12958 | processing task, is_child = 0 6.50.628.769 I slot print_timing: id 0 | task 12958 | n_gen = 147, tg = 48.64 t/s, tg_3s = 48.97 t/s 6.53.254.404 I slot print_timing: id 0 | task 12958 | prompt eval time = 1369.17 ms / 655 tokens ( 2.09 ms per token, 478.39 tokens per second) 6.53.254.410 I slot print_timing: id 0 | task 12958 | eval time = 5627.45 ms / 275 tokens ( 20.54 ms per token, 48.69 tokens per second) 6.53.254.410 I slot print_timing: id 0 | task 12958 | total time = 6996.62 ms / 930 tokens 6.53.254.411 I slot print_timing: id 0 | task 12958 | graphs reused = 12399 6.53.254.411 I slot print_timing: id 0 | task 12958 | graph reallocs = 0 / 0 (same size) / (changed size) 6.53.254.452 I slot release: id 0 | task 12958 | stop processing: n_tokens = 961, truncated = 0 6.53.260.054 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 961, t_last = 389604516371 6.53.260.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.791 MiB) 6.53.276.878 I slot launch_slot_: id 0 | task 13237 | processing task, is_child = 0 6.57.098.845 I slot print_timing: id 0 | task 13237 | prompt eval time = 1353.38 ms / 621 tokens ( 2.18 ms per token, 458.85 tokens per second) 6.57.098.848 I slot print_timing: id 0 | task 13237 | eval time = 2468.57 ms / 121 tokens ( 20.57 ms per token, 48.61 tokens per second) 6.57.098.848 I slot print_timing: id 0 | task 13237 | total time = 3821.95 ms / 742 tokens 6.57.098.849 I slot print_timing: id 0 | task 13237 | graphs reused = 12517 6.57.098.850 I slot print_timing: id 0 | task 13237 | graph reallocs = 0 / 0 (same size) / (changed size) 6.57.098.896 I slot release: id 0 | task 13237 | stop processing: n_tokens = 773, truncated = 0 6.57.104.850 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 773, t_last = 389608360815 6.57.104.906 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.671 MiB) 6.57.104.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.321 MiB) 6.57.123.738 I slot launch_slot_: id 0 | task 13362 | processing task, is_child = 0 7.01.684.243 I slot print_timing: id 0 | task 13362 | n_gen = 147, tg = 48.37 t/s, tg_3s = 48.70 t/s 7.02.443.371 I slot print_timing: id 0 | task 13362 | prompt eval time = 1542.12 ms / 767 tokens ( 2.01 ms per token, 497.37 tokens per second) 7.02.443.377 I slot print_timing: id 0 | task 13362 | eval time = 3777.50 ms / 184 tokens ( 20.64 ms per token, 48.44 tokens per second) 7.02.443.377 I slot print_timing: id 0 | task 13362 | total time = 5319.62 ms / 951 tokens 7.02.443.378 I slot print_timing: id 0 | task 13362 | graphs reused = 12699 7.02.443.378 I slot print_timing: id 0 | task 13362 | graph reallocs = 0 / 0 (same size) / (changed size) 7.02.443.430 I slot release: id 0 | task 13362 | stop processing: n_tokens = 982, truncated = 0 7.02.449.467 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 982, t_last = 389613705349 7.02.449.530 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.690 MiB) 7.02.466.219 I slot launch_slot_: id 0 | task 13550 | processing task, is_child = 0 7.07.153.744 I slot print_timing: id 0 | task 13550 | n_gen = 146, tg = 48.26 t/s, tg_3s = 48.60 t/s 7.08.327.672 I slot print_timing: id 0 | task 13550 | prompt eval time = 1683.15 ms / 864 tokens ( 1.95 ms per token, 513.32 tokens per second) 7.08.327.678 I slot print_timing: id 0 | task 13550 | eval time = 4178.29 ms / 203 tokens ( 20.68 ms per token, 48.35 tokens per second) 7.08.327.678 I slot print_timing: id 0 | task 13550 | total time = 5861.44 ms / 1067 tokens 7.08.327.679 I slot print_timing: id 0 | task 13550 | graphs reused = 12899 7.08.327.679 I slot print_timing: id 0 | task 13550 | graph reallocs = 0 / 0 (same size) / (changed size) 7.08.327.727 I slot release: id 0 | task 13550 | stop processing: n_tokens = 1098, truncated = 0 7.08.333.517 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1098, t_last = 389619589646 7.08.333.582 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 387.126 MiB) 7.08.351.940 I slot launch_slot_: id 0 | task 13757 | processing task, is_child = 0 7.12.725.471 I slot print_timing: id 0 | task 13757 | n_gen = 147, tg = 48.65 t/s, tg_3s = 48.98 t/s 7.12.786.930 I slot print_timing: id 0 | task 13757 | prompt eval time = 1372.36 ms / 646 tokens ( 2.12 ms per token, 470.72 tokens per second) 7.12.786.933 I slot print_timing: id 0 | task 13757 | eval time = 3062.62 ms / 150 tokens ( 20.55 ms per token, 48.65 tokens per second) 7.12.786.933 I slot print_timing: id 0 | task 13757 | total time = 4434.98 ms / 796 tokens 7.12.786.934 I slot print_timing: id 0 | task 13757 | graphs reused = 13046 7.12.786.935 I slot print_timing: id 0 | task 13757 | graph reallocs = 0 / 0 (same size) / (changed size) 7.12.786.979 I slot release: id 0 | task 13757 | stop processing: n_tokens = 827, truncated = 0 7.12.793.017 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 827, t_last = 389624048898 7.12.793.076 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.620 MiB) 7.12.811.798 I slot launch_slot_: id 0 | task 13911 | processing task, is_child = 0 7.17.323.287 I slot print_timing: id 0 | task 13911 | n_gen = 147, tg = 48.35 t/s, tg_3s = 48.68 t/s 7.18.879.027 I slot print_timing: id 0 | task 13911 | prompt eval time = 1491.79 ms / 720 tokens ( 2.07 ms per token, 482.64 tokens per second) 7.18.879.034 I slot print_timing: id 0 | task 13911 | eval time = 4575.42 ms / 222 tokens ( 20.70 ms per token, 48.30 tokens per second) 7.18.879.034 I slot print_timing: id 0 | task 13911 | total time = 6067.21 ms / 942 tokens 7.18.879.035 I slot print_timing: id 0 | task 13911 | graphs reused = 13265 7.18.879.036 I slot print_timing: id 0 | task 13911 | graph reallocs = 0 / 0 (same size) / (changed size) 7.18.879.077 I slot release: id 0 | task 13911 | stop processing: n_tokens = 973, truncated = 0 7.18.884.107 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 973, t_last = 389630140996 7.18.884.164 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.654 MiB) 7.18.900.657 I slot launch_slot_: id 0 | task 14137 | processing task, is_child = 0 7.22.944.537 I slot print_timing: id 0 | task 14137 | n_gen = 148, tg = 48.72 t/s, tg_3s = 49.05 t/s 7.24.296.655 I slot print_timing: id 0 | task 14137 | prompt eval time = 1026.49 ms / 509 tokens ( 2.02 ms per token, 495.86 tokens per second) 7.24.296.662 I slot print_timing: id 0 | task 14137 | eval time = 4369.49 ms / 214 tokens ( 20.51 ms per token, 48.75 tokens per second) 7.24.296.662 I slot print_timing: id 0 | task 14137 | total time = 5395.99 ms / 723 tokens 7.24.296.663 I slot print_timing: id 0 | task 14137 | graphs reused = 13477 7.24.296.663 I slot print_timing: id 0 | task 14137 | graph reallocs = 0 / 0 (same size) / (changed size) 7.24.296.698 I slot release: id 0 | task 14137 | stop processing: n_tokens = 754, truncated = 0 7.24.301.960 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 754, t_last = 389635558617 7.24.302.008 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.814 MiB) 7.24.311.339 I slot launch_slot_: id 0 | task 14354 | processing task, is_child = 0 7.28.605.715 I slot print_timing: id 0 | task 14354 | n_gen = 148, tg = 48.73 t/s, tg_3s = 49.06 t/s 7.30.536.997 I slot print_timing: id 0 | task 14354 | prompt eval time = 1277.49 ms / 581 tokens ( 2.20 ms per token, 454.80 tokens per second) 7.30.537.003 I slot print_timing: id 0 | task 14354 | eval time = 4948.16 ms / 242 tokens ( 20.53 ms per token, 48.71 tokens per second) 7.30.537.004 I slot print_timing: id 0 | task 14354 | total time = 6225.65 ms / 823 tokens 7.30.537.004 I slot print_timing: id 0 | task 14354 | graphs reused = 13716 7.30.537.005 I slot print_timing: id 0 | task 14354 | graph reallocs = 0 / 0 (same size) / (changed size) 7.30.537.042 I slot release: id 0 | task 14354 | stop processing: n_tokens = 854, truncated = 0 7.30.543.544 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 854, t_last = 389641798961 7.30.543.597 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 457.213 MiB) 7.30.556.750 I slot launch_slot_: id 0 | task 14600 | processing task, is_child = 0 7.35.338.555 I slot print_timing: id 0 | task 14600 | n_gen = 147, tg = 48.49 t/s, tg_3s = 48.82 t/s 7.37.316.968 I slot print_timing: id 0 | task 14600 | prompt eval time = 1770.87 ms / 925 tokens ( 1.91 ms per token, 522.34 tokens per second) 7.37.316.978 I slot print_timing: id 0 | task 14600 | eval time = 4989.34 ms / 243 tokens ( 20.62 ms per token, 48.50 tokens per second) 7.37.316.978 I slot print_timing: id 0 | task 14600 | total time = 6760.21 ms / 1168 tokens 7.37.316.979 I slot print_timing: id 0 | task 14600 | graphs reused = 13956 7.37.316.979 I slot print_timing: id 0 | task 14600 | graph reallocs = 0 / 0 (same size) / (changed size) 7.37.317.034 I slot release: id 0 | task 14600 | stop processing: n_tokens = 1199, truncated = 0 7.37.323.649 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1199, t_last = 389648578953 7.37.323.718 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.412 MiB) 7.37.342.230 I slot launch_slot_: id 0 | task 14847 | processing task, is_child = 0 7.42.058.366 I slot print_timing: id 0 | task 14847 | n_gen = 146, tg = 48.23 t/s, tg_3s = 48.56 t/s 7.44.098.518 I slot print_timing: id 0 | task 14847 | prompt eval time = 1709.49 ms / 885 tokens ( 1.93 ms per token, 517.70 tokens per second) 7.44.098.521 I slot print_timing: id 0 | task 14847 | eval time = 5046.78 ms / 245 tokens ( 20.68 ms per token, 48.35 tokens per second) 7.44.098.522 I slot print_timing: id 0 | task 14847 | total time = 6756.27 ms / 1130 tokens 7.44.098.523 I slot print_timing: id 0 | task 14847 | graphs reused = 14198 7.44.098.523 I slot print_timing: id 0 | task 14847 | graph reallocs = 0 / 0 (same size) / (changed size) 7.44.098.571 I slot release: id 0 | task 14847 | stop processing: n_tokens = 1161, truncated = 0 7.44.103.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1161, t_last = 389655360490 7.44.103.699 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.336 MiB) 7.44.121.722 I slot launch_slot_: id 0 | task 15096 | processing task, is_child = 0 7.45.803.715 I slot print_timing: id 0 | task 15096 | prompt eval time = 839.31 ms / 392 tokens ( 2.14 ms per token, 467.05 tokens per second) 7.45.803.721 I slot print_timing: id 0 | task 15096 | eval time = 842.68 ms / 42 tokens ( 20.55 ms per token, 48.65 tokens per second) 7.45.803.722 I slot print_timing: id 0 | task 15096 | total time = 1681.98 ms / 434 tokens 7.45.803.722 I slot print_timing: id 0 | task 15096 | graphs reused = 14238 7.45.803.723 I slot print_timing: id 0 | task 15096 | graph reallocs = 0 / 0 (same size) / (changed size) 7.45.803.758 I slot release: id 0 | task 15096 | stop processing: n_tokens = 465, truncated = 0 7.45.808.142 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 465, t_last = 389657065677 7.45.808.178 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.560 MiB) 7.45.817.475 I slot launch_slot_: id 0 | task 15141 | processing task, is_child = 0 7.49.549.553 I slot print_timing: id 0 | task 15141 | n_gen = 148, tg = 48.90 t/s, tg_3s = 49.24 t/s 7.52.563.858 I slot print_timing: id 0 | task 15141 | n_gen = 295, tg = 48.84 t/s, tg_3s = 48.77 t/s 7.53.281.516 I slot print_timing: id 0 | task 15141 | prompt eval time = 726.12 ms / 331 tokens ( 2.19 ms per token, 455.85 tokens per second) 7.53.281.523 I slot print_timing: id 0 | task 15141 | eval time = 6737.91 ms / 330 tokens ( 20.48 ms per token, 48.83 tokens per second) 7.53.281.523 I slot print_timing: id 0 | task 15141 | total time = 7464.03 ms / 661 tokens 7.53.281.524 I slot print_timing: id 0 | task 15141 | graphs reused = 14565 7.53.281.525 I slot print_timing: id 0 | task 15141 | graph reallocs = 0 / 0 (same size) / (changed size) 7.53.281.552 I slot release: id 0 | task 15141 | stop processing: n_tokens = 692, truncated = 0 7.53.286.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 692, t_last = 389664543471 7.53.286.404 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.456 MiB) 7.53.295.912 I slot launch_slot_: id 0 | task 15474 | processing task, is_child = 0 7.55.256.754 I slot print_timing: id 0 | task 15474 | prompt eval time = 794.23 ms / 357 tokens ( 2.22 ms per token, 449.49 tokens per second) 7.55.256.760 I slot print_timing: id 0 | task 15474 | eval time = 1166.60 ms / 57 tokens ( 20.83 ms per token, 48.00 tokens per second) 7.55.256.761 I slot print_timing: id 0 | task 15474 | total time = 1960.83 ms / 414 tokens 7.55.256.762 I slot print_timing: id 0 | task 15474 | graphs reused = 14620 7.55.256.762 I slot print_timing: id 0 | task 15474 | graph reallocs = 0 / 0 (same size) / (changed size) 7.55.256.790 I slot release: id 0 | task 15474 | stop processing: n_tokens = 445, truncated = 0 7.55.261.691 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 445, t_last = 389666518709 7.55.261.730 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.724 MiB) 7.55.272.596 I slot launch_slot_: id 0 | task 15534 | processing task, is_child = 0 7.57.675.447 I slot print_timing: id 0 | task 15534 | prompt eval time = 726.12 ms / 315 tokens ( 2.31 ms per token, 433.81 tokens per second) 7.57.675.452 I slot print_timing: id 0 | task 15534 | eval time = 1676.72 ms / 83 tokens ( 20.45 ms per token, 48.91 tokens per second) 7.57.675.453 I slot print_timing: id 0 | task 15534 | total time = 2402.84 ms / 398 tokens 7.57.675.454 I slot print_timing: id 0 | task 15534 | graphs reused = 14701 7.57.675.454 I slot print_timing: id 0 | task 15534 | graph reallocs = 0 / 0 (same size) / (changed size) 7.57.675.479 I slot release: id 0 | task 15534 | stop processing: n_tokens = 429, truncated = 0 7.57.680.267 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 429, t_last = 389668937398 7.57.680.302 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.481 MiB) 7.57.689.655 I slot launch_slot_: id 0 | task 15620 | processing task, is_child = 0 7.59.727.838 I slot print_timing: id 0 | task 15620 | prompt eval time = 829.63 ms / 378 tokens ( 2.19 ms per token, 455.63 tokens per second) 7.59.727.841 I slot print_timing: id 0 | task 15620 | eval time = 1208.54 ms / 60 tokens ( 20.48 ms per token, 48.82 tokens per second) 7.59.727.841 I slot print_timing: id 0 | task 15620 | total time = 2038.17 ms / 438 tokens 7.59.727.842 I slot print_timing: id 0 | task 15620 | graphs reused = 14759 7.59.727.843 I slot print_timing: id 0 | task 15620 | graph reallocs = 0 / 0 (same size) / (changed size) 7.59.727.878 I slot release: id 0 | task 15620 | stop processing: n_tokens = 469, truncated = 0 7.59.732.349 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 469, t_last = 389670989797 7.59.732.385 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.805 MiB) 7.59.741.864 I slot launch_slot_: id 0 | task 15683 | processing task, is_child = 0 8.01.009.779 I slot print_timing: id 0 | task 15683 | prompt eval time = 712.67 ms / 295 tokens ( 2.42 ms per token, 413.94 tokens per second) 8.01.009.782 I slot print_timing: id 0 | task 15683 | eval time = 555.24 ms / 28 tokens ( 20.56 ms per token, 48.63 tokens per second) 8.01.009.783 I slot print_timing: id 0 | task 15683 | total time = 1267.91 ms / 323 tokens 8.01.009.783 I slot print_timing: id 0 | task 15683 | graphs reused = 14785 8.01.009.784 I slot print_timing: id 0 | task 15683 | graph reallocs = 0 / 0 (same size) / (changed size) 8.01.009.811 I slot release: id 0 | task 15683 | stop processing: n_tokens = 354, truncated = 0 8.01.014.358 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 354, t_last = 389672271730 8.01.014.393 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.387 MiB) 8.01.023.509 I slot launch_slot_: id 0 | task 15714 | processing task, is_child = 0 8.02.686.317 I slot print_timing: id 0 | task 15714 | prompt eval time = 738.62 ms / 337 tokens ( 2.19 ms per token, 456.26 tokens per second) 8.02.686.322 I slot print_timing: id 0 | task 15714 | eval time = 924.18 ms / 46 tokens ( 20.54 ms per token, 48.69 tokens per second) 8.02.686.323 I slot print_timing: id 0 | task 15714 | total time = 1662.79 ms / 383 tokens 8.02.686.324 I slot print_timing: id 0 | task 15714 | graphs reused = 14829 8.02.686.324 I slot print_timing: id 0 | task 15714 | graph reallocs = 0 / 0 (same size) / (changed size) 8.02.686.359 I slot release: id 0 | task 15714 | stop processing: n_tokens = 414, truncated = 0 8.02.690.966 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 389673948278 8.02.700.185 I slot launch_slot_: id 0 | task 15763 | processing task, is_child = 0 8.06.253.362 I slot print_timing: id 0 | task 15763 | prompt eval time = 754.22 ms / 325 tokens ( 2.32 ms per token, 430.91 tokens per second) 8.06.253.369 I slot print_timing: id 0 | task 15763 | eval time = 2798.93 ms / 138 tokens ( 20.43 ms per token, 48.95 tokens per second) 8.06.253.370 I slot print_timing: id 0 | task 15763 | total time = 3553.16 ms / 463 tokens 8.06.253.371 I slot print_timing: id 0 | task 15763 | graphs reused = 14965 8.06.253.371 I slot print_timing: id 0 | task 15763 | graph reallocs = 0 / 0 (same size) / (changed size) 8.06.253.400 I slot release: id 0 | task 15763 | stop processing: n_tokens = 494, truncated = 0 8.06.257.837 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.108 (> 0.100 thold), f_keep = 0.065 8.06.257.875 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 459.071 MiB) 8.06.267.413 I slot launch_slot_: id 0 | task 15904 | processing task, is_child = 0 8.08.090.686 I slot print_timing: id 0 | task 15904 | prompt eval time = 676.71 ms / 264 tokens ( 2.56 ms per token, 390.12 tokens per second) 8.08.090.690 I slot print_timing: id 0 | task 15904 | eval time = 1146.55 ms / 57 tokens ( 20.47 ms per token, 48.84 tokens per second) 8.08.090.691 I slot print_timing: id 0 | task 15904 | total time = 1823.26 ms / 321 tokens 8.08.090.691 I slot print_timing: id 0 | task 15904 | graphs reused = 15020 8.08.090.692 I slot print_timing: id 0 | task 15904 | graph reallocs = 0 / 0 (same size) / (changed size) 8.08.090.716 I slot release: id 0 | task 15904 | stop processing: n_tokens = 352, truncated = 0 8.08.095.420 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 352, t_last = 389679352635 8.08.095.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 453.987 MiB) 8.08.104.598 I slot launch_slot_: id 0 | task 15964 | processing task, is_child = 0 8.09.684.336 I slot print_timing: id 0 | task 15964 | prompt eval time = 779.89 ms / 331 tokens ( 2.36 ms per token, 424.42 tokens per second) 8.09.684.342 I slot print_timing: id 0 | task 15964 | eval time = 799.83 ms / 40 tokens ( 20.51 ms per token, 48.76 tokens per second) 8.09.684.343 I slot print_timing: id 0 | task 15964 | total time = 1579.73 ms / 371 tokens 8.09.684.343 I slot print_timing: id 0 | task 15964 | graphs reused = 15058 8.09.684.344 I slot print_timing: id 0 | task 15964 | graph reallocs = 0 / 0 (same size) / (changed size) 8.09.684.377 I slot release: id 0 | task 15964 | stop processing: n_tokens = 402, truncated = 0 8.09.688.907 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 402, t_last = 389680946296 8.09.688.942 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.484 MiB) 8.09.698.280 I slot launch_slot_: id 0 | task 16007 | processing task, is_child = 0 8.11.325.682 I slot print_timing: id 0 | task 16007 | prompt eval time = 765.60 ms / 333 tokens ( 2.30 ms per token, 434.95 tokens per second) 8.11.325.689 I slot print_timing: id 0 | task 16007 | eval time = 861.79 ms / 42 tokens ( 21.02 ms per token, 47.58 tokens per second) 8.11.325.690 I slot print_timing: id 0 | task 16007 | total time = 1627.39 ms / 375 tokens 8.11.325.691 I slot print_timing: id 0 | task 16007 | graphs reused = 15098 8.11.325.691 I slot print_timing: id 0 | task 16007 | graph reallocs = 0 / 0 (same size) / (changed size) 8.11.325.719 I slot release: id 0 | task 16007 | stop processing: n_tokens = 406, truncated = 0 8.11.330.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 406, t_last = 389682587638 8.11.330.202 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 454.808 MiB) 8.11.339.389 I slot launch_slot_: id 0 | task 16052 | processing task, is_child = 0 8.13.485.048 I slot print_timing: id 0 | task 16052 | prompt eval time = 793.14 ms / 346 tokens ( 2.29 ms per token, 436.24 tokens per second) 8.13.485.054 I slot print_timing: id 0 | task 16052 | eval time = 1352.50 ms / 67 tokens ( 20.49 ms per token, 48.80 tokens per second) 8.13.485.055 I slot print_timing: id 0 | task 16052 | total time = 2145.65 ms / 413 tokens 8.13.485.056 I slot print_timing: id 0 | task 16052 | graphs reused = 15163 8.13.485.056 I slot print_timing: id 0 | task 16052 | graph reallocs = 0 / 0 (same size) / (changed size) 8.13.485.085 I slot release: id 0 | task 16052 | stop processing: n_tokens = 444, truncated = 0 8.13.489.599 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 444, t_last = 389684747004 8.13.489.634 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.895 MiB) 8.13.498.811 I slot launch_slot_: id 0 | task 16122 | processing task, is_child = 0 8.16.417.181 I slot print_timing: id 0 | task 16122 | prompt eval time = 730.36 ms / 325 tokens ( 2.25 ms per token, 444.99 tokens per second) 8.16.417.186 I slot print_timing: id 0 | task 16122 | eval time = 2188.00 ms / 108 tokens ( 20.45 ms per token, 48.90 tokens per second) 8.16.417.187 I slot print_timing: id 0 | task 16122 | total time = 2918.36 ms / 433 tokens 8.16.417.188 I slot print_timing: id 0 | task 16122 | graphs reused = 15269 8.16.417.188 I slot print_timing: id 0 | task 16122 | graph reallocs = 0 / 0 (same size) / (changed size) 8.16.417.216 I slot release: id 0 | task 16122 | stop processing: n_tokens = 464, truncated = 0 8.16.421.847 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 464, t_last = 389687679135 8.16.433.475 I slot launch_slot_: id 0 | task 16233 | processing task, is_child = 0 8.20.183.900 I slot print_timing: id 0 | task 16233 | n_gen = 148, tg = 48.93 t/s, tg_3s = 49.26 t/s 8.21.949.669 I slot print_timing: id 0 | task 16233 | prompt eval time = 745.85 ms / 322 tokens ( 2.32 ms per token, 431.72 tokens per second) 8.21.949.673 I slot print_timing: id 0 | task 16233 | eval time = 4770.34 ms / 234 tokens ( 20.47 ms per token, 48.84 tokens per second) 8.21.949.673 I slot print_timing: id 0 | task 16233 | total time = 5516.18 ms / 556 tokens 8.21.949.674 I slot print_timing: id 0 | task 16233 | graphs reused = 15500 8.21.949.674 I slot print_timing: id 0 | task 16233 | graph reallocs = 0 / 0 (same size) / (changed size) 8.21.949.706 I slot release: id 0 | task 16233 | stop processing: n_tokens = 587, truncated = 0 8.21.954.198 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 587, t_last = 389693211625 8.21.954.242 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 461.163 MiB) 8.21.966.422 I slot launch_slot_: id 0 | task 16470 | processing task, is_child = 0 8.25.741.008 I slot print_timing: id 0 | task 16470 | n_gen = 148, tg = 48.84 t/s, tg_3s = 49.17 t/s 8.28.158.543 I slot print_timing: id 0 | task 16470 | prompt eval time = 764.46 ms / 338 tokens ( 2.26 ms per token, 442.14 tokens per second) 8.28.158.549 I slot print_timing: id 0 | task 16470 | eval time = 5427.65 ms / 266 tokens ( 20.48 ms per token, 48.82 tokens per second) 8.28.158.550 I slot print_timing: id 0 | task 16470 | total time = 6192.11 ms / 604 tokens 8.28.158.551 I slot print_timing: id 0 | task 16470 | graphs reused = 15763 8.28.158.551 I slot print_timing: id 0 | task 16470 | graph reallocs = 0 / 0 (same size) / (changed size) 8.28.158.578 I slot release: id 0 | task 16470 | stop processing: n_tokens = 635, truncated = 0 8.28.163.269 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 635, t_last = 389699420497 8.28.163.312 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 455.864 MiB) 8.28.174.257 I slot launch_slot_: id 0 | task 16739 | processing task, is_child = 0 8.31.976.076 I slot print_timing: id 0 | task 16739 | n_gen = 148, tg = 48.85 t/s, tg_3s = 49.19 t/s 8.34.987.444 I slot print_timing: id 0 | task 16739 | n_gen = 295, tg = 48.84 t/s, tg_3s = 48.82 t/s 8.38.002.973 I slot print_timing: id 0 | task 16739 | n_gen = 442, tg = 48.81 t/s, tg_3s = 48.75 t/s 8.41.017.094 I slot print_timing: id 0 | task 16739 | n_gen = 589, tg = 48.80 t/s, tg_3s = 48.77 t/s 8.44.021.019 I slot print_timing: id 0 | task 16739 | n_gen = 735, tg = 48.76 t/s, tg_3s = 48.60 t/s 8.47.027.476 I slot print_timing: id 0 | task 16739 | n_gen = 881, tg = 48.73 t/s, tg_3s = 48.56 t/s 8.49.979.414 I slot print_timing: id 0 | task 16739 | prompt eval time = 792.91 ms / 347 tokens ( 2.29 ms per token, 437.63 tokens per second) 8.49.979.420 I slot print_timing: id 0 | task 16739 | eval time = 21012.24 ms / 1024 tokens ( 20.54 ms per token, 48.69 tokens per second) 8.49.979.421 I slot print_timing: id 0 | task 16739 | total time = 21805.15 ms / 1371 tokens 8.49.979.421 I slot print_timing: id 0 | task 16739 | graphs reused = 16781 8.49.979.422 I slot print_timing: id 0 | task 16739 | graph reallocs = 0 / 0 (same size) / (changed size) 8.49.979.465 I slot release: id 0 | task 16739 | stop processing: n_tokens = 1402, truncated = 0 8.49.984.915 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1402, t_last = 389721241384 8.49.985.007 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 458.719 MiB) 8.50.004.272 I slot launch_slot_: id 0 | task 17766 | processing task, is_child = 0 8.51.858.955 I slot print_timing: id 0 | task 17766 | prompt eval time = 771.56 ms / 331 tokens ( 2.33 ms per token, 429.00 tokens per second) 8.51.858.958 I slot print_timing: id 0 | task 17766 | eval time = 1083.11 ms / 54 tokens ( 20.44 ms per token, 48.93 tokens per second) 8.51.858.959 I slot print_timing: id 0 | task 17766 | total time = 1854.67 ms / 385 tokens 8.51.858.960 I slot print_timing: id 0 | task 17766 | graphs reused = 16833 8.51.858.961 I slot print_timing: id 0 | task 17766 | graph reallocs = 0 / 0 (same size) / (changed size) 8.51.858.991 I slot release: id 0 | task 17766 | stop processing: n_tokens = 416, truncated = 0 8.51.863.631 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 416, t_last = 389723120910 8.51.863.666 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 391.623 MiB) 8.51.872.779 I slot launch_slot_: id 0 | task 17823 | processing task, is_child = 0 8.53.573.769 I slot print_timing: id 0 | task 17823 | prompt eval time = 780.21 ms / 345 tokens ( 2.26 ms per token, 442.19 tokens per second) 8.53.573.774 I slot print_timing: id 0 | task 17823 | eval time = 920.77 ms / 45 tokens ( 20.93 ms per token, 47.79 tokens per second) 8.53.573.775 I slot print_timing: id 0 | task 17823 | total time = 1700.98 ms / 390 tokens 8.53.573.776 I slot print_timing: id 0 | task 17823 | graphs reused = 16876 8.53.573.776 I slot print_timing: id 0 | task 17823 | graph reallocs = 0 / 0 (same size) / (changed size) 8.53.573.807 I slot release: id 0 | task 17823 | stop processing: n_tokens = 421, truncated = 0 8.53.578.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 421, t_last = 389724835726 8.53.578.447 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 456.392 MiB) 8.53.587.694 I slot launch_slot_: id 0 | task 17871 | processing task, is_child = 0 8.54.736.922 I slot print_timing: id 0 | task 17871 | prompt eval time = 756.04 ms / 320 tokens ( 2.36 ms per token, 423.26 tokens per second) 8.54.736.928 I slot print_timing: id 0 | task 17871 | eval time = 393.18 ms / 20 tokens ( 20.69 ms per token, 48.32 tokens per second) 8.54.736.929 I slot print_timing: id 0 | task 17871 | total time = 1149.22 ms / 340 tokens 8.54.736.929 I slot print_timing: id 0 | task 17871 | graphs reused = 16894 8.54.736.930 I slot print_timing: id 0 | task 17871 | graph reallocs = 0 / 0 (same size) / (changed size) 8.54.736.958 I slot release: id 0 | task 17871 | stop processing: n_tokens = 371, truncated = 0 8.54.741.369 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 371, t_last = 389725998877 8.54.741.400 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 463.138 MiB) 8.54.750.512 I slot launch_slot_: id 0 | task 17894 | processing task, is_child = 0 8.56.401.793 I slot print_timing: id 0 | task 17894 | prompt eval time = 687.98 ms / 297 tokens ( 2.32 ms per token, 431.70 tokens per second) 8.56.401.799 I slot print_timing: id 0 | task 17894 | eval time = 963.29 ms / 47 tokens ( 20.94 ms per token, 47.75 tokens per second) 8.56.401.800 I slot print_timing: id 0 | task 17894 | total time = 1651.27 ms / 344 tokens 8.56.401.801 I slot print_timing: id 0 | task 17894 | graphs reused = 16939 8.56.401.801 I slot print_timing: id 0 | task 17894 | graph reallocs = 0 / 0 (same size) / (changed size) 8.56.401.827 I slot release: id 0 | task 17894 | stop processing: n_tokens = 375, truncated = 0 8.56.406.493 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 375, t_last = 389727663746 8.56.406.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 462.395 MiB) 8.56.416.114 I slot launch_slot_: id 0 | task 17944 | processing task, is_child = 0 8.59.562.901 I slot print_timing: id 0 | task 17944 | prompt eval time = 775.51 ms / 343 tokens ( 2.26 ms per token, 442.29 tokens per second) 8.59.562.904 I slot print_timing: id 0 | task 17944 | eval time = 2371.27 ms / 117 tokens ( 20.44 ms per token, 48.92 tokens per second) 8.59.562.904 I slot print_timing: id 0 | task 17944 | total time = 3146.78 ms / 460 tokens 8.59.562.905 I slot print_timing: id 0 | task 17944 | graphs reused = 17054 8.59.562.906 I slot print_timing: id 0 | task 17944 | graph reallocs = 0 / 0 (same size) / (changed size) 8.59.562.938 I slot release: id 0 | task 17944 | stop processing: n_tokens = 491, truncated = 0 8.59.567.765 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 491, t_last = 389730824857 8.59.577.039 I slot launch_slot_: id 0 | task 18064 | processing task, is_child = 0 9.02.875.765 I slot print_timing: id 0 | task 18064 | prompt eval time = 800.36 ms / 371 tokens ( 2.16 ms per token, 463.54 tokens per second) 9.02.875.768 I slot print_timing: id 0 | task 18064 | eval time = 2498.36 ms / 122 tokens ( 20.65 ms per token, 48.43 tokens per second) 9.02.875.768 I slot print_timing: id 0 | task 18064 | total time = 3298.72 ms / 493 tokens 9.02.875.769 I slot print_timing: id 0 | task 18064 | graphs reused = 17173 9.02.875.769 I slot print_timing: id 0 | task 18064 | graph reallocs = 0 / 0 (same size) / (changed size) 9.02.875.803 I slot release: id 0 | task 18064 | stop processing: n_tokens = 524, truncated = 0 9.02.880.233 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 524, t_last = 389734137722 9.02.880.272 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.972 MiB) 9.02.892.240 I slot launch_slot_: id 0 | task 18189 | processing task, is_child = 0 9.04.244.412 I slot print_timing: id 0 | task 18189 | prompt eval time = 717.30 ms / 292 tokens ( 2.46 ms per token, 407.08 tokens per second) 9.04.244.416 I slot print_timing: id 0 | task 18189 | eval time = 634.86 ms / 32 tokens ( 20.48 ms per token, 48.83 tokens per second) 9.04.244.417 I slot print_timing: id 0 | task 18189 | total time = 1352.16 ms / 324 tokens 9.04.244.418 I slot print_timing: id 0 | task 18189 | graphs reused = 17203 9.04.244.418 I slot print_timing: id 0 | task 18189 | graph reallocs = 0 / 0 (same size) / (changed size) 9.04.244.447 I slot release: id 0 | task 18189 | stop processing: n_tokens = 355, truncated = 0 9.04.248.923 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 355, t_last = 389735506366 9.04.248.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 390.411 MiB) 9.04.258.040 I slot launch_slot_: id 0 | task 18224 | processing task, is_child = 0 9.06.570.004 I slot print_timing: id 0 | task 18224 | prompt eval time = 698.46 ms / 301 tokens ( 2.32 ms per token, 430.95 tokens per second) 9.06.570.010 I slot print_timing: id 0 | task 18224 | eval time = 1613.49 ms / 80 tokens ( 20.42 ms per token, 48.96 tokens per second) 9.06.570.011 I slot print_timing: id 0 | task 18224 | total time = 2311.95 ms / 381 tokens 9.06.570.011 I slot print_timing: id 0 | task 18224 | graphs reused = 17281 9.06.570.012 I slot print_timing: id 0 | task 18224 | graph reallocs = 0 / 0 (same size) / (changed size) 9.06.570.038 I slot release: id 0 | task 18224 | stop processing: n_tokens = 412, truncated = 0 9.06.574.413 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 412, t_last = 389737831957 9.06.574.446 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.581 MiB) 9.06.583.526 I slot launch_slot_: id 0 | task 18307 | processing task, is_child = 0 9.09.039.882 I slot print_timing: id 0 | task 18307 | prompt eval time = 718.29 ms / 303 tokens ( 2.37 ms per token, 421.83 tokens per second) 9.09.039.887 I slot print_timing: id 0 | task 18307 | eval time = 1738.05 ms / 86 tokens ( 20.45 ms per token, 48.91 tokens per second) 9.09.039.888 I slot print_timing: id 0 | task 18307 | total time = 2456.34 ms / 389 tokens 9.09.039.889 I slot print_timing: id 0 | task 18307 | graphs reused = 17365 9.09.039.889 I slot print_timing: id 0 | task 18307 | graph reallocs = 0 / 0 (same size) / (changed size) 9.09.039.925 I slot release: id 0 | task 18307 | stop processing: n_tokens = 420, truncated = 0 9.09.044.312 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 389740301844 9.09.044.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.268 MiB) 9.09.054.002 I slot launch_slot_: id 0 | task 18396 | processing task, is_child = 0 9.10.786.910 I slot print_timing: id 0 | task 18396 | prompt eval time = 748.68 ms / 321 tokens ( 2.33 ms per token, 428.75 tokens per second) 9.10.786.917 I slot print_timing: id 0 | task 18396 | eval time = 984.22 ms / 49 tokens ( 20.50 ms per token, 48.77 tokens per second) 9.10.786.918 I slot print_timing: id 0 | task 18396 | total time = 1732.90 ms / 370 tokens 9.10.786.918 I slot print_timing: id 0 | task 18396 | graphs reused = 17412 9.10.786.919 I slot print_timing: id 0 | task 18396 | graph reallocs = 0 / 0 (same size) / (changed size) 9.10.786.946 I slot release: id 0 | task 18396 | stop processing: n_tokens = 401, truncated = 0 9.10.791.577 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 401, t_last = 389742048865 9.10.791.620 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.050 MiB) 9.10.800.888 I slot launch_slot_: id 0 | task 18448 | processing task, is_child = 0 9.12.905.398 I slot print_timing: id 0 | task 18448 | prompt eval time = 753.43 ms / 322 tokens ( 2.34 ms per token, 427.38 tokens per second) 9.12.905.401 I slot print_timing: id 0 | task 18448 | eval time = 1351.07 ms / 67 tokens ( 20.47 ms per token, 48.85 tokens per second) 9.12.905.402 I slot print_timing: id 0 | task 18448 | total time = 2104.50 ms / 389 tokens 9.12.905.403 I slot print_timing: id 0 | task 18448 | graphs reused = 17477 9.12.905.403 I slot print_timing: id 0 | task 18448 | graph reallocs = 0 / 0 (same size) / (changed size) 9.12.905.434 I slot release: id 0 | task 18448 | stop processing: n_tokens = 420, truncated = 0 9.12.910.158 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 420, t_last = 389744167353 9.12.910.194 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.802 MiB) 9.12.919.306 I slot launch_slot_: id 0 | task 18518 | processing task, is_child = 0 9.14.593.628 I slot print_timing: id 0 | task 18518 | prompt eval time = 754.33 ms / 323 tokens ( 2.34 ms per token, 428.19 tokens per second) 9.14.593.634 I slot print_timing: id 0 | task 18518 | eval time = 919.98 ms / 46 tokens ( 20.44 ms per token, 48.91 tokens per second) 9.14.593.635 I slot print_timing: id 0 | task 18518 | total time = 1674.31 ms / 369 tokens 9.14.593.635 I slot print_timing: id 0 | task 18518 | graphs reused = 17521 9.14.593.636 I slot print_timing: id 0 | task 18518 | graph reallocs = 0 / 0 (same size) / (changed size) 9.14.593.668 I slot release: id 0 | task 18518 | stop processing: n_tokens = 400, truncated = 0 9.14.598.249 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 389745855587 9.14.598.283 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.975 MiB) 9.14.607.744 I slot launch_slot_: id 0 | task 18567 | processing task, is_child = 0 9.18.340.986 I slot print_timing: id 0 | task 18567 | n_gen = 148, tg = 48.97 t/s, tg_3s = 49.30 t/s 9.21.254.033 I slot print_timing: id 0 | task 18567 | prompt eval time = 731.27 ms / 321 tokens ( 2.28 ms per token, 438.96 tokens per second) 9.21.254.038 I slot print_timing: id 0 | task 18567 | eval time = 5915.00 ms / 290 tokens ( 20.47 ms per token, 48.86 tokens per second) 9.21.254.040 I slot print_timing: id 0 | task 18567 | total time = 6646.27 ms / 611 tokens 9.21.254.040 I slot print_timing: id 0 | task 18567 | graphs reused = 17808 9.21.254.041 I slot print_timing: id 0 | task 18567 | graph reallocs = 0 / 0 (same size) / (changed size) 9.21.254.069 I slot release: id 0 | task 18567 | stop processing: n_tokens = 642, truncated = 0 9.21.258.615 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 642, t_last = 389752515988 9.21.258.658 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 386.539 MiB) 9.21.267.933 I slot launch_slot_: id 0 | task 18860 | processing task, is_child = 0 9.24.995.169 I slot print_timing: id 0 | task 18860 | n_gen = 148, tg = 48.90 t/s, tg_3s = 49.24 t/s 9.28.010.389 I slot print_timing: id 0 | task 18860 | n_gen = 295, tg = 48.83 t/s, tg_3s = 48.75 t/s 9.31.029.044 I slot print_timing: id 0 | task 18860 | n_gen = 442, tg = 48.78 t/s, tg_3s = 48.70 t/s 9.34.046.724 I slot print_timing: id 0 | task 18860 | n_gen = 589, tg = 48.77 t/s, tg_3s = 48.71 t/s 9.37.050.622 I slot print_timing: id 0 | task 18860 | n_gen = 735, tg = 48.73 t/s, tg_3s = 48.60 t/s 9.40.059.451 I slot print_timing: id 0 | task 18860 | n_gen = 881, tg = 48.70 t/s, tg_3s = 48.52 t/s 9.43.011.023 I slot print_timing: id 0 | task 18860 | prompt eval time = 721.37 ms / 322 tokens ( 2.24 ms per token, 446.37 tokens per second) 9.43.011.030 I slot print_timing: id 0 | task 18860 | eval time = 21021.71 ms / 1024 tokens ( 20.55 ms per token, 48.66 tokens per second) 9.43.011.031 I slot print_timing: id 0 | task 18860 | total time = 21743.08 ms / 1346 tokens 9.43.011.031 I slot print_timing: id 0 | task 18860 | graphs reused = 18826 9.43.011.032 I slot print_timing: id 0 | task 18860 | graph reallocs = 0 / 0 (same size) / (changed size) 9.43.011.060 I slot release: id 0 | task 18860 | stop processing: n_tokens = 1377, truncated = 0 9.43.015.843 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1377, t_last = 389774272979 9.43.015.915 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 383.763 MiB) 9.43.033.969 I slot launch_slot_: id 0 | task 19887 | processing task, is_child = 0 9.44.727.516 I slot print_timing: id 0 | task 19887 | prompt eval time = 771.34 ms / 337 tokens ( 2.29 ms per token, 436.90 tokens per second) 9.44.727.522 I slot print_timing: id 0 | task 19887 | eval time = 922.19 ms / 46 tokens ( 20.49 ms per token, 48.80 tokens per second) 9.44.727.523 I slot print_timing: id 0 | task 19887 | total time = 1693.53 ms / 383 tokens 9.44.727.524 I slot print_timing: id 0 | task 19887 | graphs reused = 18870 9.44.727.524 I slot print_timing: id 0 | task 19887 | graph reallocs = 0 / 0 (same size) / (changed size) 9.44.727.552 I slot release: id 0 | task 19887 | stop processing: n_tokens = 414, truncated = 0 9.44.732.108 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 414, t_last = 389775989471 9.44.732.140 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.740 MiB) 9.44.741.217 I slot launch_slot_: id 0 | task 19936 | processing task, is_child = 0 9.46.436.316 I slot print_timing: id 0 | task 19936 | prompt eval time = 752.82 ms / 325 tokens ( 2.32 ms per token, 431.71 tokens per second) 9.46.436.320 I slot print_timing: id 0 | task 19936 | eval time = 942.26 ms / 47 tokens ( 20.48 ms per token, 48.82 tokens per second) 9.46.436.321 I slot print_timing: id 0 | task 19936 | total time = 1695.09 ms / 372 tokens 9.46.436.321 I slot print_timing: id 0 | task 19936 | graphs reused = 18915 9.46.436.322 I slot print_timing: id 0 | task 19936 | graph reallocs = 0 / 0 (same size) / (changed size) 9.46.436.351 I slot release: id 0 | task 19936 | stop processing: n_tokens = 403, truncated = 0 9.46.440.957 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 403, t_last = 389777698270 9.46.440.996 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 384.819 MiB) 9.46.450.325 I slot launch_slot_: id 0 | task 19986 | processing task, is_child = 0 9.48.373.254 I slot print_timing: id 0 | task 19986 | prompt eval time = 777.15 ms / 331 tokens ( 2.35 ms per token, 425.92 tokens per second) 9.48.373.258 I slot print_timing: id 0 | task 19986 | eval time = 1145.77 ms / 57 tokens ( 20.46 ms per token, 48.88 tokens per second) 9.48.373.259 I slot print_timing: id 0 | task 19986 | total time = 1922.92 ms / 388 tokens 9.48.373.259 I slot print_timing: id 0 | task 19986 | graphs reused = 18970 9.48.373.260 I slot print_timing: id 0 | task 19986 | graph reallocs = 0 / 0 (same size) / (changed size) 9.48.373.287 I slot release: id 0 | task 19986 | stop processing: n_tokens = 419, truncated = 0 9.48.377.902 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 419, t_last = 389779635206 9.48.377.934 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.562 MiB) 9.48.387.092 I slot launch_slot_: id 0 | task 20046 | processing task, is_child = 0 9.50.279.067 I slot print_timing: id 0 | task 20046 | prompt eval time = 728.25 ms / 336 tokens ( 2.17 ms per token, 461.38 tokens per second) 9.50.279.071 I slot print_timing: id 0 | task 20046 | eval time = 1163.72 ms / 58 tokens ( 20.42 ms per token, 48.98 tokens per second) 9.50.279.073 I slot print_timing: id 0 | task 20046 | total time = 1891.97 ms / 394 tokens 9.50.279.073 I slot print_timing: id 0 | task 20046 | graphs reused = 19026 9.50.279.074 I slot print_timing: id 0 | task 20046 | graph reallocs = 0 / 0 (same size) / (changed size) 9.50.279.105 I slot release: id 0 | task 20046 | stop processing: n_tokens = 425, truncated = 0 9.50.284.033 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 425, t_last = 389781541024 9.50.284.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.953 MiB) 9.50.293.552 I slot launch_slot_: id 0 | task 20107 | processing task, is_child = 0 9.51.499.118 I slot print_timing: id 0 | task 20107 | prompt eval time = 812.51 ms / 349 tokens ( 2.33 ms per token, 429.53 tokens per second) 9.51.499.127 I slot print_timing: id 0 | task 20107 | eval time = 393.04 ms / 20 tokens ( 20.69 ms per token, 48.34 tokens per second) 9.51.499.128 I slot print_timing: id 0 | task 20107 | total time = 1205.55 ms / 369 tokens 9.51.499.128 I slot print_timing: id 0 | task 20107 | graphs reused = 19044 9.51.499.129 I slot print_timing: id 0 | task 20107 | graph reallocs = 0 / 0 (same size) / (changed size) 9.51.499.160 I slot release: id 0 | task 20107 | stop processing: n_tokens = 400, truncated = 0 9.51.503.808 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 400, t_last = 389782761079 9.51.503.840 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 388.358 MiB) 9.51.513.142 I slot launch_slot_: id 0 | task 20130 | processing task, is_child = 0 9.55.258.907 I slot print_timing: id 0 | task 20130 | n_gen = 148, tg = 48.84 t/s, tg_3s = 49.18 t/s 9.58.270.721 I slot print_timing: id 0 | task 20130 | n_gen = 295, tg = 48.83 t/s, tg_3s = 48.81 t/s 10.01.287.661 I slot print_timing: id 0 | task 20130 | n_gen = 442, tg = 48.79 t/s, tg_3s = 48.72 t/s 10.04.303.028 I slot print_timing: id 0 | task 20130 | n_gen = 589, tg = 48.78 t/s, tg_3s = 48.75 t/s 10.07.307.501 I slot print_timing: id 0 | task 20130 | n_gen = 735, tg = 48.74 t/s, tg_3s = 48.59 t/s 10.10.315.198 I slot print_timing: id 0 | task 20130 | n_gen = 881, tg = 48.71 t/s, tg_3s = 48.54 t/s 10.12.193.769 I slot print_timing: id 0 | task 20130 | prompt eval time = 736.12 ms / 336 tokens ( 2.19 ms per token, 456.45 tokens per second) 10.12.193.772 I slot print_timing: id 0 | task 20130 | eval time = 19944.50 ms / 972 tokens ( 20.54 ms per token, 48.69 tokens per second) 10.12.193.773 I slot print_timing: id 0 | task 20130 | total time = 20680.61 ms / 1308 tokens 10.12.193.774 I slot print_timing: id 0 | task 20130 | graphs reused = 20010 10.12.193.774 I slot print_timing: id 0 | task 20130 | graph reallocs = 0 / 0 (same size) / (changed size) 10.12.193.808 I slot release: id 0 | task 20130 | stop processing: n_tokens = 1339, truncated = 0 10.12.198.779 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 1339, t_last = 389803455727 10.12.198.858 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 389.296 MiB) 10.12.216.673 I slot launch_slot_: id 0 | task 21105 | processing task, is_child = 0 10.15.994.285 I slot print_timing: id 0 | task 21105 | n_gen = 148, tg = 48.83 t/s, tg_3s = 49.16 t/s 10.16.895.508 I slot print_timing: id 0 | task 21105 | prompt eval time = 767.20 ms / 349 tokens ( 2.20 ms per token, 454.90 tokens per second) 10.16.895.513 I slot print_timing: id 0 | task 21105 | eval time = 3911.62 ms / 192 tokens ( 20.48 ms per token, 48.83 tokens per second) 10.16.895.513 I slot print_timing: id 0 | task 21105 | total time = 4678.82 ms / 541 tokens 10.16.895.514 I slot print_timing: id 0 | task 21105 | graphs reused = 20199 10.16.895.514 I slot print_timing: id 0 | task 21105 | graph reallocs = 0 / 0 (same size) / (changed size) 10.16.895.543 I slot release: id 0 | task 21105 | stop processing: n_tokens = 572, truncated = 0 10.16.900.168 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 572, t_last = 389808157462 10.16.900.211 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 404.294 MiB) 10.16.909.937 I slot launch_slot_: id 0 | task 21300 | processing task, is_child = 0 10.18.864.532 I slot print_timing: id 0 | task 21300 | prompt eval time = 765.20 ms / 349 tokens ( 2.19 ms per token, 456.09 tokens per second) 10.18.864.538 I slot print_timing: id 0 | task 21300 | eval time = 1189.39 ms / 59 tokens ( 20.51 ms per token, 48.76 tokens per second) 10.18.864.540 I slot print_timing: id 0 | task 21300 | total time = 1954.59 ms / 408 tokens 10.18.864.540 I slot print_timing: id 0 | task 21300 | graphs reused = 20256 10.18.864.541 I slot print_timing: id 0 | task 21300 | graph reallocs = 0 / 0 (same size) / (changed size) 10.18.864.572 I slot release: id 0 | task 21300 | stop processing: n_tokens = 439, truncated = 0 10.18.869.159 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 439, t_last = 389810126491 10.18.869.192 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.014 MiB) 10.18.878.275 I slot launch_slot_: id 0 | task 21362 | processing task, is_child = 0 10.22.726.146 I slot print_timing: id 0 | task 21362 | n_gen = 148, tg = 48.78 t/s, tg_3s = 49.11 t/s 10.25.738.436 I slot print_timing: id 0 | task 21362 | n_gen = 295, tg = 48.79 t/s, tg_3s = 48.80 t/s 10.27.586.146 I slot print_timing: id 0 | task 21362 | prompt eval time = 834.10 ms / 385 tokens ( 2.17 ms per token, 461.57 tokens per second) 10.27.586.152 I slot print_timing: id 0 | task 21362 | eval time = 7873.76 ms / 385 tokens ( 20.50 ms per token, 48.77 tokens per second) 10.27.586.153 I slot print_timing: id 0 | task 21362 | total time = 8707.86 ms / 770 tokens 10.27.586.153 I slot print_timing: id 0 | task 21362 | graphs reused = 20637 10.27.586.154 I slot print_timing: id 0 | task 21362 | graph reallocs = 0 / 0 (same size) / (changed size) 10.27.586.185 I slot release: id 0 | task 21362 | stop processing: n_tokens = 801, truncated = 0 10.27.590.668 I slot get_availabl: id 0 | task -1 | selected slot by LRU, n_tokens = 801, t_last = 389818848104 10.27.590.717 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 385.112 MiB) 10.27.600.220 I slot launch_slot_: id 0 | task 21750 | processing task, is_child = 0 10.29.511.807 I slot print_timing: id 0 | task 21750 | prompt eval time = 766.11 ms / 328 tokens ( 2.34 ms per token, 428.14 tokens per second) 10.29.511.813 I slot print_timing: id 0 | task 21750 | eval time = 1145.47 ms / 57 tokens ( 20.45 ms per token, 48.89 tokens per second) 10.29.511.813 I slot print_timing: id 0 | task 21750 | total time = 1911.58 ms / 385 tokens 10.29.511.814 I slot print_timing: id 0 | task 21750 | graphs reused = 20692 10.29.511.814 I slot print_timing: id 0 | task 21750 | graph reallocs = 0 / 0 (same size) / (changed size) 10.29.511.840 I slot release: id 0 | task 21750 | stop processing: n_tokens = 416, truncated = 0 10.29.596.550 I srv operator(): operator(): cleaning up before exit...